# CleverAgents Documentation (Detailed Spec) ## Overview CleverAgents is your **command center for AI agents** — a unified platform for orchestrating any task you want agents to accomplish, from developing large software projects to writing comprehensive technical papers, administering databases, managing cloud infrastructure, or any complex multi-step workflow. The core value proposition is enabling long-running, complex, large-scale tasks to execute autonomously with minimal human intervention, making it ideal for building entire software systems, producing extensive documentation, or managing sophisticated operations largely hands-off. !!! info "Server Mode" In **server mode**, CleverAgents becomes a collaborative hub where teams can share resources — prompts, actors, actions, and projects — while executing plans in the cloud. This enables a consistent experience across all your devices: start a complex task on your laptop, check progress from your phone, and review results from any machine. !!! note "Runtime Foundation" While CleverAgents leverages LangGraph and LangChain for the underlying LLM runtime primitives (tool calling, graphs, routing), its value lies in what it builds on top of these foundations. !!! success "Core Capabilities" - [x] A **first-class plan lifecycle** (Action templates driving Strategize / Execute / Apply phases) for breaking down and tracking complex work - [x] A **project + resource model** for grounding tasks in real codebases, databases, documents, and infrastructure - [x] A consistent **actor abstraction** for defining and composing intelligent agents - [x] An independently registered **resource abstraction** for representing anything that can be read, written, or queried - [x] An independently registered **tool abstraction** for reusable, callable operations with resource bindings - [x] A **validation abstraction** that extends the tool concept with pass/fail semantics and resource-centric attachment with optional project/plan scoping - [x] A consistent **skill abstraction** for organizing tools into composable capability collections - [x] A **sandbox + checkpoint** safety model for safe, reversible execution - [x] A **CLI/TUI/Web UX** for controlling and monitoring large multi-step autonomous work !!! example "Advanced Subsystems" - A scalable **Advanced Context Management System (ACMS)** with a Universal Knowledge Ontology (UKO), a demand-driven Context Request Protocol (CRP), pluggable context strategies, a fusion coordinator, and hot/warm/cold tiers with per-actor views. - **Invariants** as first-class constraints (global, project, action, and plan scoped) that flow into the decision tree, with precedence-based conflict resolution via the Invariant Reconciliation Actor. - A future-facing ==correction model== where the user can "edit the decision tree" and only recompute affected subtrees. ### Standards Alignment CleverAgents deliberately adopts open, versioned protocols wherever possible so that clients, tools, and skills can interoperate without bespoke integrations. !!! tip "Guiding Principles" 1. **Prefer open protocols** — align with community standards to keep integrations portable and reduce vendor lock-in. 2. **Keep adapters at the edge** — standards map into stable internal domain models so core logic remains protocol-agnostic. The following standards are integrated into the architecture: | Standard | Role | Key Benefit | | :------- | :--- | :---------- | | **A2A** (Agent-to-Agent Protocol) | Versioned client-server contract for messaging, task lifecycle, plan management, registry access, and event streaming | Clients are interchangeable; Agent Card discovery enables ecosystem interoperability; reliable remote execution in server mode | | **MCP** (Model Context Protocol) | Discovering and invoking external tools over a server boundary | Plug-and-play access to a growing ecosystem of tool providers | | **LSP** (Language Server Protocol) | Attaching language intelligence (diagnostics, type info, symbol navigation, completions) to actors and agents | Actors gain semantic code understanding from the mature LSP ecosystem without bespoke language analysis | | **Agent Skills** ([AgentSkills.io](https://AgentSkills.io)) | Packaging instruction-driven, multi-step workflows as `SKILL.md` with progressive disclosure | Teaches agents *how* to accomplish complex tasks, complementing MCP tools | ??? info "Agent-to-Agent Protocol (A2A) -- Details" CleverAgents adopts the external **Agent-to-Agent (A2A) Protocol** standard ([a2a-protocol.org](https://a2a-protocol.org)) as the **sole** communication protocol for all client-server interaction. A2A is the successor to the Agent Client Protocol (ACP), which is now deprecated; A2A retains backward compatibility with ACP's JSON-RPC 2.0 foundation. A2A is built on **JSON-RPC 2.0** (with additional gRPC and REST bindings available) and defines the **fundamental boundary between the Presentation and Application layers** — every client operation flows through A2A regardless of deployment mode. The standard provides operations for messaging (`message/send`, `message/stream`), task lifecycle management, streaming updates via SSE, and **Agent Card**-based capability discovery. CleverAgents extends the standard with `_cleveragents/`-prefixed extension methods (declared via the A2A extension mechanism) for platform operations: plan lifecycle, registry CRUD, entity sync, namespace management, and diagnostics. In local mode, A2A flows over **stdio** via the JSON-RPC binding (agent as subprocess) with platform operations resolved in-process via `A2aLocalFacade`. In server mode, A2A flows over **HTTP** to the CleverAgents server. Both transports use the A2A Python SDK. All clients — CLI, TUI, IDE plugin, and third-party — communicate exclusively through A2A. See [ADR-047](adr/ADR-047-acp-standard-adoption.md), [ADR-048](adr/ADR-048-server-application-architecture.md), and [Server and Client Architecture](#server-and-client-architecture) for the full detail. ??? info "Model Context Protocol (MCP) -- Details" The standard for discovering and invoking external tools over a server boundary. MCP servers are bridged into the Tool Registry via adapters, giving CleverAgents plug-and-play access to a growing ecosystem of tool providers. ??? info "Language Server Protocol (LSP) -- Details" The standard for attaching language intelligence to actors and agents. LSP servers are registered in a global LSP Registry (namespaced like all other entities) and bound to actor graph nodes via YAML configuration. When an actor activates, the LSP Runtime starts the appropriate language servers for the actor's bound languages and workspace resources. LSP capabilities — diagnostics, type information, symbol navigation, completions, references, rename, code actions, and more — are exposed to the actor as callable tools (via the `LSPToolAdapter`) and as automatic context enrichment (diagnostics and type annotations injected into the ACMS hot context). Actors can bind LSP servers explicitly by name, by language, or automatically based on the languages detected in their project's resources. Different nodes in an actor's graph can have different LSP bindings, enabling fine-grained control over which agents receive which language intelligence capabilities. See [LSP Integration](#lsp-integration) for the full architectural detail and [ADR-027](adr/ADR-027-language-server-protocol.md) for the decision record. ??? info "Agent Skills (AgentSkills.io) -- Details" The standard for packaging instruction-driven, multi-step workflows as `SKILL.md` with progressive disclosure. Agent Skills complement MCP tools by teaching agents *how* to accomplish complex tasks rather than simply exposing callable functions. ## Glossary ???+ abstract "Plan Lifecycle" Plan : A ==ULID-identified==, hierarchical unit of work instantiated from an Action template. Progresses through four phases — **Action**, **Strategize**, **Execute**, **Apply** — persisting a decision tree at each step. May spawn child plans. Scoped to one or more projects. Top-level plans carry a namespaced name (`[[server:]namespace/]name`); child plans are identified solely by their plan ID (ULID). All plans are referenced by plan ID when precision is needed, especially in hierarchies containing subplans. Action : A YAML-defined, reusable plan template specifying a description, definition of done, strategy/execution actors, typed arguments, and optional invariants. Project-agnostic until bound to one or more projects via `agents plan use`, which instantiates a Plan. Namespaced as `[[server:]namespace/]name`. Strategize : Second phase of the plan lifecycle (following the Action phase). The first phase where active processing occurs. ==Read-only==: the strategy actor produces the initial decision tree — strategy choices, invariant enforcement records, resource selections, child plan blueprints — without modifying any resources. Execute : Third phase of the plan lifecycle. The execution actor carries out decisions from Strategize — invoking tools, spawning child plans, producing artifacts, creating checkpoints — with all mutations confined to a sandbox. May also create additional decisions constrained by Strategize-phase decisions, based on runtime discoveries. Apply : Fourth and final phase of the plan lifecycle. Merges the sandbox changeset into real project resources. Terminal states: `applied` (success), `constrained` (cannot complete — may revert to Strategize), `errored` (failed), `cancelled` (user/system cancelled). Decision : A persisted choice point in a plan's decision tree, created during Strategize or Execute. Records the question, chosen option, alternatives, confidence score, rationale, context snapshot, and downstream dependencies. Types: `prompt_definition`, `invariant_enforced`, `strategy_choice`, `subplan_spawn`, `subplan_parallel_spawn`, among others. Supports targeted correction with selective subtree recomputation. Invariant : A natural-language constraint on plan execution scoped to global, project, action, or plan level. The runtime precedence chain is four-tier: ==plan > action > project > global==. Exception: global invariants marked `non_overridable` always win regardless of scope. Reconciled by the Invariant Reconciliation Actor at the start of Strategize; recorded as `invariant_enforced` decisions that propagate to child plans. Automation Profile : A named set of confidence thresholds (each `0.0`–`1.0`) gating which plan operations proceed automatically versus requiring human approval. `0.0` = always automatic; `1.0` = always manual. Eight built-in profiles (`manual` through `full-auto`). Custom profiles namespaced as `[[server:]namespace/]name`. Each profile composes a **Safety Profile** that controls hard safety constraints (sandbox, checkpoint, unsafe-tool gating, skill restrictions, cost/retry limits). Safety Profile : A composed sub-model of an Automation Profile that groups all hard safety constraints: `require_sandbox`, `require_checkpoints`, `allow_unsafe_tools`, `require_human_approval`, `allowed_skill_categories`, `max_cost_per_plan`, `max_retries_per_step`, and `max_total_cost`. Safety profiles can also be referenced standalone on Actions when only safety constraints (without full autonomy thresholds) are needed. See [ADR-041](adr/ADR-041-safety-profile-extraction.md). ???+ abstract "Projects & Resources" Project : A named scope linking resources (from the Resource Registry), context policies, invariants, and validation attachments. Does not own resources; a single resource may be linked to multiple projects. Identified solely by its namespaced name (`[[server:]namespace/]name`) — no ULID is generated. May be local or remote. Resource : A ULID-identified entity registered in the Resource Registry representing anything readable, writable, or queryable (git repos, filesystems, databases, etc.). Classified as physical or virtual, typed by a Resource Type, and organized in a DAG via parent/child links. Resource Type : A schema-level definition constraining a category of resources. Specifies accepted CLI arguments, physical/virtual classification, permitted parent/child type relationships, auto-discovery rules, sandbox strategy, and handler implementation. Built-in types (e.g., `git-checkout`, `fs-mount`) are unnamespaced; custom types are namespaced as `[[server:]namespace/]name`. Resource types support single inheritance via the `inherits` field — see [ADR-042](adr/ADR-042-resource-type-inheritance.md). Resource Type Inheritance : A mechanism allowing one resource type to inherit properties, capabilities, child types, sandbox strategy, and handler behavior from another type via the `inherits` field in the type definition. Subtypes can selectively override or extend any inherited field. Tools bound to a parent type automatically work with all subtypes (polymorphic matching). Auto-discovery child type matching and DAG queries are also polymorphic. Single inheritance only; maximum chain depth of 5 levels. See [ADR-042](adr/ADR-042-resource-type-inheritance.md). Devcontainer : A container execution environment defined by a `.devcontainer/devcontainer.json` configuration file per the [Development Containers Specification](https://containers.dev). Auto-discovered when a `git-checkout` or `fs-directory` resource contains a `.devcontainer/` directory. Represented as a `devcontainer-instance` resource type that inherits from `container-instance`. Uses lazy activation — the container is only built when first needed by a plan. See [ADR-043](adr/ADR-043-devcontainer-integration.md). Execution Environment : The runtime context in which tools execute — either the host system or a specific container. Configurable at project scope (`execution_environment` preference), plan scope (`--execution-environment` flag), and resource scope (auto-detected devcontainers). Precedence resolution determines which environment is used when multiple are configured, with `priority: override` forcing a specific container and `priority: fallback` deferring to auto-detected devcontainers. See [ADR-043](adr/ADR-043-devcontainer-integration.md). Physical Resource : A resource bound to a concrete, located artifact — a specific file at a specific path, a specific repo at a specific URL. Directly readable and writable by tools. Two physical resources with identical content remain distinct instances. Virtual Resource : A resource representing an abstract equivalence identity that links physical resources sharing the same content, hash, or name. ==Has no location; cannot be directly read or written.== Equivalence relationships update when underlying physical resources diverge. Resource Binding : The association between a tool and the resources it operates on, declared via typed resource slots. Slots resolve through **contextual binding** (from the plan's project), **static binding** (hardcoded at registration), or **parameter binding** (passed at invocation). Resource Registry : The persistent catalog of all registered resources and their DAG relationships (parent/child links). One of the core registries, alongside the Tool Registry, Skill Registry, Actor Registry, Provider Registry, and LSP Registry. ???+ abstract "Tools & Skills" Tool : The ==atomic unit of execution==: a namespaced, independently registered callable operation. Defined by JSON Schema inputs/outputs, capability metadata (`read_only`, `writes`, `checkpointable`), and a four-stage lifecycle (`discover` / `activate` / `execute` / `deactivate`). Sources: MCP servers, Agent Skills folders, built-ins, or custom Python. Namespaced as `[[server:]namespace/]name`. Validation : A Tool subtype adding: a `mode` (`required` | `informational`) controlling whether failure blocks execution; a structured JSON return with mandatory `passed` boolean, optional `data`, and optional `message`. ==Always read-only== (`writes = false`, `checkpointable = false`). May wrap an existing Tool via `wraps` + `transform`. Managed via `agents validation add/attach/detach`; always attached to a resource, optionally scoped to a project or plan. Anonymous Tool : An inline tool definition embedded in a skill YAML or actor graph node. Same schema as a named tool but unregistered, unnamespaced, and scoped only to its defining context. Skill : A composable, namespaced collection of tools assembled by referencing named tools, defining inline anonymous tools, including other skills, or exposing MCP server tools and Agent Skills ([AgentSkills.io](https://AgentSkills.io)) tools. Actors reference skills by name to acquire capabilities. Namespaced as `[[server:]namespace/]name`. MCP (Model Context Protocol) : A standard for exposing tools and resources over a server boundary via JSON-RPC. CleverAgents discovers MCP tools through the `MCPToolAdapter` and registers them in the Tool Registry with extended capability metadata. MCP tools can be composed into skills and used as tool nodes in actor graphs. Agent Skills ([AgentSkills.io](https://AgentSkills.io)) : A standard for packaging instruction-driven, multi-step workflows as `SKILL.md` files with optional `scripts/`, `references/`, and `assets/` directories, using progressive disclosure. Surfaced as tools inside skills and loaded on demand by the actor runtime. ???+ abstract "Actors & Sessions" Actor : A YAML-configured conversational unit — either a single LLM/agent or a composed LangGraph of actors and tool nodes. Specialized roles: strategy actor, execution actor, estimation actor, invariant reconciliation actor. Namespaced as `[[server:]namespace/]name`. Session : A persistent conversation thread tied to an orchestrator actor. Maintains message history across plans and serves as the user's natural-language interface. Server : An optional shared backend providing multi-user storage, namespace resolution, and remote plan execution. ???+ abstract "Protocols & Standards" A2A (Agent-to-Agent Protocol) : The external **Agent-to-Agent (A2A) Protocol** standard ([a2a-protocol.org](https://a2a-protocol.org)), built on **JSON-RPC 2.0** (with gRPC and REST bindings available), used as the **sole** communication protocol for all client-server interaction. A2A is the successor to the Agent Client Protocol (ACP), which is now deprecated; A2A retains backward compatibility with ACP's JSON-RPC 2.0 foundation. A2A defines the **fundamental boundary between the Presentation and Application layers**. Standard A2A operations handle agent messaging (`message/send`, `message/stream`), task lifecycle, streaming updates, and Agent Card-based discovery. CleverAgents `_cleveragents/`-prefixed extension methods handle platform operations (plan lifecycle, registry CRUD, entity sync, namespace management, diagnostics). In local mode A2A flows over stdio via JSON-RPC (agent as subprocess); in server mode over HTTP. Every CLI command maps to an A2A operation. See [Core Concepts > Server > A2A](#agent-to-agent-protocol-a2a) and [Server and Client Architecture](#server-and-client-architecture) for full detail. LSP (Language Server Protocol) : A standard protocol for language intelligence, used in CleverAgents to attach semantic code understanding to actors and agents. LSP servers are registered in the global **LSP Registry** (namespaced as `[[server:]namespace/]name`) and bound to actor graph nodes via YAML configuration. Capabilities — diagnostics, type information, symbol navigation, completions, references, rename, code actions — are exposed as tools (via `LSPToolAdapter`) and as automatic context enrichment. Actors can bind LSP servers explicitly by name, by language, or automatically based on detected resource languages. The LSP Runtime in the Infrastructure layer manages server lifecycle, workspace mapping, and file synchronization. See [LSP Integration](#lsp-integration) for full detail. ???+ abstract "Naming & Identity" Namespace : The scoping segment in the name format `[[server:]namespace/]name`. Defaults to `local/` when omitted. `local/` is reserved for local-only items. Non-`local/` namespaces with server omitted assume the default configured server. Built-in LLM actors use provider prefixes (e.g., `openai/`, `anthropic/`). Built-in resource types are unnamespaced. ULID : ==Universally Unique Lexicographically Sortable Identifier.== Assigned to plans, decisions, resources, correction attempts, and validation attachments. Projects, actions, skills, and tools use their namespaced name as sole identifier instead. ???+ abstract "Context Management (ACMS)" ACMS (Advanced Context Management System) : The pluggable, strategy-driven framework for assembling actor context. Comprises the UKO, CRP, pluggable context strategies, the Context Assembly Pipeline, and hot/warm/cold tiered storage with per-actor scoped views. UKO (Universal Knowledge Ontology) : An RDF-based, inheritance-driven ontology representing resources at multiple abstraction levels with provenance and temporal versioning. Four layers: universal foundation, domain specializations (software, documents, data schemas, infrastructure), paradigm/format specializations (procedural programming, markdown), and technology-specific (Python, PostgreSQL). ==Semantically aware — implicit relationships are inferred from content analysis.== CRP (Context Request Protocol) : A structured vocabulary through which actors declare needed information, desired detail depth, and scope. Context Strategy : A pluggable retrieval component that searches for and assembles ContextFragments using a specific approach (keyword search, semantic embedding, graph navigation, temporal archaeology, etc.). Registered with the Context Assembly Pipeline; executed in parallel by the StrategyExecutor. Context Assembly Pipeline : The central ACMS orchestrator. Ten pluggable Protocol-defined components in three phases: **Strategy Orchestration**, **Fragment Fusion**, and **Context Finalization**. Each component ships with a default implementation and is overridable at global, project, or plan scope. Skeleton (context) : A compressed representation of a plan's accumulated context produced by the SkeletonCompressor. Propagated from parent plans to child plans as inherited context. Size governed by the `skeleton_ratio` budget parameter. ## CLI Commands !!! adr "Architecture Decision" The CLI command structure, output rendering, and interaction patterns are defined in [ADR-021: CLI and Output Rendering](adr/ADR-021-cli-and-output-rendering.md). ### Command Synopsis 

agents|cleveragents  [--data-dir <DATA_PATH>] [--config-path <CONFIG_PATH>]
                     [--format (rich|color|table|plain|json|yaml)]
                     [--help|-h] [--version]
                     [--install-completion [<INST_SHELL>]] [--show-completion [<SHOW_SHELL>]]
                     [-v...] <COMMAND> [<ARGS>...]

agents version
agents info
agents diagnostics
agents init [--yes|-y]

agents session create [--actor <ACTOR>]
agents session list
agents session show <SESSION_ID>
agents session delete [--yes|-y] <SESSION_ID>
agents session export [(--output|-o) <FILE>] <SESSION_ID>
agents session import (--input|-i) <FILE>
agents session tell --session <SESSION_ID> [--actor <ACTOR>] [--stream] <PROMPT>

agents project create [(--description|-d) <DESC>] [--resource <RESOURCE>]...
                     [--invariant <INVARIANT>]... [--invariant-actor <ACTOR>] <NAME>
agents project link-resource [--read-only] <PROJECT> <RESOURCE>
agents project unlink-resource [--yes|-y] <PROJECT> <RESOURCE_NAME>
agents project list [(--namespace|-n) NS] [<REGEX>]
agents project show <PROJECT>
agents project delete [--force|-f] [--yes|-y] <NAME>
agents project context set[--view (strategize|execute|apply|default)]
                          [--include-resource <INCLUDE_RESOURCE>]...
                          [--exclude-resource <EXCLUDE_RESOURCE>]...
                          [--include-path <INCLUDE_GLOB>]...
                          [--exclude-path <EXCLUDE_GLOB>]...
                          [--hot-max-tokens <N>]
                          [--warm-max-decisions <N_WARM_MAX>]
                          [--cold-max-decisions <N_COLD_MAX>]
                          [--query-limit <N>]
                          [--max-file-size <MAX_FILE_BYTES>]
                          [--max-total-size <MAX_TOTAL_BYTES>]
                          [--summarize|--no-summarize]
                          [--summary-max-tokens <N>]
                          [--strategy <STRATEGY>]...
                          [--default-breadth <N>]
                          [--default-depth <INT_OR_NAME>]
                          [--depth-gradient <HOP:INT_OR_NAME>]...
                          [--skeleton-ratio <FLOAT>]
                          [--temporal-scope (current|recent|all)]
                          [--auto-refresh|--no-auto-refresh]
                          [--execution-environment <RESOURCE_NAME>]
                          [--execution-env-priority (fallback|override)]
                          [--clear] <PROJECT>
agents project context show [--view (strategize|execute|apply|default)]
                            <PROJECT>
agents project context inspect [--view (strategize|execute|apply|default)]
                               [--strategy <STRATEGY>]
                               [--focus <UKO_URI>]...
                               [--breadth <N>] [--depth <INT_OR_NAME>]
                               <PROJECT>
agents project context simulate [--view (strategize|execute|apply|default)]
                                [--budget <TOKENS>]
                                [--focus <UKO_URI>]...
                                [--strategy <STRATEGY>]...
                                <PROJECT>

agents validation add --config|-c <FILE> [--update]
agents validation attach [--project <PROJECT>|--plan <PLAN_ID>]
                         <RESOURCE> <VALIDATION> [--<KEY> <VALUE>]...
agents validation detach [--yes|-y] <ATTACHMENT_ID>

agents actor run [(--output|-o) <OUTPUT_FILE>]
                 [-v...] [--unsafe|-u] [--context <CONTEXT_NAME>]
                 [--context-dir <CONTEXT_PATH>] [--load-context <LOAD_CONTEXT_NAME>]
                 [(--temperature|-t) <TEMP>] [--allow-rxpy-in-run-mode]
                 [--skill <SKILL>]... <NAME> <PROMPT>
agents actor add --config|-c <FILE> [--update]
agents actor remove [--format <FORMAT>] <NAME>
agents actor list
agents actor show <NAME>
agents actor context remove [--yes|-y] (--all|-a|<NAME>)
agents actor context list [<REGEX>]
agents actor context show <NAME>
agents actor context export (--output|-o) <FILE> <NAME>
agents actor context import [--update] (--input|-i) <FILE> [<NAME>]
agents actor context clear [--yes|-y] (--all|-a|<NAME>)

agents skill add --config|-c <FILE> [--update]
agents skill remove [--yes|-y] <NAME>
agents skill list [(--namespace|-n) <NS>] [--source <SOURCE>]
agents skill show  <NAME>
agents skill tools <NAME>

agents tool add --config|-c <FILE> [--update]
agents tool remove [--yes|-y] <NAME>
agents tool list [(--namespace|-n) <NS>] [--source <SOURCE>] [--type (tool|validation)] [<REGEX>]
agents tool show <NAME>

agents lsp add --config|-c <FILE> [--update]
agents lsp remove [--yes|-y] <NAME>
agents lsp list [(--namespace|-n) <NS>] [--language <LANG>]
agents lsp show <NAME>
agents lsp serve [--log-level <LEVEL>]

agents resource type add --config|-c <FILE> [--update]
agents resource type remove [--yes|-y] <NAME>
agents resource type list [<REGEX>]
agents resource type show <NAME>

agents resource add [(--description|-d) <DESC>] [--update] <TYPE> <NAME> [type-specific-flags...]
agents resource remove [--yes|-y] <NAME>
agents resource list [--all] [(--type|-t) <TYPE>]
agents resource show <RESOURCE>
agents resource inspect [--tree] [--file <PATH>] <RESOURCE>
agents resource tree [(--depth|-d) <N>] [(--type|-t) <TYPE>] <RESOURCE>
agents resource link-child <PARENT> <CHILD>
agents resource unlink-child [--yes|-y] <PARENT> <CHILD>
agents resource stop <NAME>
agents resource rebuild <NAME>

agents plan list [--phase <PHASE>] [--state <STATE>] [--project <PROJECT>]
                 [--action <ACTION>] [<REGEX>]
agents plan use [--automation-profile <PROFILE>]
                [--invariant <INVARIANT>]...
                [--strategy-actor <STRATEGY_ACTOR>]
                [--execution-actor <EXEC_ACTOR>]
                [--estimation-actor <EST_ACTOR>]
                [--invariant-actor <INV_ACTOR>]
                [--execution-environment <RESOURCE_NAME>]
                [--execution-env-priority (fallback|override)]
                [--arg/-a name=value]...
                <ACTION> <PROJECT>...
agents plan execute <PLAN_ID>
agents plan apply [--yes|-y] <PLAN_ID>
agents plan status <PLAN_ID>
agents plan cancel [(--reason|-r) <REASON>] <PLAN_ID>
agents plan tree [--show-superseded] <PLAN_ID>
agents plan explain [--show-context] [--show-reasoning] <DECISION_ID>
agents plan correct --mode (revert|append) (--guidance|-g) <GUIDANCE>
                   [--dry-run] [--yes|-y] <DECISION_ID>
agents plan diff (--correction <CORRECTION_ATTEMPT_ID>|<PLAN_ID>)
agents plan artifacts <PLAN_ID>
agents plan prompt <PLAN_ID> <GUIDANCE>
agents plan rollback [--yes|-y] <PLAN_ID> <CHECKPOINT_ID>
agents plan errors <PLAN_ID>

agents action create --config|-c <CFG_FILE>
agents action list [(--namespace|-n) <NS>] [(--state|-s) <STATE>] [<REGEX>]
agents action show <ACTION_NAME>
agents action archive <ACTION_NAME>

agents automation-profile add --config|-c <FILE> [--update]
agents automation-profile remove [--yes|-y] <NAME>
agents automation-profile list [<REGEX>]
agents automation-profile show <NAME>

agents config set <key> <value>
agents config get <key>
agents config list [--filter-values <REGEX>] [<REGEX>]

agents invariant add [--global] [(--project|-p) PROJECT] [--plan PLAN_ID]...
                     [--action ACTION]... <INVARIANT_TEXT>
agents invariant list [--global] [(--project|-p) PROJECT] [--plan PLAN_ID] [--action ACTION]
                     [--effective] [<REGEX>]
agents invariant remove [--yes|-y] <INVARIANT_ID>
### Command Reference !!! info "Output Format Tabs" Each command example below is shown in multiple output formats using content tabs. Select a tab to see how the same command renders in that format. The `table` format is visually identical to `rich` in static documentation (the difference is live animation). The `color` format has the same layout as `plain` but with ANSI color codes applied to headers, keys, and values. See **Output Rendering Framework** for full format specifications. #### Global Options !!! note "Purpose" Configure global state locations and shell integration for every command. **Arguments** - `--data-dir PATH`: Overrides the global data directory (database, caches, sessions, logs). When omitted, the default data location is used. - `--config-path PATH`: Overrides the global configuration file path. When omitted, the default config path is used. - `--format rich|color|table|plain|json|yaml`: Set the output rendering format for all subcommands. When omitted, the value is read from the global config key `core.format`. If not set in config either, defaults to `rich`. See **Output Rendering Framework** for full details on each format. ??? tip "Available Output Formats" | Format | Description | Best For | | :----- | :---------- | :------- | | `rich` | Modern rich CLI elements with dynamic effects, animated spinners, progress bars, and generous color | Interactive terminal use **(default)** | | `color` | Plain scrolling text with ANSI color codes | Terminals that support color but not advanced rendering | | `table` | ASCII box-drawing characters to create structured tables and panels with color | Structured visual output similar to examples in this document | | `plain` | Plain text with no color codes or non-ASCII characters | Piping into files, logs, or non-terminal consumers | | `json` | Structured JSON output for programmatic consumption | Scripts, CI/CD pipelines, programmatic consumption | | `yaml` | Structured YAML output for programmatic consumption | Configuration, programmatic consumption | - `--help`, `-h`: Print help for the current command. - `--version`: Print the version and exit. - `--install-completion [SHELL]`: Install shell completion for the given shell. - `--show-completion [SHELL]`: Show the completion script for the given shell. - `-v`: Increase log verbosity for a single invocation (repeatable). By default (no `-v`), only normal command output is shown on stdout; logging output is suppressed except on fatal errors where the application exits entirely and displays the error. Each additional `-v` raises the verbosity one level: `-v` = ERROR (non-fatal, recoverable errors), `-vv` = WARN (warnings that may indicate a degraded system but are not necessarily errors), `-vvv` = INFO (routine informative messages useful to common users), `-vvvv` = DEBUG (coarse debugging output), `-vvvvv` = TRACE (the most granular logging level available). Increased verbosity writes to both the log file and stderr by default, keeping log output separate from normal program output on stdout. The destination for log output raised by `-v` is configurable: it can be sent to the terminal (stderr by default, or redirected to another stream such as stdin or a device), to the log file only, or to both. See `core.log.terminal`, `core.log.terminal-stream`, and `core.log.file-enabled` configuration keys for details. This flag does not persist — it only affects the current invocation. **Examples** === "Rich" 

    $ agents --data-dir /srv/cleveragents --config-path /srv/cleveragents/config.toml info

    ╭─ System Snapshot ─────────────────╮
    │ CleverAgents 1.0.0                │
    │ Mode: local                       │
    │ Automation: review                │
    │ Status: ready                     │
    ╰───────────────────────────────────╯

    ╭─ Paths ───────────────────────────────╮
    │ Data Dir: /srv/cleveragents           │
    │ Config: /srv/cleveragents/config.toml │
    │ Logs: /srv/cleveragents/logs          │
    │ Cache: /srv/cleveragents/cache        │
    │ Database: /srv/cleveragents/agents.db │
    ╰───────────────────────────────────────╯

    ╭─ Runtime ──────────╮
    │ PID: 4127          │
    │ Uptime: 00:14:32   │
    │ Python: 3.13.1     │
    │ Host: devbox.local │
    │ Platform: linux    │
    ╰────────────────────╯

    ╭─ Projects & Sessions ─╮
    │ Projects: 2           │
    │ Sessions: 1 active    │
    │ Active Plans: 0       │
    │ Actors: 3             │
    ╰───────────────────────╯

    ✓ OK Environment loaded
=== "Plain" ``` $ agents --data-dir /srv/cleveragents --config-path /srv/cleveragents/config.toml info System Snapshot CleverAgents 1.0.0 Mode: local Automation: review Status: ready Paths Data Dir: /srv/cleveragents Config: /srv/cleveragents/config.toml Logs: /srv/cleveragents/logs Cache: /srv/cleveragents/cache Database: /srv/cleveragents/agents.db Runtime PID: 4127 Uptime: 00:14:32 Python: 3.13.1 Host: devbox.local Platform: linux Projects & Sessions Projects: 2 Sessions: 1 active Active Plans: 0 Actors: 3 [OK] Environment loaded ``` === "JSON" ```json { "command": "info", "status": "ok", "exit_code": 0, "data": { "system_snapshot": { "name": "CleverAgents", "version": "1.0.0", "mode": "local", "automation": "review", "status": "ready" }, "paths": { "data_dir": "/srv/cleveragents", "config": "/srv/cleveragents/config.toml", "logs": "/srv/cleveragents/logs", "cache": "/srv/cleveragents/cache", "database": "/srv/cleveragents/agents.db" }, "runtime": { "pid": 4127, "uptime": "00:14:32", "python": "3.13.1", "host": "devbox.local", "platform": "linux" }, "projects_and_sessions": { "projects": 2, "sessions": "1 active", "active_plans": 0, "actors": 3 } }, "timing": { "duration_ms": 12 }, "messages": [ { "level": "ok", "text": "Environment loaded" } ] } ``` === "YAML" ```yaml command: info status: ok exit_code: 0 data: system_snapshot: name: CleverAgents version: "1.0.0" mode: local automation: review status: ready paths: data_dir: /srv/cleveragents config: /srv/cleveragents/config.toml logs: /srv/cleveragents/logs cache: /srv/cleveragents/cache database: /srv/cleveragents/agents.db runtime: pid: 4127 uptime: "00:14:32" python: "3.13.1" host: devbox.local platform: linux projects_and_sessions: projects: 2 sessions: 1 active active_plans: 0 actors: 3 timing: duration_ms: 12 messages: - level: ok text: Environment loaded ``` #### agents version 
agents version
**Purpose** Print the current CLI version. **Arguments** None. **Examples** === "Rich" 

    $ agents version

    ╭─ CLI Version ────╮
    │ CleverAgents CLI │
    │ Version: 1.0.0   │
    │ Channel: stable  │
    │ Python: 3.13     │
    ╰──────────────────╯

    ╭─ Build ────────────────╮
    │ Build Date: 2026-02-08 │
    │ Commit: a17c3f9        │
    │ Schema: v3             │
    │ Platform: linux-x86_64 │
    ╰────────────────────────╯

    ╭─ Dependencies ─────────────────╮
    │ LangGraph: 0.2.60              │
    │ LangChain: 0.3.18              │
    │ MCP SDK: 1.4.0                 │
    │ Pydantic: 2.10.4               │
    ╰────────────────────────────────╯

    ✓ OK Version reported
=== "Plain" ``` $ agents version CLI Version CleverAgents CLI Version: 1.0.0 Channel: stable Python: 3.13 Build Build Date: 2026-02-08 Commit: a17c3f9 Schema: v3 Platform: linux-x86_64 Dependencies LangGraph: 0.2.60 LangChain: 0.3.18 MCP SDK: 1.4.0 Pydantic: 2.10.4 [OK] Version reported ``` === "JSON" ```json { "command": "version", "status": "ok", "exit_code": 0, "data": { "cli": { "name": "CleverAgents CLI", "version": "1.0.0", "channel": "stable", "python": "3.13" }, "build": { "build_date": "2026-02-08", "commit": "a17c3f9", "schema": "v3", "platform": "linux-x86_64" }, "dependencies": { "langgraph": "0.2.60", "langchain": "0.3.18", "mcp_sdk": "1.4.0", "pydantic": "2.10.4" } }, "timing": { "duration_ms": 8 }, "messages": [ { "level": "ok", "text": "Version reported" } ] } ``` === "YAML" ```yaml command: version status: ok exit_code: 0 data: cli: name: CleverAgents CLI version: "1.0.0" channel: stable python: "3.13" build: build_date: "2026-02-08" commit: a17c3f9 schema: v3 platform: linux-x86_64 dependencies: langgraph: "0.2.60" langchain: "0.3.18" mcp_sdk: "1.4.0" pydantic: "2.10.4" timing: duration_ms: 8 messages: - level: ok text: Version reported ``` #### agents info 
agents info
**Purpose** Show configuration and runtime information useful for debugging or support. **Arguments** None. **Examples** === "Rich" 

    $ agents info

    ╭─ Environment ───────────────────────────────────────────────╮
    │ Data Dir: /home/alex/.cleveragents                          │
    │ Config: /home/alex/.cleveragents/config.toml                │
    │ Database: sqlite:///home/alex/.cleveragents/cleveragents.db │
    │ Server Mode: disabled                                       │
    │ Platform: Linux 6.8.0 (x86_64)                              │
    ╰─────────────────────────────────────────────────────────────╯

    ╭─ Runtime ─────────────────────────╮
    │ Automation: review                │
    │ Providers: 3 configured           │
    │ Sessions: 2 active                │
    │ Active Plans: 1                   │
    ╰───────────────────────────────────╯

    ╭─ Storage ─────╮
    │ Cache: 118 MB │
    │ Logs: 42 MB   │
    │ Backups: 3    │
    │ DB Size: 8 MB │
    ╰───────────────╯

    ╭─ Indexing ─────────────╮
    │ Text Index: ready      │
    │ Vector Index: ready    │
    │ Graph Store: disabled  │
    │ Indexed Files: 1,247   │
    ╰────────────────────────╯

    ✓ OK Environment details ready
=== "Plain" ``` $ agents info Environment Data Dir: /home/alex/.cleveragents Config: /home/alex/.cleveragents/config.toml Database: sqlite:///home/alex/.cleveragents/cleveragents.db Server Mode: disabled Platform: Linux 6.8.0 (x86_64) Runtime Automation: review Providers: 3 configured Sessions: 2 active Active Plans: 1 Storage Cache: 118 MB Logs: 42 MB Backups: 3 DB Size: 8 MB Indexing Text Index: ready Vector Index: ready Graph Store: disabled Indexed Files: 1,247 [OK] Environment details ready ``` === "JSON" ```json { "command": "info", "status": "ok", "exit_code": 0, "data": { "environment": { "data_dir": "/home/alex/.cleveragents", "config": "/home/alex/.cleveragents/config.toml", "database": "sqlite:///home/alex/.cleveragents/cleveragents.db", "server_mode": "disabled", "platform": "Linux 6.8.0 (x86_64)" }, "runtime": { "automation": "review", "providers": 3, "sessions": "2 active", "active_plans": 1 }, "storage": { "cache_mb": 118, "logs_mb": 42, "backups": 3, "db_size_mb": 8 }, "indexing": { "text_index": "ready", "vector_index": "ready", "graph_store": "disabled", "indexed_files": 1247 } }, "timing": { "duration_ms": 18 }, "messages": [ { "level": "ok", "text": "Environment details ready" } ] } ``` === "YAML" ```yaml command: info status: ok exit_code: 0 data: environment: data_dir: /home/alex/.cleveragents config: /home/alex/.cleveragents/config.toml database: sqlite:///home/alex/.cleveragents/cleveragents.db server_mode: disabled platform: Linux 6.8.0 (x86_64) runtime: automation: review providers: 3 sessions: 2 active active_plans: 1 storage: cache_mb: 118 logs_mb: 42 backups: 3 db_size_mb: 8 indexing: text_index: ready vector_index: ready graph_store: disabled indexed_files: 1247 timing: duration_ms: 18 messages: - level: ok text: Environment details ready ``` #### agents diagnostics 
agents diagnostics
**Purpose** Run health checks for configuration, providers, and filesystem permissions. **Arguments** None. **Examples** === "Rich" 

    $ agents diagnostics

    ╭─ Checks ──────────────────────────────────────────────────╮
    │ Check                     Status  Details               │
    │ ───────────────────────────  ──────  ───────────────────── │
    │ Config file               OK      readable               │
    │ Database                  OK      writable               │
    │ OpenAI key                WARN    missing                │
    │ Anthropic key             OK      configured             │
    │ Google key                WARN    missing                │
    │ Gemini key                WARN    missing                │
    │ Azure OpenAI key          WARN    missing                │
    │ OpenRouter key            WARN    missing                │
    │ Cohere key                WARN    missing                │
    │ Groq key                  WARN    missing                │
    │ Together key              WARN    missing                │
    │ Disk space                OK      2.1 GB free            │
    │ Text index                OK      tantivy 0.22           │
    │ Vector index              OK      faiss (CPU)            │
    │ Graph store               WARN    not configured         │
    │ File permissions          OK      data dir r/w           │
    │ Git                       OK      git 2.43.0             │
    ╰───────────────────────────────────────────────────────────╯

    ╭─ Summary ─────────╮
    │ Checks: 17 total  │
    │ Warnings: 9       │
    │ Errors: 0         │
    │ Duration: 0.6s    │
    ╰───────────────────╯

    ╭─ Recommendations ──────────────────────────────────────────────╮
    │ - Set OPENAI_API_KEY to enable OpenAI models                   │
    │ - Set GOOGLE_API_KEY to enable Google models                   │
    │ - Set GEMINI_API_KEY to enable Gemini models                   │
    │ - Set AZURE_OPENAI_API_KEY to enable Azure OpenAI models       │
    │ - Set OPENROUTER_API_KEY to enable OpenRouter models           │
    │ - Set COHERE_API_KEY to enable Cohere models                   │
    │ - Set GROQ_API_KEY to enable Groq models                       │
    │ - Set TOGETHER_API_KEY to enable Together models               │
    │ - Configure a graph store backend for structural code queries  │
    ╰────────────────────────────────────────────────────────────────╯

    ⚠ WARN 9 warnings require attention
=== "Plain" ``` $ agents diagnostics Checks Check Status Details ------------------------ ------ -------------- Config file OK readable Database OK writable OpenAI key WARN missing Anthropic key OK configured Google key WARN missing Gemini key WARN missing Azure OpenAI key WARN missing OpenRouter key WARN missing Cohere key WARN missing Groq key WARN missing Together key WARN missing Disk space OK 2.1 GB free Text index OK tantivy 0.22 Vector index OK faiss (CPU) Graph store WARN not configured File permissions OK data dir r/w Git OK git 2.43.0 Summary Checks: 17 total Warnings: 9 Errors: 0 Duration: 0.6s Recommendations - Set OPENAI_API_KEY to enable OpenAI models - Set GOOGLE_API_KEY to enable Google models - Set GEMINI_API_KEY to enable Gemini models - Set AZURE_OPENAI_API_KEY to enable Azure OpenAI models - Set OPENROUTER_API_KEY to enable OpenRouter models - Set COHERE_API_KEY to enable Cohere models - Set GROQ_API_KEY to enable Groq models - Set TOGETHER_API_KEY to enable Together models - Configure a graph store backend for structural code queries [WARN] 9 warnings require attention ``` === "JSON" ```json { "command": "diagnostics", "status": "ok", "exit_code": 0, "data": { "checks": [ { "check": "Config file", "status": "ok", "details": "readable" }, { "check": "Database", "status": "ok", "details": "writable" }, { "check": "OpenAI key", "status": "warn", "details": "missing" }, { "check": "Anthropic key", "status": "ok", "details": "configured" }, { "check": "Google key", "status": "warn", "details": "missing" }, { "check": "Gemini key", "status": "warn", "details": "missing" }, { "check": "Azure OpenAI key", "status": "warn", "details": "missing" }, { "check": "OpenRouter key", "status": "warn", "details": "missing" }, { "check": "Cohere key", "status": "warn", "details": "missing" }, { "check": "Groq key", "status": "warn", "details": "missing" }, { "check": "Together key", "status": "warn", "details": "missing" }, { "check": "Disk space", "status": "ok", "details": "2.1 GB free" }, { "check": "Text index", "status": "ok", "details": "tantivy 0.22" }, { "check": "Vector index", "status": "ok", "details": "faiss (CPU)" }, { "check": "Graph store", "status": "warn", "details": "not configured" }, { "check": "File permissions", "status": "ok", "details": "data dir r/w" }, { "check": "Git", "status": "ok", "details": "git 2.43.0" } ], "summary": { "total": 17, "warnings": 9, "errors": 0, "duration_s": 0.6 }, "recommendations": [ "Set OPENAI_API_KEY to enable OpenAI models", "Set GOOGLE_API_KEY to enable Google models", "Set GEMINI_API_KEY to enable Gemini models", "Set AZURE_OPENAI_API_KEY to enable Azure OpenAI models", "Set OPENROUTER_API_KEY to enable OpenRouter models", "Set COHERE_API_KEY to enable Cohere models", "Set GROQ_API_KEY to enable Groq models", "Set TOGETHER_API_KEY to enable Together models", "Configure a graph store backend for structural code queries" ] }, "timing": { "duration_ms": 600 }, "messages": [ { "level": "warn", "text": "9 warnings require attention" } ] } ``` === "YAML" ```yaml command: diagnostics status: ok exit_code: 0 data: checks: - check: Config file status: ok details: readable - check: Database status: ok details: writable - check: OpenAI key status: warn details: missing - check: Anthropic key status: ok details: configured - check: Google key status: warn details: missing - check: Gemini key status: warn details: missing - check: Azure OpenAI key status: warn details: missing - check: OpenRouter key status: warn details: missing - check: Cohere key status: warn details: missing - check: Groq key status: warn details: missing - check: Together key status: warn details: missing - check: Disk space status: ok details: 2.1 GB free - check: Text index status: ok details: tantivy 0.22 - check: Vector index status: ok details: faiss (CPU) - check: Graph store status: warn details: not configured - check: File permissions status: ok details: data dir r/w - check: Git status: ok details: git 2.43.0 summary: total: 17 warnings: 9 errors: 0 duration_s: 0.6 recommendations: - Set OPENAI_API_KEY to enable OpenAI models - Set GOOGLE_API_KEY to enable Google models - Set GEMINI_API_KEY to enable Gemini models - Set AZURE_OPENAI_API_KEY to enable Azure OpenAI models - Set OPENROUTER_API_KEY to enable OpenRouter models - Set COHERE_API_KEY to enable Cohere models - Set GROQ_API_KEY to enable Groq models - Set TOGETHER_API_KEY to enable Together models - Configure a graph store backend for structural code queries timing: duration_ms: 600 messages: - level: warn text: 9 warnings require attention ``` When critical checks fail, diagnostics reports errors: === "Rich" 

    $ agents diagnostics

    ╭─ Checks ──────────────────────────────────────────────────╮
    │ Check                     Status   Details                   │
    │ ───────────────────────────  ───────  ───────────────────────────── │
    │ Config file               OK       readable                    │
    │ Database                  ERROR    locked by another process    │
    │ OpenAI key                ERROR    invalid key format           │
    │ Anthropic key             OK       configured                  │
    │ Google key                WARN     missing                     │
    │ Gemini key                WARN     missing                     │
    │ Azure OpenAI key          WARN     missing                     │
    │ OpenRouter key            WARN     missing                     │
    │ Cohere key                WARN     missing                     │
    │ Groq key                  WARN     missing                     │
    │ Together key              WARN     missing                     │
    │ Disk space                WARN     312 MB free (low)            │
    │ Text index                OK       tantivy 0.22                │
    │ Vector index              ERROR    FAISS library not found      │
    │ Graph store               OK       neo4j 5.15                   │
    │ File permissions          OK       data dir r/w                 │
    │ Git                       OK       git 2.43.0                  │
    ╰───────────────────────────────────────────────────────────╯

    ╭─ Summary ─────────╮
    │ Checks: 17 total  │
    │ Warnings: 8       │
    │ Errors: 3         │
    │ Duration: 1.2s    │
    ╰───────────────────╯

    ╭─ Errors (must fix) ─────────────────────────────────────────────────╮
    │ 1. Database is locked by PID 12847 — stop the other process or      │
    │    delete the lock file at ~/.cleveragents/agents.db-lock           │
    │ 2. OpenAI key starts with "pk-" — expected "sk-" prefix          │
    │    Run: agents config set provider.openai.api-key      │
    │ 3. FAISS library not installed — vector search will not work        │
    │    Run: pip install faiss-cpu                                       │
    ╰─────────────────────────────────────────────────────────────────────╯

    ✗ ERROR 3 errors must be resolved before CleverAgents can operate
=== "Plain" ``` $ agents diagnostics Checks Check Status Details ------------------------ ------- -------------------------- Config file OK readable Database ERROR locked by another process OpenAI key ERROR invalid key format Anthropic key OK configured Google key WARN missing Gemini key WARN missing Azure OpenAI key WARN missing OpenRouter key WARN missing Cohere key WARN missing Groq key WARN missing Together key WARN missing Disk space WARN 312 MB free (low) Text index OK tantivy 0.22 Vector index ERROR FAISS library not found Graph store OK neo4j 5.15 File permissions OK data dir r/w Git OK git 2.43.0 Summary Checks: 17 total Warnings: 8 Errors: 3 Duration: 1.2s Errors (must fix) 1. Database is locked by PID 12847 -- stop the other process or delete the lock file at ~/.cleveragents/agents.db-lock 2. OpenAI key starts with "pk-" -- expected "sk-" prefix Run: agents config set provider.openai.api-key 3. FAISS library not installed -- vector search will not work Run: pip install faiss-cpu [ERROR] 3 errors must be resolved before CleverAgents can operate ``` === "JSON" ```json { "command": "diagnostics", "status": "error", "exit_code": 1, "data": { "checks": [ { "check": "Config file", "status": "ok", "details": "readable" }, { "check": "Database", "status": "error", "details": "locked by another process" }, { "check": "OpenAI key", "status": "error", "details": "invalid key format" }, { "check": "Anthropic key", "status": "ok", "details": "configured" }, { "check": "Google key", "status": "warn", "details": "missing" }, { "check": "Gemini key", "status": "warn", "details": "missing" }, { "check": "Azure OpenAI key", "status": "warn", "details": "missing" }, { "check": "OpenRouter key", "status": "warn", "details": "missing" }, { "check": "Cohere key", "status": "warn", "details": "missing" }, { "check": "Groq key", "status": "warn", "details": "missing" }, { "check": "Together key", "status": "warn", "details": "missing" }, { "check": "Disk space", "status": "warn", "details": "312 MB free (low)" }, { "check": "Text index", "status": "ok", "details": "tantivy 0.22" }, { "check": "Vector index", "status": "error", "details": "FAISS library not found" }, { "check": "Graph store", "status": "ok", "details": "neo4j 5.15" }, { "check": "File permissions", "status": "ok", "details": "data dir r/w" }, { "check": "Git", "status": "ok", "details": "git 2.43.0" } ], "summary": { "total": 17, "warnings": 8, "errors": 3, "duration_s": 1.2 }, "errors": [ { "index": 1, "message": "Database is locked by PID 12847 -- stop the other process or delete the lock file at ~/.cleveragents/agents.db-lock" }, { "index": 2, "message": "OpenAI key starts with \"pk-\" -- expected \"sk-\" prefix", "fix": "agents config set provider.openai.api-key " }, { "index": 3, "message": "FAISS library not installed -- vector search will not work", "fix": "pip install faiss-cpu" } ] }, "timing": { "duration_ms": 1200 }, "messages": [ { "level": "error", "text": "3 errors must be resolved before CleverAgents can operate" } ] } ``` === "YAML" ```yaml command: diagnostics status: error exit_code: 1 data: checks: - check: Config file status: ok details: readable - check: Database status: error details: locked by another process - check: OpenAI key status: error details: invalid key format - check: Anthropic key status: ok details: configured - check: Google key status: warn details: missing - check: Gemini key status: warn details: missing - check: Azure OpenAI key status: warn details: missing - check: OpenRouter key status: warn details: missing - check: Cohere key status: warn details: missing - check: Groq key status: warn details: missing - check: Together key status: warn details: missing - check: Disk space status: warn details: 312 MB free (low) - check: Text index status: ok details: tantivy 0.22 - check: Vector index status: error details: FAISS library not found - check: Graph store status: ok details: neo4j 5.15 - check: File permissions status: ok details: data dir r/w - check: Git status: ok details: git 2.43.0 summary: total: 17 warnings: 8 errors: 3 duration_s: 1.2 errors: - index: 1 message: >- Database is locked by PID 12847 -- stop the other process or delete the lock file at ~/.cleveragents/agents.db-lock - index: 2 message: >- OpenAI key starts with "pk-" -- expected "sk-" prefix fix: agents config set provider.openai.api-key - index: 3 message: >- FAISS library not installed -- vector search will not work fix: pip install faiss-cpu timing: duration_ms: 1200 messages: - level: error text: 3 errors must be resolved before CleverAgents can operate ``` #### agents init 
agents init [--yes|-y]
!!! danger "Destructive Operation" This command ==wipes all existing data== and re-creates the global config and database. A backup is created automatically, but all sessions, plans, and registry entries will be removed. **Purpose** Initialize or reset the global CleverAgents environment. This wipes any existing data and re-creates the global config and database. **Arguments** - `--yes`: Skip the confirmation prompt and proceed with the wipe. **Examples** === "Rich" 

    $ agents init

    Warning: This will remove all data in /home/alex/.cleveragents
    Continue? [y/N]: y

    ╭─ Environment Reset ────────────────────────────────╮
    │ Config: /home/alex/.cleveragents/config.toml       │
    │ Database: /home/alex/.cleveragents/cleveragents.db │
    │ Backup: /home/alex/.cleveragents.backup-2026-02-08 │
    │ Status: ready                                      │
    ╰────────────────────────────────────────────────────╯

    ╭─ Defaults ──────────────────────────────────╮
    │ Automation Profile: supervised              │
    │ Built-in Profiles: 8 loaded                 │
    ╰─────────────────────────────────────────────╯

    ╭─ Created ─────────────────╮
    │ Config: config.toml       │
    │ Database: cleveragents.db │
    │ Logs: logs/               │
    │ Cache: cache/             │
    │ Backups: backups/         │
    ╰───────────────────────────╯

    ╭─ Schema ───────────────────────╮
    │ Version: v3                    │
    │ Tables: 12 created             │
    │ Migrations: up to date         │
    ╰────────────────────────────────╯

    ✓ OK Environment initialized
=== "Plain" ``` $ agents init Warning: This will remove all data in /home/alex/.cleveragents Continue? [y/N]: y Environment Reset Config: /home/alex/.cleveragents/config.toml Database: /home/alex/.cleveragents/cleveragents.db Backup: /home/alex/.cleveragents.backup-2026-02-08 Status: ready Defaults Automation Profile: supervised Built-in Profiles: 8 loaded Created Config: config.toml Database: cleveragents.db Logs: logs/ Cache: cache/ Backups: backups/ Schema Version: v3 Tables: 12 created Migrations: up to date [OK] Environment initialized ``` === "JSON" ```json { "command": "init", "status": "ok", "exit_code": 0, "data": { "environment_reset": { "config": "/home/alex/.cleveragents/config.toml", "database": "/home/alex/.cleveragents/cleveragents.db", "backup": "/home/alex/.cleveragents.backup-2026-02-08", "status": "ready" }, "defaults": { "automation_profile": "supervised", "builtin_profiles": 8 }, "created": { "config": "config.toml", "database": "cleveragents.db", "logs": "logs/", "cache": "cache/", "backups": "backups/" }, "schema": { "version": "v3", "tables": 12, "migrations": "up to date" } }, "timing": { "duration_ms": 340 }, "messages": [ { "level": "ok", "text": "Environment initialized" } ] } ``` === "YAML" ```yaml command: init status: ok exit_code: 0 data: environment_reset: config: /home/alex/.cleveragents/config.toml database: /home/alex/.cleveragents/cleveragents.db backup: /home/alex/.cleveragents.backup-2026-02-08 status: ready defaults: automation_profile: supervised builtin_profiles: 8 created: config: config.toml database: cleveragents.db logs: logs/ cache: cache/ backups: backups/ schema: version: v3 tables: 12 migrations: up to date timing: duration_ms: 340 messages: - level: ok text: Environment initialized ``` Non-interactive initialization using `--yes` (useful in scripts and CI): === "Rich" 

    $ agents init --yes

    ╭─ Initialized ──────────────────────────────────────────╮
    │ Data Dir: /home/alex/.cleveragents (created)           │
    │ Config: /home/alex/.cleveragents/config.toml           │
    │ Database: initialized (schema v3)                      │
    │ Directories: logs, cache, sessions, contexts           │
    ╰────────────────────────────────────────────────────────╯

    ✓ OK Initialized (non-interactive)
=== "Plain" ``` $ agents init --yes Initialized Data Dir: /home/alex/.cleveragents (created) Config: /home/alex/.cleveragents/config.toml Database: initialized (schema v3) Directories: logs, cache, sessions, contexts [OK] Initialized (non-interactive) ``` === "JSON" ```json { "command": "init --yes", "status": "ok", "exit_code": 0, "data": { "initialized": { "data_dir": "/home/alex/.cleveragents", "config": "/home/alex/.cleveragents/config.toml", "database": "initialized (schema v3)", "directories": ["logs", "cache", "sessions", "contexts"] } }, "timing": { "duration_ms": 280 }, "messages": [ { "level": "ok", "text": "Initialized (non-interactive)" } ] } ``` === "YAML" ```yaml command: init --yes status: ok exit_code: 0 data: initialized: data_dir: /home/alex/.cleveragents config: /home/alex/.cleveragents/config.toml database: initialized (schema v3) directories: - logs - cache - sessions - contexts timing: duration_ms: 280 messages: - level: ok text: Initialized (non-interactive) ``` #### agents session **Purpose** Manage interactive sessions that hold a conversation history and orchestrator state. ##### agents session create 
agents session create [--actor <ACTOR>]
**Purpose** Create a new session for interactive work. **Arguments** - `--actor ACTOR`: Orchestrator actor to use for `session tell`. **Examples** === "Rich" 

    $ agents session create --actor local/orchestrator

    ╭─ Session ───────────────────────╮
    │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z  │
    │ Actor: local/orchestrator       │
    │ Created: 2026-02-08 12:44       │
    │ Namespace: local                │
    ╰─────────────────────────────────╯

    ╭─ Settings ─────────────╮
    │ Automation: review     │
    │ Streaming: off         │
    │ Context: default       │
    │ Memory: enabled        │
    │ Max History: 50 turns  │
    ╰────────────────────────╯

    ╭─ Actor Details ───────────────────╮
    │ Provider: anthropic               │
    │ Model: claude-3.5                 │
    │ Temperature: 0.7                  │
    │ Context Window: 200K tokens       │
    ╰───────────────────────────────────╯

    ✓ OK Session created
=== "Plain" ``` $ agents session create --actor local/orchestrator Session ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Actor: local/orchestrator Created: 2026-02-08 12:44 Namespace: local Settings Automation: review Streaming: off Context: default Memory: enabled Max History: 50 turns Actor Details Provider: anthropic Model: claude-3.5 Temperature: 0.7 Context Window: 200K tokens [OK] Session created ``` === "JSON" ```json { "command": "agents session create --actor local/orchestrator", "status": "ok", "exit_code": 0, "data": { "session": { "id": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "actor": "local/orchestrator", "created": "2026-02-08T12:44:00Z", "namespace": "local" }, "settings": { "automation": "review", "streaming": "off", "context": "default", "memory": "enabled", "max_history": 50 }, "actor_details": { "provider": "anthropic", "model": "claude-3.5", "temperature": 0.7, "context_window": "200K tokens" } }, "timing": { "duration_ms": 120 }, "messages": [{ "level": "ok", "text": "Session created" }] } ``` === "YAML" ```yaml command: agents session create --actor local/orchestrator status: ok exit_code: 0 data: session: id: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z actor: local/orchestrator created: "2026-02-08T12:44:00Z" namespace: local settings: automation: review streaming: "off" context: default memory: enabled max_history: 50 actor_details: provider: anthropic model: claude-3.5 temperature: 0.7 context_window: 200K tokens timing: duration_ms: 120 messages: - level: ok text: Session created ``` ##### agents session list 
agents session list
**Purpose** List sessions available on the local machine. **Arguments** None. **Examples** === "Rich" 

    $ agents --format table session list

    ╭─ Sessions ───────────────────────────────────────────────────────────────────╮
    │ ID        Name             Actor               Messages  Updated             │
    │ ────────  ───────────────  ──────────────────  ────────  ────────────────    │
    │ 01HXM2A61MQHZ4MRBAY3MPNJTN  weekly-planning  local/orchestrator  6         2026-02-08 12:44    │
    │ 01HXM1F21MQHZ4MRBAY3MPNJTN  refactor-sprint  local/orchestrator  14        2026-02-07 18:11    │
    ╰──────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ────────────────────╮
    │ Total: 2                     │
    │ Most Recent: weekly-planning │
    │ Oldest: refactor-sprint      │
    │ Total Messages: 20           │
    │ Storage: 42 KB               │
    ╰──────────────────────────────╯

    ✓ OK 2 sessions listed
=== "Plain" ``` $ agents --format table session list Sessions ID Name Actor Messages Updated -------- --------------- ------------------ -------- ---------------- 01HXM2A61MQHZ4MRBAY3MPNJTN weekly-planning local/orchestrator 6 2026-02-08 12:44 01HXM1F21MQHZ4MRBAY3MPNJTN refactor-sprint local/orchestrator 14 2026-02-07 18:11 Summary Total: 2 Most Recent: weekly-planning Oldest: refactor-sprint Total Messages: 20 Storage: 42 KB [OK] 2 sessions listed ``` === "JSON" ```json { "command": "agents --format table session list", "status": "ok", "exit_code": 0, "data": { "sessions": [ { "id": "01HXM2A61MQHZ4MRBAY3MPNJTN", "name": "weekly-planning", "actor": "local/orchestrator", "messages": 6, "updated": "2026-02-08T12:44:00Z" }, { "id": "01HXM1F21MQHZ4MRBAY3MPNJTN", "name": "refactor-sprint", "actor": "local/orchestrator", "messages": 14, "updated": "2026-02-07T18:11:00Z" } ], "summary": { "total": 2, "most_recent": "weekly-planning", "oldest": "refactor-sprint", "total_messages": 20, "storage": "42 KB" } }, "timing": { "duration_ms": 85 }, "messages": [{ "level": "ok", "text": "2 sessions listed" }] } ``` === "YAML" ```yaml command: agents --format table session list status: ok exit_code: 0 data: sessions: - id: 01HXM2A61MQHZ4MRBAY3MPNJTN name: weekly-planning actor: local/orchestrator messages: 6 updated: "2026-02-08T12:44:00Z" - id: 01HXM1F21MQHZ4MRBAY3MPNJTN name: refactor-sprint actor: local/orchestrator messages: 14 updated: "2026-02-07T18:11:00Z" summary: total: 2 most_recent: weekly-planning oldest: refactor-sprint total_messages: 20 storage: 42 KB timing: duration_ms: 85 messages: - level: ok text: 2 sessions listed ``` ##### agents session show 
agents session show <SESSION_ID>
**Purpose** Show details and recent messages for a session. **Arguments** - ``: The session identifier. **Examples** === "Rich" 

    $ agents session show 01HXM2A6K1P2E9Q9D4GQ7J4S7Z

    ╭─ Session Summary ───────────────╮
    │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z  │
    │ Actor: local/orchestrator       │
    │ Messages: 6                     │
    │ Created: 2026-02-08 12:30       │
    │ Updated: 2026-02-08 12:44       │
    │ Automation: review              │
    ╰─────────────────────────────────╯

    ╭─ Recent Messages ──────────────────────────────────╮
    │ user  Create an action to refresh dependency locks │
    │ assistant  Plan created, running commands...       │
    │ assistant  Completed 2 commands                    │
    ╰────────────────────────────────────────────────────╯

    ╭─ Linked Plans ────────────────────────────────╮
    │ Plan ID                     Phase   State     │
    │ ──────────────────────────  ──────  ────────  │
    │ 01HXM8C2ZK4Q7C2B3F2R4VYV6J  execute  complete │
    ╰───────────────────────────────────────────────╯

    ╭─ Token Usage ──────────────╮
    │ Input Tokens: 3,420        │
    │ Output Tokens: 1,185       │
    │ Estimated Cost: $0.0184    │
    ╰────────────────────────────╯

    ✓ OK Session details loaded
=== "Plain" ``` $ agents session show 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Session Summary ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Actor: local/orchestrator Messages: 6 Created: 2026-02-08 12:30 Updated: 2026-02-08 12:44 Automation: review Recent Messages user Create an action to refresh dependency locks assistant Plan created, running commands... assistant Completed 2 commands Linked Plans Plan ID Phase State -------------------------- ------- -------- 01HXM8C2ZK4Q7C2B3F2R4VYV6J execute complete Token Usage Input Tokens: 3,420 Output Tokens: 1,185 Estimated Cost: $0.0184 [OK] Session details loaded ``` === "JSON" ```json { "command": "agents session show 01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "status": "ok", "exit_code": 0, "data": { "session_summary": { "id": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "actor": "local/orchestrator", "messages": 6, "created": "2026-02-08T12:30:00Z", "updated": "2026-02-08T12:44:00Z", "automation": "review" }, "recent_messages": [ { "role": "user", "text": "Create an action to refresh dependency locks" }, { "role": "assistant", "text": "Plan created, running commands..." }, { "role": "assistant", "text": "Completed 2 commands" } ], "linked_plans": [ { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "state": "complete" } ], "token_usage": { "input_tokens": 3420, "output_tokens": 1185, "estimated_cost": "$0.0184" } }, "timing": { "duration_ms": 95 }, "messages": [{ "level": "ok", "text": "Session details loaded" }] } ``` === "YAML" ```yaml command: agents session show 01HXM2A6K1P2E9Q9D4GQ7J4S7Z status: ok exit_code: 0 data: session_summary: id: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z actor: local/orchestrator messages: 6 created: "2026-02-08T12:30:00Z" updated: "2026-02-08T12:44:00Z" automation: review recent_messages: - role: user text: Create an action to refresh dependency locks - role: assistant text: Plan created, running commands... - role: assistant text: Completed 2 commands linked_plans: - plan_id: 01HXM8C2ZK4Q7C2B3F2R4VYV6J phase: execute state: complete token_usage: input_tokens: 3420 output_tokens: 1185 estimated_cost: "$0.0184" timing: duration_ms: 95 messages: - level: ok text: Session details loaded ``` ##### agents session delete 
agents session delete [--yes|-y] <SESSION_ID>
!!! danger "Irreversible Deletion" This command ==permanently deletes== a session and its stored conversation history. Messages and context cannot be recovered after deletion. Use `--yes` to skip the confirmation prompt. **Arguments** - ``: The session identifier. - `--yes, -y`: Skip the confirmation prompt. **Examples** === "Rich" 

    $ agents session delete 01HXM2A6K1P2E9Q9D4GQ7J4S7Z

    Delete session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z? [y/N]: y

    ╭─ Deletion Summary ──────────────────╮
    │ Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z │
    │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z      │
    │ Messages: 6 removed                 │
    │ Storage: 18 KB freed                │
    │ Plans Orphaned: 0                   │
    ╰─────────────────────────────────────╯

    ╭─ Cleanup ───────────╮
    │ Backups: none       │
    │ Logs: preserved     │
    │ Context: cleared    │
    │ Checkpoints: none   │
    ╰─────────────────────╯

    ✓ OK Session deleted
=== "Plain" ``` $ agents session delete 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Delete session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z? [y/N]: y Deletion Summary Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Messages: 6 removed Storage: 18 KB freed Plans Orphaned: 0 Cleanup Backups: none Logs: preserved Context: cleared Checkpoints: none [OK] Session deleted ``` === "JSON" ```json { "command": "agents session delete 01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "status": "ok", "exit_code": 0, "data": { "deletion_summary": { "session": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "id": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "messages_removed": 6, "storage_freed": "18 KB", "plans_orphaned": 0 }, "cleanup": { "backups": "none", "logs": "preserved", "context": "cleared", "checkpoints": "none" } }, "timing": { "duration_ms": 62 }, "messages": [{ "level": "ok", "text": "Session deleted" }] } ``` === "YAML" ```yaml command: agents session delete 01HXM2A6K1P2E9Q9D4GQ7J4S7Z status: ok exit_code: 0 data: deletion_summary: session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z id: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z messages_removed: 6 storage_freed: 18 KB plans_orphaned: 0 cleanup: backups: none logs: preserved context: cleared checkpoints: none timing: duration_ms: 62 messages: - level: ok text: Session deleted ``` ##### agents session export 
agents session export [(--output|-o) <FILE>] <SESSION_ID>
**Purpose** Export a session as a portable JSON file. **Arguments** - ``: The session identifier. - `--output/-o FILE`: Output file path (optional). **Examples** === "Rich" 

    $ agents session export --output /tmp/weekly-planning.json 01HXM2A6K1P2E9Q9D4GQ7J4S7Z

    ╭─ Session Export ────────────────────╮
    │ Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z │
    │ Output: /tmp/weekly-planning.json   │
    │ Messages: 6                         │
    │ Size: 24 KB                         │
    │ Format: JSON                        │
    ╰─────────────────────────────────────╯

    ╭─ Contents ─────────────────╮
    │ Messages: 6                │
    │ Plan References: 1         │
    │ Metadata Keys: 2           │
    │ Actor Config: included     │
    │ Schema Version: v3         │
    ╰────────────────────────────╯

    ╭─ Integrity ──────────────────╮
    │ Checksum: sha256:7a9b...42c1 │
    │ Encrypted: no                │
    ╰──────────────────────────────╯

    ✓ OK Export completed
=== "Plain" ``` $ agents session export --output /tmp/weekly-planning.json 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Session Export Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Output: /tmp/weekly-planning.json Messages: 6 Size: 24 KB Format: JSON Contents Messages: 6 Plan References: 1 Metadata Keys: 2 Actor Config: included Schema Version: v3 Integrity Checksum: sha256:7a9b...42c1 Encrypted: no [OK] Export completed ``` === "JSON" ```json { "command": "agents session export --output /tmp/weekly-planning.json 01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "status": "ok", "exit_code": 0, "data": { "session_export": { "session": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "output": "/tmp/weekly-planning.json", "messages": 6, "size": "24 KB", "format": "JSON" }, "contents": { "messages": 6, "plan_references": 1, "metadata_keys": 2, "actor_config": "included", "schema_version": "v3" }, "integrity": { "checksum": "sha256:7a9b...42c1", "encrypted": false } }, "timing": { "duration_ms": 140 }, "messages": [{ "level": "ok", "text": "Export completed" }] } ``` === "YAML" ```yaml command: agents session export --output /tmp/weekly-planning.json 01HXM2A6K1P2E9Q9D4GQ7J4S7Z status: ok exit_code: 0 data: session_export: session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z output: /tmp/weekly-planning.json messages: 6 size: 24 KB format: JSON contents: messages: 6 plan_references: 1 metadata_keys: 2 actor_config: included schema_version: v3 integrity: checksum: "sha256:7a9b...42c1" encrypted: false timing: duration_ms: 140 messages: - level: ok text: Export completed ``` ##### agents session import 
agents session import (--input|-i) <FILE>
**Purpose** Import a session JSON file. **Arguments** - `--input/-i FILE`: Input JSON file. **Examples** === "Rich" 

    $ agents session import --input /tmp/weekly-planning.json

    ╭─ Session Import ────────────────────────╮
    │ Input: /tmp/weekly-planning.json        │
    │ Session ID: 01HXM3D3B2W4CQYQ3P4ZB8A5T1  │
    │ Messages: 6                             │
    │ Schema: v3                              │
    ╰─────────────────────────────────────────╯

    ╭─ Validation ────────────╮
    │ Checksum: verified      │
    │ Schema: compatible      │
    │ Actor Ref: resolved     │
    ╰─────────────────────────╯

    ╭─ Merge ──────────────╮
    │ Existing: none       │
    │ Strategy: create new │
    ╰──────────────────────╯

    ✓ OK Import completed
=== "Plain" ``` $ agents session import --input /tmp/weekly-planning.json Session Import Input: /tmp/weekly-planning.json Session ID: 01HXM3D3B2W4CQYQ3P4ZB8A5T1 Messages: 6 Schema: v3 Validation Checksum: verified Schema: compatible Actor Ref: resolved Merge Existing: none Strategy: create new [OK] Import completed ``` === "JSON" ```json { "command": "agents session import --input /tmp/weekly-planning.json", "status": "ok", "exit_code": 0, "data": { "session_import": { "input": "/tmp/weekly-planning.json", "session_id": "01HXM3D3B2W4CQYQ3P4ZB8A5T1", "messages": 6, "schema": "v3" }, "validation": { "checksum": "verified", "schema": "compatible", "actor_ref": "resolved" }, "merge": { "existing": "none", "strategy": "create new" } }, "timing": { "duration_ms": 210 }, "messages": [{ "level": "ok", "text": "Import completed" }] } ``` === "YAML" ```yaml command: agents session import --input /tmp/weekly-planning.json status: ok exit_code: 0 data: session_import: input: /tmp/weekly-planning.json session_id: 01HXM3D3B2W4CQYQ3P4ZB8A5T1 messages: 6 schema: v3 validation: checksum: verified schema: compatible actor_ref: resolved merge: existing: none strategy: create new timing: duration_ms: 210 messages: - level: ok text: Import completed ``` ##### agents session tell 
agents session tell --session <SESSION_ID> [--actor <ACTOR>] [--stream] <PROMPT>
!!! tip "Primary User Interface" This is the main natural-language interface for interacting with CleverAgents. The orchestrator interprets your request and issues the necessary CleverAgents commands under the hood — creating actions, plans, or project changes as needed. Use `--stream` to see responses in real time. **Purpose** Send a natural-language request to the orchestrator. The orchestrator can create actions, plans, or project changes by issuing the necessary CleverAgents commands under the hood. **Arguments** - ``: Instruction text (positional argument). - `--session SESSION_ID`: Session to use (required). - `--actor ACTOR`: Override the session actor for this request. - `--stream`: Stream progress as the orchestrator works. **Examples** === "Rich" 

    $ agents session tell "Create an action to refresh dependency locks and add it to the platform project" \
      --session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z

    ╭─ Plan Request ──────────────────────────────────────────╮
    │ Actor: local/orchestrator                               │
    │ Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z                     │
    │ Automation: review                                      │
    │ Prompt: Create an action to refresh dependency locks... │
    ╰─────────────────────────────────────────────────────────╯

    ╭─ Commands Executed ─────────────────────────────────────────────────────────────────────────────────────────╮
    │ - agents action create --config ./actions/refresh-locks.yaml                                                │
    │ - agents resource add git-checkout local/platform-repo --path /repos/platform                               │
    │ - agents project link-resource local/platform local/platform-repo                                           │
    ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Result ──────────────────────────╮
    │ Action: local/refresh-locks       │
    │ Project: local/platform           │
    │ Resource: local/platform-repo     │
    ╰───────────────────────────────────╯

    ╭─ Usage ─────────────────────╮
    │ Input Tokens: 1,842         │
    │ Output Tokens: 624          │
    │ Cost: $0.0094               │
    │ Duration: 3.2s              │
    │ Tool Calls: 3               │
    ╰─────────────────────────────╯

    ✓ OK Orchestrator completed 3 commands
=== "Plain" ``` $ agents session tell "Create an action to refresh dependency locks and add it to the platform project" \ --session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Plan Request Actor: local/orchestrator Session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Automation: review Prompt: Create an action to refresh dependency locks... Commands Executed - agents action create --config ./actions/refresh-locks.yaml - agents resource add git-checkout local/platform-repo --path /repos/platform - agents project link-resource local/platform local/platform-repo Result Action: local/refresh-locks Project: local/platform Resource: local/platform-repo Usage Input Tokens: 1,842 Output Tokens: 624 Cost: $0.0094 Duration: 3.2s Tool Calls: 3 [OK] Orchestrator completed 3 commands ``` === "JSON" ```json { "command": "agents session tell \"Create an action to refresh dependency locks and add it to the platform project\" --session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "status": "ok", "exit_code": 0, "data": { "plan_request": { "actor": "local/orchestrator", "session": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "automation": "review", "prompt": "Create an action to refresh dependency locks..." }, "commands_executed": [ "agents action create --config ./actions/refresh-locks.yaml", "agents resource add git-checkout local/platform-repo --path /repos/platform", "agents project link-resource local/platform local/platform-repo" ], "result": { "action": "local/refresh-locks", "project": "local/platform", "resource": "local/platform-repo" }, "usage": { "input_tokens": 1842, "output_tokens": 624, "cost": "$0.0094", "duration_s": 3.2, "tool_calls": 3 } }, "timing": { "duration_ms": 3200 }, "messages": [{ "level": "ok", "text": "Orchestrator completed 3 commands" }] } ``` === "YAML" ```yaml command: agents session tell "Create an action to refresh dependency locks and add it to the platform project" --session 01HXM2A6K1P2E9Q9D4GQ7J4S7Z status: ok exit_code: 0 data: plan_request: actor: local/orchestrator session: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z automation: review prompt: Create an action to refresh dependency locks... commands_executed: - agents action create --config ./actions/refresh-locks.yaml - agents resource add git-checkout local/platform-repo --path /repos/platform - agents project link-resource local/platform local/platform-repo result: action: local/refresh-locks project: local/platform resource: local/platform-repo usage: input_tokens: 1842 output_tokens: 624 cost: "$0.0094" duration_s: 3.2 tool_calls: 3 timing: duration_ms: 3200 messages: - level: ok text: Orchestrator completed 3 commands ``` Using `--stream` to see the response as it is generated (token by token): === "Rich" 

    $ agents session tell --session 01HXM2A6K1 --stream "What files were changed in the last plan?"

    ╭─ Session ──────────────────────────╮
    │ ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z     │
    │ Actor: local/orchestrator          │
    │ Mode: streaming                    │
    ╰────────────────────────────────────╯

    ▍ The last plan (01HXM8C2ZK) modified 6 files in the auth module:

      1. `src/auth/session.py` — refactored session validation
      2. `src/auth/tokens.py` — updated token expiry to 7200s
      3. `src/auth/__init__.py` — updated exports
      4. `tests/test_auth.py` — added 12 new test cases
      5. `tests/test_session.py` — updated session fixtures
      6. `docs/auth.md` — updated API documentation

    All changes passed validation (24/24 tests, lint clean).

    ╭─ Usage ──────────────────╮
    │ Tokens: 1,240 (stream)   │
    │ Duration: 3.1s           │
    │ Tool Calls: 2            │
    ╰──────────────────────────╯

    ✓ OK Stream complete
=== "Plain" ``` $ agents session tell --session 01HXM2A6K1 --stream "What files were changed in the last plan?" Session ID: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z Actor: local/orchestrator Mode: streaming The last plan (01HXM8C2ZK) modified 6 files in the auth module: 1. src/auth/session.py -- refactored session validation 2. src/auth/tokens.py -- updated token expiry to 7200s 3. src/auth/__init__.py -- updated exports 4. tests/test_auth.py -- added 12 new test cases 5. tests/test_session.py -- updated session fixtures 6. docs/auth.md -- updated API documentation All changes passed validation (24/24 tests, lint clean). Usage Tokens: 1,240 (stream) Duration: 3.1s Tool Calls: 2 [OK] Stream complete ``` === "JSON" ```json { "command": "agents session tell --session 01HXM2A6K1 --stream \"What files were changed in the last plan?\"", "status": "ok", "exit_code": 0, "data": { "session": { "id": "01HXM2A6K1P2E9Q9D4GQ7J4S7Z", "actor": "local/orchestrator", "mode": "streaming" }, "response": "The last plan (01HXM8C2ZK) modified 6 files in the auth module:\n\n1. src/auth/session.py \u2014 refactored session validation\n2. src/auth/tokens.py \u2014 updated token expiry to 7200s\n3. src/auth/__init__.py \u2014 updated exports\n4. tests/test_auth.py \u2014 added 12 new test cases\n5. tests/test_session.py \u2014 updated session fixtures\n6. docs/auth.md \u2014 updated API documentation\n\nAll changes passed validation (24/24 tests, lint clean).", "files_changed": [ "src/auth/session.py", "src/auth/tokens.py", "src/auth/__init__.py", "tests/test_auth.py", "tests/test_session.py", "docs/auth.md" ], "usage": { "tokens": 1240, "duration_s": 3.1, "tool_calls": 2 } }, "timing": { "duration_ms": 3100 }, "messages": [{ "level": "ok", "text": "Stream complete" }] } ``` === "YAML" ```yaml command: agents session tell --session 01HXM2A6K1 --stream "What files were changed in the last plan?" status: ok exit_code: 0 data: session: id: 01HXM2A6K1P2E9Q9D4GQ7J4S7Z actor: local/orchestrator mode: streaming response: > The last plan (01HXM8C2ZK) modified 6 files in the auth module: 1. src/auth/session.py -- refactored session validation 2. src/auth/tokens.py -- updated token expiry to 7200s 3. src/auth/__init__.py -- updated exports 4. tests/test_auth.py -- added 12 new test cases 5. tests/test_session.py -- updated session fixtures 6. docs/auth.md -- updated API documentation All changes passed validation (24/24 tests, lint clean). files_changed: - src/auth/session.py - src/auth/tokens.py - src/auth/__init__.py - tests/test_auth.py - tests/test_session.py - docs/auth.md usage: tokens: 1240 duration_s: 3.1 tool_calls: 2 timing: duration_ms: 3100 messages: - level: ok text: Stream complete ``` #### agents project **Purpose** Manage projects and their resources. ##### agents project create 
agents project create [(--description|-d) <DESC>] [--resource <RESOURCE>]...
                     [--invariant <INVARIANT>]... [--invariant-actor <ACTOR>] <NAME>
**Purpose** Create a new project record. **Arguments** - ``: Namespaced project name (positional argument). - `--description/-d TEXT`: Optional description. - `--resource RESOURCE`: Resource name or ULID to link to the project at creation time (repeatable). - `--invariant TEXT`: Invariant to attach to this project (repeatable). These invariants apply to all plans targeting this project. - `--invariant-actor ACTOR`: Invariant Reconciliation Actor for this project. Used to reconcile project-level invariants against global invariants for all plans targeting this project (unless the plan overrides it). **Examples** === "Rich" 

    $ agents project create --description "Backend API" local/api-service

    ╭─ Project ──────────────────────╮
    │ Name: local/api-service        │
    │ Description: Backend API       │
    │ Type: local                    │
    │ Created: 2026-02-08 12:46      │
    ╰────────────────────────────────╯

    ╭─ Paths ────────────────────────────────────╮
    │ Root: /repos/api-service                   │
    │ Data Dir: /repos/api-service/.cleveragents │
    ╰────────────────────────────────────────────╯

    ╭─ Defaults ──────────────────────────────╮
    │ Sandbox: git_worktree                   │
    │ Validations: 0                          │
    │ Context Filters: none                   │
    │ Automation Profile: (inherits global)   │
    ╰─────────────────────────────────────────╯

    ╭─ Resources ──────╮
    │ Total: 0         │
    │ Indexed: 0       │
    │ Sandboxable: 0   │
    ╰──────────────────╯

    ✓ OK Project created
=== "Plain" ``` $ agents project create --description "Backend API" local/api-service Project Name: local/api-service Description: Backend API Type: local Created: 2026-02-08 12:46 Paths Root: /repos/api-service Data Dir: /repos/api-service/.cleveragents Defaults Sandbox: git_worktree Validations: 0 Context Filters: none Automation Profile: (inherits global) Resources Total: 0 Indexed: 0 Sandboxable: 0 [OK] Project created ``` === "JSON" ```json { "command": "agents project create --description \"Backend API\" local/api-service", "status": "ok", "exit_code": 0, "data": { "project": { "name": "local/api-service", "description": "Backend API", "type": "local", "created": "2026-02-08T12:46:00Z" }, "paths": { "root": "/repos/api-service", "data_dir": "/repos/api-service/.cleveragents" }, "defaults": { "sandbox": "git_worktree", "validations": 0, "context_filters": null, "automation_profile": null }, "resources": { "total": 0, "indexed": 0, "sandboxable": 0 } }, "timing": { "duration_ms": 85 }, "messages": [{ "level": "ok", "text": "Project created" }] } ``` === "YAML" ```yaml command: agents project create --description "Backend API" local/api-service status: ok exit_code: 0 data: project: name: local/api-service description: Backend API type: local created: "2026-02-08T12:46:00Z" paths: root: /repos/api-service data_dir: /repos/api-service/.cleveragents defaults: sandbox: git_worktree validations: 0 context_filters: null automation_profile: null resources: total: 0 indexed: 0 sandboxable: 0 timing: duration_ms: 85 messages: - level: ok text: Project created ``` Creating a project with resources and invariants in one command: === "Rich" 

    $ agents project create -d "Frontend web application" \
      --resource local/web-repo --resource local/web-db \
      --invariant "All components must have unit tests" \
      --invariant "CSS must pass stylelint checks" \
      --invariant-actor local/invariant-resolver \
      local/web-app

    ╭─ Project Created ─────────────────────╮
    │ Name: local/web-app                   │
    │ Description: Frontend web app         │
    │ Remote: no                            │
    ╰───────────────────────────────────────╯

    ╭─ Linked Resources ───────────────────────────────────────╮
    │ Name               Type          Read-Only               │
    │ ─────────────────  ──────────────  ─────────             │
    │ local/web-repo     git-checkout    no                    │
    │ local/web-db       local/database  no                    │
    ╰──────────────────────────────────────────────────────────╯

    ╭─ Invariants ────────────────────────────────────╮
    │ 1. All components must have unit tests          │
    │ 2. CSS must pass stylelint checks               │
    │ Reconciliation Actor: local/invariant-resolver  │
    ╰─────────────────────────────────────────────────╯

    ✓ OK Project created
=== "Plain" ``` $ agents project create -d "Frontend web application" \ --resource local/web-repo --resource local/web-db \ --invariant "All components must have unit tests" \ --invariant "CSS must pass stylelint checks" \ --invariant-actor local/invariant-resolver \ local/web-app Project Created Name: local/web-app Description: Frontend web app Remote: no Linked Resources Name Type Read-Only ----------------- -------------- --------- local/web-repo git-checkout no local/web-db local/database no Invariants 1. All components must have unit tests 2. CSS must pass stylelint checks Reconciliation Actor: local/invariant-resolver [OK] Project created ``` === "JSON" ```json { "command": "agents project create -d \"Frontend web application\" --resource local/web-repo --resource local/web-db --invariant \"All components must have unit tests\" --invariant \"CSS must pass stylelint checks\" --invariant-actor local/invariant-resolver local/web-app", "status": "ok", "exit_code": 0, "data": { "project": { "name": "local/web-app", "description": "Frontend web app", "remote": false }, "linked_resources": [ { "name": "local/web-repo", "type": "git-checkout", "read_only": false }, { "name": "local/web-db", "type": "local/database", "read_only": false } ], "invariants": { "items": [ "All components must have unit tests", "CSS must pass stylelint checks" ], "reconciliation_actor": "local/invariant-resolver" } }, "timing": { "duration_ms": 120 }, "messages": [{ "level": "ok", "text": "Project created" }] } ``` === "YAML" ```yaml command: agents project create -d "Frontend web application" --resource local/web-repo --resource local/web-db --invariant "All components must have unit tests" --invariant "CSS must pass stylelint checks" --invariant-actor local/invariant-resolver local/web-app status: ok exit_code: 0 data: project: name: local/web-app description: Frontend web app remote: false linked_resources: - name: local/web-repo type: git-checkout read_only: false - name: local/web-db type: local/database read_only: false invariants: items: - All components must have unit tests - CSS must pass stylelint checks reconciliation_actor: local/invariant-resolver timing: duration_ms: 120 messages: - level: ok text: Project created ``` ##### agents project link-resource 
agents project link-resource [--read-only] <PROJECT> <RESOURCE>
**Purpose** Link a registered resource to a project. The resource must already be registered via `agents resource add`. A resource can be linked to multiple projects. Optionally, the resource can be marked as read-only within this project context, and given an alias for convenience. **Arguments** - ``: Project name (positional argument). - ``: Resource name or ULID (positional argument). - `--read-only`: Mark the resource as read-only within this project (even if the resource itself is writable). **Examples** === "Rich" 

    $ agents resource add git-checkout local/api-repo --path /repos/api --branch main
    $ agents project link-resource local/api-service local/api-repo

    ╭─ Resource Linked ───────────────────────╮
    │ Project: local/api-service              │
    │ Resource: local/api-repo                │
    │ Type: git-checkout                      │
    │ Read-Only: no                           │
    ╰─────────────────────────────────────────╯

    ╭─ Access ─────────────────╮
    │ Read: allowed            │
    │ Write: allowed           │
    │ Apply: requires approval │
    ╰──────────────────────────╯

    ╭─ Indexing ─────────────────────╮
    │ Status: indexing...            │
    │ Files Found: 347               │
    │ Language: Python (primary)     │
    │ Estimated Time: ~20 seconds    │
    ╰────────────────────────────────╯

    ✓ OK Resource linked to project
=== "Plain" ``` $ agents resource add git-checkout local/api-repo --path /repos/api --branch main $ agents project link-resource local/api-service local/api-repo Resource Linked Project: local/api-service Resource: local/api-repo Type: git-checkout Read-Only: no Access Read: allowed Write: allowed Apply: requires approval Indexing Status: indexing... Files Found: 347 Language: Python (primary) Estimated Time: ~20 seconds [OK] Resource linked to project ``` === "JSON" ```json { "command": "agents project link-resource local/api-service local/api-repo", "status": "ok", "exit_code": 0, "data": { "resource_linked": { "project": "local/api-service", "resource": "local/api-repo", "type": "git-checkout", "read_only": false }, "access": { "read": "allowed", "write": "allowed", "apply": "requires approval" }, "indexing": { "status": "indexing", "files_found": 347, "language": "Python (primary)", "estimated_time_seconds": 20 } }, "timing": { "duration_ms": 92 }, "messages": [{ "level": "ok", "text": "Resource linked to project" }] } ``` === "YAML" ```yaml command: agents project link-resource local/api-service local/api-repo status: ok exit_code: 0 data: resource_linked: project: local/api-service resource: local/api-repo type: git-checkout read_only: false access: read: allowed write: allowed apply: requires approval indexing: status: indexing files_found: 347 language: Python (primary) estimated_time_seconds: 20 timing: duration_ms: 92 messages: - level: ok text: Resource linked to project ``` ##### agents project unlink-resource 
agents project unlink-resource [--yes|-y] <PROJECT> <RESOURCE_NAME>
**Purpose** Unlink a resource from a project. The resource itself remains registered in the Resource Registry and can still be linked to other projects. Active plans using this resource in this project context will be warned. **Arguments** - ``: Project name (positional argument). - ``: Resource name (positional argument). Only user-added (named) resources can be unlinked. - `--yes, -y`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents project unlink-resource local/api-service local/api-repo

    Unlink local/api-repo from local/api-service? [y/N]: y

    ╭─ Resource Unlinked ─────────────────────────────────╮
    │ Project: local/api-service                          │
    │ Resource: local/api-repo                            │
    │ Type: git-checkout                                  │
    ╰─────────────────────────────────────────────────────╯

    ╭─ Index Cleanup ──────────╮
    │ Text Index: 347 removed  │
    │ Vectors: 892 removed     │
    │ Graph Triples: cleared   │
    │ Duration: 0.3s           │
    ╰──────────────────────────╯

    ╭─ Project Summary ──────────────╮
    │ Linked Resources: 1 remaining  │
    │ Last Updated: 2026-02-09 10:30 │
    │ Active Plans: 0                │
    ╰────────────────────────────────╯

    ✓ OK Resource unlinked from project
=== "Plain" ``` $ agents project unlink-resource local/api-service local/api-repo Unlink local/api-repo from local/api-service? [y/N]: y Resource Unlinked Project: local/api-service Resource: local/api-repo Type: git-checkout Index Cleanup Text Index: 347 removed Vectors: 892 removed Graph Triples: cleared Duration: 0.3s Project Summary Linked Resources: 1 remaining Last Updated: 2026-02-09 10:30 Active Plans: 0 [OK] Resource unlinked from project ``` === "JSON" ```json { "command": "agents project unlink-resource local/api-service local/api-repo", "status": "ok", "exit_code": 0, "data": { "resource_unlinked": { "project": "local/api-service", "resource": "local/api-repo", "type": "git-checkout" }, "index_cleanup": { "text_index": "347 removed", "vectors": "892 removed", "graph_triples": "cleared", "duration_seconds": 0.3 }, "project_summary": { "linked_resources": 1, "last_updated": "2026-02-09T10:30:00Z", "active_plans": 0 } }, "timing": { "duration_ms": 340 }, "messages": [{ "level": "ok", "text": "Resource unlinked from project" }] } ``` === "YAML" ```yaml command: agents project unlink-resource local/api-service local/api-repo status: ok exit_code: 0 data: resource_unlinked: project: local/api-service resource: local/api-repo type: git-checkout index_cleanup: text_index: 347 removed vectors: 892 removed graph_triples: cleared duration_seconds: 0.3 project_summary: linked_resources: 1 last_updated: "2026-02-09T10:30:00Z" active_plans: 0 timing: duration_ms: 340 messages: - level: ok text: Resource unlinked from project ``` ##### agents project list 
agents project list [(--namespace|-n) NS] [<REGEX>]
**Purpose** List projects with optional filters. **Arguments** - `--namespace/-n NS`: Filter by namespace. **Examples** === "Rich" 

    $ agents --format table project list

    ╭─ Projects ────────────────────────────────────────────────────╮
    │ Name               Resources  Remote  Active Plans            │
    │ ─────────────────  ─────────  ──────  ────────────            │
    │ local/api-service  2          No      1                       │
    │ local/docs         1          No      0                       │
    ╰───────────────────────────────────────────────────────────────╯

    ╭─ Summary ──────────────────╮
    │ Total: 2                   │
    │ With Resources: 2          │
    │ Remote: 0                  │
    │ Total Resources: 3         │
    │ Indexed Files: 1,247       │
    │ Active Plans: 1            │
    ╰────────────────────────────╯

    ✓ OK 2 projects listed
=== "Plain" ``` $ agents --format table project list Projects Name Resources Remote Active Plans ----------------- --------- ------ ------------ local/api-service 2 No 1 local/docs 1 No 0 Summary Total: 2 With Resources: 2 Remote: 0 Total Resources: 3 Indexed Files: 1,247 Active Plans: 1 [OK] 2 projects listed ``` === "JSON" ```json { "command": "agents --format table project list", "status": "ok", "exit_code": 0, "data": { "projects": [ { "name": "local/api-service", "resources": 2, "remote": false, "active_plans": 1 }, { "name": "local/docs", "resources": 1, "remote": false, "active_plans": 0 } ], "summary": { "total": 2, "with_resources": 2, "remote": 0, "total_resources": 3, "indexed_files": 1247, "active_plans": 1 } }, "timing": { "duration_ms": 45 }, "messages": [{ "level": "ok", "text": "2 projects listed" }] } ``` === "YAML" ```yaml command: agents --format table project list status: ok exit_code: 0 data: projects: - name: local/api-service resources: 2 remote: false active_plans: 1 - name: local/docs resources: 1 remote: false active_plans: 0 summary: total: 2 with_resources: 2 remote: 0 total_resources: 3 indexed_files: 1247 active_plans: 1 timing: duration_ms: 45 messages: - level: ok text: 2 projects listed ``` ##### agents project show 
agents project show <PROJECT>
**Purpose** Show full project details. **Arguments** - ``: Project name. **Examples** === "Rich" 

    $ agents project show local/api-service

    ╭─ Project Details ──────────────╮
    │ Name: local/api-service        │
    │ Description: Backend API       │
    │ Resources: 2                   │
    │ Remote: no                     │
    │ Created: 2026-02-08 12:46      │
    ╰────────────────────────────────╯

    ╭─ Linked Resources ──────────────────────────────────────────────────────╮
    │ Resource          Type            Sandbox              Read-Only        │
    │ ────────────────  ──────────────  ────────────────────  ─────────       │
    │ local/api-repo   git-checkout    git_worktree         no                │
    │ local/staging-db local/database  transaction_rollback yes               │
    ╰─────────────────────────────────────────────────────────────────────────╯

    ╭─ Validations (3) ──────────────────────────────────────────────────────────────────╮
    │ local/run-tests          Run unit tests with coverage    required                  │
    │   resource: local/api-repo  scope: project  (attachment: 01HXM5A1B2C3D4E5F6G7…)    │
    │ local/lint-check         Lint check                     required                   │
    │   resource: local/api-repo  scope: direct (always active)  (attachment: 01HXM5…)   │
    │ local/check-bundle-size  Check bundle size (advisory)   informational              │
    │   resource: local/api-repo  scope: project  (attachment: 01HXM5D4E5F6G7H8J9…)      │
    ╰────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Context ───────────────────╮
    │ Include: repo               │
    │ Exclude: **/node_modules/**     │
    │ Max File Size: 1 MB         │
    ╰─────────────────────────────╯

    ╭─ Indexing Status ──────────╮
    │ Text Index: ready          │
    │ Vector Index: ready        │
    │ Graph Store: disabled      │
    │ Indexed Files: 347         │
    │ Last Indexed: 12:48        │
    ╰────────────────────────────╯

    ╭─ Active Plans ──────────────────────────╮
    │ Plan ID   Action               Phase    │
    │ ────────  ───────────────────  ───────  │
    │ 01HXM7A9  local/code-coverage  execute  │
    ╰─────────────────────────────────────────╯

    ✓ OK Project loaded
=== "Plain" ``` $ agents project show local/api-service Project Details Name: local/api-service Description: Backend API Resources: 2 Remote: no Created: 2026-02-08 12:46 Linked Resources Resource Type Sandbox Read-Only ---------------- -------------- -------------------- --------- local/api-repo git-checkout git_worktree no local/staging-db local/database transaction_rollback yes Validations (3) local/run-tests Run unit tests with coverage required resource: local/api-repo scope: project (attachment: 01HXM5A1B2C3D4E5F6G7...) local/lint-check Lint check required resource: local/api-repo scope: direct (always active) (attachment: 01HXM5...) local/check-bundle-size Check bundle size (advisory) informational resource: local/api-repo scope: project (attachment: 01HXM5D4E5F6G7H8J9...) Context Include: repo Exclude: **/node_modules/** Max File Size: 1 MB Indexing Status Text Index: ready Vector Index: ready Graph Store: disabled Indexed Files: 347 Last Indexed: 12:48 Active Plans Plan ID Action Phase -------- ------------------- ------- 01HXM7A9 local/code-coverage execute [OK] Project loaded ``` === "JSON" ```json { "command": "agents project show local/api-service", "status": "ok", "exit_code": 0, "data": { "project": { "name": "local/api-service", "description": "Backend API", "resources": 2, "remote": false, "created": "2026-02-08T12:46:00Z" }, "linked_resources": [ { "name": "local/api-repo", "type": "git-checkout", "sandbox": "git_worktree", "read_only": false }, { "name": "local/staging-db", "type": "local/database", "sandbox": "transaction_rollback", "read_only": true } ], "validations": [ { "name": "local/run-tests", "description": "Run unit tests with coverage", "mode": "required", "resource": "local/api-repo", "scope": "project", "attachment_id": "01HXM5A1B2C3D4E5F6G7" }, { "name": "local/lint-check", "description": "Lint check", "mode": "required", "resource": "local/api-repo", "scope": "direct", "attachment_id": "01HXM5" }, { "name": "local/check-bundle-size", "description": "Check bundle size (advisory)", "mode": "informational", "resource": "local/api-repo", "scope": "project", "attachment_id": "01HXM5D4E5F6G7H8J9" } ], "context": { "include": ["repo"], "exclude": ["**/node_modules/**"], "max_file_size_bytes": 1048576 }, "indexing_status": { "text_index": "ready", "vector_index": "ready", "graph_store": "disabled", "indexed_files": 347, "last_indexed": "12:48" }, "active_plans": [ { "plan_id": "01HXM7A9", "action": "local/code-coverage", "phase": "execute" } ] }, "timing": { "duration_ms": 62 }, "messages": [{ "level": "ok", "text": "Project loaded" }] } ``` === "YAML" ```yaml command: agents project show local/api-service status: ok exit_code: 0 data: project: name: local/api-service description: Backend API resources: 2 remote: false created: "2026-02-08T12:46:00Z" linked_resources: - name: local/api-repo type: git-checkout sandbox: git_worktree read_only: false - name: local/staging-db type: local/database sandbox: transaction_rollback read_only: true validations: - name: local/run-tests description: Run unit tests with coverage mode: required resource: local/api-repo scope: project attachment_id: 01HXM5A1B2C3D4E5F6G7 - name: local/lint-check description: Lint check mode: required resource: local/api-repo scope: direct attachment_id: 01HXM5 - name: local/check-bundle-size description: Check bundle size (advisory) mode: informational resource: local/api-repo scope: project attachment_id: 01HXM5D4E5F6G7H8J9 context: include: - repo exclude: - "**/node_modules/**" max_file_size_bytes: 1048576 indexing_status: text_index: ready vector_index: ready graph_store: disabled indexed_files: 347 last_indexed: "12:48" active_plans: - plan_id: 01HXM7A9 action: local/code-coverage phase: execute timing: duration_ms: 62 messages: - level: ok text: Project loaded ``` ##### agents project validations Note: Validations are managed as a top-level entity via `agents validation` commands (see the **agents validation** section below). A validation is always attached to a resource, but can optionally be scoped to a project via `agents validation attach --project `. When scoped to a project, the validation only runs when that resource is accessed through the specified project. The `agents project show` command displays all validations relevant to the project — both directly-attached validations on linked resources and project-scoped validations. See: [agents validation](#agents-validation) for full details on creating, managing, and attaching validations. ##### agents project delete 
agents project delete [--force|-f] [--yes|-y] <NAME>
!!! warning "Irreversible Action" Deleting a project ==cannot be undone==. All resource links, validation attachments, and context policies will be removed. The resources themselves remain in the Resource Registry. Use `--force` to also cancel active plans targeting this project. **Purpose** Delete a project and unlink all associated resources. The resources themselves remain in the Resource Registry. **Arguments** - ``: Project name. - `--force/-f`: Delete even if active plans exist. - `--yes`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents project delete local/docs

    Delete project local/docs? This cannot be undone. [y/N]: y

    ╭─ Deletion Summary ──────────────────╮
    │ Project: local/docs                 │
    │ Resources: 1 unlinked               │
    │ Data Dir: /repos/docs/.cleveragents │
    ╰─────────────────────────────────────╯

    ╭─ Index Cleanup ────────╮
    │ Text Index: cleared    │
    │ Vectors: 240 removed   │
    │ Graph Triples: none    │
    │ Storage Freed: 12 MB   │
    ╰────────────────────────╯

    ╭─ Backups ────────────────────────────────────╮
    │ Snapshot: /backups/local-docs-2026-02-08.tgz │
    │ Retention: 7 days                            │
    ╰──────────────────────────────────────────────╯

    ✓ OK Project deleted
=== "Plain" ``` $ agents project delete local/docs Delete project local/docs? This cannot be undone. [y/N]: y Deletion Summary Project: local/docs Resources: 1 unlinked Data Dir: /repos/docs/.cleveragents Index Cleanup Text Index: cleared Vectors: 240 removed Graph Triples: none Storage Freed: 12 MB Backups Snapshot: /backups/local-docs-2026-02-08.tgz Retention: 7 days [OK] Project deleted ``` === "JSON" ```json { "command": "agents project delete local/docs", "status": "ok", "exit_code": 0, "data": { "deletion_summary": { "project": "local/docs", "resources_unlinked": 1, "data_dir": "/repos/docs/.cleveragents" }, "index_cleanup": { "text_index": "cleared", "vectors": "240 removed", "graph_triples": "none", "storage_freed_mb": 12 }, "backups": { "snapshot": "/backups/local-docs-2026-02-08.tgz", "retention_days": 7 } }, "timing": { "duration_ms": 530 }, "messages": [{ "level": "ok", "text": "Project deleted" }] } ``` === "YAML" ```yaml command: agents project delete local/docs status: ok exit_code: 0 data: deletion_summary: project: local/docs resources_unlinked: 1 data_dir: /repos/docs/.cleveragents index_cleanup: text_index: cleared vectors: 240 removed graph_triples: none storage_freed_mb: 12 backups: snapshot: /backups/local-docs-2026-02-08.tgz retention_days: 7 timing: duration_ms: 530 messages: - level: ok text: Project deleted ``` Attempting to delete a project that has active plans (without `--force`): === "Rich" 

    $ agents project delete local/api-service

    Delete project local/api-service? [y/N]: y

    ╭─ Delete Blocked ──────────────────────────────────────────╮
    │ Cannot delete: project has active plans                   │
    │ Active Plans: 2                                           │
    │   01HXM7A9 — execute/processing (local/code-coverage)     │
    │   01HXM4J1 — strategize/processing (local/refactor-api)   │
    ╰───────────────────────────────────────────────────────────╯

    ╭─ Resolution ──────────────────────────────────────────────────────╮
    │ - Cancel or complete active plans first, or                       │
    │ - Use --force to cancel all active plans and delete the project   │
    ╰───────────────────────────────────────────────────────────────────╯

    ✗ ERROR Delete blocked — 2 active plans
=== "Plain" ``` $ agents project delete local/api-service Delete project local/api-service? [y/N]: y Delete Blocked Cannot delete: project has active plans Active Plans: 2 01HXM7A9 -- execute/processing (local/code-coverage) 01HXM4J1 -- strategize/processing (local/refactor-api) Resolution - Cancel or complete active plans first, or - Use --force to cancel all active plans and delete the project [ERROR] Delete blocked -- 2 active plans ``` === "JSON" ```json { "command": "agents project delete local/api-service", "status": "error", "exit_code": 1, "data": { "delete_blocked": { "reason": "project has active plans", "active_plans": [ { "plan_id": "01HXM7A9", "phase": "execute/processing", "action": "local/code-coverage" }, { "plan_id": "01HXM4J1", "phase": "strategize/processing", "action": "local/refactor-api" } ] }, "resolution": [ "Cancel or complete active plans first", "Use --force to cancel all active plans and delete the project" ] }, "timing": { "duration_ms": 38 }, "messages": [{ "level": "error", "text": "Delete blocked — 2 active plans" }] } ``` === "YAML" ```yaml command: agents project delete local/api-service status: error exit_code: 1 data: delete_blocked: reason: project has active plans active_plans: - plan_id: 01HXM7A9 phase: execute/processing action: local/code-coverage - plan_id: 01HXM4J1 phase: strategize/processing action: local/refactor-api resolution: - Cancel or complete active plans first - Use --force to cancel all active plans and delete the project timing: duration_ms: 38 messages: - level: error text: "Delete blocked \u2014 2 active plans" ``` Force-deleting a project with active plans: === "Rich" 

    $ agents project delete --force --yes local/api-service

    ╭─ Force Delete ─────────────────────────────────────────╮
    │ Cancelling: 2 active plans                             │
    │   01HXM7A9 — cancelled (was execute/processing)        │
    │   01HXM4J1 — cancelled (was strategize/processing)     │
    ╰────────────────────────────────────────────────────────╯

    ╭─ Deleted ────────────────────╮
    │ Project: local/api-service   │
    │ Resources Unlinked: 2        │
    │ Validations Detached: 3      │
    │ Plans Cancelled: 2           │
    │ Context Policies: cleared    │
    ╰──────────────────────────────╯

    ✓ OK Project force-deleted
=== "Plain" ``` $ agents project delete --force --yes local/api-service Force Delete Cancelling: 2 active plans 01HXM7A9 -- cancelled (was execute/processing) 01HXM4J1 -- cancelled (was strategize/processing) Deleted Project: local/api-service Resources Unlinked: 2 Validations Detached: 3 Plans Cancelled: 2 Context Policies: cleared [OK] Project force-deleted ``` === "JSON" ```json { "command": "agents project delete --force --yes local/api-service", "status": "ok", "exit_code": 0, "data": { "force_delete": { "cancelled_plans": [ { "plan_id": "01HXM7A9", "previous_state": "execute/processing" }, { "plan_id": "01HXM4J1", "previous_state": "strategize/processing" } ] }, "deleted": { "project": "local/api-service", "resources_unlinked": 2, "validations_detached": 3, "plans_cancelled": 2, "context_policies": "cleared" } }, "timing": { "duration_ms": 245 }, "messages": [{ "level": "ok", "text": "Project force-deleted" }] } ``` === "YAML" ```yaml command: agents project delete --force --yes local/api-service status: ok exit_code: 0 data: force_delete: cancelled_plans: - plan_id: 01HXM7A9 previous_state: execute/processing - plan_id: 01HXM4J1 previous_state: strategize/processing deleted: project: local/api-service resources_unlinked: 2 validations_detached: 3 plans_cancelled: 2 context_policies: cleared timing: duration_ms: 245 messages: - level: ok text: Project force-deleted ``` ##### agents project context **Purpose** Manage ACMS context policies for the hot/warm/cold tiers, per-view context selection, strategy configuration, UKO depth/breadth parameters, and context budget tuning. ###### agents project context set 
agents project context set[--view (strategize|execute|apply|default)]
                          [--include-resource <INCLUDE_RESOURCE>]...
                          [--exclude-resource <EXCLUDE_RESOURCE>]...
                          [--include-path <INCLUDE_GLOB>]...
                          [--exclude-path <EXCLUDE_GLOB>]...
                          [--hot-max-tokens <N>]
                          [--warm-max-decisions <N_WARM_MAX>]
                          [--cold-max-decisions <N_COLD_MAX>]
                          [--query-limit <N>]
                          [--max-file-size <MAX_FILE_BYTES>]
                          [--max-total-size <MAX_TOTAL_BYTES>]
                          [--summarize|--no-summarize]
                          [--summary-max-tokens <N>]
                          [--strategy <STRATEGY>]...
                          [--default-breadth <N>]
                          [--default-depth <INT_OR_NAME>]
                          [--depth-gradient <HOP:INT_OR_NAME>]...
                          [--skeleton-ratio <FLOAT>]
                          [--temporal-scope (current|recent|all)]
                          [--auto-refresh|--no-auto-refresh]
                          [--execution-environment <RESOURCE_NAME>]
                          [--execution-env-priority (fallback|override)]
                          [--clear] <PROJECT>
**Purpose** Set the context policy for a project and (optionally) a specific view. **Arguments** - ``: Project name (positional argument, at end of command). - `--view strategize|execute|apply|default`: Which view this policy applies to. - `--include-resource NAME`: Resource allowlist (repeatable). - `--exclude-resource NAME`: Resource denylist (repeatable). - `--include-path GLOB`: Path allowlist (repeatable). - `--exclude-path GLOB`: Path denylist (repeatable). - `--hot-max-tokens N`: Maximum token budget for hot context. This is a soft cap and may be null. The actor/LLM hard limit can be lower; the effective hot context is the lesser of the two. - `--warm-max-decisions N`: Maximum number of decisions kept in warm context. - `--cold-max-decisions N`: Maximum number of decisions kept in cold context. - `--query-limit N`: Max number of retrieval results per query. - `--max-file-size BYTES`: Max file size included in context. - `--max-total-size BYTES`: Max total size across included files. - `--summarize/--no-summarize`: Enable or disable summarization for large context segments. - `--summary-max-tokens N`: Token limit for generated summaries. - `--strategy STRATEGY`: ACMS context strategy to enable for this view (repeatable). Overrides the global `context.strategies.enabled` list. Built-in: `simple-keyword`, `semantic-embedding`, `breadth-depth-navigator`, `arce`, `temporal-archaeology`, `plan-decision-context`. - `--default-breadth N`: Default number of hops from focus nodes in the UKO graph. `0` = focus nodes only. Default: `2`. - `--default-depth INT_OR_NAME`: Default detail depth for context fragments. Accepts a raw integer (e.g., `4`) or a named level from the active domain's DetailLevelMap (e.g., `SIGNATURES`, `MEMBER_SUMMARY`). Named levels are resolved to integers via the DetailLevelMap inheritance chain. Default: `3` (typically `MEMBER_SUMMARY` / `FULL_TOC` / `TYPED_COLUMNS` depending on domain). - `--depth-gradient HOP:INT_OR_NAME`: Per-hop detail depth override (repeatable). Format: `0:9`, `1:4`, `2:0` or `0:FULL_SOURCE`, `1:SIGNATURES`, `2:MODULE_LISTING`. Hops not specified use `--default-depth`. - `--skeleton-ratio FLOAT`: Fraction of context budget reserved for inherited plan skeleton. Range: 0.0–1.0. Default: `0.15`. - `--temporal-scope current|recent|all`: Temporal scope for UKO node resolution. Default: `current`. - `--auto-refresh/--no-auto-refresh`: Enable or disable automatic context re-assembly on budget changes. - `--execution-environment RESOURCE_NAME`: Name of a `container-instance` or `devcontainer-instance` resource to use as the default execution environment for this project. When set, tool invocations during plan execution are routed to this container unless overridden at the plan level. See [ADR-043 §3.3](adr/ADR-043-devcontainer-integration.md). - `--execution-env-priority fallback|override`: Priority semantics for the project-level execution environment. `fallback` (default): defers to auto-detected devcontainers when present; used only when no closer-scoped environment exists. `override`: always uses the specified environment, bypassing devcontainer auto-detection. See §Execution Environment Routing. - `--clear`: Clear the policy for the selected view. **Examples** === "Rich" 

    $ agents project context set --view strategize \
      --include-resource repo --exclude-path "**/node_modules/**" \
      --hot-max-tokens 12000 --warm-max-decisions 50 --cold-max-decisions 200 \
      --summarize --summary-max-tokens 800 local/api-service

    ╭─ Context Policy ────────────╮
    │ Project: local/api-service  │
    │ View: strategize            │
    │ Include: repo               │
    │ Exclude: **/node_modules/**     │
    ╰─────────────────────────────╯

    ╭─ Limits ─────────────────────╮
    │ Hot Tokens: 12000 (soft cap) │
    │ Warm Decisions: 50           │
    │ Cold Decisions: 200          │
    │ Query Limit: 20              │
    │ Max File Size: 1 MB          │
    │ Max Total Size: 50 MB        │
    ╰──────────────────────────────╯

    ╭─ Summarization ─╮
    │ Enabled: yes    │
    │ Max Tokens: 800 │
    ╰─────────────────╯

    ╭─ Other Views ────────╮
    │ execute: (default)   │
    │ apply: (default)     │
    │ default: (unset)     │
    ╰──────────────────────╯

    ✓ OK Context policy updated
=== "Plain" ``` $ agents project context set --view strategize \ --include-resource repo --exclude-path "**/node_modules/**" \ --hot-max-tokens 12000 --warm-max-decisions 50 --cold-max-decisions 200 \ --summarize --summary-max-tokens 800 local/api-service Context Policy Project: local/api-service View: strategize Include: repo Exclude: **/node_modules/** Limits Hot Tokens: 12000 (soft cap) Warm Decisions: 50 Cold Decisions: 200 Query Limit: 20 Max File Size: 1 MB Max Total Size: 50 MB Summarization Enabled: yes Max Tokens: 800 Other Views execute: (default) apply: (default) default: (unset) [OK] Context policy updated ``` === "JSON" ```json { "command": "project context set", "status": "ok", "exit_code": 0, "data": { "context_policy": { "project": "local/api-service", "view": "strategize", "include_resources": ["repo"], "exclude_paths": ["**/node_modules/**"] }, "limits": { "hot_max_tokens": 12000, "warm_max_decisions": 50, "cold_max_decisions": 200, "query_limit": 20, "max_file_size": "1 MB", "max_total_size": "50 MB" }, "summarization": { "enabled": true, "max_tokens": 800 }, "other_views": { "execute": "(default)", "apply": "(default)", "default": "(unset)" } }, "timing": { "duration_ms": 42 }, "messages": ["Context policy updated"] } ``` === "YAML" ```yaml command: project context set status: ok exit_code: 0 data: context_policy: project: local/api-service view: strategize include_resources: - repo exclude_paths: - "**/node_modules/**" limits: hot_max_tokens: 12000 warm_max_decisions: 50 cold_max_decisions: 200 query_limit: 20 max_file_size: 1 MB max_total_size: 50 MB summarization: enabled: true max_tokens: 800 other_views: execute: (default) apply: (default) default: (unset) timing: duration_ms: 42 messages: - Context policy updated ``` ###### agents project context show 
agents project context show [--view (strategize|execute|apply|default)]
                            <PROJECT>
**Purpose** Show the active context policy for a project. **Arguments** - ``: Project name (positional argument, at end of command). - `--view strategize|execute|apply|default`: View to display. **Examples** === "Rich" 

    $ agents project context show --view strategize local/api-service

    ╭─ Context Policy ────────────╮
    │ Project: local/api-service  │
    │ View: strategize            │
    │ Include: repo               │
    │ Exclude: **/node_modules/**     │
    ╰─────────────────────────────╯

    ╭─ Limits ─────────────────────╮
    │ Hot Tokens: 12000 (soft cap) │
    │ Warm Decisions: 50           │
    │ Cold Decisions: 200          │
    │ Query Limit: 20              │
    │ Max File Size: 1 MB          │
    │ Max Total Size: 50 MB        │
    ╰──────────────────────────────╯

    ╭─ Summarization ─╮
    │ Enabled: yes    │
    │ Max Tokens: 800 │
    ╰─────────────────╯

    ╭─ Current Usage ──────────────╮
    │ Hot Context: 8,420 / 12,000  │
    │ Warm Entries: 12 / 50        │
    │ Cold Entries: 47 / 200       │
    │ Indexed Resources: 1         │
    ╰──────────────────────────────╯

    ✓ OK Context policy loaded
=== "Plain" ``` $ agents project context show --view strategize local/api-service Context Policy Project: local/api-service View: strategize Include: repo Exclude: **/node_modules/** Limits Hot Tokens: 12000 (soft cap) Warm Decisions: 50 Cold Decisions: 200 Query Limit: 20 Max File Size: 1 MB Max Total Size: 50 MB Summarization Enabled: yes Max Tokens: 800 Current Usage Hot Context: 8,420 / 12,000 Warm Entries: 12 / 50 Cold Entries: 47 / 200 Indexed Resources: 1 [OK] Context policy loaded ``` === "JSON" ```json { "command": "project context show", "status": "ok", "exit_code": 0, "data": { "context_policy": { "project": "local/api-service", "view": "strategize", "include_resources": ["repo"], "exclude_paths": ["**/node_modules/**"] }, "limits": { "hot_max_tokens": 12000, "warm_max_decisions": 50, "cold_max_decisions": 200, "query_limit": 20, "max_file_size": "1 MB", "max_total_size": "50 MB" }, "summarization": { "enabled": true, "max_tokens": 800 }, "current_usage": { "hot_context_tokens": 8420, "hot_context_limit": 12000, "warm_entries": 12, "warm_limit": 50, "cold_entries": 47, "cold_limit": 200, "indexed_resources": 1 } }, "timing": { "duration_ms": 38 }, "messages": ["Context policy loaded"] } ``` === "YAML" ```yaml command: project context show status: ok exit_code: 0 data: context_policy: project: local/api-service view: strategize include_resources: - repo exclude_paths: - "**/node_modules/**" limits: hot_max_tokens: 12000 warm_max_decisions: 50 cold_max_decisions: 200 query_limit: 20 max_file_size: 1 MB max_total_size: 50 MB summarization: enabled: true max_tokens: 800 current_usage: hot_context_tokens: 8420 hot_context_limit: 12000 warm_entries: 12 warm_limit: 50 cold_entries: 47 cold_limit: 200 indexed_resources: 1 timing: duration_ms: 38 messages: - Context policy loaded ``` ###### agents project context inspect 
agents project context inspect [--view (strategize|execute|apply|default)]
                               [--strategy <STRATEGY>]
                               [--focus <UKO_URI>]...
                               [--breadth <N>] [--depth <INT_OR_NAME>]
                               <PROJECT>
**Purpose** Inspect the current state of the ACMS context assembly for a project. Shows the UKO graph structure, active strategies, indexed resources, context budget usage, and the most recent fusion result. Useful for debugging context quality issues. **Arguments** - ``: Project name (positional argument, at end of command). - `--view strategize|execute|apply|default`: View to inspect. Default: `default`. - `--strategy STRATEGY`: Filter to show results from a specific strategy only. - `--focus UKO_URI`: Show the UKO subgraph rooted at these focus nodes (repeatable). When omitted, shows a summary of the full indexed graph. - `--breadth N`: Override the breadth (hop count) for the focus node expansion. Default: uses the view's `default_breadth`. - `--depth INT_OR_NAME`: Override the detail depth for the display. Accepts a raw integer or a named level from the active DetailLevelMap. Default: uses the view's `default_depth`. **Examples** === "Rich" 

    $ agents project context inspect --view execute --focus uko-py:module/src.auth --breadth 2 local/api-service

    ╭─ ACMS Context Inspection ────────────────────────────────────────╮
    │ Project: local/api-service                                       │
    │ View: execute                                                    │
    │ Focus: uko-py:module/src.auth                                    │
    │ Breadth: 2 hops  │  Depth: 3 (MEMBER_SUMMARY)                    │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ UKO Graph (2-hop neighborhood) ─────────────────────────────────╮
    │ uko-py:module/src.auth (depth 9/FULL_SOURCE, 1,240 tokens)       │
    │   ├─ contains → uko-py:class/AuthHandler (depth 3, 320 tokens)   │
    │   ├─ contains → uko-py:class/TokenValidator (depth 3, 280 tok)   │
    │   ├─ imports  → uko-py:module/src.db (depth 0, 90 tokens)        │
    │   └─ imports  → uko-py:module/src.config (depth 0, 60 tok)       │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Active Strategies ──────────────────────────────────────────────╮
    │ breadth-depth-navigator  quality=0.85  budget=45%  4 fragments   │
    │ semantic-embedding       quality=0.60  budget=35%  6 fragments   │
    │ simple-keyword           quality=0.30  budget=20%  3 fragments   │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Budget ─────────────────────────────╮
    │ Model Window: 128,000 tokens         │
    │ Response Reserve: 4,096 tokens       │
    │ Tool Definitions: 2,400 tokens       │
    │ System Prompt: 1,200 tokens          │
    │ Skeleton Reserve: 18,046 (15%)       │
    │ Available Budget: 102,258 tokens     │
    │ Used: 1,990 / 102,258 (1.9%)         │
    ╰──────────────────────────────────────╯

    ✓ OK Context inspection complete
=== "Plain" ``` $ agents project context inspect --view execute --focus uko-py:module/src.auth --breadth 2 local/api-service ACMS Context Inspection Project: local/api-service View: execute Focus: uko-py:module/src.auth Breadth: 2 hops Depth: 3 (MEMBER_SUMMARY) UKO Graph (2-hop neighborhood) uko-py:module/src.auth (depth 9/FULL_SOURCE, 1,240 tokens) contains -> uko-py:class/AuthHandler (depth 3, 320 tokens) contains -> uko-py:class/TokenValidator (depth 3, 280 tok) imports -> uko-py:module/src.db (depth 0, 90 tokens) imports -> uko-py:module/src.config (depth 0, 60 tok) Active Strategies Strategy Quality Budget Fragments ------------------------- ------- ------ --------- breadth-depth-navigator 0.85 45% 4 semantic-embedding 0.60 35% 6 simple-keyword 0.30 20% 3 Budget Model Window: 128,000 tokens Response Reserve: 4,096 tokens Tool Definitions: 2,400 tokens System Prompt: 1,200 tokens Skeleton Reserve: 18,046 (15%) Available Budget: 102,258 tokens Used: 1,990 / 102,258 (1.9%) [OK] Context inspection complete ``` === "JSON" ```json { "command": "project context inspect", "status": "ok", "exit_code": 0, "data": { "inspection": { "project": "local/api-service", "view": "execute", "focus": ["uko-py:module/src.auth"], "breadth": 2, "depth": 3, "depth_name": "MEMBER_SUMMARY" }, "uko_graph": { "root": "uko-py:module/src.auth", "root_depth": 9, "root_depth_name": "FULL_SOURCE", "root_tokens": 1240, "edges": [ { "relation": "contains", "target": "uko-py:class/AuthHandler", "depth": 3, "tokens": 320 }, { "relation": "contains", "target": "uko-py:class/TokenValidator", "depth": 3, "tokens": 280 }, { "relation": "imports", "target": "uko-py:module/src.db", "depth": 0, "tokens": 90 }, { "relation": "imports", "target": "uko-py:module/src.config", "depth": 0, "tokens": 60 } ] }, "active_strategies": [ { "name": "breadth-depth-navigator", "quality": 0.85, "budget_pct": 0.45, "fragments": 4 }, { "name": "semantic-embedding", "quality": 0.60, "budget_pct": 0.35, "fragments": 6 }, { "name": "simple-keyword", "quality": 0.30, "budget_pct": 0.20, "fragments": 3 } ], "budget": { "model_window": 128000, "response_reserve": 4096, "tool_definitions": 2400, "system_prompt": 1200, "skeleton_reserve": 18046, "skeleton_ratio": 0.15, "available_budget": 102258, "used": 1990, "utilization": 0.019 } }, "timing": { "duration_ms": 185 }, "messages": ["Context inspection complete"] } ``` === "YAML" ```yaml command: project context inspect status: ok exit_code: 0 data: inspection: project: local/api-service view: execute focus: - uko-py:module/src.auth breadth: 2 depth: 3 depth_name: MEMBER_SUMMARY uko_graph: root: uko-py:module/src.auth root_depth: 9 root_depth_name: FULL_SOURCE root_tokens: 1240 edges: - relation: contains target: uko-py:class/AuthHandler depth: 3 tokens: 320 - relation: contains target: uko-py:class/TokenValidator depth: 3 tokens: 280 - relation: imports target: uko-py:module/src.db depth: 0 tokens: 90 - relation: imports target: uko-py:module/src.config depth: 0 tokens: 60 active_strategies: - name: breadth-depth-navigator quality: 0.85 budget_pct: 0.45 fragments: 4 - name: semantic-embedding quality: 0.60 budget_pct: 0.35 fragments: 6 - name: simple-keyword quality: 0.30 budget_pct: 0.20 fragments: 3 budget: model_window: 128000 response_reserve: 4096 tool_definitions: 2400 system_prompt: 1200 skeleton_reserve: 18046 skeleton_ratio: 0.15 available_budget: 102258 used: 1990 utilization: 0.019 timing: duration_ms: 185 messages: - Context inspection complete ``` ###### agents project context simulate 
agents project context simulate [--view (strategize|execute|apply|default)]
                                [--budget <TOKENS>]
                                [--focus <UKO_URI>]...
                                [--strategy <STRATEGY>]...
                                <PROJECT>
**Purpose** Simulate a context assembly run without invoking an actor. Produces a dry-run report showing what the Context Assembly Pipeline would include in the context payload, which strategies contributed, how the budget was allocated, and what was excluded. Useful for tuning context view configurations before running plans. **Arguments** - ``: Project name (positional argument, at end of command). - `--view strategize|execute|apply|default`: View to simulate. Default: `default`. - `--budget TOKENS`: Override the context budget in tokens. When omitted, uses the dynamic budget calculation. - `--focus UKO_URI`: Focus nodes for the simulation (repeatable). When omitted, uses a default focus derived from recent plan activity. - `--strategy STRATEGY`: Override which strategies to run (repeatable). When omitted, uses the view's configured strategies. **Examples** === "Rich" 

    $ agents project context simulate --view strategize --budget 16000 \
        --focus uko-py:module/src.auth --focus uko-py:module/src.db \
        local/api-service

    ╭─ ACMS Simulation ────────────────────────────────────────────────╮
    │ Project: local/api-service                                       │
    │ View: strategize                                                 │
    │ Budget: 16,000 tokens (override)                                 │
    │ Focus: uko-py:module/src.auth, uko-py:module/src.db              │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Strategy Results ───────────────────────────────────────────────╮
    │ breadth-depth-navigator                                          │
    │   Confidence: 0.85  │  Budget: 7,200 tokens  │  12 fragments     │
    │   Top: src/auth/__init__.py (depth 9, 1,240t, score=0.95)            │
    │        src/db/models.py (depth 3, 480t, score=0.88)              │
    │                                                                  │
    │ semantic-embedding                                               │
    │   Confidence: 0.60  │  Budget: 5,600 tokens  │  8 fragments      │
    │   Top: src/auth/jwt.py (depth 3, 380t, score=0.82)               │
    │        src/middleware/auth_check.py (depth 3, 290t, score=0.79)  │
    │                                                                  │
    │ simple-keyword                                                   │
    │   Confidence: 0.30  │  Budget: 3,200 tokens  │  5 fragments      │
    │   Top: src/auth/utils.py (depth 6, 210t, score=0.71)             │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Fusion Result ──────────────────────────────────────────────────╮
    │ Included: 18 fragments (14,820 tokens, 92.6% of budget)          │
    │ Excluded: 7 fragments (3,200 tokens, below budget cutoff)        │
    │ Deduplicated: 4 fragments merged                                 │
    │ Skeleton: 2,400 tokens (15% reserve)                             │
    │ Preamble: 180 tokens                                             │
    ╰──────────────────────────────────────────────────────────────────╯

    ✓ OK Simulation complete (dry run — no context was assembled)
=== "Plain" ``` $ agents project context simulate --view strategize --budget 16000 \ --focus uko-py:module/src.auth --focus uko-py:module/src.db \ local/api-service ACMS Simulation Project: local/api-service View: strategize Budget: 16,000 tokens (override) Focus: uko-py:module/src.auth, uko-py:module/src.db Strategy Results breadth-depth-navigator Confidence: 0.85 Budget: 7,200 tokens 12 fragments Top: src/auth/__init__.py (depth 9, 1,240t, score=0.95) src/db/models.py (depth 3, 480t, score=0.88) semantic-embedding Confidence: 0.60 Budget: 5,600 tokens 8 fragments Top: src/auth/jwt.py (depth 3, 380t, score=0.82) src/middleware/auth_check.py (depth 3, 290t, score=0.79) simple-keyword Confidence: 0.30 Budget: 3,200 tokens 5 fragments Top: src/auth/utils.py (depth 6, 210t, score=0.71) Fusion Result Included: 18 fragments (14,820 tokens, 92.6% of budget) Excluded: 7 fragments (3,200 tokens, below budget cutoff) Deduplicated: 4 fragments merged Skeleton: 2,400 tokens (15% reserve) Preamble: 180 tokens [OK] Simulation complete (dry run -- no context was assembled) ``` === "JSON" ```json { "command": "project context simulate", "status": "ok", "exit_code": 0, "data": { "simulation": { "project": "local/api-service", "view": "strategize", "budget": 16000, "budget_source": "override", "focus": ["uko-py:module/src.auth", "uko-py:module/src.db"] }, "strategy_results": [ { "name": "breadth-depth-navigator", "confidence": 0.85, "budget_tokens": 7200, "fragments": 12, "top": [ { "path": "src/auth/__init__.py", "depth": 9, "tokens": 1240, "score": 0.95 }, { "path": "src/db/models.py", "depth": 3, "tokens": 480, "score": 0.88 } ] }, { "name": "semantic-embedding", "confidence": 0.60, "budget_tokens": 5600, "fragments": 8, "top": [ { "path": "src/auth/jwt.py", "depth": 3, "tokens": 380, "score": 0.82 }, { "path": "src/middleware/auth_check.py", "depth": 3, "tokens": 290, "score": 0.79 } ] }, { "name": "simple-keyword", "confidence": 0.30, "budget_tokens": 3200, "fragments": 5, "top": [ { "path": "src/auth/utils.py", "depth": 6, "tokens": 210, "score": 0.71 } ] } ], "fusion_result": { "included_fragments": 18, "included_tokens": 14820, "budget_utilization": 0.926, "excluded_fragments": 7, "excluded_tokens": 3200, "deduplicated_fragments": 4, "skeleton_tokens": 2400, "skeleton_ratio": 0.15, "preamble_tokens": 180 } }, "timing": { "duration_ms": 310 }, "messages": ["Simulation complete (dry run -- no context was assembled)"] } ``` === "YAML" ```yaml command: project context simulate status: ok exit_code: 0 data: simulation: project: local/api-service view: strategize budget: 16000 budget_source: override focus: - uko-py:module/src.auth - uko-py:module/src.db strategy_results: - name: breadth-depth-navigator confidence: 0.85 budget_tokens: 7200 fragments: 12 top: - path: src/auth/__init__.py depth: 9 tokens: 1240 score: 0.95 - path: src/db/models.py depth: 3 tokens: 480 score: 0.88 - name: semantic-embedding confidence: 0.60 budget_tokens: 5600 fragments: 8 top: - path: src/auth/jwt.py depth: 3 tokens: 380 score: 0.82 - path: src/middleware/auth_check.py depth: 3 tokens: 290 score: 0.79 - name: simple-keyword confidence: 0.30 budget_tokens: 3200 fragments: 5 top: - path: src/auth/utils.py depth: 6 tokens: 210 score: 0.71 fusion_result: included_fragments: 18 included_tokens: 14820 budget_utilization: 0.926 excluded_fragments: 7 excluded_tokens: 3200 deduplicated_fragments: 4 skeleton_tokens: 2400 skeleton_ratio: 0.15 preamble_tokens: 180 timing: duration_ms: 310 messages: - "Simulation complete (dry run -- no context was assembled)" ``` #### agents actor **Purpose** Manage actors and run actor configurations directly. ##### agents actor run 
agents actor run [(--output|-o) <OUTPUT_FILE>]
                 [-v...] [--unsafe|-u] [--context <CONTEXT_NAME>]
                 [--context-dir <CONTEXT_PATH>] [--load-context <LOAD_CONTEXT_NAME>]
                 [(--temperature|-t) <TEMP>] [--allow-rxpy-in-run-mode]
                 [--skill <SKILL>]... <NAME> <PROMPT>
**Purpose** Run a named actor in isolation with simple, manual context. **Arguments** - ``: The name of the actor to run (required). - ``: Prompt text (positional argument). - `--output/-o FILE`: Output file path. - `--verbose/-v`: Increase log verbosity (repeatable). Same semantics as the global `-v` flag: no `-v` = normal output only, `-v` = ERROR, `-vv` = WARN, `-vvv` = INFO, `-vvvv` = DEBUG, `-vvvvv` = TRACE. - `--unsafe/-u`: Allow unsafe configs. - `--context NAME`: Named actor context to attach. - `--context-dir PATH`: Context storage location. - `--load-context FILE`: Load context from JSON. - `--temperature/-t FLOAT`: Override temperature. - `--skill NAME`: Skill to attach (repeatable). - `--allow-rxpy-in-run-mode`: Allow RxPy routes in run mode. **Examples** === "Rich" 

    $ agents actor run --context docs local/code_reader "Summarize the README"

    ╭─ Run Summary ─────────────────╮
    │ Actor: local/code_reader      │
    │ Context: docs                 │
    │ Temperature: 0.2              │
    │ Provider: anthropic           │
    │ Model: claude-3.5             │
    ╰───────────────────────────────╯

    ╭─ Inputs ─────────────────────╮
    │ Prompt: Summarize the README │
    │ Context Files: 3             │
    │ Context Size: 12.4 KB        │
    ╰──────────────────────────────╯

    ╭─ Result Metrics ───────╮
    │ Output: stdout         │
    │ Input Tokens: 1,524    │
    │ Output Tokens: 842     │
    │ Duration: 1.8s         │
    │ Cost: $0.0021          │
    │ Tool Calls: 0          │
    ╰────────────────────────╯

    ✓ OK Summary generated
=== "Plain" ``` $ agents actor run --context docs local/code_reader "Summarize the README" Run Summary Actor: local/code_reader Context: docs Temperature: 0.2 Provider: anthropic Model: claude-3.5 Inputs Prompt: Summarize the README Context Files: 3 Context Size: 12.4 KB Result Metrics Output: stdout Input Tokens: 1,524 Output Tokens: 842 Duration: 1.8s Cost: $0.0021 Tool Calls: 0 [OK] Summary generated ``` === "JSON" ```json { "command": "agents actor run --context docs local/code_reader \"Summarize the README\"", "status": "ok", "exit_code": 0, "data": { "run_summary": { "actor": "local/code_reader", "context": "docs", "temperature": 0.2, "provider": "anthropic", "model": "claude-3.5" }, "inputs": { "prompt": "Summarize the README", "context_files": 3, "context_size": "12.4 KB" }, "result_metrics": { "output": "stdout", "input_tokens": 1524, "output_tokens": 842, "duration_s": 1.8, "cost": "$0.0021", "tool_calls": 0 } }, "timing": { "duration_ms": 1800 }, "messages": [ { "level": "ok", "text": "Summary generated" } ] } ``` === "YAML" ```yaml command: agents actor run --context docs local/code_reader "Summarize the README" status: ok exit_code: 0 data: run_summary: actor: local/code_reader context: docs temperature: 0.2 provider: anthropic model: claude-3.5 inputs: prompt: Summarize the README context_files: 3 context_size: 12.4 KB result_metrics: output: stdout input_tokens: 1524 output_tokens: 842 duration_s: 1.8 cost: "$0.0021" tool_calls: 0 timing: duration_ms: 1800 messages: - level: ok text: Summary generated ``` Running an actor with a custom temperature and skill attachment: === "Rich" 

    $ agents actor run --temperature 0.2 --skill local/code-analysis \
      local/reviewer "Review the auth module for security issues"

    ╭─ Actor Run ─────────────────────────╮
    │ Actor: local/reviewer               │
    │ Type: agent                         │
    │ Temperature: 0.2                    │
    │ Skill: local/code-analysis          │
    ╰─────────────────────────────────────╯

    ╭─ Response ────────────────────────────────────────────────────────╮
    │ I identified 3 potential security concerns in the auth module:    │
    │                                                                   │
    │ 1. Token expiry not validated in `validate_session()` at              │
    │    src/auth/session.py:42. The JWT expiry claim is decoded but    │
    │    not checked against current time.                              │
    │                                                                   │
    │ 2. Missing rate limiting on the `/auth/refresh` endpoint.            │
    │    An attacker could brute-force refresh tokens.                  │
    │                                                                   │
    │ 3. Low severity: Password hashing uses bcrypt with cost=10.       │
    │    Consider cost=12 for production deployments.                   │
    ╰───────────────────────────────────────────────────────────────────╯

    ╭─ Usage ──────────────╮
    │ Tokens: 2,840        │
    │ Duration: 4.2s       │
    │ Cost: $0.009         │
    │ Tool Calls: 6        │
    ╰──────────────────────╯

    ✓ OK Actor run completed
=== "Plain" ``` $ agents actor run --temperature 0.2 --skill local/code-analysis \ local/reviewer "Review the auth module for security issues" Actor Run Actor: local/reviewer Type: agent Temperature: 0.2 Skill: local/code-analysis Response I identified 3 potential security concerns in the auth module: 1. Token expiry not validated in validate_session() at src/auth/session.py:42. The JWT expiry claim is decoded but not checked against current time. 2. Missing rate limiting on the /auth/refresh endpoint. An attacker could brute-force refresh tokens. 3. Low severity: Password hashing uses bcrypt with cost=10. Consider cost=12 for production deployments. Usage Tokens: 2,840 Duration: 4.2s Cost: $0.009 Tool Calls: 6 [OK] Actor run completed ``` === "JSON" ```json { "command": "agents actor run --temperature 0.2 --skill local/code-analysis local/reviewer \"Review the auth module for security issues\"", "status": "ok", "exit_code": 0, "data": { "actor_run": { "actor": "local/reviewer", "type": "agent", "temperature": 0.2, "skill": "local/code-analysis" }, "response": { "text": "I identified 3 potential security concerns in the auth module:\n\n1. Token expiry not validated in validate_session() at src/auth/session.py:42. The JWT expiry claim is decoded but not checked against current time.\n\n2. Missing rate limiting on the /auth/refresh endpoint. An attacker could brute-force refresh tokens.\n\n3. Low severity: Password hashing uses bcrypt with cost=10. Consider cost=12 for production deployments.", "issues_found": 3 }, "usage": { "tokens": 2840, "duration_s": 4.2, "cost": "$0.009", "tool_calls": 6 } }, "timing": { "duration_ms": 4200 }, "messages": [ { "level": "ok", "text": "Actor run completed" } ] } ``` === "YAML" ```yaml command: >- agents actor run --temperature 0.2 --skill local/code-analysis local/reviewer "Review the auth module for security issues" status: ok exit_code: 0 data: actor_run: actor: local/reviewer type: agent temperature: 0.2 skill: local/code-analysis response: text: >- I identified 3 potential security concerns in the auth module: 1. Token expiry not validated in validate_session() at src/auth/session.py:42. The JWT expiry claim is decoded but not checked against current time. 2. Missing rate limiting on the /auth/refresh endpoint. An attacker could brute-force refresh tokens. 3. Low severity: Password hashing uses bcrypt with cost=10. Consider cost=12 for production deployments. issues_found: 3 usage: tokens: 2840 duration_s: 4.2 cost: "$0.009" tool_calls: 6 timing: duration_ms: 4200 messages: - level: ok text: Actor run completed ``` Saving actor output to a file: === "Rich" 

    $ agents actor run --output review.md local/reviewer "Write a code review report"

    ╭─ Actor Run ───────────────╮
    │ Actor: local/reviewer     │
    │ Output: review.md         │
    │ Tokens: 4,120             │
    │ Duration: 6.8s            │
    ╰───────────────────────────╯

    ✓ OK Output written to review.md (2.4 KB)
=== "Plain" ``` $ agents actor run --output review.md local/reviewer "Write a code review report" Actor Run Actor: local/reviewer Output: review.md Tokens: 4,120 Duration: 6.8s [OK] Output written to review.md (2.4 KB) ``` === "JSON" ```json { "command": "agents actor run --output review.md local/reviewer \"Write a code review report\"", "status": "ok", "exit_code": 0, "data": { "actor_run": { "actor": "local/reviewer", "output": "review.md", "tokens": 4120, "duration_s": 6.8 } }, "timing": { "duration_ms": 6800 }, "messages": [ { "level": "ok", "text": "Output written to review.md (2.4 KB)" } ] } ``` === "YAML" ```yaml command: agents actor run --output review.md local/reviewer "Write a code review report" status: ok exit_code: 0 data: actor_run: actor: local/reviewer output: review.md tokens: 4120 duration_s: 6.8 timing: duration_ms: 6800 messages: - level: ok text: Output written to review.md (2.4 KB) ``` ##### agents actor add 
agents actor add --config|-c <FILE> [--update]
**Purpose** Add a new actor configuration, or replace an existing one with `--update`. The actor is fully defined by the YAML configuration file specified with `--config`. If a local actor with the same name already exists, the command fails unless the `--update` flag is provided, which replaces the existing actor. **Arguments** - `--config/-c FILE`: Actor config file (required). The file must fully define the actor, including the `name` field which determines the actor's registered name. - `--update`: Replace an existing local actor with the same name. Without this flag, attempting to add an actor whose name is already registered will fail. **Examples** === "Rich" 

    $ agents actor add --config ./actors/reviewer.yaml

    ╭─ Actor Added ────────╮
    │ Name: local/reviewer │
    │ Provider: openai     │
    │ Model: gpt-4         │
    │ Default: yes         │
    │ Unsafe: no           │
    │ Type: graph          │
    ╰──────────────────────╯

    ╭─ Config ─────────────────────╮
    │ Path: ./actors/reviewer.yaml │
    │ Hash: 8b3f3d2                │
    │ Options: 4                   │
    │ Nodes: 3                     │
    │ Edges: 4                     │
    ╰──────────────────────────────╯

    ╭─ Capabilities ───────╮
    │ - code review        │
    │ - diff summarization │
    │ - lint guidance      │
    ╰──────────────────────╯

    ╭─ Tools ────────────────────────╮
    │ Tool          Read-Only  Safe  │
    │ ────────────  ─────────  ────  │
    │ read_file     yes        yes   │
    │ search_files  yes        yes   │
    │ git_diff      yes        yes   │
    ╰────────────────────────────────╯

    ✓ OK Actor added
=== "Plain" ``` $ agents actor add --config ./actors/reviewer.yaml Actor Added Name: local/reviewer Provider: openai Model: gpt-4 Default: yes Unsafe: no Type: graph Config Path: ./actors/reviewer.yaml Hash: 8b3f3d2 Options: 4 Nodes: 3 Edges: 4 Capabilities - code review - diff summarization - lint guidance Tools Tool Read-Only Safe ------------ --------- ---- read_file yes yes search_files yes yes git_diff yes yes [OK] Actor added ``` === "JSON" ```json { "command": "agents actor add --config ./actors/reviewer.yaml", "status": "ok", "exit_code": 0, "data": { "actor_added": { "name": "local/reviewer", "provider": "openai", "model": "gpt-4", "default": true, "unsafe": false, "type": "graph" }, "config": { "path": "./actors/reviewer.yaml", "hash": "8b3f3d2", "options": 4, "nodes": 3, "edges": 4 }, "capabilities": [ "code review", "diff summarization", "lint guidance" ], "tools": [ { "tool": "read_file", "read_only": true, "safe": true }, { "tool": "search_files", "read_only": true, "safe": true }, { "tool": "git_diff", "read_only": true, "safe": true } ] }, "timing": { "duration_ms": 95 }, "messages": [ { "level": "ok", "text": "Actor added" } ] } ``` === "YAML" ```yaml command: agents actor add --config ./actors/reviewer.yaml status: ok exit_code: 0 data: actor_added: name: local/reviewer provider: openai model: gpt-4 default: true unsafe: false type: graph config: path: ./actors/reviewer.yaml hash: 8b3f3d2 options: 4 nodes: 3 edges: 4 capabilities: - code review - diff summarization - lint guidance tools: - tool: read_file read_only: true safe: true - tool: search_files read_only: true safe: true - tool: git_diff read_only: true safe: true timing: duration_ms: 95 messages: - level: ok text: Actor added ``` Attempting to register an actor that already exists (without `--update`): === "Rich" 

    $ agents actor add --config ./actors/reviewer.yaml

    ╭─ Error ─────────────────────────────────────────────────╮
    │ Actor already exists: local/reviewer                    │
    │ Registered: 2026-02-07 14:22                            │
    │ Use --update to replace the existing actor definition.  │
    ╰─────────────────────────────────────────────────────────╯

    ✗ ERROR Actor already registered — use --update to replace
=== "Plain" ``` $ agents actor add --config ./actors/reviewer.yaml Error Actor already exists: local/reviewer Registered: 2026-02-07 14:22 Use --update to replace the existing actor definition. [ERROR] Actor already registered -- use --update to replace ``` === "JSON" ```json { "command": "agents actor add --config ./actors/reviewer.yaml", "status": "error", "exit_code": 1, "data": { "error": { "message": "Actor already exists: local/reviewer", "registered": "2026-02-07T14:22:00Z", "hint": "Use --update to replace the existing actor definition." } }, "timing": { "duration_ms": 42 }, "messages": [ { "level": "error", "text": "Actor already registered -- use --update to replace" } ] } ``` === "YAML" ```yaml command: agents actor add --config ./actors/reviewer.yaml status: error exit_code: 1 data: error: message: "Actor already exists: local/reviewer" registered: "2026-02-07T14:22:00Z" hint: Use --update to replace the existing actor definition. timing: duration_ms: 42 messages: - level: error text: Actor already registered -- use --update to replace ``` Updating an existing actor with `--update`: === "Rich" 

    $ agents actor add --config ./actors/reviewer.yaml --update

    ╭─ Actor Updated ─────────────────────╮
    │ Name: local/reviewer                │
    │ Type: agent                         │
    │ Status: updated                     │
    ╰─────────────────────────────────────╯

    ╭─ Changes ────────────────────────────╮
    │ Skills: +1 (local/code-analysis)     │
    │ Model: unchanged                     │
    │ Graph: updated                       │
    ╰──────────────────────────────────────╯

    ✓ OK Actor updated
=== "Plain" ``` $ agents actor add --config ./actors/reviewer.yaml --update Actor Updated Name: local/reviewer Type: agent Status: updated Changes Skills: +1 (local/code-analysis) Model: unchanged Graph: updated [OK] Actor updated ``` === "JSON" ```json { "command": "agents actor add --config ./actors/reviewer.yaml --update", "status": "ok", "exit_code": 0, "data": { "actor_updated": { "name": "local/reviewer", "type": "agent", "status": "updated" }, "changes": { "skills": "+1 (local/code-analysis)", "model": "unchanged", "graph": "updated" } }, "timing": { "duration_ms": 88 }, "messages": [ { "level": "ok", "text": "Actor updated" } ] } ``` === "YAML" ```yaml command: agents actor add --config ./actors/reviewer.yaml --update status: ok exit_code: 0 data: actor_updated: name: local/reviewer type: agent status: updated changes: skills: "+1 (local/code-analysis)" model: unchanged graph: updated timing: duration_ms: 88 messages: - level: ok text: Actor updated ``` ##### agents actor remove 
agents actor remove <NAME>
!!! warning "Destructive Operation" Removes a custom actor registration. Active plans and actions referencing this actor will lose their actor binding. Check the **Impact** section in the output to verify no active plans or sessions are affected. **Arguments** - ``: Actor name. **Examples** === "Rich" 

    $ agents actor remove local/reviewer

    ╭─ Actor Removed ──────╮
    │ Name: local/reviewer │
    │ Provider: openai     │
    │ Model: gpt-4         │
    ╰──────────────────────╯

    ╭─ Impact ───────────────────────────────────╮
    │ Sessions: 0 affected                       │
    │ Active Plans: 0 affected                   │
    │ Actions Referencing: 0                     │
    ╰────────────────────────────────────────────╯

    ╭─ Cleanup ──────────────╮
    │ Config: kept on disk   │
    │ Contexts: 1 orphaned   │
    ╰────────────────────────╯

    ✓ OK Actor removed
=== "Plain" ``` $ agents actor remove local/reviewer Actor Removed Name: local/reviewer Provider: openai Model: gpt-4 Impact Sessions: 0 affected Active Plans: 0 affected Actions Referencing: 0 Cleanup Config: kept on disk Contexts: 1 orphaned [OK] Actor removed ``` === "JSON" ```json { "command": "agents actor remove local/reviewer", "status": "ok", "exit_code": 0, "data": { "actor_removed": { "name": "local/reviewer", "provider": "openai", "model": "gpt-4" }, "impact": { "sessions": 0, "active_plans": 0, "actions_referencing": 0 }, "cleanup": { "config": "kept on disk", "contexts": "1 orphaned" } }, "timing": { "duration_ms": 65 }, "messages": [ { "level": "ok", "text": "Actor removed" } ] } ``` === "YAML" ```yaml command: agents actor remove local/reviewer status: ok exit_code: 0 data: actor_removed: name: local/reviewer provider: openai model: gpt-4 impact: sessions: 0 active_plans: 0 actions_referencing: 0 cleanup: config: kept on disk contexts: 1 orphaned timing: duration_ms: 65 messages: - level: ok text: Actor removed ``` ##### agents actor list 
agents actor list
**Purpose** List all actors. **Arguments** None. **Examples** === "Rich" 

    $ agents actor list

    ╭─ Actors ──────────────────────────────────────────────────────────────╮
    │ Name            Provider   Model       Default  Built-in  Unsafe      │
    │ ──────────────  ─────────  ──────────  ───────  ────────  ──────      │
    │ local/reviewer  openai     gpt-4       ✓                  no          │
    │ openai/gpt-4    openai     gpt-4                ✓         no          │
    │ anthropic/3.5   anthropic  claude-3.5           ✓         no          │
    ╰───────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ──────────────╮
    │ Total: 3               │
    │ Built-in: 2            │
    │ Custom: 1              │
    │ Unsafe: 0              │
    │ Providers Used: 2      │
    ╰────────────────────────╯

    ✓ OK 3 actors listed
=== "Plain" ``` $ agents actor list Actors Name Provider Model Default Built-in Unsafe -------------- --------- ---------- ------- -------- ------ local/reviewer openai gpt-4 yes no openai/gpt-4 openai gpt-4 yes no anthropic/3.5 anthropic claude-3.5 yes no Summary Total: 3 Built-in: 2 Custom: 1 Unsafe: 0 Providers Used: 2 [OK] 3 actors listed ``` === "JSON" ```json { "command": "agents actor list", "status": "ok", "exit_code": 0, "data": { "actors": [ { "name": "local/reviewer", "provider": "openai", "model": "gpt-4", "default": true, "builtin": false, "unsafe": false }, { "name": "openai/gpt-4", "provider": "openai", "model": "gpt-4", "default": false, "builtin": true, "unsafe": false }, { "name": "anthropic/3.5", "provider": "anthropic", "model": "claude-3.5", "default": false, "builtin": true, "unsafe": false } ], "summary": { "total": 3, "builtin": 2, "custom": 1, "unsafe": 0, "providers_used": 2 } }, "timing": { "duration_ms": 55 }, "messages": [ { "level": "ok", "text": "3 actors listed" } ] } ``` === "YAML" ```yaml command: agents actor list status: ok exit_code: 0 data: actors: - name: local/reviewer provider: openai model: gpt-4 default: true builtin: false unsafe: false - name: openai/gpt-4 provider: openai model: gpt-4 default: false builtin: true unsafe: false - name: anthropic/3.5 provider: anthropic model: claude-3.5 default: false builtin: true unsafe: false summary: total: 3 builtin: 2 custom: 1 unsafe: 0 providers_used: 2 timing: duration_ms: 55 messages: - level: ok text: 3 actors listed ``` ##### agents actor show 
agents actor show <NAME>
**Purpose** Show details for a single actor. **Arguments** - ``: Actor name. **Examples** === "Rich" 

    $ agents actor show local/reviewer

    ╭─ Actor Details ────────────────────╮
    │ Name: local/reviewer               │
    │ Provider: openai                   │
    │ Model: gpt-4                       │
    │ Default: yes                       │
    │ Built-in: no                       │
    │ Unsafe: no                         │
    │ Type: graph                        │
    │ Created: 2026-02-08 12:35          │
    │ Updated: 2026-02-08 12:40          │
    │ Config: ./actors/reviewer.yaml     │
    │ Config Hash: 9c4e2a1               │
    ╰────────────────────────────────────╯

    ╭─ Options ──────────╮
    │ - temperature: 0.2 │
    │ - max_tokens: 2048 │
    │ - top_p: 1.0       │
    ╰────────────────────╯

    ╭─ Graph Structure ─╮
    │ Nodes: 3          │
    │ Edges: 4          │
    │ Entry: analyze    │
    │ Exit: report      │
    ╰───────────────────╯

    ╭─ Tools ────────────────────────╮
    │ Tool          Read-Only  Safe  │
    │ ────────────  ─────────  ────  │
    │ read_file     yes        yes   │
    │ search_files  yes        yes   │
    │ git_diff      yes        yes   │
    ╰────────────────────────────────╯

    ╭─ Access ────────────╮
    │ Unsafe: no          │
    │ Filesystem: allowed │
    │ Network: restricted │
    ╰─────────────────────╯

    ╭─ Usage ─────────────────────────────────────────╮
    │ Referenced by Actions: 1 (local/code-coverage)  │
    │ Active in Sessions: 0                           │
    │ Total Runs: 14                                  │
    │ Avg Cost/Run: $0.0032                           │
    ╰─────────────────────────────────────────────────╯

    ✓ OK Actor loaded
=== "Plain" ``` $ agents actor show local/reviewer Actor Details Name: local/reviewer Provider: openai Model: gpt-4 Default: yes Built-in: no Unsafe: no Type: graph Created: 2026-02-08 12:35 Updated: 2026-02-08 12:40 Config: ./actors/reviewer.yaml Config Hash: 9c4e2a1 Options - temperature: 0.2 - max_tokens: 2048 - top_p: 1.0 Graph Structure Nodes: 3 Edges: 4 Entry: analyze Exit: report Tools Tool Read-Only Safe ------------ --------- ---- read_file yes yes search_files yes yes git_diff yes yes Access Unsafe: no Filesystem: allowed Network: restricted Usage Referenced by Actions: 1 (local/code-coverage) Active in Sessions: 0 Total Runs: 14 Avg Cost/Run: $0.0032 [OK] Actor loaded ``` === "JSON" ```json { "command": "agents actor show local/reviewer", "status": "ok", "exit_code": 0, "data": { "actor_details": { "name": "local/reviewer", "provider": "openai", "model": "gpt-4", "default": true, "builtin": false, "unsafe": false, "type": "graph", "created": "2026-02-08T12:35:00Z", "updated": "2026-02-08T12:40:00Z", "config": "./actors/reviewer.yaml", "config_hash": "9c4e2a1" }, "options": { "temperature": 0.2, "max_tokens": 2048, "top_p": 1.0 }, "graph_structure": { "nodes": 3, "edges": 4, "entry": "analyze", "exit": "report" }, "tools": [ { "tool": "read_file", "read_only": true, "safe": true }, { "tool": "search_files", "read_only": true, "safe": true }, { "tool": "git_diff", "read_only": true, "safe": true } ], "access": { "unsafe": false, "filesystem": "allowed", "network": "restricted" }, "usage": { "referenced_by_actions": "1 (local/code-coverage)", "active_in_sessions": 0, "total_runs": 14, "avg_cost_per_run": "$0.0032" } }, "timing": { "duration_ms": 78 }, "messages": [ { "level": "ok", "text": "Actor loaded" } ] } ``` === "YAML" ```yaml command: agents actor show local/reviewer status: ok exit_code: 0 data: actor_details: name: local/reviewer provider: openai model: gpt-4 default: true builtin: false unsafe: false type: graph created: "2026-02-08T12:35:00Z" updated: "2026-02-08T12:40:00Z" config: ./actors/reviewer.yaml config_hash: 9c4e2a1 options: temperature: 0.2 max_tokens: 2048 top_p: 1.0 graph_structure: nodes: 3 edges: 4 entry: analyze exit: report tools: - tool: read_file read_only: true safe: true - tool: search_files read_only: true safe: true - tool: git_diff read_only: true safe: true access: unsafe: false filesystem: allowed network: restricted usage: referenced_by_actions: 1 (local/code-coverage) active_in_sessions: 0 total_runs: 14 avg_cost_per_run: "$0.0032" timing: duration_ms: 78 messages: - level: ok text: Actor loaded ``` ##### agents actor context **Purpose** Manage manual context for actor runs. These commands mirror the legacy context behavior but are scoped to an actor context name. ###### agents actor context remove 
agents actor context remove [--yes|-y] (--all|-a|<NAME>)
!!! warning "Context Data Loss" Remove files or directories from an actor context. Use `--all` to clear all contexts at once. Context data is not recoverable after removal. **Arguments** - ``: Context name (positional argument). Use --all/-a to target all contexts. - `--all, -a`: Target all contexts instead of a named one. - `--yes, -y`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents actor context remove docs

    ╭─ Context Removed ───────────╮
    │ Context: docs               │
    │ Status: removed             │
    ╰─────────────────────────────╯

    ╭─ Stats ───────────────────╮
    │ Remaining Size: 48 KB     │
    │ Updated: 2026-02-08 13:06 │
    ╰───────────────────────────╯

    ✓ OK Context updated
=== "Plain" ``` $ agents actor context remove docs Context Removed Context: docs Status: removed Stats Remaining Size: 48 KB Updated: 2026-02-08 13:06 [OK] Context updated ``` === "JSON" ```json { "command": "agents actor context remove docs", "status": "ok", "exit_code": 0, "data": { "context_removed": { "context": "docs", "status": "removed" }, "stats": { "remaining_size_kb": 48, "updated": "2026-02-08T13:06:00Z" } }, "timing": { "duration_ms": 65 }, "messages": [{ "level": "ok", "text": "Context updated" }] } ``` === "YAML" ```yaml command: agents actor context remove docs status: ok exit_code: 0 data: context_removed: context: docs status: removed stats: remaining_size_kb: 48 updated: "2026-02-08T13:06:00Z" timing: duration_ms: 65 messages: - level: ok text: Context updated ``` ###### agents actor context list 
agents actor context list [<REGEX>]
**Purpose** List files stored in an actor context. **Arguments** - `[REGEX]`: Optional regex filter for context names. **Examples** === "Rich" 

    $ agents actor context list docs

    ╭─ Context Files ──────────────────────────────╮
    │ Name              Type  Size     Added       │
    │ ────────────────  ────  ───────  ──────────  │
    │ README.md         file  4.2 KB   02-08 12:10 │
    │ docs/overview.md  file  12.8 KB  02-08 12:10 │
    │ docs/cli.md       file  9.5 KB   02-08 12:10 │
    ╰──────────────────────────────────────────────╯

    ╭─ Stats ───────────────────────╮
    │ Total Files: 3                │
    │ Total Size: 26.5 KB           │
    │ Estimated Tokens: ~6,600      │
    │ Languages: Markdown           │
    ╰───────────────────────────────╯

    ✓ OK 3 files listed
=== "Plain" ``` $ agents actor context list docs Context Files Name Type Size Added ---------------- ---- ------- ---------- README.md file 4.2 KB 02-08 12:10 docs/overview.md file 12.8 KB 02-08 12:10 docs/cli.md file 9.5 KB 02-08 12:10 Stats Total Files: 3 Total Size: 26.5 KB Estimated Tokens: ~6,600 Languages: Markdown [OK] 3 files listed ``` === "JSON" ```json { "command": "agents actor context list docs", "status": "ok", "exit_code": 0, "data": { "context_files": [ { "name": "README.md", "type": "file", "size_kb": 4.2, "added": "2026-02-08T12:10:00Z" }, { "name": "docs/overview.md", "type": "file", "size_kb": 12.8, "added": "2026-02-08T12:10:00Z" }, { "name": "docs/cli.md", "type": "file", "size_kb": 9.5, "added": "2026-02-08T12:10:00Z" } ], "stats": { "total_files": 3, "total_size_kb": 26.5, "estimated_tokens": 6600, "languages": ["Markdown"] } }, "timing": { "duration_ms": 35 }, "messages": [{ "level": "ok", "text": "3 files listed" }] } ``` === "YAML" ```yaml command: agents actor context list docs status: ok exit_code: 0 data: context_files: - name: README.md type: file size_kb: 4.2 added: "2026-02-08T12:10:00Z" - name: docs/overview.md type: file size_kb: 12.8 added: "2026-02-08T12:10:00Z" - name: docs/cli.md type: file size_kb: 9.5 added: "2026-02-08T12:10:00Z" stats: total_files: 3 total_size_kb: 26.5 estimated_tokens: 6600 languages: - Markdown timing: duration_ms: 35 messages: - level: ok text: 3 files listed ``` ###### agents actor context show 
agents actor context show <NAME>
**Purpose** Show content of a file in an actor context. **Arguments** - ``: Context name (positional argument). **Examples** === "Rich" 

    $ agents actor context show docs

    ╭─ Context Summary ───────────╮
    │ Context: docs               │
    │ Files: 3                    │
    │ Total Size: 26.5 KB         │
    │ Estimated Tokens: ~6,600    │
    │ Created: 2026-02-08 12:10   │
    ╰─────────────────────────────╯

    ✓ OK Context displayed
=== "Plain" ``` $ agents actor context show docs Context Summary Context: docs Files: 3 Total Size: 26.5 KB Estimated Tokens: ~6,600 Created: 2026-02-08 12:10 [OK] Context displayed ``` === "JSON" ```json { "command": "agents actor context show docs", "status": "ok", "exit_code": 0, "data": { "context_summary": { "context": "docs", "files": 3, "total_size_kb": 26.5, "estimated_tokens": 6600, "created": "2026-02-08T12:10:00Z" } }, "timing": { "duration_ms": 45 }, "messages": [{ "level": "ok", "text": "Context displayed" }] } ``` === "YAML" ```yaml command: agents actor context show docs status: ok exit_code: 0 data: context_summary: context: docs files: 3 total_size_kb: 26.5 estimated_tokens: 6600 created: "2026-02-08T12:10:00Z" timing: duration_ms: 45 messages: - level: ok text: Context displayed ``` ###### agents actor context export 
agents actor context export (--output|-o) <FILE> <NAME>
**Purpose** Export a context as JSON. **Arguments** - ``: Context name (positional argument). - `--output/-o FILE`: Output file path (required). **Examples** === "Rich" 

    $ agents actor context export --output /tmp/docs-context.json docs

    ╭─ Context Export ───────────────╮
    │ Context: docs                  │
    │ Output: /tmp/docs-context.json │
    │ Items: 12                      │
    │ Size: 48 KB                    │
    ╰────────────────────────────────╯

    ╭─ Integrity ──────────────────╮
    │ Checksum: sha256:19b2...a7d0 │
    │ Compressed: no               │
    ╰──────────────────────────────╯

    ✓ OK Export completed
=== "Plain" ``` $ agents actor context export --output /tmp/docs-context.json docs Context Export Context: docs Output: /tmp/docs-context.json Items: 12 Size: 48 KB Integrity Checksum: sha256:19b2...a7d0 Compressed: no [OK] Export completed ``` === "JSON" ```json { "command": "agents actor context export --output /tmp/docs-context.json docs", "status": "ok", "exit_code": 0, "data": { "context_export": { "context": "docs", "output": "/tmp/docs-context.json", "items": 12, "size_kb": 48 }, "integrity": { "checksum": "sha256:19b2...a7d0", "compressed": false } }, "timing": { "duration_ms": 180 }, "messages": [{ "level": "ok", "text": "Export completed" }] } ``` === "YAML" ```yaml command: agents actor context export --output /tmp/docs-context.json docs status: ok exit_code: 0 data: context_export: context: docs output: /tmp/docs-context.json items: 12 size_kb: 48 integrity: checksum: "sha256:19b2...a7d0" compressed: false timing: duration_ms: 180 messages: - level: ok text: Export completed ``` ###### agents actor context import 
agents actor context import [--update] (--input|-i) <FILE> [<NAME>]
**Purpose** Import a context from JSON. **Arguments** - `[NAME]`: Context name (optional, inferred from file if omitted). - `--input/-i FILE`: Input JSON file (required). - `--update`: Replace an existing context with the same name. **Examples** === "Rich" 

    $ agents actor context import --input /tmp/docs-context.json docs

    ╭─ Context Import ──────────────╮
    │ Context: docs                 │
    │ Input: /tmp/docs-context.json │
    │ Items: 12                     │
    ╰───────────────────────────────╯

    ╭─ Merge ───────────╮
    │ Strategy: replace │
    │ Conflicts: 0      │
    ╰───────────────────╯

    ✓ OK Import completed
=== "Plain" ``` $ agents actor context import --input /tmp/docs-context.json docs Context Import Context: docs Input: /tmp/docs-context.json Items: 12 Merge Strategy: replace Conflicts: 0 [OK] Import completed ``` === "JSON" ```json { "command": "agents actor context import --input /tmp/docs-context.json docs", "status": "ok", "exit_code": 0, "data": { "context_import": { "context": "docs", "input": "/tmp/docs-context.json", "items": 12 }, "merge": { "strategy": "replace", "conflicts": 0 } }, "timing": { "duration_ms": 210 }, "messages": [{ "level": "ok", "text": "Import completed" }] } ``` === "YAML" ```yaml command: agents actor context import --input /tmp/docs-context.json docs status: ok exit_code: 0 data: context_import: context: docs input: /tmp/docs-context.json items: 12 merge: strategy: replace conflicts: 0 timing: duration_ms: 210 messages: - level: ok text: Import completed ``` ###### agents actor context clear 
agents actor context clear [--yes|-y] (--all|-a|<NAME>)
**Purpose** Clear all files from a context but keep the context itself. **Arguments** - ``: Context name (positional argument). Use --all/-a to target all contexts. - `--all, -a`: Target all contexts instead of a named one. - `--yes, -y`: Skip confirmation. **Examples** === "Rich" 

    $ agents actor context clear docs

    Clear context docs? [y/N]: y

    ╭─ Context Cleared ────╮
    │ Context: docs        │
    │ Items: 12 removed    │
    │ Storage: 48 KB freed │
    ╰──────────────────────╯

    ╭─ Retention ────────╮
    │ Context: preserved │
    │ Files: removed     │
    ╰────────────────────╯

    ✓ OK Context cleared
=== "Plain" ``` $ agents actor context clear docs Clear context docs? [y/N]: y Context Cleared Context: docs Items: 12 removed Storage: 48 KB freed Retention Context: preserved Files: removed [OK] Context cleared ``` === "JSON" ```json { "command": "agents actor context clear docs", "status": "ok", "exit_code": 0, "data": { "context_cleared": { "context": "docs", "items": "12 removed", "storage": "48 KB freed" }, "retention": { "context": "preserved", "files": "removed" } }, "timing": { "duration_ms": 85 }, "messages": [{ "level": "ok", "text": "Context cleared" }] } ``` === "YAML" ```yaml command: agents actor context clear docs status: ok exit_code: 0 data: context_cleared: context: docs items: 12 removed storage: 48 KB freed retention: context: preserved files: removed timing: duration_ms: 85 messages: - level: ok text: Context cleared ``` #### agents skill !!! info "Purpose" Manage skills — reusable, namespaced collections of tools. Skills are defined in their own YAML configuration files and registered in the system through these commands. Once registered, skills can be referenced by actors. ##### agents skill add 
agents skill add --config|-c <FILE> [--update]
**Purpose** Register a new skill. The skill is fully defined by the YAML configuration file specified with `--config`. If a skill with the same name already exists, the command fails unless the `--update` flag is provided, which allows overwriting the existing registration with the new configuration. **Arguments** - `--config/-c FILE`: Path to the skill YAML configuration file (required). The file must fully define the skill, including the `name` field which determines the skill's registered name. - `--update`: Allow overwriting an existing skill registration. Without this flag, attempting to add a skill whose name is already registered will fail. **Examples** Registering a new skill: === "Rich" 

    $ agents skill add --config ./skills/devops-toolkit.yaml

    ╭─ Skill Registered ────────────────────────╮
    │ Name: local/devops-toolkit                │
    │ Description: Full-stack development tools │
    │ Config: ./skills/devops-toolkit.yaml      │
    │ Created: 2026-02-08 13:10                 │
    ╰───────────────────────────────────────────╯

    ╭─ Includes ────────────────────╮
    │ local/file-ops (registered)   │
    │ local/git-ops (registered)    │
    │ local/github (registered)     │
    ╰───────────────────────────────╯

    ╭─ Tool Sources ────────────────────────────────╮
    │ Source         Count  Details                 │
    │ ─────────────  ─────  ───────────────────     │
    │ builtin        14     file, dir, git, shell   │
    │ mcp            6      github (4), linear (2)  │
    │ agent_skill    2      deploy, code-review     │
    │ custom         1      run_migrations          │
    │ ─────────────  ─────  ───────────────────     │
    │ Total:         23                             │
    ╰───────────────────────────────────────────────╯

    ╭─ MCP Servers ────────────────────╮
    │ linear: validated (2 tools)      │
    ╰──────────────────────────────────╯

    ✓ OK Skill registered with 23 tools
=== "Plain" ``` $ agents skill add --config ./skills/devops-toolkit.yaml Skill Registered Name: local/devops-toolkit Description: Full-stack development tools Config: ./skills/devops-toolkit.yaml Created: 2026-02-08 13:10 Includes local/file-ops (registered) local/git-ops (registered) local/github (registered) Tool Sources Source Count Details ------------- ----- ------------------- builtin 14 file, dir, git, shell mcp 6 github (4), linear (2) agent_skill 2 deploy, code-review custom 1 run_migrations ------------- ----- ------------------- Total: 23 MCP Servers linear: validated (2 tools) [OK] Skill registered with 23 tools ``` === "JSON" ```json { "command": "skill add --config ./skills/devops-toolkit.yaml", "status": "ok", "exit_code": 0, "data": { "skill": { "name": "local/devops-toolkit", "description": "Full-stack development tools", "config": "./skills/devops-toolkit.yaml", "created": "2026-02-08T13:10:00Z" }, "includes": [ { "name": "local/file-ops", "status": "registered" }, { "name": "local/git-ops", "status": "registered" }, { "name": "local/github", "status": "registered" } ], "tool_sources": [ { "source": "builtin", "count": 14, "details": "file, dir, git, shell" }, { "source": "mcp", "count": 6, "details": "github (4), linear (2)" }, { "source": "agent_skill", "count": 2, "details": "deploy, code-review" }, { "source": "custom", "count": 1, "details": "run_migrations" } ], "total_tools": 23, "mcp_servers": [ { "name": "linear", "status": "validated", "tools": 2 } ] }, "timing": { "duration_ms": 150 }, "messages": [ { "level": "ok", "text": "Skill registered with 23 tools" } ] } ``` === "YAML" ```yaml command: skill add --config ./skills/devops-toolkit.yaml status: ok exit_code: 0 data: skill: name: local/devops-toolkit description: Full-stack development tools config: ./skills/devops-toolkit.yaml created: "2026-02-08T13:10:00Z" includes: - name: local/file-ops status: registered - name: local/git-ops status: registered - name: local/github status: registered tool_sources: - source: builtin count: 14 details: file, dir, git, shell - source: mcp count: 6 details: github (4), linear (2) - source: agent_skill count: 2 details: deploy, code-review - source: custom count: 1 details: run_migrations total_tools: 23 mcp_servers: - name: linear status: validated tools: 2 timing: duration_ms: 150 messages: - level: ok text: Skill registered with 23 tools ``` Attempting to add a skill that already exists (without `--update`): === "Rich" 

    $ agents skill add --config ./skills/devops-toolkit-v2.yaml

    ✗ Error: Skill 'local/devops-toolkit' is already registered.

    To overwrite the existing configuration, re-run with --update:

      agents skill add --config ./skills/devops-toolkit-v2.yaml --update
=== "Plain" ``` $ agents skill add --config ./skills/devops-toolkit-v2.yaml Error: Skill 'local/devops-toolkit' is already registered. To overwrite the existing configuration, re-run with --update: agents skill add --config ./skills/devops-toolkit-v2.yaml --update ``` === "JSON" ```json { "command": "skill add --config ./skills/devops-toolkit-v2.yaml", "status": "error", "exit_code": 1, "data": { "skill_name": "local/devops-toolkit", "reason": "already registered" }, "timing": { "duration_ms": 30 }, "messages": [ { "level": "error", "text": "Skill 'local/devops-toolkit' is already registered." }, { "level": "info", "text": "To overwrite the existing configuration, re-run with --update" } ] } ``` === "YAML" ```yaml command: skill add --config ./skills/devops-toolkit-v2.yaml status: error exit_code: 1 data: skill_name: local/devops-toolkit reason: already registered timing: duration_ms: 30 messages: - level: error text: "Skill 'local/devops-toolkit' is already registered." - level: info text: To overwrite the existing configuration, re-run with --update ``` Updating an existing skill with `--update`: === "Rich" 

    $ agents skill add --config ./skills/devops-toolkit-v2.yaml --update

    ╭─ Skill Updated ───────────────────────────╮
    │ Name: local/devops-toolkit                │
    │ Description: Full-stack development tools │
    │ Updated: 2026-02-08 14:22                 │
    ╰───────────────────────────────────────────╯

    ╭─ Changes ─────────────────────╮
    │ Tools Added: 2                │
    │ Tools Removed: 0              │
    │ Tools Modified: 1             │
    │ Includes Changed: no          │
    │ MCP Servers Changed: no       │
    ╰───────────────────────────────╯

    ╭─ Affected Actors ─────────────────────────────╮
    │ Warning: 2 actors reference this skill:       │
    │ - local/code-assistant                        │
    │ - local/full-stack-assistant                  │
    │ These actors will pick up changes on next use │
    ╰───────────────────────────────────────────────╯

    ✓ OK Skill updated (23 → 25 tools)
=== "Plain" ``` $ agents skill add --config ./skills/devops-toolkit-v2.yaml --update Skill Updated Name: local/devops-toolkit Description: Full-stack development tools Updated: 2026-02-08 14:22 Changes Tools Added: 2 Tools Removed: 0 Tools Modified: 1 Includes Changed: no MCP Servers Changed: no Affected Actors Warning: 2 actors reference this skill: - local/code-assistant - local/full-stack-assistant These actors will pick up changes on next use [OK] Skill updated (23 -> 25 tools) ``` === "JSON" ```json { "command": "skill add --config ./skills/devops-toolkit-v2.yaml --update", "status": "ok", "exit_code": 0, "data": { "skill": { "name": "local/devops-toolkit", "description": "Full-stack development tools", "updated": "2026-02-08T14:22:00Z" }, "changes": { "tools_added": 2, "tools_removed": 0, "tools_modified": 1, "includes_changed": false, "mcp_servers_changed": false }, "affected_actors": [ "local/code-assistant", "local/full-stack-assistant" ], "tool_count": { "before": 23, "after": 25 } }, "timing": { "duration_ms": 180 }, "messages": [ { "level": "ok", "text": "Skill updated (23 -> 25 tools)" }, { "level": "warn", "text": "2 actors reference this skill and will pick up changes on next use" } ] } ``` === "YAML" ```yaml command: skill add --config ./skills/devops-toolkit-v2.yaml --update status: ok exit_code: 0 data: skill: name: local/devops-toolkit description: Full-stack development tools updated: "2026-02-08T14:22:00Z" changes: tools_added: 2 tools_removed: 0 tools_modified: 1 includes_changed: false mcp_servers_changed: false affected_actors: - local/code-assistant - local/full-stack-assistant tool_count: before: 23 after: 25 timing: duration_ms: 180 messages: - level: ok text: "Skill updated (23 -> 25 tools)" - level: warn text: 2 actors reference this skill and will pick up changes on next use ``` ##### agents skill remove 
agents skill remove [--yes|-y] <NAME>
!!! warning "Cascading Impact" Removing a skill ==unregisters all tools== provided by that skill and closes any associated MCP server connections. Other skills that include this skill, and actors that reference it, will lose access to those tools. **Arguments** - ``: Skill name to remove. - `--yes`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents skill remove local/devops-toolkit

    Remove skill local/devops-toolkit? [y/N]: y

    ╭─ Skill Removed ──────────────────────╮
    │ Name: local/devops-toolkit           │
    │ Tools: 23 removed from registry      │
    │ MCP Servers: 1 connection closed     │
    ╰──────────────────────────────────────╯

    ╭─ Dependency Check ─────────────────────────────────╮
    │ Warning: 1 skill includes this skill:              │
    │ - local/full-stack-dev (will lose devops tools)    │
    │ Warning: 2 actors reference this skill:            │
    │ - local/code-assistant                             │
    │ - local/full-stack-assistant                       │
    ╰────────────────────────────────────────────────────╯

    ✓ OK Skill removed
=== "Plain" ``` $ agents skill remove local/devops-toolkit Remove skill local/devops-toolkit? [y/N]: y Skill Removed Name: local/devops-toolkit Tools: 23 removed from registry MCP Servers: 1 connection closed Dependency Check Warning: 1 skill includes this skill: - local/full-stack-dev (will lose devops tools) Warning: 2 actors reference this skill: - local/code-assistant - local/full-stack-assistant [OK] Skill removed ``` === "JSON" ```json { "command": "skill remove local/devops-toolkit", "status": "ok", "exit_code": 0, "data": { "skill": { "name": "local/devops-toolkit", "tools_removed": 23, "mcp_servers_closed": 1 }, "dependency_check": { "including_skills": [ { "name": "local/full-stack-dev", "impact": "will lose devops tools" } ], "referencing_actors": [ "local/code-assistant", "local/full-stack-assistant" ] } }, "timing": { "duration_ms": 95 }, "messages": [ { "level": "ok", "text": "Skill removed" }, { "level": "warn", "text": "1 skill includes this skill" }, { "level": "warn", "text": "2 actors reference this skill" } ] } ``` === "YAML" ```yaml command: skill remove local/devops-toolkit status: ok exit_code: 0 data: skill: name: local/devops-toolkit tools_removed: 23 mcp_servers_closed: 1 dependency_check: including_skills: - name: local/full-stack-dev impact: will lose devops tools referencing_actors: - local/code-assistant - local/full-stack-assistant timing: duration_ms: 95 messages: - level: ok text: Skill removed - level: warn text: 1 skill includes this skill - level: warn text: 2 actors reference this skill ``` ##### agents skill list 
agents skill list [(--namespace|-n) <NS>] [--source <SOURCE>]
**Purpose** List registered skills with optional filters. **Arguments** - `--namespace/-n NS`: Filter by namespace. - `--source SOURCE`: Filter by tool source type (mcp, agent_skill, builtin, custom). **Examples** === "Rich" 

    $ agents skill list

    ╭─ Skills ────────────────────────────────────────────────────────────╮
    │ Name                    Tools  Includes  Sources                    │
    │ ──────────────────────  ─────  ────────  ──────────────────────     │
    │ local/file-ops          9      0         builtin                    │
    │ local/git-ops           4      0         builtin                    │
    │ local/github            4      0         mcp                        │
    │ local/devops-toolkit    23     3         builtin, mcp, custom       │
    │ local/full-stack-dev    25     4         builtin, mcp, custom       │
    ╰─────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ─────────╮
    │ Total: 5          │
    │ Local: 5          │
    │ Server: 0         │
    │ Total Tools: 28   │
    ╰───────────────────╯

    ✓ OK 5 skills listed
=== "Plain" ``` $ agents skill list Skills Name Tools Includes Sources ---------------------- ----- -------- ---------------------- local/file-ops 9 0 builtin local/git-ops 4 0 builtin local/github 4 0 mcp local/devops-toolkit 23 3 builtin, mcp, custom local/full-stack-dev 25 4 builtin, mcp, custom Summary Total: 5 Local: 5 Server: 0 Total Tools: 28 [OK] 5 skills listed ``` === "JSON" ```json { "command": "skill list", "status": "ok", "exit_code": 0, "data": { "skills": [ { "name": "local/file-ops", "tools": 9, "includes": 0, "sources": ["builtin"] }, { "name": "local/git-ops", "tools": 4, "includes": 0, "sources": ["builtin"] }, { "name": "local/github", "tools": 4, "includes": 0, "sources": ["mcp"] }, { "name": "local/devops-toolkit", "tools": 23, "includes": 3, "sources": ["builtin", "mcp", "custom"] }, { "name": "local/full-stack-dev", "tools": 25, "includes": 4, "sources": ["builtin", "mcp", "custom"] } ], "summary": { "total": 5, "local": 5, "server": 0, "total_tools": 28 } }, "timing": { "duration_ms": 45 }, "messages": [ { "level": "ok", "text": "5 skills listed" } ] } ``` === "YAML" ```yaml command: skill list status: ok exit_code: 0 data: skills: - name: local/file-ops tools: 9 includes: 0 sources: - builtin - name: local/git-ops tools: 4 includes: 0 sources: - builtin - name: local/github tools: 4 includes: 0 sources: - mcp - name: local/devops-toolkit tools: 23 includes: 3 sources: - builtin - mcp - custom - name: local/full-stack-dev tools: 25 includes: 4 sources: - builtin - mcp - custom summary: total: 5 local: 5 server: 0 total_tools: 28 timing: duration_ms: 45 messages: - level: ok text: 5 skills listed ``` ##### agents skill show 
agents skill show  <NAME>
**Purpose** Show full details for a registered skill, including its includes, tool sources, and capability summary. **Arguments** - ``: Skill name. **Examples** === "Rich" 

    $ agents skill show local/devops-toolkit

    ╭─ Skill Details ──────────────────────────────╮
    │ Name: local/devops-toolkit                   │
    │ Description: Full-stack development tools    │
    │ Config: ./skills/devops-toolkit.yaml         │
    │ Created: 2026-02-08 13:10                    │
    │ Updated: 2026-02-08 14:22                    │
    ╰──────────────────────────────────────────────╯

    ╭─ Includes (3) ────────────────────────────╮
    │ local/file-ops  → 9 tools (builtin)       │
    │ local/git-ops   → 4 tools (builtin)       │
    │ local/github    → 4 tools (mcp)           │
    ╰───────────────────────────────────────────╯

    ╭─ Direct Tools (6) ────────────────────────────────────────╮
    │ Name              Source       Writes  Checkpoint         │
    │ ────────────────  ───────────  ──────  ──────────         │
    │ create_issue      mcp:linear   yes     no                 │
    │ list_issues       mcp:linear   no      —                  │
    │ deploy-to-staging agent_skill  yes     composite          │
    │ code-review       agent_skill  no      —                  │
    │ run_migrations    custom       yes     transaction        │
    │ shell_execute     builtin      yes     snapshot           │
    ╰───────────────────────────────────────────────────────────╯

    ╭─ MCP Servers (1) ───────────────────╮
    │ linear: stdio, 2 tools, connected   │
    ╰─────────────────────────────────────╯

    ╭─ Capability Summary ──────────╮
    │ Total Tools: 23               │
    │ Read-Only: 10                 │
    │ Writes: 13                    │
    │ Checkpointable: 10            │
    │ Has Side Effects: 3           │
    │ Requires Approval: 1          │
    ╰───────────────────────────────╯

    ╭─ Referenced By ───────────────────╮
    │ Actors: local/code-assistant      │
    │ Skills: local/full-stack-dev      │
    ╰───────────────────────────────────╯

    ✓ OK Skill loaded
=== "Plain" ``` $ agents skill show local/devops-toolkit Skill Details Name: local/devops-toolkit Description: Full-stack development tools Config: ./skills/devops-toolkit.yaml Created: 2026-02-08 13:10 Updated: 2026-02-08 14:22 Includes (3) local/file-ops -> 9 tools (builtin) local/git-ops -> 4 tools (builtin) local/github -> 4 tools (mcp) Direct Tools (6) Name Source Writes Checkpoint ---------------- ----------- ------ ---------- create_issue mcp:linear yes no list_issues mcp:linear no - deploy-to-staging agent_skill yes composite code-review agent_skill no - run_migrations custom yes transaction shell_execute builtin yes snapshot MCP Servers (1) linear: stdio, 2 tools, connected Capability Summary Total Tools: 23 Read-Only: 10 Writes: 13 Checkpointable: 10 Has Side Effects: 3 Requires Approval: 1 Referenced By Actors: local/code-assistant Skills: local/full-stack-dev [OK] Skill loaded ``` === "JSON" ```json { "command": "skill show local/devops-toolkit", "status": "ok", "exit_code": 0, "data": { "skill": { "name": "local/devops-toolkit", "description": "Full-stack development tools", "config": "./skills/devops-toolkit.yaml", "created": "2026-02-08T13:10:00Z", "updated": "2026-02-08T14:22:00Z" }, "includes": [ { "name": "local/file-ops", "tools": 9, "source": "builtin" }, { "name": "local/git-ops", "tools": 4, "source": "builtin" }, { "name": "local/github", "tools": 4, "source": "mcp" } ], "direct_tools": [ { "name": "create_issue", "source": "mcp:linear", "writes": true, "checkpoint": "no" }, { "name": "list_issues", "source": "mcp:linear", "writes": false, "checkpoint": null }, { "name": "deploy-to-staging", "source": "agent_skill", "writes": true, "checkpoint": "composite" }, { "name": "code-review", "source": "agent_skill", "writes": false, "checkpoint": null }, { "name": "run_migrations", "source": "custom", "writes": true, "checkpoint": "transaction" }, { "name": "shell_execute", "source": "builtin", "writes": true, "checkpoint": "snapshot" } ], "mcp_servers": [ { "name": "linear", "transport": "stdio", "tools": 2, "status": "connected" } ], "capability_summary": { "total_tools": 23, "read_only": 10, "writes": 13, "checkpointable": 10, "has_side_effects": 3, "requires_approval": 1 }, "referenced_by": { "actors": ["local/code-assistant"], "skills": ["local/full-stack-dev"] } }, "timing": { "duration_ms": 110 }, "messages": [ { "level": "ok", "text": "Skill loaded" } ] } ``` === "YAML" ```yaml command: skill show local/devops-toolkit status: ok exit_code: 0 data: skill: name: local/devops-toolkit description: Full-stack development tools config: ./skills/devops-toolkit.yaml created: "2026-02-08T13:10:00Z" updated: "2026-02-08T14:22:00Z" includes: - name: local/file-ops tools: 9 source: builtin - name: local/git-ops tools: 4 source: builtin - name: local/github tools: 4 source: mcp direct_tools: - name: create_issue source: "mcp:linear" writes: true checkpoint: "no" - name: list_issues source: "mcp:linear" writes: false checkpoint: null - name: deploy-to-staging source: agent_skill writes: true checkpoint: composite - name: code-review source: agent_skill writes: false checkpoint: null - name: run_migrations source: custom writes: true checkpoint: transaction - name: shell_execute source: builtin writes: true checkpoint: snapshot mcp_servers: - name: linear transport: stdio tools: 2 status: connected capability_summary: total_tools: 23 read_only: 10 writes: 13 checkpointable: 10 has_side_effects: 3 requires_approval: 1 referenced_by: actors: - local/code-assistant skills: - local/full-stack-dev timing: duration_ms: 110 messages: - level: ok text: Skill loaded ``` ##### agents skill tools 
agents skill tools <NAME>
**Purpose** List all tools provided by a skill, including those inherited from included skills (the flattened tool set). **Arguments** - ``: Skill name. **Examples** === "Rich" 

    $ agents skill tools local/devops-toolkit

    ╭─ Tools for local/devops-toolkit ─────────────────────────────────────────────────────────╮
    │ Tool               Source       From Skill      Read-Only  Writes  Checkpoint            │
    │ ─────────────────  ───────────  ──────────────  ─────────  ──────  ──────────            │
    │ read_file          builtin      local/file-ops  ✓          —       —                     │
    │ write_file         builtin      local/file-ops  —          ✓       file                  │
    │ edit_file          builtin      local/file-ops  —          ✓       file                  │
    │ delete_file        builtin      local/file-ops  —          ✓       file                  │
    │ move_file          builtin      local/file-ops  —          ✓       file                  │
    │ copy_file          builtin      local/file-ops  —          ✓       file                  │
    │ create_directory   builtin      local/file-ops  —          ✓       file                  │
    │ list_directory     builtin      local/file-ops  ✓          —       —                     │
    │ delete_directory   builtin      local/file-ops  —          ✓       file                  │
    │ git_status         builtin      local/git-ops   ✓          —       —                     │
    │ git_diff           builtin      local/git-ops   ✓          —       —                     │
    │ git_log            builtin      local/git-ops   ✓          —       —                     │
    │ git_blame          builtin      local/git-ops   ✓          —       —                     │
    │ create_issue       mcp:github   local/github    —          ✓       no                    │
    │ create_pr          mcp:github   local/github    —          ✓       no                    │
    │ list_repos         mcp:github   local/github    ✓          —       —                     │
    │ get_file_contents  mcp:github   local/github    ✓          —       —                     │
    │ create_issue       mcp:linear   (direct)        —          ✓       no                    │
    │ list_issues        mcp:linear   (direct)        ✓          —       —                     │
    │ run_migrations     custom       (direct)        —          ✓       transaction           │
    │ deploy-to-staging  agent_skill  (direct)        —          ✓       composite             │
    │ code-review        agent_skill  (direct)        ✓          —       —                     │
    │ shell_execute      builtin      (direct)        —          ✓       snapshot              │
    ╰──────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ──────────────────╮
    │ Total: 23                  │
    │ From Includes: 17          │
    │ Direct: 6                  │
    │ Read-Only: 10              │
    │ Writes: 13                 │
    │ Checkpointable: 10         │
    ╰────────────────────────────╯

    ✓ OK 23 tools listed
=== "Plain" ``` $ agents skill tools local/devops-toolkit Tools for local/devops-toolkit Tool Source From Skill Read-Only Writes Checkpoint ----------------- ----------- -------------- --------- ------ ---------- read_file builtin local/file-ops yes - - write_file builtin local/file-ops - yes file edit_file builtin local/file-ops - yes file delete_file builtin local/file-ops - yes file move_file builtin local/file-ops - yes file copy_file builtin local/file-ops - yes file create_directory builtin local/file-ops - yes file list_directory builtin local/file-ops yes - - delete_directory builtin local/file-ops - yes file git_status builtin local/git-ops yes - - git_diff builtin local/git-ops yes - - git_log builtin local/git-ops yes - - git_blame builtin local/git-ops yes - - create_issue mcp:github local/github - yes no create_pr mcp:github local/github - yes no list_repos mcp:github local/github yes - - get_file_contents mcp:github local/github yes - - create_issue mcp:linear (direct) - yes no list_issues mcp:linear (direct) yes - - run_migrations custom (direct) - yes transaction deploy-to-staging agent_skill (direct) - yes composite code-review agent_skill (direct) yes - - shell_execute builtin (direct) - yes snapshot Summary Total: 23 From Includes: 17 Direct: 6 Read-Only: 10 Writes: 13 Checkpointable: 10 [OK] 23 tools listed ``` === "JSON" ```json { "command": "skill tools local/devops-toolkit", "status": "ok", "exit_code": 0, "data": { "tools": [ { "name": "read_file", "source": "builtin", "from_skill": "local/file-ops", "read_only": true, "writes": false, "checkpoint": null }, { "name": "write_file", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "edit_file", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "delete_file", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "move_file", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "copy_file", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "create_directory", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "list_directory", "source": "builtin", "from_skill": "local/file-ops", "read_only": true, "writes": false, "checkpoint": null }, { "name": "delete_directory", "source": "builtin", "from_skill": "local/file-ops", "read_only": false, "writes": true, "checkpoint": "file" }, { "name": "git_status", "source": "builtin", "from_skill": "local/git-ops", "read_only": true, "writes": false, "checkpoint": null }, { "name": "git_diff", "source": "builtin", "from_skill": "local/git-ops", "read_only": true, "writes": false, "checkpoint": null }, { "name": "git_log", "source": "builtin", "from_skill": "local/git-ops", "read_only": true, "writes": false, "checkpoint": null }, { "name": "git_blame", "source": "builtin", "from_skill": "local/git-ops", "read_only": true, "writes": false, "checkpoint": null }, { "name": "create_issue", "source": "mcp:github", "from_skill": "local/github", "read_only": false, "writes": true, "checkpoint": "no" }, { "name": "create_pr", "source": "mcp:github", "from_skill": "local/github", "read_only": false, "writes": true, "checkpoint": "no" }, { "name": "list_repos", "source": "mcp:github", "from_skill": "local/github", "read_only": true, "writes": false, "checkpoint": null }, { "name": "get_file_contents", "source": "mcp:github", "from_skill": "local/github", "read_only": true, "writes": false, "checkpoint": null }, { "name": "create_issue", "source": "mcp:linear", "from_skill": null, "read_only": false, "writes": true, "checkpoint": "no" }, { "name": "list_issues", "source": "mcp:linear", "from_skill": null, "read_only": true, "writes": false, "checkpoint": null }, { "name": "run_migrations", "source": "custom", "from_skill": null, "read_only": false, "writes": true, "checkpoint": "transaction" }, { "name": "deploy-to-staging", "source": "agent_skill", "from_skill": null, "read_only": false, "writes": true, "checkpoint": "composite" }, { "name": "code-review", "source": "agent_skill", "from_skill": null, "read_only": true, "writes": false, "checkpoint": null }, { "name": "shell_execute", "source": "builtin", "from_skill": null, "read_only": false, "writes": true, "checkpoint": "snapshot" } ], "summary": { "total": 23, "from_includes": 17, "direct": 6, "read_only": 10, "writes": 13, "checkpointable": 10 } }, "timing": { "duration_ms": 85 }, "messages": [ { "level": "ok", "text": "23 tools listed" } ] } ``` === "YAML" ```yaml command: skill tools local/devops-toolkit status: ok exit_code: 0 data: tools: - name: read_file source: builtin from_skill: local/file-ops read_only: true writes: false checkpoint: null - name: write_file source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: edit_file source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: delete_file source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: move_file source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: copy_file source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: create_directory source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: list_directory source: builtin from_skill: local/file-ops read_only: true writes: false checkpoint: null - name: delete_directory source: builtin from_skill: local/file-ops read_only: false writes: true checkpoint: file - name: git_status source: builtin from_skill: local/git-ops read_only: true writes: false checkpoint: null - name: git_diff source: builtin from_skill: local/git-ops read_only: true writes: false checkpoint: null - name: git_log source: builtin from_skill: local/git-ops read_only: true writes: false checkpoint: null - name: git_blame source: builtin from_skill: local/git-ops read_only: true writes: false checkpoint: null - name: create_issue source: "mcp:github" from_skill: local/github read_only: false writes: true checkpoint: "no" - name: create_pr source: "mcp:github" from_skill: local/github read_only: false writes: true checkpoint: "no" - name: list_repos source: "mcp:github" from_skill: local/github read_only: true writes: false checkpoint: null - name: get_file_contents source: "mcp:github" from_skill: local/github read_only: true writes: false checkpoint: null - name: create_issue source: "mcp:linear" from_skill: null read_only: false writes: true checkpoint: "no" - name: list_issues source: "mcp:linear" from_skill: null read_only: true writes: false checkpoint: null - name: run_migrations source: custom from_skill: null read_only: false writes: true checkpoint: transaction - name: deploy-to-staging source: agent_skill from_skill: null read_only: false writes: true checkpoint: composite - name: code-review source: agent_skill from_skill: null read_only: true writes: false checkpoint: null - name: shell_execute source: builtin from_skill: null read_only: false writes: true checkpoint: snapshot summary: total: 23 from_includes: 17 direct: 6 read_only: 10 writes: 13 checkpointable: 10 timing: duration_ms: 85 messages: - level: ok text: 23 tools listed ``` #### agents tool !!! info "Purpose" Manage ==tools== — namespaced, independently registered, callable operations. Tools are defined in their own YAML configuration files and registered in the system through these commands. Once registered, tools can be referenced by name in skills (as part of a tool collection) and in actor graphs (as tool nodes). ??? tip "Tool Lifecycle Overview" | Stage | Command | Description | | :---- | :------ | :---------- | | **Register** | `agents tool add` | Register from YAML config | | **Inspect** | `agents tool show` | View tool details and capabilities | | **List** | `agents tool list` | Browse registered tools | | **Update** | `agents tool add --update` | Re-register with updated config | | **Remove** | `agents tool remove` | Unregister a tool | ##### agents tool add 
agents tool add --config|-c <FILE> [--update]
**Purpose** Register a new tool. The tool is fully defined by the YAML configuration file specified with `--config`. If a tool with the same name already exists, the command fails unless the `--update` flag is provided, which allows overwriting the existing registration with the new configuration. **Arguments** - `--config/-c FILE`: Path to the tool YAML configuration file (required). The file must fully define the tool, including the `name` field which determines the tool's registered name. - `--update`: Allow overwriting an existing tool registration. Without this flag, attempting to add a tool whose name is already registered will fail. **Examples** Registering a new tool: === "Rich" 

    $ agents tool add --config ./tools/run-migrations.yaml

    ╭─ Tool Registered ────────────────────────────╮
    │ Name: local/run-migrations                   │
    │ Description: Run database migrations         │
    │ Source: custom                               │
    │ Config: ./tools/run-migrations.yaml          │
    │ Created: 2026-02-09 10:15                    │
    ╰──────────────────────────────────────────────╯

    ╭─ Capability ─────────────────────╮
    │ Writes: true                     │
    │ Write Scope: database:migrations │
    │ Checkpointable: true             │
    │ Checkpoint Scope: transaction    │
    │ Side Effects: schema_mutation    │
    ╰──────────────────────────────────╯

    ✓ OK Tool registered
=== "Plain" ``` $ agents tool add --config ./tools/run-migrations.yaml Tool Registered Name: local/run-migrations Description: Run database migrations Source: custom Config: ./tools/run-migrations.yaml Created: 2026-02-09 10:15 Capability Writes: true Write Scope: database:migrations Checkpointable: true Checkpoint Scope: transaction Side Effects: schema_mutation [OK] Tool registered ``` === "JSON" ```json { "command": "tool add", "status": "ok", "exit_code": 0, "data": { "tool_registered": { "name": "local/run-migrations", "description": "Run database migrations", "source": "custom", "config": "./tools/run-migrations.yaml", "created": "2026-02-09T10:15:00Z" }, "capability": { "writes": true, "write_scope": "database:migrations", "checkpointable": true, "checkpoint_scope": "transaction", "side_effects": ["schema_mutation"] } }, "timing": { "duration_ms": 58 }, "messages": ["Tool registered"] } ``` === "YAML" ```yaml command: tool add status: ok exit_code: 0 data: tool_registered: name: local/run-migrations description: Run database migrations source: custom config: ./tools/run-migrations.yaml created: "2026-02-09T10:15:00Z" capability: writes: true write_scope: "database:migrations" checkpointable: true checkpoint_scope: transaction side_effects: - schema_mutation timing: duration_ms: 58 messages: - Tool registered ``` Attempting to add a tool that already exists (without `--update`): === "Rich" 

    $ agents tool add --config ./tools/run-migrations-v2.yaml

    ✗ Error: Tool 'local/run-migrations' is already registered.

    To overwrite the existing configuration, re-run with --update:

      agents tool add --config ./tools/run-migrations-v2.yaml --update
=== "Plain" ``` $ agents tool add --config ./tools/run-migrations-v2.yaml [ERROR] Tool 'local/run-migrations' is already registered. To overwrite the existing configuration, re-run with --update: agents tool add --config ./tools/run-migrations-v2.yaml --update ``` === "JSON" ```json { "command": "tool add", "status": "error", "exit_code": 1, "data": { "error": "Tool 'local/run-migrations' is already registered.", "hint": "To overwrite the existing configuration, re-run with --update", "suggested_command": "agents tool add --config ./tools/run-migrations-v2.yaml --update" }, "timing": { "duration_ms": 12 }, "messages": ["Tool 'local/run-migrations' is already registered."] } ``` === "YAML" ```yaml command: tool add status: error exit_code: 1 data: error: "Tool 'local/run-migrations' is already registered." hint: "To overwrite the existing configuration, re-run with --update" suggested_command: "agents tool add --config ./tools/run-migrations-v2.yaml --update" timing: duration_ms: 12 messages: - "Tool 'local/run-migrations' is already registered." ``` Updating an existing tool with `--update`: === "Rich" 

    $ agents tool add --config ./tools/db-migrate.yaml --update

    ╭─ Tool Updated ─────────────────────────────╮
    │ Name: local/db-migrate                     │
    │ Source: custom (Python)                    │
    │ Status: updated (was version 1 → now 2)    │
    ╰────────────────────────────────────────────╯

    ╭─ Changes ─────────────────────────────────────╮
    │ Input Schema: modified (added batch_size)     │
    │ Capabilities: unchanged (writes, checkpoint)  │
    │ Description: updated                          │
    ╰───────────────────────────────────────────────╯

    ╭─ References ──────────────────╮
    │ Skills: 1 (local/db-tools)    │
    │ Actors: 0                     │
    │ Referencing skills will use   │
    │ the updated definition.       │
    ╰───────────────────────────────╯

    ✓ OK Tool updated
=== "Plain" ``` $ agents tool add --config ./tools/db-migrate.yaml --update Tool Updated Name: local/db-migrate Source: custom (Python) Status: updated (was version 1 -> now 2) Changes Input Schema: modified (added batch_size) Capabilities: unchanged (writes, checkpoint) Description: updated References Skills: 1 (local/db-tools) Actors: 0 Referencing skills will use the updated definition. [OK] Tool updated ``` === "JSON" ```json { "command": "tool add", "status": "ok", "exit_code": 0, "data": { "tool_updated": { "name": "local/db-migrate", "source": "custom", "source_language": "Python", "status": "updated", "previous_version": 1, "current_version": 2 }, "changes": { "input_schema": "modified (added batch_size)", "capabilities": "unchanged (writes, checkpoint)", "description": "updated" }, "references": { "skills": ["local/db-tools"], "actors": [] } }, "timing": { "duration_ms": 45 }, "messages": ["Tool updated"] } ``` === "YAML" ```yaml command: tool add status: ok exit_code: 0 data: tool_updated: name: local/db-migrate source: custom source_language: Python status: updated previous_version: 1 current_version: 2 changes: input_schema: "modified (added batch_size)" capabilities: "unchanged (writes, checkpoint)" description: updated references: skills: - local/db-tools actors: [] timing: duration_ms: 45 messages: - Tool updated ``` ##### agents tool remove 
agents tool remove [--yes|-y] <NAME>
!!! danger "Destructive Operation" Remove a registered tool. Because Validations are a subtype of Tool and share the same registry, this command ==also removes validations==. When removing a Validation, all attachments are automatically detached before the entry is removed from the registry. References from skills and actor graphs will **break** until resolved. **Arguments** - ``: Tool or validation name to remove. - `--yes`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents tool remove local/run-migrations

    Remove tool local/run-migrations? [y/N]: y

    ╭─ Tool Removed ────────────────────╮
    │ Name: local/run-migrations        │
    │ Source: custom                    │
    ╰───────────────────────────────────╯

    ╭─ References ──────────────────────────────────────╮
    │ Warning: This tool is referenced by:              │
    │ - Skill: local/devops-toolkit                     │
    │ - Actor graph node: code_executor.run_db_migrate  │
    │ These references will break until resolved.       │
    ╰───────────────────────────────────────────────────╯

    ✓ OK Tool removed
=== "Plain" ``` $ agents tool remove local/run-migrations Remove tool local/run-migrations? [y/N]: y Tool Removed Name: local/run-migrations Source: custom References Warning: This tool is referenced by: - Skill: local/devops-toolkit - Actor graph node: code_executor.run_db_migrate These references will break until resolved. [OK] Tool removed ``` === "JSON" ```json { "command": "tool remove", "status": "ok", "exit_code": 0, "data": { "tool_removed": { "name": "local/run-migrations", "source": "custom" }, "broken_references": [ { "type": "skill", "name": "local/devops-toolkit" }, { "type": "actor_graph_node", "name": "code_executor.run_db_migrate" } ] }, "timing": { "duration_ms": 34 }, "messages": [ "Tool removed", "Warning: This tool is referenced by 1 skill and 1 actor graph node. These references will break until resolved." ] } ``` === "YAML" ```yaml command: tool remove status: ok exit_code: 0 data: tool_removed: name: local/run-migrations source: custom broken_references: - type: skill name: local/devops-toolkit - type: actor_graph_node name: code_executor.run_db_migrate timing: duration_ms: 34 messages: - Tool removed - "Warning: This tool is referenced by 1 skill and 1 actor graph node. These references will break until resolved." ``` When removing a validation, attachments are cleaned up automatically: === "Rich" 

    $ agents tool remove local/check-bundle-size

    Remove validation local/check-bundle-size? [y/N]: y

    ╭─ Validation Removed ─────────────────────────────╮
    │ Name: local/check-bundle-size                    │
    │ Description: Check bundle size (advisory)        │
    ╰──────────────────────────────────────────────────╯

    ╭─ Detached From ────────────────────────────────────────────╮
    │ Warning: This validation had 2 attachments:                │
    │ - local/api-repo (scope: project local/api-service)        │
    │ - local/api-repo (direct)                                  │
    │ These attachments have been removed.                       │
    ╰────────────────────────────────────────────────────────────╯

    ✓ OK Validation removed─
=== "Plain" ``` $ agents tool remove local/check-bundle-size Remove validation local/check-bundle-size? [y/N]: y Validation Removed Name: local/check-bundle-size Description: Check bundle size (advisory) Detached From Warning: This validation had 2 attachments: - local/api-repo (scope: project local/api-service) - local/api-repo (direct) These attachments have been removed. [OK] Validation removed ``` === "JSON" ```json { "command": "tool remove", "status": "ok", "exit_code": 0, "data": { "validation_removed": { "name": "local/check-bundle-size", "description": "Check bundle size (advisory)" }, "detached_attachments": [ { "resource": "local/api-repo", "scope": "project", "project": "local/api-service" }, { "resource": "local/api-repo", "scope": "direct" } ] }, "timing": { "duration_ms": 41 }, "messages": [ "Validation removed", "Warning: This validation had 2 attachments which have been removed." ] } ``` === "YAML" ```yaml command: tool remove status: ok exit_code: 0 data: validation_removed: name: local/check-bundle-size description: "Check bundle size (advisory)" detached_attachments: - resource: local/api-repo scope: project project: local/api-service - resource: local/api-repo scope: direct timing: duration_ms: 41 messages: - Validation removed - "Warning: This validation had 2 attachments which have been removed." ``` ##### agents tool list 
agents tool list [(--namespace|-n) <NS>] [--source <SOURCE>] [--type (tool|validation)] [<REGEX>]
**Purpose** List registered tools with optional filters. Because Validations are a subtype of Tool and share the same registry, this command lists both plain tools and validations. Use `--type validation` to show only validations, or `--type tool` to show only plain tools. When `--type` is omitted, both are listed with a `Type` column distinguishing them. **Arguments** - `--namespace/-n NS`: Filter by namespace. - `--source SOURCE`: Filter by tool source type (mcp, agent_skill, builtin, custom). - `--type TYPE`: Filter by entry type: `tool` (plain tools only) or `validation` (validations only). When omitted, both are listed. **Examples** === "Rich" 

    $ agents tool list --namespace local

    ╭─ Tools ─────────────────────────────────────────────────────────────────╮
    │ Name                       Type        Source   Read-Only  Writes       │
    │ ─────────────────────────  ──────────  ───────  ─────────  ──────       │
    │ local/run-migrations       tool        custom   —          ✓            │
    │ local/validate-api-compat  tool        custom   —          ✓            │
    │ local/create-subplan       tool        custom   —          ✓            │
    │ local/deploy-staging       tool        agent    —          ✓            │
    │ local/run-tests            validation  custom   ✓          —            │
    │ local/lint-check           validation  custom   ✓          —            │
    │ local/check-bundle-size    validation  custom   ✓          —            │
    │ local/type-check           validation  custom   ✓          —            │
    ╰─────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ────────────────╮
    │ Total: 8                 │
    │ Tools: 4                 │
    │ Validations: 4           │
    │ Read-Only: 4             │
    │ Writes: 4                │
    ╰──────────────────────────╯

    ✓ OK 8 tools listed
=== "Plain" ``` $ agents tool list --namespace local Tools Name Type Source Read-Only Writes ------------------------- ---------- ------- --------- ------ local/run-migrations tool custom - yes local/validate-api-compat tool custom - yes local/create-subplan tool custom - yes local/deploy-staging tool agent - yes local/run-tests validation custom yes - local/lint-check validation custom yes - local/check-bundle-size validation custom yes - local/type-check validation custom yes - Summary Total: 8 Tools: 4 Validations: 4 Read-Only: 4 Writes: 4 [OK] 8 tools listed ``` === "JSON" ```json { "command": "tool list", "status": "ok", "exit_code": 0, "data": { "tools": [ { "name": "local/run-migrations", "type": "tool", "source": "custom", "read_only": false, "writes": true }, { "name": "local/validate-api-compat", "type": "tool", "source": "custom", "read_only": false, "writes": true }, { "name": "local/create-subplan", "type": "tool", "source": "custom", "read_only": false, "writes": true }, { "name": "local/deploy-staging", "type": "tool", "source": "agent", "read_only": false, "writes": true }, { "name": "local/run-tests", "type": "validation", "source": "custom", "read_only": true, "writes": false }, { "name": "local/lint-check", "type": "validation", "source": "custom", "read_only": true, "writes": false }, { "name": "local/check-bundle-size", "type": "validation", "source": "custom", "read_only": true, "writes": false }, { "name": "local/type-check", "type": "validation", "source": "custom", "read_only": true, "writes": false } ], "summary": { "total": 8, "tools": 4, "validations": 4, "read_only": 4, "writes": 4 } }, "timing": { "duration_ms": 22 }, "messages": ["8 tools listed"] } ``` === "YAML" ```yaml command: tool list status: ok exit_code: 0 data: tools: - name: local/run-migrations type: tool source: custom read_only: false writes: true - name: local/validate-api-compat type: tool source: custom read_only: false writes: true - name: local/create-subplan type: tool source: custom read_only: false writes: true - name: local/deploy-staging type: tool source: agent read_only: false writes: true - name: local/run-tests type: validation source: custom read_only: true writes: false - name: local/lint-check type: validation source: custom read_only: true writes: false - name: local/check-bundle-size type: validation source: custom read_only: true writes: false - name: local/type-check type: validation source: custom read_only: true writes: false summary: total: 8 tools: 4 validations: 4 read_only: 4 writes: 4 timing: duration_ms: 22 messages: - 8 tools listed ``` === "Rich" 

    $ agents tool list --type validation --namespace local

    ╭─ Validations ─────────────────────────────────────────────────────────────────╮
    │ Name                       Source   Mode          Attachments                 │
    │ ─────────────────────────  ───────  ────────────  ────────────────────────    │
    │ local/run-tests            custom   required      2 (1 direct, 1 project)     │
    │ local/lint-check           custom   required      1 (1 direct)                │
    │ local/check-bundle-size    custom   informational 1 (1 project)               │
    │ local/type-check           custom   required      2 (2 project)               │
    ╰───────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ──────────────╮
    │ Total: 4               │
    │ Required: 3            │
    │ Informational: 1       │
    ╰────────────────────────╯

    ✓ OK 4 validations listed
=== "Plain" ``` $ agents tool list --type validation --namespace local Validations Name Source Mode Attachments ------------------------- ------- ------------ ------------------------ local/run-tests custom required 2 (1 direct, 1 project) local/lint-check custom required 1 (1 direct) local/check-bundle-size custom informational 1 (1 project) local/type-check custom required 2 (2 project) Summary Total: 4 Required: 3 Informational: 1 [OK] 4 validations listed ``` === "JSON" ```json { "command": "tool list", "status": "ok", "exit_code": 0, "data": { "validations": [ { "name": "local/run-tests", "source": "custom", "mode": "required", "attachments": { "total": 2, "direct": 1, "project": 1 } }, { "name": "local/lint-check", "source": "custom", "mode": "required", "attachments": { "total": 1, "direct": 1 } }, { "name": "local/check-bundle-size", "source": "custom", "mode": "informational", "attachments": { "total": 1, "project": 1 } }, { "name": "local/type-check", "source": "custom", "mode": "required", "attachments": { "total": 2, "project": 2 } } ], "summary": { "total": 4, "required": 3, "informational": 1 } }, "timing": { "duration_ms": 18 }, "messages": ["4 validations listed"] } ``` === "YAML" ```yaml command: tool list status: ok exit_code: 0 data: validations: - name: local/run-tests source: custom mode: required attachments: total: 2 direct: 1 project: 1 - name: local/lint-check source: custom mode: required attachments: total: 1 direct: 1 - name: local/check-bundle-size source: custom mode: informational attachments: total: 1 project: 1 - name: local/type-check source: custom mode: required attachments: total: 2 project: 2 summary: total: 4 required: 3 informational: 1 timing: duration_ms: 18 messages: - 4 validations listed ``` ##### agents tool show 
agents tool show <NAME>
**Purpose** Show full details for a registered tool, including its schema, capability metadata, and where it is referenced. Because Validations are a subtype of Tool and share the same registry, this command also shows validation details. When showing a Validation, additional validation-specific fields are displayed: `Mode` (required/informational) and `Attached To` (listing each resource attachment with its scope — direct, project-scoped, or plan-scoped). **Arguments** - ``: Tool or validation name. **Examples** === "Rich" 

    $ agents tool show local/run-migrations

    ╭─ Tool Details ───────────────────────────────╮
    │ Name: local/run-migrations                   │
    │ Description: Run database migrations         │
    │ Source: custom                               │
    │ Config: ./tools/run-migrations.yaml          │
    │ Registered: 2026-02-09 10:15                 │
    ╰──────────────────────────────────────────────╯

    ╭─ Input Schema ─────────────────────────────────╮
    │ direction: string (required) enum: [up, down]  │
    │ count: integer (default: 1)                    │
    ╰────────────────────────────────────────────────╯

    ╭─ Capability ──────────────────────╮
    │ Read-Only: false                  │
    │ Writes: true                      │
    │ Write Scope: database:migrations  │
    │ Checkpointable: true              │
    │ Checkpoint Scope: transaction     │
    │ Side Effects: schema_mutation     │
    │ Idempotent: false                 │
    ╰───────────────────────────────────╯

    ╭─ Referenced By ───────────────────────╮
    │ Skills:                               │
    │   - local/devops-toolkit              │
    │ Actor Graph Nodes:                    │
    │   - code_executor.run_db_migrate      │
    ╰───────────────────────────────────────╯

    ✓ OK Tool details loaded
=== "Plain" ``` $ agents tool show local/run-migrations Tool Details Name: local/run-migrations Description: Run database migrations Source: custom Config: ./tools/run-migrations.yaml Registered: 2026-02-09 10:15 Input Schema direction: string (required) enum: [up, down] count: integer (default: 1) Capability Read-Only: false Writes: true Write Scope: database:migrations Checkpointable: true Checkpoint Scope: transaction Side Effects: schema_mutation Idempotent: false Referenced By Skills: - local/devops-toolkit Actor Graph Nodes: - code_executor.run_db_migrate [OK] Tool details loaded ``` === "JSON" ```json { "command": "tool show", "status": "ok", "exit_code": 0, "data": { "tool_details": { "name": "local/run-migrations", "description": "Run database migrations", "source": "custom", "config": "./tools/run-migrations.yaml", "registered": "2026-02-09T10:15:00Z" }, "input_schema": { "direction": { "type": "string", "required": true, "enum": ["up", "down"] }, "count": { "type": "integer", "default": 1 } }, "capability": { "read_only": false, "writes": true, "write_scope": "database:migrations", "checkpointable": true, "checkpoint_scope": "transaction", "side_effects": ["schema_mutation"], "idempotent": false }, "referenced_by": { "skills": ["local/devops-toolkit"], "actor_graph_nodes": ["code_executor.run_db_migrate"] } }, "timing": { "duration_ms": 15 }, "messages": ["Tool details loaded"] } ``` === "YAML" ```yaml command: tool show status: ok exit_code: 0 data: tool_details: name: local/run-migrations description: Run database migrations source: custom config: ./tools/run-migrations.yaml registered: "2026-02-09T10:15:00Z" input_schema: direction: type: string required: true enum: - up - down count: type: integer default: 1 capability: read_only: false writes: true write_scope: "database:migrations" checkpointable: true checkpoint_scope: transaction side_effects: - schema_mutation idempotent: false referenced_by: skills: - local/devops-toolkit actor_graph_nodes: - code_executor.run_db_migrate timing: duration_ms: 15 messages: - Tool details loaded ``` When showing a Validation, the output includes validation-specific sections: === "Rich" 

    $ agents tool show local/run-tests

    ╭─ Validation Details ──────────────────────────────╮
    │ Name: local/run-tests                             │
    │ Type: validation                                  │
    │ Description: Run unit tests with coverage         │
    │ Source: custom                                    │
    │ Mode: required                                    │
    │ Config: ./validations/run-tests.yaml              │
    │ Registered: 2026-02-09 10:15                      │
    ╰───────────────────────────────────────────────────╯

    ╭─ Input Schema ─────────────────────────────────────╮
    │ coverage_threshold: integer (default: 80)          │
    ╰────────────────────────────────────────────────────╯

    ╭─ Output Schema (Validation Return Format) ─────────╮
    │ passed: boolean (required)                         │
    │ message: string (optional)                         │
    │ data: object (optional, arbitrary structure)       │
    ╰────────────────────────────────────────────────────╯

    ╭─ Capability ──────────────────────╮
    │ Read-Only: true (enforced)        │
    │ Checkpointable: false (enforced)  │
    │ Timeout: 600s                     │
    ╰───────────────────────────────────╯

    ╭─ Attached To ─────────────────────────────────────────────────────╮
    │ local/api-repo (direct, always active)                            │
    │   (attachment: 01HXM5B2C3D4E5F6G7H8J9K0L1)                        │
    │ local/api-repo (scope: project local/api-service)                 │
    │   (attachment: 01HXM5A1B2C3D4E5F6G7H8J9K0)                        │
    ╰───────────────────────────────────────────────────────────────────╯

    ✓ OK Validation details loaded
=== "Plain" ``` $ agents tool show local/run-tests Validation Details Name: local/run-tests Type: validation Description: Run unit tests with coverage Source: custom Mode: required Config: ./validations/run-tests.yaml Registered: 2026-02-09 10:15 Input Schema coverage_threshold: integer (default: 80) Output Schema (Validation Return Format) passed: boolean (required) message: string (optional) data: object (optional, arbitrary structure) Capability Read-Only: true (enforced) Checkpointable: false (enforced) Timeout: 600s Attached To local/api-repo (direct, always active) (attachment: 01HXM5B2C3D4E5F6G7H8J9K0L1) local/api-repo (scope: project local/api-service) (attachment: 01HXM5A1B2C3D4E5F6G7H8J9K0) [OK] Validation details loaded ``` === "JSON" ```json { "command": "tool show", "status": "ok", "exit_code": 0, "data": { "validation_details": { "name": "local/run-tests", "type": "validation", "description": "Run unit tests with coverage", "source": "custom", "mode": "required", "config": "./validations/run-tests.yaml", "registered": "2026-02-09T10:15:00Z" }, "input_schema": { "coverage_threshold": { "type": "integer", "default": 80 } }, "output_schema": { "passed": { "type": "boolean", "required": true }, "message": { "type": "string", "required": false }, "data": { "type": "object", "required": false, "description": "arbitrary structure" } }, "capability": { "read_only": true, "read_only_enforced": true, "checkpointable": false, "checkpointable_enforced": true, "timeout_seconds": 600 }, "attached_to": [ { "resource": "local/api-repo", "scope": "direct", "attachment_id": "01HXM5B2C3D4E5F6G7H8J9K0L1" }, { "resource": "local/api-repo", "scope": "project", "project": "local/api-service", "attachment_id": "01HXM5A1B2C3D4E5F6G7H8J9K0" } ] }, "timing": { "duration_ms": 19 }, "messages": ["Validation details loaded"] } ``` === "YAML" ```yaml command: tool show status: ok exit_code: 0 data: validation_details: name: local/run-tests type: validation description: Run unit tests with coverage source: custom mode: required config: ./validations/run-tests.yaml registered: "2026-02-09T10:15:00Z" input_schema: coverage_threshold: type: integer default: 80 output_schema: passed: type: boolean required: true message: type: string required: false data: type: object required: false description: arbitrary structure capability: read_only: true read_only_enforced: true checkpointable: false checkpointable_enforced: true timeout_seconds: 600 attached_to: - resource: local/api-repo scope: direct attachment_id: 01HXM5B2C3D4E5F6G7H8J9K0L1 - resource: local/api-repo scope: project project: local/api-service attachment_id: 01HXM5A1B2C3D4E5F6G7H8J9K0 timing: duration_ms: 19 messages: - Validation details loaded ``` #### agents lsp !!! info "Purpose" Manage the **LSP Registry** — the global registry of Language Server Protocol servers that provide language intelligence (diagnostics, type information, completions, references, definitions, symbols, formatting, code actions, renaming) to actors. LSP servers are Infrastructure-layer components attached to actors via the `lsp:` configuration field; they have nothing to do with IDE integration. Each registered LSP server has a namespaced name (`[[server:]namespace/]name`), a launch command, supported languages, initialization options, and capability declarations. The `agents lsp` commands mirror the structure of `agents tool` commands. ##### agents lsp add 
agents lsp add [--update|-u] (--config|-c) <FILE>
**Purpose** Register an LSP server from a YAML configuration file. The config file defines the server's namespaced name, launch command, supported languages, initialization options, and capability declarations. If the server already exists and `--update` is not provided, the command fails with an error and a hint to use `--update`. **Arguments** - `--config/-c FILE`: Path to LSP server YAML configuration file (required). - `--update/-u`: Overwrite if the server already exists in the registry. **Examples** Registering a new LSP server: === "Rich" 

    $ agents lsp add --config lsp/pyright.yaml

    ╭─ LSP Server Registered ──────────────────────────────────╮
    │ Name: local/pyright                                      │
    │ Languages: python                                        │
    │ Command: pyright-langserver --stdio                      │
    │ Capabilities: diagnostics, hover, completions,           │
    │               references, definitions, symbols,          │
    │               rename, code_actions                       │
    ╰──────────────────────────────────────────────────────────╯

    ✓ OK LSP server registered
=== "Plain" ``` $ agents lsp add --config lsp/pyright.yaml LSP Server Registered Name: local/pyright Languages: python Command: pyright-langserver --stdio Capabilities: diagnostics, hover, completions, references, definitions, symbols, rename, code_actions [OK] LSP server registered ``` === "JSON" ```json { "command": "lsp add", "status": "ok", "exit_code": 0, "data": { "lsp_server": { "name": "local/pyright", "languages": ["python"], "command": "pyright-langserver --stdio", "capabilities": [ "diagnostics", "hover", "completions", "references", "definitions", "symbols", "rename", "code_actions" ] } }, "timing": { "duration_ms": 12 }, "messages": ["LSP server registered"] } ``` === "YAML" ```yaml command: lsp add status: ok exit_code: 0 data: lsp_server: name: local/pyright languages: - python command: pyright-langserver --stdio capabilities: - diagnostics - hover - completions - references - definitions - symbols - rename - code_actions timing: duration_ms: 12 messages: - LSP server registered ``` Attempting to add a server that already exists (without `--update`): === "Rich" 

    $ agents lsp add --config lsp/pyright.yaml

    ✗ ERROR LSP server 'local/pyright' already exists

    Hint: Use --update to overwrite: agents lsp add --update --config lsp/pyright.yaml
=== "Plain" ``` $ agents lsp add --config lsp/pyright.yaml [ERROR] LSP server 'local/pyright' already exists Hint: Use --update to overwrite: agents lsp add --update --config lsp/pyright.yaml ``` === "JSON" ```json { "command": "lsp add", "status": "error", "exit_code": 1, "data": { "error": "LSP server 'local/pyright' already exists" }, "hint": "Use --update to overwrite", "suggested_command": "agents lsp add --update --config lsp/pyright.yaml", "timing": { "duration_ms": 5 }, "messages": ["LSP server 'local/pyright' already exists"] } ``` === "YAML" ```yaml command: lsp add status: error exit_code: 1 data: error: "LSP server 'local/pyright' already exists" hint: Use --update to overwrite suggested_command: agents lsp add --update --config lsp/pyright.yaml timing: duration_ms: 5 messages: - "LSP server 'local/pyright' already exists" ``` ##### agents lsp remove 
agents lsp remove [--yes|-y] <NAME>
!!! danger "Destructive Operation" Remove a registered LSP server from the LSP Registry. Running LSP server processes bound to the removed entry are terminated. Actor configurations referencing this server by name will fail at activation until resolved. **Arguments** - ``: Namespaced LSP server name to remove. - `--yes/-y`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents lsp remove local/pyright

    Remove LSP server local/pyright? [y/N]: y

    ╭─ LSP Server Removed ─────────────────────╮
    │ Name: local/pyright                      │
    │ Languages: python                        │
    ╰──────────────────────────────────────────╯

    ╭─ References ──────────────────────────────────────────────────╮
    │ Warning: This LSP server is referenced by:                    │
    │ - Actor: local/code-reviewer (lsp: [local/pyright])           │
    │ - Actor: local/refactor-agent (lsp: [local/pyright])          │
    │ These actor LSP bindings will fail until resolved.            │
    ╰───────────────────────────────────────────────────────────────╯

    ✓ OK LSP server removed
=== "Plain" ``` $ agents lsp remove local/pyright Remove LSP server local/pyright? [y/N]: y LSP Server Removed Name: local/pyright Languages: python References Warning: This LSP server is referenced by: - Actor: local/code-reviewer (lsp: [local/pyright]) - Actor: local/refactor-agent (lsp: [local/pyright]) These actor LSP bindings will fail until resolved. [OK] LSP server removed ``` === "JSON" ```json { "command": "lsp remove", "status": "ok", "exit_code": 0, "data": { "lsp_server_removed": { "name": "local/pyright", "languages": ["python"] }, "broken_references": [ { "type": "actor", "name": "local/code-reviewer" }, { "type": "actor", "name": "local/refactor-agent" } ] }, "timing": { "duration_ms": 28 }, "messages": [ "LSP server removed", "Warning: This LSP server is referenced by 2 actors. These actor LSP bindings will fail until resolved." ] } ``` === "YAML" ```yaml command: lsp remove status: ok exit_code: 0 data: lsp_server_removed: name: local/pyright languages: - python broken_references: - type: actor name: local/code-reviewer - type: actor name: local/refactor-agent timing: duration_ms: 28 messages: - LSP server removed - "Warning: This LSP server is referenced by 2 actors. These actor LSP bindings will fail until resolved." ``` ##### agents lsp list 
agents lsp list [(--namespace|-n) <NS>] [--language <LANG>] [<REGEX>]
**Purpose** List registered LSP servers with optional filters. Shows each server's name, supported languages, command, and the number of actors currently bound to it. **Arguments** - `--namespace/-n NS`: Filter by namespace. - `--language LANG`: Filter by supported language (e.g., `python`, `typescript`). - ``: Optional name filter pattern. **Examples** === "Rich" 

    $ agents lsp list

    ╭─ LSP Registry (3 servers) ───────────────────────────────────────────────────────────╮
    │ Name                    │ Languages            │ Command                     │ Bound │
    │─────────────────────────│──────────────────────│─────────────────────────────│───────│
    │ local/pyright           │ python               │ pyright-langserver --stdio  │   3   │
    │ local/ts-server         │ typescript, jsx, tsx │ typescript-language-server  │   2   │
    │ local/gopls             │ go                   │ gopls serve                 │   1   │
    ╰──────────────────────────────────────────────────────────────────────────────────────╯
=== "Plain" ``` $ agents lsp list LSP Registry (3 servers) Name Languages Command Bound local/pyright python pyright-langserver --stdio 3 local/ts-server typescript, jsx, tsx typescript-language-server 2 local/gopls go gopls serve 1 ``` === "JSON" ```json { "command": "lsp list", "status": "ok", "exit_code": 0, "data": { "lsp_servers": [ { "name": "local/pyright", "languages": ["python"], "command": "pyright-langserver --stdio", "bound_actors": 3 }, { "name": "local/ts-server", "languages": ["typescript", "jsx", "tsx"], "command": "typescript-language-server", "bound_actors": 2 }, { "name": "local/gopls", "languages": ["go"], "command": "gopls serve", "bound_actors": 1 } ], "total": 3 }, "timing": { "duration_ms": 8 }, "messages": ["3 LSP servers listed"] } ``` === "YAML" ```yaml command: lsp list status: ok exit_code: 0 data: lsp_servers: - name: local/pyright languages: - python command: pyright-langserver --stdio bound_actors: 3 - name: local/ts-server languages: - typescript - jsx - tsx command: typescript-language-server bound_actors: 2 - name: local/gopls languages: - go command: gopls serve bound_actors: 1 total: 3 timing: duration_ms: 8 messages: - 3 LSP servers listed ``` Filtering by language: === "Rich" 

    $ agents lsp list --language python

    ╭─ LSP Registry (1 server, filtered: language=python) ─────────────────────────────╮
    │ Name                    │ Languages  │ Command                           │ Bound │
    │─────────────────────────│────────────│───────────────────────────────────│───────│
    │ local/pyright           │ python     │ pyright-langserver --stdio        │   3   │
    ╰──────────────────────────────────────────────────────────────────────────────────╯
=== "Plain" ``` $ agents lsp list --language python LSP Registry (1 server, filtered: language=python) Name Languages Command Bound local/pyright python pyright-langserver --stdio 3 ``` === "JSON" ```json { "command": "lsp list", "status": "ok", "exit_code": 0, "data": { "lsp_servers": [ { "name": "local/pyright", "languages": ["python"], "command": "pyright-langserver --stdio", "bound_actors": 3 } ], "total": 1, "filter": { "language": "python" } }, "timing": { "duration_ms": 6 }, "messages": ["1 LSP server listed (filtered: language=python)"] } ``` === "YAML" ```yaml command: lsp list status: ok exit_code: 0 data: lsp_servers: - name: local/pyright languages: - python command: pyright-langserver --stdio bound_actors: 3 total: 1 filter: language: python timing: duration_ms: 6 messages: - "1 LSP server listed (filtered: language=python)" ``` ##### agents lsp show 
agents lsp show <NAME>
**Purpose** Show full details for a registered LSP server, including its configuration, supported languages, capabilities, initialization options, and which actors are bound to it. **Arguments** - ``: Namespaced LSP server name. **Examples** === "Rich" 

    $ agents lsp show local/pyright

    ╭─ LSP Server Details ──────────────────────────────────────────╮
    │ Name: local/pyright                                           │
    │ Languages: python                                             │
    │ Command: pyright-langserver --stdio                           │
    │ Root path: {{ project.root }}                                 │
    │ Init options:                                                 │
    │   python.analysis.typeCheckingMode: standard                  │
    │   python.analysis.autoSearchPaths: true                       │
    ╰───────────────────────────────────────────────────────────────╯

    ╭─ Capabilities ────────────────────────────────────────────────╮
    │ diagnostics, hover, completions, references, definitions,     │
    │ symbols, rename, code_actions                                 │
    ╰───────────────────────────────────────────────────────────────╯

    ╭─ Bound Actors ────────────────────────────────────────────────╮
    │ local/code-reviewer      (explicit binding)                   │
    │ local/refactor-agent     (language-based: python)             │
    │ local/polyglot-planner   (auto-discovery)                     │
    ╰───────────────────────────────────────────────────────────────╯
=== "Plain" ``` $ agents lsp show local/pyright LSP Server Details Name: local/pyright Languages: python Command: pyright-langserver --stdio Root path: {{ project.root }} Init options: python.analysis.typeCheckingMode: standard python.analysis.autoSearchPaths: true Capabilities diagnostics, hover, completions, references, definitions, symbols, rename, code_actions Bound Actors local/code-reviewer (explicit binding) local/refactor-agent (language-based: python) local/polyglot-planner (auto-discovery) ``` === "JSON" ```json { "command": "lsp show", "status": "ok", "exit_code": 0, "data": { "lsp_server": { "name": "local/pyright", "languages": ["python"], "command": "pyright-langserver --stdio", "root_path": "{{ project.root }}", "init_options": { "python.analysis.typeCheckingMode": "standard", "python.analysis.autoSearchPaths": true }, "capabilities": [ "diagnostics", "hover", "completions", "references", "definitions", "symbols", "rename", "code_actions" ], "bound_actors": [ { "name": "local/code-reviewer", "binding_mode": "explicit" }, { "name": "local/refactor-agent", "binding_mode": "language_based", "language": "python" }, { "name": "local/polyglot-planner", "binding_mode": "auto_discovery" } ] } }, "timing": { "duration_ms": 14 }, "messages": ["LSP server details loaded"] } ``` === "YAML" ```yaml command: lsp show status: ok exit_code: 0 data: lsp_server: name: local/pyright languages: - python command: pyright-langserver --stdio root_path: "{{ project.root }}" init_options: python.analysis.typeCheckingMode: standard python.analysis.autoSearchPaths: true capabilities: - diagnostics - hover - completions - references - definitions - symbols - rename - code_actions bound_actors: - name: local/code-reviewer binding_mode: explicit - name: local/refactor-agent binding_mode: language_based language: python - name: local/polyglot-planner binding_mode: auto_discovery timing: duration_ms: 14 messages: - LSP server details loaded ``` ##### agents lsp serve 
agents lsp serve [--log-level <LEVEL>]
**Purpose** Launch the stub LSP server over stdin/stdout using the JSON-RPC base protocol with Content-Length header framing. The server supports the `initialize`, `shutdown`, and `exit` lifecycle methods. Requests received **before** `initialize` are rejected with `ServerNotInitialized` (-32002) per the LSP specification. After initialization, unsupported LSP methods return a `MethodNotFound` (-32601) error. After `shutdown` is received, only `exit` is accepted; other requests are rejected with `InvalidRequest` (-32600). Sending `initialize` a second time is also rejected with `InvalidRequest`. This command is intended for development and testing of LSP transport integration. In a future milestone the stub handlers will be replaced by real LSP server proxying through the A2A facade. **Arguments** - `--log-level LEVEL`: Logging level for the server process. Valid values: `debug`, `info` (default), `warning`, `error`. Invalid values cause immediate exit with a descriptive error message. **Transport Limits** | Limit | Value | Description | |-------|-------|-------------| | Max Content-Length | 10 MB | Messages exceeding this are rejected with a warning log (DoS guard) | | Max header lines | 32 | Headers with more lines are rejected with a warning log (DoS guard) | **Examples** === "Rich" 

    $ agents lsp serve

    CleverAgents LSP Server (stub) starting — PID 7412
      Log level: info
      Transport: stdin/stdout (JSON-RPC, Content-Length framing)
      Supported methods: initialize, shutdown, exit
      All other methods → MethodNotFound (-32601)
=== "Plain" ``` $ agents lsp serve CleverAgents LSP Server (stub) starting — PID 7412 Log level: info Transport: stdin/stdout (JSON-RPC, Content-Length framing) Supported methods: initialize, shutdown, exit All other methods → MethodNotFound (-32601) ``` #### agents validation !!! info "Purpose" Register and attach ==validations== — a specialized subtype of Tool that extends the Tool class with pass/fail semantics and attachment scoping. A Validation inherits all base Tool properties (name, source, input_schema, capability, resource bindings, lifecycle hooks, etc.) and adds: a `mode` field (`required` or `informational`), and a structured JSON return format with a mandatory `passed` boolean, an optional `message` string, and an optional `data` object for arbitrary informational output. Since Validation extends Tool, it shares the same backing sources (custom, MCP, agent_skill, builtin) plus the additional `wrapped` source type for Validations that wrap an existing Tool via the `wraps` field. It uses the same YAML configuration format (with an additional `validation` block and optional `wraps`/`transform` fields), and the same registries and resolution mechanisms. Validations are always read-only (`writes` is always `false`, `checkpointable` is always `false`). Because Validations are a subtype of Tool and share the same Tool Registry and naming namespace, only validation-specific operations have dedicated subcommands here: `add` (registration with validation-specific fields like `mode`), `attach`, and `detach`. General tool operations — listing, inspection, and removal — are handled through the `agents tool` commands: - **List validations**: `agents tool list --type validation` - **Show validation details**: `agents tool show ` (displays validation-specific fields when the entry is a Validation) - **Remove a validation**: `agents tool remove ` (automatically removes all attachments) A validation is always attached to a resource. The optional `--project` or `--plan` flag controls the scope of the attachment: - **Direct attachment** (no scope flag): The validation is always active for that resource, regardless of which plan or project accesses it. Use `agents validation attach [-- ]...`. - **Project-scoped attachment** (`--project`): The validation only runs for that resource when it is being interacted with through the specified project. Use `agents validation attach --project [-- ]...`. - **Plan-scoped attachment** (`--plan`): The validation only runs for that resource when it is being interacted with through the specified plan. Use `agents validation attach --plan [-- ]...`. The same validation can be attached to the same resource multiple times — directly, through different projects, and through different plans — and since validations accept arguments, attaching the same validation to the same resource multiple times with different arguments is a common and useful configuration pattern (e.g., running the same test suite with different coverage thresholds for different projects). Each `attach` invocation returns a system-assigned **attachment ULID** uniquely identifying that attachment. Use this ULID with `agents validation detach ` to remove a specific attachment. When multiple attachment scopes apply, the union of all applicable validations is used. A resource with a directly-attached validation will always have that validation run, plus any additional validations attached through the active project or plan. ##### agents validation add 
agents validation add --config|-c <FILE> [--required | --informational] [--update]
**Purpose** Register a new validation. The validation is fully defined by the YAML configuration file specified with `--config`. The validation is registered in the shared Tool Registry under the name specified in the config file; the name must not conflict with any existing tool or validation. If a validation with the same name already exists, the command fails unless `--update` is provided. The validation YAML may use `wraps` to reference an existing Tool, reusing its implementation and interpreting its output through a `transform` function (see Tool Wrapping under Core Concepts > Validation). When `wraps` is used, the wrapped Tool must already be registered. **Arguments** - `--config/-c FILE`: Path to the validation YAML configuration file (required). The file must fully define the validation, including the `name` field which determines the validation's registered name, the `validation.mode` field (`required` or `informational`), and either inline implementation (`source` + `code`) or wrapping (`wraps` + `transform`). - `--required`: Override the mode in the YAML config to `required`. Mutually exclusive with `--informational`. - `--informational`: Override the mode in the YAML config to `informational`. Mutually exclusive with `--required`. - `--update`: Allow overwriting an existing validation registration. **Examples** === "Rich" 

    $ agents validation add --config ./validations/run-tests.yaml

    ╭─ Validation Registered ────────────────────────────────╮
    │ Name: local/run-tests                                  │
    │ Description: Run unit tests with coverage              │
    │ Source: custom                                         │
    │ Mode: required                                         │
    │ Config: ./validations/run-tests.yaml                   │
    │ Created: 2026-02-09 10:15                              │
    ╰────────────────────────────────────────────────────────╯

    ╭─ Capability ────────────────────────╮
    │ Read-Only: true (enforced)          │
    │ Checkpointable: false (enforced)    │
    │ Timeout: 600s                       │
    ╰─────────────────────────────────────╯

    ✓ OK Validation registered
=== "Plain" ``` $ agents validation add --config ./validations/run-tests.yaml Validation Registered Name: local/run-tests Description: Run unit tests with coverage Source: custom Mode: required Config: ./validations/run-tests.yaml Created: 2026-02-09 10:15 Capability Read-Only: true (enforced) Checkpointable: false (enforced) Timeout: 600s [OK] Validation registered ``` === "JSON" ```json { "command": "validation add", "status": "ok", "exit_code": 0, "data": { "validation_registered": { "name": "local/run-tests", "description": "Run unit tests with coverage", "source": "custom", "mode": "required", "config": "./validations/run-tests.yaml", "created": "2026-02-09 10:15" }, "capability": { "read_only": "true (enforced)", "checkpointable": "false (enforced)", "timeout": "600s" } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 120 }, "messages": ["Validation registered"] } ``` === "YAML" ```yaml command: validation add status: ok exit_code: 0 data: validation_registered: name: local/run-tests description: Run unit tests with coverage source: custom mode: required config: ./validations/run-tests.yaml created: "2026-02-09 10:15" capability: read_only: "true (enforced)" checkpointable: "false (enforced)" timeout: 600s timing: started: "2026-02-09T10:15:00Z" duration_ms: 120 messages: - "Validation registered" ``` === "Rich" 

    $ agents validation add --config ./validations/lint-check.yaml

    ╭─ Validation Registered ──────────────╮
    │ Name: local/lint-check               │
    │ Description: Lint check              │
    │ Source: custom                       │
    │ Mode: required                       │
    │ Timeout: 300s                        │
    ╰──────────────────────────────────────╯

    ✓ OK Validation registered
=== "Plain" ``` $ agents validation add --config ./validations/lint-check.yaml Validation Registered Name: local/lint-check Description: Lint check Source: custom Mode: required Timeout: 300s [OK] Validation registered ``` === "JSON" ```json { "command": "validation add", "status": "ok", "exit_code": 0, "data": { "validation_registered": { "name": "local/lint-check", "description": "Lint check", "source": "custom", "mode": "required", "timeout": "300s" } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 95 }, "messages": ["Validation registered"] } ``` === "YAML" ```yaml command: validation add status: ok exit_code: 0 data: validation_registered: name: local/lint-check description: Lint check source: custom mode: required timeout: 300s timing: started: "2026-02-09T10:15:00Z" duration_ms: 95 messages: - "Validation registered" ``` === "Rich" 

    $ agents validation add --config ./validations/check-bundle-size.yaml

    ╭─ Validation Registered ───────────────────────────╮
    │ Name: local/check-bundle-size                     │
    │ Description: Check bundle size (advisory)         │
    │ Source: custom                                    │
    │ Mode: informational                               │
    │ Timeout: 300s                                     │
    ╰───────────────────────────────────────────────────╯

    ✓ OK Validation registered
=== "Plain" ``` $ agents validation add --config ./validations/check-bundle-size.yaml Validation Registered Name: local/check-bundle-size Description: Check bundle size (advisory) Source: custom Mode: informational Timeout: 300s [OK] Validation registered ``` === "JSON" ```json { "command": "validation add", "status": "ok", "exit_code": 0, "data": { "validation_registered": { "name": "local/check-bundle-size", "description": "Check bundle size (advisory)", "source": "custom", "mode": "informational", "timeout": "300s" } }, "timing": { "started": "2026-02-09T10:16:00Z", "duration_ms": 88 }, "messages": ["Validation registered"] } ``` === "YAML" ```yaml command: validation add status: ok exit_code: 0 data: validation_registered: name: local/check-bundle-size description: "Check bundle size (advisory)" source: custom mode: informational timeout: 300s timing: started: "2026-02-09T10:16:00Z" duration_ms: 88 messages: - "Validation registered" ``` ##### agents validation attach 
agents validation attach [--project <PROJECT>|--plan <PLAN_ID>]
                         <RESOURCE> <VALIDATION> [--<KEY> <VALUE>]...
**Purpose** Attach a registered validation to a resource, with an optional project or plan scope. A resource is always required — validations are fundamentally resource-centric. The optional `--project` or `--plan` flag narrows when the validation is active: without either flag, the validation runs whenever any plan or project accesses the resource; with `--project`, it only runs when the resource is accessed through that project; with `--plan`, it only runs when the resource is accessed through that plan. At most one scope flag may be provided per invocation. The command returns a system-assigned **attachment ULID** that uniquely identifies this specific attachment association. This ULID is used to detach the validation later via `agents validation detach `. The same validation can be attached to the same resource multiple times — directly, through different projects, through different plans, and even to the same resource and scope multiple times with different arguments. **Arguments** - ``: Resource name or ULID to attach the validation to (positional argument, required). - ``: Validation name (positional argument, required). - `--project PROJECT`: Scope the attachment to a specific project. The validation only runs for this resource when it is accessed through the specified project. - `--plan PLAN_ID`: Scope the attachment to a specific plan. The validation only runs for this resource when it is accessed through the specified plan. - `[-- ]...`: Optional validation-specific arguments in named option format. Each argument is passed as `--key value` (e.g. `--coverage-threshold 90`). Hyphens in option names are converted to underscores in the stored argument dict (e.g. `--coverage-threshold` becomes `coverage_threshold`). Positional `key=value` format is not accepted. **Examples** === "Rich" 

    $ agents validation attach --project local/api-service local/api-repo local/run-tests

    ╭─ Validation Attached ──────────────────────────────────────╮
    │ Attachment ID: 01HXM5A1B2C3D4E5F6G7H8J9K0                  │
    │ Validation: local/run-tests                                │
    │ Mode: required                                             │
    │ Resource: local/api-repo                                   │
    │ Scope: project local/api-service                           │
    ╰────────────────────────────────────────────────────────────╯

    ✓ OK Validation attached
=== "Plain" ``` $ agents validation attach --project local/api-service local/api-repo local/run-tests Validation Attached Attachment ID: 01HXM5A1B2C3D4E5F6G7H8J9K0 Validation: local/run-tests Mode: required Resource: local/api-repo Scope: project local/api-service [OK] Validation attached ``` === "JSON" ```json { "command": "validation attach", "status": "ok", "exit_code": 0, "data": { "validation_attached": { "attachment_id": "01HXM5A1B2C3D4E5F6G7H8J9K0", "validation": "local/run-tests", "mode": "required", "resource": "local/api-repo", "scope": "project local/api-service" } }, "timing": { "started": "2026-02-09T10:20:00Z", "duration_ms": 45 }, "messages": ["Validation attached"] } ``` === "YAML" ```yaml command: validation attach status: ok exit_code: 0 data: validation_attached: attachment_id: 01HXM5A1B2C3D4E5F6G7H8J9K0 validation: local/run-tests mode: required resource: local/api-repo scope: project local/api-service timing: started: "2026-02-09T10:20:00Z" duration_ms: 45 messages: - "Validation attached" ``` === "Rich" 

    $ agents validation attach local/api-repo local/lint-check

    ╭─ Validation Attached ──────────────────────────────────────╮
    │ Attachment ID: 01HXM5B2C3D4E5F6G7H8J9K0L1                  │
    │ Validation: local/lint-check                               │
    │ Mode: required                                             │
    │ Resource: local/api-repo                                   │
    │ Scope: direct (always active)                              │
    │ This validation will run for ALL plans/projects            │
    │ that access this resource.                                 │
    ╰────────────────────────────────────────────────────────────╯

    ✓ OK Validation attached
=== "Plain" ``` $ agents validation attach local/api-repo local/lint-check Validation Attached Attachment ID: 01HXM5B2C3D4E5F6G7H8J9K0L1 Validation: local/lint-check Mode: required Resource: local/api-repo Scope: direct (always active) This validation will run for ALL plans/projects that access this resource. [OK] Validation attached ``` === "JSON" ```json { "command": "validation attach", "status": "ok", "exit_code": 0, "data": { "validation_attached": { "attachment_id": "01HXM5B2C3D4E5F6G7H8J9K0L1", "validation": "local/lint-check", "mode": "required", "resource": "local/api-repo", "scope": "direct (always active)", "note": "This validation will run for ALL plans/projects that access this resource." } }, "timing": { "started": "2026-02-09T10:21:00Z", "duration_ms": 42 }, "messages": ["Validation attached"] } ``` === "YAML" ```yaml command: validation attach status: ok exit_code: 0 data: validation_attached: attachment_id: 01HXM5B2C3D4E5F6G7H8J9K0L1 validation: local/lint-check mode: required resource: local/api-repo scope: "direct (always active)" note: "This validation will run for ALL plans/projects that access this resource." timing: started: "2026-02-09T10:21:00Z" duration_ms: 42 messages: - "Validation attached" ``` Attaching with validation-specific arguments: === "Rich" 

    $ agents validation attach --project local/api-service local/api-repo local/run-tests --coverage-threshold 90

    ╭─ Validation Attached ──────────────────────────────────────╮
    │ Attachment ID: 01HXM5C3D4E5F6G7H8J9K0L1M2                  │
    │ Validation: local/run-tests                                │
    │ Mode: required                                             │
    │ Resource: local/api-repo                                   │
    │ Scope: project local/api-service                           │
    │ Args: coverage_threshold=90                                │
    ╰────────────────────────────────────────────────────────────╯

    ✓ OK Validation attached
=== "Plain" ``` $ agents validation attach --project local/api-service local/api-repo local/run-tests --coverage-threshold 90 Validation Attached Attachment ID: 01HXM5C3D4E5F6G7H8J9K0L1M2 Validation: local/run-tests Mode: required Resource: local/api-repo Scope: project local/api-service Args: coverage_threshold=90 [OK] Validation attached ``` === "JSON" ```json { "command": "validation attach", "status": "ok", "exit_code": 0, "data": { "validation_attached": { "attachment_id": "01HXM5C3D4E5F6G7H8J9K0L1M2", "validation": "local/run-tests", "mode": "required", "resource": "local/api-repo", "scope": "project local/api-service", "args": { "coverage_threshold": 90 } } }, "timing": { "started": "2026-02-09T10:22:00Z", "duration_ms": 48 }, "messages": ["Validation attached"] } ``` === "YAML" ```yaml command: validation attach status: ok exit_code: 0 data: validation_attached: attachment_id: 01HXM5C3D4E5F6G7H8J9K0L1M2 validation: local/run-tests mode: required resource: local/api-repo scope: project local/api-service args: coverage_threshold: 90 timing: started: "2026-02-09T10:22:00Z" duration_ms: 48 messages: - "Validation attached" ``` ##### agents validation detach 
agents validation detach [--yes|-y] <ATTACHMENT_ID>
**Purpose** Detach a validation by its attachment ULID. The attachment ULID is returned by `agents validation attach` when the attachment is created and is also displayed by `agents tool show ` in the "Attached To" section. Because a validation may be attached to the same resource multiple times — directly, through different projects, through different plans, or even to the same resource and scope with different arguments — the ULID uniquely identifies the specific attachment to remove. The validation itself remains registered in the Tool Registry; only the attachment association is removed. **Arguments** - ``: The ULID of the attachment to remove (returned by `agents validation attach`). - `--yes, -y`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents validation detach 01HXM5A1B2C3D4E5F6G7H8J9K0

    Detach validation local/run-tests from resource local/api-repo (scope: project local/api-service)? [y/N]: y

    ╭─ Validation Detached ───────────────────────────────────────╮
    │ Attachment ID: 01HXM5A1B2C3D4E5F6G7H8J9K0                   │
    │ Validation: local/run-tests                                 │
    │ Resource: local/api-repo                                    │
    │ Scope: project local/api-service                            │
    ╰─────────────────────────────────────────────────────────────╯

    ✓ OK Validation detached
=== "Plain" ``` $ agents validation detach 01HXM5A1B2C3D4E5F6G7H8J9K0 Detach validation local/run-tests from resource local/api-repo (scope: project local/api-service)? [y/N]: y Validation Detached Attachment ID: 01HXM5A1B2C3D4E5F6G7H8J9K0 Validation: local/run-tests Resource: local/api-repo Scope: project local/api-service [OK] Validation detached ``` === "JSON" ```json { "command": "validation detach", "status": "ok", "exit_code": 0, "data": { "validation_detached": { "attachment_id": "01HXM5A1B2C3D4E5F6G7H8J9K0", "validation": "local/run-tests", "resource": "local/api-repo", "scope": "project local/api-service" }, "confirmation": "Detach validation local/run-tests from resource local/api-repo (scope: project local/api-service)? [y/N]: y" }, "timing": { "started": "2026-02-09T10:25:00Z", "duration_ms": 1200 }, "messages": ["Validation detached"] } ``` === "YAML" ```yaml command: validation detach status: ok exit_code: 0 data: validation_detached: attachment_id: 01HXM5A1B2C3D4E5F6G7H8J9K0 validation: local/run-tests resource: local/api-repo scope: project local/api-service confirmation: "Detach validation local/run-tests from resource local/api-repo (scope: project local/api-service)? [y/N]: y" timing: started: "2026-02-09T10:25:00Z" duration_ms: 1200 messages: - "Validation detached" ``` #### agents resource type **Purpose** Manage resource type definitions. Resource types are schema-level definitions that constrain categories of resources — they define what CLI arguments `agents resource add ` accepts, whether instances are physical or virtual, allowed parent/child types, auto-discovery behavior, sandbox strategy, and handler implementation. Built-in types (`git-checkout`, `git`, `fs-mount`, `fs-directory`, and their child types) are hardcoded. Custom types are defined in YAML configuration files and extend the system with new `agents resource add` subcommands. ##### agents resource type add 
agents resource type add --config|-c <FILE> [--update]
**Purpose** Register a new custom resource type. The resource type is fully defined by the YAML configuration file specified with `--config`. **Arguments** - `--config/-c FILE`: Path to the resource type YAML configuration file (required). The file must fully define the resource type, including the `name` field which determines the type's registered name. - `--update`: If the type name already exists, overwrite it. Without this flag, adding a duplicate name fails with an error. **Examples** === "Rich" 

    $ agents resource type add --config ./resource-types/svn.yaml

    ╭─ Resource Type ────────────────────╮
    │ Name: local/svn                    │
    │ Physical/Virtual: physical         │
    │ User Addable: yes                  │
    │ Registered: 2026-02-09 10:15       │
    ╰────────────────────────────────────╯

    ╭─ CLI Arguments ────────────────────────╮
    │ Argument      Required  Description    │
    │ ────────────  ────────  ─────────────  │
    │ --url         yes       Repository URL │
    │ --checkout    no        Local checkout │
    ╰────────────────────────────────────────╯

    ╭─ Child Types ──────────────────────────╮
    │ Auto-discover: svn-revision, svn-file  │
    │ Manual link: fs-mount                  │
    ╰────────────────────────────────────────╯

    ╭─ Sandbox ──────────────────────╮
    │ Strategy: copy_on_write        │
    │ Handler: SVNHandler (custom)   │
    ╰────────────────────────────────╯

    ✓ OK Resource type registered
    ℹ New subcommand available: agents resource add local/svn
=== "Plain" ``` $ agents resource type add --config ./resource-types/svn.yaml Resource Type Name: local/svn Physical/Virtual: physical User Addable: yes Registered: 2026-02-09 10:15 CLI Arguments Argument Required Description ------------ -------- ------------- --url yes Repository URL --checkout no Local checkout Child Types Auto-discover: svn-revision, svn-file Manual link: fs-mount Sandbox Strategy: copy_on_write Handler: SVNHandler (custom) [OK] Resource type registered Info: New subcommand available: agents resource add local/svn ``` === "JSON" ```json { "command": "resource type add", "status": "ok", "exit_code": 0, "data": { "name": "local/svn", "physical_virtual": "physical", "user_addable": true, "registered": "2026-02-09T10:15:00Z", "cli_arguments": [ { "argument": "--url", "required": true, "description": "Repository URL" }, { "argument": "--checkout", "required": false, "description": "Local checkout" } ], "child_types": { "auto_discover": ["svn-revision", "svn-file"], "manual_link": ["fs-mount"] }, "sandbox": { "strategy": "copy_on_write", "handler": "SVNHandler (custom)" } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 85 }, "messages": ["Resource type registered", "New subcommand available: agents resource add local/svn"] } ``` === "YAML" ```yaml command: resource type add status: ok exit_code: 0 data: name: local/svn physical_virtual: physical user_addable: true registered: "2026-02-09T10:15:00Z" cli_arguments: - argument: "--url" required: true description: Repository URL - argument: "--checkout" required: false description: Local checkout child_types: auto_discover: - svn-revision - svn-file manual_link: - fs-mount sandbox: strategy: copy_on_write handler: "SVNHandler (custom)" timing: started: "2026-02-09T10:15:00Z" duration_ms: 85 messages: - "Resource type registered" - "New subcommand available: agents resource add local/svn" ``` ##### agents resource type remove 
agents resource type remove [--yes|-y] <NAME>
!!! warning "Destructive Operation" Remove a custom resource type. ==Built-in types cannot be removed.== Fails if any registered resources currently use this type — remove those resources first. **Arguments** - ``: Resource type name. - `--yes`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents resource type remove local/svn

    Remove resource type local/svn? [y/N]: y

    ╭─ Resource Type Removed ───────╮
    │ Name: local/svn               │
    │ Resources Using: 0            │
    │ Subcommand Removed: yes       │
    ╰───────────────────────────────╯

    ✓ OK Resource type removed
=== "Plain" ``` $ agents resource type remove local/svn Remove resource type local/svn? [y/N]: y Resource Type Removed Name: local/svn Resources Using: 0 Subcommand Removed: yes [OK] Resource type removed ``` === "JSON" ```json { "command": "resource type remove", "status": "ok", "exit_code": 0, "data": { "name": "local/svn", "resources_using": 0, "subcommand_removed": true }, "timing": { "started": "2026-02-09T10:16:00Z", "duration_ms": 60 }, "messages": ["Resource type removed"] } ``` === "YAML" ```yaml command: resource type remove status: ok exit_code: 0 data: name: local/svn resources_using: 0 subcommand_removed: true timing: started: "2026-02-09T10:16:00Z" duration_ms: 60 messages: - "Resource type removed" ``` ##### agents resource type list 
agents resource type list [<REGEX>]
**Purpose** List all registered resource types (built-in and custom). **Arguments** None (use the global `--format` option to control output format). **Examples** === "Rich" 

    $ agents resource type list

    ╭─ Resource Types ──────────────────────────────────────────────────────────────────────────────────╮
    │ Name                 Source    Phys/Virt  Addable  Auto-children                                  │
    │ ───────────────────  ────────  ─────────  ───────  ──────────────────────────────────────         │
    │ git-checkout        built-in  physical   yes      git, fs-directory                               │
    │ git                 built-in  physical   yes      git-remote, git-branch, git-tag,                │
    │                                                    git-commit, git-stash, git-submodule           │
    │ git-remote          built-in  physical   no       (none)                                          │
    │ git-branch          built-in  physical   no       git-commit                                      │
    │ git-tag             built-in  physical   no       (none)                                          │
    │ git-commit          built-in  physical   no       git-tree                                        │
    │ git-tree            built-in  physical   no       git-tree-entry                                  │
    │ git-tree-entry      built-in  physical   no       (none)                                          │
    │ git-stash           built-in  physical   no       (none)                                          │
    │ git-submodule       built-in  physical   no       (none)                                          │
    │ fs-mount            built-in  physical   yes      fs-directory                                    │
    │ fs-directory        built-in  physical   yes      fs-file, fs-directory,                          │
    │                                                    fs-symlink, fs-hardlink                        │
    │ fs-file             built-in  physical   no       (none)                                          │
    │ fs-symlink          built-in  physical   no       (none)                                          │
    │ fs-hardlink         built-in  physical   no       (none)                                          │
    │ file                built-in  virtual    no       (none)                                          │
    │ directory           built-in  virtual    no       (none)                                          │
    │ symlink             built-in  virtual    no       (none)                                          │
    │ commit              built-in  virtual    no       (none)                                          │
    │ branch              built-in  virtual    no       (none)                                          │
    │ tag                 built-in  virtual    no       (none)                                          │
    │ remote              built-in  virtual    no       (none)                                          │
    │ submodule           built-in  virtual    no       (none)                                          │
    │ tree                built-in  virtual    no       (none)                                          │
    │ local/svn           custom    physical   yes      svn-revision, svn-file                          │
    ╰───────────────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ─────────────────╮
    │ Built-in: 24              │
    │ Custom: 1                 │
    │ User Addable: 4           │
    ╰───────────────────────────╯

    ✓ OK 25 resource types listed
=== "Plain" ``` $ agents resource type list Resource Types ------------------- Name Source Phys/Virt Addable Auto-children ------------------- -------- --------- ------- -------------------------------------- git-checkout built-in physical yes git, fs-directory git built-in physical yes git-remote, git-branch, git-tag, git-commit, git-stash, git-submodule git-remote built-in physical no (none) git-branch built-in physical no git-commit git-tag built-in physical no (none) git-commit built-in physical no git-tree git-tree built-in physical no git-tree-entry git-tree-entry built-in physical no (none) git-stash built-in physical no (none) git-submodule built-in physical no (none) fs-mount built-in physical yes fs-directory fs-directory built-in physical yes fs-file, fs-directory, fs-symlink, fs-hardlink fs-file built-in physical no (none) fs-symlink built-in physical no (none) fs-hardlink built-in physical no (none) file built-in virtual no (none) directory built-in virtual no (none) symlink built-in virtual no (none) commit built-in virtual no (none) branch built-in virtual no (none) tag built-in virtual no (none) remote built-in virtual no (none) submodule built-in virtual no (none) tree built-in virtual no (none) local/svn custom physical yes svn-revision, svn-file Summary Built-in: 24 Custom: 1 User Addable: 4 [OK] 25 resource types listed ``` === "JSON" ```json { "command": "resource type list", "status": "ok", "exit_code": 0, "data": { "resource_types": [ { "name": "git-checkout", "source": "built-in", "physical_virtual": "physical", "addable": true, "auto_children": ["git", "fs-directory"] }, { "name": "git", "source": "built-in", "physical_virtual": "physical", "addable": true, "auto_children": ["git-remote", "git-branch", "git-tag", "git-commit", "git-stash", "git-submodule"] }, { "name": "git-remote", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "git-branch", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": ["git-commit"] }, { "name": "git-tag", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "git-commit", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": ["git-tree"] }, { "name": "git-tree", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": ["git-tree-entry"] }, { "name": "git-tree-entry", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "git-stash", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "git-submodule", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "fs-mount", "source": "built-in", "physical_virtual": "physical", "addable": true, "auto_children": ["fs-directory"] }, { "name": "fs-directory", "source": "built-in", "physical_virtual": "physical", "addable": true, "auto_children": ["fs-file", "fs-directory", "fs-symlink", "fs-hardlink"] }, { "name": "fs-file", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "fs-symlink", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "fs-hardlink", "source": "built-in", "physical_virtual": "physical", "addable": false, "auto_children": [] }, { "name": "file", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "directory", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "symlink", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "commit", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "branch", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "tag", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "remote", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "submodule", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "tree", "source": "built-in", "physical_virtual": "virtual", "addable": false, "auto_children": [] }, { "name": "local/svn", "source": "custom", "physical_virtual": "physical", "addable": true, "auto_children": ["svn-revision", "svn-file"] } ], "summary": { "built_in": 24, "custom": 1, "user_addable": 4 } }, "timing": { "started": "2026-02-09T10:16:00Z", "duration_ms": 45 }, "messages": ["25 resource types listed"] } ``` === "YAML" ```yaml command: resource type list status: ok exit_code: 0 data: resource_types: - name: git-checkout source: built-in physical_virtual: physical addable: true auto_children: [git, fs-directory] - name: git source: built-in physical_virtual: physical addable: true auto_children: [git-remote, git-branch, git-tag, git-commit, git-stash, git-submodule] - name: git-remote source: built-in physical_virtual: physical addable: false auto_children: [] - name: git-branch source: built-in physical_virtual: physical addable: false auto_children: [git-commit] - name: git-tag source: built-in physical_virtual: physical addable: false auto_children: [] - name: git-commit source: built-in physical_virtual: physical addable: false auto_children: [git-tree] - name: git-tree source: built-in physical_virtual: physical addable: false auto_children: [git-tree-entry] - name: git-tree-entry source: built-in physical_virtual: physical addable: false auto_children: [] - name: git-stash source: built-in physical_virtual: physical addable: false auto_children: [] - name: git-submodule source: built-in physical_virtual: physical addable: false auto_children: [] - name: fs-mount source: built-in physical_virtual: physical addable: true auto_children: [fs-directory] - name: fs-directory source: built-in physical_virtual: physical addable: true auto_children: [fs-file, fs-directory, fs-symlink, fs-hardlink] - name: fs-file source: built-in physical_virtual: physical addable: false auto_children: [] - name: fs-symlink source: built-in physical_virtual: physical addable: false auto_children: [] - name: fs-hardlink source: built-in physical_virtual: physical addable: false auto_children: [] - name: file source: built-in physical_virtual: virtual addable: false auto_children: [] - name: directory source: built-in physical_virtual: virtual addable: false auto_children: [] - name: symlink source: built-in physical_virtual: virtual addable: false auto_children: [] - name: commit source: built-in physical_virtual: virtual addable: false auto_children: [] - name: branch source: built-in physical_virtual: virtual addable: false auto_children: [] - name: tag source: built-in physical_virtual: virtual addable: false auto_children: [] - name: remote source: built-in physical_virtual: virtual addable: false auto_children: [] - name: submodule source: built-in physical_virtual: virtual addable: false auto_children: [] - name: tree source: built-in physical_virtual: virtual addable: false auto_children: [] - name: local/svn source: custom physical_virtual: physical addable: true auto_children: [svn-revision, svn-file] summary: built_in: 24 custom: 1 user_addable: 4 timing: started: "2026-02-09T10:16:00Z" duration_ms: 45 messages: - "25 resource types listed" ``` ##### agents resource type show 
agents resource type show <NAME>
**Purpose** Show detailed information about a resource type, including its full schema. **Arguments** - ``: Resource type name. **Examples** === "Rich" 

    $ agents resource type show git-checkout

    ╭─ Resource Type ──────────────────────────────────────────────────────╮
    │ Name: git-checkout                                                   │
    │ Source: built-in                                                     │
    │ Description: A locally checked-out git repository with worktree      │
    │ Physical/Virtual: physical                                           │
    │ User Addable: yes                                                    │
    ╰──────────────────────────────────────────────────────────────────────╯

    ╭─ CLI Arguments (agents resource add git-checkout) ─────────────────╮
    │ Argument    Required  Type    Description                          │
    │ ──────────  ────────  ──────  ──────────────────────────────       │
    │ --path      yes       path    Local checkout directory             │
    │ --branch    no        string  Default branch (default: main)       │
    ╰────────────────────────────────────────────────────────────────────╯

    ╭─ Parent Types ───────────────╮
    │ Allowed: (any, top-level OK) │
    ╰──────────────────────────────╯

    ╭─ Child Types ────────────────────────────────────────────────────╮
    │ Type           Auto  Manual Link  Description                    │
    │ ─────────────  ────  ───────────  ──────────────────────────     │
    │ git            yes   no           Repo object DB and history     │
    │ fs-directory   yes   no           Worktree root directory        │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Sandbox ──────────────────────╮
    │ Strategy: git_worktree         │
    │ Checkpointable: yes            │
    │ Handler: GitCheckoutHandler    │
    ╰────────────────────────────────╯

    ✓ OK Resource type details loaded
=== "Plain" ``` $ agents resource type show git-checkout Resource Type Name: git-checkout Source: built-in Description: A locally checked-out git repository with worktree Physical/Virtual: physical User Addable: yes CLI Arguments (agents resource add git-checkout) Argument Required Type Description ---------- -------- ------ ------------------------------ --path yes path Local checkout directory --branch no string Default branch (default: main) Parent Types Allowed: (any, top-level OK) Child Types Type Auto Manual Link Description ------------- ---- ----------- -------------------------- git yes no Repo object DB and history fs-directory yes no Worktree root directory Sandbox Strategy: git_worktree Checkpointable: yes Handler: GitCheckoutHandler [OK] Resource type details loaded ``` === "JSON" ```json { "command": "resource type show", "status": "ok", "exit_code": 0, "data": { "name": "git-checkout", "source": "built-in", "description": "A locally checked-out git repository with worktree", "physical_virtual": "physical", "user_addable": true, "cli_arguments": [ { "argument": "--path", "required": true, "type": "path", "description": "Local checkout directory" }, { "argument": "--branch", "required": false, "type": "string", "description": "Default branch (default: main)" } ], "parent_types": { "allowed": "any", "top_level": true }, "child_types": [ { "type": "git", "auto": true, "manual_link": false, "description": "Repo object DB and history" }, { "type": "fs-directory", "auto": true, "manual_link": false, "description": "Worktree root directory" } ], "sandbox": { "strategy": "git_worktree", "checkpointable": true, "handler": "GitCheckoutHandler" } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 42 }, "messages": ["Resource type details loaded"] } ``` === "YAML" ```yaml command: resource type show status: ok exit_code: 0 data: name: git-checkout source: built-in description: "A locally checked-out git repository with worktree" physical_virtual: physical user_addable: true cli_arguments: - argument: "--path" required: true type: path description: "Local checkout directory" - argument: "--branch" required: false type: string description: "Default branch (default: main)" parent_types: allowed: any top_level: true child_types: - type: git auto: true manual_link: false description: "Repo object DB and history" - type: fs-directory auto: true manual_link: false description: "Worktree root directory" sandbox: strategy: git_worktree checkpointable: true handler: GitCheckoutHandler timing: started: "2026-02-09T10:15:00Z" duration_ms: 42 messages: - "Resource type details loaded" ``` #### agents resource !!! info "Purpose" Manage independently registered ==resources==. Resources represent anything that can be read, written, or queried — git repositories, filesystems, databases, APIs, and more. Resources are registered independently of projects and linked to one or more projects via `agents project link-resource`. Resources form a ==directed acyclic graph (DAG)== with parent/child relationships, and child resources are often auto-discovered when a parent resource is registered. ??? example "Supported Resource Types" | Type | Physical | Description | | :--- | :------: | :---------- | | `git-checkout` | Yes | Local git working directory | | `git` | Yes | Bare git repository | | `fs-mount` | Yes | Filesystem mount point | | `fs-directory` | Virtual | Directory within a mount | | `fs-file` | Virtual | Individual file reference | | `container-instance` | Yes | Container instance ([ADR-039](adr/ADR-039-container-resource-types.md)) | | `devcontainer-instance` | Yes | Devcontainer instance ([ADR-043](adr/ADR-043-devcontainer-integration.md)) | | Custom types | Varies | Registered via `agents resource type add` | ##### agents resource add 
agents resource add [(--description|-d) <DESC>] [--update] <TYPE> <NAME> [type-specific-flags...]
**Purpose** Register a new resource. Every resource receives a system-assigned ULID. User-added resources also require a namespaced name (`[[server:]namespace/]name`) specified at creation time. The `add` command uses type-specific subcommands — each registered resource type (built-in or custom) provides its own subcommand with type-appropriate arguments. On success, the command returns both the name and the ULID assigned to the newly created resource. **Arguments** - ``: Resource type name (e.g., `git-checkout`, `git`, `fs-mount`, `fs-directory`, `local/svn`). Determines type-specific flags. - ``: Namespaced resource name (positional, required). Must be globally unique following the standard `[[server:]namespace/]name` format. - `--description/-d TEXT`: Optional resource description. Type-specific flags depend on the resource type. See `agents resource type show ` for available arguments. **Container-specific flags** (for `container-instance` and `devcontainer-instance` types): - `--image IMAGE_REF`: Container image reference (e.g., `ubuntu:latest`, `python:3.12-slim`). Required for `container-instance` when `--container-id` is not provided. Not required for `devcontainer-instance` (image is derived from `devcontainer.json`). - `--mount RESOURCE_OR_PATH:CONTAINER_PATH`: Mount a resource or host path into the container (repeatable). Accepts either a resource reference (`local/api-repo:/workspace`) or a raw host path (`/home/user/projects/api:/workspace`). See [ADR-043 §3.2](adr/ADR-043-devcontainer-integration.md). - `--clone-into REPO_URL:CONTAINER_PATH`: Clone a remote repository into the container at the specified path. The clone happens lazily on first container start. The command returns the name and ULID of the newly created resource. Auto-discovered child resources are created automatically with ULIDs only (no names). **Examples** === "Rich" 

    $ agents resource add git-checkout local/api-repo --path /home/user/projects/api-service --branch main

    ╭─ Resource ──────────────────────────────────────╮
    │ Name: local/api-repo                            │
    │ ID: 01HXR1A1B2C3D4E5F6G7H8J9K0                  │
    │ Type: git-checkout                              │
    │ Physical/Virtual: physical                      │
    │ Path: /home/user/projects/api-service           │
    │ Branch: main                                    │
    │ Created: 2026-02-09 10:20                       │
    ╰─────────────────────────────────────────────────╯

    ╭─ Auto-discovered Children ─────────────────────────────────────────╮
    │ ID               Type            Status                            │
    │ ───────────────  ──────────────  ─────────────────                 │
    │ 01HXR1A1B2C3…   git             created                            │
    │ 01HXR1A1B2C4…   git-remote      created                            │
    │ 01HXR1A1B2C5…   git-branch      created                            │
    │ 01HXR1A1B2C6…   git-branch      created                            │
    │ 01HXR1A1B2C7…   fs-directory    created                            │
    │   + 47 git-commit resources                                        │
    │   + 312 git-tree-entry resources                                   │
    │   + 3 fs-directory + 28 fs-file                                    │
    ╰────────────────────────────────────────────────────────────────────╯

    ╭─ Capabilities ─────────────────╮
    │ Readable: yes                  │
    │ Writable: yes                  │
    │ Sandboxable: yes               │
    │ Checkpointable: yes            │
    │ Sandbox Strategy: git_worktree │
    ╰────────────────────────────────╯

    ✓ OK Resource registered (395 child resources discovered)
    

    $ agents resource add fs-mount local/docs --mount-path /docs/api-reference

    ╭─ Resource ──────────────────────────────────────╮
    │ Name: local/docs                                │
    │ ID: 01HXR2B3C4D5E6F7G8H9J0K1L2                  │
    │ Type: fs-mount                                  │
    │ Physical/Virtual: physical                      │
    │ Mount Path: /docs/api-reference                 │
    │ Created: 2026-02-09 10:22                       │
    ╰─────────────────────────────────────────────────╯

    ╭─ Auto-discovered Children ────────────────────╮
    │   + 1 fs-directory (root)                     │
    │   + 3 fs-directory resources                  │
    │   + 28 fs-file resources                      │
    ╰───────────────────────────────────────────────╯

    ╭─ Capabilities ──────────────────────╮
    │ Readable: yes                       │
    │ Writable: yes                       │
    │ Sandboxable: yes                    │
    │ Checkpointable: yes                 │
    │ Sandbox Strategy: copy_on_write     │
    ╰─────────────────────────────────────╯

    ✓ OK Resource registered (31 child resources discovered)
    

    $ agents resource add container-instance local/api-dev --mount local/api-repo:/workspace --mount /home/user/.config/nvim:/home/dev/.config/nvim

    ╭─ Resource ──────────────────────────────────────╮
    │ Name: local/api-dev                             │
    │ ID: 01HXR3C4D5E6F7G8H9J0K1L2M3                  │
    │ Type: container-instance                        │
    │ Physical/Virtual: physical                      │
    │ State: created (not started)                    │
    │ Created: 2026-02-09 10:25                       │
    ╰─────────────────────────────────────────────────╯

    ╭─ Mounts ──────────────────────────────────────────────────────────╮
    │ Source                            Container Path   Kind           │
    │ ────────────────────────────────  ───────────────  ───────────    │
    │ local/api-repo                    /workspace       resource-ref   │
    │ /home/user/.config/nvim           /home/dev/…      host-path      │
    ╰───────────────────────────────────────────────────────────────────╯

    ✓ OK Container resource registered (container will start on first access)
    

    $ agents resource add container-instance cloud/ci-runner --clone-into https://github.com/acme/api.git:/workspace

    ╭─ Resource ──────────────────────────────────────╮
    │ Name: cloud/ci-runner                           │
    │ ID: 01HXR4D5E6F7G8H9J0K1L2M3N4                  │
    │ Type: container-instance                        │
    │ Physical/Virtual: physical                      │
    │ State: created (not started)                    │
    │ Clone: https://github.com/acme/api.git          │
    │ Clone Target: /workspace                        │
    │ Created: 2026-02-09 10:27                       │
    ╰─────────────────────────────────────────────────╯

    ✓ OK Container resource registered (repo will be cloned on first start)
    

    $ agents resource add git-checkout local/webapp --path /home/user/projects/webapp

    ╭─ Resource ──────────────────────────────────────────╮
    │ Name: local/webapp                                  │
    │ ID: 01HXR5E6F7G8H9J0K1L2M3N4O5                      │
    │ Type: git-checkout                                  │
    │ Physical/Virtual: physical                          │
    │ Path: /home/user/projects/webapp                    │
    │ Branch: main                                        │
    │ Created: 2026-02-09 10:30                           │
    ╰─────────────────────────────────────────────────────╯

    ╭─ Auto-discovered Children ─────────────────────────────────────────╮
    │ ID               Type                    Status                    │
    │ ───────────────  ──────────────────────  ───────────────────       │
    │ 01HXR5E6F7G9…   git                     created                    │
    │ 01HXR5E6F7GA…   devcontainer-instance   detected (not built)       │
    │ 01HXR5E6F7GB…   fs-directory            created                    │
    │   + 52 git-commit resources                                        │
    │   + 189 git-tree-entry resources                                   │
    ╰────────────────────────────────────────────────────────────────────╯

    ⚠ Devcontainer detected at .devcontainer/devcontainer.json
      Container will be built lazily on first access.
      Use agents resource show 01HXR5E6F7GA… to inspect.

    ✓ OK Resource registered (245 child resources discovered)
=== "Plain" ``` $ agents resource add git-checkout local/api-repo --path /home/user/projects/api-service --branch main Resource Name: local/api-repo ID: 01HXR1A1B2C3D4E5F6G7H8J9K0 Type: git-checkout Physical/Virtual: physical Path: /home/user/projects/api-service Branch: main Created: 2026-02-09 10:20 Auto-discovered Children ID Type Status --------------- -------------- ----------------- 01HXR1A1B2C3.. git created 01HXR1A1B2C4.. git-remote created 01HXR1A1B2C5.. git-branch created 01HXR1A1B2C6.. git-branch created 01HXR1A1B2C7.. fs-directory created + 47 git-commit resources + 312 git-tree-entry resources + 3 fs-directory + 28 fs-file Capabilities Readable: yes Writable: yes Sandboxable: yes Checkpointable: yes Sandbox Strategy: git_worktree [OK] Resource registered (395 child resources discovered) $ agents resource add fs-mount local/docs --mount-path /docs/api-reference Resource Name: local/docs ID: 01HXR2B3C4D5E6F7G8H9J0K1L2 Type: fs-mount Physical/Virtual: physical Mount Path: /docs/api-reference Created: 2026-02-09 10:22 Auto-discovered Children + 1 fs-directory (root) + 3 fs-directory resources + 28 fs-file resources Capabilities Readable: yes Writable: yes Sandboxable: yes Checkpointable: yes Sandbox Strategy: copy_on_write [OK] Resource registered (31 child resources discovered) $ agents resource add container-instance local/api-dev --mount local/api-repo:/workspace --mount /home/user/.config/nvim:/home/dev/.config/nvim Resource Name: local/api-dev ID: 01HXR3C4D5E6F7G8H9J0K1L2M3 Type: container-instance Physical/Virtual: physical State: created (not started) Created: 2026-02-09 10:25 Mounts Source Container Path Kind -------------------------------- --------------- --------- local/api-repo /workspace resource-ref /home/user/.config/nvim /home/dev/... host-path [OK] Container resource registered (container will start on first access) $ agents resource add container-instance cloud/ci-runner --clone-into https://github.com/acme/api.git:/workspace Resource Name: cloud/ci-runner ID: 01HXR4D5E6F7G8H9J0K1L2M3N4 Type: container-instance Physical/Virtual: physical State: created (not started) Clone: https://github.com/acme/api.git Clone Target: /workspace Created: 2026-02-09 10:27 [OK] Container resource registered (repo will be cloned on first start) $ agents resource add git-checkout local/webapp --path /home/user/projects/webapp Resource Name: local/webapp ID: 01HXR5E6F7G8H9J0K1L2M3N4O5 Type: git-checkout Physical/Virtual: physical Path: /home/user/projects/webapp Branch: main Created: 2026-02-09 10:30 Auto-discovered Children ID Type Status --------------- ---------------------- ----------------- 01HXR5E6F7G9.. git created 01HXR5E6F7GA.. devcontainer-instance detected (not built) 01HXR5E6F7GB.. fs-directory created + 52 git-commit resources + 189 git-tree-entry resources [WARN] Devcontainer detected at .devcontainer/devcontainer.json Container will be built lazily on first access. Use agents resource show 01HXR5E6F7GA… to inspect. [OK] Resource registered (245 child resources discovered) ``` === "JSON" ```json { "command": "resource add", "status": "ok", "exit_code": 0, "data": { "name": "local/api-repo", "id": "01HXR1A1B2C3D4E5F6G7H8J9K0", "type": "git-checkout", "physical_virtual": "physical", "path": "/home/user/projects/api-service", "branch": "main", "created": "2026-02-09T10:20:00Z", "auto_discovered_children": [ { "id": "01HXR1A1B2C3…", "type": "git", "status": "created" }, { "id": "01HXR1A1B2C4…", "type": "git-remote", "status": "created" }, { "id": "01HXR1A1B2C5…", "type": "git-branch", "status": "created" }, { "id": "01HXR1A1B2C6…", "type": "git-branch", "status": "created" }, { "id": "01HXR1A1B2C7…", "type": "fs-directory", "status": "created" } ], "children_summary": { "git_commit": 47, "git_tree_entry": 312, "fs_directory": 3, "fs_file": 28 }, "total_children": 395, "capabilities": { "readable": true, "writable": true, "sandboxable": true, "checkpointable": true, "sandbox_strategy": "git_worktree" } }, "timing": { "started": "2026-02-09T10:20:00Z", "duration_ms": 250 }, "messages": ["Resource registered (395 child resources discovered)"] } ``` === "YAML" ```yaml command: resource add status: ok exit_code: 0 data: name: local/api-repo id: 01HXR1A1B2C3D4E5F6G7H8J9K0 type: git-checkout physical_virtual: physical path: /home/user/projects/api-service branch: main created: "2026-02-09T10:20:00Z" auto_discovered_children: - id: "01HXR1A1B2C3\u2026" type: git status: created - id: "01HXR1A1B2C4\u2026" type: git-remote status: created - id: "01HXR1A1B2C5\u2026" type: git-branch status: created - id: "01HXR1A1B2C6\u2026" type: git-branch status: created - id: "01HXR1A1B2C7\u2026" type: fs-directory status: created children_summary: git_commit: 47 git_tree_entry: 312 fs_directory: 3 fs_file: 28 total_children: 395 capabilities: readable: true writable: true sandboxable: true checkpointable: true sandbox_strategy: git_worktree timing: started: "2026-02-09T10:20:00Z" duration_ms: 250 messages: - "Resource registered (395 child resources discovered)" ``` ##### agents resource remove 
agents resource remove [--yes|-y] <NAME>
!!! danger "Cascading Deletion" Removes a registered resource ==and all its auto-discovered child resources==. A `git-checkout` resource can have hundreds of child resources (files, directories). This operation fails if the resource is linked to any project — use `agents project unlink-resource` first. **Arguments** - ``: Resource name (only user-added resources can be removed). - `--yes`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents resource remove local/api-repo

    Remove resource local/api-repo and 395 child resources? [y/N]: y

    ╭─ Resource Removed ──────────────────────────────────╮
    │ Name: local/api-repo                                │
    │ Type: git-checkout                                  │
    │ Children Removed: 395                               │
    │ Projects Unlinked: 0                                │
    ╰─────────────────────────────────────────────────────╯

    ✓ OK Resource removed
=== "Plain" ``` $ agents resource remove local/api-repo Remove resource local/api-repo and 395 child resources? [y/N]: y Resource Removed Name: local/api-repo Type: git-checkout Children Removed: 395 Projects Unlinked: 0 [OK] Resource removed ``` === "JSON" ```json { "command": "resource remove", "status": "ok", "exit_code": 0, "data": { "name": "local/api-repo", "type": "git-checkout", "children_removed": 395, "projects_unlinked": 0 }, "timing": { "started": "2026-02-09T10:24:00Z", "duration_ms": 120 }, "messages": ["Resource removed"] } ``` === "YAML" ```yaml command: resource remove status: ok exit_code: 0 data: name: local/api-repo type: git-checkout children_removed: 395 projects_unlinked: 0 timing: started: "2026-02-09T10:24:00Z" duration_ms: 120 messages: - "Resource removed" ``` ##### agents resource list 
agents resource list [--all] [(--type|-t) <TYPE>]
**Purpose** List registered resources with optional filters. By default, lists only user-added (named) resources. Use `--all` to include auto-discovered child resources. **Arguments** - `--type/-t TYPE`: Filter by resource type (accepts a regex). - `--all`: Include auto-discovered child resources (by default only user-added resources are shown). **Examples** === "Rich" 

    $ agents resource list

    ╭─ Resources ──────────────────────────────────────────────────────────────────────────────────────────────╮
    │ Name               ID                            Type         Phys/Virt  Children  Projects              │
    │ ─────────────────  ────────────────────────────  ───────────  ─────────  ────────  ────────────────      │
    │ local/api-repo     01HXR1A1B2C3D4E5F6G7H8J9K0    git-checkout physical   395       local/api-service     │
    │ local/docs         01HXR2B2C3D4E5F6G7H8J9K0L1    fs-mount     physical   32        local/api-service     │
    │ local/staging-db   01HXR3C3D4E5F6G7H8J9K0L1M2    database     physical   12        local/api-service,    │
    │                                                                                    local/staging         │
    ╰──────────────────────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ───────────╮
    │ Total: 3            │
    │ Physical: 3         │
    │ Virtual: 0          │
    │ Total Children: 405 │
    ╰─────────────────────╯

    ✓ OK 3 resources listed
=== "Plain" ``` $ agents resource list Resources --------- Name ID Type Phys/Virt Children Projects ----------------- ---------------------------- ----------- --------- -------- ---------------- local/api-repo 01HXR1A1B2C3D4E5F6G7H8J9K0 git-checkout physical 395 local/api-service local/docs 01HXR2B2C3D4E5F6G7H8J9K0L1 fs-mount physical 32 local/api-service local/staging-db 01HXR3C3D4E5F6G7H8J9K0L1M2 database physical 12 local/api-service, local/staging Summary Total: 3 Physical: 3 Virtual: 0 Total Children: 405 [OK] 3 resources listed ``` === "JSON" ```json { "command": "resource list", "status": "ok", "exit_code": 0, "data": { "resources": [ { "name": "local/api-repo", "id": "01HXR1A1B2C3D4E5F6G7H8J9K0", "type": "git-checkout", "physical_virtual": "physical", "children": 395, "projects": ["local/api-service"] }, { "name": "local/docs", "id": "01HXR2B2C3D4E5F6G7H8J9K0L1", "type": "fs-mount", "physical_virtual": "physical", "children": 32, "projects": ["local/api-service"] }, { "name": "local/staging-db", "id": "01HXR3C3D4E5F6G7H8J9K0L1M2", "type": "database", "physical_virtual": "physical", "children": 12, "projects": ["local/api-service", "local/staging"] } ], "summary": { "total": 3, "physical": 3, "virtual": 0, "total_children": 405 } }, "timing": { "started": "2026-02-09T10:25:00Z", "duration_ms": 90 }, "messages": ["3 resources listed"] } ``` === "YAML" ```yaml command: resource list status: ok exit_code: 0 data: resources: - name: local/api-repo id: 01HXR1A1B2C3D4E5F6G7H8J9K0 type: git-checkout physical_virtual: physical children: 395 projects: - local/api-service - name: local/docs id: 01HXR2B2C3D4E5F6G7H8J9K0L1 type: fs-mount physical_virtual: physical children: 32 projects: - local/api-service - name: local/staging-db id: 01HXR3C3D4E5F6G7H8J9K0L1M2 type: database physical_virtual: physical children: 12 projects: - local/api-service - local/staging summary: total: 3 physical: 3 virtual: 0 total_children: 405 timing: started: "2026-02-09T10:25:00Z" duration_ms: 90 messages: - "3 resources listed" ``` ##### agents resource show 
agents resource show <RESOURCE>
**Purpose** Show detailed information about a registered resource including its type, capabilities, parent/child relationships, and linked projects. **Arguments** - ``: Resource name or ULID. **Examples** === "Rich" 

    $ agents resource show local/api-repo

    ╭─ Resource ─────────────────────────────────────────╮
    │ Name: local/api-repo                               │
    │ ID: 01HXR1A1B2C3D4E5F6G7H8J9K0                     │
    │ Type: git-checkout                                 │
    │ Physical/Virtual: physical                         │
    │ Path: /home/user/projects/api-service              │
    │ Branch: main                                       │
    │ Created: 2026-02-09 10:20                          │
    ╰────────────────────────────────────────────────────╯

    ╭─ Capabilities ────────────────────╮
    │ Readable: yes                     │
    │ Writable: yes                     │
    │ Sandboxable: yes                  │
    │ Checkpointable: yes               │
    │ Sandbox Strategy: git_worktree    │
    ╰───────────────────────────────────╯

    ╭─ Parents ────╮
    │ (top-level)  │
    ╰──────────────╯

    ╭─ Direct Children ──────────────────────────────────────────────────────╮
    │ ID                            Type          Auto  Children             │
    │ ────────────────────────────  ────────────  ────  ────────             │
    │ 01HXR4D4E5F6G7H8J9K0L1M2N3    git           yes   363                  │
    │ 01HXR5E5F6G7H8J9K0L1M2N3P4    fs-directory  yes   32                   │
    ╰────────────────────────────────────────────────────────────────────────╯

    ╭─ Linked Projects ─────────────╮
    │ - local/api-service (r/w)     │
    ╰───────────────────────────────╯

    ╭─ Tool Bindings ────────────────────────────────╮
    │ Tool                      Slot   Access        │
    │ ────────────────────────  ─────  ───────────   │
    │ (builtin) git_status      repo   read_only     │
    │ (builtin) git_diff        repo   read_only     │
    │ (builtin) git_log         repo   read_only     │
    │ local/run-migrations      db     (not bound)   │
    ╰────────────────────────────────────────────────╯

    ✓ OK Resource details loaded
=== "Plain" ``` $ agents resource show local/api-repo Resource Name: local/api-repo ID: 01HXR1A1B2C3D4E5F6G7H8J9K0 Type: git-checkout Physical/Virtual: physical Path: /home/user/projects/api-service Branch: main Created: 2026-02-09 10:20 Capabilities Readable: yes Writable: yes Sandboxable: yes Checkpointable: yes Sandbox Strategy: git_worktree Parents (top-level) Direct Children ID Type Auto Children ---------------------------- ------------ ---- -------- 01HXR4D4E5F6G7H8J9K0L1M2N3 git yes 363 01HXR5E5F6G7H8J9K0L1M2N3P4 fs-directory yes 32 Linked Projects - local/api-service (r/w) Tool Bindings Tool Slot Access ------------------------ ----- ----------- (builtin) git_status repo read_only (builtin) git_diff repo read_only (builtin) git_log repo read_only local/run-migrations db (not bound) [OK] Resource details loaded ``` === "JSON" ```json { "command": "resource show", "status": "ok", "exit_code": 0, "data": { "name": "local/api-repo", "id": "01HXR1A1B2C3D4E5F6G7H8J9K0", "type": "git-checkout", "physical_virtual": "physical", "path": "/home/user/projects/api-service", "branch": "main", "created": "2026-02-09T10:20:00Z", "capabilities": { "readable": true, "writable": true, "sandboxable": true, "checkpointable": true, "sandbox_strategy": "git_worktree" }, "parents": ["(top-level)"], "direct_children": [ { "id": "01HXR4D4E5F6G7H8J9K0L1M2N3", "type": "git", "auto": true, "children": 363 }, { "id": "01HXR5E5F6G7H8J9K0L1M2N3P4", "type": "fs-directory", "auto": true, "children": 32 } ], "linked_projects": [ { "name": "local/api-service", "access": "r/w" } ], "tool_bindings": [ { "tool": "(builtin) git_status", "slot": "repo", "access": "read_only" }, { "tool": "(builtin) git_diff", "slot": "repo", "access": "read_only" }, { "tool": "(builtin) git_log", "slot": "repo", "access": "read_only" }, { "tool": "local/run-migrations", "slot": "db", "access": "(not bound)" } ] }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 65 }, "messages": ["Resource details loaded"] } ``` === "YAML" ```yaml command: resource show status: ok exit_code: 0 data: name: local/api-repo id: 01HXR1A1B2C3D4E5F6G7H8J9K0 type: git-checkout physical_virtual: physical path: /home/user/projects/api-service branch: main created: "2026-02-09T10:20:00Z" capabilities: readable: true writable: true sandboxable: true checkpointable: true sandbox_strategy: git_worktree parents: - (top-level) direct_children: - id: 01HXR4D4E5F6G7H8J9K0L1M2N3 type: git auto: true children: 363 - id: 01HXR5E5F6G7H8J9K0L1M2N3P4 type: fs-directory auto: true children: 32 linked_projects: - name: local/api-service access: r/w tool_bindings: - tool: (builtin) git_status slot: repo access: read_only - tool: (builtin) git_diff slot: repo access: read_only - tool: (builtin) git_log slot: repo access: read_only - tool: local/run-migrations slot: db access: (not bound) timing: started: "2026-02-09T10:15:00Z" duration_ms: 65 messages: - Resource details loaded ``` ##### agents resource inspect 
agents resource inspect [--tree] [--file <PATH>] <RESOURCE>
**Purpose** Inspect a resource's contents. For file-based resources (git checkouts, filesystem mounts, directories), displays the file tree or the contents of a specific file. Works with any resource — user-added or auto-discovered — via name or ULID. **Arguments** - ``: Resource name or ULID. - `--tree`: Show the resource's file/content tree. - `--file PATH`: Show contents of a specific file within the resource. **Examples** === "Rich" 

    $ agents resource inspect local/api-repo --tree

    ╭─ Resource Tree: local/api-repo ──────────────────────────────────────╮
    │                                                                      │
    │ /home/user/projects/api-service                                      │
    │ ├── src/                                                             │
    │ │   ├── api/                                                         │
    │ │   │   ├── __init__.py                                                  │
    │ │   │   ├── auth/                                                    │
    │ │   │   │   ├── auth_middleware.py                                   │
    │ │   │   │   ├── token_service.py                                     │
    │ │   │   │   └── rbac.py                                              │
    │ │   │   ├── routes/                                                  │
    │ │   │   └── models/                                                  │
    │ │   └── utils/                                                       │
    │ ├── tests/                                                           │
    │ ├── README.md                                                        │
    │ └── pyproject.toml                                                   │
    │                                                                      │
    ╰──────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ──────────────╮
    │ Directories: 8         │
    │ Files: 41              │
    │ Total Size: 284 KB     │
    ╰────────────────────────╯

    ✓ OK Resource tree displayed
=== "Plain" ``` $ agents resource inspect local/api-repo --tree Resource Tree: local/api-repo /home/user/projects/api-service +-- src/ | +-- api/ | | +-- __init__.py | | +-- auth/ | | | +-- auth_middleware.py | | | +-- token_service.py | | | +-- rbac.py | | +-- routes/ | | +-- models/ | +-- utils/ +-- tests/ +-- README.md +-- pyproject.toml Summary Directories: 8 Files: 41 Total Size: 284 KB [OK] Resource tree displayed ``` === "JSON" ```json { "command": "resource inspect", "status": "ok", "exit_code": 0, "data": { "resource": "local/api-repo", "mode": "tree", "root": "/home/user/projects/api-service", "tree": [ { "name": "src/", "type": "directory", "children": [ { "name": "api/", "type": "directory", "children": [ { "name": "__init__.py", "type": "file" }, { "name": "auth/", "type": "directory", "children": [ { "name": "auth_middleware.py", "type": "file" }, { "name": "token_service.py", "type": "file" }, { "name": "rbac.py", "type": "file" } ] }, { "name": "routes/", "type": "directory" }, { "name": "models/", "type": "directory" } ] }, { "name": "utils/", "type": "directory" } ] }, { "name": "tests/", "type": "directory" }, { "name": "README.md", "type": "file" }, { "name": "pyproject.toml", "type": "file" } ], "summary": { "directories": 8, "files": 41, "total_size": "284 KB" } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 150 }, "messages": ["Resource tree displayed"] } ``` === "YAML" ```yaml command: resource inspect status: ok exit_code: 0 data: resource: local/api-repo mode: tree root: /home/user/projects/api-service tree: - name: src/ type: directory children: - name: api/ type: directory children: - name: __init__.py type: file - name: auth/ type: directory children: - name: auth_middleware.py type: file - name: token_service.py type: file - name: rbac.py type: file - name: routes/ type: directory - name: models/ type: directory - name: utils/ type: directory - name: tests/ type: directory - name: README.md type: file - name: pyproject.toml type: file summary: directories: 8 files: 41 total_size: 284 KB timing: started: "2026-02-09T10:15:00Z" duration_ms: 150 messages: - Resource tree displayed ``` === "Rich" 

    $ agents resource inspect local/api-repo --file src/api/auth/auth_middleware.py

    ╭─ File: src/api/auth/auth_middleware.py ──────────────────╮
    │ Resource: local/api-repo                                 │
    │ Size: 2.4 KB                                             │
    │ Language: Python                                         │
    │ Last Modified: 2026-02-10 14:32                          │
    ╰──────────────────────────────────────────────────────────╯

      1 │ from fastapi import Request, HTTPException
      2 │ from .token_service import validate_token
      3 │
      4 │ async def auth_middleware(request: Request):
      5 │     token = request.headers.get("Authorization")
      6 │     if not token:
      7 │         raise HTTPException(status_code=401)
      8 │     user = await validate_token(token)
      9 │     request.state.user = user
     10 │     return user
        │ ... (24 more lines)

    ✓ OK File displayed
=== "Plain" ``` $ agents resource inspect local/api-repo --file src/api/auth/auth_middleware.py File: src/api/auth/auth_middleware.py Resource: local/api-repo Size: 2.4 KB Language: Python Last Modified: 2026-02-10 14:32 1 | from fastapi import Request, HTTPException 2 | from .token_service import validate_token 3 | 4 | async def auth_middleware(request: Request): 5 | token = request.headers.get("Authorization") 6 | if not token: 7 | raise HTTPException(status_code=401) 8 | user = await validate_token(token) 9 | request.state.user = user 10 | return user | ... (24 more lines) [OK] File displayed ``` === "JSON" ```json { "command": "resource inspect", "status": "ok", "exit_code": 0, "data": { "resource": "local/api-repo", "mode": "file", "file": { "path": "src/api/auth/auth_middleware.py", "size": "2.4 KB", "language": "Python", "last_modified": "2026-02-10T14:32:00Z", "lines_shown": 10, "total_lines": 34, "content": "from fastapi import Request, HTTPException\nfrom .token_service import validate_token\n\nasync def auth_middleware(request: Request):\n token = request.headers.get(\"Authorization\")\n if not token:\n raise HTTPException(status_code=401)\n user = await validate_token(token)\n request.state.user = user\n return user\n" } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 30 }, "messages": ["File displayed"] } ``` === "YAML" ```yaml command: resource inspect status: ok exit_code: 0 data: resource: local/api-repo mode: file file: path: src/api/auth/auth_middleware.py size: 2.4 KB language: Python last_modified: "2026-02-10T14:32:00Z" lines_shown: 10 total_lines: 34 content: | from fastapi import Request, HTTPException from .token_service import validate_token async def auth_middleware(request: Request): token = request.headers.get("Authorization") if not token: raise HTTPException(status_code=401) user = await validate_token(token) request.state.user = user return user timing: started: "2026-02-09T10:15:00Z" duration_ms: 30 messages: - File displayed ``` ##### agents resource tree 
agents resource tree [(--depth|-d) <N>] [(--type|-t) <TYPE>] <RESOURCE>
**Purpose** Display the resource DAG as a tree starting from a given resource, showing parent/child relationships. **Arguments** - ``: Resource name or ULID. - `--depth/-d N`: Maximum depth to display (default: 3). - `--type/-t TYPE`: Filter to only show children of a specific type. **Examples** === "Rich" 

    $ agents resource tree local/api-repo --depth 2

    ╭─ Resource Tree: local/api-repo ─────────────────────────────────────╮
    │                                                                     │
    │ git-checkout 01HXR1A1..J9K0 (physical)                              │
    │ ├── git 01HXR4D4..M2N3 (physical)                                   │
    │ │   ├── git-remote 01HXR6F6..P4Q5                                   │
    │ │   ├── git-branch 01HXR7G7..Q5R6                                   │
    │ │   │   ├── git-commit 01HXR8H8..R6S7                               │
    │ │   │   └── ... 22 more git-commit resources                        │
    │ │   └── git-branch 01HXR9J9..S7T8                                   │
    │ │       └── ... 26 git-commit resources                             │
    │ └── fs-directory 01HXR5E5..N3P4 (physical)                          │
    │     ├── fs-directory 01HXRAK1..T8U9                                 │
    │     ├── fs-directory 01HXRBL2..U9V0                                 │
    │     └── ... 28 more fs-file resources                               │
    │                                                                     │
    ╰─────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ──────────────╮
    │ Total shown: 14        │
    │ Total in subtree: 395  │
    │ Max depth: 2           │
    ╰────────────────────────╯

    ✓ OK Resource tree displayed
=== "Plain" ``` $ agents resource tree local/api-repo --depth 2 Resource Tree: local/api-repo git-checkout 01HXR1A1..J9K0 (physical) +-- git 01HXR4D4..M2N3 (physical) | +-- git-remote 01HXR6F6..P4Q5 | +-- git-branch 01HXR7G7..Q5R6 | | +-- git-commit 01HXR8H8..R6S7 | | +-- ... 22 more git-commit resources | +-- git-branch 01HXR9J9..S7T8 | +-- ... 26 git-commit resources +-- fs-directory 01HXR5E5..N3P4 (physical) +-- fs-directory 01HXRAK1..T8U9 +-- fs-directory 01HXRBL2..U9V0 +-- ... 28 more fs-file resources Summary Total shown: 14 Total in subtree: 395 Max depth: 2 [OK] Resource tree displayed ``` === "JSON" ```json { "command": "resource tree", "status": "ok", "exit_code": 0, "data": { "resource": "local/api-repo", "max_depth": 2, "tree": { "type": "git-checkout", "id": "01HXR1A1..J9K0", "physical": true, "children": [ { "type": "git", "id": "01HXR4D4..M2N3", "physical": true, "children": [ { "type": "git-remote", "id": "01HXR6F6..P4Q5" }, { "type": "git-branch", "id": "01HXR7G7..Q5R6", "children": [ { "type": "git-commit", "id": "01HXR8H8..R6S7" }, "... 22 more git-commit resources" ] }, { "type": "git-branch", "id": "01HXR9J9..S7T8", "children": ["... 26 git-commit resources"] } ] }, { "type": "fs-directory", "id": "01HXR5E5..N3P4", "physical": true, "children": [ { "type": "fs-directory", "id": "01HXRAK1..T8U9" }, { "type": "fs-directory", "id": "01HXRBL2..U9V0" }, "... 28 more fs-file resources" ] } ] }, "summary": { "total_shown": 14, "total_in_subtree": 395, "max_depth": 2 } }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 85 }, "messages": ["Resource tree displayed"] } ``` === "YAML" ```yaml command: resource tree status: ok exit_code: 0 data: resource: local/api-repo max_depth: 2 tree: type: git-checkout id: 01HXR1A1..J9K0 physical: true children: - type: git id: 01HXR4D4..M2N3 physical: true children: - type: git-remote id: 01HXR6F6..P4Q5 - type: git-branch id: 01HXR7G7..Q5R6 children: - type: git-commit id: 01HXR8H8..R6S7 - "... 22 more git-commit resources" - type: git-branch id: 01HXR9J9..S7T8 children: - "... 26 git-commit resources" - type: fs-directory id: 01HXR5E5..N3P4 physical: true children: - type: fs-directory id: 01HXRAK1..T8U9 - type: fs-directory id: 01HXRBL2..U9V0 - "... 28 more fs-file resources" summary: total_shown: 14 total_in_subtree: 395 max_depth: 2 timing: started: "2026-02-09T10:15:00Z" duration_ms: 85 messages: - Resource tree displayed ``` ##### agents resource link-child 
agents resource link-child <PARENT> <CHILD>
**Purpose** Manually link one resource as a child of another. The child resource must already be registered. The resource types must be compatible (the parent type must allow the child type). A resource can have multiple parents. **Arguments** - ``: Parent resource name or ULID. - ``: Child resource name or ULID. **Examples** === "Rich" 

    $ agents resource link-child local/api-repo 01HXR2B2C3D4E5F6G7H8J9K0L1

    ╭─ Child Linked ──────────────────────────────────────╮
    │ Parent: local/api-repo                              │
    │ Child: 01HXR2B2C3D4E5F6G7H8J9K0L1                   │
    │ Child Type: fs-mount                                │
    │ Status: linked                                      │
    ╰─────────────────────────────────────────────────────╯

    ✓ OK Child resource linked
=== "Plain" ``` $ agents resource link-child local/api-repo 01HXR2B2C3D4E5F6G7H8J9K0L1 Child Linked Parent: local/api-repo Child: 01HXR2B2C3D4E5F6G7H8J9K0L1 Child Type: fs-mount Status: linked [OK] Child resource linked ``` === "JSON" ```json { "command": "resource link-child", "status": "ok", "exit_code": 0, "data": { "parent": "local/api-repo", "child": "01HXR2B2C3D4E5F6G7H8J9K0L1", "child_type": "fs-mount", "status": "linked" }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 38 }, "messages": ["Child resource linked"] } ``` === "YAML" ```yaml command: resource link-child status: ok exit_code: 0 data: parent: local/api-repo child: 01HXR2B2C3D4E5F6G7H8J9K0L1 child_type: fs-mount status: linked timing: started: "2026-02-09T10:15:00Z" duration_ms: 38 messages: - Child resource linked ``` ##### agents resource unlink-child 
agents resource unlink-child [--yes|-y] <PARENT> <CHILD>
**Purpose** Remove a manual parent/child link between two resources. Auto-discovered links cannot be manually unlinked. **Arguments** - ``: Parent resource name or ULID. - ``: Child resource name or ULID. - `--yes`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents resource unlink-child local/api-repo 01HXR2B2C3D4E5F6G7H8J9K0L1

    Unlink 01HXR2B2C3D4E5F6G7H8J9K0L1 from parent local/api-repo? [y/N]: y

    ╭─ Child Unlinked ────────────────────────────────────╮
    │ Parent: local/api-repo                              │
    │ Child: 01HXR2B2C3D4E5F6G7H8J9K0L1                   │
    │ Status: unlinked                                    │
    ╰─────────────────────────────────────────────────────╯

    ✓ OK Child resource unlinked
=== "Plain" ``` $ agents resource unlink-child local/api-repo 01HXR2B2C3D4E5F6G7H8J9K0L1 Unlink 01HXR2B2C3D4E5F6G7H8J9K0L1 from parent local/api-repo? [y/N]: y Child Unlinked Parent: local/api-repo Child: 01HXR2B2C3D4E5F6G7H8J9K0L1 Status: unlinked [OK] Child resource unlinked ``` === "JSON" ```json { "command": "resource unlink-child", "status": "ok", "exit_code": 0, "data": { "parent": "local/api-repo", "child": "01HXR2B2C3D4E5F6G7H8J9K0L1", "status": "unlinked" }, "timing": { "started": "2026-02-09T10:15:00Z", "duration_ms": 45 }, "messages": ["Child resource unlinked"] } ``` === "YAML" ```yaml command: resource unlink-child status: ok exit_code: 0 data: parent: local/api-repo child: 01HXR2B2C3D4E5F6G7H8J9K0L1 status: unlinked timing: started: "2026-02-09T10:15:00Z" duration_ms: 45 messages: - Child resource unlinked ``` ##### agents resource stop 
agents resource stop <NAME> [--yes | -y]
**Purpose** Stop an active `devcontainer-instance` or `container-instance` resource. Transitions the container through `running → stopping → stopped`. Only container-typed resources may be stopped; attempting to stop other resource types produces an error. **Arguments** - ``: Resource name or ULID of the devcontainer to stop. **Options** - `--yes` / `-y`: Skip the confirmation prompt (useful in scripts and automation). **Examples** === "Rich" 

    $ agents resource stop local/my-dc

    Stopping container local/my-dc (state: running)...
    Stopped: local/my-dc
=== "Plain" ``` $ agents resource stop local/my-dc Stopping container local/my-dc (state: running)... Stopped: local/my-dc ``` ##### agents resource rebuild 
agents resource rebuild <NAME> [--yes | -y]
**Purpose** Rebuild a stopped or failed `devcontainer-instance` resource. Transitions the container through `stopped/failed → building → running` by invoking `devcontainer up` with the resource's workspace location. Only `devcontainer-instance` resources may be rebuilt since the rebuild process invokes the devcontainer CLI; generic `container-instance` resources do not support rebuild. **Arguments** - ``: Resource name or ULID of the devcontainer to rebuild. **Options** - `--yes` / `-y`: Skip the confirmation prompt (useful in scripts and automation). **Examples** === "Rich" 

    $ agents resource rebuild local/my-dc

    Rebuilding local/my-dc...
    Rebuilt: local/my-dc
=== "Plain" ``` $ agents resource rebuild local/my-dc Rebuilding local/my-dc... Rebuilt: local/my-dc ``` #### agents plan !!! info "Purpose" Manage ==plans== through the **Strategize → Execute → Apply** lifecycle (instantiated from Action templates). ??? abstract "Plan Lifecycle at a Glance" ``` Action ──use──▶ Strategize ──execute──▶ Execute ──apply──▶ Apply ▲ │ │ └──────────────────────┘ │ ▲ (reversion) │ └────────────────────────────────────────┘ ``` - [x] **Action** — Reusable template defining work, actors, and constraints - [x] **Strategize** — Strategy actor produces a decision tree - [x] **Execute** — Execution actor implements the strategy in a sandbox - [x] **Apply** — Changeset is merged into real project resources !!! note "Phase Reversion" Both Execute and Apply can revert to Strategize when constraints are too restrictive. See `delete_content` and `access_network` automation profile flags. ##### agents plan list 
agents plan list [--phase <PHASE>] [--state <STATE>] [--project <PROJECT>]
                [--action <ACTION>] [<REGEX>]
**Purpose** List plans with optional filtering. **Arguments** - `--phase PHASE`: Filter by phase. - `--state STATE`: Filter by processing state. - `--project PROJECT`: Filter by project. - `--action ACTION`: Filter by action name. **Examples** === "Rich" 

    $ agents --format table plan list --phase execute

    ╭─ Plans ──────────────────────────────────────────────────────────────────────────────╮
    │ ID        Phase    State       Action               Project            Elapsed       │
    │ ────────  ───────  ──────────  ───────────────────  ─────────────────  ─────────     │
    │ 01HXM7A9  execute  processing  local/code-coverage  local/api-service  00:01:12      │
    ╰──────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Filters ──────╮
    │ Phase: execute │
    │ State: (any)   │
    │ Project: (any) │
    │ Action: (any)  │
    ╰────────────────╯

    ╭─ Summary ─────────╮
    │ Total: 1          │
    │ Processing: 1     │
    │ Completed: 0      │
    │ Errored: 0        │
    ╰───────────────────╯

    ✓ OK 1 plan listed
=== "Plain" ``` $ agents --format table plan list --phase execute Plans ID Phase State Action Project Elapsed -------- ------- ---------- ------------------- ----------------- --------- 01HXM7A9 execute processing local/code-coverage local/api-service 00:01:12 Filters Phase: execute State: (any) Project: (any) Action: (any) Summary Total: 1 Processing: 1 Completed: 0 Errored: 0 [OK] 1 plan listed ``` === "JSON" ```json { "command": "plan list", "status": "ok", "exit_code": 0, "data": { "plans": [ { "id": "01HXM7A9", "phase": "execute", "state": "processing", "action": "local/code-coverage", "project": "local/api-service", "elapsed": "00:01:12" } ], "filters": { "phase": "execute", "state": null, "project": null, "action": null }, "summary": { "total": 1, "processing": 1, "completed": 0, "errored": 0 } }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 95 }, "messages": ["1 plan listed"] } ``` === "YAML" ```yaml command: plan list status: ok exit_code: 0 data: plans: - id: "01HXM7A9" phase: execute state: processing action: "local/code-coverage" project: "local/api-service" elapsed: "00:01:12" filters: phase: execute state: null project: null action: null summary: total: 1 processing: 1 completed: 0 errored: 0 timing: started: "2026-02-09T14:30:00Z" duration_ms: 95 messages: - "1 plan listed" ``` Listing all plans without filters shows plans across all phases and states: === "Rich" 

    $ agents plan list

    ╭─ Plans ──────────────────────────────────────────────────────────────────────────────────────╮
    │ ID        Phase       State       Action               Project            Elapsed            │
    │ ────────  ──────────  ──────────  ───────────────────  ─────────────────  ─────────          │
    │ 01HXM7A9  execute     processing  local/code-coverage  local/api-service  00:01:12           │
    │ 01HXM6R3  apply       applied     local/add-auth       local/api-service  00:07:14           │
    │ 01HXM5K2  execute     errored     local/migrate-db     local/api-service  00:04:33           │
    │ 01HXM4J1  strategize  processing  local/refactor-api   local/web-app      00:00:45           │
    │ 01HXM3H8  cancelled   cancelled   local/add-logging    local/api-service  00:02:10           │
    ╰──────────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ─────────────╮
    │ Total: 5              │
    │ Processing: 2         │
    │ Completed: 1          │
    │ Errored: 1            │
    │ Cancelled: 1          │
    ╰───────────────────────╯

    ✓ OK 5 plans listed
=== "Plain" ``` $ agents plan list Plans ID Phase State Action Project Elapsed -------- ---------- ---------- ------------------- ----------------- --------- 01HXM7A9 execute processing local/code-coverage local/api-service 00:01:12 01HXM6R3 apply applied local/add-auth local/api-service 00:07:14 01HXM5K2 execute errored local/migrate-db local/api-service 00:04:33 01HXM4J1 strategize processing local/refactor-api local/web-app 00:00:45 01HXM3H8 cancelled cancelled local/add-logging local/api-service 00:02:10 Summary Total: 5 Processing: 2 Completed: 1 Errored: 1 Cancelled: 1 [OK] 5 plans listed ``` === "JSON" ```json { "command": "plan list", "status": "ok", "exit_code": 0, "data": { "plans": [ { "id": "01HXM7A9", "phase": "execute", "state": "processing", "action": "local/code-coverage", "project": "local/api-service", "elapsed": "00:01:12" }, { "id": "01HXM6R3", "phase": "apply", "state": "applied", "action": "local/add-auth", "project": "local/api-service", "elapsed": "00:07:14" }, { "id": "01HXM5K2", "phase": "execute", "state": "errored", "action": "local/migrate-db", "project": "local/api-service", "elapsed": "00:04:33" }, { "id": "01HXM4J1", "phase": "strategize", "state": "processing", "action": "local/refactor-api", "project": "local/web-app", "elapsed": "00:00:45" }, { "id": "01HXM3H8", "phase": "cancelled", "state": "cancelled", "action": "local/add-logging", "project": "local/api-service", "elapsed": "00:02:10" } ], "summary": { "total": 5, "processing": 2, "completed": 1, "errored": 1, "cancelled": 1 } }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 95 }, "messages": ["5 plans listed"] } ``` === "YAML" ```yaml command: plan list status: ok exit_code: 0 data: plans: - id: "01HXM7A9" phase: execute state: processing action: "local/code-coverage" project: "local/api-service" elapsed: "00:01:12" - id: "01HXM6R3" phase: apply state: applied action: "local/add-auth" project: "local/api-service" elapsed: "00:07:14" - id: "01HXM5K2" phase: execute state: errored action: "local/migrate-db" project: "local/api-service" elapsed: "00:04:33" - id: "01HXM4J1" phase: strategize state: processing action: "local/refactor-api" project: "local/web-app" elapsed: "00:00:45" - id: "01HXM3H8" phase: cancelled state: cancelled action: "local/add-logging" project: "local/api-service" elapsed: "00:02:10" summary: total: 5 processing: 2 completed: 1 errored: 1 cancelled: 1 timing: started: "2026-02-09T14:30:00Z" duration_ms: 95 messages: - "5 plans listed" ``` Filtering by project with `--project`: === "Rich" 

    $ agents plan list --project local/web-app

    ╭─ Plans ──────────────────────────────────────────────────────────────────────────────╮
    │ ID        Phase       State       Action               Project        Elapsed        │
    │ ────────  ──────────  ──────────  ───────────────────  ─────────────  ─────────      │
    │ 01HXM4J1  strategize  processing  local/refactor-api   local/web-app  00:00:45       │
    ╰──────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Filters ─────────────────╮
    │ Phase: (any)              │
    │ State: (any)              │
    │ Project: local/web-app    │
    │ Action: (any)             │
    ╰───────────────────────────╯

    ✓ OK 1 plan listed
=== "Plain" ``` $ agents plan list --project local/web-app Plans ID Phase State Action Project Elapsed -------- ---------- ---------- ------------------- ------------- --------- 01HXM4J1 strategize processing local/refactor-api local/web-app 00:00:45 Filters Phase: (any) State: (any) Project: local/web-app Action: (any) [OK] 1 plan listed ``` === "JSON" ```json { "command": "plan list", "status": "ok", "exit_code": 0, "data": { "plans": [ { "id": "01HXM4J1", "phase": "strategize", "state": "processing", "action": "local/refactor-api", "project": "local/web-app", "elapsed": "00:00:45" } ], "filters": { "phase": null, "state": null, "project": "local/web-app", "action": null }, "total": 1 }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 85 }, "messages": ["1 plan listed"] } ``` === "YAML" ```yaml command: plan list status: ok exit_code: 0 data: plans: - id: "01HXM4J1" phase: strategize state: processing action: "local/refactor-api" project: "local/web-app" elapsed: "00:00:45" filters: phase: null state: null project: "local/web-app" action: null total: 1 timing: started: "2026-02-09T14:30:00Z" duration_ms: 85 messages: - "1 plan listed" ``` ##### agents plan use 
agents plan use [--automation-profile <PROFILE>]
                [--invariant <INVARIANT>]...
                [--strategy-actor <STRATEGY_ACTOR>]
                [--execution-actor <EXEC_ACTOR>]
                [--estimation-actor <EST_ACTOR>]
                [--invariant-actor <INV_ACTOR>]
                [--execution-environment <RESOURCE_NAME>]
                [--execution-env-priority (fallback|override)]
                [--arg/-a name=value]...
                <ACTION> <PROJECT>...
**Purpose** Apply an action to one or more projects and start the Strategize phase. **Arguments** - ``: Action name. - ``: One or more project names (positional arguments, repeatable). - `--arg/-a name=value`: Action argument (repeatable). - `--automation-profile PROFILE`: Automation profile name (e.g., `trusted`, `auto`, `local/careful-auto`). Overrides the profile inherited from the action, project, or global config. - `--strategy-actor ACTOR`: Override the action's strategy actor for this plan. - `--execution-actor ACTOR`: Override the action's execution actor for this plan. - `--estimation-actor ACTOR`: Override the action's estimation actor for this plan. - `--invariant-actor ACTOR`: Override the action's Invariant Reconciliation Actor for this plan. - `--invariant TEXT`: Invariant to attach to the created plan (repeatable). These are added as plan-level invariants in addition to any invariants inherited from the action, project, or global scope. - `--execution-environment RESOURCE_NAME`: Name of a `container-instance` or `devcontainer-instance` resource to use as the execution environment for this plan. Overrides or supplements the project-level `execution_environment` setting depending on `--execution-env-priority`. See [ADR-043 §3.3](adr/ADR-043-devcontainer-integration.md). - `--execution-env-priority fallback|override`: Priority semantics for the plan-level execution environment. `fallback` (default): defers to auto-detected devcontainers or project-level overrides. `override`: always uses the specified environment, bypassing all other resolution. See §Execution Environment Routing. All actor arguments (`--strategy-actor`, `--execution-actor`, `--estimation-actor`, `--invariant-actor`) are optional overrides. When provided, they replace whatever was set when creating the action. When omitted, the action's configured actors are used. **Examples** === "Rich" 

    $ agents plan use local/code-coverage local/api-service \
      --arg target_coverage_percent=85 --automation-profile trusted

    ╭─ Plan Created ──────────────────────╮
    │ Plan ID: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    │ Phase: strategize                   │
    │ Action: local/code-coverage         │
    │ Project: local/api-service          │
    │ Automation: trusted                 │
    │ Attempt: 1                          │
    ╰─────────────────────────────────────╯

    ╭─ Inputs ──────────────────────╮
    │ - target_coverage_percent=85  │
    │ - automation_profile=trusted  │
    ╰───────────────────────────────╯

    ╭─ Actors ────────────────────────╮
    │ Strategy: local/strategist      │
    │ Execution: local/executor       │
    │ Estimation: (none)              │
    ╰─────────────────────────────────╯

    ╭─ Automation ─────────────────────────╮
    │ Profile: trusted                     │
    │ Source: CLI flag                     │
    │ Read-Only: no                        │
    ╰──────────────────────────────────────╯

    ╭─ Context ───────────────────────╮
    │ Resources: 2 (repo, db)         │
    │ Indexed Files: 347              │
    │ View: strategize                │
    │ Hot Token Budget: 12,000        │
    ╰─────────────────────────────────╯

    ╭─ Next Steps ─────────────────────────────────────╮
    │ - agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    │ - agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J  │
    │ - agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J    │
    ╰──────────────────────────────────────────────────╯

    ✓ OK Plan created
=== "Plain" ``` $ agents plan use local/code-coverage local/api-service \ --arg target_coverage_percent=85 --automation-profile trusted Plan Created Plan ID: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Phase: strategize Action: local/code-coverage Project: local/api-service Automation: trusted Attempt: 1 Inputs - target_coverage_percent=85 - automation_profile=trusted Actors Strategy: local/strategist Execution: local/executor Estimation: (none) Automation Profile: trusted Source: CLI flag Read-Only: no Context Resources: 2 (repo, db) Indexed Files: 347 View: strategize Hot Token Budget: 12,000 Next Steps - agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J - agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J - agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J [OK] Plan created ``` === "JSON" ```json { "command": "plan use", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "phase": "strategize", "action": "local/code-coverage", "project": "local/api-service", "automation_profile": "trusted", "attempt": 1, "inputs": { "target_coverage_percent": 85, "automation_profile": "trusted" }, "actors": { "strategy": "local/strategist", "execution": "local/executor", "estimation": null }, "automation": { "profile": "trusted", "source": "CLI flag", "read_only": false }, "context": { "resources": 2, "indexed_files": 347, "view": "strategize", "hot_token_budget": 12000 }, "next_steps": [ "agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J", "agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J", "agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J" ] }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 95 }, "messages": ["Plan created"] } ``` === "YAML" ```yaml command: plan use status: ok exit_code: 0 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" phase: strategize action: "local/code-coverage" project: "local/api-service" automation_profile: trusted attempt: 1 inputs: target_coverage_percent: 85 automation_profile: trusted actors: strategy: "local/strategist" execution: "local/executor" estimation: null automation: profile: trusted source: "CLI flag" read_only: false context: resources: 2 indexed_files: 347 view: strategize hot_token_budget: 12000 next_steps: - "agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J" - "agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J" - "agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J" timing: started: "2026-02-09T14:30:00Z" duration_ms: 95 messages: - "Plan created" ``` Applying an action to multiple projects simultaneously, with plan-level invariants: === "Rich" 

    $ agents plan use local/security-audit local/api-service local/web-app \
      --invariant "Never modify production database schemas" \
      --invariant "All changes must include test coverage" \
      --automation-profile supervised

    ╭─ Plan Created ──────────────────────────────────────╮
    │ Plan: 01HXM9D2ZK4Q7C2B3F2R4VYV6J                    │
    │ Action: local/security-audit                        │
    │ Phase: strategize (running)                         │
    │ Automation: supervised                              │
    ╰─────────────────────────────────────────────────────╯

    ╭─ Target Projects ───────────────────╮
    │ 1. local/api-service (3 resources)  │
    │ 2. local/web-app (2 resources)      │
    ╰─────────────────────────────────────╯

    ╭─ Plan Invariants ──────────────────────────────────────────╮
    │ Scope     Source   Invariant                               │
    │ ────────  ───────  ──────────────────────────────────      │
    │ plan      CLI      Never modify production DB schemas      │
    │ plan      CLI      All changes must include test coverage  │
    │ project   config   API responses must be backward-compat   │
    │ global    config   Follow Python PEP 8 style guide         │
    ╰────────────────────────────────────────────────────────────╯

    ✓ OK Plan created — strategize in progress
=== "Plain" ``` $ agents plan use local/security-audit local/api-service local/web-app \ --invariant "Never modify production database schemas" \ --invariant "All changes must include test coverage" \ --automation-profile supervised Plan Created Plan: 01HXM9D2ZK4Q7C2B3F2R4VYV6J Action: local/security-audit Phase: strategize (running) Automation: supervised Target Projects 1. local/api-service (3 resources) 2. local/web-app (2 resources) Plan Invariants Scope Source Invariant -------- ------- ---------------------------------- plan CLI Never modify production DB schemas plan CLI All changes must include test coverage project config API responses must be backward-compat global config Follow Python PEP 8 style guide [OK] Plan created -- strategize in progress ``` === "JSON" ```json { "command": "plan use", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM9D2ZK4Q7C2B3F2R4VYV6J", "action": "local/security-audit", "phase": "strategize", "phase_state": "running", "automation_profile": "supervised", "target_projects": [ { "name": "local/api-service", "resources": 3 }, { "name": "local/web-app", "resources": 2 } ], "invariants": [ { "scope": "plan", "source": "CLI", "text": "Never modify production DB schemas" }, { "scope": "plan", "source": "CLI", "text": "All changes must include test coverage" }, { "scope": "project", "source": "config", "text": "API responses must be backward-compat" }, { "scope": "global", "source": "config", "text": "Follow Python PEP 8 style guide" } ] }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 130 }, "messages": ["Plan created -- strategize in progress"] } ``` === "YAML" ```yaml command: plan use status: ok exit_code: 0 data: plan_id: "01HXM9D2ZK4Q7C2B3F2R4VYV6J" action: "local/security-audit" phase: strategize phase_state: running automation_profile: supervised target_projects: - name: "local/api-service" resources: 3 - name: "local/web-app" resources: 2 invariants: - scope: plan source: CLI text: "Never modify production DB schemas" - scope: plan source: CLI text: "All changes must include test coverage" - scope: project source: config text: "API responses must be backward-compat" - scope: global source: config text: "Follow Python PEP 8 style guide" timing: started: "2026-02-09T14:30:00Z" duration_ms: 130 messages: - "Plan created -- strategize in progress" ``` Using an action with custom actor overrides: === "Rich" 

    $ agents plan use local/code-coverage local/api-service \
      --strategy-actor local/senior-planner \
      --execution-actor local/fast-executor \
      --arg target_coverage_percent=95

    ╭─ Plan Created ──────────────────────────────────────╮
    │ Plan: 01HXM9E3ZK4Q7C2B3F2R4VYV6J                    │
    │ Action: local/code-coverage                         │
    │ Phase: strategize (running)                         │
    │ Automation: trusted                                 │
    ╰─────────────────────────────────────────────────────╯

    ╭─ Actor Overrides ────────────────────╮
    │ Strategy: local/senior-planner       │
    │ Execution: local/fast-executor       │
    │ (Estimation: action default)         │
    ╰──────────────────────────────────────╯

    ╭─ Arguments ─────────────────╮
    │ target_coverage_percent: 95 │
    ╰─────────────────────────────╯

    ✓ OK Plan created — strategize in progress
=== "Plain" ``` $ agents plan use local/code-coverage local/api-service \ --strategy-actor local/senior-planner \ --execution-actor local/fast-executor \ --arg target_coverage_percent=95 Plan Created Plan: 01HXM9E3ZK4Q7C2B3F2R4VYV6J Action: local/code-coverage Phase: strategize (running) Automation: trusted Actor Overrides Strategy: local/senior-planner Execution: local/fast-executor (Estimation: action default) Arguments target_coverage_percent: 95 [OK] Plan created -- strategize in progress ``` === "JSON" ```json { "command": "plan use", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM9E3ZK4Q7C2B3F2R4VYV6J", "action": "local/code-coverage", "phase": "strategize", "phase_state": "running", "automation_profile": "trusted", "actor_overrides": { "strategy": "local/senior-planner", "execution": "local/fast-executor", "estimation": null }, "arguments": { "target_coverage_percent": 95 } }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 110 }, "messages": ["Plan created -- strategize in progress"] } ``` === "YAML" ```yaml command: plan use status: ok exit_code: 0 data: plan_id: "01HXM9E3ZK4Q7C2B3F2R4VYV6J" action: "local/code-coverage" phase: strategize phase_state: running automation_profile: trusted actor_overrides: strategy: "local/senior-planner" execution: "local/fast-executor" estimation: null arguments: target_coverage_percent: 95 timing: started: "2026-02-09T14:30:00Z" duration_ms: 110 messages: - "Plan created -- strategize in progress" ``` ##### agents plan execute 
agents plan execute <PLAN_ID>
**Purpose** Start or resume execution for a plan. **Arguments** - ``: Plan ID (required). **Examples** === "Rich" 

    $ agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Execution ──────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    │ Phase: execute                   │
    │ Sandbox: git_worktree            │
    │ Worker: local/executor           │
    │ Started: 12:58:10                │
    │ Attempt: 1                       │
    ╰──────────────────────────────────╯

    ╭─ Sandbox ──────────────────────────────────╮
    │ Strategy: git_worktree                     │
    │ Path: /repos/api/.worktrees/plan-01HXM8    │
    │ Branch: cleveragents/plan-01HXM8C2         │
    │ Status: active                             │
    ╰────────────────────────────────────────────╯

    ╭─ Strategy Summary ─────────────────────╮
    │ Decisions: 8                           │
    │ Invariants: 2                          │
    │ Planned Child Plans: 2+                │
    │ Estimated Files: ~12                   │
    │ Risk: low                              │
    ╰────────────────────────────────────────╯

    ╭─ Progress ─────────╮
    │ ⏳ Collect context │
    │ • Run tools        │
    │ • Build changeset  │
    │ • Validate         │
    ╰────────────────────╯

    ✓ OK Execution started
=== "Plain" ``` $ agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J Execution Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Phase: execute Sandbox: git_worktree Worker: local/executor Started: 12:58:10 Attempt: 1 Sandbox Strategy: git_worktree Path: /repos/api/.worktrees/plan-01HXM8 Branch: cleveragents/plan-01HXM8C2 Status: active Strategy Summary Decisions: 8 Invariants: 2 Planned Child Plans: 2+ Estimated Files: ~12 Risk: low Progress ... Collect context . Run tools . Build changeset . Validate [OK] Execution started ``` === "JSON" ```json { "command": "plan execute", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "sandbox": { "strategy": "git_worktree", "path": "/repos/api/.worktrees/plan-01HXM8", "branch": "cleveragents/plan-01HXM8C2", "status": "active" }, "worker": "local/executor", "started": "12:58:10", "attempt": 1, "strategy_summary": { "decisions": 8, "invariants": 2, "planned_child_plans": "2+", "estimated_files": 12, "risk": "low" }, "progress": [ { "label": "Collect context", "status": "running" }, { "label": "Run tools", "status": "pending" }, { "label": "Build changeset", "status": "pending" }, { "label": "Validate", "status": "pending" } ] }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 150 }, "messages": ["Execution started"] } ``` === "YAML" ```yaml command: plan execute status: ok exit_code: 0 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" phase: execute sandbox: strategy: git_worktree path: "/repos/api/.worktrees/plan-01HXM8" branch: "cleveragents/plan-01HXM8C2" status: active worker: "local/executor" started: "12:58:10" attempt: 1 strategy_summary: decisions: 8 invariants: 2 planned_child_plans: "2+" estimated_files: 12 risk: low progress: - label: "Collect context" status: running - label: "Run tools" status: pending - label: "Build changeset" status: pending - label: "Validate" status: pending timing: started: "2026-02-09T14:30:00Z" duration_ms: 150 messages: - "Execution started" ``` Resuming execution of a plan that was previously paused or errored: === "Rich" 

    $ agents plan execute 01HXM7K2ZK4Q7C2B3F2R4VYV6J

    ╭─ Execution Resumed ─────────────────╮
    │ Plan: 01HXM7K2ZK4Q7C2B3F2R4VYV6J    │
    │ Phase: execute (resumed)            │
    │ Sandbox: git_worktree               │
    │ Worker: local/executor              │
    │ Checkpoint: cp_01HXM8C2 (loaded)    │
    │ Resumed From: step 4 of 6           │
    ╰─────────────────────────────────────╯

    ╭─ Previous Progress ──────────────────────╮
    │ ✓ Step 1: Collect context (0.8s)         │
    │ ✓ Step 2: Analyze codebase (4.2s)        │
    │ ✓ Step 3: Generate migrations (6.1s)     │
    │ ✗ Step 4: Apply migrations (errored)     │
    │ ○ Step 5: Update models (pending)        │
    │ ○ Step 6: Run validations (pending)      │
    ╰──────────────────────────────────────────╯

    ╭─ Guidance Applied ──────────────────────────────────────────────╮
    │ "Use smaller batch sizes for the migration to avoid timeouts"   │
    ╰─────────────────────────────────────────────────────────────────╯

    ✓ OK Execution resumed from checkpoint cp_01HXM8C2
=== "Plain" ``` $ agents plan execute 01HXM7K2ZK4Q7C2B3F2R4VYV6J Execution Resumed Plan: 01HXM7K2ZK4Q7C2B3F2R4VYV6J Phase: execute (resumed) Sandbox: git_worktree Worker: local/executor Checkpoint: cp_01HXM8C2 (loaded) Resumed From: step 4 of 6 Previous Progress v Step 1: Collect context (0.8s) v Step 2: Analyze codebase (4.2s) v Step 3: Generate migrations (6.1s) x Step 4: Apply migrations (errored) o Step 5: Update models (pending) o Step 6: Run validations (pending) Guidance Applied "Use smaller batch sizes for the migration to avoid timeouts" [OK] Execution resumed from checkpoint cp_01HXM8C2 ``` === "JSON" ```json { "command": "plan execute", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM7K2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "resumed": true, "sandbox": "git_worktree", "worker": "local/executor", "checkpoint": "cp_01HXM8C2", "resumed_from": "step 4 of 6", "progress": [ { "step": 1, "label": "Collect context", "status": "done", "duration_s": 0.8 }, { "step": 2, "label": "Analyze codebase", "status": "done", "duration_s": 4.2 }, { "step": 3, "label": "Generate migrations", "status": "done", "duration_s": 6.1 }, { "step": 4, "label": "Apply migrations", "status": "errored" }, { "step": 5, "label": "Update models", "status": "pending" }, { "step": 6, "label": "Run validations", "status": "pending" } ], "guidance": "Use smaller batch sizes for the migration to avoid timeouts" }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 180 }, "messages": ["Execution resumed from checkpoint cp_01HXM8C2"] } ``` === "YAML" ```yaml command: plan execute status: ok exit_code: 0 data: plan_id: "01HXM7K2ZK4Q7C2B3F2R4VYV6J" phase: execute resumed: true sandbox: git_worktree worker: "local/executor" checkpoint: "cp_01HXM8C2" resumed_from: "step 4 of 6" progress: - step: 1 label: "Collect context" status: done duration_s: 0.8 - step: 2 label: "Analyze codebase" status: done duration_s: 4.2 - step: 3 label: "Generate migrations" status: done duration_s: 6.1 - step: 4 label: "Apply migrations" status: errored - step: 5 label: "Update models" status: pending - step: 6 label: "Run validations" status: pending guidance: "Use smaller batch sizes for the migration to avoid timeouts" timing: started: "2026-02-09T14:30:00Z" duration_ms: 180 messages: - "Execution resumed from checkpoint cp_01HXM8C2" ``` ##### agents plan apply 
agents plan apply [--yes|-y] <PLAN_ID>
**Purpose** Apply sandboxed changes to real resources. **Arguments** - ``: Plan ID. - `--yes`: Skip confirmation. **Examples** === "Rich" 

    $ agents plan apply 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    Apply changes for plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J? [y/N]: y

    ╭─ Apply Summary ─────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J    │
    │ Artifacts: 6 files updated          │
    │ Changes: 42 insertions, 9 deletions │
    │ Project: local/api-service          │
    │ Applied At: 2026-02-08 13:04        │
    ╰─────────────────────────────────────╯

    ╭─ Validation (from Execute) ────╮
    │ Tests: passed (24/24)          │
    │ Lint: passed (0 warnings)      │
    │ Type Check: passed (0 errors)  │
    │ Duration: 12.4s                │
    ╰────────────────────────────────╯

    ╭─ Sandbox Cleanup ─────────╮
    │ Worktree: removed         │
    │ Branch: merged to main    │
    │ Checkpoint: archived      │
    ╰───────────────────────────╯

    ╭─ Plan Lifecycle ────────────────────────╮
    │ Phase: apply                            │
    │ State: applied                          │
    │ Total Duration: 00:06:14                │
    │ Total Cost: $0.0847                     │
    │ Decisions Made: 8                       │
    │ Child Plans: 2 (completed)              │
    ╰─────────────────────────────────────────╯

    ╭─ Next Steps ──────╮
    │ - Review git diff │
    │ - Commit changes  │
    ╰───────────────────╯

    ✓ OK Changes applied
=== "Plain" ``` $ agents plan apply 01HXM8C2ZK4Q7C2B3F2R4VYV6J Apply changes for plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J? [y/N]: y Apply Summary Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Artifacts: 6 files updated Changes: 42 insertions, 9 deletions Project: local/api-service Applied At: 2026-02-08 13:04 Validation (from Execute) Tests: passed (24/24) Lint: passed (0 warnings) Type Check: passed (0 errors) Duration: 12.4s Sandbox Cleanup Worktree: removed Branch: merged to main Checkpoint: archived Plan Lifecycle Phase: apply State: applied Total Duration: 00:06:14 Total Cost: $0.0847 Decisions Made: 8 Child Plans: 2 (completed) Next Steps - Review git diff - Commit changes [OK] Changes applied ``` === "JSON" ```json { "command": "plan apply", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "artifacts": 6, "changes": { "insertions": 42, "deletions": 9 }, "project": "local/api-service", "applied_at": "2026-02-08T13:04:00Z", "validation": { "tests": { "status": "passed", "passed": 24, "total": 24 }, "lint": { "status": "passed", "warnings": 0 }, "type_check": { "status": "passed", "errors": 0 }, "duration_s": 12.4 }, "sandbox_cleanup": { "worktree": "removed", "branch": "merged to main", "checkpoint": "archived" }, "lifecycle": { "phase": "apply", "state": "applied", "total_duration": "00:06:14", "total_cost": "$0.0847", "decisions_made": 8, "child_plans": 2 } }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 1250 }, "messages": ["Changes applied"] } ``` === "YAML" ```yaml command: plan apply status: ok exit_code: 0 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" artifacts: 6 changes: insertions: 42 deletions: 9 project: "local/api-service" applied_at: "2026-02-08T13:04:00Z" validation: tests: status: passed passed: 24 total: 24 lint: status: passed warnings: 0 type_check: status: passed errors: 0 duration_s: 12.4 sandbox_cleanup: worktree: removed branch: merged to main checkpoint: archived lifecycle: phase: apply state: applied total_duration: "00:06:14" total_cost: "$0.0847" decisions_made: 8 child_plans: 2 timing: started: "2026-02-09T14:30:00Z" duration_ms: 1250 messages: - "Changes applied" ``` When Execute-phase validations failed and were not resolved (e.g., the execution actor exhausted its retry limit or failed outright), the plan cannot be applied. Apply checks the validation record and refuses to proceed: === "Rich" 

    $ agents plan apply --yes 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Apply Summary ─────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J    │
    │ Artifacts: 6 files updated          │
    │ Changes: 42 insertions, 9 deletions │
    │ Project: local/api-service          │
    ╰─────────────────────────────────────╯

    ╭─ Validation ───────────────────────────────────────────────╮
    │ ✗ Tests: FAILED (22/24 passed, 2 failed)                   │
    │   FAIL test_auth.py::test_session_refresh — AssertionError │
    │   FAIL test_auth.py::test_token_expiry — TimeoutError      │
    │ ✓ Lint: passed (0 warnings)                                │
    │ ✓ Type Check: passed (0 errors)                            │
    │ Duration: 14.8s                                            │
    ╰────────────────────────────────────────────────────────────╯

    ╭─ Sandbox Status ─────────────────────────────────────────────╮
    │ Worktree: preserved (changes NOT committed)                  │
    │ Checkpoint: cp_01HXM8C2 (pre-apply state available)          │
    │ The sandbox is preserved for correction or manual review.    │
    ╰──────────────────────────────────────────────────────────────╯

    ╭─ Recovery Options ──────────────────────────────────────────────────╮
    │ - agents plan prompt — provide guidance to fix test failures        │
    │ - agents plan correct — revert and re-execute with guidance         │
    │ - agents plan rollback — restore to a previous checkpoint           │
    │ - agents plan cancel — abort the plan entirely                      │
    ╰─────────────────────────────────────────────────────────────────────╯

    ✗ ERROR Apply refused — 2 required Execute-phase validations did not pass
=== "Plain" ``` $ agents plan apply --yes 01HXM8C2ZK4Q7C2B3F2R4VYV6J Apply Summary Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Artifacts: 6 files updated Changes: 42 insertions, 9 deletions Project: local/api-service Validation x Tests: FAILED (22/24 passed, 2 failed) FAIL test_auth.py::test_session_refresh -- AssertionError FAIL test_auth.py::test_token_expiry -- TimeoutError v Lint: passed (0 warnings) v Type Check: passed (0 errors) Duration: 14.8s Sandbox Status Worktree: preserved (changes NOT committed) Checkpoint: cp_01HXM8C2 (pre-apply state available) The sandbox is preserved for correction or manual review. Recovery Options - agents plan prompt -- provide guidance to fix test failures - agents plan correct -- revert and re-execute with guidance - agents plan rollback -- restore to a previous checkpoint - agents plan cancel -- abort the plan entirely [ERROR] Apply refused -- 2 required Execute-phase validations did not pass ``` === "JSON" ```json { "command": "plan apply", "status": "error", "exit_code": 1, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "artifacts": 6, "changes": { "insertions": 42, "deletions": 9 }, "project": "local/api-service", "validation": { "tests": { "status": "failed", "passed": 22, "total": 24, "failures": [ "test_auth.py::test_session_refresh -- AssertionError", "test_auth.py::test_token_expiry -- TimeoutError" ] }, "lint": { "status": "passed", "warnings": 0 }, "type_check": { "status": "passed", "errors": 0 }, "duration_s": 14.8 }, "sandbox": { "worktree": "preserved", "checkpoint": "cp_01HXM8C2" }, "recovery_options": [ "agents plan prompt", "agents plan correct", "agents plan rollback", "agents plan cancel" ] }, "timing": { "started": "2026-02-09T14:30:00Z", "duration_ms": 320 }, "messages": ["Apply refused -- 2 required Execute-phase validations did not pass"] } ``` === "YAML" ```yaml command: plan apply status: error exit_code: 1 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" artifacts: 6 changes: insertions: 42 deletions: 9 project: "local/api-service" validation: tests: status: failed passed: 22 total: 24 failures: - "test_auth.py::test_session_refresh -- AssertionError" - "test_auth.py::test_token_expiry -- TimeoutError" lint: status: passed warnings: 0 type_check: status: passed errors: 0 duration_s: 14.8 sandbox: worktree: preserved checkpoint: "cp_01HXM8C2" recovery_options: - "agents plan prompt" - "agents plan correct" - "agents plan rollback" - "agents plan cancel" timing: started: "2026-02-09T14:30:00Z" duration_ms: 320 messages: - "Apply refused -- 2 required Execute-phase validations did not pass" ``` ##### agents plan status 
agents plan status <PLAN_ID>
**Purpose** Show detailed status for a plan. **Arguments** - ``: Plan ID (required). **Examples** === "Rich" 

    $ agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Plan Status ────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    │ Phase: execute                   │
    │ State: processing                │
    │ Action: local/code-coverage      │
    │ Project: local/api-service       │
    │ Automation: review               │
    │ Attempt: 1                       │
    ╰──────────────────────────────────╯

    ╭─ Progress ───────╮
    │ ✓ Strategize     │
    │ ⏳ Execute       │
    │ • Apply (queued) │
    ╰──────────────────╯

    ╭─ Timing ──────────╮
    │ Started: 12:57:01 │
    │ Elapsed: 00:01:12 │
    │ ETA: 00:03:45     │
    ╰───────────────────╯

    ╭─ Execution Detail ──────────╮
    │ Sandbox: git_worktree       │
    │ Tool Calls: 8               │
    │ Files Modified: 3           │
    │ Child Plans: 1/2 complete   │
    │ Checkpoints: 2 created      │
    ╰─────────────────────────────╯

    ╭─ Cost ───────────────╮
    │ Tokens Used: 12,420  │
    │ Cost So Far: $0.041  │
    │ Estimated: $0.085    │
    ╰──────────────────────╯

    ✓ OK Status refreshed
=== "Plain" ``` $ agents plan status 01HXM8C2ZK4Q7C2B3F2R4VYV6J Plan Status Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Phase: execute State: processing Action: local/code-coverage Project: local/api-service Automation: review Attempt: 1 Progress [OK] Strategize ... Execute . Apply (queued) Timing Started: 12:57:01 Elapsed: 00:01:12 ETA: 00:03:45 Execution Detail Sandbox: git_worktree Tool Calls: 8 Files Modified: 3 Child Plans: 1/2 complete Checkpoints: 2 created Cost Tokens Used: 12,420 Cost So Far: $0.041 Estimated: $0.085 [OK] Status refreshed ``` === "JSON" ```json { "command": "plan status", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "state": "processing", "action": "local/code-coverage", "project": "local/api-service", "automation": "review", "attempt": 1, "progress": [ { "step": "Strategize", "status": "done" }, { "step": "Execute", "status": "running" }, { "step": "Apply", "status": "queued" } ], "timing": { "started": "12:57:01", "elapsed": "00:01:12", "eta": "00:03:45" }, "execution": { "sandbox": "git_worktree", "tool_calls": 8, "files_modified": 3, "child_plans": "1/2 complete", "checkpoints": 2 }, "cost": { "tokens_used": 12420, "cost_so_far": 0.041, "estimated": 0.085 } }, "timing": { "started": "2026-02-08T12:57:01Z", "duration_ms": 120 }, "messages": ["Status refreshed"] } ``` === "YAML" ```yaml command: plan status status: ok exit_code: 0 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" phase: execute state: processing action: local/code-coverage project: local/api-service automation: review attempt: 1 progress: - step: Strategize status: done - step: Execute status: running - step: Apply status: queued timing: started: "12:57:01" elapsed: "00:01:12" eta: "00:03:45" execution: sandbox: git_worktree tool_calls: 8 files_modified: 3 child_plans: "1/2 complete" checkpoints: 2 cost: tokens_used: 12420 cost_so_far: 0.041 estimated: 0.085 timing: started: "2026-02-08T12:57:01Z" duration_ms: 120 messages: - "Status refreshed" ``` Status of a plan that has completed successfully: === "Rich" 

    $ agents plan status 01HXM6R3ZK4Q7C2B3F2R4VYV6J

    ╭─ Plan Status ─────────────────────╮
    │ Plan: 01HXM6R3ZK4Q7C2B3F2R4VYV6J  │
    │ Phase: apply                      │
    │ State: applied                    │
    │ Action: local/add-auth            │
    │ Project: local/api-service        │
    │ Automation: trusted               │
    │ Attempt: 1                        │
    ╰───────────────────────────────────╯

    ╭─ Progress ───────────╮
    │ ✓ Strategize         │
    │ ✓ Execute            │
    │ ✓ Apply (committed)  │
    ╰──────────────────────╯

    ╭─ Timing ─────────────────────────╮
    │ Started: 2026-02-08 12:57:01     │
    │ Finished: 2026-02-08 13:04:15    │
    │ Total Duration: 00:07:14         │
    ╰──────────────────────────────────╯

    ╭─ Result ────────────────────────────╮
    │ Decisions Made: 8                   │
    │ Child Plans: 2/2 complete           │
    │ Artifacts: 6 files updated          │
    │ Validations: 3/3 passed             │
    │ Total Cost: $0.085                  │
    ╰─────────────────────────────────────╯

    ✓ OK Plan completed successfully
=== "Plain" ``` $ agents plan status 01HXM6R3ZK4Q7C2B3F2R4VYV6J Plan Status Plan: 01HXM6R3ZK4Q7C2B3F2R4VYV6J Phase: apply State: applied Action: local/add-auth Project: local/api-service Automation: trusted Attempt: 1 Progress [OK] Strategize [OK] Execute [OK] Apply (committed) Timing Started: 2026-02-08 12:57:01 Finished: 2026-02-08 13:04:15 Total Duration: 00:07:14 Result Decisions Made: 8 Child Plans: 2/2 complete Artifacts: 6 files updated Validations: 3/3 passed Total Cost: $0.085 [OK] Plan completed successfully ``` === "JSON" ```json { "command": "plan status", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM6R3ZK4Q7C2B3F2R4VYV6J", "phase": "apply", "state": "applied", "action": "local/add-auth", "project": "local/api-service", "automation": "trusted", "attempt": 1, "progress": [ { "step": "Strategize", "status": "done" }, { "step": "Execute", "status": "done" }, { "step": "Apply", "status": "committed" } ], "timing": { "started": "2026-02-08T12:57:01Z", "finished": "2026-02-08T13:04:15Z", "total_duration": "00:07:14" }, "result": { "decisions_made": 8, "child_plans": "2/2 complete", "artifacts": "6 files updated", "validations": "3/3 passed", "total_cost": 0.085 } }, "timing": { "started": "2026-02-08T12:57:01Z", "duration_ms": 434000 }, "messages": ["Plan completed successfully"] } ``` === "YAML" ```yaml command: plan status status: ok exit_code: 0 data: plan_id: "01HXM6R3ZK4Q7C2B3F2R4VYV6J" phase: apply state: applied action: local/add-auth project: local/api-service automation: trusted attempt: 1 progress: - step: Strategize status: done - step: Execute status: done - step: Apply status: committed timing: started: "2026-02-08T12:57:01Z" finished: "2026-02-08T13:04:15Z" total_duration: "00:07:14" result: decisions_made: 8 child_plans: "2/2 complete" artifacts: "6 files updated" validations: "3/3 passed" total_cost: 0.085 timing: started: "2026-02-08T12:57:01Z" duration_ms: 434000 messages: - "Plan completed successfully" ``` Status of a plan in the strategize phase: === "Rich" 

    $ agents plan status 01HXM9F2ZK4Q7C2B3F2R4VYV6J

    ╭─ Plan Status ────────────────────╮
    │ Plan: 01HXM9F2ZK4Q7C2B3F2R4VYV6J │
    │ Phase: strategize                │
    │ State: processing                │
    │ Action: local/refactor-auth      │
    │ Project: local/api-service       │
    │ Automation: supervised           │
    ╰──────────────────────────────────╯

    ╭─ Progress ───────────────╮
    │ ⏳ Strategize (running)  │
    │ ○ Execute (waiting)      │
    │ ○ Apply (waiting)        │
    ╰──────────────────────────╯

    ╭─ Strategy Progress ────────╮
    │ Decisions Made: 4          │
    │ Invariants Enforced: 2     │
    │ Child Plans Planned: 3     │
    │ Elapsed: 00:00:28          │
    ╰────────────────────────────╯

    ✓ OK Strategize in progress
=== "Plain" ``` $ agents plan status 01HXM9F2ZK4Q7C2B3F2R4VYV6J Plan Status Plan: 01HXM9F2ZK4Q7C2B3F2R4VYV6J Phase: strategize State: processing Action: local/refactor-auth Project: local/api-service Automation: supervised Progress ... Strategize (running) o Execute (waiting) o Apply (waiting) Strategy Progress Decisions Made: 4 Invariants Enforced: 2 Child Plans Planned: 3 Elapsed: 00:00:28 [OK] Strategize in progress ``` === "JSON" ```json { "command": "plan status", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM9F2ZK4Q7C2B3F2R4VYV6J", "phase": "strategize", "state": "processing", "action": "local/refactor-auth", "project": "local/api-service", "automation": "supervised", "progress": [ { "step": "Strategize", "status": "running" }, { "step": "Execute", "status": "waiting" }, { "step": "Apply", "status": "waiting" } ], "strategy_progress": { "decisions_made": 4, "invariants_enforced": 2, "child_plans_planned": 3, "elapsed": "00:00:28" } }, "timing": { "started": "2026-02-08T12:57:01Z", "duration_ms": 28000 }, "messages": ["Strategize in progress"] } ``` === "YAML" ```yaml command: plan status status: ok exit_code: 0 data: plan_id: "01HXM9F2ZK4Q7C2B3F2R4VYV6J" phase: strategize state: processing action: local/refactor-auth project: local/api-service automation: supervised progress: - step: Strategize status: running - step: Execute status: waiting - step: Apply status: waiting strategy_progress: decisions_made: 4 invariants_enforced: 2 child_plans_planned: 3 elapsed: "00:00:28" timing: started: "2026-02-08T12:57:01Z" duration_ms: 28000 messages: - "Strategize in progress" ``` Status of a plan that encountered an error: === "Rich" 

    $ agents plan status 01HXM7K2ZK4Q7C2B3F2R4VYV6J

    ╭─ Plan Status ────────────────────╮
    │ Plan: 01HXM7K2ZK4Q7C2B3F2R4VYV6J │
    │ Phase: execute                   │
    │ State: errored                   │
    │ Action: local/migrate-db         │
    │ Project: local/api-service       │
    │ Automation: supervised           │
    │ Attempt: 1                       │
    ╰──────────────────────────────────╯

    ╭─ Progress ───────────╮
    │ ✓ Strategize         │
    │ ✗ Execute            │
    │ ○ Apply (skipped)    │
    ╰──────────────────────╯

    ╭─ Error Detail ──────────────────────────────────────────────────╮
    │ Error: Tool invocation failed: connection refused               │
    │ Tool: local/db-migrate                                          │
    │ Step: 4 of 6                                                    │
    │ Checkpoint: cp_01HXM8C2 (sandbox state preserved)               │
    │ Recoverable: yes — use "agents plan prompt" to provide guidance │
    ╰─────────────────────────────────────────────────────────────────╯

    ╭─ Cost ───────────────╮
    │ Tokens Used: 8,340   │
    │ Cost So Far: $0.028  │
    ╰──────────────────────╯

    ✗ ERROR Plan errored — use `agents plan prompt` to resume or `agents plan cancel` to abort
=== "Plain" ``` $ agents plan status 01HXM7K2ZK4Q7C2B3F2R4VYV6J Plan Status Plan: 01HXM7K2ZK4Q7C2B3F2R4VYV6J Phase: execute State: errored Action: local/migrate-db Project: local/api-service Automation: supervised Attempt: 1 Progress [OK] Strategize [FAIL] Execute o Apply (skipped) Error Detail Error: Tool invocation failed: connection refused Tool: local/db-migrate Step: 4 of 6 Checkpoint: cp_01HXM8C2 (sandbox state preserved) Recoverable: yes -- use "agents plan prompt" to provide guidance Cost Tokens Used: 8,340 Cost So Far: $0.028 [ERROR] Plan errored -- use `agents plan prompt` to resume or `agents plan cancel` to abort ``` === "JSON" ```json { "command": "plan status", "status": "error", "exit_code": 1, "data": { "plan_id": "01HXM7K2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "state": "errored", "action": "local/migrate-db", "project": "local/api-service", "automation": "supervised", "attempt": 1, "progress": [ { "step": "Strategize", "status": "done" }, { "step": "Execute", "status": "failed" }, { "step": "Apply", "status": "skipped" } ], "error": { "message": "Tool invocation failed: connection refused", "tool": "local/db-migrate", "step": "4 of 6", "checkpoint": "cp_01HXM8C2", "recoverable": true }, "cost": { "tokens_used": 8340, "cost_so_far": 0.028 } }, "timing": { "started": "2026-02-08T12:57:01Z", "duration_ms": 72000 }, "messages": ["Plan errored — use `agents plan prompt` to resume or `agents plan cancel` to abort"] } ``` === "YAML" ```yaml command: plan status status: error exit_code: 1 data: plan_id: "01HXM7K2ZK4Q7C2B3F2R4VYV6J" phase: execute state: errored action: local/migrate-db project: local/api-service automation: supervised attempt: 1 progress: - step: Strategize status: done - step: Execute status: failed - step: Apply status: skipped error: message: "Tool invocation failed: connection refused" tool: local/db-migrate step: "4 of 6" checkpoint: cp_01HXM8C2 recoverable: true cost: tokens_used: 8340 cost_so_far: 0.028 timing: started: "2026-02-08T12:57:01Z" duration_ms: 72000 messages: - "Plan errored — use `agents plan prompt` to resume or `agents plan cancel` to abort" ``` ##### agents plan cancel 
agents plan cancel [(--reason|-r) <REASON>] <PLAN_ID>
!!! warning "Irreversible State Transition" Cancel a plan that is not in a terminal state. Cancellation transitions the plan to the `cancelled` state, which is ==terminal==. The sandbox and any child plan artifacts are preserved for inspection but cannot be resumed. !!! tip "Recovery After Cancel" A cancelled plan cannot be resumed, but you can re-execute the same action with `agents plan use` to create a new plan instance. **Arguments** - ``: Plan ID. - `--reason/-r TEXT`: Optional reason. **Examples** === "Rich" 

    $ agents plan cancel 01HXM8C2ZK4Q7C2B3F2R4VYV6J --reason "blocked on credentials"

    ╭─ Plan Cancelled ─────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    │ Phase: execute                   │
    │ Reason: blocked on credentials   │
    │ State: cancelled                 │
    │ Cancelled At: 13:02:15           │
    ╰──────────────────────────────────╯

    ╭─ Sandbox ────────────────╮
    │ Status: preserved        │
    │ Files Modified: 3        │
    │ Checkpoints: 2           │
    ╰──────────────────────────╯

    ╭─ Child Plans ─────────────╮
    │ Completed: 1              │
    │ Cancelled: 1              │
    │ Artifacts Preserved: yes  │
    ╰───────────────────────────╯

    ╭─ Recovery ───────────────────────────────────────────╮
    │ - Resolve credentials                                │
    │ - Run agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    ╰──────────────────────────────────────────────────────╯

    ✓ OK Plan cancelled
=== "Plain" ``` $ agents plan cancel 01HXM8C2ZK4Q7C2B3F2R4VYV6J --reason "blocked on credentials" Plan Cancelled Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Phase: execute Reason: blocked on credentials State: cancelled Cancelled At: 13:02:15 Sandbox Status: preserved Files Modified: 3 Checkpoints: 2 Child Plans Completed: 1 Cancelled: 1 Artifacts Preserved: yes Recovery - Resolve credentials - Run agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J [OK] Plan cancelled ``` === "JSON" ```json { "command": "plan cancel", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "reason": "blocked on credentials", "state": "cancelled", "cancelled_at": "13:02:15", "sandbox": { "status": "preserved", "files_modified": 3, "checkpoints": 2 }, "child_plans": { "completed": 1, "cancelled": 1, "artifacts_preserved": true }, "recovery": [ "Resolve credentials", "Run agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J" ] }, "timing": { "started": "2026-02-08T13:02:15Z", "duration_ms": 340 }, "messages": ["Plan cancelled"] } ``` === "YAML" ```yaml command: plan cancel status: ok exit_code: 0 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" phase: execute reason: "blocked on credentials" state: cancelled cancelled_at: "13:02:15" sandbox: status: preserved files_modified: 3 checkpoints: 2 child_plans: completed: 1 cancelled: 1 artifacts_preserved: true recovery: - "Resolve credentials" - "Run agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J" timing: started: "2026-02-08T13:02:15Z" duration_ms: 340 messages: - "Plan cancelled" ``` ##### agents plan tree 
agents plan tree [--show-superseded] <PLAN_ID>
**Purpose** Render the decision tree for a plan. **Arguments** - ``: Plan ID (required). - `--show-superseded`: Include superseded decisions. **Examples** === "Rich" 

    $ agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Decision Tree ──────────────────────────────────────────────────────────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J                                                         │
    │ ├─ [prompt_definition] "Increase test coverage to 85%"                                   │
    │ ├─ [invariant_enforced] "Prioritize financial transaction and user mgmt code"            │
    │ ├─ [invariant_enforced] "All API calls over TCP must be mocked"                          │
    │ ├─ [strategy_choice] "Prioritize auth and payments" (confidence: 0.82)                   │
    │ ├─ [subplan_parallel_spawn] "Implement auth and payment modules, in parallel"            │
    │ │  ├─ [subplan_spawn] "Write auth tests" → Plan: 01HXM9F1A                               │
    │ │  └─ [subplan_spawn] "Write payment tests" → Plan: 01HXM9F2B                            │
    │ └─ [subplan_parallel_spawn] "Write tests for remaining modules"                          │
    │    └─ ...                                                                                │
    ╰──────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Tree Summary ─────────────╮
    │ Nodes: 9                   │
    │ Depth: 3                   │
    │ Child Plans: 2+            │
    │ Invariants: 2              │
    │ Superseded: 0 (hidden)     │
    ╰────────────────────────────╯

    ╭─ Child Plans ──────────────────────────────────────╮
    │ ID          Phase    State                         │
    │ ──────────  ───────  ─────────                     │
    │ 01HXM9F1A   execute  processing                    │
    │ 01HXM9F2B   execute  queued                        │
    ╰────────────────────────────────────────────────────╯

    ╭─ Decision IDs (for correction) ──────────────────╮
    │ Root: 01HXM9A0B1Q2W3R5G8Z0P4Q1X8                 │
    │ Invariant 1: 01HXM9A0C1R3X4S6G9Z1P5Q2Y9          │
    │ Invariant 2: 01HXM9A0D2S4Y5T7H0Z2P6Q3Z0          │
    │ Strategy: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9             │
    │ Parallel 1: 01HXM9A1D3R8X5S7H1Z2P5Q2Y0           │
    │ Spawn Auth: 01HXM9A2D3Q8W4R6H9Z1P5Q2X0           │
    │ Spawn Payment: 01HXM9A3E4Q9W5R7I0Z2P6Q3X1        │
    │ Parallel 2: 01HXM9A4F5Q0W6R8J1Z3P7Q4X2           │
    ╰──────────────────────────────────────────────────╯

    ✓ OK Decision tree rendered
=== "Plain" ``` $ agents plan tree 01HXM8C2ZK4Q7C2B3F2R4VYV6J Decision Tree Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J +-- [prompt_definition] "Increase test coverage to 85%" +-- [invariant_enforced] "Prioritize financial transaction and user mgmt code" +-- [invariant_enforced] "All API calls over TCP must be mocked" +-- [strategy_choice] "Prioritize auth and payments" (confidence: 0.82) +-- [subplan_parallel_spawn] "Implement auth and payment modules, in parallel" | +-- [subplan_spawn] "Write auth tests" -> Plan: 01HXM9F1A | +-- [subplan_spawn] "Write payment tests" -> Plan: 01HXM9F2B +-- [subplan_parallel_spawn] "Write tests for remaining modules" +-- ... Tree Summary Nodes: 9 Depth: 3 Child Plans: 2+ Invariants: 2 Superseded: 0 (hidden) Child Plans ID Phase State ---------- ------- --------- 01HXM9F1A execute processing 01HXM9F2B execute queued Decision IDs (for correction) Root: 01HXM9A0B1Q2W3R5G8Z0P4Q1X8 Invariant 1: 01HXM9A0C1R3X4S6G9Z1P5Q2Y9 Invariant 2: 01HXM9A0D2S4Y5T7H0Z2P6Q3Z0 Strategy: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Parallel 1: 01HXM9A1D3R8X5S7H1Z2P5Q2Y0 Spawn Auth: 01HXM9A2D3Q8W4R6H9Z1P5Q2X0 Spawn Payment: 01HXM9A3E4Q9W5R7I0Z2P6Q3X1 Parallel 2: 01HXM9A4F5Q0W6R8J1Z3P7Q4X2 [OK] Decision tree rendered ``` === "JSON" ```json { "command": "plan tree", "status": "ok", "exit_code": 0, "data": { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "tree": { "type": "prompt_definition", "description": "Increase test coverage to 85%", "children": [ { "type": "invariant_enforced", "description": "Prioritize financial transaction and user mgmt code" }, { "type": "invariant_enforced", "description": "All API calls over TCP must be mocked" }, { "type": "strategy_choice", "description": "Prioritize auth and payments", "confidence": 0.82 }, { "type": "subplan_parallel_spawn", "description": "Implement auth and payment modules, in parallel", "children": [ { "type": "subplan_spawn", "description": "Write auth tests", "plan_id": "01HXM9F1A" }, { "type": "subplan_spawn", "description": "Write payment tests", "plan_id": "01HXM9F2B" } ] }, { "type": "subplan_parallel_spawn", "description": "Write tests for remaining modules", "children": ["..."] } ] }, "summary": { "nodes": 9, "depth": 3, "child_plans": "2+", "invariants": 2, "superseded": 0 }, "child_plans": [ { "id": "01HXM9F1A", "phase": "execute", "state": "processing" }, { "id": "01HXM9F2B", "phase": "execute", "state": "queued" } ], "decision_ids": { "root": "01HXM9A0B1Q2W3R5G8Z0P4Q1X8", "invariant_1": "01HXM9A0C1R3X4S6G9Z1P5Q2Y9", "invariant_2": "01HXM9A0D2S4Y5T7H0Z2P6Q3Z0", "strategy": "01HXM9A1C2Q7W3R5G8Z0P4Q1X9", "parallel_1": "01HXM9A1D3R8X5S7H1Z2P5Q2Y0", "spawn_auth": "01HXM9A2D3Q8W4R6H9Z1P5Q2X0", "spawn_payment": "01HXM9A3E4Q9W5R7I0Z2P6Q3X1", "parallel_2": "01HXM9A4F5Q0W6R8J1Z3P7Q4X2" } }, "timing": { "started": "2026-02-08T12:58:00Z", "duration_ms": 85 }, "messages": ["Decision tree rendered"] } ``` === "YAML" ```yaml command: plan tree status: ok exit_code: 0 data: plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" tree: type: prompt_definition description: "Increase test coverage to 85%" children: - type: invariant_enforced description: "Prioritize financial transaction and user mgmt code" - type: invariant_enforced description: "All API calls over TCP must be mocked" - type: strategy_choice description: "Prioritize auth and payments" confidence: 0.82 - type: subplan_parallel_spawn description: "Implement auth and payment modules, in parallel" children: - type: subplan_spawn description: "Write auth tests" plan_id: "01HXM9F1A" - type: subplan_spawn description: "Write payment tests" plan_id: "01HXM9F2B" - type: subplan_parallel_spawn description: "Write tests for remaining modules" children: - "..." summary: nodes: 9 depth: 3 child_plans: "2+" invariants: 2 superseded: 0 child_plans: - id: "01HXM9F1A" phase: execute state: processing - id: "01HXM9F2B" phase: execute state: queued decision_ids: root: "01HXM9A0B1Q2W3R5G8Z0P4Q1X8" invariant_1: "01HXM9A0C1R3X4S6G9Z1P5Q2Y9" invariant_2: "01HXM9A0D2S4Y5T7H0Z2P6Q3Z0" strategy: "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" parallel_1: "01HXM9A1D3R8X5S7H1Z2P5Q2Y0" spawn_auth: "01HXM9A2D3Q8W4R6H9Z1P5Q2X0" spawn_payment: "01HXM9A3E4Q9W5R7I0Z2P6Q3X1" parallel_2: "01HXM9A4F5Q0W6R8J1Z3P7Q4X2" timing: started: "2026-02-08T12:58:00Z" duration_ms: 85 messages: - "Decision tree rendered" ``` ##### agents plan explain 
agents plan explain [--show-context] [--show-reasoning] <DECISION_ID>
**Purpose** Show a detailed explanation for a decision. **Arguments** - ``: Decision ID. - `--show-context`: Include the context snapshot. - `--show-reasoning`: Include raw model reasoning if available. **Examples** === "Rich" 

    $ agents plan explain 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --show-context

    ╭─ Decision ─────────────────────────────────────╮
    │ ID: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9                 │
    │ Type: strategy_choice                          │
    │ Question: Which modules should be prioritized? │
    │ Chosen: Auth and payments                      │
    │ Confidence: 0.82                               │
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J               │
    │ Sequence: 2 of 5                               │
    │ Created: 2026-02-08 12:58                      │
    ╰────────────────────────────────────────────────╯

    ╭─ Alternatives Considered ──────────────────────╮
    │ 1. Auth and payments (chosen)                  │
    │ 2. User module first (coverage 71%, med risk)  │
    │ 3. All modules equally (spread thin)           │
    ╰────────────────────────────────────────────────╯

    ╭─ Impact ──────────────────────╮
    │ Downstream Decisions: 3       │
    │ Downstream Child Plans: 2     │
    │ Artifacts Produced: 5         │
    │ Correction Impact: medium     │
    ╰───────────────────────────────╯

    ╭─ Context Snapshot ───────────────╮
    │ - Coverage < 70% in auth         │
    │ - Payments failures last release │
    │ - Auth: 12 files, 45% coverage   │
    │ - Payments: 8 files, 52% cover.  │
    │ Hot Context Hash: sha256:4b2e... │
    ╰──────────────────────────────────╯

    ╭─ Rationale ───────────────────────────────────────╮
    │ Auth and payment modules have the lowest coverage │
    │ and highest business risk. Auth handles security  │
    │ tokens, payments handles money. Both had bugs in  │
    │ the last release traceable to missing tests.      │
    ╰───────────────────────────────────────────────────╯

    ╭─ Correction ──────────────────────────────────────────────╮
    │ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9            │
    │   --mode revert --guidance "Prioritize payments first..." │
    ╰───────────────────────────────────────────────────────────╯

    ✓ OK Decision explained
=== "Plain" ``` $ agents plan explain 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --show-context Decision ID: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Type: strategy_choice Question: Which modules should be prioritized? Chosen: Auth and payments Confidence: 0.82 Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Sequence: 2 of 5 Created: 2026-02-08 12:58 Alternatives Considered 1. Auth and payments (chosen) 2. User module first (coverage 71%, med risk) 3. All modules equally (spread thin) Impact Downstream Decisions: 3 Downstream Child Plans: 2 Artifacts Produced: 5 Correction Impact: medium Context Snapshot - Coverage < 70% in auth - Payments failures last release - Auth: 12 files, 45% coverage - Payments: 8 files, 52% cover. Hot Context Hash: sha256:4b2e... Rationale Auth and payment modules have the lowest coverage and highest business risk. Auth handles security tokens, payments handles money. Both had bugs in the last release traceable to missing tests. Correction agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert --guidance "Prioritize payments first..." [OK] Decision explained ``` === "JSON" ```json { "command": "plan explain", "status": "ok", "exit_code": 0, "data": { "decision_id": "01HXM9A1C2Q7W3R5G8Z0P4Q1X9", "type": "strategy_choice", "question": "Which modules should be prioritized?", "chosen": "Auth and payments", "confidence": 0.82, "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "sequence": "2 of 5", "created": "2026-02-08T12:58:00Z", "alternatives": [ { "index": 1, "description": "Auth and payments", "chosen": true }, { "index": 2, "description": "User module first (coverage 71%, med risk)", "chosen": false }, { "index": 3, "description": "All modules equally (spread thin)", "chosen": false } ], "impact": { "downstream_decisions": 3, "downstream_child_plans": 2, "artifacts_produced": 5, "correction_impact": "medium" }, "context_snapshot": { "items": [ "Coverage < 70% in auth", "Payments failures last release", "Auth: 12 files, 45% coverage", "Payments: 8 files, 52% cover." ], "hot_context_hash": "sha256:4b2e..." }, "rationale": "Auth and payment modules have the lowest coverage and highest business risk. Auth handles security tokens, payments handles money. Both had bugs in the last release traceable to missing tests.", "correction_hint": "agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert --guidance "Prioritize payments first..."" }, "timing": { "started": "2026-02-08T12:58:00Z", "duration_ms": 110 }, "messages": ["Decision explained"] } ``` === "YAML" ```yaml command: plan explain status: ok exit_code: 0 data: decision_id: "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" type: strategy_choice question: "Which modules should be prioritized?" chosen: "Auth and payments" confidence: 0.82 plan_id: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" sequence: "2 of 5" created: "2026-02-08T12:58:00Z" alternatives: - index: 1 description: "Auth and payments" chosen: true - index: 2 description: "User module first (coverage 71%, med risk)" chosen: false - index: 3 description: "All modules equally (spread thin)" chosen: false impact: downstream_decisions: 3 downstream_child_plans: 2 artifacts_produced: 5 correction_impact: medium context_snapshot: items: - "Coverage < 70% in auth" - "Payments failures last release" - "Auth: 12 files, 45% coverage" - "Payments: 8 files, 52% cover." hot_context_hash: "sha256:4b2e..." rationale: >- Auth and payment modules have the lowest coverage and highest business risk. Auth handles security tokens, payments handles money. Both had bugs in the last release traceable to missing tests. correction_hint: >- agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert --guidance "Prioritize payments first..." timing: started: "2026-02-08T12:58:00Z" duration_ms: 110 messages: - "Decision explained" ``` Including the raw model reasoning with `--show-reasoning`: === "Rich" 

    $ agents plan explain --show-reasoning 01HXM9A1C2Q7W3R5G8Z0P4Q1X9

    ╭─ Decision ──────────────────────────────╮
    │ ID: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9          │
    │ Type: strategy_choice                   │
    │ Choice: Convert to async/await          │
    │ Alternatives: 3                         │
    ╰─────────────────────────────────────────╯

    ╭─ Alternatives Considered ────────────────────────────────────╮
    │ 1. Convert to async/await patterns (chosen)                  │
    │    2. Keep synchronous with thread pool                      │
    │    3. Use callback-based approach                            │
    ╰──────────────────────────────────────────────────────────────╯

    ╭─ Rationale ──────────────────────────────────────────────────╮
    │ Async/await is the modern Python standard for I/O-bound      │
    │ operations. The project already uses asyncio in 3 modules.   │
    │ Thread pools would add complexity without native support.    │
    ╰──────────────────────────────────────────────────────────────╯

    ╭─ Model Reasoning (raw) ───────────────────────────────────────╮
    │ I need to decide on the concurrency pattern for the payment   │
    │ processing module. Let me analyze the current codebase:       │
    │                                                               │
    │ 1. src/payments/api.py uses synchronous requests.             │
    │ 2. src/core/scheduler.py already uses asyncio.                │
    │ 3. The database driver (asyncpg) supports async natively.     │
    │ 4. Project invariant says "prefer modern Python patterns".    │
    │                                                               │
    │ Given that 3/5 core modules already use asyncio, and the      │
    │ database driver supports it, converting to async/await is     │
    │ the most consistent choice. Thread pools would work but       │
    │ add unnecessary complexity and don't integrate well with      │
    │ the existing asyncio event loop in scheduler.py.              │
    ╰───────────────────────────────────────────────────────────────╯

    ✓ OK Decision explained
=== "Plain" ``` $ agents plan explain --show-reasoning 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Decision ID: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Type: strategy_choice Choice: Convert to async/await Alternatives: 3 Alternatives Considered 1. Convert to async/await patterns (chosen) 2. Keep synchronous with thread pool 3. Use callback-based approach Rationale Async/await is the modern Python standard for I/O-bound operations. The project already uses asyncio in 3 modules. Thread pools would add complexity without native support. Model Reasoning (raw) I need to decide on the concurrency pattern for the payment processing module. Let me analyze the current codebase: 1. src/payments/api.py uses synchronous requests. 2. src/core/scheduler.py already uses asyncio. 3. The database driver (asyncpg) supports async natively. 4. Project invariant says "prefer modern Python patterns". Given that 3/5 core modules already use asyncio, and the database driver supports it, converting to async/await is the most consistent choice. Thread pools would work but add unnecessary complexity and don't integrate well with the existing asyncio event loop in scheduler.py. [OK] Decision explained ``` === "JSON" ```json { "command": "plan explain", "status": "ok", "exit_code": 0, "data": { "decision_id": "01HXM9A1C2Q7W3R5G8Z0P4Q1X9", "type": "strategy_choice", "choice": "Convert to async/await", "alternatives_count": 3, "alternatives": [ { "index": 1, "description": "Convert to async/await patterns", "chosen": true }, { "index": 2, "description": "Keep synchronous with thread pool", "chosen": false }, { "index": 3, "description": "Use callback-based approach", "chosen": false } ], "rationale": "Async/await is the modern Python standard for I/O-bound operations. The project already uses asyncio in 3 modules. Thread pools would add complexity without native support.", "model_reasoning": "I need to decide on the concurrency pattern for the payment processing module. Let me analyze the current codebase:\n\n1. src/payments/api.py uses synchronous requests.\n2. src/core/scheduler.py already uses asyncio.\n3. The database driver (asyncpg) supports async natively.\n4. Project invariant says \"prefer modern Python patterns\".\n\nGiven that 3/5 core modules already use asyncio, and the database driver supports it, converting to async/await is the most consistent choice. Thread pools would work but add unnecessary complexity and don't integrate well with the existing asyncio event loop in scheduler.py." }, "timing": { "started": "2026-02-08T12:58:00Z", "duration_ms": 95 }, "messages": ["Decision explained"] } ``` === "YAML" ```yaml command: plan explain status: ok exit_code: 0 data: decision_id: "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" type: strategy_choice choice: "Convert to async/await" alternatives_count: 3 alternatives: - index: 1 description: "Convert to async/await patterns" chosen: true - index: 2 description: "Keep synchronous with thread pool" chosen: false - index: 3 description: "Use callback-based approach" chosen: false rationale: >- Async/await is the modern Python standard for I/O-bound operations. The project already uses asyncio in 3 modules. Thread pools would add complexity without native support. model_reasoning: >- I need to decide on the concurrency pattern for the payment processing module. Let me analyze the current codebase: 1. src/payments/api.py uses synchronous requests. 2. src/core/scheduler.py already uses asyncio. 3. The database driver (asyncpg) supports async natively. 4. Project invariant says "prefer modern Python patterns". Given that 3/5 core modules already use asyncio, and the database driver supports it, converting to async/await is the most consistent choice. timing: started: "2026-02-08T12:58:00Z" duration_ms: 95 messages: - "Decision explained" ``` ##### agents plan correct 
agents plan correct --mode (revert|append) (--guidance|-g) <GUIDANCE>
                   [--dry-run] [--yes|-y] <DECISION_ID>
**Purpose** Correct a decision either by reverting and re-executing or by appending a fix. **Arguments** - ``: Decision ID. - `--mode revert|append`: Correction mode. - `--guidance/-g TEXT`: Guidance text. - `--dry-run`: Show impact without executing. - `--yes`: Skip confirmation for revert mode. **Examples** === "Rich" 

    $ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert \
      --guidance "Prioritize payments first" --yes

    ╭─ Correction ────────────────────────────────────────╮
    │ Mode: revert                                        │
    │ Impact: 3 decisions, 2 child plans, 5 artifacts     │
    │ New Decision: 01HXM9B7Z3Q1Q8K2E9H7K3W2M8            │
    │ Corrects: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9                │
    │ Attempt: 2                                          │
    ╰─────────────────────────────────────────────────────╯

    ╭─ Affected Subtree ──────────────╮
    │ Decisions Invalidated: 3        │
    │ Child Plans Rolled Back: 2      │
    │ Artifacts Archived: 5           │
    │ Unaffected Decisions: 2         │
    ╰─────────────────────────────────╯

    ╭─ Sandbox Rollback ─────────────╮
    │ Checkpoint: cp_01HXM8C2        │
    │ Files Reverted: 5              │
    │ Status: restored               │
    ╰────────────────────────────────╯

    ╭─ Recompute ──────────────╮
    │ Queued: 2 child plans    │
    │ ETA: 4m                  │
    ╰──────────────────────────╯

    ╭─ History ───────────────────────────────────────────╮
    │ - Original decision superseded                      │
    │ - Prior artifacts archived for comparison           │
    │ - agents plan diff --correction 01HXM9B7Z3Q1Q8K2..  │
    ╰─────────────────────────────────────────────────────╯

    ✓ OK Correction applied
=== "Plain" ``` $ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert --guidance "Prioritize payments first" --yes Correction Mode: revert Impact: 3 decisions, 2 child plans, 5 artifacts New Decision: 01HXM9B7Z3Q1Q8K2E9H7K3W2M8 Corrects: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Attempt: 2 Affected Subtree Decisions Invalidated: 3 Child Plans Rolled Back: 2 Artifacts Archived: 5 Unaffected Decisions: 2 Sandbox Rollback Checkpoint: cp_01HXM8C2 Files Reverted: 5 Status: restored Recompute Queued: 2 child plans ETA: 4m History - Original decision superseded - Prior artifacts archived for comparison - agents plan diff --correction 01HXM9B7Z3Q1Q8K2.. [OK] Correction applied ``` === "JSON" ```json { "command": "plan correct", "status": "ok", "exit_code": 0, "data": { "correction": { "mode": "revert", "impact": "3 decisions, 2 child plans, 5 artifacts", "new_decision": "01HXM9B7Z3Q1Q8K2E9H7K3W2M8", "corrects": "01HXM9A1C2Q7W3R5G8Z0P4Q1X9", "attempt": 2 }, "affected_subtree": { "decisions_invalidated": 3, "child_plans_rolled_back": 2, "artifacts_archived": 5, "unaffected_decisions": 2 }, "sandbox_rollback": { "checkpoint": "cp_01HXM8C2", "files_reverted": 5, "status": "restored" }, "recompute": { "queued": "2 child plans", "eta": "4m" }, "history": [ "Original decision superseded", "Prior artifacts archived for comparison", "agents plan diff --correction 01HXM9B7Z3Q1Q8K2.." ] }, "timing": { "started": "2025-06-15T10:24:00Z", "duration_ms": 2350 }, "messages": ["Correction applied"] } ``` === "YAML" ```yaml command: plan correct status: ok exit_code: 0 data: correction: mode: revert impact: "3 decisions, 2 child plans, 5 artifacts" new_decision: "01HXM9B7Z3Q1Q8K2E9H7K3W2M8" corrects: "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" attempt: 2 affected_subtree: decisions_invalidated: 3 child_plans_rolled_back: 2 artifacts_archived: 5 unaffected_decisions: 2 sandbox_rollback: checkpoint: cp_01HXM8C2 files_reverted: 5 status: restored recompute: queued: "2 child plans" eta: "4m" history: - "Original decision superseded" - "Prior artifacts archived for comparison" - "agents plan diff --correction 01HXM9B7Z3Q1Q8K2.." timing: started: "2025-06-15T10:24:00Z" duration_ms: 2350 messages: - "Correction applied" ``` Using `--mode append` to add a corrective decision without reverting existing work (useful when the original decision was partially correct): === "Rich" 

    $ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode append \
      --guidance "Also add rate limiting to the auth endpoints"

    ╭─ Correction ─────────────────────────────────────╮
    │ Mode: append                                     │
    │ Impact: adds to existing subtree, no rollback    │
    │ New Decision: 01HXM9C3Z5T2Q8K2E9H7K3W2M8         │
    │ Appended After: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9       │
    │ Attempt: 2                                       │
    ╰──────────────────────────────────────────────────╯

    ╭─ Append Detail ─────────────────────────────────────────────────╮
    │ Original decision preserved: yes                                │
    │ Existing artifacts kept: yes                                    │
    │ Additional work: appended as new child plan                     │
    │ The original 5 artifacts remain; a new child plan will add      │
    │ rate-limiting code on top of the existing auth changes.         │
    ╰─────────────────────────────────────────────────────────────────╯

    ╭─ Queued ──────────╮
    │ New child: 1      │
    │ ETA: 2m           │
    ╰───────────────────╯

    ✓ OK Append correction queued
=== "Plain" ``` $ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode append --guidance "Also add rate limiting to the auth endpoints" Correction Mode: append Impact: adds to existing subtree, no rollback New Decision: 01HXM9C3Z5T2Q8K2E9H7K3W2M8 Appended After: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Attempt: 2 Append Detail Original decision preserved: yes Existing artifacts kept: yes Additional work: appended as new child plan The original 5 artifacts remain; a new child plan will add rate-limiting code on top of the existing auth changes. Queued New child: 1 ETA: 2m [OK] Append correction queued ``` === "JSON" ```json { "command": "plan correct", "status": "ok", "exit_code": 0, "data": { "correction": { "mode": "append", "impact": "adds to existing subtree, no rollback", "new_decision": "01HXM9C3Z5T2Q8K2E9H7K3W2M8", "appended_after": "01HXM9A1C2Q7W3R5G8Z0P4Q1X9", "attempt": 2 }, "append_detail": { "original_decision_preserved": true, "existing_artifacts_kept": true, "additional_work": "appended as new child plan", "note": "The original 5 artifacts remain; a new child plan will add rate-limiting code on top of the existing auth changes." }, "queued": { "new_child": 1, "eta": "2m" } }, "timing": { "started": "2025-06-15T10:26:00Z", "duration_ms": 890 }, "messages": ["Append correction queued"] } ``` === "YAML" ```yaml command: plan correct status: ok exit_code: 0 data: correction: mode: append impact: "adds to existing subtree, no rollback" new_decision: "01HXM9C3Z5T2Q8K2E9H7K3W2M8" appended_after: "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" attempt: 2 append_detail: original_decision_preserved: true existing_artifacts_kept: true additional_work: "appended as new child plan" note: "The original 5 artifacts remain; a new child plan will add rate-limiting code on top of the existing auth changes." queued: new_child: 1 eta: "2m" timing: started: "2025-06-15T10:26:00Z" duration_ms: 890 messages: - "Append correction queued" ``` Using `--dry-run` to preview the impact of a correction before committing to it: === "Rich" 

    $ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert \
      --guidance "Use async/await pattern instead" --dry-run

    ╭─ Dry Run — Correction Preview ─────────────────────────────────────╮
    │ ⚠  This is a preview only. No changes will be made.                │
    ╰────────────────────────────────────────────────────────────────────╯

    ╭─ Would Revert ───────────────────────────────────────╮
    │ Decisions to invalidate: 3                           │
    │   01HXM9A1..  strategy_choice    "sync pattern"      │
    │   01HXM9A2..  implementation_choice  "requests"      │
    │   01HXM9A3..  tool_invocation    write_file ×4       │
    │ Child plans to roll back: 2                          │
    │ Artifacts to archive: 5 files                        │
    │ Unaffected decisions: 2 (will be kept)               │
    ╰──────────────────────────────────────────────────────╯

    ╭─ Estimated Cost ──────────╮
    │ Re-strategize: ~$0.012    │
    │ Re-execute: ~$0.035       │
    │ Total: ~$0.047            │
    │ ETA: ~4 minutes           │
    ╰───────────────────────────╯

    To execute this correction, remove --dry-run and add --yes
=== "Plain" ``` $ agents plan correct 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 --mode revert --guidance "Use async/await pattern instead" --dry-run Dry Run -- Correction Preview WARNING: This is a preview only. No changes will be made. Would Revert Decisions to invalidate: 3 01HXM9A1.. strategy_choice "sync pattern" 01HXM9A2.. implementation_choice "requests" 01HXM9A3.. tool_invocation write_file x4 Child plans to roll back: 2 Artifacts to archive: 5 files Unaffected decisions: 2 (will be kept) Estimated Cost Re-strategize: ~$0.012 Re-execute: ~$0.035 Total: ~$0.047 ETA: ~4 minutes To execute this correction, remove --dry-run and add --yes ``` === "JSON" ```json { "command": "plan correct", "status": "ok", "exit_code": 0, "data": { "dry_run": true, "would_revert": { "decisions_to_invalidate": [ { "id": "01HXM9A1..", "type": "strategy_choice", "label": "sync pattern" }, { "id": "01HXM9A2..", "type": "implementation_choice", "label": "requests" }, { "id": "01HXM9A3..", "type": "tool_invocation", "label": "write_file x4" } ], "child_plans_to_roll_back": 2, "artifacts_to_archive": 5, "unaffected_decisions": 2 }, "estimated_cost": { "re_strategize": "$0.012", "re_execute": "$0.035", "total": "$0.047", "eta": "~4 minutes" } }, "timing": { "started": "2025-06-15T10:28:00Z", "duration_ms": 320 }, "messages": ["To execute this correction, remove --dry-run and add --yes"] } ``` === "YAML" ```yaml command: plan correct status: ok exit_code: 0 data: dry_run: true would_revert: decisions_to_invalidate: - id: "01HXM9A1.." type: strategy_choice label: "sync pattern" - id: "01HXM9A2.." type: implementation_choice label: "requests" - id: "01HXM9A3.." type: tool_invocation label: "write_file x4" child_plans_to_roll_back: 2 artifacts_to_archive: 5 unaffected_decisions: 2 estimated_cost: re_strategize: "$0.012" re_execute: "$0.035" total: "$0.047" eta: "~4 minutes" timing: started: "2025-06-15T10:28:00Z" duration_ms: 320 messages: - "To execute this correction, remove --dry-run and add --yes" ``` ##### agents plan diff 
agents plan diff (--correction <CORRECTION_ATTEMPT_ID>|<PLAN_ID>)
**Purpose** Show diffs for a plan or a correction attempt. **Arguments** - ``: Show diff for a plan (positional argument). Mutually exclusive with --correction. - `--correction CORRECTION_ATTEMPT_ID`: Show diff for a correction attempt instead. **Examples** === "Rich" 

    $ agents plan diff 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Diff Summary ─────────────────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J               │
    │ Project: local/api-service                     │
    │ Files Changed: 2                               │
    │ Insertions: 12                                 │
    │ Deletions: 4                                   │
    │ Net Change: +8 lines                           │
    ╰────────────────────────────────────────────────╯

    ╭─ Files ───────────────────────────────╮
    │ Path                 Change  Status   │
    │ ───────────────────  ──────  ──────── │
    │ src/auth/session.py  +8 -2   modified │
    │ src/auth/tokens.py   +4 -2   modified │
    ╰───────────────────────────────────────╯

    ╭─ Patch Preview ──────────────────────────╮
    │ --- a/src/auth/session.py                │
    │ +++ b/src/auth/session.py                │
    │ @@ -12,4 +12,10 @@                       │
    │ - import jwt                             │
    │ + import sessionlib                      │
    │ - def validate_token(...)                │
    │ + def validate_session(...)              │
    │ --- a/src/auth/tokens.py                 │
    │ +++ b/src/auth/tokens.py                 │
    │ @@ -5,3 +5,7 @@                          │
    │ - TOKEN_EXPIRY = 3600                    │
    │ + TOKEN_EXPIRY = 7200                    │
    ╰──────────────────────────────────────────╯

    ╭─ Risk Assessment ────────────────╮
    │ API Compatibility: preserved     │
    │ Test Coverage: maintained        │
    │ Breaking Changes: none detected  │
    ╰──────────────────────────────────╯

    ✓ OK Diff generated
=== "Plain" ``` $ agents plan diff 01HXM8C2ZK4Q7C2B3F2R4VYV6J Diff Summary Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Project: local/api-service Files Changed: 2 Insertions: 12 Deletions: 4 Net Change: +8 lines Files Path Change Status ------------------- ------ -------- src/auth/session.py +8 -2 modified src/auth/tokens.py +4 -2 modified Patch Preview --- a/src/auth/session.py +++ b/src/auth/session.py @@ -12,4 +12,10 @@ - import jwt + import sessionlib - def validate_token(...) + def validate_session(...) --- a/src/auth/tokens.py +++ b/src/auth/tokens.py @@ -5,3 +5,7 @@ - TOKEN_EXPIRY = 3600 + TOKEN_EXPIRY = 7200 Risk Assessment API Compatibility: preserved Test Coverage: maintained Breaking Changes: none detected [OK] Diff generated ``` === "JSON" ```json { "command": "plan diff", "status": "ok", "exit_code": 0, "data": { "diff_summary": { "plan": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "project": "local/api-service", "files_changed": 2, "insertions": 12, "deletions": 4, "net_change": "+8 lines" }, "files": [ { "path": "src/auth/session.py", "change": "+8 -2", "status": "modified" }, { "path": "src/auth/tokens.py", "change": "+4 -2", "status": "modified" } ], "patch_preview": [ { "file": "src/auth/session.py", "hunks": [ { "range": "@@ -12,4 +12,10 @@", "deletions": ["import jwt", "def validate_token(...)"], "insertions": ["import sessionlib", "def validate_session(...)"] } ] }, { "file": "src/auth/tokens.py", "hunks": [ { "range": "@@ -5,3 +5,7 @@", "deletions": ["TOKEN_EXPIRY = 3600"], "insertions": ["TOKEN_EXPIRY = 7200"] } ] } ], "risk_assessment": { "api_compatibility": "preserved", "test_coverage": "maintained", "breaking_changes": "none detected" } }, "timing": { "started": "2025-06-15T10:30:00Z", "duration_ms": 750 }, "messages": ["Diff generated"] } ``` === "YAML" ```yaml command: plan diff status: ok exit_code: 0 data: diff_summary: plan: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" project: local/api-service files_changed: 2 insertions: 12 deletions: 4 net_change: "+8 lines" files: - path: src/auth/session.py change: "+8 -2" status: modified - path: src/auth/tokens.py change: "+4 -2" status: modified patch_preview: - file: src/auth/session.py hunks: - range: "@@ -12,4 +12,10 @@" deletions: - "import jwt" - "def validate_token(...)" insertions: - "import sessionlib" - "def validate_session(...)" - file: src/auth/tokens.py hunks: - range: "@@ -5,3 +5,7 @@" deletions: - "TOKEN_EXPIRY = 3600" insertions: - "TOKEN_EXPIRY = 7200" risk_assessment: api_compatibility: preserved test_coverage: maintained breaking_changes: none detected timing: started: "2025-06-15T10:30:00Z" duration_ms: 750 messages: - "Diff generated" ``` Showing the diff for a specific correction attempt, comparing what changed between the original and corrected execution: === "Rich" 

    $ agents plan diff --correction 01HXM9B7Z3Q1Q8K2E9H7K3W2M8

    ╭─ Correction Diff ───────────────────────────────╮
    │ Correction: 01HXM9B7Z3Q1Q8K2E9H7K3W2M8          │
    │ Original Decision: 01HXM9A1C2Q7W3R5..           │
    │ Mode: revert                                    │
    │ Files Changed: 3                                │
    │ New Insertions: 18                              │
    │ New Deletions: 6                                │
    ╰─────────────────────────────────────────────────╯

    ╭─ Comparison ─────────────────────────────────────────────────────╮
    │ File                  Before (original)  After (corrected)       │
    │ ────────────────────  ────────────────  ────────────────────     │
    │ src/payments/api.py   +12 -4            +18 -6 (expanded)        │
    │ src/auth/tokens.py    +8 -2             (unchanged)              │
    │ tests/test_payments.py  (new file)      (new file, larger)       │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Patch Preview (corrected vs original) ───────────╮
    │ --- a/src/payments/api.py (original)              │
    │ +++ b/src/payments/api.py (corrected)             │
    │ @@ -1,12 +1,18 @@                                 │
    │ - # sync payment processing                       │
    │ + # async payment processing (corrected)          │
    │ + import asyncio                                  │
    │ + from aiohttp import ClientSession               │
    │   ...                                             │
    ╰───────────────────────────────────────────────────╯

    ✓ OK Correction diff generated
=== "Plain" ``` $ agents plan diff --correction 01HXM9B7Z3Q1Q8K2E9H7K3W2M8 Correction Diff Correction: 01HXM9B7Z3Q1Q8K2E9H7K3W2M8 Original Decision: 01HXM9A1C2Q7W3R5.. Mode: revert Files Changed: 3 New Insertions: 18 New Deletions: 6 Comparison File Before (original) After (corrected) -------------------- ----------------- -------------------- src/payments/api.py +12 -4 +18 -6 (expanded) src/auth/tokens.py +8 -2 (unchanged) tests/test_payments.py (new file) (new file, larger) Patch Preview (corrected vs original) --- a/src/payments/api.py (original) +++ b/src/payments/api.py (corrected) @@ -1,12 +1,18 @@ - # sync payment processing + # async payment processing (corrected) + import asyncio + from aiohttp import ClientSession ... [OK] Correction diff generated ``` === "JSON" ```json { "command": "plan diff", "status": "ok", "exit_code": 0, "data": { "correction_diff": { "correction": "01HXM9B7Z3Q1Q8K2E9H7K3W2M8", "original_decision": "01HXM9A1C2Q7W3R5..", "mode": "revert", "files_changed": 3, "new_insertions": 18, "new_deletions": 6 }, "comparison": [ { "file": "src/payments/api.py", "before": "+12 -4", "after": "+18 -6 (expanded)" }, { "file": "src/auth/tokens.py", "before": "+8 -2", "after": "(unchanged)" }, { "file": "tests/test_payments.py", "before": "(new file)", "after": "(new file, larger)" } ], "patch_preview": [ { "file": "src/payments/api.py", "context": "corrected vs original", "hunks": [ { "range": "@@ -1,12 +1,18 @@", "deletions": ["# sync payment processing"], "insertions": ["# async payment processing (corrected)", "import asyncio", "from aiohttp import ClientSession"] } ] } ] }, "timing": { "started": "2025-06-15T10:32:00Z", "duration_ms": 920 }, "messages": ["Correction diff generated"] } ``` === "YAML" ```yaml command: plan diff status: ok exit_code: 0 data: correction_diff: correction: "01HXM9B7Z3Q1Q8K2E9H7K3W2M8" original_decision: "01HXM9A1C2Q7W3R5.." mode: revert files_changed: 3 new_insertions: 18 new_deletions: 6 comparison: - file: src/payments/api.py before: "+12 -4" after: "+18 -6 (expanded)" - file: src/auth/tokens.py before: "+8 -2" after: "(unchanged)" - file: tests/test_payments.py before: "(new file)" after: "(new file, larger)" patch_preview: - file: src/payments/api.py context: "corrected vs original" hunks: - range: "@@ -1,12 +1,18 @@" deletions: - "# sync payment processing" insertions: - "# async payment processing (corrected)" - "import asyncio" - "from aiohttp import ClientSession" timing: started: "2025-06-15T10:32:00Z" duration_ms: 920 messages: - "Correction diff generated" ``` ##### agents plan artifacts 
agents plan artifacts <PLAN_ID>
**Purpose** List artifacts produced by a plan. **Arguments** - ``: Plan ID. **Examples** === "Rich" 

    $ agents plan artifacts 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Artifacts ─────────────────────────────────────────────────╮
    │ Path                   Type   Size    Change     Child Plan │
    │ ─────────────────────  ─────  ──────  ─────────  ───────    │
    │ src/auth/session.py    write  2.1 KB  +8 -2      root       │
    │ tests/test_session.py  write  4.7 KB  +47 -0     root       │
    │ src/auth/tokens.py     edit   1.8 KB  +4 -2      root       │
    │ tests/test_tokens.py   write  3.2 KB  +32 -0     auth       │
    ╰─────────────────────────────────────────────────────────────╯

    ╭─ Summary ───────────╮
    │ Total: 4            │
    │ Writes: 2 (new)     │
    │ Edits: 2 (modified) │
    │ Deletes: 0          │
    │ Total Size: 11.8 KB │
    ╰─────────────────────╯

    ╭─ By Plan ─────────────────╮
    │ Root Plan: 3 artifacts    │
    │ auth-tests: 1 artifact    │
    │ payment-tests: (pending)  │
    ╰───────────────────────────╯

    ✓ OK 4 artifacts listed
=== "Plain" ``` $ agents plan artifacts 01HXM8C2ZK4Q7C2B3F2R4VYV6J Artifacts Path Type Size Change Child Plan --------------------- ----- ------ --------- ---------- src/auth/session.py write 2.1 KB +8 -2 root tests/test_session.py write 4.7 KB +47 -0 root src/auth/tokens.py edit 1.8 KB +4 -2 root tests/test_tokens.py write 3.2 KB +32 -0 auth Summary Total: 4 Writes: 2 (new) Edits: 2 (modified) Deletes: 0 Total Size: 11.8 KB By Plan Root Plan: 3 artifacts auth-tests: 1 artifact payment-tests: (pending) [OK] 4 artifacts listed ``` === "JSON" ```json { "command": "plan artifacts", "status": "ok", "exit_code": 0, "data": { "artifacts": [ { "path": "src/auth/session.py", "type": "write", "size": "2.1 KB", "change": "+8 -2", "child_plan": "root" }, { "path": "tests/test_session.py", "type": "write", "size": "4.7 KB", "change": "+47 -0", "child_plan": "root" }, { "path": "src/auth/tokens.py", "type": "edit", "size": "1.8 KB", "change": "+4 -2", "child_plan": "root" }, { "path": "tests/test_tokens.py", "type": "write", "size": "3.2 KB", "change": "+32 -0", "child_plan": "auth" } ], "summary": { "total": 4, "writes": 2, "edits": 2, "deletes": 0, "total_size": "11.8 KB" }, "by_plan": { "root": 3, "auth-tests": 1, "payment-tests": "pending" } }, "timing": { "started": "2025-06-15T10:33:00Z", "duration_ms": 480 }, "messages": ["4 artifacts listed"] } ``` === "YAML" ```yaml command: plan artifacts status: ok exit_code: 0 data: artifacts: - path: src/auth/session.py type: write size: "2.1 KB" change: "+8 -2" child_plan: root - path: tests/test_session.py type: write size: "4.7 KB" change: "+47 -0" child_plan: root - path: src/auth/tokens.py type: edit size: "1.8 KB" change: "+4 -2" child_plan: root - path: tests/test_tokens.py type: write size: "3.2 KB" change: "+32 -0" child_plan: auth summary: total: 4 writes: 2 edits: 2 deletes: 0 total_size: "11.8 KB" by_plan: root: 3 auth-tests: 1 payment-tests: pending timing: started: "2025-06-15T10:33:00Z" duration_ms: 480 messages: - "4 artifacts listed" ``` ##### agents plan errors 
agents plan errors <PLAN_ID>
**Purpose** Show error decisions with recovery hints and retry history for a plan. **Arguments** - ``: Plan ID (ULID). **Examples** === "Rich" 

    $ agents plan errors 01HXM8C2ZK4Q7C2B3F2R4VYV6J

    ╭─ Plan Errors ──────────────────────────────────────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J                                  │
    │ Phase: execute                                                    │
    │ State: errored                                                    │
    │ Error: Tool execution failed: write_file permission denied         │
    │                                                                    │
    │ Error Category: tool_execution                                    │
    │ Error Phase: execute                                              │
    │ Retry Count: 2/3                                                  │
    │ Retriable: true                                                   │
    │                                                                    │
    │ Recovery Suggestions:                                             │
    │   → Check sandbox permissions and retry execution                  │
    │     $ agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J              │
    │   → Revert to Strategize phase to adjust the plan                  │
    │     $ agents plan correct --mode revert -g "..." <DECISION_ID>     │
    ╰────────────────────────────────────────────────────────────────────╯

    ✓ OK
=== "Plain" ``` $ agents plan errors 01HXM8C2ZK4Q7C2B3F2R4VYV6J Plan Errors Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Phase: execute State: errored Error: Tool execution failed: write_file permission denied Error Category: tool_execution Error Phase: execute Retry Count: 2/3 Retriable: true Recovery Suggestions → Check sandbox permissions and retry execution $ agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J → Revert to Strategize phase to adjust the plan $ agents plan correct --mode revert -g "..." [OK] ``` === "JSON" ```json { "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "phase": "execute", "state": "errored", "error_message": "Tool execution failed: write_file permission denied", "error_category": "tool_execution", "error_phase": "execute", "retry_count": 2, "max_retries": 3, "is_retriable": true, "recovery_hints": [ { "action": "retry", "message": "Check sandbox permissions and retry execution", "cli_command": "agents plan execute 01HXM8C2ZK4Q7C2B3F2R4VYV6J" }, { "action": "revert", "message": "Revert to Strategize phase to adjust the plan", "cli_command": "agents plan correct --mode revert -g \"...\" " } ] } ``` ##### agents plan prompt 
agents plan prompt <PLAN_ID> <GUIDANCE>
**Purpose** Provide additional guidance to a plan, typically when it is errored or awaiting input. **Arguments** - ``: Plan ID. - `""`: Guidance text. **Examples** === "Rich" 

    $ agents plan prompt 01HXM8C2ZK4Q7C2B3F2R4VYV6J "Use mocks for database tests"

    ╭─ Guidance Added ────────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J        │
    │ Guidance: Use mocks for database tests  │
    │ Scope: next execution step              │
    │ Phase: execute                          │
    │ State: errored → processing             │
    ╰─────────────────────────────────────────╯

    ╭─ Decision Created ────────────────────────╮
    │ Type: user_intervention                   │
    │ ID: 01HXM9C5G7R2X8S3K4Z5Q8R6Y3            │
    │ Parent: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9        │
    ╰───────────────────────────────────────────╯

    ╭─ Queue ────╮
    │ Pending: 1 │
    │ Applied: 0 │
    ╰────────────╯

    ✓ OK Guidance queued
=== "Plain" ``` $ agents plan prompt 01HXM8C2ZK4Q7C2B3F2R4VYV6J "Use mocks for database tests" Guidance Added Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Guidance: Use mocks for database tests Scope: next execution step Phase: execute State: errored -> processing Decision Created Type: user_intervention ID: 01HXM9C5G7R2X8S3K4Z5Q8R6Y3 Parent: 01HXM9A1C2Q7W3R5G8Z0P4Q1X9 Queue Pending: 1 Applied: 0 [OK] Guidance queued ``` === "JSON" ```json { "command": "plan prompt", "status": "ok", "exit_code": 0, "data": { "guidance_added": { "plan": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "guidance": "Use mocks for database tests", "scope": "next execution step", "phase": "execute", "state_transition": "errored -> processing" }, "decision_created": { "type": "user_intervention", "id": "01HXM9C5G7R2X8S3K4Z5Q8R6Y3", "parent": "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" }, "queue": { "pending": 1, "applied": 0 } }, "timing": { "started": "2025-06-15T10:35:00Z", "duration_ms": 620 }, "messages": ["Guidance queued"] } ``` === "YAML" ```yaml command: plan prompt status: ok exit_code: 0 data: guidance_added: plan: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" guidance: "Use mocks for database tests" scope: next execution step phase: execute state_transition: "errored -> processing" decision_created: type: user_intervention id: "01HXM9C5G7R2X8S3K4Z5Q8R6Y3" parent: "01HXM9A1C2Q7W3R5G8Z0P4Q1X9" queue: pending: 1 applied: 0 timing: started: "2025-06-15T10:35:00Z" duration_ms: 620 messages: - "Guidance queued" ``` ##### agents plan rollback 
agents plan rollback [--yes|-y] <PLAN_ID> <CHECKPOINT_ID>
!!! danger "Destructive Operation" Rollback a plan sandbox to a previous checkpoint. All changes made ==after== the target checkpoint are **reverted**: files are restored or removed, decisions are discarded, and tool calls are undone. Child plans spawned after the checkpoint are invalidated. **Arguments** - ``: Plan ID. - ``: Checkpoint ID. - `--yes`: Skip confirmation. **Examples** === "Rich" 

    $ agents plan rollback 01HXM8C2ZK4Q7C2B3F2R4VYV6J cp_01HXM8C2

    Rollback plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J to cp_01HXM8C2? [y/N]: y

    ╭─ Rollback Summary ───────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
    │ Checkpoint: cp_01HXM8C2          │
    │ Label: before auth refactor      │
    │ Files: 6 reverted                │
    ╰──────────────────────────────────╯

    ╭─ Changes Reverted ──────────────────╮
    │ File                    Action      │
    │ ──────────────────────  ──────────  │
    │ src/auth/session.py     restored    │
    │ src/auth/tokens.py      restored    │
    │ tests/test_session.py   removed     │
    │ tests/test_tokens.py    removed     │
    │ src/auth/fixtures.py    restored    │
    │ src/auth/__init__.py    restored        │
    ╰─────────────────────────────────────╯

    ╭─ Impact ──────────────────────────────╮
    │ Child Plans Invalidated: 2            │
    │ Sandbox: restored to cp_01HXM8C2      │
    │ Decisions After CP: 2 discarded       │
    │ Tool Calls After CP: 5 undone         │
    ╰───────────────────────────────────────╯

    ╭─ Post-Rollback State ──────────╮
    │ Phase: execute                 │
    │ State: queued (awaiting input) │
    │ Checkpoints Remaining: 2       │
    ╰────────────────────────────────╯

    ✓ OK Rollback complete
=== "Plain" ``` $ agents plan rollback 01HXM8C2ZK4Q7C2B3F2R4VYV6J cp_01HXM8C2 Rollback plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J to cp_01HXM8C2? [y/N]: y Rollback Summary Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Checkpoint: cp_01HXM8C2 Label: before auth refactor Files: 6 reverted Changes Reverted File Action ---------------------- ---------- src/auth/session.py restored src/auth/tokens.py restored tests/test_session.py removed tests/test_tokens.py removed src/auth/fixtures.py restored src/auth/__init__.py restored Impact Child Plans Invalidated: 2 Sandbox: restored to cp_01HXM8C2 Decisions After CP: 2 discarded Tool Calls After CP: 5 undone Post-Rollback State Phase: execute State: queued (awaiting input) Checkpoints Remaining: 2 [OK] Rollback complete ``` === "JSON" ```json { "command": "plan rollback", "status": "ok", "exit_code": 0, "data": { "rollback_summary": { "plan": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "checkpoint": "cp_01HXM8C2", "label": "before auth refactor", "files_reverted": 6 }, "changes_reverted": [ { "file": "src/auth/session.py", "action": "restored" }, { "file": "src/auth/tokens.py", "action": "restored" }, { "file": "tests/test_session.py", "action": "removed" }, { "file": "tests/test_tokens.py", "action": "removed" }, { "file": "src/auth/fixtures.py", "action": "restored" }, { "file": "src/auth/__init__.py", "action": "restored" } ], "impact": { "child_plans_invalidated": 2, "sandbox": "restored to cp_01HXM8C2", "decisions_after_cp": "2 discarded", "tool_calls_after_cp": "5 undone" }, "post_rollback_state": { "phase": "execute", "state": "queued (awaiting input)", "checkpoints_remaining": 2 } }, "timing": { "started": "2025-06-15T10:37:00Z", "duration_ms": 1850 }, "messages": ["Rollback complete"] } ``` === "YAML" ```yaml command: plan rollback status: ok exit_code: 0 data: rollback_summary: plan: "01HXM8C2ZK4Q7C2B3F2R4VYV6J" checkpoint: cp_01HXM8C2 label: before auth refactor files_reverted: 6 changes_reverted: - file: src/auth/session.py action: restored - file: src/auth/tokens.py action: restored - file: tests/test_session.py action: removed - file: tests/test_tokens.py action: removed - file: src/auth/fixtures.py action: restored - file: src/auth/__init__.py action: restored impact: child_plans_invalidated: 2 sandbox: "restored to cp_01HXM8C2" decisions_after_cp: "2 discarded" tool_calls_after_cp: "5 undone" post_rollback_state: phase: execute state: "queued (awaiting input)" checkpoints_remaining: 2 timing: started: "2025-06-15T10:37:00Z" duration_ms: 1850 messages: - "Rollback complete" ``` #### agents action !!! info "Purpose" Manage ==reusable actions== — named templates that define a complete unit of work including strategy actors, execution actors, definition of done, arguments, and invariants. Actions serve as the entry point to the plan lifecycle. ??? tip "Action vs Plan" An **action** is a ==template==; a **plan** is an ==instance==. When you run `agents plan use `, the action template spawns a new plan that progresses through the lifecycle phases. Actions can be reused many times (default) or configured as single-use (`reusable: false`). ##### agents action create 
agents action create --config|-c <CFG_FILE>
**Purpose** Create a new action template from a YAML configuration file. The `--config` file is required and must fully define the action. **Arguments** - `--config/-c FILE`: YAML configuration file defining the action (required). The file must fully define the action, including the `name` field, `strategy-actor`, `execution-actor`, and `definition-of-done`. **Examples** === "Rich" 

    $ agents action create --config ./actions/code-coverage.yaml

    ╭─ Action Created ────────────────────────╮
    │ Name: local/code-coverage               │
    │ State: available                        │
    │ Strategy Actor: local/strategist        │
    │ Execution Actor: local/executor         │
    │ Reusable: yes                           │
    │ Read Only: no                           │
    │ Config: ./actions/code-coverage.yaml    │
    │ Created: 2026-02-08 12:20               │
    ╰─────────────────────────────────────────╯

    ╭─ Definition of Done ─╮
    │ Coverage reaches 85% │
    ╰──────────────────────╯

    ╭─ Arguments ──────────────────────────────────────────────────────╮
    │ Name                     Type    Required  Description           │
    │ ───────────────────────  ──────  ────────  ───────────────────── │
    │ target_coverage_percent  int     yes       Target coverage %     │
    │ test_command             string  no        Test framework to use │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Automation ──────────────────────────╮
    │ Profile: supervised                   │
    │ Source: default                       │
    ╰───────────────────────────────────────╯

    ✓ OK Action created
=== "Plain" ``` $ agents action create --config ./actions/code-coverage.yaml Action Created Name: local/code-coverage State: available Strategy Actor: local/strategist Execution Actor: local/executor Reusable: yes Read Only: no Config: ./actions/code-coverage.yaml Created: 2026-02-08 12:20 Definition of Done Coverage reaches 85% Arguments Name Type Required Description ----------------------- ------ -------- --------------------- target_coverage_percent int yes Target coverage % test_command string no Test framework to use Automation Profile: supervised Source: default [OK] Action created ``` === "JSON" ```json { "command": "action create", "status": "ok", "exit_code": 0, "data": { "name": "local/code-coverage", "state": "available", "strategy_actor": "local/strategist", "execution_actor": "local/executor", "reusable": true, "read_only": false, "config": "./actions/code-coverage.yaml", "created": "2026-02-08T12:20:00Z", "definition_of_done": "Coverage reaches 85%", "arguments": [ { "name": "target_coverage_percent", "type": "int", "required": true, "description": "Target coverage %" }, { "name": "test_command", "type": "string", "required": false, "description": "Test framework to use" } ], "automation": { "profile": "supervised", "source": "default" } }, "timing": { "started": "2026-02-08T12:20:00Z", "duration_ms": 110 }, "messages": ["Action created"] } ``` === "YAML" ```yaml command: action create status: ok exit_code: 0 data: name: local/code-coverage state: available strategy_actor: local/strategist execution_actor: local/executor reusable: true read_only: false config: "./actions/code-coverage.yaml" created: "2026-02-08T12:20:00Z" definition_of_done: "Coverage reaches 85%" arguments: - name: target_coverage_percent type: int required: true description: "Target coverage %" - name: test_command type: string required: false description: "Test framework to use" automation: profile: supervised source: default timing: started: "2026-02-08T12:20:00Z" duration_ms: 110 messages: - "Action created" ``` ##### agents action list 
agents action list [(--namespace|-n) <NS>] [(--state|-s) <STATE>] [<REGEX>]
**Purpose** List actions with optional filters. **Arguments** - `--namespace/-n NS`: Filter by namespace. - `--state/-s STATE`: Filter by state. **Examples** === "Rich" 

    $ agents action list

    ╭─ Actions ──────────────────────────────────────────────────────────────────────────────────╮
    │ Name                 State      Strategy Actor    Execution Actor  Reusable  Plans         │
    │ ───────────────────  ─────────  ────────────────  ───────────────  ────────  ─────         │
    │ local/code-coverage  available  local/strategist  local/executor   ✓         3             │
    ╰────────────────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Filters ────────╮
    │ State: available │
    │ Namespace: (any) │
    ╰──────────────────╯

    ╭─ Summary ──────────────╮
    │ Total: 1               │
    │ Available: 1           │
    │ Archived: 0            │
    │ Total Plans Created: 3 │
    ╰────────────────────────╯

    ✓ OK 1 action listed
=== "Plain" ``` $ agents action list Actions Name State Strategy Actor Execution Actor Reusable Plans ------------------- --------- ---------------- --------------- -------- ----- local/code-coverage available local/strategist local/executor yes 3 Filters State: available Namespace: (any) Summary Total: 1 Available: 1 Archived: 0 Total Plans Created: 3 [OK] 1 action listed ``` === "JSON" ```json { "command": "action list", "status": "ok", "exit_code": 0, "data": { "actions": [ { "name": "local/code-coverage", "state": "available", "strategy_actor": "local/strategist", "execution_actor": "local/executor", "reusable": true, "plans": 3 } ], "filters": { "state": "available", "namespace": null }, "summary": { "total": 1, "available": 1, "archived": 0, "total_plans_created": 3 } }, "timing": { "started": "2026-02-08T12:21:00Z", "duration_ms": 45 }, "messages": ["1 action listed"] } ``` === "YAML" ```yaml command: action list status: ok exit_code: 0 data: actions: - name: local/code-coverage state: available strategy_actor: local/strategist execution_actor: local/executor reusable: true plans: 3 filters: state: available namespace: null summary: total: 1 available: 1 archived: 0 total_plans_created: 3 timing: started: "2026-02-08T12:21:00Z" duration_ms: 45 messages: - "1 action listed" ``` ##### agents action show 
agents action show <ACTION_NAME>
**Purpose** Show details for an action. **Arguments** - ``: Action name. **Examples** === "Rich" 

    $ agents action show local/code-coverage

    ╭─ Action Details ──────────────────────╮
    │ Name: local/code-coverage             │
    │ State: available                      │
    │ Strategy Actor: local/strategist      │
    │ Execution Actor: local/executor       │
    │ Reusable: yes                         │
    │ Read Only: no                         │
    │ Created: 2026-02-08 12:20             │
    ╰───────────────────────────────────────╯

    ╭─ Definition of Done ─╮
    │ Coverage reaches 85% │
    ╰──────────────────────╯

    ╭─ Arguments ──────────────────────────────────────────────────────╮
    │ Name                     Type    Required  Description           │
    │ ───────────────────────  ──────  ────────  ───────────────────── │
    │ target_coverage_percent  int     yes       Target coverage %     │
    │ test_command             string  no        Test framework to use │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Automation ──────────────────────────╮
    │ Profile: supervised                   │
    │ Source: default                       │
    ╰───────────────────────────────────────╯

    ╭─ History ────────────────────╮
    │ Plans Created: 3             │
    │ Plans Completed: 2           │
    │ Plans Failed: 0              │
    │ Avg Duration: 00:04:30       │
    │ Avg Cost: $0.072             │
    ╰──────────────────────────────╯

    ╭─ Usage ───────────────────────────────────────────────────────────╮
    │ - agents plan use local/code-coverage local/api-service           │
    │     --arg target_coverage_percent=85                              │
    ╰───────────────────────────────────────────────────────────────────╯

    ✓ OK Action loaded
=== "Plain" ``` $ agents action show local/code-coverage Action Details Name: local/code-coverage State: available Strategy Actor: local/strategist Execution Actor: local/executor Reusable: yes Read Only: no Created: 2026-02-08 12:20 Definition of Done Coverage reaches 85% Arguments Name Type Required Description ----------------------- ------ -------- --------------------- target_coverage_percent int yes Target coverage % test_command string no Test framework to use Automation Profile: supervised Source: default History Plans Created: 3 Plans Completed: 2 Plans Failed: 0 Avg Duration: 00:04:30 Avg Cost: $0.072 Usage agents plan use local/code-coverage local/api-service --arg target_coverage_percent=85 [OK] Action loaded ``` === "JSON" ```json { "command": "action show", "status": "ok", "exit_code": 0, "data": { "name": "local/code-coverage", "state": "available", "strategy_actor": "local/strategist", "execution_actor": "local/executor", "reusable": true, "read_only": false, "created": "2026-02-08T12:20:00Z", "definition_of_done": "Coverage reaches 85%", "arguments": [ { "name": "target_coverage_percent", "type": "int", "required": true, "description": "Target coverage %" }, { "name": "test_command", "type": "string", "required": false, "description": "Test framework to use" } ], "automation": { "profile": "supervised", "source": "default" }, "history": { "plans_created": 3, "plans_completed": 2, "plans_failed": 0, "avg_duration": "00:04:30", "avg_cost": "$0.072" } }, "timing": { "started": "2026-02-08T12:21:00Z", "duration_ms": 60 }, "messages": ["Action loaded"] } ``` === "YAML" ```yaml command: action show status: ok exit_code: 0 data: name: local/code-coverage state: available strategy_actor: local/strategist execution_actor: local/executor reusable: true read_only: false created: "2026-02-08T12:20:00Z" definition_of_done: "Coverage reaches 85%" arguments: - name: target_coverage_percent type: int required: true description: "Target coverage %" - name: test_command type: string required: false description: "Test framework to use" automation: profile: supervised source: default history: plans_created: 3 plans_completed: 2 plans_failed: 0 avg_duration: "00:04:30" avg_cost: "$0.072" timing: started: "2026-02-08T12:21:00Z" duration_ms: 60 messages: - "Action loaded" ``` ##### agents action archive 
agents action archive <ACTION_NAME>
**Purpose** Archive an action. **Arguments** - ``: Action name. **Examples** === "Rich" 

    $ agents action archive local/old-action

    ╭─ Action Archived ───────────╮
    │ Name: local/old-action      │
    │ State: available → archived │
    │ Archived: 2026-02-08 12:22  │
    ╰─────────────────────────────╯

    ╭─ Impact ───────────────────────╮
    │ Availability: hidden from list │
    │ Existing Plans: unchanged      │
    │ Active Plans: 0 affected       │
    ╰────────────────────────────────╯

    ╭─ History ─────────────────╮
    │ Total Plans: 5            │
    │ Completed: 4              │
    │ Failed: 1                 │
    │ Last Used: 2026-02-06     │
    ╰───────────────────────────╯

    ✓ OK Action archived
=== "Plain" ``` $ agents action archive local/old-action Action Archived Name: local/old-action State: available -> archived Archived: 2026-02-08 12:22 Impact Availability: hidden from list Existing Plans: unchanged Active Plans: 0 affected History Total Plans: 5 Completed: 4 Failed: 1 Last Used: 2026-02-06 [OK] Action archived ``` === "JSON" ```json { "command": "action archive", "status": "ok", "exit_code": 0, "data": { "name": "local/old-action", "state_transition": "available -> archived", "archived": "2026-02-08T12:22:00Z", "impact": { "availability": "hidden from list", "existing_plans": "unchanged", "active_plans_affected": 0 }, "history": { "total_plans": 5, "completed": 4, "failed": 1, "last_used": "2026-02-06" } }, "timing": { "started": "2026-02-08T12:22:00Z", "duration_ms": 55 }, "messages": ["Action archived"] } ``` === "YAML" ```yaml command: action archive status: ok exit_code: 0 data: name: local/old-action state_transition: "available -> archived" archived: "2026-02-08T12:22:00Z" impact: availability: hidden from list existing_plans: unchanged active_plans_affected: 0 history: total_plans: 5 completed: 4 failed: 1 last_used: "2026-02-06" timing: started: "2026-02-08T12:22:00Z" duration_ms: 55 messages: - "Action archived" ``` #### agents automation-profile !!! info "Purpose" Manage ==automation profiles== — named collections of confidence thresholds (floating-point values from `0.0` to `1.0`) that control which tasks are automated vs. require human approval. Each threshold specifies the minimum confidence level at which the system proceeds automatically; below the threshold, the system drops to manual mode. !!! tip "Threshold Scale" | Value | Meaning | | :---: | :------ | | `0.0` | ==Always automatic== — no human approval needed | | `0.5` | Automatic when confidence ≥ 50% | | `1.0` | ==Always manual== — always requires human approval | ??? example "Built-in Profiles" The following profiles are always available and cannot be removed: | Profile | Description | | :------ | :---------- | | `manual` | All thresholds at `1.0` — everything requires approval | | `review` | Automatic strategize and execute, manual apply | | `supervised` | Automatic strategize, manual execute and apply | | `cautious` | Most operations automatic, manual for risky decisions | | `trusted` | Nearly fully automatic, manual only for apply | | `auto` | Fully automatic except apply | | `ci` | Optimized for CI/CD pipelines | | `full-auto` | All thresholds at `0.0` — fully autonomous | Custom profiles follow the same `/` naming convention as other entities. ##### agents automation-profile add 
agents automation-profile add --config|-c <FILE> [--update]
**Purpose** Register a new custom automation profile from a YAML configuration file. The profile is fully defined by the config file. If a profile with the same name already exists, the command fails unless the `--update` flag is provided. **Arguments** - `--config/-c FILE`: YAML configuration file defining the profile (required). The file must fully define the profile, including the `name` field which determines the profile's registered name. - `--update`: Replace an existing profile with the same name. **Examples** === "Rich" 

    $ agents automation-profile add --config ./profiles/careful-auto.yaml

    ╭─ Profile Registered ─────────────────────────────────────────────╮
    │ Name: local/careful-auto                                         │
    │ Description: Autonomous execution with mandatory sandbox         │
    │              and manual apply                                    │
    │ Created: 2026-02-08 14:30                                        │
    ╰──────────────────────────────────────────────────────────────────╯

    ╭─ Confidence Thresholds ────────────────╮
    │ decompose_task: 0.0                   │
    │ create_tool: 0.0                      │
    │ select_tool: 1.0                        │
    │ edit_code: 0.0         │
    │ execute_command: 0.0            │
    │ create_file: 0.0               │
    │ delete_content: 1.0            │
    │ access_network: 1.0         │
    │ install_dependency: 0.0                  │
    │ modify_config: 0.0              │
    │ approve_plan: 0.0           │
    │ require_sandbox: true                  │
    │ require_checkpoints: true              │
    │ allow_unsafe_tools: false              │
    ╰────────────────────────────────────────╯

    ✓ OK Profile registered
=== "Plain" ``` $ agents automation-profile add --config ./profiles/careful-auto.yaml Profile Registered Name: local/careful-auto Description: Autonomous execution with mandatory sandbox and manual apply Created: 2026-02-08 14:30 Confidence Thresholds decompose_task: 0.0 create_tool: 0.0 select_tool: 1.0 edit_code: 0.0 execute_command: 0.0 create_file: 0.0 delete_content: 1.0 access_network: 1.0 install_dependency: 0.0 modify_config: 0.0 approve_plan: 0.0 require_sandbox: true require_checkpoints: true allow_unsafe_tools: false [OK] Profile registered ``` === "JSON" ```json { "command": "automation-profile add", "status": "ok", "exit_code": 0, "data": { "name": "local/careful-auto", "description": "Autonomous execution with mandatory sandbox and manual apply", "created": "2026-02-08T14:30:00Z", "thresholds": { "decompose_task": 0.0, "create_tool": 0.0, "select_tool": 1.0, "edit_code": 0.0, "execute_command": 0.0, "create_file": 0.0, "delete_content": 1.0, "access_network": 1.0, "install_dependency": 0.0, "modify_config": 0.0, "approve_plan": 0.0 }, "flags": { "require_sandbox": true, "require_checkpoints": true, "allow_unsafe_tools": false } }, "timing": { "started": "2026-02-08T14:30:00Z", "duration_ms": 70 }, "messages": ["Profile registered"] } ``` === "YAML" ```yaml command: automation-profile add status: ok exit_code: 0 data: name: local/careful-auto description: "Autonomous execution with mandatory sandbox and manual apply" created: "2026-02-08T14:30:00Z" thresholds: decompose_task: 0.0 create_tool: 0.0 select_tool: 1.0 edit_code: 0.0 execute_command: 0.0 create_file: 0.0 delete_content: 1.0 access_network: 1.0 install_dependency: 0.0 modify_config: 0.0 approve_plan: 0.0 flags: require_sandbox: true require_checkpoints: true allow_unsafe_tools: false timing: started: "2026-02-08T14:30:00Z" duration_ms: 70 messages: - "Profile registered" ``` ##### agents automation-profile remove 
agents automation-profile remove [--yes|-y] <NAME>
!!! warning "Destructive Operation" Remove a custom automation profile. ==Built-in profiles cannot be removed.== Plans and projects currently referencing this profile will fall back to their inherited or global default profile. **Arguments** - ``: Profile name. - `--yes, -y`: Skip confirmation prompt. **Examples** === "Rich" 

    $ agents automation-profile remove local/careful-auto

    Remove automation profile local/careful-auto? [y/N]: y

    ╭─ Profile Removed ──────────╮
    │ Name: local/careful-auto   │
    ╰────────────────────────────╯

    ✓ OK Profile removed
=== "Plain" ``` $ agents automation-profile remove local/careful-auto Remove automation profile local/careful-auto? [y/N]: y Profile Removed Name: local/careful-auto [OK] Profile removed ``` === "JSON" ```json { "command": "automation-profile remove", "status": "ok", "exit_code": 0, "data": { "name": "local/careful-auto" }, "timing": { "started": "2026-02-08T14:31:00Z", "duration_ms": 40 }, "messages": ["Profile removed"] } ``` === "YAML" ```yaml command: automation-profile remove status: ok exit_code: 0 data: name: local/careful-auto timing: started: "2026-02-08T14:31:00Z" duration_ms: 40 messages: - "Profile removed" ``` ##### agents automation-profile list 
agents automation-profile list [<REGEX>]
**Purpose** List all available automation profiles (built-in and custom). **Arguments** - `[REGEX]`: Optional filter pattern. **Examples** === "Rich" 

    $ agents automation-profile list

    ╭─ Automation Profiles ──────────────────────────────────────────────────────────╮
    │ Name                Source    Auto-Apply  Sandbox  Description                 │
    │ ──────────────────  ────────  ──────────  ───────  ────────────────────────    │
    │ manual             built-in  1.0         yes      Human-driven (default)       │
    │ review             built-in  1.0         yes      Auto-phase, manual decisions │
    │ supervised         built-in  1.0         yes      Auto-plan, manual exec       │
    │ cautious           built-in  1.0         yes      Confidence-gated automation  │
    │ trusted            built-in  1.0         yes      Auto-exec, manual apply      │
    │ auto               built-in  1.0         yes      Full auto except apply       │
    │ ci                 built-in  0.0         yes      Full auto, safe CI/CD        │
    │ full-auto          built-in  0.0         no       Complete automation          │
    │ local/careful-auto custom    0.8         yes      Custom careful profile       │
    ╰────────────────────────────────────────────────────────────────────────────────╯

    ╭─ Summary ───────────╮
    │ Built-in: 8         │
    │ Custom: 1           │
    │ Total: 9            │
    ╰─────────────────────╯

    ✓ OK 9 profiles listed
=== "Plain" ``` $ agents automation-profile list Automation Profiles Name Source Auto-Apply Sandbox Description ------------------ -------- ---------- ------- ---------------------------- manual built-in 1.0 yes Human-driven (default) review built-in 1.0 yes Auto-phase, manual decisions supervised built-in 1.0 yes Auto-plan, manual exec cautious built-in 1.0 yes Confidence-gated automation trusted built-in 1.0 yes Auto-exec, manual apply auto built-in 1.0 yes Full auto except apply ci built-in 0.0 yes Full auto, safe CI/CD full-auto built-in 0.0 no Complete automation local/careful-auto custom 0.8 yes Custom careful profile Summary Built-in: 8 Custom: 1 Total: 9 [OK] 9 profiles listed ``` === "JSON" ```json { "command": "automation-profile list", "status": "ok", "exit_code": 0, "data": { "profiles": [ { "name": "manual", "source": "built-in", "select_tool": 1.0, "sandbox": true, "description": "Human-driven (default)" }, { "name": "review", "source": "built-in", "select_tool": 1.0, "sandbox": true, "description": "Auto-phase, manual decisions" }, { "name": "supervised", "source": "built-in", "select_tool": 1.0, "sandbox": true, "description": "Auto-plan, manual exec" }, { "name": "cautious", "source": "built-in", "select_tool": 1.0, "sandbox": true, "description": "Confidence-gated automation" }, { "name": "trusted", "source": "built-in", "select_tool": 1.0, "sandbox": true, "description": "Auto-exec, manual apply" }, { "name": "auto", "source": "built-in", "select_tool": 1.0, "sandbox": true, "description": "Full auto except apply" }, { "name": "ci", "source": "built-in", "select_tool": 0.0, "sandbox": true, "description": "Full auto, safe CI/CD" }, { "name": "full-auto", "source": "built-in", "select_tool": 0.0, "sandbox": false, "description": "Complete automation" }, { "name": "local/careful-auto", "source": "custom", "select_tool": 0.8, "sandbox": true, "description": "Custom careful profile" } ], "summary": { "built_in": 8, "custom": 1, "total": 9 } }, "timing": { "started": "2026-02-08T14:31:00Z", "duration_ms": 50 }, "messages": ["9 profiles listed"] } ``` === "YAML" ```yaml command: automation-profile list status: ok exit_code: 0 data: profiles: - name: manual source: built-in select_tool: 1.0 sandbox: true description: "Human-driven (default)" - name: review source: built-in select_tool: 1.0 sandbox: true description: "Auto-phase, manual decisions" - name: supervised source: built-in select_tool: 1.0 sandbox: true description: "Auto-plan, manual exec" - name: cautious source: built-in select_tool: 1.0 sandbox: true description: "Confidence-gated automation" - name: trusted source: built-in select_tool: 1.0 sandbox: true description: "Auto-exec, manual apply" - name: auto source: built-in select_tool: 1.0 sandbox: true description: "Full auto except apply" - name: ci source: built-in select_tool: 0.0 sandbox: true description: "Full auto, safe CI/CD" - name: full-auto source: built-in select_tool: 0.0 sandbox: false description: "Complete automation" - name: local/careful-auto source: custom select_tool: 0.8 sandbox: true description: "Custom careful profile" summary: built_in: 8 custom: 1 total: 9 timing: started: "2026-02-08T14:31:00Z" duration_ms: 50 messages: - "9 profiles listed" ``` ##### agents automation-profile show 
agents automation-profile show <NAME>
**Purpose** Show full details for an automation profile, including all flag values. **Arguments** - ``: Profile name. **Examples** === "Rich" 

    $ agents automation-profile show trusted

    ╭─ Automation Profile ───────────────────────────────────────────╮
    │ Name: trusted                                                  │
    │ Source: built-in                                               │
    │ Description: Auto-exec, manual apply. Day-to-day development   │
    ╰────────────────────────────────────────────────────────────────╯

    ╭─ Phase Transitions (thresholds) ─────╮
    │ decompose_task: 0.0                 │
    │ create_tool: 0.0                    │
    │ select_tool: 1.0                      │
    ╰──────────────────────────────────────╯

    ╭─ Decision Automation (thresholds) ───╮
    │ edit_code: 0.0       │
    │ execute_command: 0.0          │
    ╰──────────────────────────────────────╯

    ╭─ Self-Repair (thresholds) ───────────╮
    │ create_file: 0.0             │
    │ delete_content: 1.0          │
    │ access_network: 1.0         │
    │ modify_config: 0.0            │
    │ approve_plan: 1.0         │
    ╰──────────────────────────────────────╯

    ╭─ Execution Controls (thresholds) ────╮
    │ install_dependency: 0.0                │
    │ require_sandbox: true                │
    │ require_checkpoints: true            │
    │ allow_unsafe_tools: false            │
    ╰──────────────────────────────────────╯

    ✓ OK Profile loaded
=== "Plain" ``` $ agents automation-profile show trusted Automation Profile Name: trusted Source: built-in Description: Auto-exec, manual apply. Day-to-day development Phase Transitions (thresholds) decompose_task: 0.0 create_tool: 0.0 select_tool: 1.0 Decision Automation (thresholds) edit_code: 0.0 execute_command: 0.0 Self-Repair (thresholds) create_file: 0.0 delete_content: 1.0 access_network: 1.0 modify_config: 0.0 approve_plan: 1.0 Execution Controls (thresholds) install_dependency: 0.0 require_sandbox: true require_checkpoints: true allow_unsafe_tools: false [OK] Profile loaded ``` === "JSON" ```json { "command": "automation-profile show", "status": "ok", "exit_code": 0, "data": { "name": "trusted", "source": "built-in", "description": "Auto-exec, manual apply. Day-to-day development", "phase_transitions": { "decompose_task": 0.0, "create_tool": 0.0, "select_tool": 1.0 }, "decision_automation": { "edit_code": 0.0, "execute_command": 0.0 }, "self_repair": { "create_file": 0.0, "delete_content": 1.0, "access_network": 1.0, "modify_config": 0.0, "approve_plan": 1.0 }, "execution_controls": { "install_dependency": 0.0, "require_sandbox": true, "require_checkpoints": true, "allow_unsafe_tools": false } }, "timing": { "started": "2026-02-08T14:31:00Z", "duration_ms": 55 }, "messages": ["Profile loaded"] } ``` === "YAML" ```yaml command: automation-profile show status: ok exit_code: 0 data: name: trusted source: built-in description: "Auto-exec, manual apply. Day-to-day development" phase_transitions: decompose_task: 0.0 create_tool: 0.0 select_tool: 1.0 decision_automation: edit_code: 0.0 execute_command: 0.0 self_repair: create_file: 0.0 delete_content: 1.0 access_network: 1.0 modify_config: 0.0 approve_plan: 1.0 execution_controls: install_dependency: 0.0 require_sandbox: true require_checkpoints: true allow_unsafe_tools: false timing: started: "2026-02-08T14:31:00Z" duration_ms: 55 messages: - "Profile loaded" ``` #### agents config !!! info "Purpose" Manage ==global configuration values== that control system-wide defaults. Configuration keys use hierarchical dot-path notation (e.g., `core.automation-profile`, `core.log.level`). ??? tip "Key Configuration Categories" | Category | Example Keys | Description | | :------- | :----------- | :---------- | | **Core** | `core.automation-profile`, `core.format`, `core.log.level` | System-wide defaults | | **Actor** | `actor.default.invariant` | Default actor assignments | | **Output** | `core.format` | Default rendering format (`rich`, `json`, `yaml`, etc.) | ##### agents config set 
agents config set <key> <value>
**Purpose** Set a configuration key. **Arguments** - ``: Hierarchical dot-path key name (e.g., `core.automation-profile`, `core.log.level`, `actor.default.invariant`, `core.format`). See **Global Configuration Keys** for the complete reference. - ``: Value to set. The `actor.default.invariant` key sets the default Invariant Reconciliation Actor used globally. This actor is used to reconcile invariant conflicts when neither the plan nor the project specifies one. The `core.format` key sets the default output rendering format used by all commands. Accepted values are `rich`, `color`, `table`, `plain`, `json`, `yaml`. When set, this value is used unless overridden by the `--format` CLI flag. See **Output Rendering Framework** for details. **Examples** === "Rich" 

    $ agents config set core.automation-profile trusted

    ╭─ Config Updated ──────────────────────╮
    │ Key: core.automation-profile          │
    │ Value: trusted                        │
    │ Previous: manual                      │
    │ Source: config                        │
    │ Scope: global                         │
    ╰───────────────────────────────────────╯

    ╭─ Effective ────────────────────────╮
    │ Sessions: new sessions             │
    │ Plans: future plans (unless set)   │
    │ Existing: unchanged                │
    ╰────────────────────────────────────╯

    ╭─ Saved To ──────────────────────────╮
    │ File: ~/.cleveragents/config.toml   │
    │ Line: 8                             │
    ╰─────────────────────────────────────╯

    ✓ OK Config updated
=== "Plain" ``` $ agents config set core.automation-profile trusted Config Updated Key: core.automation-profile Value: trusted Previous: manual Source: config Scope: global Effective Sessions: new sessions Plans: future plans (unless set) Existing: unchanged Saved To File: ~/.cleveragents/config.toml Line: 8 [OK] Config updated ``` === "JSON" ```json { "command": "config set", "status": "ok", "exit_code": 0, "data": { "key": "core.automation-profile", "value": "trusted", "previous": "manual", "source": "config", "scope": "global", "effective": { "sessions": "new sessions", "plans": "future plans (unless set)", "existing": "unchanged" }, "saved_to": { "file": "~/.cleveragents/config.toml", "line": 8 } }, "timing": { "started": "2026-02-08T14:32:00Z", "duration_ms": 30 }, "messages": ["Config updated"] } ``` === "YAML" ```yaml command: config set status: ok exit_code: 0 data: key: core.automation-profile value: trusted previous: manual source: config scope: global effective: sessions: new sessions plans: "future plans (unless set)" existing: unchanged saved_to: file: "~/.cleveragents/config.toml" line: 8 timing: started: "2026-02-08T14:32:00Z" duration_ms: 30 messages: - "Config updated" ``` Setting the default output format: === "Rich" 

    $ agents config set core.format table

    ╭─ Config Updated ─────────────────╮
    │ Key: core.format                 │
    │ Previous: rich                   │
    │ New Value: table                 │
    │ Scope: user (~/.cleveragents)    │
    ╰──────────────────────────────────╯

    ✓ OK Set core.format = table
=== "Plain" ``` $ agents config set core.format table Config Updated Key: core.format Previous: rich New Value: table Scope: user (~/.cleveragents) [OK] Set core.format = table ``` === "JSON" ```json { "command": "config set", "status": "ok", "exit_code": 0, "data": { "key": "core.format", "previous": "rich", "value": "table", "scope": "user (~/.cleveragents)" }, "timing": { "started": "2026-02-08T14:32:00Z", "duration_ms": 25 }, "messages": ["Set core.format = table"] } ``` === "YAML" ```yaml command: config set status: ok exit_code: 0 data: key: core.format previous: rich value: table scope: "user (~/.cleveragents)" timing: started: "2026-02-08T14:32:00Z" duration_ms: 25 messages: - "Set core.format = table" ``` Setting a global invariant actor: === "Rich" 

    $ agents config set actor.default.invariant local/invariant-resolver

    ╭─ Config Updated ──────────────────────────────────╮
    │ Key: actor.default.invariant                      │
    │ Previous: (not set)                               │
    │ New Value: local/invariant-resolver               │
    │ Scope: user (~/.cleveragents)                     │
    ╰───────────────────────────────────────────────────╯

    ✓ OK Set actor.default.invariant = local/invariant-resolver
=== "Plain" ``` $ agents config set actor.default.invariant local/invariant-resolver Config Updated Key: actor.default.invariant Previous: (not set) New Value: local/invariant-resolver Scope: user (~/.cleveragents) [OK] Set actor.default.invariant = local/invariant-resolver ``` === "JSON" ```json { "command": "config set", "status": "ok", "exit_code": 0, "data": { "key": "actor.default.invariant", "previous": null, "value": "local/invariant-resolver", "scope": "user (~/.cleveragents)" }, "timing": { "started": "2026-02-08T14:32:00Z", "duration_ms": 28 }, "messages": ["Set actor.default.invariant = local/invariant-resolver"] } ``` === "YAML" ```yaml command: config set status: ok exit_code: 0 data: key: actor.default.invariant previous: null value: local/invariant-resolver scope: "user (~/.cleveragents)" timing: started: "2026-02-08T14:32:00Z" duration_ms: 28 messages: - "Set actor.default.invariant = local/invariant-resolver" ``` ##### agents config get 
agents config get <key>
**Purpose** Get a configuration value. **Arguments** - ``: Key to read. **Examples** === "Rich" 

    $ agents config get core.automation-profile

    ╭─ Config ──────────────────────────╮
    │ Key: core.automation-profile      │
    │ Value: trusted                    │
    │ Source: config                    │
    │ Overridden: no                    │
    │ Type: string                      │
    ╰───────────────────────────────────╯

    ╭─ Origin ──────────────────────────╮
    │ File: ~/.cleveragents/config.toml │
    │ Line: 8                           │
    │ Default: supervised               │
    ╰───────────────────────────────────╯

    ╭─ Resolution Chain ──────────────╮
    │ 1. CLI flag: (not set)          │
    │ 2. Env var: (not set)           │
    │ 3. Config file: trusted         │
    │ 4. Default: supervised          │
    │ Winner: config file (level 3)   │
    ╰─────────────────────────────────╯

    ✓ OK Config read
=== "Plain" ``` $ agents config get core.automation-profile Config Key: core.automation-profile Value: trusted Source: config Overridden: no Type: string Origin File: ~/.cleveragents/config.toml Line: 8 Default: supervised Resolution Chain 1. CLI flag: (not set) 2. Env var: (not set) 3. Config file: trusted 4. Default: supervised Winner: config file (level 3) [OK] Config read ``` === "JSON" ```json { "command": "config get", "status": "ok", "exit_code": 0, "data": { "key": "core.automation-profile", "value": "trusted", "source": "config", "overridden": false, "type": "string", "origin": { "file": "~/.cleveragents/config.toml", "line": 8, "default": "supervised" }, "resolution_chain": [ { "level": 1, "source": "CLI flag", "value": null }, { "level": 2, "source": "Env var", "value": null }, { "level": 3, "source": "Config file", "value": "trusted" }, { "level": 4, "source": "Default", "value": "supervised" } ], "winner": { "source": "config file", "level": 3 } }, "timing": { "started": "2026-02-08T14:33:00Z", "duration_ms": 20 }, "messages": ["Config read"] } ``` === "YAML" ```yaml command: config get status: ok exit_code: 0 data: key: core.automation-profile value: trusted source: config overridden: false type: string origin: file: "~/.cleveragents/config.toml" line: 8 default: supervised resolution_chain: - level: 1 source: "CLI flag" value: null - level: 2 source: "Env var" value: null - level: 3 source: "Config file" value: trusted - level: 4 source: Default value: supervised winner: source: "config file" level: 3 timing: started: "2026-02-08T14:33:00Z" duration_ms: 20 messages: - "Config read" ``` ##### agents config list 
agents config list [--filter-values <REGEX>] [<REGEX>]
**Purpose** List all configuration values. **Arguments** None. **Examples** === "Rich" 

    $ agents config list

    ╭─ Config ───────────────────────────────────────────────────╮
    │ Key               Value               Source   Modified    │
    │ ────────────────  ──────────────────  ───────  ────────    │
    │ core.automation-profile  trusted             config   yes  │
    │ actor.default.invariant local/reconciler    config   yes   │
    │ core.log.level          FATAL               default  no    │
    ╰────────────────────────────────────────────────────────────╯

    ╭─ Overrides ─────╮
    │ Env: none       │
    │ CLI Flags: none │
    ╰─────────────────╯

    ╭─ Config File ───────────────────────╮
    │ Path: ~/.cleveragents/config.toml   │
    │ Size: 284 bytes                     │
    │ Valid: yes                          │
    ╰─────────────────────────────────────╯

    ✓ OK 6 settings listed
=== "Plain" ``` $ agents config list Config Key Value Source Modified ----------------------- ------------------ ------- -------- core.automation-profile trusted config yes actor.default.invariant local/reconciler config yes core.log.level FATAL default no Overrides Env: none CLI Flags: none Config File Path: ~/.cleveragents/config.toml Size: 284 bytes Valid: yes [OK] 6 settings listed ``` === "JSON" ```json { "command": "config list", "status": "ok", "exit_code": 0, "data": { "settings": [ { "key": "core.automation-profile", "value": "trusted", "source": "config", "modified": true }, { "key": "actor.default.invariant", "value": "local/reconciler", "source": "config", "modified": true }, { "key": "core.log.level", "value": "FATAL", "source": "default", "modified": false } ], "overrides": { "env": null, "cli_flags": null }, "config_file": { "path": "~/.cleveragents/config.toml", "size_bytes": 284, "valid": true } }, "timing": { "started": "2026-02-08T14:33:00Z", "duration_ms": 25 }, "messages": ["6 settings listed"] } ``` === "YAML" ```yaml command: config list status: ok exit_code: 0 data: settings: - key: core.automation-profile value: trusted source: config modified: true - key: actor.default.invariant value: local/reconciler source: config modified: true - key: core.log.level value: FATAL source: default modified: false overrides: env: null cli_flags: null config_file: path: "~/.cleveragents/config.toml" size_bytes: 284 valid: true timing: started: "2026-02-08T14:33:00Z" duration_ms: 25 messages: - "6 settings listed" ``` #### agents invariant !!! info "Purpose" Manage ==invariants== — named constraints that guide and constrain plan execution. Invariants can be attached to any scope: global (all plans), project (all plans targeting that project), plan (a specific plan and its child plans), or action (carried forward when the action is used). !!! warning "Scope Requirements" Exactly ==one scope flag== is required for `add` and `list`. The available scopes are: | Scope | Flag | Applies To | | :---- | :--- | :--------- | | **Global** | `--global` | All plans across all projects | | **Project** | `--project ` | All plans targeting that project | | **Plan** | `--plan ` | A specific plan and its child plans | | **Action** | `--action ` | Carried forward when the action is used | When multiple scopes apply to a plan, the ==union== of all applicable invariants is enforced. ##### agents invariant add 
agents invariant add [--global] [(--project|-p) PROJECT] [--plan PLAN_ID]...
                     [--action ACTION]... <INVARIANT_TEXT>
**Purpose** Add an invariant at the specified scope. **Arguments** - ``: The invariant text (positional argument at end of command). - `--global`: Attach as a global invariant (applies to all plans). - `--project/-p PROJECT`: Attach to a project (applies to all plans targeting this project). - `--plan PLAN_ID`: Attach to a plan (plan-level invariant). Repeatable. - `--action ACTION`: Attach to an action (action-level invariant). Repeatable. At least one scope flag (`--global`, `--project`, `--plan`, or `--action`) must be provided. `--plan` and `--action` can be repeated to attach the same invariant to multiple plans or actions. **Examples** === "Rich" 

    $ agents invariant add --global "All public APIs must maintain backward compatibility"

    ╭─ Invariant Added ──────────────────────────────────────────────────────╮
    │ Invariant: All public APIs must maintain backward compatibility        │
    │ Scope: global                                                          │
    │ ID: inv_01HXM9A1B                                                      │
    ╰────────────────────────────────────────────────────────────────────────╯

    ✓ OK Invariant added

    $ agents invariant add --project local/api-service "All endpoints must validate auth tokens"

    ╭─ Invariant Added ──────────────────────────────────────────────╮
    │ Project: local/api-service                                     │
    │ Invariant: All endpoints must validate auth tokens             │
    │ Scope: project                                                 │
    │ ID: inv_01HXM9A2C                                              │
    ╰────────────────────────────────────────────────────────────────╯

    ✓ OK Invariant added

    $ agents invariant add --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J "All database queries must use parameterized statements"

    ╭─ Invariant Added ─────────────────────────────────────────────────────╮
    │ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J                                      │
    │ Invariant: All database queries must use parameterized statements     │
    │ Scope: plan                                                           │
    │ ID: inv_01HXM9G3A                                                     │
    ╰───────────────────────────────────────────────────────────────────────╯

    ✓ OK Invariant added

    $ agents invariant add --action local/code-coverage "Test files must not import production secrets"

    ╭─ Invariant Added ──────────────────────────────────────────────────────╮
    │ Action: local/code-coverage                                            │
    │ Invariant: Test files must not import production secrets               │
    │ Scope: action                                                          │
    │ ID: inv_01HXM9H4B                                                      │
    ╰────────────────────────────────────────────────────────────────────────╯

    ✓ OK Invariant added
=== "Plain" ``` $ agents invariant add --global "All public APIs must maintain backward compatibility" Invariant Added Invariant: All public APIs must maintain backward compatibility Scope: global ID: inv_01HXM9A1B [OK] Invariant added $ agents invariant add --project local/api-service "All endpoints must validate auth tokens" Invariant Added Project: local/api-service Invariant: All endpoints must validate auth tokens Scope: project ID: inv_01HXM9A2C [OK] Invariant added $ agents invariant add --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J "All database queries must use parameterized statements" Invariant Added Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J Invariant: All database queries must use parameterized statements Scope: plan ID: inv_01HXM9G3A [OK] Invariant added $ agents invariant add --action local/code-coverage "Test files must not import production secrets" Invariant Added Action: local/code-coverage Invariant: Test files must not import production secrets Scope: action ID: inv_01HXM9H4B [OK] Invariant added ``` === "JSON" ```json { "command": "invariant add", "status": "ok", "exit_code": 0, "data": [ { "invariant": "All public APIs must maintain backward compatibility", "scope": "global", "id": "inv_01HXM9A1B" }, { "project": "local/api-service", "invariant": "All endpoints must validate auth tokens", "scope": "project", "id": "inv_01HXM9A2C" }, { "plan": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "invariant": "All database queries must use parameterized statements", "scope": "plan", "id": "inv_01HXM9G3A" }, { "action": "local/code-coverage", "invariant": "Test files must not import production secrets", "scope": "action", "id": "inv_01HXM9H4B" } ], "timing": { "started": "2026-02-08T14:35:00Z", "duration_ms": 45 }, "messages": ["Invariant added"] } ``` === "YAML" ```yaml command: invariant add status: ok exit_code: 0 data: - invariant: "All public APIs must maintain backward compatibility" scope: global id: inv_01HXM9A1B - project: local/api-service invariant: "All endpoints must validate auth tokens" scope: project id: inv_01HXM9A2C - plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J invariant: "All database queries must use parameterized statements" scope: plan id: inv_01HXM9G3A - action: local/code-coverage invariant: "Test files must not import production secrets" scope: action id: inv_01HXM9H4B timing: started: "2026-02-08T14:35:00Z" duration_ms: 45 messages: - "Invariant added" ``` ##### agents invariant list 
agents invariant list [--global] [(--project|-p) PROJECT] [--plan PLAN_ID] [--action ACTION]
                     [--effective] [<REGEX>]
**Purpose** List invariants at a given scope. Use `--effective` with `--plan` to show the final reconciled view of invariants (after precedence resolution) rather than just the invariants directly attached at that scope. **Arguments** - `--global`: List global invariants. - `--project/-p PROJECT`: List invariants attached to a project. - `--plan PLAN_ID`: List invariants attached to a plan. - `--action ACTION`: List invariants attached to an action. - `--effective`: (Only with `--plan`) Show the reconciled invariant view after precedence resolution across all scopes. **Examples** === "Rich" 

    $ agents invariant list --global

    ╭─ Global Invariants ──────────────────────────────────────────────────────╮
    │ ID              Text                                                     │
    │ ──────────────  ────────────────────────────────────────────────────     │
    │ inv_01HXM9A1B  All public APIs must maintain backward compatibility      │
    │ inv_01HXM9A1C  Payment processing must be idempotent                     │
    ╰──────────────────────────────────────────────────────────────────────────╯

    ✓ OK 2 invariants

    $ agents invariant list --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J --effective

    ╭─ Effective Invariants (Plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J) ──────────────────────────────────╮
    │ ID              Source   Text                                                             │
    │ ──────────────  ───────  ──────────────────────────────────────────────────────           │
    │ inv_01HXM9A1B  global   All public APIs must maintain backward compatibility              │
    │ inv_01HXM9A2C  project  All endpoints must validate auth tokens                           │
    │ inv_01HXM9G3A  plan     All database queries must use parameterized statements            │
    ╰───────────────────────────────────────────────────────────────────────────────────────────╯

    │ Conflicts Resolved: 1                                                              │
    │   Global "Use shared DB pool" overridden by plan "All database queries must use    │
    │   parameterized statements"                                                        │

    ✓ OK 3 effective invariants (1 global, 1 project, 1 plan; 1 conflict resolved)
=== "Plain" ``` $ agents invariant list --global Global Invariants ID Text -------------- -------------------------------------------------------- inv_01HXM9A1B All public APIs must maintain backward compatibility inv_01HXM9A1C Payment processing must be idempotent [OK] 2 invariants $ agents invariant list --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J --effective Effective Invariants (Plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J) ID Source Text -------------- ------- -------------------------------------------------- inv_01HXM9A1B global All public APIs must maintain backward compatibility inv_01HXM9A2C project All endpoints must validate auth tokens inv_01HXM9G3A plan All database queries must use parameterized statements Conflicts Resolved: 1 Global "Use shared DB pool" overridden by plan "All database queries must use parameterized statements" [OK] 3 effective invariants (1 global, 1 project, 1 plan; 1 conflict resolved) ``` === "JSON" ```json { "command": "invariant list", "status": "ok", "exit_code": 0, "data": { "scope": "plan", "plan_id": "01HXM8C2ZK4Q7C2B3F2R4VYV6J", "effective": true, "invariants": [ { "id": "inv_01HXM9A1B", "source": "global", "text": "All public APIs must maintain backward compatibility" }, { "id": "inv_01HXM9A2C", "source": "project", "text": "All endpoints must validate auth tokens" }, { "id": "inv_01HXM9G3A", "source": "plan", "text": "All database queries must use parameterized statements" } ], "conflicts_resolved": [ { "overridden": { "source": "global", "text": "Use shared DB pool" }, "by": { "source": "plan", "text": "All database queries must use parameterized statements" } } ] }, "timing": { "started": "2026-02-08T14:35:00Z", "duration_ms": 35 }, "messages": ["3 effective invariants (1 global, 1 project, 1 plan; 1 conflict resolved)"] } ``` === "YAML" ```yaml command: invariant list status: ok exit_code: 0 data: scope: plan plan_id: 01HXM8C2ZK4Q7C2B3F2R4VYV6J effective: true invariants: - id: inv_01HXM9A1B source: global text: "All public APIs must maintain backward compatibility" - id: inv_01HXM9A2C source: project text: "All endpoints must validate auth tokens" - id: inv_01HXM9G3A source: plan text: "All database queries must use parameterized statements" conflicts_resolved: - overridden: source: global text: "Use shared DB pool" by: source: plan text: "All database queries must use parameterized statements" timing: started: "2026-02-08T14:35:00Z" duration_ms: 35 messages: - "3 effective invariants (1 global, 1 project, 1 plan; 1 conflict resolved)" ``` ##### agents invariant remove 
agents invariant remove [--yes|-y] <INVARIANT_ID>
!!! warning "Constraint Removal" Remove an invariant by ID. The invariant is removed from whichever scope it was originally attached to. ==Active plans== that have already incorporated this invariant into their decision trees are not retroactively affected, but future plans will no longer enforce this constraint. **Arguments** - ``: Invariant ID to remove. - `--yes`: Skip confirmation. **Examples** === "Rich" 

    $ agents invariant remove inv_01HXM9A1C

    Remove invariant inv_01HXM9A1C ("Payment processing must be idempotent", scope: global)? [y/N]: y

    ╭─ Invariant Removed ──────────────────────────────────────────────╮
    │ Removed: Payment processing must be idempotent                   │
    │ Scope: global                                                    │
    │ ID: inv_01HXM9A1C                                                │
    ╰──────────────────────────────────────────────────────────────────╯

    ✓ OK Invariant removed
=== "Plain" ``` $ agents invariant remove inv_01HXM9A1C Remove invariant inv_01HXM9A1C ("Payment processing must be idempotent", scope: global)? [y/N]: y Invariant Removed Removed: Payment processing must be idempotent Scope: global ID: inv_01HXM9A1C [OK] Invariant removed ``` === "JSON" ```json { "command": "invariant remove", "status": "ok", "exit_code": 0, "data": { "removed": "Payment processing must be idempotent", "scope": "global", "id": "inv_01HXM9A1C" }, "timing": { "started": "2026-02-08T14:36:00Z", "duration_ms": 30 }, "messages": ["Invariant removed"] } ``` === "YAML" ```yaml command: invariant remove status: ok exit_code: 0 data: removed: "Payment processing must be idempotent" scope: global id: inv_01HXM9A1C timing: started: "2026-02-08T14:36:00Z" duration_ms: 30 messages: - "Invariant removed" ``` ## Core Concepts ### Plan !!! adr "Architecture Decision" The plan lifecycle, phase transitions, and plan hierarchy are defined in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md). A **plan** is the fundamental unit of orchestration and traceability. #### Plan Lifecycle Phases A plan progresses through four phases: **Action → Strategize → Execute → Apply** In this spec: * **Action** is the first phase. An action serves as a reusable plan template — it defines the work to be done (description, definition of done, actors, arguments, invariants) without being bound to any project. No significant processing occurs during the Action phase. When an action is used (via `agents plan use`), it spawns a new plan entity that enters the Strategize phase. By default, the original action remains available for reuse; single-use actions (created with `reusable: false`) are deleted after first use. Although Action is formally a phase in the lifecycle, it is unique in that it functions primarily as a template from which plans are instantiated. * **Strategize** is the second phase and the first where active processing occurs (the output is a **strategy**). * **Execute** is the third phase (the output is a **changeset**). * **Apply** is the fourth and final phase. Apply merges the sandbox changeset into real project resources. Upon completion, the plan reaches one of several terminal states: `applied` (success — changes committed), `constrained` (cannot complete within the current strategy's constraints — may trigger reversion to Strategize), `errored` (failed), or `cancelled`. The normal phase progression is forward, but both Execute and Apply may revert to Strategize when the current strategy's constraints are too restrictive (see *Phase Reversion* below). #### Phase Transition Verbs (CLI / UX Contract) Verbs that trigger phase transitions. CleverAgents should standardize these verbs as the **public API** (CLI, TUI, web): | Current Phase | Command Verb | Next Phase | | ------------- | ------------ | ---------- | | (none) | `create` | Action | | Action | `use` | Strategize | | Strategize | `execute` | Execute | | Execute | `apply` | Apply | !!! note "Important behavioral rules" * CleverAgents uses **automation profiles** to control which of these phase transitions happen automatically. The profile determines whether each transition requires explicit user action or proceeds autonomously, but the verbs remain the conceptual contract. * **There is no `strategize` command.** The phase transition verbs are used in CLI commands — not the phase names. The `use` verb (as in `agents plan use`) is the command that transitions a plan from the Action phase into Strategize. This is by design: ==`use` describes the user's intent== (using an action template on a project), and the system responds by entering the Strategize phase. #### Phase Reversion (→ Strategize) !!! adr "Architecture Decision" Phase reversion rules and the decision tree model are detailed in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md) and [ADR-007: Decision Tree and Correction](adr/ADR-007-decision-tree-and-correction.md). While the normal phase progression is forward (Action → Strategize → Execute → Apply), both the Execute and Apply phases may **revert to Strategize** under specific conditions. In all cases, the reversion target is always Strategize — there is no reversion to Execute or any other intermediate phase. ##### Execute → Strategize * **Trigger:** During execution, the execution actor discovers that constraints established during Strategize are too restrictive to complete the work. For example, a strategy decision may have mandated an approach that proves infeasible once actual resources are examined, dependencies are resolved, or implementation details are encountered. * **Behavior:** Rather than overriding or silently violating Strategize-phase decisions, the plan reverts to the Strategize phase so the strategy actor can adjust the decision tree. Execute-phase decisions must always be constrained by Strategize-phase decisions — if those constraints cannot be honored, the correct response is reversion, not violation. * **After reversion:** The strategy actor receives the execution actor's findings (the reason for reversion, the specific constraints that were too restrictive) and produces an updated decision tree. The plan then re-enters the Execute phase with the revised strategy. * **Automation:** Controlled by the `delete_content` automation profile flag. ##### Apply → Strategize * **Trigger:** During the Apply phase, the system determines that the changeset cannot be successfully applied within the current strategy's constraints. Examples include: merge conflicts that violate invariants, validation failures at apply time that cannot be resolved within the strategy's scope, or resource state drift that contradicts strategy assumptions. * **Behavior:** The plan enters the `constrained` terminal state within the Apply phase. From this state, the plan may revert to Strategize either automatically (if the `access_network` automation profile flag allows it) or after manual user approval. * **After reversion:** The strategy actor receives the Apply phase's findings (the constraint violations, the specific issues encountered) and produces an updated decision tree. The plan then progresses forward again through Execute and Apply with the revised strategy. * **Automation:** Controlled by the `access_network` automation profile flag (separate from `delete_content`, which governs Execute → Strategize reversion). #### Plan States (Per Phase) A plan's ==phase== indicates "what step of the lifecycle it is in." Separately, the plan has a ==processing state== indicating "what is happening right now." === "Action Phase" | State | Description | | :---- | :---------- | | `available` | Action exists and can be used | | `archived` | Soft-deleted or hidden (optional) | === "Strategize / Execute Phases" | State | Terminal? | Description | | :---- | :-------: | :---------- | | `queued` | No | Waiting for compute/worker | | `processing` | No | Currently running | | `errored` | Yes | Failed; includes error metadata | | `complete` | Yes | Finished successfully | | `cancelled` | Yes | User/system cancelled; safe terminal | === "Apply Phase" | State | Terminal? | Description | | :---- | :-------: | :---------- | | `queued` | No | Waiting for compute/worker | | `processing` | No | Currently running — diff review, conflict resolution, validation | | `errored` | Yes | Failed; includes error metadata | | `applied` | Yes | ==Changes successfully committed== to real resources | | `constrained` | Yes | Cannot complete within current strategy's constraints; may trigger reversion to Strategize | | `cancelled` | Yes | User/system cancelled; safe terminal | #### Plan Identity and Traceability Every plan should have: | Field | Type | Description | | :---- | :--- | :---------- | | `plan_id` | ULID | ==Unique, immutable== identifier | | `parent_plan_id` | ULID? | Nullable; present for child plans | | `root_plan_id` | ULID | The top-most plan in the tree | | `attempt` | Integer | Attempt counter (increments on phase re-run) | | `created_at` | Timestamp | When the plan was created | | `updated_at` | Timestamp | Last modification time | | `completed_at` | Timestamp? | When the plan reached a terminal state | | `created_by` | Identity | User or session identity | #### Plan Hierarchy and Parallelism !!! adr "Architecture Decision" Plan hierarchy, child plan spawning, and parallel execution are covered in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md). A single plan should usually represent the smallest "complete" unit of work (similar to what would fit in one git commit). However: * **Plans are hierarchical.** A child plan is simply a Plan with a parent — it follows the same lifecycle, has the same data model, and is functionally identical to a root plan except that it has a `parent_plan_id`. * **Decisions about child plans are made during Strategize** (as `subplan_spawn` decision types). Multiple child plans that should execute concurrently are grouped under a `subplan_parallel_spawn` decision. * **Child plans are actually spawned during Execute** (based on those decisions). * Child plans can run **in parallel** (via `subplan_parallel_spawn`) or **sequentially** (via individual `subplan_spawn` decisions). Without a `subplan_parallel_spawn` wrapper, each `subplan_spawn` decision results in sequential execution. * **Applicable invariants are enforced** during Strategize by adding `invariant_enforced` decisions to the tree, which constrain downstream decisions and child plans. * The parent plan is responsible for **merging results**. This is core to the long-term objective: tackling large tasks while only recomputing parts of the decision tree when corrected. ##### Hierarchical Decomposition for Scale ??? example "Example: Converting Firefox to Rust" When handling massive tasks, the system uses hierarchical decomposition. Each level spawns child plans (which are themselves full Plans with their own decision trees): **1. Root Plan** — High-level architectural decisions and invariants : - "Convert Firefox Renderer to Rust" - Invariant: "Maintain API compatibility with existing C++ callers" - Decision: "Start with leaf modules, work inward" - Context: Module dependency graph (2,847 modules) **2. Subsystem-Level Plans** — Major component decisions (`subplan_parallel_spawn`) : - "Phase 1: Convert utility libraries (no external deps)" - Each subsystem plan gets its own bounded context and inherits parent invariants **3. Module-Level Plans** — Individual module conversions : - "Convert string_utils module" - Context: Only the 47 functions and 12 dependent files - Decision: "Use Rust's String type" **4. File-Level Plans** — Specific file changes : - Actual code transformations - Minimal context needed !!! tip At each level, only the ==relevant context== is loaded. The persistent decision graph means we can always reconstruct why we're converting a particular module and what constraints apply from higher-level decisions. ##### Child Plan Spawning Mechanism In the actor definition for the execution actor, tool nodes can directly invoke registered tools to trigger child plans. The `local/create-subplan` tool is independently registered and referenced by name in the actor graph node. During execution, `subplan_spawn` decisions are realized as actual child plans, and `subplan_parallel_spawn` groups trigger concurrent spawning of all enclosed child plans. 

# Example: Execution actor with subplan spawning capability.
# The graph uses a tool node referencing a named registered tool.
actors:
  code_executor:
    type: graph
    config:
      actor: anthropic/claude-3-opus
    skills:
      - local/plan-tools          # Skill containing create_subplan for LLM tool-calling
      - local/file-ops
    routes:
      execute_workflow:
        nodes:
          - name: spawn_test_subplan
            type: tool
            tool: local/create-subplan # Named tool from Tool Registry
The `local/create-subplan` tool is independently registered via its own YAML configuration file: 

# File: tools/create-subplan.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/create-subplan
  description: "Spawn a subplan for a given action"
  source: custom

  input_schema:
    type: object
    properties:
      action: { type: string }
      target_files: { type: array, items: { type: string } }
    required: [action]

  capability:
    writes: true
    checkpointable: false
    side_effects: [spawn_subplan]

  code: |
    subplan = ctx.spawn_subplan(
        action=params["action"],
        target_files=params.get("target_files", [])
    )
    return {"subplan_id": subplan.id}
The `local/plan-tools` skill references this tool (and others) by name: 

# File: skills/plan-tools.yaml
skill:
  name: local/plan-tools
  description: "Tools for spawning and managing subplans"
  tools:
    - local/create-subplan
##### Child Plan Execution Modes === "Sequential" Individual `subplan_spawn` decisions without a `subplan_parallel_spawn` wrapper execute one after another. If one fails, subsequent child plans are ==not started==. === "Parallel" Multiple `subplan_spawn` decisions grouped under a `subplan_parallel_spawn` decision execute ==concurrently==. If one fails, others can continue. The `subplan_parallel_spawn` decision acts as a container that signals the system to spawn all enclosed child plans simultaneously. Parallel execution is bounded by `SubplanConfig.max_parallel` (default: `5`, range: 1–50). This cap prevents runaway resource consumption when a large number of child plans are spawned simultaneously. The runtime uses a `ThreadPoolExecutor` with `min(max_parallel, len(subplans))` workers. The `SubplanConfig` model also controls `merge_strategy` (default: `git_three_way`), `fail_fast` (default: `false`), `timeout_per_subplan_seconds` (default: `null`), `retry_failed` (default: `true`), and `max_retries` (default: `2`). === "Dependency-Ordered" When child plans have explicit dependencies on each other, the `DEPENDENCY_ORDERED` execution mode respects those dependencies while maximizing concurrency. The dependency graph is provided as a `dependency_graph: dict[str, list[str]]` mapping each `subplan_id` to the list of `subplan_ids` it depends on. The runtime performs a topological sort to determine execution order, then executes independent subplans (those whose dependencies are all satisfied) concurrently in "waves". Subsequent waves wait for the previous wave to complete. Circular dependencies are detected and raise a `ValueError`. This mode is useful when child plans produce artifacts that other child plans consume — for example, a code generation plan that must complete before a test plan can run. ##### Child Plan Failure Handling !!! note "Failure Semantics" | Execution Mode | On Failure | Behavior | | :------------- | :--------- | :------- | | **Parallel** | One child fails | Other child plans ==continue== | | **Sequential** | One child fails | Subsequent child plans ==not started== | | **Dependency-Ordered** | One child fails | Dependent child plans ==not started==; independent plans ==continue== | !!! tip An "error" only occurs if an exception is thrown by the application (a bug). Plan failures (e.g., tests don't pass) are handled within the plan's logic, not as application errors. ##### Child Plan Result Merging The way child plan results are merged depends on the resource type: * **Git-compatible resources** (source code, text files): Git-style merge * **Databases**: Transaction coordination or sequential application * **Other resources**: Pluggable merge strategies based on resource type * **Non-mergeable resources**: May require sequential execution only ##### Selective Subtree Recomputation for Decision Correction When a decision in the decomposition tree is found to be incorrect, the system supports **selective subtree recomputation**: only the subtree rooted at the target node is re-evaluated, while sibling branches and ancestor nodes are preserved unchanged. This is implemented by `DecompositionService.recompute_subtree()`, which: 1. Accepts a `node_id` identifying the root of the subtree to recompute and an `existing_result` (`DecompositionResult`) containing the current tree. 2. Performs a breadth-first search over `children_ids` to collect all nodes in the subtree (the target node and all its descendants). 3. Partitions the nodes into two groups: - **Recomputed nodes** — the target node and all its descendants. - **Preserved nodes** — all other nodes (siblings, ancestors, and unrelated branches). 4. Returns a `DecisionCorrectionResult` with both groups, the configuration used, and diagnostic metrics (`recomputed_count`, `preserved_count`, `subtree_size`). **Acceptance criteria:** | # | Criterion | Behaviour | | :- | :-------- | :-------- | | 1 | Leaf recomputation | Only the target leaf is recomputed; all other nodes preserved | | 2 | Middle-node recomputation | Target node and all its descendants recomputed; ancestors and siblings preserved | | 3 | Root recomputation | All nodes recomputed; no nodes preserved | | 4 | Unknown node | `ValueError` raised when `node_id` is not found in the result | | 5 | Custom config | Caller-supplied `DecompositionConfig` is attached to the result | | 6 | Metrics | `recomputed_count`, `preserved_count`, and `subtree_size` always present | #### The Plan "Decision Tree" and Visualization !!! adr "Architecture Decision" The decision tree's dual structure (structural tree and influence DAG), versioning model, and historical reconstruction are defined in [ADR-034: Decision Tree Versioning and History](adr/ADR-034-decision-tree-versioning-and-history.md). CleverAgents records enough information to render: * an **ASCII tree** in the TUI, and * optionally a GUI tree via visualization tools (D3/Cytoscape) once the data exists. This implies each plan should persist: * decisions made, * the rationale (or at least the prompt/context snapshot that produced it), * dependencies ("this decision influenced these child plans"). This is required for "correcting plans" (see Behavior section). ##### Dual Structure: Structural Tree and Influence DAG A plan's decisions form two overlapping structures that serve different purposes: **Structural Tree** (`parent_decision_id`): Defines the hierarchical rendering order. Each decision has at most one parent. The `prompt_definition` decision is the root. This tree determines how `agents plan tree` renders the hierarchy. **Influence DAG** (`decision_dependencies` table): Captures which decisions constrained or influenced which other decisions. A single decision may be influenced by multiple upstream decisions. For example, an `implementation_choice` might be influenced by both a `strategy_choice` (which set the approach) and a `resource_selection` (which determined the files to modify). | Structure | Storage | Purpose | Used For | |---|---|---|---| | Structural tree | `parent_decision_id` column | Rendering, navigation, tree visualization | `agents plan tree`, `agents plan explain` | | Influence DAG | `decision_dependencies` table | Dependency tracking, impact analysis | `agents plan correct` (affected subtree computation) | A decision's parent in the structural tree may differ from its dependencies in the influence DAG. The tree answers "what is this decision nested under?"; the DAG answers "what decisions caused this one to exist?" ##### Current Tree vs. Superseded Branches The **current tree** for a plan is the set of active, non-superseded decisions: 

SELECT * FROM decisions
WHERE plan_id = :plan_id
  AND superseded_by IS NULL
ORDER BY sequence_number;
When a decision is corrected, the original and all its descendants are marked `superseded_by = `. **Superseded decisions are never deleted** — they remain in the database as permanent records, forming an append-only history. `agents plan tree --show-superseded` renders both current and historical branches, with superseded decisions displayed dimmed and annotated. ##### Structural Invariants The current tree always satisfies: 1. **Single root**: Exactly one `prompt_definition` decision with `parent_decision_id IS NULL`. 2. **Reachability**: Every non-root decision is reachable from the root via `parent_decision_id` links. 3. **Acyclicity**: No circular references in `parent_decision_id` chains. 4. **Monotonic ordering**: `sequence_number` is monotonically increasing per plan. New decisions (including corrections) always receive higher sequence numbers than existing ones. Gaps in the current tree's sequence numbers indicate where superseded decisions once existed. #### Decision Data Model !!! adr "Architecture Decision" The decision data model, decision types, and decision tree semantics are defined in [ADR-007: Decision Tree and Correction](adr/ADR-007-decision-tree-and-correction.md). ##### Relationship Between Plan Description and Decisions Each plan has a **description field** (inherited from the action's description, potentially with argument substitutions). This description acts as the **primary component of the prompt** fed to the strategy actor during the Strategize phase. **Decisions are choices that are NOT explicitly defined by the plan description.** They represent the gaps, ambiguities, or implementation details that must be resolved to execute the plan. For example: - **Plan description**: "Increase test coverage to 85%" - **Decisions that emerge**: - "Which modules should be prioritized?" (not specified in description) - "Should we use mocks or integration tests for the database layer?" (not specified) - "Should we refactor the auth module to make it more testable, or write tests around it as-is?" (not specified) ##### Decision Making Based on Autonomy Level Who makes decisions depends on the plan's **automation profile**: | Profile Flag | Who Makes Decisions | |-------------|---------------------| | `edit_code = 1.0` (always manual) | User is prompted for each decision point during Strategize | | `edit_code = 0.0` (always automatic) | Strategy actor makes decisions autonomously, records reasoning | | `execute_command = 1.0` (always manual) | User is prompted for each decision point during Execute | | `execute_command = 0.0` (always automatic) | Execution actor makes decisions autonomously | Intermediate thresholds (e.g., `edit_code = 0.7`) cause the system to auto-decide only when the Semantic Escalation confidence score meets or exceeds the threshold; otherwise the user is prompted. When **automation allows automatic decisions**, the strategy actor uses its best judgment based on context, and records its reasoning in the decision's `rationale` field. When **user input is required**, the system pauses and prompts the user: 

Decision required: Which modules should be prioritized for test coverage?

Options identified by the strategy actor:
  1. auth module (currently 45% coverage, high risk)
  2. payment module (currently 52% coverage, high risk)  
  3. user module (currently 71% coverage, medium risk)

Your choice (or provide custom guidance): _
##### The Prompt as the Root Decision **The prompt passed to the strategize actor is itself a decision node** in the decision tree—specifically, it's the **root decision** of type `prompt_definition`. This is important because: 1. **Every plan has its own prompt**: The root plan's prompt comes from the action description + user arguments. Child plan prompts are created by parent plans during their execution. 2. **Parent plans create child plan prompts**: When a parent plan spawns a child plan, it decides what prompt to give that child plan. This is recorded as a `prompt_definition` decision in the parent's tree, and becomes the root decision of the child plan's tree. 3. **Invariants flow into the decision tree**: During Strategize, applicable invariants (from global, project, action, and plan scopes) are reconciled via the **Invariant Reconciliation Actor** and recorded as `invariant_enforced` decisions, making them explicit constraints that influence downstream decisions and child plans. 4. **Unified correction mechanism**: Since the prompt, invariants, and all other decisions are part of the same tree, correcting any of them uses the same `agents plan correct` command. 

Plan: 01KH29QDEE6DZTXKWNKCV8VP0F
├── [prompt_definition] "Increase test coverage to 85% for the whole project."
├── [invariant_enforced] "Prioritize all functionality related to financial transactions and user management"
├── [invariant_enforced] "All API calls over TCP must be mocked"
├── [strategy_choice] "Prioritize auth and payment modules, implement them in parallel before the rest"
├── [subplan_parallel_spawn] "Implement auth and payment modules, in parallel"
│   ├── [subplan_spawn] "Write tests for auth module"
│   │   └── Plan: 01KH29R8WPKPBHRY7Q0NA9XW86
│   │       ├── [prompt_definition] "Write unit tests for auth module using mocks for the remote API calls"
│   │       ├── [implementation_choice] "Test login flow first"
│   │       └── ...
│   └── [subplan_spawn] "Write tests for payment module"
│       └── Plan: 01KH29RN2YKSXMTBDG82AKRHRA
│           ├── [prompt_definition] "Write unit tests for payment module using"
│           └── ...
└── [subplan_parallel_spawn] "Write tests for all modules except the auth and payment modules"
    └──  ...
##### Correcting Decisions (Including Prompts) All corrections use the same unified command: 

agents plan correct <decision_id> --mode=<mode> --guidance "<corrected decision text>"
**Parameters:** * ``: The ULID of the decision to correct * `--mode`: Either `revert` (rollback and re-run) or `append` (add fix at end) * `--guidance`: Free-form text specifying what the correct decision should be **Examples:** 

# Correct a strategy choice
agents plan correct 01ARZ3NDEKTSV4RRFFQ69G5FAV --mode=revert \
  --guidance "Prioritize the payment module first, not auth, due to upcoming deadline"

# Correct the root prompt to be more specific
agents plan tree <plan_id>
# Shows: [prompt_definition] id=01ARZ3NDEKTSV4RRFFQ69G5FAV "Increase test coverage to 85%"

agents plan correct 01ARZ3NDEKTSV4RRFFQ69G5FAV --mode=revert \
  --guidance "Increase test coverage to 85%, prioritizing auth and payment modules. Use mocks for database tests, not integration tests."

# Correct a subplan's prompt (originally created by parent plan)
agents plan correct 01BRZ4PDFLUTW5SSGR70H6GBW --mode=revert \
  --guidance "Write unit tests for auth module, focusing on edge cases for token expiration"

# Append a fix rather than rewriting history
agents plan correct 01ARZ3NDEKTSV4RRFFQ69G5FAV --mode=append \
  --guidance "The previous approach missed error handling tests - add comprehensive error path coverage"

# Remove an invariant that shouldn't apply
agents plan correct 01CRZ5QEHMVUX6TTHR81I7HCX --mode=revert \
  --guidance "Remove this invariant - TCP mocking is not needed for this module since it has no network calls"

# Add a missing invariant to the plan
agents invariant add --plan 01HXM8C2ZK4Q7C2B3F2R4VYV6J "All database queries must use parameterized statements"
**Note:** CLI commands should not require interactive input. The `--guidance` parameter provides the correction inline. **When to correct the prompt vs. a specific decision:** | Situation | Correction Approach | |-----------|---------------------| | Original request was too vague | Correct the `prompt_definition` decision | | Strategy actor made a bad choice on a specific question | Correct that specific decision | | Parent plan gave a child plan a bad prompt | Correct the child plan's `prompt_definition` | | An invariant should not apply to this plan | Correct (remove) the `invariant_enforced` decision | | A missing constraint should be added | Add a new `invariant_enforced` decision via `agents invariant add --plan` or correct the plan's strategy | | Sequential child plans should run in parallel | Correct the relevant decisions to use a `subplan_parallel_spawn` grouping | Because the prompt is part of the decision tree, the system automatically knows that correcting it invalidates all downstream decisions in that plan (and its child plans). **Decisions are created during both the Strategize and Execute phases.** The Strategize phase produces the initial decision tree — strategy choices, invariant enforcement, resource selections, and child plan blueprints. The Execute phase may create additional decisions constrained by those made during Strategize, reflecting discoveries and adjustments that arise during execution. If Execute finds that Strategize-phase constraints are too restrictive to proceed, the plan reverts to Strategize for adjustment (see *Phase Reversion* below). The decision tree captures what choices were made and why, enabling correction and replay. ##### Decision Recording Protocol !!! adr "Architecture Decision" The decision recording protocol, tool-based recording mechanism, and context snapshot capture are defined in [ADR-033: Decision Recording Protocol](adr/ADR-033-decision-recording-protocol.md). Decision-aligned checkpointing during Execute is defined in [ADR-035: Decision Tree Rollback and Replay](adr/ADR-035-decision-tree-rollback-and-replay.md). Actors record decisions by calling a **built-in `record_decision` tool**. This tool is automatically included in every actor's skill set for plan-related invocations. Decision types are partitioned into three creation categories: | Category | Decision Types | Creator | Mechanism | |---|---|---|---| | **System-created** | `prompt_definition`, `user_intervention` | Plan lifecycle engine | Created automatically at plan instantiation (prompt) and when user provides guidance (intervention) | | **Reconciliation-actor-recorded** | `invariant_enforced` | Invariant Reconciliation Actor | The actor evaluates applicable invariants, resolves conflicts using precedence rules, and calls `record_decision` for each enforced invariant | | **Actor-recorded** | `strategy_choice`, `resource_selection`, `subplan_spawn`, `subplan_parallel_spawn`, `implementation_choice`, `tool_invocation`, `error_recovery`, `validation_response` | Strategy or Execution actor | Actor identifies a choice point and calls `record_decision` | The `record_decision` tool accepts the decision type, question, chosen option, alternatives considered, confidence score, and rationale. The system automatically captures the **context snapshot** at the moment of the call — the hot context hash, resource references, and a LangGraph checkpoint of the actor's complete state (`actor_state_ref`). This snapshot enables replay from the exact decision point during correction. **Strategize-phase recording loop**: The strategy actor's system prompt instructs it to identify ambiguities and choice points in the plan description. For each choice point, the actor gathers context, evaluates options, and calls `record_decision`. Each recorded decision becomes part of the actor's context for subsequent reasoning. 

# Pseudocode: Strategy actor decision recording loop
while unresolved_ambiguities_remain(plan, context):
    choice_point = analyze_context_for_ambiguity(context)
    options = generate_and_evaluate_options(choice_point, context, invariants)

    # Record via tool call — system auto-captures context snapshot
    decision_id = record_decision(
        decision_type = choice_point.type,
        question = choice_point.question,
        chosen_option = best_option.description,
        alternatives_considered = [o.description for o in rejected_options],
        confidence_score = best_option.confidence,
        rationale = best_option.reasoning
    )

    context.add_decision(decision_id)  # Decision informs subsequent reasoning
**Execute-phase recording pattern**: The execution actor sees Strategize-phase decisions as read-only constraints. When it encounters a choice point not already resolved by the strategy (implementation detail, error handling, tool selection), it calls `record_decision`. Execute-phase decisions must be consistent with Strategize-phase constraints — if they cannot be, the plan reverts to Strategize rather than recording a contradictory decision. !!! warning "Execute-Phase Checkpoint Trigger" In the Execute phase, `record_decision` is treated as a **write operation** for checkpoint purposes. The system automatically creates a **coordinated checkpoint group** — one checkpoint per modified sandbox resource — at every Execute-phase decision point. This creates a 1:1 mapping between decisions and resource states, enabling fine-grained rollback to any Execute-phase decision (see *Correcting Plans* in the Behavior section). **Automation profile integration**: When `record_decision` is called, the system checks the confidence score against the applicable threshold (`edit_code` or `execute_command`). If confidence is below the threshold, execution pauses and the decision is presented to the user for approval or override. ##### Decision Record Structure 

Decision:
  # Identity
  decision_id: ULID # Unique identifier
  plan_id: ULID # Parent plan this decision belongs to
  parent_decision_id: ULID | null # Parent decision (for tree structure)
  sequence_number: int # Order within the plan's decisions

  # Classification
  decision_type: enum
    - prompt_definition         # The prompt/description for this plan (root decision)
    - invariant_enforced        # An invariant (from global, project, action, or plan scope) applicable to this plan, added as a constraint
    - strategy_choice           # High-level approach decision during Strategize
    - implementation_choice     # How to implement a specific task
    - resource_selection        # Which resources to read/modify
    - subplan_spawn             # Decision to create a child plan (spawned later in Execute)
    - subplan_parallel_spawn    # Decision to spawn a group of child plans in parallel (contains subplan_spawn children)
    - tool_invocation           # Which skill/tool to use
    - error_recovery            # How to handle a failure
    - validation_response       # Response to validation failure
    - user_intervention         # User provided guidance/correction

  # The Decision Itself
  question: str # What question was being answered
  chosen_option: str # What was decided
  alternatives_considered: list[str] # Other options that were evaluated
  confidence_score: float | null # 0.0-1.0 if the actor provided confidence

  # Context Snapshot (for replay)
  context_snapshot:
    hot_context_hash: str # Cryptographic hash of the exact context
    hot_context_ref: str # Pointer to the full stored snapshot
    relevant_resources: list[ResourceRef] # Every file/symbol that influenced this decision
    actor_state_ref: str # Complete LangGraph checkpoint

  # When the system decides "refactor the authentication module to use async patterns," 
  # it permanently records:
  # - Which files were examined to make that decision
  # - What symbols and dependencies were traced
  # - The exact code state that was analyzed
  # - The reasoning chain that led to this choice
  # - Alternative approaches that were considered but rejected

  # Rationale
  rationale: str # Why this option was chosen
  actor_reasoning: str | null # Raw LLM reasoning if available

  # Downstream Impact (populated during Execute phase)
  downstream_decision_ids: list[ULID] # Decisions that depend on this one
  downstream_plan_ids: list[ULID] # Child plans spawned because of this decision
  artifacts_produced: list[ArtifactRef] # Files/outputs created under this decision

  # Timestamps
  created_at: datetime

  # Correction Metadata
  is_correction: bool # Was this decision a correction of another?
  corrects_decision_id: ULID | null # If correction, which decision was replaced
  correction_reason: str | null # Why the correction was made
  superseded_by: ULID | null # If this decision was later corrected
##### Decision Timing | Phase | Decision Activity | |-------|-------------------| | **Strategize** | Initial decisions are **created**, including `invariant_enforced` decisions for applicable invariants, `strategy_choice` decisions, `subplan_spawn` decisions, and `subplan_parallel_spawn` decisions grouping parallel child plans. `downstream_plan_ids` is empty. The system aims to make reasonable, comprehensive decisions at this stage to guide execution. | | **Execute** | Child plans are **spawned** and `downstream_plan_ids` is **populated** based on `subplan_spawn` decisions. **Additional decisions may be created** during execution — these are constrained by Strategize-phase decisions and arise from discoveries made during execution (e.g., `implementation_choice`, `resource_selection`, `tool_invocation`, `error_recovery`). If Execute determines that Strategize-phase constraints are too restrictive, the plan **reverts to Strategize** for adjustment rather than overriding those constraints. | | **Apply** | No new decisions. History can be flagged for cleanup after successful apply. | ##### Decision Tree Storage Schema 

-- Core decision table
CREATE TABLE decisions (
    decision_id TEXT PRIMARY KEY,      -- ULID
    plan_id TEXT NOT NULL,
    parent_decision_id TEXT,
    sequence_number INTEGER NOT NULL,
    decision_type TEXT NOT NULL,        -- prompt_definition, invariant_enforced, strategy_choice,
                                       -- implementation_choice, resource_selection, subplan_spawn,
                                       -- subplan_parallel_spawn, tool_invocation, error_recovery,
                                       -- validation_response, user_intervention
    question TEXT,
    chosen_option TEXT NOT NULL,
    alternatives_considered TEXT,      -- JSON array
    confidence_score REAL,
    rationale TEXT,
    actor_reasoning TEXT,
    context_snapshot TEXT NOT NULL,    -- JSON blob
    is_correction BOOLEAN DEFAULT FALSE,
    corrects_decision_id TEXT,
    correction_reason TEXT,
    superseded_by TEXT,
    created_at TEXT NOT NULL,

    FOREIGN KEY (plan_id) REFERENCES plans(plan_id),
    FOREIGN KEY (parent_decision_id) REFERENCES decisions(decision_id),
    FOREIGN KEY (corrects_decision_id) REFERENCES decisions(decision_id),
    FOREIGN KEY (superseded_by) REFERENCES decisions(decision_id)
);

-- Downstream relationships (many-to-many for DAG)
CREATE TABLE decision_dependencies (
    upstream_decision_id TEXT NOT NULL,
    downstream_decision_id TEXT NOT NULL,
    dependency_type TEXT NOT NULL,     -- 'decision', 'plan', 'artifact'
    downstream_ref TEXT NOT NULL,      -- The actual ID of decision/plan/artifact

    PRIMARY KEY (upstream_decision_id, downstream_decision_id, downstream_ref),
    FOREIGN KEY (upstream_decision_id) REFERENCES decisions(decision_id)
);

-- Correction history
CREATE TABLE correction_attempts (
    attempt_id TEXT PRIMARY KEY,       -- ULID
    plan_id TEXT NOT NULL,
    original_decision_id TEXT NOT NULL,
    new_decision_id TEXT,
    original_subtree_snapshot TEXT,    -- Reference to archived state
    correction_reason TEXT,
    status TEXT NOT NULL,              -- 'pending', 'executing', 'completed', 'failed'
    created_at TEXT NOT NULL,
    completed_at TEXT,

    FOREIGN KEY (plan_id) REFERENCES plans(plan_id),
    FOREIGN KEY (original_decision_id) REFERENCES decisions(decision_id),
    FOREIGN KEY (new_decision_id) REFERENCES decisions(decision_id)
);
### Action !!! adr "Architecture Decision" Actions as reusable plan templates and the action-to-plan transition are defined in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md). #### What an Action Is An **action** is a reusable plan template that is not associated with any projects yet. **Actions are created via CLI commands with a required `--config` YAML file** that fully defines the action. Any CLI options supplied alongside the config file act as optional overrides for values in the YAML. Examples: * "Increase test coverage to 80%" * "Refactor module X to be async-safe" * "Write an RFC for feature Y" * "Provision an infra cluster and validate access" (non-code) Actions are **intentionally project-agnostic** so they can be reused across projects. An action is the first stage of a plan — before it is used. Because of this, **invariants can be attached to actions**. When an action is used (via `agents plan use`), any invariants attached to the action are carried forward as plan-level invariants on the resulting plan. This allows teams to bake constraints directly into reusable templates. Invariants can also be added to a plan after the action is used, via `agents invariant add --plan` or `--invariant` flags on `agents plan use`. #### Action Creation (CLI) Actions are created using the CLI. The action is fully defined by the YAML configuration file: 

agents action create --config ./actions/code-coverage.yaml
The YAML file provides the complete action definition, including the name, strategy-actor, execution-actor, definition-of-done, arguments, invariants, and all other properties. **Required parameters:** * `--config`: YAML configuration file that fully defines the action (name, strategy-actor, execution-actor, definition-of-done, etc.) Arguments defined in the YAML's `args` section are values that will be: * Injected into the description and/or definition of done (via templating) * Passed into the context of the actors * Required when using the action on projects #### Action Data Model (Expanded) A plan in the Action phase has: ##### 1) `name` (namespaced) Format: * `[server:][namespace/]` Rules: * If server is omitted, default server is assumed unless namespace is `local`. * If namespace is omitted, default is `local`. * Names should be stable identifiers (kebab-case recommended). Examples: * `local/code-coverage` * `myusername/code-coverage` * `myorgname/code-coverage` * `prod:myorgname/code-coverage` (server-qualified) ##### 2) `short_description` Optional at creation; auto-filled if blank. ##### 3) `long_description` Optional but recommended for reusable actions. ##### 4) `definition_of_done` (DoD) Required. Must be explicit and testable. ##### 5) `actors` Two actors minimum, two optional: * **strategy_actor** (planner/architect) — required * **execution_actor** (builder/implementer) — required * **estimation_actor** (cost/risk estimator) — optional * **invariant_actor** (Invariant Reconciliation Actor) — optional; resolves invariant conflicts when the plan enters Strategize. Lookup falls back to project, then global config. Actors can be: * an LLM agent (built-in), * a graph (custom yaml, or built-in), Note: graphs are hierarchical allowing them to reference other actors as nodes. Actor abstraction is central: an actor may be a single agent or an entire graph. ##### 6) `reusable` (boolean) * Default: `true`. * If `true`: using the action creates a *new* plan in Strategize while leaving the action available. * If `false`: action self-deletes (or auto-archives) after first use. ##### 7) `read_only` (boolean) * Default: `false`. * If `true`: the plan must only use read-only tools (tools with `read_only: true` in their capability metadata) and must never modify resources (even in sandbox). * Read-only actions are still useful for "investigation reports," architecture reviews, or dry-run planning. ##### 8) `inputs_schema` (recommended addition) To make actions genuinely reusable, actions should declare their inputs: * required args (e.g., target coverage percent), * optional args (e.g., test framework), * validation rules (types, bounds). Example: * `target_coverage_percent`: integer 0–100 ##### 9) `automation_profile` The resolved automation profile name for this plan (e.g., `trusted`, `auto`, `local/careful-auto`). Determined at `plan use` time using the profile precedence rules (plan > action > project > global). Once set, it is locked to the plan. ### Strategy (Strategize Phase) !!! adr "Architecture Decision" The Strategize phase, strategy actors, and decision generation are defined in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md). #### Using an Action (Transition to Strategize) The `use` command transitions an Action into the Strategize phase by applying it to one or more projects: 

# Basic usage
agents plan use local/code-coverage my-api-service

# Multiple projects
agents plan use local/schema-update \
  api-service \
  web-frontend \
  mobile-app

# With action arguments
agents plan use local/code-coverage \
  my-api-service \
  --arg target_coverage_percent=85 \
  --arg test_framework=pytest

# With explicit automation profile
agents plan use local/deploy-action \
  staging-env \
  --automation-profile manual

# With invariants attached at use time
agents plan use local/code-coverage \
  my-api-service \
  --arg target_coverage_percent=85 \
  --invariant "All API calls over TCP must be mocked" \
  --invariant "Do not modify the payments module"
**Parameters:** * ``: Project to apply the action to (positional, can be repeated for multi-project plans) * `--arg`: Action argument values (format: `name=value`) * `--automation-profile`: Override automation profile for this plan * `--invariant`: Invariant to attach to the created plan (can be repeated). These are added as plan-level invariants in addition to any inherited from the action, project, or global scope. When the action is used: 1. A new plan is created with a unique ULID 2. The plan's automation profile is resolved (plan > action > project > global precedence) 3. Any invariants from the action are carried forward as plan-level invariants, combined with any `--invariant` flags provided 4. The plan enters the **Strategize** phase 5. The **Invariant Reconciliation Actor** computes the effective invariant view (resolving conflicts using plan > action > project > global precedence) 6. The `strategy_actor` begins analyzing the project(s) #### What Strategize Does When an action is **used** on projects, it becomes a **plan in Strategize**. Strategize is: * **read-only**, producing a plan of attack, * responsible for gathering context from project resources, * responsible for collecting applicable invariants (from global, project, action, and plan scopes), computing the effective invariant view via the **Invariant Reconciliation Actor** (applying plan > action > project > global precedence), and recording them as `invariant_enforced` decisions, * responsible for generating a strategy and child plan blueprint (using `subplan_spawn` and `subplan_parallel_spawn` decisions), * not allowed to execute child plans or modify resources. This "architect vs coder" separation is explicitly described as a core motivation. **Resource-aware dependency analysis**: During the Strategize phase, the strategy actor employs specialized mechanisms to compute precise dependency closures: 

# Pseudocode of what happens inside a strategy actor
def compute_closure_for_refactoring(target_module):
    closure = ResourceClosure()

    # Direct file dependencies
    closure.add_files(find_imports(target_module))
    closure.add_files(find_includes(target_module))

    # Symbol dependencies
    for symbol in extract_exported_symbols(target_module):
        closure.add_files(find_symbol_usage(symbol, scope='project'))

    # Test dependencies
    closure.add_files(find_tests_for_module(target_module))

    # Build system dependencies
    closure.add_files(find_build_references(target_module))

    return closure
The system leverages several key insights: - **Modular boundaries exist**: Even in legacy codebases, there are natural boundaries - **Changes are incremental**: We don't convert 50,000 files atomically - **Dependencies are sparse**: Most modules depend on a small fraction of the codebase - **Interfaces are narrow**: Public APIs are much smaller than implementations #### Strategize Data Model A plan in Strategize contains all Action fields plus: ##### 1) `projects` A list of projects the plan is used on. Important: A strategy plan may target **multiple projects**. Multi-project work in one "window" is considered a major usability advantage over tools that require being run from a single directory. ##### 2) `strategy_context` A structured object describing: * what resources were considered, * how they were retrieved, * what filtering/limits were applied, * what the actor saw. This matters because a plan must be debuggable and correctable later. Recommended fields: * `resource_refs`: IDs of resources used * `queries`: search queries performed * `selected_chunks`: chunk IDs + sources + reasons * `constraints`: context window limits, file ignore patterns * `generated_summaries`: if summarization occurred ##### 3) `strategy` The output plan: * steps (ordered and/or DAG), * conditions/branches ("if tests fail, do X"), * child plans to spawn (including which action templates to use, and whether they should run in parallel via `subplan_parallel_spawn`), * evaluation criteria (how to know success), * risk assessment. ##### 4) `execution_blueprint` (recommended addition) Strategize should output not only narrative text but also a machine-usable blueprint: * list of tasks, * required skills, * expected outputs, * dependencies between tasks. This blueprint becomes the input to Execute. ##### 5) `cost_estimate` and `risk_estimate` (optional) **Cost and risk estimation is optional** but recommended for production use. When enabled, a specialized **estimation actor** analyzes: * The initial prompt/request * The strategy produced by the Strategize phase * Historical data from similar plans (if available) And produces estimates for: * LLM tokens/cost range * Number of steps/child plans expected * Expected risk of rollbacks * Estimated execution time **Implementation**: Similar to how there's a `strategy_actor` and `execution_actor` for each action, there can be an optional `estimation_actor` whose entire job is cost/risk estimation. This actor runs after Strategize completes (before Execute) and its output is informational only. Estimation failures are logged but never block the Execute transition. **Estimation actor resolution** follows a 4-level fallback chain (highest priority first): 1. CLI `--estimation-actor` override (applied post-creation by the CLI layer) 2. Action YAML `estimation_actor` field 3. *(project-scoped key — reserved for future use)* 4. `actor.default.estimation` global config key (`CLEVERAGENTS_DEFAULT_ESTIMATION_ACTOR`) When the resolved actor is set, `PlanLifecycleService.complete_strategize()` invokes `_run_estimation()` and emits a `PLAN_ESTIMATION_COMPLETE` event on success. The result is stored on the plan and `plan.cost_estimate_usd` is populated from the midpoint of the estimated cost range. 

# Example: Action with estimation actor (defined in the YAML config file)
agents action create --config ./actions/expensive-refactor.yaml
This becomes critical in server/multi-user usage and cost controls. ### Execution (Execute Phase) !!! adr "Architecture Decision" The Execute phase, sandbox model, and execution safety mechanisms are defined in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md) and [ADR-015: Sandbox and Checkpoint](adr/ADR-015-sandbox-and-checkpoint.md). #### What Execute Does Execute is where the plan actually performs work, but **in a sandboxed environment** that can later be reviewed and applied. Key properties: 1. **Work happens in a sandbox** All file modifications, generated artifacts, and intermediate outputs live in an isolated "execution workspace" until Apply. 2. **Execute may spawn child plans** Child plan spawning is a first-class behavior of Execute: a parent plan can distribute work to child plans (sequentially via `subplan_spawn` or concurrently via `subplan_parallel_spawn`) and merge results. 3. **Execute must support checkpointing / rollback (when enabled)** Checkpointable tools allow rolling back to a checkpoint ID to recover from partial failure or wrong turns. 4. **Execute produces a "reviewable diff"** Diff review sandbox is described as a differentiating feature: users can inspect changes before applying. #### Execution Workspace / Sandbox Model (Detailed) !!! adr "Architecture Decision" Sandbox isolation, lazy sandboxing, and resource-type-specific sandbox strategies are detailed in [ADR-015: Sandbox and Checkpoint](adr/ADR-015-sandbox-and-checkpoint.md). A sandbox isolates plan execution from the real project resources until Apply. !!! tip "Key Sandbox Principles" - [x] **Lazy Sandboxing** — Resources are sandboxed ==only when accessed==, not upfront - [x] **Per-Plan Sandboxes** — Each plan and child plan has its own isolated sandbox - [x] **Resource-Defined Strategy** — The sandbox strategy is defined on each **resource**, not globally - [x] **Cleanup Behavior** — Automatic cleanup on exit, crash recovery on next run, retention-based archival ??? info "Why Lazy Sandboxing?" A project may have many resources (git repo + 10 databases + cloud accounts), but a plan may only modify one resource. Only accessed resources are sandboxed, making this efficient for large projects with many linked resources. ##### Sandbox Implementation Strategies Different resource types require different sandbox strategies: | Resource Type | Strategy | Rollback Mechanism | |--------------|----------|-------------------| | `git-checkout` | `git_worktree` | Git reset/checkout | | `git` | `none` | N/A (represents a repo instance — not directly sandboxable) | | `fs-mount` | `copy_on_write` or `overlay` | Restore from snapshot | | `fs-directory` | `copy_on_write` | Restore from snapshot | | Custom database types | `transaction_rollback` | Transaction rollback | | Custom API types | `none` | Often not sandboxable | **1. Git worktree / branch sandbox (preferred for code)** * Create a worktree or temporary branch * All modifications are commits or staged changes * Apply merges/cherry-picks Pros: natural rollback, diff support, efficient Cons: requires git **2. Filesystem copy sandbox** * Copy project directory to a sandbox directory * Execute modifies sandbox copy * Apply syncs diff back Pros: simple Cons: expensive for huge repos **3. Overlay filesystem sandbox** * Use overlayfs-style "copy-on-write" to avoid full copies Pros: efficient Cons: more complex, OS-dependent **4. Transaction-based sandbox (for databases)** * Begin transaction at sandbox creation * All operations within transaction * Rollback on failure, commit on apply Pros: native to databases Cons: long-running transactions can cause issues **5. No sandbox (for non-sandboxable resources)** * Some resources cannot be sandboxed (certain APIs, cloud services) * User proceeds at their own risk * Plan should warn about non-sandboxable resources ##### Multi-Resource Sandboxing When a plan accesses multiple resources: * Each resource gets its own sandbox (based on its defined strategy) * Sandboxes are independent * Apply commits each sandbox separately * If any sandbox Apply fails, others may still succeed (partial apply) **Complete isolation during execution prevents compound errors**: Each plan executes in its own sandbox, which means: 

Plan A (refactoring auth module):
- Sandbox A1: Contains only auth/*.cpp, auth_tests/*.cpp
- Cannot see Plan B's intermediate states
- Cannot accidentally depend on Plan B's half-done work

Plan B (updating API endpoints):
- Sandbox B1: Contains only api/*.cpp, api_tests/*.cpp  
- Makes changes assuming current auth interface
- Protected from Plan A's intermediate refactoring
**Hierarchical merge resolution**: When child plans complete, the parent plan performs intelligent merging: 

def merge_subplan_results(subplan_results):
    # Group by resource type
    by_resource = group_by_resource_type(subplan_results)

    # Apply resource-specific merge strategies
    for resource_type, changes in by_resource:
        if resource_type == 'git-checkout':
            merge_git_changes(changes)  # Three-way merge
        elif resource_type == 'fs-mount':
            merge_fs_changes(changes)   # Copy-on-write reconciliation
        elif resource_type.startswith('database'):
            merge_db_changes(changes)   # Sequential application

    # Validate merged state
    run_integration_tests()
#### Execution Data Model A plan in Execute contains: ##### 1) `execution_context` The context used for execution (often smaller/more tactical than strategy context). ##### 2) `execution_log` Structured timeline of: * tool calls (with parent skill noted), * actor calls, * outputs, * errors and retries, * checkpoints created. This log is essential for debugging. ##### 3) `artifacts` Outputs produced: * changed files, * generated files, * reports, * diagrams, * test outputs, * diffs. ##### 4) `sandbox_ref` Pointer to the sandbox location/state: * path, branch name, workspace ID, container ID, etc. ##### 5) `checkpoint_graph` (if enabled) A record of checkpoints: * checkpoint ID * timestamp * tool responsible (and its parent skill) * resources affected * rollback instructions / metadata #### Checkpointing in Execute (Core Safety Mechanism) !!! adr "Architecture Decision" Checkpointing, rollback, and transaction safety are defined in [ADR-015: Sandbox and Checkpoint](adr/ADR-015-sandbox-and-checkpoint.md). The intended user-level behavior is: * "Give me a checkpoint ID." * Perform additional operations. * "Roll back to checkpoint X." Not all tools can support this; checkpointing must be declared per tool (in its capability metadata). ##### Tool-level checkpointability Each tool declares (via its capability metadata): * `checkpointable: true|false` * `checkpoint_scope`: what granularity of rollback is supported (file, transaction, commit, snapshot) * `rollback_mechanism`: how rollback occurs Examples: * File tools (from a file-ops skill): snapshot file states pre-modification * Git tools (from a git-ops skill): create commit or stash; rollback is reset/checkout * Shell/CLI tools (running inside a container): rollback by restoring filesystem snapshot or reloading base image state It should be noted that checkpointing is easier when tool scope is constrained (e.g., "only files within a docker image + git"). ##### Plan-level rollback policy Plans should have an option: * `rollback_enabled: true|false` If disabled, the plan may use more generic/unsafe tools with fewer restrictions (useful for low-stakes tasks). ##### CheckpointService Operations The `CheckpointService` provides the following key operations for checkpoint lifecycle management: - **`create_checkpoint(plan_id, sandbox_ref, reason, source_tool, phase, decision_id, checkpoint_type, size_bytes)`** — Creates a standard checkpoint record. The `sandbox_ref` is a git commit hash of the current HEAD. - **`create_workspace_snapshot(plan_id, sandbox_ref, decision_id, *, reason, phase)`** — Creates a diff-based workspace snapshot before decision execution. Captures only files that differ from the previous checkpoint (or the initial sandbox state when no prior checkpoints exist). The diff manifest is stored in checkpoint metadata under `"diff_paths"`, `"diff_based"`, and `"diff_hash"` keys. Returns the new `Checkpoint`. - **`selective_rollback(plan_id, checkpoint_id)`** — Rolls back to a specific checkpoint with atomic (all-or-nothing) semantics. If the rollback fails partway through, a best-effort recovery attempt restores the sandbox to its pre-rollback HEAD. Raises `BusinessRuleViolation` if recovery also fails. Raises `ResourceNotFoundError` if the checkpoint does not exist. - **`archive_artifacts(sandbox_path, artifact_paths, archive_dir)`** — Physically moves artifact files to an archive directory, preserving them outside the sandbox for later retrieval. The service supports both database-backed persistence (via `CheckpointRepository`) and in-memory fallback for tests. Guard checks (whether a plan has been applied, whether a sandbox exists) are resolved via `PlanLifecycleService` when wired, querying persistent plan state rather than relying on in-memory flags. ##### Automatic Checkpoint Triggers The execution engine supports four automatic checkpoint triggers, configurable via `core.checkpoints.auto_create_on` (default: all four enabled): | Trigger | When | Component | |---------|------|-----------| | `before_tool_execute` | Before each write-tool execution | `ToolRunner` | | `after_tool_execute` | After each write-tool execution | `ToolRunner` | | `on_subplan_spawn` | Before first subplan execution attempt | `SubplanExecutionService` | | `on_error` | When the Execute phase fails | `PlanExecutor` | Configuration: ```toml [core.checkpoints] auto_create_on = ["before_tool_execute", "after_tool_execute", "on_subplan_spawn", "on_error"] ``` To disable a specific trigger, remove it from the list. To disable all automatic checkpoints, set the list to empty (`auto_create_on = []`). The `CheckpointService` is injected as an optional parameter into `ToolRunner`, `SubplanExecutionService`, and `PlanExecutor`. When `checkpoint_service` is `None`, all automatic checkpointing is skipped (backward-compatible no-op). #### Execution as Transactions (Recommended) Execution should be treated like a transactional pipeline: * Each step either: * commits a checkpoint on success, or * rolls back to the previous checkpoint on failure. This is explicitly motivated by "partial failure leaves codebase inconsistent" and the need for transaction rollback. #### Execution Environment Routing !!! adr "Architecture Decision" Execution environment routing, devcontainer integration, and the 6-level precedence chain are defined in [ADR-043: Devcontainer Integration](adr/ADR-043-devcontainer-integration.md). Container resource types are defined in [ADR-039: Container Resource Types](adr/ADR-039-container-resource-types.md). When a plan enters the **Execute** phase, the runtime must determine _where_ each tool invocation runs: on the host, or inside a container. This decision is called **execution environment routing**. The router evaluates a 6-level precedence chain and selects the first matching environment. **Precedence Chain (highest → lowest):** | Priority | Source | Condition | | :------: | :----- | :-------- | | 1 | Plan-level `execution_environment` with `priority: override` | Always wins when set. Configured via `agents plan use --execution-environment … --execution-env-priority override`. | | 2 | Project-level `execution_environment` with `priority: override` | Wins unless a plan-level override exists. Configured via `agents project context set --execution-environment … --execution-env-priority override`. | | 3 | Nearest-ancestor devcontainer | Auto-detected `devcontainer-instance` resource that is a child (or descendant) of a resource linked to the project. Lazy-built on first access. | | 4 | Plan-level `execution_environment` with `priority: fallback` | Used only when no devcontainer is detected and no override exists above. | | 5 | Project-level `execution_environment` with `priority: fallback` | Used only when no closer-scoped environment exists. | | 6 | Host | The local operating system. Default when no container environment is configured or detected. | **Routing Algorithm:** ``` function resolve_execution_environment(plan, project): # Level 1: plan override if plan.execution_environment AND plan.execution_env_priority == "override": return plan.execution_environment # Level 2: project override if project.execution_environment AND project.execution_env_priority == "override": return project.execution_environment # Level 3: nearest-ancestor devcontainer for resource in project.linked_resources (ordered by DAG depth, shallowest first): devcontainer = find_child_of_type(resource, "devcontainer-instance") if devcontainer: if devcontainer.state == "detected": build_and_start(devcontainer) # lazy activation return devcontainer # Level 4: plan fallback if plan.execution_environment AND plan.execution_env_priority == "fallback": return plan.execution_environment # Level 5: project fallback if project.execution_environment AND project.execution_env_priority == "fallback": return project.execution_environment # Level 6: host return HOST_ENVIRONMENT ``` **Tool-Level Environment Preferences:** Individual tools may declare environment preferences via the `environment` field in their capability metadata (see §Tool Capability Metadata): - `environment.required`: Tool _must_ run in this environment type (`container` or `host`). If the resolved environment doesn't match, the tool invocation fails with an error rather than silently running in the wrong environment. - `environment.preferred`: Tool _prefers_ this environment type but will run wherever the router places it. - `environment.specific`: Tool targets a specific named resource (e.g., `local/api-dev`). If the named resource is available and running, the tool is routed there regardless of the general precedence chain. When a tool declares `environment.required: container` but the router resolves to `host`, the runtime MUST raise an error. The operator can then either: (a) add a container resource to the project, or (b) change the tool's environment requirement. **Lazy Activation:** Devcontainers detected during auto-discovery are created in `detected (not built)` state. They are built and started _only_ when the execution environment router first selects them. This avoids unnecessary container builds when the user never executes a plan that needs container isolation. Once built, the container remains available for subsequent plan executions until explicitly stopped or the resource is removed. #### Tool-Based Resource Modification (Modern Architecture) !!! adr "Architecture Decision" The tool-based resource modification approach and tool execution model are defined in [ADR-011: Tool System](adr/ADR-011-tool-system.md). **IMPORTANT: CleverAgents does NOT parse LLM output to extract code.** Instead, it uses the modern tool-based approach pioneered by Claude Code, Cursor, and Aider where: 1. **LLMs call tools directly** (`edit_file()`, `write_file()`, `delete_file()`, etc.) — tools provided by referenced skills 2. **Tools operate on the sandbox** - each tool invocation modifies sandbox state directly 3. **ChangeSet is built from tool invocations** - not by parsing LLM text output 4. **Validation runs on sandbox state** - after tools execute, not on parsed output This architecture provides: * **Atomic operations**: Each tool call is a discrete, trackable change * **No parsing ambiguity**: Tools have structured parameters (path, content, etc.) * **Resource-agnostic**: Same pattern works for files, databases, APIs, any resource type * **Safety by design**: Tools run in sandbox with defined capabilities and restrictions * **MCP compatibility**: Tools from MCP-based skills map directly to MCP tools for external integrations ##### How It Works ```kroki-mermaid sequenceDiagram participant LLM as LLM Agent participant Router as Tool Router participant Sandbox as Sandbox participant CS as ChangeSet participant Val as Validator LLM->>Router: Tool call (with parameters) Router->>Router: Validate parameters Router->>Router: Enforce capability restrictions Router->>Sandbox: Execute tool in sandbox Sandbox->>Sandbox: Operate on sandboxed state Sandbox->>Sandbox: Record invocation Sandbox->>Sandbox: Create checkpoint (if needed) Sandbox->>CS: Emit Change record CS->>CS: Accumulate into ChangeSet CS->>Val: Submit for validation Val->>Val: Run validators on sandbox state Val->>Val: Generate diff from ChangeSet Val-->>LLM: Present for review before Apply ``` ##### Built-in Resource Tools CleverAgents provides these core tools (via built-in skills) for resource manipulation: | Tool | Description | Creates Change? | |-------|-------------|-----------------| | `read_file(path)` | Read file contents | No | | `write_file(path, content)` | Create/overwrite file | Yes | | `edit_file(path, changes)` | Apply targeted edits | Yes | | `delete_file(path)` | Remove file | Yes | | `move_file(src, dst)` | Rename/move file | Yes | | `create_directory(path)` | Create directory | Yes | | `list_files(pattern)` | List files matching glob | No | | `search_files(pattern, content)` | Search file contents | No | | `get_file_info(path)` | Get file metadata | No | Each built-in tool automatically: * Operates within sandbox boundaries * Records changes to the ChangeSet * Validates parameters against project configuration * Enforces deny-list patterns (`.git/`, `node_modules/`, etc.) ##### Why Not Parse LLM Output? The obsolete approach of parsing markdown code fences has fundamental problems: 1. **Ambiguity**: Is text explanation or code? Where does one file end and another begin? 2. **Fragility**: Models output varying formats; regex parsing is brittle 3. **Loss of semantics**: You lose the intent (create vs modify vs delete) 4. **No atomicity**: Can't rollback individual operations 5. **Resource-limited**: Only works for files, not databases or other resources The tool-based approach solves all of these by making each operation explicit, typed, and trackable. ### Semantic Error Prevention !!! adr "Architecture Decision" The multi-layer error prevention strategy and guardrail architecture are defined in [ADR-018: Semantic Error Prevention](adr/ADR-018-semantic-error-prevention.md). CleverAgents provides multiple layers of proactive error prevention that catch semantic errors before they can propagate through the system. #### Layer 1: Decision-time Validation During Strategize Every decision includes semantic validation: 

Decision: Refactor payment module to async
alternatives_considered:
  - "Convert to async/await patterns" (chosen)
  - "Use thread pool with channels" (rejected: doesn't integrate with async ecosystem)
  - "Keep synchronous with timeout" (rejected: doesn't solve core latency issue)
confidence_score: 0.85
validation_performed:
  - Checked all payment API consumers can handle async
  - Verified database driver supports async operations
  - Confirmed no regulatory requirement for sync processing
#### Layer 2: Execution-time Semantic Guards The execution actor uses a tool node that references the independently registered `local/validate-api-compat` tool: 

# Actor graph uses a named tool node for semantic validation
actors:
  code_executor:
    type: graph
    skills:
      - local/semantic-validators    # Skill containing validation tools for LLM tool-calling
    nodes:
      - name: semantic_validator
        type: tool
        tool: local/validate-api-compat # Named tool from Tool Registry
The `local/validate-api-compat` tool is independently registered via its own YAML: 

# File: tools/validate-api-compat.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/validate-api-compat
  description: "Check for breaking API changes and attempt auto-migration"
  source: custom

  capability:
    writes: true
    checkpointable: true

  code: |
    # Not just syntax checking - semantic validation
    old_api = extract_api_signature(previous_version)
    new_api = extract_api_signature(current_version)

    breaking_changes = find_breaking_changes(old_api, new_api)
    if breaking_changes:
        affected_consumers = find_api_consumers(breaking_changes)
        migration_plan = generate_migration(breaking_changes)

        if can_auto_migrate(affected_consumers, migration_plan):
            apply_migration(migration_plan)
        else:
            raise SemanticError(
                "Breaking API changes require manual review",
                changes=breaking_changes,
                affected=affected_consumers
            )
The `local/semantic-validators` skill references this tool by name: 

# File: skills/semantic-validators.yaml
skill:
  name: local/semantic-validators
  description: "Semantic validation tools for API compatibility and code invariants"
  tools:
    - local/validate-api-compat
#### Layer 3: Invariant Enforcement !!! adr "Architecture Decision" Invariant scoping, enforcement mechanisms, and inheritance rules are defined in [ADR-016: Invariant System](adr/ADR-016-invariant-system.md). Invariants are named constraints that guide and constrain plan execution. They can be attached at four scopes, all managed through the unified `agents invariant` command: * **Global invariants**: Apply to all plans across all projects. Added via `agents invariant add --global`. * **Project invariants**: Apply to all plans targeting a specific project. Added via `agents invariant add --project`. Can also be attached at creation time via `agents project create --invariant`. * **Action invariants**: Attached to an action and carried forward as plan-level invariants when the action is used. Added via `agents invariant add --action`. Can also be attached at creation time via `agents action create --invariant`. * **Plan invariants**: Apply to a specific plan and its child plans. Added via `agents invariant add --plan`. Can also be attached at creation time via `agents plan use --invariant`. **Precedence and conflict resolution**: When invariants from different scopes conflict, narrower scopes override broader scopes: * **Plan-level** invariants override **action-level**, **project-level**, and **global-level** invariants. * **Action-level** invariants override **project-level** and **global-level** invariants. * **Project-level** invariants override **global-level** invariants. Exception: **Non-overridable global invariants** (marked `non_overridable: true`) always take precedence over all other scopes, including plan-level invariants. See below. The full precedence chain (highest to lowest): `plan > action > project > global`. Conflict resolution is performed by the **Invariant Reconciliation Actor** — a dedicated actor responsible for comparing invariants across scopes, identifying conflicts, and producing the final **effective invariant view** for a plan. The Invariant Reconciliation Actor is set at three levels via `--invariant-actor`: 1. **Global config**: Set via `agents config set actor.default.invariant `. Defines the default Invariant Reconciliation Actor used when neither the project nor the plan specifies one. 2. **Project-level**: Set via `--invariant-actor` on `agents project create`. If a project defines an Invariant Reconciliation Actor, it is used to reconcile that project's invariants against global invariants. 3. **Plan-level**: Set via `--invariant-actor` on `agents action create` (carried forward when the action is used) or `agents plan use` (which overrides whatever was set on the action). If a plan has an Invariant Reconciliation Actor, it reconciles invariants from all scopes (plan, project, and global) and produces the final effective view for that plan. The lookup order is: plan → project → global config. The first Invariant Reconciliation Actor found is used. **Invariant view calculation**: When an action is used and a plan enters the Strategize phase, the Invariant Reconciliation Actor computes the effective invariant view by: 1. Collecting all invariants from global, project, plan, and action scopes. 2. Identifying conflicts (invariants from different scopes that contradict each other). 3. Applying precedence rules (plan > action > project > global) to resolve conflicts, with non-overridable global invariants taking absolute precedence. 4. Producing the final set of effective invariants. Each effective invariant is then recorded as an `invariant_enforced` decision in the plan's decision tree. This makes invariants visible, auditable, and correctable through the standard decision correction mechanism. **Non-overridable global invariants**: A global invariant may be marked `non_overridable: true`. When set, this invariant takes precedence over all lower-scope invariants regardless of the normal precedence chain -- even plan-level invariants cannot override it. This is intended for system-wide safety constraints that must never be relaxed (e.g., "Never commit secrets to version control"). Non-overridable invariants are set via `agents invariant add --global --non-overridable ""`. The `non_overridable` flag is only meaningful on `GLOBAL`-scoped invariants; it is ignored on project, action, and plan invariants. **Child plan inheritance**: When a top-level plan spawns child plans, the parent's effective invariant view (already reconciled) is passed down to each child plan. Child plans do not re-run reconciliation — they inherit the parent's resolved view. **Correcting invariants**: The correction mechanism for `invariant_enforced` decisions supports two operations: * **Remove**: Remove an existing invariant from the plan's decision tree (the invariant remains defined at its scope but is no longer enforced for this plan). * **Add**: Add a new invariant to the plan. When adding, the user can select from invariants already accessible to the plan (those defined at the plan, action, project, or global scope), or provide free-form text to create a new ad-hoc invariant. 

# Add invariants at different scopes
agents invariant add --global "All public APIs must maintain backward compatibility"
agents invariant add --global "Payment processing must be idempotent"
agents invariant add --project local/api-service \
  "Database transactions must complete within 5 seconds"
agents invariant add --project local/api-service \
  "Authentication must always use OAuth2"
agents invariant add --plan <PLAN_ID> "All API calls over TCP must be mocked"
agents invariant add --action local/code-coverage "Test files must not import production secrets"

# List invariants
agents invariant list --global
agents invariant list --project local/api-service
agents invariant list --plan <PLAN_ID> --effective   # Shows reconciled view

# Remove an invariant
agents invariant remove <INVARIANT_ID>

# Attach invariants at creation time (convenience)
agents project create --invariant "All endpoints must validate auth tokens" local/api-service
agents action create --config ./actions/code-coverage.yaml
agents plan use local/code-coverage local/api-service --invariant "Mock all network calls"

# Correct an invariant decision (remove or replace via standard correction)
agents plan correct <DECISION_ID> --mode=revert \
  --guidance "Remove this invariant - it does not apply to this module"
The system collects, reconciles, and checks invariants: 

class InvariantEnforcer:
    def compute_effective_invariants(self, plan):
        """Compute the effective invariant view for a plan using the Invariant Reconciliation Actor."""
        # 1. Collect raw invariants from all scopes
        raw = self.collect_all_invariants(plan)

        # 2. Find the Invariant Reconciliation Actor (plan -> project -> global config)
        reconciler = (
            self.get_plan_invariant_actor(plan)
            or self.get_project_invariant_actor(plan)
            or self.get_global_invariant_actor()
        )

        # 3. Reconcile: apply precedence (plan > project > global), resolve conflicts
        effective = reconciler.reconcile(raw, precedence=['plan', 'project', 'global'])
        return effective

    def collect_all_invariants(self, plan):
        """Collect invariants from all scopes accessible to this plan."""
        invariants = []
        invariants.extend(self.get_global_invariants())
        for project in plan.projects:
            invariants.extend(self.get_project_invariants(project))
        invariants.extend(self.get_action_invariants(plan.action))
        invariants.extend(self.get_plan_invariants(plan))
        return invariants

    def check_invariant_preservation(self, changes, enforced_invariants):
        """Check that changes respect all enforced invariants."""
        for invariant in enforced_invariants:
            if not self.verify_invariant(invariant, changes):
                return InvariantViolation(invariant, changes)
        return Success()
#### Layer 4: Predictive Error Prevention The system learns from past failures: 

Error Pattern Database:
  - pattern: "Async conversion in payment module"
    historical_failures:
      - "Race condition in payment confirmation"
      - "Timeout handling breaks idempotency"
    preventive_checks:
      - "Add explicit transaction boundaries"
      - "Verify idempotency keys are preserved"
      - "Check distributed lock acquisition"
### Apply Phase !!! adr "Architecture Decision" The Apply phase, conflict resolution, and apply strategies are defined in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md). #### What Apply Does Apply takes the sandboxed work product and makes it "real" in the project. Core properties: 1. **Apply is a controlled commit step** Apply exists specifically to separate "generated work" from "committed work," enabling review and safer automation. 2. **Apply is often the highest-risk step** It changes real systems. This is where approvals and checks matter most. 3. **Apply produces a terminal 'applied' state** After successful apply, the plan reaches the `applied` terminal state within the Apply phase. #### Apply Responsibilities (Recommended Checklist) Apply should perform (configurable) validations before committing: * **Diff review gate** * If the `select_tool` threshold is not met (i.e., confidence < threshold, or threshold is `1.0`) in the automation profile, show: * changed files summary, * full diff, * risk warnings. * **Conflict resolution** * If applying to a git repo, handle rebase/merge conflicts safely. * **Audit log** * Record who applied, what changed, when, and why. #### Validation in Apply Validation runs during **Execute**, not during Apply. By the time a plan reaches the Apply phase, all required validations have already passed. Apply commits the sandbox changes to the real resources and does not re-run validations. For full details on validation — including the Validation type system, modes, attachment scoping, failure handling, fix-then-revalidate loops, and data model — see the **Validation** section under Core Concepts. #### Apply Data Model A plan in Apply includes: * `apply_summary` * `applied_artifacts` (final commit hash, merged PR link, file list) * `final_validation_results` (per-validation tool invocation results: `passed`, `message`, and `data` for each) * `approval_record` (if human approvals are required) * `deployment_record` (optional, if apply triggers deploy) #### Apply Terminal States Apply is the final phase. It does not transition to another phase — instead, the plan reaches one of several terminal states within the Apply phase: **When Apply succeeds:** * plan.phase = `apply` * plan.state = `applied` * the sandbox may be cleaned up or archived depending on retention policy * changes have been committed to real project resources **When Apply cannot complete within constraints:** * plan.phase = `apply` * plan.state = `constrained` * the Apply phase has determined that the current strategy's constraints prevent successful application (e.g., merge conflicts that violate invariants, validation failures that cannot be resolved within the strategy's scope, resource state drift that contradicts strategy assumptions) * depending on the `access_network` automation profile flag, this may automatically trigger a reversion to Strategize, or the system may pause for user decision * sandbox remains intact pending reversion or user action **When Apply fails:** * plan.phase = `apply` * plan.state = `errored` * sandbox remains intact for inspection/retry **When Apply is cancelled:** * plan.phase = `apply` * plan.state = `cancelled` * sandbox remains intact for inspection ### Project !!! adr "Architecture Decision" The project concept, resource linking, and project-level configuration are defined in [ADR-009: Project Model](adr/ADR-009-project-model.md). A **project** is the boundary that answers: * "Where is the work happening?" * "What can this plan read and write?" * "What skills (and their tools) can this plan use?" * "What context is available?" A project is a **collection of linked resources and configuration**. Projects link to independently registered resources from the **Resource Registry** — they do not define resources inline. A resource can be linked to multiple projects, enabling shared resources across teams and workflows. **Important: Projects are created via CLI commands, NOT YAML configuration files.** #### Project Types: Local vs Remote Projects are classified based on their resources: | Type | Definition | Where Plans Can Execute | |------|------------|------------------------| | **Local** | Contains at least one local-only resource | Client only | | **Remote** | All resources are remotely accessible | Client or Server | This distinction matters for server mode: the server can only execute plans on **remote** projects because it needs network access to all resources. #### Project Creation (CLI) 

# Step 1: Register resources independently
agents resource add git-checkout local/api-repo \
  --path /repos/api-service \
  --branch main

agents resource add local/database local/staging-db \
  --connection-string "postgresql://staging.example.com/mydb" \
  --read-only

# Step 2: Create the project
agents project create "my-api-service"

# Step 3: Link resources to the project
agents project link-resource "my-api-service" local/api-repo

agents project link-resource "my-api-service" local/staging-db --read-only
Resources are registered once and can be linked to multiple projects. The resource's type, sandbox strategy, and capabilities are defined by its resource type in the Resource Registry — not by the project. #### Project Data Model A project includes: ##### 1) Identity * `name` — the namespaced project name (e.g., `local/api-service`). This serves as the project's globally unique identifier; no separate ULID or ID is generated. The namespacing scheme (`[[server:]namespace/]name`) ensures global uniqueness across systems. * `namespace` (follows same rules as actors: `local/`, `/`, `/`) * `is_remote` (boolean, derived from resources) ##### 2) Linked Resources Resources are the "things you can act on." Projects **link** to independently registered resources from the Resource Registry rather than defining them inline. This means: * A resource can be linked to multiple projects (shared resources). * The resource's type, capabilities, sandbox strategy, and DAG relationships are defined by the resource itself — not by the project. * Projects can apply project-level overrides when linking (e.g., marking a writable resource as read-only within a specific project context). Each linked resource reference has: * `resource_id` (ULID reference to a Resource Registry entry). Resources can be referenced by name or ULID in CLI commands; name is resolved to `resource_id` at command time. * `project_read_only` (boolean — project-level read-only override) * `alias` (optional short name for referencing within the project) The full resource details (type, location, sandbox strategy, capabilities, parent/child DAG, etc.) are stored in the Resource Registry. See the **Resources** section for details. ##### 3) Context configuration Project-level defaults: * ignore patterns (like `.gitignore` semantics) * max file size * indexing strategy * preferred chunking/summarization policy (even if evolving) * context retention policy ##### 4) Execution Environment !!! adr "Architecture Decision" Execution environment routing is defined in [ADR-043: Devcontainer Integration and Container-Project Association](adr/ADR-043-devcontainer-integration.md). Projects can configure a default execution environment — a container in which tools execute instead of on the host. This is set via `agents project context set`: 

execution_environment:
  default: local/dev-container        # Resource name of the default container
  priority: fallback                 # fallback | override
**Priority semantics:** * `fallback` (default): Use this execution environment only when no devcontainer is auto-detected for the current resource or its ancestors. If a resource (or ancestor) has a `.devcontainer/`, the devcontainer wins. * `override`: Always use this execution environment, ignoring any auto-detected devcontainers. When a project has multiple containers linked as resources, the `execution_environment.default` field specifies which one to use. Without this setting, the system relies on auto-detected devcontainers or falls back to host execution. Plans can override the project-level execution environment via `--execution-environment` on `agents plan use` (see [Execution Environment Routing](#execution-environment-routing)). #### Multi-Project Operations A single plan may target multiple projects (e.g., updating shared schemas across services). This is considered a key UX advantage over "run in one directory" systems. Because resources are independently registered and can be linked to multiple projects, shared resources across projects are a natural part of the architecture. In multi-project execution: * Strategize must clarify which steps affect which projects. * Execution must isolate sandboxes per project OR define a composite sandbox. When multiple projects share the same resource, a single sandbox for that resource is used. * Apply must commit changes to each project separately, with separate approval records if necessary. * Tool resource bindings are resolved per-project — the same tool may bind to different resources depending on which project context it runs in. ### Namespaces !!! adr "Architecture Decision" The namespace system, resolution rules, and ownership model are defined in [ADR-002: Namespace System](adr/ADR-002-namespace-system.md). Namespaces define **ownership, scoping, and discoverability** of actors, tools, skills, resources, resource types, actions, projects, and plans. **All named entities use the format `/`.** #### Namespace Types | Namespace | Scope | Storage | Examples | |-----------|-------|---------|----------| | `local/` | Current machine only | Local database | `local/my-reviewer`, `local/test-action` | | `/` | Personal server namespace | Server database | `freemo/code-analyzer`, `jsmith/deploy-script` | | `/` | Organization namespace | Server database | `cleverthis/standard-review`, `acme/deploy-action` | | `openai/`, `anthropic/`, etc. | Built-in LLM actors | N/A (built-in) | `openai/gpt-4`, `anthropic/claude-3-opus` | #### Namespace Rules * **`local/`** * Reserved namespace for local-only items * Exists only on the current machine * Stored in local database * Fast iteration, no sharing * Default namespace when none specified * **`/`** (e.g., `freemo/`, `jsmith/`) * Personal namespace on the server * Created when user registers an account * Stored on server, synced when connected * Used for reusable entities (actions, actors, tools, skills, resources) a user wants across machines * Only the owning user can create/modify items * **`/`** (e.g., `cleverthis/`, `acme/`) * Organization namespace on the server * Created when organization is registered * Shared across team members * All namespaced entities (actions, actors, tools, skills, resources, projects) can be centrally managed * **Built-in Provider Namespaces** (`openai/`, `anthropic/`, `google/`, etc.) * Reserved for built-in LLM actors * Automatically available when API keys are configured * In server mode: available if logged in and server has keys * In local mode: requires environment variables or app configuration * Cannot be used for custom actors #### Server-qualified Names To disambiguate between servers (when connected to multiple): * `dev:freemo/code-coverage` (personal namespace on dev server) * `prod:cleverthis/deploy-action` (org namespace on prod server) This enables a pattern where: * local machine runs a lightweight client * server stores canonical definitions * multiple servers can coexist ### Actor !!! adr "Architecture Decision" The actor abstraction, actor types, and actor graph composition are defined in [ADR-010: Actor and Agent Architecture](adr/ADR-010-actor-and-agent-architecture.md). #### What an Actor Is !!! adr "Architecture Decision" The canonical definition of an actor — anything conversational, actor-as-graph principle, hierarchical composition, and the actor/agent distinction — is formalized in [ADR-031: Actor Abstraction Definition](adr/ADR-031-actor-abstraction-definition.md). An **actor** is the abstraction that generalizes "agent" into "anything conversational." !!! abstract "Actor at a Glance" * It can be as small as a ==single LLM agent==. * It can also be an ==entire graph== that itself calls other actors/tools. * Actors can be nested/hierarchical, enabling "orchestrator of orchestrators." **Every custom actor IS a graph** (a LangGraph defined via YAML configuration). Even a simple actor wrapping a single LLM is technically a graph with one node. #### Actor Naming Actors are **always named using `/` format**: ??? example "Naming Examples" | Name | Namespace | Description | | :--- | :-------- | :---------- | | `local/my-reviewer` | `local` | Local actor on this machine | | `freemo/code-analyzer` | `freemo` | Personal server actor | | `cleverthis/deploy-specialist` | `cleverthis` | Organization actor | | `openai/gpt-4` | `openai` | Built-in LLM actor | #### Actor Definition (YAML Configuration) Actors are defined via **YAML configuration files**. Tools and skills are also defined via their own YAML configuration files. YAML configuration is used for actors, tools, and skills (not for actions or projects). Example actor configuration (see `examples/` directory for full examples): 

name: local/my-workflow

cleveragents:
  version: "3.0"
  default_actor: workflow_controller

actors:
  # Simple LLM actor with skills referenced by name
  my_assistant:
    type: llm
    config:
      actor: openai/gpt-4 # Reference to built-in actor
      temperature: 0.7
      system_prompt: |
        You are a helpful assistant.
        Current task: {{ context.task_description }}
    skills:
      - local/file-ops               # Grants access to all tools in this skill
      - local/git-ops

  # LLM actor with a composite skill (includes many sub-skills)
  data_processor:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        You are a data processing assistant.
    skills:
      - local/data-toolkit           # A skill containing analysis + transformation tools

  # Actor referencing another actor
  reviewer:
    type: llm
    config:
      actor: local/code-reviewer # Reference to another custom actor
      memory_enabled: true
      max_history: 20
    skills:
      - local/file-ops
      - local/git-ops

routes:
  main_workflow:
    type: graph
    entry_point: start
    nodes:
      - name: analyze
        type: agent
        agent: my_assistant
      - name: process
        type: agent
        agent: data_processor
    edges:
      - source: start
        target: analyze
      - source: analyze
        target: process
      - source: process
        target: end

context:
  global:
    task_description: "Default task"
#### Jinja2 Template Preprocessing !!! adr "Architecture Decision" The two-phase Jinja2 + environment variable preprocessing pipeline for actor YAML files is defined in [ADR-032: Jinja2 YAML Template Preprocessing](adr/ADR-032-jinja2-yaml-template-preprocessing.md). Actor configuration YAML files are processed through a **two-phase pipeline** before the resulting data structure is validated and loaded: 1. **Phase 1 — Jinja2 Template Rendering**: The raw file content is run through a sandboxed Jinja2 template engine, resolving `{{ }}` expressions, `{% %}` control structures, and `{# #}` comments into static YAML text. 2. **Phase 2 — Environment Variable Interpolation**: After YAML parsing, all string values matching `${VAR}` or `${VAR:default}` are recursively replaced with OS environment variable values, with automatic type coercion. !!! warning "Execution Order" Jinja2 templates are evaluated **before** YAML parsing. Environment variables are interpolated **after** YAML parsing. The two phases are never interleaved. ##### Jinja2 Template Syntax The engine uses standard Jinja2 delimiters inside the YAML file: | Delimiter | Purpose | Example | |-----------|---------|---------| | `{{ ... }}` | Variable expression | `{{ context.paper_details.topic }}` | | `{% ... %}` | Block statement (`if`, `for`, `block`, etc.) | `{% if context.auto_finish_active %}` | | `{# ... #}` | Comment (stripped from output) | `{# This is ignored #}` | **Variable expressions** are used to inject dynamic values into prompts and configuration fields: ```yaml system_prompt: | You are writing a paper on {{ context.paper_details.topic | tojson }}. Target length: {{ context.paper_details.length | tojson }} words. Audience: {{ context.paper_details.audience | tojson }}. ``` **Conditional blocks** enable a single configuration to define behavior for multiple modes: ```yaml system_prompt: | You are a research assistant. {% if context.auto_finish_active %} Auto-finish mode is active. Do not ask questions. Proceed autonomously. {% else %} Engage in interactive conversation to refine the output. {% endif %} ``` **For loops** generate repetitive YAML structure from data: ```yaml system_prompt: | Available sections: {% for section in context.section_paths %} - {{ section }} {% endfor %} ``` ##### Sandboxed Execution All template rendering uses `jinja2.sandbox.SandboxedEnvironment`, which prevents templates from: - Executing arbitrary Python code - Accessing the filesystem - Calling `os.system`, `eval`, `exec`, or similar unsafe operations - Accessing private attributes of objects ##### Custom Jinja2 Filters The engine registers four custom filters in addition to all standard Jinja2 built-in filters: | Filter | Purpose | Example | |--------|---------|---------| | `yaml` | Serializes any value to a YAML-formatted string | `{{ my_dict \| yaml }}` | | `indent` | Indents text by N spaces (default 2) | `{{ content \| indent(4) }}` | | `sum` | Sums a numeric iterable | `{{ values \| sum }}` | | `selectattr` | Selects a named attribute from each item in a sequence | `{{ items \| selectattr('name') }}` | All standard Jinja2 built-in filters are also available, including: `tojson`, `default`, `lower`, `upper`, `trim`, `join`, `replace`, `length`, `first`, `last`, `sort`, `unique`, `map`, `reject`, `select`, `batch`, `slice`, `int`, `float`, `string`, `list`, `dictsort`, `escape`, `safe`, `truncate`, `wordwrap`, `center`, `format`, `title`, `capitalize`, `striptags`, `urlencode`, `abs`, `round`, `pprint`, `groupby`, `max`, `min`, `random`, `filesizeformat`, `wordcount`, `reverse`. ##### Exposed Built-in Functions The following safe Python built-in functions are exposed in the template context and can be called directly in expressions: | Function | Purpose | Example | |----------|---------|---------| | `range()` | Generates integer sequences | `{% for i in range(5) %}` | | `abs()` | Absolute value | `{{ abs(score) }}` | | `round()` | Rounds a number | `{{ round(value, 2) }}` | | `len()` | Length of a collection | `{{ len(items) }}` | | `min()` | Minimum value | `{{ min(scores) }}` | | `max()` | Maximum value | `{{ max(scores) }}` | | `sum()` | Sum of values | `{{ sum(counts) }}` | ##### Template Context Resolution Template variables are resolved from a context dictionary. The context supports a nested `context` key convention: - `{{ context.paper_details.topic }}` → resolves `context["paper_details"]["topic"]` - `{{ context.brainstorming_summary }}` → resolves `context["brainstorming_summary"]` The `global_context` top-level key in the actor configuration file populates this dictionary at load time. At runtime, the actor invocation context, plan context, and session context are merged with the following precedence: **runtime context > plan context > session context > global_context from YAML**. ##### Template Detection and Bypass The engine detects Jinja2 content by scanning for `{%` or `{{` markers in the raw text. Files without these markers bypass Jinja2 processing entirely and are parsed as plain YAML with zero template overhead. ##### Deferred Rendering When Jinja2 markers are present but no context is available at load time, the engine performs **deferred rendering**: it parses the YAML with template markers intact as literal strings. Templates are preserved in the parsed structure and rendered later when runtime context becomes available. This is the mechanism by which `system_prompt` fields retain their Jinja2 templates for runtime evaluation. ##### Template Protection for `system_prompt` Fields A special protection mechanism ensures Jinja2 syntax inside `system_prompt` fields survives the YAML loading process: 1. During loading, all Jinja2 delimiters in the raw file are temporarily replaced with sentinel markers: - `{{` → `<<>>` - `}}` → `<<>>` - `{%` → `<<>>` - `%}` → `<<>>` 2. The protected text is parsed as YAML. 3. After parsing, the sentinels are restored to Jinja2 syntax **only within `system_prompt` fields** (recursively through all nested dictionaries and lists). This allows system prompts to contain Jinja2 templates that are evaluated at **runtime** (when the actor's full context is available) rather than at file-load time. ##### YAML Post-Processing After Jinja2 rendering, the engine applies automatic post-processing to fix common issues: 1. **Blank line cleanup**: Removes extraneous blank lines generated by `{% %}` block tags between YAML keys. 2. **Multi-colon line splitting**: Detects and splits lines where template expansion produces multiple `key: value` pairs on a single line. 3. **Indentation correction**: Inserts indentation hints for `{% for %}` loops to ensure generated YAML maintains correct structure. ##### Environment Variable Interpolation After YAML parsing, all string values are recursively scanned for environment variable references: | Pattern | Behavior | |---------|----------| | `${VAR}` | Replaced with `os.environ["VAR"]`. Raises `ValueError` if not set. | | `${VAR:default}` | Replaced with `os.environ.get("VAR", "default")`. Uses default if not set. | **Automatic type coercion** is applied after substitution: | Substituted Value | Coerced Type | Example | |------------------|-------------|---------| | `"true"` / `"false"` (case-insensitive) | `bool` | `True` / `False` | | Digits only (with optional leading `-`) | `int` | `42`, `-7` | | Digits with single `.` | `float` | `3.14`, `-0.5` | | Anything else | `str` | Unchanged | This enables configurations like: ```yaml env_vars: WORK_DIR: ${HOME}/workspace # String: /home/user/workspace LOG_LEVEL: ${LOG_LEVEL:info} # String: info (default) MAX_RETRIES: ${MAX_RETRIES:3} # Integer: 3 (coerced from default) DEBUG: ${DEBUG_MODE:false} # Boolean: False (coerced from default) ``` Environment variable interpolation is applied recursively to all nested dictionaries and lists, ensuring resolution at any depth. #### Actor Arguments **All actors can receive arguments when invoked**, including built-in actors. Arguments are passed when: 1. An action is used on projects (arguments flow to strategy/execution actors) 2. An actor is directly invoked Arguments are injected into the actor's context and can be used in Jinja2 templates within prompts. For built-in actors (like `openai/gpt-4`), common arguments include: * `temperature` * `max_tokens` * `system_prompt` #### Actor Composition (Hierarchical References) Actors can reference other actors **by name**: ```yaml actors: complex_workflow: type: llm config: actor: local/base-analyzer # References another registered actor ``` **Load order matters**: Referenced actors must be loaded/defined before actors that depend on them. This enables hierarchical composition where: * Actor A's graph can include nodes that call Actor B (by name) * Actor B itself is a graph that might call Actor C * And so on (no depth limit) Circular actor references are **prohibited** and detected at registration time. #### Actor vs Agent (Relationship) !!! adr "Architecture Decision" The formal actor/agent distinction — actors as the general abstraction, agents as a specialized subset — is defined in [ADR-031: Actor Abstraction Definition](adr/ADR-031-actor-abstraction-definition.md). * **Agent**: an actor that is specifically an LLM with tools and reasoning behaviors. * **Actor**: may be an agent, but may also be: * a composite workflow, * a multi-step graph, * a wrapper around a third-party system (as long as it's "text in → text out" conversationally). #### Actor Definition Fields (Complete Reference) The complete set of fields available in an actor definition. For the formal JSON Schema and additional annotated examples, see [Actor Configuration Files](#actor-configuration-files) in the Configuration section. | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Namespaced actor name in `/` format. Used as the registered identity. | | `type` | string | Yes | Actor type: `llm` (language model), `tool` (tool collection), or `graph` (multi-node workflow). | | `description` | string | Yes | Human-readable description of what the actor does. | | `version` | string | No | Schema version (default: `"1.0"`). | | `model` | string | Yes (LLM/GRAPH) | LLM model identifier (e.g., `gpt-4`, `claude-3.5-sonnet`). | | `system_prompt` | string | No | System prompt text. Supports Jinja2 templates for dynamic content. | | `tools` | list | Yes (TOOL) | List of tool references (strings) and/or inline tool definitions. | | `context_view` | string | No | Role-based context filtering: `strategist`, `executor`, `reviewer`, or `full`. | | `memory` | object | No | Conversation history settings (see Memory Configuration below). | | `context` | object | No | File inclusion and context window settings (see Context Configuration below). | | `route` | object | Yes (GRAPH) | Graph topology (see Route Configuration below). | | `env_vars` | object | No | Environment variable key-value mappings. | | `skills` | list[string] | No | List of skill names this actor can use. Each entry is a namespaced skill name (e.g., `local/file-ops`). Skills provide tool capabilities to the actor. See [Actor References to Skills and Tools](#actor-references-to-skills-and-tools). | | `lsp` | list\|object | No | LSP server bindings for language intelligence. Can be a list of namespaced LSP server names (explicit binding), an object with `languages:` list (language-based binding), or an object with `auto: true` (resource-auto binding). See [LSP Integration](#lsp-integration). | | `lsp_capabilities` | list[string]\|`"all"` | No | Controls which LSP capabilities are exposed as tools. When omitted or `"all"`, all capabilities from bound servers are available. When a list, only the named capabilities are exposed (e.g., `[diagnostics, hover, definitions]`). | | `lsp_context_enrichment` | object | No | Controls automatic LSP context enrichment. Keys: `diagnostics` (bool, default `true`), `type_annotations` (bool, default `false`), `max_diagnostics_per_file` (int, default `50`). | **Additional fields available in the v2/runtime actor definition format** (within the `config:` block of actors defined inside the `actors:` top-level key): | Field | Type | Required | Description | |-------|------|----------|-------------| | `config.provider` | string | Yes (LLM) | LLM provider identifier: `openai`, `anthropic`, `google`, `azure`, `openrouter`, etc. | | `config.model` | string | Yes (LLM) | Model identifier within the provider. | | `config.actor` | string | No | Combined `provider/model` format (alternative to separate `provider` + `model`). | | `config.system_prompt` | string | No | System prompt text with Jinja2 template support. | | `config.temperature` | float | No | Sampling temperature (0.0 to 2.0). Lower = more deterministic. | | `config.max_tokens` | integer | No | Maximum tokens in the generated response. | | `config.memory_enabled` | boolean | No | Enable conversation memory (default: `false`). | | `config.max_history` | integer | No | Maximum conversation turns retained in memory (default: `50`). | | `config.unsafe` | boolean | No | Allow this actor to perform unsafe operations (default: `false`). | | `config.options` | object | No | Provider-specific options passed through to the underlying LLM API. | | `config.tools` | list | Yes (tool) | List of inline tool definitions (each with `name` and `code`). | | `config.response_format` | object | No | JSON schema for structured output from the LLM. | ##### Memory Configuration | Field | Type | Default | Description | |-------|------|---------|-------------| | `enabled` | boolean | `true` | Whether to maintain conversation history. | | `max_messages` | integer | `null` (unlimited) | Maximum number of messages to retain. | | `max_tokens` | integer | `null` (unlimited) | Maximum tokens in retained history. | | `summarize_old` | boolean | `false` | Whether to summarize old messages instead of discarding them. | ##### Context Configuration | Field | Type | Default | Description | |-------|------|---------|-------------| | `include_files` | list[string] | `[]` | File paths to include in the actor's context. | | `include_dirs` | list[string] | `[]` | Directory paths to include in the actor's context. | | `exclude_patterns` | list[string] | `[]` | Glob patterns to exclude from context (e.g., `"**/__pycache__/**"`). | | `max_context_tokens` | integer | `null` (model default) | Maximum size of the context window in tokens. | ##### Context View The `context_view` field controls role-based context filtering: | Value | Purpose | Includes | |-------|---------|----------| | `strategist` | High-level planning view | Project structure, goals, constraints, architectural summaries | | `executor` | Implementation view | Source code, file contents, specific task details | | `reviewer` | Validation view | Changes, diffs, test results, review criteria | | `full` | Complete view (use sparingly) | All available context from all categories | ##### Type-Specific Requirements | Actor Type | Required Fields | Optional Fields | |-----------|----------------|-----------------| | `llm` | `model` | `system_prompt`, `tools`, `context_view`, `memory`, `context`, `env_vars`, `lsp`, `lsp_capabilities`, `lsp_context_enrichment` | | `tool` | `tools` (at least one) | `context_view`, `env_vars` | | `graph` | `model`, `route` | `system_prompt`, `tools`, `context_view`, `memory`, `context`, `env_vars`, `lsp`, `lsp_capabilities`, `lsp_context_enrichment` | ##### Tool Definitions (Inline) Tools in an actor can be either **string references** to registered tools or **inline definitions**: ```yaml tools: # String reference to a registered tool - files/read_file - files/list_directory # Inline tool definition - name: utils/count_lines description: Count the number of lines in a file parameters: - name: file_path type: str description: Path to the file required: true default: null code: | def count_lines(file_path: str) -> int: with open(file_path, 'r', encoding='utf-8') as f: return len(f.readlines()) ``` Each inline tool parameter supports: | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Parameter name (must be a valid Python identifier). | | `type` | string | Yes | Python type annotation as string (e.g., `str`, `int`, `list[str]`). | | `description` | string | Yes | Human-readable description. | | `required` | boolean | No | Whether the parameter must be provided (default: `true`). | | `default` | any | No | Default value if not provided (only for optional parameters). | Inline tool `name` must follow the `namespace/tool_name` format. The `code` field contains Python source code that defines a callable function. ##### Route Configuration (Graph Topology) For `type: graph` actors, the `route` field defines the graph structure: | Field | Type | Required | Description | |-------|------|----------|-------------| | `nodes` | list[NodeDefinition] | Yes | All nodes in the graph. | | `edges` | list[EdgeDefinition] | Yes | All edges connecting nodes. | | `entry_node` | string | Yes | ID of the starting node. | | `exit_nodes` | list[string] | Yes | IDs of terminal nodes. | **Node Definition:** | Field | Type | Required | Description | |-------|------|----------|-------------| | `id` | string | Yes | Unique node identifier (alphanumeric with underscores/hyphens). | | `type` | string | Yes | Node type: `agent`, `tool`, `conditional`, or `subgraph`. | | `name` | string | Yes | Human-readable node name. | | `description` | string | Yes | Node purpose and behavior. | | `config` | object | No | Type-specific configuration (see below). | **Node type-specific config:** | Node Type | Config Fields | Description | |-----------|---------------|-------------| | `agent` | `model`, `prompt`, `tools` | LLM agent with optional tools | | `tool` | `tool_name`, `parameters` | Deterministic tool execution | | `conditional` | `conditions[].check`, `conditions[].route_to` | Routes based on state conditions (Python expressions) | | `subgraph` | `actor_path` | Embeds another actor as a nested workflow | **Edge Definition:** | Field | Type | Required | Description | |-------|------|----------|-------------| | `from_node` | string | Yes | Source node ID. | | `to_node` | string | Yes | Target node ID. | | `condition` | string | No | Python expression for conditional routing. | | `priority` | integer | No | Edge priority for multiple outgoing edges (higher = evaluated first, default: `0`). | **Graph Validation:** - All node IDs must be unique within the graph. - The `entry_node` must reference an existing node ID. - All `exit_nodes` must reference existing node IDs. - All edge `from_node` and `to_node` must reference existing node IDs. - The graph must be **acyclic** — cycles are detected via DFS and rejected at validation time. - All nodes must be reachable from the entry node. #### Actor Composition and Graphs !!! adr "Architecture Decision" Hierarchical actor composition, the actor-as-graph principle, and graph node types are defined in [ADR-031: Actor Abstraction Definition](adr/ADR-031-actor-abstraction-definition.md). Actors can reference: * other actors (by namespaced name) * skills (by namespaced name — all tools from referenced skills become available) * subgraphs This is central to enabling both: * multi-agent orchestration, and * modular reuse of workflows. #### Nodes in the Graph: Actors and Tools !!! adr "Architecture Decision" The two graph node types (actor nodes and tool nodes) and their relationship to the skill and tool systems are defined in [ADR-031: Actor Abstraction Definition](adr/ADR-031-actor-abstraction-definition.md) and [ADR-030: Skill Abstraction Definition](adr/ADR-030-skill-abstraction-definition.md). Graph nodes can be any of: * an **actor** (another LLM agent or composite workflow, referenced by name), * a **tool node** — a deterministic, non-LLM step that directly invokes a tool. Tool nodes can: * **Reference a named registered tool** by its fully-qualified name (e.g., `tool: local/run-migrations`). The tool must be registered in the Tool Registry via `agents tool add`. Metadata can optionally be overridden at the point of use. * **Define an anonymous inline tool** using the same format as a tool YAML body (with `anonymous: true`). This is useful for one-off, workflow-specific operations that don't warrant separate registration. This is a powerful simplification: actors provide intelligence, tools provide capability (both as graph nodes and through skills for LLM tool-calling), and skills organize tools into reusable collections. Everything participates in the same graph. **Tool node with named tool reference:** 

nodes:
  - name: run_db_migrate
    type: tool
    tool: local/run-migrations # Named tool from Tool Registry
    override:                           # Optional metadata override
      capability:
        human_approval_required: true

  - name: spawn_tests
    type: tool
    tool: local/create-subplan # Another named tool
**Tool node with anonymous inline tool:** 

nodes:
  - name: custom_validation
    type: tool
    anonymous: true
    description: "Validate output format before proceeding"
    input_schema:
      type: object
      properties:
        data: { type: object }
    capability:
      read_only: true
    code: |
      # Inline Python — same format as a named tool YAML body
      if not params["data"].get("status"):
          raise ValueError("Missing status field")
      return {"valid": True}
#### LSP Integration !!! adr "Architecture Decision" The Language Server Protocol integration architecture — LSP Registry, actor LSP binding, capability exposure, and server lifecycle — is defined in [ADR-027: Language Server Protocol (LSP) Integration](adr/ADR-027-language-server-protocol.md). Actors that perform software development tasks — writing code, refactoring, reviewing, debugging — benefit from **language intelligence**: the ability to understand types, navigate symbol definitions, discover references, identify compilation errors, and comprehend the structural relationships within a codebase. The **Language Server Protocol (LSP)** is the standard for this kind of intelligence, and CleverAgents integrates LSP servers directly into the actor runtime so that agents gain the same semantic code understanding that human developers enjoy in their IDEs. !!! abstract "LSP at a Glance" * LSP servers are registered in a global **LSP Registry** (namespaced like tools, skills, and actors). * Actors bind LSP servers via their YAML configuration — explicitly by name, by language, or automatically based on project resources. * Different nodes in an actor's graph can have different LSP bindings. * LSP capabilities are exposed as **tools** (via `LSPToolAdapter`) and as **context enrichment** (diagnostics/type info injected into ACMS hot context). * The **LSP Runtime** in the Infrastructure layer manages server lifecycle, workspace mapping, and file synchronization. ##### LSP Registry Language servers are registered as first-class entities in the global **LSP Registry**, following the same patterns as the Tool Registry, Skill Registry, and Actor Registry. Each entry defines a language server — its command, the languages it covers, its capabilities, and any initialization options. LSP entries are: - **Namespaced** as `[[server:]namespace/]name` (e.g., `local/pyright`, `local/clangd`, `cleverthis/rust-analyzer`). - **Defined via YAML configuration** and registered with `agents lsp add --config `. - **Managed** via `agents lsp list`, `agents lsp show`, `agents lsp remove`. Example LSP configuration: 

name: local/pyright
description: "Pyright language server for Python type checking and intelligence"

command: pyright-langserver
args: ["--stdio"]
transport: stdio

languages:
  - python

capabilities:
  - diagnostics
  - hover
  - completions
  - definitions
  - references
  - rename
  - code_actions
  - formatting
  - signature_help
  - document_symbols
  - workspace_symbols

initialization:
  python:
    pythonPath: "${PYTHON_PATH:/usr/bin/python3}"
    analysis:
      typeCheckingMode: "basic"
      autoSearchPaths: true
LSP configuration fields: | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Namespaced identifier (`/`). | | `description` | string | No | Human-readable description of the language server. | | `command` | string | Yes | Executable command to launch the language server process. | | `args` | list[string] | No | Command-line arguments for the server process. | | `transport` | string | No | Communication transport: `stdio` (default) or `tcp`. | | `languages` | list[string] | Yes | Programming languages this server provides intelligence for (e.g., `python`, `typescript`, `rust`). | | `capabilities` | list[string] | No | Explicit list of LSP capabilities this server provides. When omitted, capabilities are auto-discovered from the server's `initialize` response. | | `initialization` | object | No | LSP `initializationOptions` sent during the `initialize` handshake. Supports `${ENV_VAR}` interpolation. | | `workspace_settings` | object | No | LSP workspace configuration sent via `workspace/didChangeConfiguration`. | ##### Resource Language Discovery Resources attached to projects represent codebases, file trees, and repositories that contain source code in one or more programming languages. The system determines what languages a resource contains through a layered discovery process: 1. **File extension analysis** — File extensions (`.py`, `.ts`, `.rs`, `.go`, `.cpp`, etc.) are mapped to language identifiers using a built-in extension-to-language table. This is the fastest and most common method. 2. **Content analysis** — For files without extensions or with ambiguous extensions, content markers are inspected: shebang lines (`#!/usr/bin/env python3`), magic comments, and structural patterns. 3. **UKO classification** — The Universal Knowledge Ontology classifies resources at the technology-specific layer (Python, TypeScript, Rust, etc.), providing semantic language identification that persists across sessions. 4. **Explicit project-level declaration** — Projects may explicitly declare their languages via configuration, overriding or supplementing automatic discovery. Language discovery results are cached per resource and invalidated when content changes. ##### Actor LSP Binding Actors declare LSP dependencies in their YAML configuration via the `lsp:` field. Three binding modes are supported, from fully explicit to fully automatic: **Explicit binding** (by server name): 

actors:
  code_analyst:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        You are a Python code analyst. Use LSP tools to understand
        type information and identify issues in the codebase.
    skills:
      - local/file-ops
    lsp:
      - local/pyright
      - local/ruff-lsp
**Language-based binding** (runtime resolves servers from registry): 

actors:
  polyglot_reviewer:
    type: llm
    config:
      actor: openai/gpt-4
    lsp:
      languages:
        - python
        - typescript
        - rust
**Resource-auto binding** (auto-discover from project resources): 

actors:
  universal_developer:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        You are a software developer.
    lsp:
      auto: true
When `auto: true` is set, the runtime inspects the project's bound resources via language discovery, determines which languages are present, and binds the appropriate LSP servers automatically. This is the most reusable pattern — an actor configured with `lsp: { auto: true }` works correctly regardless of the language of the project it is assigned to. **Jinja2 dynamic binding** (template-driven resolution): 

actors:
  dynamic_analyst:
    type: llm
    config:
      actor: openai/gpt-4
    lsp:
      {% for lang in context.project_languages %}
      - {{ lsp_registry.for_language(lang) | first }}
      {% endfor %}
Template variables available during LSP resolution: | Variable | Type | Description | |----------|------|-------------| | `lsp_registry` | object | The LSP Registry. Supports `.for_language(lang)` returning matching server names and `.all()` returning all entries. | | `context.project_languages` | list[string] | Languages detected in the current project's resources. | | `context.resource_languages` | list[string] | Languages detected in the specific resource being processed. | ##### Per-Node LSP Binding Different nodes in an actor's graph can have different LSP configurations. This allows fine-grained control — for example, giving a strategy actor read-only diagnostics while giving an execution actor full LSP capabilities: 

actors:
  strategy_planner:
    type: llm
    config:
      actor: openai/gpt-4
      system_prompt: |
        Plan the implementation strategy. Use LSP diagnostics
        to assess codebase health before proposing changes.
    lsp:
      - local/pyright
    lsp_capabilities:           # Restrict to read-only
      - diagnostics
      - hover
      - definitions
      - references

  code_implementer:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        Implement code changes. Use full LSP capabilities
        for navigation, diagnostics, and refactoring.
    lsp:
      auto: true
    lsp_capabilities: all       # Full capabilities (default)

routes:
  dev_workflow:
    type: graph
    entry_point: plan
    nodes:
      - name: plan
        type: agent
        agent: strategy_planner
      - name: implement
        type: agent
        agent: code_implementer
    edges:
      - source: plan
        target: implement
      - source: implement
        target: end
The `lsp_capabilities` field controls which LSP features are exposed to the actor as tools. When omitted or set to `all`, every capability declared by the bound LSP servers is available. ##### LSP Capability Exposure LSP capabilities reach actors through two complementary mechanisms: **As Tools (via LSPToolAdapter)** The `LSPToolAdapter` is an Infrastructure-layer adapter (analogous to `MCPToolAdapter` for MCP) that translates LSP server capabilities into CleverAgents tools. When an actor with LSP bindings activates, the adapter generates tool definitions for each exposed capability and injects them into the actor's tool surface alongside skill-provided tools. Available LSP tools: | Capability | LSP Method | Tool Name | Description | |-----------|-----------|-----------|-------------| | `diagnostics` | `textDocument/publishDiagnostics` | `lsp/diagnostics` | Retrieve compilation errors, warnings, and hints for a file | | `hover` | `textDocument/hover` | `lsp/hover` | Get type information and documentation at a position | | `completions` | `textDocument/completion` | `lsp/completions` | Get code completion suggestions at a position | | `definitions` | `textDocument/definition` | `lsp/definition` | Go to the definition of a symbol | | `references` | `textDocument/references` | `lsp/references` | Find all references to a symbol | | `rename` | `textDocument/rename` | `lsp/rename` | Compute a rename refactoring across files | | `code_actions` | `textDocument/codeAction` | `lsp/code-actions` | Get available code actions (quick fixes, refactors) | | `formatting` | `textDocument/formatting` | `lsp/format` | Format a document according to language conventions | | `signature_help` | `textDocument/signatureHelp` | `lsp/signature` | Get function signature information at a call site | | `document_symbols` | `textDocument/documentSymbol` | `lsp/symbols` | List all symbols (classes, functions, variables) in a file | | `workspace_symbols` | `workspace/symbol` | `lsp/workspace-symbols` | Search for symbols across the entire workspace | When multiple LSP servers are bound to an actor (e.g., `local/pyright` for Python and `local/typescript-lsp` for TypeScript), the tool adapter routes requests to the appropriate server based on the file's detected language. The tool names remain the same — routing is transparent to the actor. **As Context Enrichment** In addition to explicit tool calls, LSP servers can automatically enrich the actor's context: - **Diagnostic injection**: When a source file enters the actor's hot context, the LSP server's diagnostics for that file are appended as structured annotations. The actor "sees" type errors, unused imports, and other issues without explicitly calling `lsp/diagnostics`. - **Type annotation overlay**: Hover information for key symbols (function signatures, class hierarchies, variable types) can be pre-fetched and included as context metadata. Context enrichment is controlled per actor: 

actors:
  enriched_reviewer:
    type: llm
    config:
      actor: openai/gpt-4
    lsp:
      auto: true
    lsp_context_enrichment:
      diagnostics: true                # Auto-inject diagnostics (default: true)
      type_annotations: false           # Auto-inject type info (default: false)
      max_diagnostics_per_file: 50     # Limit to avoid context bloat
##### LSP Server Lifecycle LSP servers are managed by the **LSP Runtime** in the Infrastructure layer: 1. **Startup** — When an actor with LSP bindings activates (for a plan phase or `agents actor run`), the LSP Runtime starts the required language server processes. Each server is initialized with the `initialize` LSP handshake, passing `initializationOptions` from the registry entry and workspace root paths mapped from bound resources. 2. **Workspace Mapping** — LSP workspace roots correspond to registered resource physical paths. When the actor operates within a sandbox (Execute phase), the sandbox's working directory is used as the workspace root, ensuring the language server analyzes sandboxed code — not the original. 3. **File Synchronization** — As the actor reads and modifies files (via tools), the LSP Runtime sends `textDocument/didOpen`, `textDocument/didChange`, and `textDocument/didClose` notifications to keep the language server's view synchronized with the actor's mutations. 4. **Shared Instances** — If multiple actors in the same plan or session require the same language server for the same workspace, the LSP Runtime shares a single server instance. Reference counting ensures the server stays alive as long as at least one actor needs it. 5. **Shutdown** — When the actor deactivates (plan phase completes, session ends), the LSP Runtime sends `shutdown` and `exit` lifecycle messages. Shared instances shut down only when the last referencing actor deactivates. 6. **Crash Recovery** — If a language server process crashes, the LSP Runtime restarts it automatically, re-sends the `initialize` handshake, re-opens tracked documents, and resumes operations without disrupting the actor's execution. ##### LSP in the Plan Lifecycle LSP integration enhances each phase of the plan lifecycle: | Phase | LSP Role | Example Use | |-------|---------|-------------| | **Strategize** | Read-only intelligence — diagnostics, type information, and symbol navigation inform strategy decisions | Strategy actor calls `lsp/diagnostics` to assess codebase health, `lsp/symbols` to understand module structure, `lsp/references` to gauge impact of proposed changes | | **Execute** | Full intelligence — all capabilities available during code generation and modification | Execution actor calls `lsp/definition` to understand APIs before using them, `lsp/diagnostics` to verify changes compile, `lsp/rename` to perform safe refactorings | | **Apply** | Validation intelligence — diagnostics confirm the final changeset is clean | Apply-phase validations invoke `lsp/diagnostics` on all modified files to ensure no regressions before merge | ##### Comparison with MCP LSP and MCP are both standard protocols for external capability servers integrated into the actor runtime: | Aspect | MCP (Model Context Protocol) | LSP (Language Server Protocol) | |--------|------------------------------|-------------------------------| | **Purpose** | General-purpose tool discovery and invocation | Language-specific code intelligence | | **Scope** | Any callable operation (file I/O, API calls, data queries) | Code analysis capabilities (diagnostics, navigation, completions) | | **Registry** | Tool Registry (via `MCPToolAdapter`) | LSP Registry (via `LSPToolAdapter`) | | **Binding** | Skills compose MCP tools; actors acquire via skill references | Actors bind LSP servers directly via `lsp:` configuration | | **Tool generation** | Tools pre-defined by MCP server, registered at discovery | Tools generated dynamically from LSP server capabilities at activation | | **Lifecycle** | Managed by MCP SDK connection lifecycle | Managed by LSP Runtime with workspace mapping and file synchronization | Both adapters follow the same architectural pattern: a standard protocol server in the Infrastructure layer is bridged into the actor's tool surface through a typed adapter. The key difference is that MCP tools are general-purpose and explicitly authored, while LSP tools are language-specific and automatically derived from the protocol's capability model. #### Multi-Actor Configuration File (Complete Structure) A single actor configuration YAML file can define an entire multi-actor system — multiple actors, graph routing, stream processing, context sharing, and message routing — all in one file. This is the format used for complex workflows like the scientific paper writer. ##### Top-Level Keys | Key | Type | Required | Description | |-----|------|----------|-------------| | `name` | string | Yes | Namespaced actor name (`/`). | | `cleveragents` | object | No | Metadata: version, logging, template engine, safety, default actor. | | `actors` (or `agents`) | object | Yes | Map of actor names to definitions. Both key names are accepted. | | `routes` | object | No | Map of route names to stream or graph topology definitions. | | `merges` | list | No | Stream merge operations combining multiple sources into one target. | | `splits` | list | No | Stream split operations dividing one source into multiple targets. | | `publications` | list | No | Output stream names (e.g., `["__output__"]`). | | `templates` | object | No | Reusable template definitions for Jinja2 inheritance. | | `instances` | object | No | Instantiated templates with bound parameters. | | `global_context` | object | No | Key-value pairs accessible to all actors via `{{ context.key }}`. | | `context` | object | No | Alternative context block with `global:` sub-key. | | `prompts` | object | No | Named prompt templates referenceable by actors. | | `pipelines` | object | No | Hybrid pipeline definitions combining stream and graph stages. | ##### `cleveragents` Metadata Block ```yaml cleveragents: version: "3.0" # Schema version (default: "3.0") logging: level: "INFO" # DEBUG, INFO, WARNING, ERROR (default: INFO) template_engine: "JINJA2" # JINJA2 or NONE (default: JINJA2) unsafe: false # Allow unsafe operations (default: false) default_actor: my_actor # Default actor when multiple defined ``` ##### Route Definitions Routes connect actors via **stream** or **graph** topologies: **Stream Routes** — reactive processing pipelines: ```yaml routes: chat_stream: type: stream stream_type: cold # cold (default), hot, or replay operators: - type: map # map or graph_execute params: agent: chat_agent # Actor name for map operators publications: - __output__ # Output stream name subscriptions: - __input__ # Input stream name buffer_size: 10 # Stream buffer size (default: 10) initial_value: null # Initial value (optional) ``` **Graph Routes** — LangGraph-based directed graph workflows: ```yaml routes: main: type: graph entry_point: start # Entry node name (required) nodes: start: type: START # Special start node end: type: END # Special end node router: type: message_router # Message-based routing node rules: # Routing rules (see below) - ... my_actor_node: type: agent # Actor-backed node agent: my_actor # References actor by name metadata: {} # Optional metadata edges: - source: start target: router - source: router target: my_actor_node condition: context_value: next_node equals: my_actor_node - source: my_actor_node target: end checkpointing: false # Enable checkpointing (default: false) checkpoint_dir: null # Checkpoint storage directory enable_time_travel: false # Enable time travel debugging (default: false) parallel_execution: false # Allow parallel node execution (default: false) state_class: null # Custom state class name ``` ##### Graph Node Types | Type | Purpose | Key Fields | |------|---------|------------| | `agent` | Node backed by an actor | `agent: ` | | `tool` | Node invoking tools | `tools: [, ...]` | | `function` | Node backed by a Python function | `function: ` | | `conditional` | Branching node | `condition: { ... }` | | `subgraph` | Delegates to another graph route | `subgraph: ` | | `start` / `START` | Explicit start node | (none) | | `end` / `END` | Terminal node | (none) | | `message_router` | Content-based message routing | `rules: [...]` | ##### Message Router Node The `message_router` node type routes messages to different actors based on message content. It uses a rules-based system: ```yaml router: type: message_router rules: # Prefix-based routing - type: prefix match: "GOTO_BRAINSTORMING" target: brainstorming strip_match: true # Remove the prefix before forwarding # Contains-based routing - type: contains match: "SET_TOPIC:" target: discovery # Suffix-based routing (catch-all) - type: suffix match: "" # Empty string matches everything target: workflow_controller ``` Each rule specifies: | Field | Type | Description | |-------|------|-------------| | `type` | string | Match type: `prefix`, `contains`, or `suffix`. | | `match` | string | Pattern to match against the message content. | | `target` | string | Node name to route the message to. | | `strip_match` | boolean | Whether to strip the matched pattern from the message (default: `false`). | Rules are evaluated in order; the first matching rule determines the target node. ##### Routing Prefixes (Inter-Actor Communication) Actors communicate with each other and the routing system via **routing prefixes** — special string prefixes prepended to output text that the message router interprets: | Prefix Pattern | Purpose | Example | |----------------|---------|---------| | `GOTO_:` | Route to a specific node | `GOTO_BRAINSTORMING:Start the brainstorm` | | `SET_:` | Set a context field value | `SET_TOPIC:Quantum computing` | | `ROUTE_:` | Route to a sub-target | `ROUTE_ASK_TOPIC:What topic?` | | `COMMAND_OUTPUT:` | Display output directly to user | `COMMAND_OUTPUT:Help text here` | | `DISCOVERY_RESPONSE:` | Response from discovery stage | `DISCOVERY_RESPONSE:Topic set` | Tool actors return these prefixes as their `result` variable. The message router parses the prefix and routes accordingly. The message content after the colon is forwarded to the target node. ##### Conditional Edges Graph edges can include conditions that control routing based on graph state: ```yaml edges: # Unconditional edge - source: start target: router # Conditional edge — routes based on context value - source: router target: brainstorming condition: context_value: next_node equals: brainstorming # Conditional edge — routes based on boolean flag - source: passthrough target: auto_driver condition: context_value: auto_finish_active equals: true ``` ##### Merges and Splits **Merges** combine multiple input streams into a single stream: ```yaml merges: - sources: [__input__] # Special __input__ = user input target: main # Route name to send merged input to ``` **Splits** divide a single stream into multiple output streams: ```yaml splits: - source: main_output targets: [log_stream, display_stream] ``` Special stream names: - `__input__` — the user's input - `__output__` — the final output displayed to the user ##### Inline Tool Code Model Tool-type actors define their behavior entirely in inline Python code within the `code:` field: ```yaml my_tool_actor: type: tool config: tools: - name: my_tool code: | import sys # Available variables: # input_data — the input text/message passed to this tool # context — shared mutable context dictionary # result — set this variable to define the tool's output msg = input_data or '' context['last_input'] = msg if msg.startswith('!help'): result = "COMMAND_OUTPUT:Available commands: !help, !next" else: result = f"GOTO_PROCESSOR:{msg}" print(f"DEBUG: {result}", file=sys.stderr) ``` The inline code execution model provides three implicit variables: | Variable | Type | Description | |----------|------|-------------| | `input_data` | string | The input text/message passed to the tool. | | `context` | dict | Shared mutable context dictionary. Changes persist across invocations. | | `result` | string | **Set this variable** to define the tool's output. | The `context` dictionary is the primary mechanism for inter-actor state sharing. All actors in the same configuration share the same context, enabling data flow between stages. ##### Context Sharing The `context` dictionary (accessible in tool code and Jinja2 templates) serves as shared state: ```yaml # Set via global_context in YAML: global_context: writing_stage: intro paper_details: topic: null length: null audience: null # Or via context.global: context: global: conversation_mode: true default_actor: openai/gpt-4 ``` At runtime, tool actors read and modify context freely: ```python # In tool code: context['writing_stage'] = 'brainstorming' # Update stage topic = context.get('paper_details', {}).get('topic') # Read nested value context.setdefault('history', []).append(msg) # Append to list ``` In Jinja2 templates (system prompts): ```yaml system_prompt: | Paper topic: {{ context.paper_details.topic | tojson }} {% if context.auto_finish_active %} Proceed autonomously. {% endif %} ``` ##### Stream-to-Graph Bridge Routes can include bridge configuration for dynamic topology changes: ```yaml routes: adaptive: type: stream bridge: upgrade_conditions: message_count_threshold: 5 downgrade_conditions: idle_timeout: 30 state_extractor: "extract_graph_state" state_flattener: "flatten_to_stream" preserve_subscriptions: true preserve_checkpointing: true ``` ##### Publications The `publications` key defines output streams at the route or top level: ```yaml # Route-level publications routes: chat_stream: type: stream publications: - __output__ # Top-level publications publications: - __output__ ``` #### Actor Configuration File Loading Actor configuration files can be loaded from either JSON or YAML format: 1. The loader first attempts JSON parsing (`json.loads`) 2. If JSON parsing fails, it falls back to the YAML pipeline (Jinja2 preprocessing + `yaml.safe_load` + environment variable interpolation) The resolution order for `provider` and `model` values when loading: 1. CLI override (`--provider`, `--model`) 2. Top-level `provider` / `model` keys 3. Top-level `provider_type` / `model_id` aliases 4. v2-extracted values from `actors..config.provider` / `.model` For `unsafe` flag: the result is `true` if **any** of the following is `true`: the top-level `unsafe` key, the v2-extracted `unsafe` flag, or the CLI `--unsafe` flag. ### Agent !!! adr "Architecture Decision" The agent specialization and its relationship to the actor abstraction are defined in [ADR-010: Actor and Agent Architecture](adr/ADR-010-actor-and-agent-architecture.md). #### Agent Definition In CleverAgents, an **agent** is a specialized actor with: * a conversational interface, * tool-calling capability, * potentially memory, planning heuristics, and role identity. Examples of agent roles: * planner/architect (strategy actor) * coder/implementer (execution actor) * reviewer/qa agent * release/apply agent The transcript explicitly discusses role separation like planner/coder/reviewer in context views/memory proposals. #### Agent Behavior Configuration Agents should be configurable without code changes: * prompt templates * tool sets * safety constraints * style constraints (verbosity, code style) * reliability controls (self-checks, validations) A design goal is user empowerment: "users customize LLM behavior without modifying core code." ### Tools !!! adr "Architecture Decision" The tool system, tool adapter layer, and tool lifecycle are defined in [ADR-011: Tool System](adr/ADR-011-tool-system.md). #### What a Tool Is A **tool** is a namespaced, independently registered, callable operation. It is the ==atomic unit of execution== in CleverAgents — the smallest piece of functionality that can read, write, or transform resources. Tools are defined in their own YAML configuration files, managed through the `agents tool` CLI commands, and registered in the **Tool Registry**. Tools follow the same `/` naming convention as actors, skills, and other entities (e.g., `local/run-migrations`, `cleverthis/validate-api`, `local/create-subplan`). They support optional server-qualified prefixes for multi-server disambiguation (e.g., `dev:freemo/custom-analysis`). **Validation as a Tool subtype**: A **Validation** is a specialized subtype of Tool that extends the Tool class with validation-specific metadata (`mode`: required/informational) and a structured JSON return format (`{ "passed": bool, "message": string, "data": object }`). Because Validation extends Tool via standard class inheritance, it inherits all base properties and behaviors — registration, resource bindings, lifecycle hooks, capability metadata, source types (custom, MCP, agent_skill, builtin, and the validation-specific `wrapped` source for Validations that delegate to an existing Tool), and the ability to exist as a tool node in an actor graph. A Validation can also **wrap** an existing plain Tool via the `wraps` field, reusing the Tool's implementation and interpreting its output through a `transform` function — see the **Tool Wrapping** subsection under Core Concepts > Validation for details. !!! note "Key Constraints on Validations" - **Always read-only**: Validations observe and report but ==never modify resources==. `writes` is always `false` and `checkpointable` is always `false`. - **Shared namespace**: Validations and plain Tools share the same naming namespace in the Tool Registry. A name conflict results in an error. - **Superset/subset semantics**: A Validation can be used anywhere a Tool is expected (since it IS a Tool), but not vice versa. - **Unified management**: Listed via `agents tool list --type validation`, inspected via `agents tool show`, removed via `agents tool remove`. Only `add`, `attach`, and `detach` have validation-specific CLI commands. Validations can be attached to resources directly, or to resources through projects or plans. The same mechanisms used to determine what tools can operate on what resources carry over to determining what validations apply to a particular resource. See the **Validation** section (immediately following this Tools section) for full details on the Validation type system, modes, attachment scoping, failure handling, and data model. #### The Dual Role of Tools Tools serve two distinct roles in CleverAgents: 1. **As components of a Skill**: A skill references tools by name to assemble a reusable capability collection. When an actor references a skill, all of that skill's tools (including those from included child skills) become available to the actor's LLM agent for tool-calling. 2. **As tool nodes in an Actor graph**: An actor's graph definition can include `type: tool` nodes that directly invoke a specific tool. This is used for deterministic, non-LLM steps in a workflow — e.g., spawning a child plan, running validation, or executing a migration. The tool node either references a named registered tool or defines an anonymous inline tool. ```kroki-mermaid block-beta columns 3 space:3 block:header:3 A["Tool: Dual Role"] end space:3 block:role1:1 B["Role 1: In a Skill"] C["Skill: local/devops"] D["tools:"] E[" - local/run-migrations"] F[" - local/validate-schema"] G["(tool-calling by LLM)"] end space:1 block:role2:1 H["Role 2: In an Actor Graph"] I["Actor Graph node:"] J[" name: run_db"] K[" type: tool"] L[" tool: local/run-migrations"] M["(deterministic invoke)"] end ``` #### Tool Configuration (YAML) Tools are defined in their own YAML configuration files, separate from skills and actors. A tool YAML file declares the tool's identity, schema, capability metadata, and implementation: 

# File: tools/run-migrations.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/run-migrations
  description: "Run database migrations for the API service"

  source: custom # mcp | agent_skill | builtin | custom

  # Resource bindings — what resources this tool needs access to
  resources:
    db:
      type: local/database
      access: read_write
      required: true
      description: "Target database for migrations"

  input_schema:
    type: object
    properties:
      direction:
        type: string
        enum: [up, down]
      count:
        type: integer
        default: 1
    required: [direction]

  capability:
    writes: true
    write_scope:
      resource_slots: [db] # References the "db" resource slot
    checkpointable: true
    checkpoint_scope: transaction
    side_effects: [schema_mutation]

  code: |
    import subprocess
    direction = params["direction"]
    count = params.get("count", 1)
    db = ctx.resources["db"]          # Access the bound database resource
    result = subprocess.run(
        ["alembic", direction, str(count)],
        capture_output=True, text=True, cwd=db.sandbox.root
    )
    return {"stdout": result.stdout, "returncode": result.returncode}
Another example — a tool that wraps an MCP server endpoint: 

# File: tools/create-github-issue.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/create-github-issue
  description: "Create a GitHub issue via MCP"

  source: mcp
  mcp_server:
    command: "npx @anthropic/mcp-github"
    env:
      GITHUB_TOKEN: "${GITHUB_TOKEN}"
    tool_name: create_issue # The tool name as exposed by the MCP server

  capability:
    writes: true
    write_scope: [github:issues]
    checkpointable: false
And an Agent Skill tool: 

# File: tools/deploy-staging.yaml
cleveragents:
  version: "3.0"

tool:
  name: local/deploy-staging
  description: "Deploy the current branch to the staging environment"

  source: agent_skill
  agent_skill:
    path: ./skills/deploy-to-staging
    sandbox_policy: container
    allowed_tools: ["Bash(docker:*)", "Bash(kubectl:*)", "Read"]

  capability:
    writes: true
    checkpointable: false
    side_effects: [deploy, infrastructure]
#### Tool Registration and Management Tools are managed through the `agents tool` CLI commands: 

# Register a new tool from its YAML configuration
agents tool add --config ./tools/run-migrations.yaml

# Update an existing tool (re-reads the config file, overwrites registration)
agents tool add --config ./tools/run-migrations.yaml --update

# List all registered tools
agents tool list

# Show details for a tool (schema, capability, references)
agents tool show local/run-migrations

# Remove a tool
agents tool remove local/run-migrations
Once registered, a tool is available to be referenced by skills (in their `tools` list) and by actor graphs (as `type: tool` nodes). Tools persist in the database (local or server) and follow the same namespace rules as actors and skills. #### Anonymous Tools An **anonymous tool** is an inline tool definition that appears directly in a skill YAML or an actor graph node. Anonymous tools use the **same format** as a named tool's YAML definition (same `input_schema`, `capability`, and `code` fields) but lack a namespaced name. They are: * **Not registered** in the Tool Registry * **Not reusable** — they exist only within the YAML file where they are defined * **Useful for one-off operations** that are too specific to warrant separate registration Anonymous tools in a skill YAML: 

skill:
  name: local/my-skill
  tools:
    - local/run-migrations          # Named tool reference
    - local/validate-api-compat     # Named tool reference

  anonymous_tools:                  # Inline definitions, same format as tool YAML
    - description: "One-off data cleanup for this project"
      input_schema:
        type: object
        properties:
          table: { type: string }
      capability:
        writes: true
        checkpointable: true
      code: |
        # ... Python code ...
        return {"cleaned": count}
Anonymous tools in an actor graph node: 

nodes:
  - name: custom_step
    type: tool
    anonymous: true
    description: "Inline validation specific to this workflow"
    input_schema:
      type: object
      properties:
        data: { type: object }
    capability:
      read_only: true
    code: |
      # ... Python code ...
      return {"valid": True}
The anonymous tool format is intentionally identical to the body of a named tool YAML — this means promoting an anonymous tool to a named, registered tool is a simple copy-paste into its own YAML file and `agents tool add`. #### Metadata Overrides When referencing a named tool in a skill or actor graph, its registered metadata can optionally be **overridden** at the point of use. This allows context-specific adjustments without modifying the tool's global registration. **Overriding tool metadata in a skill:** 

skill:
  name: local/strict-devops
  tools:
    - name: local/run-migrations
      override:
        capability:
          human_approval_required: true # Override: require approval in this skill
          write_scope: [database:staging] # Override: restrict scope for this context

    - local/validate-api-compat            # No overrides, use as registered
**Overriding tool metadata in an actor graph node:** 

nodes:
  - name: safe_migrate
    type: tool
    tool: local/run-migrations
    override:
      capability:
        human_approval_required: true
**Overriding tool metadata when including a sub-skill:** When a skill includes another skill (importing all its tools), individual tools from the included skill can have their metadata overridden: 

skill:
  name: local/production-ops
  includes:
    - name: local/devops-toolkit
      tool_overrides:
        - tool: local/run-migrations
          override:
            capability:
              human_approval_required: true # In this context, require human approval
              write_scope: [database:production]

        - tool: local/create-github-issue
          override:
            capability:
              human_approval_required: true # Require approval in this context
Override rules: 1. Overrides are **shallow-merged** — only the specified fields are replaced; unspecified fields retain their registered values. 2. Overrides **never persist** back to the Tool Registry — they apply only at the point of use. 3. Built-in tool metadata **cannot be overridden** (it is authoritative from the implementation). 4. The override scope is limited to `capability` and `description` fields. Schema (`input_schema`, `output_schema`) cannot be overridden because it would break callers' expectations. #### Resource Bindings !!! adr "Architecture Decision" Resource binding resolution, slot declarations, and project-specific binding are defined in [ADR-008: Resource System](adr/ADR-008-resource-system.md) and [ADR-011: Tool System](adr/ADR-011-tool-system.md). Tools operate on **resources** — git repositories, filesystems, databases, and more. The **resource binding** system declares and resolves the relationship between a tool and the resources it needs access to. ##### Resource Slots A tool declares one or more **resource slots** in its YAML configuration. Each slot is a typed placeholder that specifies: * **Slot name**: A logical name used to reference the resource within the tool's code and parameters. * **Resource type**: The resource type required (e.g., `git`, `fs-mount`, `local/database`). The bound resource must be of this type (or a compatible subtype). * **Access mode**: `read_only`, `write_only`, or `read_write`. * **Description**: Human-readable explanation of what the tool uses this resource for. * **Required/optional**: Whether the slot must be bound for the tool to function. Example tool YAML with resource slots: 

tool:
  name: local/run-migrations
  description: "Run database migrations"
  source: custom

  resources:
    db:
      type: local/database
      access: read_write
      required: true
      description: "Target database for migrations"

  capability:
    writes: true
    write_scope: [db:migrations] # References the "db" slot
    checkpointable: true

  code: |
    direction = params["direction"]
    db_resource = ctx.resources["db"]   # Access the bound resource
    result = db_resource.handler.execute_migration(direction, db_resource.sandbox)
    return {"status": "ok"}
A tool that works with multiple resources: 

tool:
  name: local/cross-repo-diff
  description: "Compare files across two git repositories"
  source: custom

  resources:
    source_repo:
      type: git-checkout
      access: read_only
      required: true
      description: "Source repository to compare from"
    target_repo:
      type: git-checkout
      access: read_only
      required: true
      description: "Target repository to compare against"

  capability:
    read_only: true

  code: |
    source = ctx.resources["source_repo"]
    target = ctx.resources["target_repo"]
    # ... compare files across repos ...
##### Three Binding Modes Resource slots are resolved to actual resources through one of three binding modes: **1. Contextual Binding (default)** The slot declares a resource type requirement, and the system resolves it from the plan's project context at activation time. This is the most common mode — the tool says "I need a git-checkout resource" and the system finds one among the project's linked resources. 

resources:
  repo:
    type: git-checkout
    access: read_write
    # No `bind` field → contextual binding
Resolution rules for contextual binding: * The system searches the plan's project for linked resources matching the slot's type. * If exactly one resource of the right type exists, it is automatically bound. * If multiple resources match, the system uses the slot name as a hint (e.g., a slot named `repo` prefers a resource with alias `repo`). If ambiguous, the plan execution raises an error requiring explicit binding. * If no resource matches, the tool cannot be activated for this plan (a validation error is raised during plan creation). **2. Static Binding** The slot is hardcoded to a specific registered resource by name. This is useful for tools that always operate on the same resource, regardless of project context. 

resources:
  docs:
    type: fs-mount
    access: read_only
    bind: local/company-docs # Static: always this resource
    description: "Company documentation corpus"
Static bindings are resolved at registration time and validated — the named resource must exist and be of the correct type. **3. Parameter Binding** The resource reference is passed as a tool argument at invocation time. This is useful for tools that operate on user-specified resources. 

resources:
  target:
    type: git-checkout
    access: read_only
    from_param: repository # Bound from the "repository" input parameter
    description: "Repository to analyze"

input_schema:
  type: object
  properties:
    repository:
      type: string
      description: "Name of the registered resource to analyze"
  required: [repository]
The `from_param` field links a resource slot to an input parameter. At invocation time, the system resolves the parameter value as a resource name from the Resource Registry and validates type compatibility. ##### Binding Resolution Flow ```kroki-mermaid stateDiagram-v2 [*] --> ToolActivation: Actor references skill or tool node state "For Each Resource Slot" as ForEach { state binding_check <> [*] --> binding_check: Check binding type binding_check --> StaticBinding: has bind field binding_check --> ContextualBinding: no bind, no from_param binding_check --> ParameterBinding: has from_param state "Static Binding" as StaticBinding { [*] --> ResolveByName: Resolve from Resource Registry ResolveByName --> ValidateType: Validate type compatibility } state "Contextual Binding" as ContextualBinding { [*] --> SearchProject: Search plan's project resources SearchProject --> FilterByType: Filter by resource type state match_check <> FilterByType --> match_check match_check --> AutoBind: One match match_check --> TryAlias: Multiple matches match_check --> ValidationError: No matches TryAlias --> AliasMatch: Try alias/name match AliasMatch --> AutoBind: Match found AliasMatch --> ValidationError: No match } state "Parameter Binding" as ParameterBinding { [*] --> DeferBinding: Defer to invocation time } StaticBinding --> StoreBindings AutoBind --> StoreBindings ParameterBinding --> StoreBindings state "Store in ToolActivationContext" as StoreBindings } state "Tool Invocation" as Invocation { [*] --> ResolveParams: Resolve parameter-bound slots\nfrom invocation params [*] --> ValidateAccess: Ensure sandbox exists\nValidate access mode ResolveParams --> Execute ValidateAccess --> Execute state "Execute tool with bound resources" as Execute } ForEach --> Invocation Invocation --> [*] ``` ##### Built-in Tool Resource Bindings Built-in tools have **implicit resource slots** that do not need to be declared in YAML (they are hardcoded in the implementation): | Built-in Tool Group | Implicit Slot | Slot Type | Access | |---------------------|--------------|-----------|--------| | `file_operations` (read_file, write_file, edit_file, etc.) | `directory` | `fs-directory` or `git-checkout` | `read_write` | | `directory_operations` (create_directory, list_directory, etc.) | `directory` | `fs-directory` or `git-checkout` | `read_write` | | `search_operations` (search_files, find_definition, etc.) | `directory` | `fs-directory` or `git-checkout` | `read_only` | | `git_operations` (git_status, git_diff, git_log, etc.) | `repo` | `git-checkout` | `read_only` | Built-in tools accept both `fs-directory` and `git-checkout` types for file operations because a `git-checkout` resource's worktree root is an `fs-directory`. When binding to a `git-checkout`, the resource router automatically resolves to the worktree root `fs-directory` child for file operations. A standalone `fs-mount` resource also works — the router resolves through the `fs-mount` → root `fs-directory` chain. ##### Resource Discovery via Bindings The binding system enables powerful resource discovery queries: * **"What tools can modify this resource?"** → Find all tools with resource slots matching the resource's type and `access: read_write` or `access: write_only`. * **"What tools can read this virtual file?"** → Find the virtual file's physical children, then find tools with slots matching each physical resource's type. * **"What resources does this tool need?"** → Inspect the tool's declared resource slots. * **"Is this tool compatible with this project?"** → Check if the project's linked resources can satisfy all of the tool's required resource slots. ##### Transitive Reachability !!! adr "Architecture Decision" Tool reachability, access projection, and read/write routing are defined in [ADR-037: Tool Reachability and Access Projection](adr/ADR-037-tool-reachability-and-access-projection.md). Tool reachability extends beyond direct binding. A tool bound to a `git-checkout` can transitively reach every descendant `fs-file` through the DAG's `contains` edges. **Forward reachability**: Given a tool `T` bound to resource `R`, the set of all resources `T` can access is `{R} ∪ {all descendants of R via contains edges}`. **Inverse reachability**: Given a resource `r`, the set of tools that can reach it is found by walking **up** the containment hierarchy from `r`, collecting all ancestors, and finding tools with resource slots compatible with any ancestor's type. **Cross-equivalence reachability**: If resource `r` has a virtual parent, the system also finds tools that can reach any sibling physical manifestation of the same virtual resource. This answers: "What tools can reach the same logical resource through any physical path?" Example: `fs-file` at `/repo/src/main.py` is reachable by: * `write_file` (bound to `git-checkout` ancestor → forward reach) * `lsp_hover` (bound to `lsp-workspace` → reaches equivalent `lsp-document` sibling) * `docker_exec` (bound to `container-instance` → reaches equivalent `fs-file` in container mount) ##### Access Projection When a tool bound to ancestor resource `R` accesses descendant resource `d`, the **access projection** computes how `d` is identified within `R`'s access space. Each resource type handler implements a `project_access` method that returns an `AccessProjection`: * **`access_path`**: The path in the binding resource's namespace (e.g., `src/main.py` for filesystem, `file:///repo/src/main.py` for LSP). * **`protocol`**: The access mechanism (`filesystem`, `lsp-textdocument`, `container-exec`, `sql`, etc.). * **`crosses_sandbox`**: Whether this projection crosses a sandbox boundary (important: an LSP server reading from the real filesystem crosses the sandbox and sees pre-sandbox content). * **`read_richness`**: A score indicating how much information this access path provides (LSP: 10, filesystem: 1). Used for read routing. ##### Read/Write Routing When a virtual resource has multiple physical manifestations reachable through different tools, the system **routes reads and writes through different paths**: **For writes**: Route to the **canonical write target** — the physical manifestation in the strongest sandbox domain (preference: `git_worktree` > `snapshot` > `copy_on_write` > `transaction_rollback`). This ensures writes are sandbox-tracked and checkpointable. **For reads**: Route to the **richest available source**, ranked by `read_richness`: | Source | Richness | Provides | |--------|----------|----------| | `lsp-document` | 10 | Type info, symbols, diagnostics, go-to-def, references, completions | | Semantic index | 5 | Pre-computed symbol index, dependency graph | | `fs-file` via git-checkout | 1 | Raw file content, git history | | `fs-file` via container mount | 1 | Raw file content | | `git-tree-entry` | 1 | File content at specific commit | The routing algorithm selects the highest-richness source that is available, current (coherence checks pass), and compatible with the query type. #### Tool Registry CleverAgents maintains a **Tool Registry** — a persistent catalog of all independently registered tools: ```kroki-plantuml @startuml skinparam classAttributeIconSize 0 skinparam classFontSize 13 skinparam noteFontSize 11 skinparam defaultFontSize 12 class ToolRegistry { - toolIndex : Map -- + add(config_path) : ToolRecord + update(name, config_path) : ToolRecord + remove(name) : void + lookup(name) : ToolRecord + list(filters) : ToolRecord[] } class ToolRecord { + name : String + description : String + source : String {mcp|agent_skill|builtin|custom} + config_path : String + input_schema : JSONSchema + output_schema : JSONSchema + capability_metadata : CapabilityMetadata + resource_slots : List + code : String } ToolRegistry "1" *-- "0..*" ToolRecord : indexes > note right of ToolRegistry **Populated by:** - agents tool add CLI command - Dynamic refresh on MCP notifications **Consumed by:** - Skill registration - Actor graph construction - Resource binding resolution - Plan validation end note @enduml ``` The Tool Registry works alongside the Skill Registry (described in the Skills section). Skills reference tools by name from the Tool Registry; the Skill Registry's flattened tool sets are composed from Tool Registry entries plus any anonymous inline tools. #### Tool Interface and Architecture Each individual tool — whether independently registered or defined as an anonymous inline tool — conforms to a uniform interface regardless of its source: ```kroki-plantuml @startuml skinparam classAttributeIconSize 0 skinparam classFontSize 13 skinparam defaultFontSize 12 skinparam linetype ortho class Tool { } class Identity { + name : String + qualified_name : String + source : ToolSource } class Schema { + input_schema : JSONSchema + output_schema : JSONSchema } class CapabilityMetadata { + read_only : Boolean + writes : Boolean + write_scope : String + idempotent : Boolean + checkpointable : Boolean + side_effects : List + cost_profile : String + human_approval_required : Boolean } class ResourceBindings { + slots : Map } class ResourceSlot { + type : String + access : String + required : Boolean + bind : String + from_param : String + description : String } interface Lifecycle <> { + discover() : ToolDescriptor + activate() : void + execute(params, ctx) : Result + deactivate() : void } class ExecutionContext { + sandbox : Sandbox + plan : Plan + changes : List + resources : Map } enum ToolSource { mcp agent_skill builtin custom } Tool *-- Identity Tool *-- Schema Tool *-- CapabilityMetadata Tool *-- ResourceBindings Tool *-- Lifecycle Tool o-- ExecutionContext : uses at runtime > ResourceBindings *-- "0..*" ResourceSlot Identity --> ToolSource @enduml ``` Every tool implements the same four lifecycle methods. The **tool adapter layer** is responsible for translating source-specific behavior into these methods. #### Tool Adapter Layer !!! adr "Architecture Decision" The adapter pattern for tool sources and the uniform tool interface are defined in [ADR-011: Tool System](adr/ADR-011-tool-system.md). Each tool source has a corresponding **adapter** that translates source-specific protocols into the uniform tool interface: ```kroki-plantuml @startuml skinparam classAttributeIconSize 0 skinparam classFontSize 13 skinparam defaultFontSize 12 interface "ToolInterface" as UTI <> { + discover() : ToolDescriptor + activate() : void + execute(params, ctx) : Result + deactivate() : void } class MCPToolAdapter { + discover() : ToolDescriptor .. tools/list RPC → descriptors .. + activate() : void .. spawn server, init JSON-RPC .. + execute(params, ctx) : Result .. tools/call RPC → result .. + deactivate() : void .. shutdown server .. } class AgentSkillAdapter { + discover() : ToolDescriptor .. parse SKILL.md frontmatter .. + activate() : void .. load SKILL.md body into agent context .. + execute(params, ctx) : Result .. agent follows instructions, runs scripts .. + deactivate() : void .. remove from context .. } class BuiltinAdapter { + discover() : ToolDescriptor .. return hardcoded descriptors .. + activate() : void .. no-op .. + execute(params, ctx) : Result .. call native Python impl .. + deactivate() : void .. no-op .. } MCPToolAdapter .up.|> UTI AgentSkillAdapter .up.|> UTI BuiltinAdapter .up.|> UTI @enduml ``` ##### MCPToolAdapter Bridges external MCP servers into the tool model: 1. **discover()**: Spawns the MCP server process (or connects to a remote Streamable HTTP endpoint), performs the MCP `initialize` handshake, negotiates capabilities, then calls `tools/list` to enumerate available tools. Each MCP tool becomes a separate `ToolDescriptor` with its `inputSchema` and inferred capability metadata. 2. **activate()**: Ensures the MCP server process is running and the JSON-RPC connection is healthy. For remote servers, validates the authentication token. Registers for `notifications/tools/list_changed` so CleverAgents can dynamically update available tools. 3. **execute()**: Translates a `Tool.execute(params, ctx)` call into an MCP `tools/call` JSON-RPC request. Before dispatching: - Rewrites file paths to sandbox-relative paths - Validates params against `inputSchema` - Checks capability metadata against plan access policy - Creates a checkpoint if the tool is marked checkpointable After the MCP tool returns its `content[]` response, the adapter: - **Error detection**: If `isError: true` is present in the response, the error message is extracted from `content[0].text` per the MCP 1.4.0 protocol (the non-standard top-level `error` key is not used). Falls back to `"unknown error"` when `content` is absent or malformed. - Parses the result into the CleverAgents `Result` format - Records any resource mutations as `Change` objects in the plan's `ChangeSet` 4. **deactivate()**: Sends a clean shutdown to the MCP server process and closes the JSON-RPC connection. **Capability inference**: MCP tools expose limited metadata (name, description, inputSchema). The adapter infers extended capability metadata using heuristics: - Tools whose names contain `read`, `get`, `list`, `search`, `find` → `read_only: true` - Tools whose names contain `write`, `create`, `update`, `delete`, `set` → `writes: true` - All inferences can be overridden via the `overrides` block in tool or skill YAML ##### AgentSkillAdapter Bridges Agent Skills Standard (`SKILL.md` folders) into the tool model. Agent Skills are fundamentally different from MCP tools — they are **instruction-driven** rather than **schema-driven**. An Agent Skill is not a single function call; it is a bundle of procedural knowledge that an LLM agent loads into its context and follows. 1. **discover()**: Scans the configured skill directory for a `SKILL.md` file. Parses only the YAML frontmatter (`name`, `description`, optional `compatibility`, `metadata`, `allowed-tools`) to produce a lightweight `ToolDescriptor`. This metadata is injected into the agent's system prompt in a structured format so the LLM can decide when the skill is relevant: 

   <style="color: cyan; font-weight: 600;">available_agent_skills>
     <style="color: cyan; font-weight: 600;">agent_skill>
       <style="color: cyan; font-weight: 600;">name>deploy-to-staging</style="color: cyan; font-weight: 600;">name>
       <style="color: cyan; font-weight: 600;">description>Deploy the current branch to the staging environment.</style="color: cyan; font-weight: 600;">description>
       <style="color: cyan; font-weight: 600;">tool>local/deploy-staging</style="color: cyan; font-weight: 600;">tool>
     </style="color: cyan; font-weight: 600;">agent_skill>
   </style="color: cyan; font-weight: 600;">available_agent_skills>
Discovery is **low-cost** — only ~50–100 tokens per Agent Skill for metadata. The full instructions are not loaded until activation. 2. **activate()**: When the LLM agent determines (or is instructed) that a task matches the skill's description, the adapter loads the full `SKILL.md` Markdown body into the agent's active context. This injects step-by-step instructions, examples, edge cases, and references to bundled scripts. The tool is now "active" — the agent has the procedural knowledge to execute it. If the skill references additional files (`references/*.md`, `scripts/*.py`, `assets/*`), these are made available on demand — the agent can read them as needed, following the Agent Skills Standard's **progressive disclosure** model. 3. **execute()**: Unlike MCP tools (which are single RPC calls), Agent Skill execution is **agent-mediated**. The LLM agent follows the loaded instructions, potentially: - Running bundled scripts via shell execution (sandboxed) - Reading reference files for additional context - Using other available tools (e.g., built-in file operations) as part of the procedure - Making multiple tool calls in sequence to accomplish the workflow The adapter wraps this execution in a tool execution context so that all mutations are tracked, sandboxed, and checkpointable. Script execution respects the `allowed_tools` and `sandbox_policy` declared in the tool's YAML. 4. **deactivate()**: Removes the skill's instructions from the agent's active context to free up token budget. The skill's metadata remains available for re-activation. **Key design principle**: Agent Skills extend the agent's *knowledge*, not just its *toolset*. An Agent Skill can teach an agent a multi-step workflow that involves calling multiple other tools, making decisions based on intermediate results, and following domain-specific best practices — something a single MCP tool call cannot express. ##### BuiltinToolAdapter Wraps CleverAgents' native resource operations as tools: 1. **discover()**: Returns hardcoded `ToolDescriptor` objects for each built-in operation. These descriptors have fully specified capability metadata since the implementation is first-party. 2. **activate()**: No-op. Built-in tools are always available. 3. **execute()**: Calls the native Python implementation directly. Built-in tools operate through the resource abstraction layer, automatically integrating with sandbox path mapping, change tracking, and checkpointing. 4. **deactivate()**: No-op. **Built-in tool groups:** **File Operations (`file_operations`):** 

read_file(path: str) -> str
write_file(path: str, content: str) -> None
edit_file(path: str, edits: list[Edit]) -> None
delete_file(path: str) -> None
move_file(source: str, destination: str) -> None
copy_file(source: str, destination: str) -> None
**Directory Operations (`directory_operations`):** 

create_directory(path: str) -> None
list_directory(path: str, pattern: str = "*") -> list[str]
delete_directory(path: str, recursive: bool = False) -> None
**Search Operations (`search_operations`):** 

search_files(pattern: str, content_pattern: str = None) -> list[Match]
find_definition(symbol: str) -> list[Location]
find_references(symbol: str) -> list[Location]
**Git Operations (`git_operations`, when resource is a git repository):** 

git_status() -> GitStatus
git_diff(path: str = None) -> str
git_log(count: int = 10) -> list[Commit]
git_blame(path: str) -> list[BlameLine]
Each built-in tool: * Has fully defined capability metadata * Operates through the resource abstraction layer * Automatically tracks changes to the ChangeSet * Respects sandbox boundaries and deny-lists #### Tool Capability Metadata (Critical for Safety) MCP's metadata is not sufficient (read-only/idempotent is not enough; write scope is unclear). CleverAgents extends every tool — regardless of source — with a uniform capability metadata schema: 

capability:
  read_only: bool # Whether tool only performs read operations
  writes: bool # Whether tool can modify resources
  write_scope:             # What the tool is allowed to mutate
    - file_paths: ["src/**", "tests/**"]     # Path patterns within bound resources
    - resource_slots: ["repo", "db"]         # Resource slot names (from resource bindings)
    - environment:             # Execution environment compatibility
        required: container | host | any  # Where the tool CAN run (default: any)
        preferred: container | host        # Where the tool PREFERS to run (optional)
        specific: <resource-name>           # A specific container required (optional)
  idempotent: bool # Whether repeated calls produce same result
  checkpointable: bool # Whether tool supports checkpoint/rollback
  checkpoint_scope: str # What can be rolled back (file, transaction, commit, snapshot)
  side_effects:            # Non-reversible effects
    - install_packages
    - mutate_infra
    - send_email
  cost_profile:            # Usage constraints
    rate_limit: "10/min"
    estimated_cost: "$0.01/call"
  human_approval_required: bool # Whether a human must approve invocation
**Where metadata comes from per source:** | Source | Metadata origin | Override mechanism | |--------|-----------------|--------------------| | Built-in | Hardcoded in implementation | Not overridable (authoritative) | | MCP | Inferred from tool name/description + MCP annotations | `overrides` block in tool or skill YAML; `override` at skill/actor reference point | | Agent Skill | Declared in SKILL.md frontmatter `metadata` + inferred from `allowed-tools` | Tool YAML `capability` block; `override` at skill/actor reference point | | Custom | Manually declared in tool YAML `capability` block | `override` at skill/actor reference point (author is the source of truth for registered values) | #### Read-Only Actions and Tool Access Control When an action is marked `read_only: true`, it can **only use tools that have `read_only: true`** in their capability metadata. This is enforced at runtime by the tool execution context — any attempt to invoke a tool with `writes: true` from a read-only plan raises a `AccessDeniedError`. #### Tool Execution Flow When an LLM agent decides to use a tool (regardless of source), the following flow occurs through the unified execution pipeline: 

1. LLM generates tool call
   e.g., edit_file(path="src/main.py", changes=[...])
   or:   local/github.create_issue(title="Bug fix", body="...")
   or:   (activates Agent Skill "deploy-to-staging" via instructions)
                                ↓
2. Tool Router receives call
   - Resolves tool by name from the Tool Registry or actor's skill tool sets
   - Validates parameters against inputSchema
    - Checks capability metadata against plan's access policy:
     • Is this tool in allowed skill categories?
     • Does the plan allow writes?
     • Is human approval required?
   - If denied → return AccessDeniedError to LLM
                                ↓
3. Resource Binding Resolution & Sandbox Context
   - Resolve resource bindings for this tool:
     • Static bindings: already resolved at registration
     • Contextual bindings: resolve from plan's project resources
     • Parameter bindings: resolve from invocation arguments
   - Validate resource type compatibility for each slot
   - Validate access mode (e.g., read_write tool on read_only resource → error)
   - Ensure sandbox exists for each bound resource (lazy sandboxing)
   - Maps logical paths to sandbox-relative paths via bound resource handlers
   - Inject bound resources into ctx.resources[slot_name]
   - If tool is checkpointable → create pre-execution checkpoint
                                ↓
4. Adapter-Specific Execution
   - MCP: sends tools/call JSON-RPC to server process
   - Agent Skill: agent follows loaded SKILL.md instructions,
     running scripts and tools in sandboxed shell
   - Built-in: calls native Python implementation directly
   - Custom: executes inline code with sandboxed context
                                ↓
5. Change Recording
   - If tool modified resources → create Change record(s)
   - Append Change(s) to plan's ChangeSet
   - Update sandbox state
   - If checkpointable → record checkpoint for rollback
                                ↓
6. Result Return
   - Normalize result to uniform Result type
   - Return to LLM agent for continued reasoning
#### Change Tracking from Tool Invocations **Critical Architecture Point:** The ChangeSet is NOT built by parsing LLM output. It is built by recording the effects of tool invocations: 

class ToolExecutionContext:
    """Context provided to every tool execution, regardless of source."""

    def __init__(self, plan: Plan, sandbox: Sandbox,
                 resources: dict[str, BoundResource]):
        self.plan = plan
        self.sandbox = sandbox
        self.resources = resources    # slot_name → BoundResource
        self.changes: list[Change] = []

    def record_change(self, change: Change) -> None:
        """Record a change made by a tool."""
        self.changes.append(change)
        self.plan.changeset.add_change(change)


class WriteFileTool:
    """Example: built-in tool for writing files."""

    def execute(self, path: str, content: str, ctx: ToolExecutionContext) -> None:
        handler = ctx.sandbox.get_handler(path)
        change = handler.write(path, content, ctx.sandbox)
        ctx.record_change(change)
This approach means: * Every resource modification is explicit and tracked * The ChangeSet accurately reflects what was done, not what was said * Rollback is precise (replay inverse of recorded changes) * Audit logs show exactly which tool invocation produced each change #### MCP Integration Details !!! adr "Architecture Decision" MCP adoption, tool-to-skill mapping, and actor-graph usage are defined in [ADR-029: Model Context Protocol (MCP) Adoption](adr/ADR-029-model-context-protocol.md). CleverAgents integrates with the Model Context Protocol (MCP) to discover and invoke external tools, then normalizes them into the Tool Registry with extended capability metadata and sandbox-aware execution. MCP tools are composed into skills and appear as tool nodes in actor graphs, giving them the same lifecycle, change-tracking, and checkpoint semantics as built-in tools. ##### MCP Concepts Mapping | MCP Concept | CleverAgents Equivalent | Extension | |------------|------------------------|-----------| | Tool | Independently registered Tool (source: mcp), referenced by skills | Extended capability metadata (write_scope, checkpointable, side_effects) | | Resource | Resource | Extended to support both read AND write operations | | Prompt | Action template | Full plan lifecycle (Strategize → Execute → Apply) | | Server | MCP Server connection (declared in tool or skill YAML) | Managed by MCPToolAdapter with lifecycle and reconnection | | JSON-RPC | Internal adapter protocol | Abstracted behind Tool.execute() | ##### MCP Server Lifecycle Management CleverAgents manages MCP server processes as part of the tool/skill/actor lifecycle: ```kroki-mermaid sequenceDiagram participant CLI as CLI participant Reg as Registry participant ActorRT as Actor Runtime participant Adapter as MCPToolAdapter participant MCP as MCP Server note over CLI,Reg: Phase 1 - Registration CLI->>Reg: agents tool add or skill add Reg->>Reg: Validate server command or endpoint Reg->>Reg: Store server config in record note over ActorRT,MCP: Phase 2 - Actor Activation ActorRT->>Adapter: Activate (for each MCP server) Adapter->>MCP: Spawn process (stdio) or connect (HTTP) Adapter->>MCP: MCP initialize handshake MCP-->>Adapter: Capabilities Adapter->>MCP: tools list MCP-->>Adapter: Tool descriptors Adapter->>MCP: Subscribe notifications tools list_changed note over ActorRT,MCP: Phase 3 - Execution ActorRT->>Adapter: LLM generates tool call Adapter->>MCP: tools call (JSON-RPC) MCP-->>Adapter: Result Adapter->>ActorRT: Result + Change tracking note over ActorRT,MCP: Phase 4 - Deactivation ActorRT->>Adapter: Deactivate Adapter->>MCP: Clean shutdown ``` ##### Sandbox Path Rewriting for MCP Tools MCP servers operate on real filesystem paths, but CleverAgents executes plans in sandboxes. The MCPToolAdapter transparently rewrites paths: 

# Before sending to MCP server:
# Logical path: "src/main.py"
# Sandbox path: "/tmp/sandbox-01HXM/worktree/src/main.py"
# The adapter rewrites the tool arguments so the MCP server
# operates on sandboxed state without knowing about the sandbox.
This ensures MCP tools respect sandbox boundaries even though they have no awareness of the CleverAgents sandbox model. #### Agent Skills Integration Details !!! adr "Architecture Decision" The Agent Skills standard integration is defined in [ADR-028: Agent Skills Standard (AgentSkills.io)](adr/ADR-028-agent-skills-standard.md). Agent Skills follow the Agent Skills standard from [https://AgentSkills.io](https://AgentSkills.io), which defines the `SKILL.md` structure and the progressive disclosure model used by the runtime. Within actor graphs, Agent Skills appear as tool nodes — the actor runtime loads the skill's instructions into the LLM context when the node activates, enabling the agent to follow multi-step procedures that may invoke MCP tools, built-in tools, or other Agent Skills during execution. ##### Discovery and Progressive Disclosure Agent Skills follow a three-tier progressive disclosure model that maps directly to the tool lifecycle: | Tier | What loads | When | Token cost | |------|-----------|------|------------| | **Metadata** | `name` + `description` from SKILL.md frontmatter | Tool registration / actor activation | ~50–100 tokens per Agent Skill | | **Instructions** | Full SKILL.md Markdown body | When LLM determines task matches the skill (activate phase) | Recommended < 5000 tokens | | **Resources** | `scripts/`, `references/`, `assets/` | On demand during execution | Variable | This means an actor can have dozens of Agent Skill tools available but only pay the token cost for their metadata at startup. Full instructions load only when relevant. ##### Agent Skills vs. MCP Tools: When to Use Which | Dimension | MCP Tools | Agent Skills | |-----------|-----------|--------------| | **Interaction model** | Single function call with JSON params/result | Multi-step procedure with instructions the agent follows | | **Knowledge type** | "Here is a function you can call" | "Here is how to accomplish a complex task" | | **Statefulness** | Stateless per-call | Stateful across multiple tool calls within a procedure | | **Authoring** | Implement an MCP server (code) | Write a SKILL.md file (prose + optional scripts) | | **Portability** | Any MCP-compatible host | Any Agent Skills-compatible agent | | **Best for** | Atomic operations (CRUD, queries, API calls) | Complex workflows (code review processes, deployment procedures, data analysis pipelines) | Both can coexist in the same skill. A common pattern is an Agent Skill tool that teaches the agent a workflow which involves calling multiple MCP tools: 

Agent Skill Tool: "local/deploy-staging"
  SKILL.md instructions:
    1. Run tests using the built-in shell tool
    2. Create a PR using the GitHub MCP tool (create_pull_request)
    3. Wait for CI using the GitHub MCP tool (get_check_runs)
    4. Deploy using the AWS MCP tool (ecs_update_service)
    5. Verify deployment using the HTTP MCP tool (fetch_url)
#### Tool-Level Checkpointability Each tool declares whether it supports checkpoint/rollback via its capability metadata. Checkpointing behavior varies by source: | Source | Checkpoint mechanism | |--------|---------------------| | **Built-in file ops** | Snapshot file state pre-modification; rollback restores file content | | **Built-in git ops** | Create commit or stash; rollback via `git reset` / `git checkout` | | **MCP tools** | Adapter-created checkpoints of affected resources; rollback replays inverse operations where possible | | **Agent Skills** | Composite — each sub-tool-call within the skill's execution is individually checkpointed | | **Custom (containerized)** | Filesystem snapshot or container image layer; rollback restores snapshot | Checkpointing is easier when tool scope is constrained (e.g., "only files within a sandbox worktree + git"). The capability metadata's `checkpoint_scope` field communicates what granularity of rollback is supported. When `require_checkpoints` is enabled on a plan, the plan may **only** use tools that have `checkpointable: true`. If disabled, the plan may use more generic/unsafe tools with fewer restrictions (useful for low-stakes tasks). ### Validation !!! adr "Architecture Decision" The validation system, gate types, and validation lifecycle are defined in [ADR-013: Validation Abstraction](adr/ADR-013-validation-abstraction.md). #### What a Validation Is !!! abstract "Validation in Brief" A **Validation** is a specialized subtype of Tool designed to verify that work performed during plan execution meets specified quality, correctness, or compliance criteria. A Validation observes the current state of resources, evaluates a condition, and returns a structured ==pass/fail result==. It never modifies resources — it only reads and reports. Because Validation extends Tool via standard class inheritance, it is not a separate concept bolted onto the system — it *is* a tool, with additional constraints and metadata. This means validation benefits from the entire tool infrastructure: source types, resource bindings, lifecycle hooks, input/output schemas, registry management, skill composition, and actor graph integration. No parallel system is required. !!! success "Safety Guarantee" Validations are ==always safe to run==. They cannot cause side effects, corrupt state, or require rollback. This enables aggressive parallelization, speculative validation, and retry without concern. #### Relationship to Tool A Validation inherits **all** base Tool properties: | Inherited from Tool | Additional in Validation | |---------------------|--------------------------| | `name` (namespaced) | `mode` (`required` or `informational`) | | `description` | Structured return format enforcement | | `source` (custom, mcp, agent_skill, builtin, wrapped) | Read-only enforcement (`writes: false`, `checkpointable: false`) | | `input_schema` (JSON Schema) | Attachment scoping (resource-centric, with optional project/plan scope) | | `output_schema` (JSON Schema) | Attachment ULID (system-assigned per attachment) | | `capability` metadata | `wraps` (optional reference to an existing Tool) | | `resource_slots` (resource bindings) | `transform` (Python function to convert wrapped Tool output to validation format) | | `lifecycle` hooks (discover/activate/execute/deactivate) | | | `code` (inline implementation) | | | `mcp_server` / `mcp_tool_name` (MCP source) | | | `timeout` | | | `idempotent` | | **Shared namespace**: Validations and plain Tools share the same naming namespace in the Tool Registry. A name like `local/run-tests` can refer to either a Tool or a Validation — but never both simultaneously. Attempting to register a Validation with a name already taken by a plain Tool (or vice versa) results in a conflict error. This shared namespace enables unified management: `agents tool list` shows both types, `agents tool show` works for both, and `agents tool remove` removes either type. **Superset/subset semantics**: Because Validation extends Tool, a Validation can be used anywhere a Tool is expected — it can appear in a skill's tool list, serve as a tool node in an actor graph, or be invoked directly by an LLM agent. However, a plain Tool **cannot** be used where a Validation is specifically required. For example, `agents validation attach` rejects a name that resolves to a plain Tool rather than a Validation. This distinction is enforced by the `type` discriminator stored in the Tool Registry: each entry is tagged as either `tool` or `validation`. #### Read-Only Enforcement !!! danger "Hard Constraint — Not a Convention" Validations are **always read-only**: | Property | Value | Reason | | :------- | :---: | :----- | | `writes` | `false` | Must never modify, create, or delete resources | | `checkpointable` | `false` | No state changes → nothing to checkpoint | | `read_only` | `true` | Implicit inverse of `writes` | This constraint is enforced at ==multiple levels==: 1. **Registration time**: The `agents validation add` command does not accept `--writes`/`--no-writes` or `--checkpointable`/`--no-checkpointable` flags. Any such values in the validation YAML are silently overridden to `false`. 2. **Runtime enforcement**: The execution runtime treats validation invocations as read-only operations. Resource bindings are resolved with `access: read_only` semantics. If a validation's implementation attempts to write, the sandbox enforces the constraint and the invocation fails. 3. **Sandbox interaction**: When a validation executes within a plan's sandbox, it reads the sandbox state but cannot modify it — verifying work-in-progress without risk of corruption. The read-only guarantee has an important architectural consequence: validations are **always safe to run**. They cannot cause side effects, corrupt state, or require rollback. This enables aggressive parallelization, speculative validation (running validations before all work is complete to provide early feedback), and retry without concern for accumulated state changes. #### Validation Mode Each Validation has a `mode` that determines how the system responds to failure: === "Required (`mode: required`)" !!! danger "Hard Gate" Required validations ==must pass== for execution to proceed to the Apply phase. They define the "definition of done" for a plan. - When a required validation fails, the execution actor attempts to **fix the underlying issue** (e.g., fix failing tests, correct lint errors) within the bounds of the current strategy, then re-runs the validation. - This fix-then-revalidate loop continues up to the configured retry limit. - If self-fix is exhausted, the actor may request a strategy revision or escalate to the user, depending on the automation profile. === "Informational (`mode: informational`)" !!! info "Advisory Check" Informational validations are ==recorded but do not block== execution. Useful for advisory checks where failure is noteworthy but not blocking. - When an informational validation fails, the result (including `message` and `data`) is included in the plan's validation summary for human review, but the plan continues normally. - Use cases: bundle size reports, code complexity metrics, deprecation warnings, performance benchmarks. ??? tip "Gradual Promotion Pattern" The distinction between required and informational allows teams to introduce new validations gradually — start as ==informational== to measure impact, then promote to ==required== once the codebase is clean. The mode is set at registration time (in the validation YAML or via `--required`/`--informational` on `agents validation add`) and applies globally to that validation. The mode cannot be overridden per-attachment — if different scopes need different enforcement levels for the same check, register separate validations with different names and modes. #### Structured Return Format Every Validation must return a JSON object conforming to this structure: 
{
  "passed": true,
  "message": "All 247 tests passed, 94% coverage",
  "data": {
    "tests_run": 247,
    "tests_passed": 247,
    "tests_failed": 0,
    "coverage_percent": 94.2,
    "coverage_threshold": 80,
    "duration_seconds": 12.4
  }
}
| Field | Type | Required | Description | |-------|------|----------|-------------| | `passed` | boolean | **Yes** | Whether the validation passed (`true`) or failed (`false`). This is the only field that drives system behavior (gating for required, recording for informational). | | `message` | string | No | Human-readable summary of the result. Displayed in CLI output, plan summaries, and used by the execution actor to understand failures. Should be concise but actionable (e.g., "3 lint errors in src/api/handler.py" rather than just "failed"). | | `data` | object | No | Arbitrary structured data in any format the validation chooses. This is the validation's primary output channel for rich, machine-readable results. Examples: test coverage reports, lint error lists with file/line/column, security vulnerability details, performance measurement data. The `data` field has no required schema — each validation defines its own structure. | **Return format enforcement**: If a validation returns output that is not valid JSON, or valid JSON that lacks the `passed` boolean field, the system treats the invocation as an error (distinct from a validation failure). The validation result is recorded as `"passed": false` with a system-generated `message` indicating the malformed return, and the original output is preserved in `data.raw_output` for debugging. The structured return format serves multiple consumers: - **The execution actor** reads `message` and `data` to understand failures and attempt fixes. A well-structured `data` field (e.g., with file paths and line numbers) enables more targeted fix attempts. - **The plan summary** records all validation results for human review and auditing. - **Downstream automation** (CI scripts, dashboards) can parse `data` programmatically via `agents --format json plan show`. #### Attachment Scoping Validations are not globally active — they must be explicitly **attached** to one or more scopes to take effect. This attachment model provides fine-grained control over which validations run for which work. ##### Attachment Model A validation is always attached to a resource. The optional `--project` or `--plan` flag controls the scope under which the validation is active for that resource: 1. **Direct attachment** (`agents validation attach [-- ]...`) The validation is always active when that resource is accessed by any plan, regardless of which project or plan is involved. This scope is for invariants that must hold for a resource in all contexts — e.g., a lint check that must pass for a repository no matter what project is using it. Use cases: - Repository-wide lint/format checks - Schema validation on database resources - Security scanning on any codebase resource - License compliance checks 2. **Project-scoped attachment** (`agents validation attach --project [-- ]...`) The validation is active only for that resource when it is being interacted with through the specified project. Different projects using the same resource can have different validation requirements. This is the most common attachment scope. Use cases: - Unit test suites specific to a project - Type checking for a TypeScript project (not relevant for a Python project using the same repo) - API compatibility checks for a microservice project - Bundle size checks for a frontend project 3. **Plan-scoped attachment** (`agents validation attach --plan [-- ]...`) The validation is active only for that resource when it is being interacted with through the specified plan. This is the most targeted scope, useful for one-off or experimental validations. Use cases: - Temporary extra checks during a risky migration - One-time regression validation for a specific bug fix - Experimental validations being tested before promoting to project scope - User-added ad hoc checks during an interactive session Since validations accept arguments, the same validation can be attached to the same resource multiple times with different arguments. For example, `local/run-tests` might be attached to `local/api-repo` through project `local/api-service` with `--coverage-threshold 90` and also through project `local/staging` with `--coverage-threshold 70`. ##### Attachment Resolution When a plan executes, the system collects all applicable validations for each resource the plan accesses. The resolution algorithm: 1. **Collect direct validations**: For every resource the plan accesses, collect all validations directly attached to that resource (no scope flag). 2. **Collect project-scoped validations**: For every resource the plan accesses, collect all validations attached to that resource with a `--project` scope matching the plan's target project. 3. **Collect plan-scoped validations**: For every resource the plan accesses, collect all validations attached to that resource with a `--plan` scope matching the plan itself. 4. **Union**: Take the union of all collected validations per resource. If the same validation name appears from multiple scopes for the same resource (e.g., attached both directly and through a project), each attachment is treated as a distinct invocation — they may have different arguments and thus produce different results. When the same validation name appears from multiple scopes with identical arguments, the most specific scope wins (plan > project > direct) and the validation runs once. 5. **Child plan inheritance**: Child plans (spawned via `subplan_spawn` or `subplan_parallel_spawn`) inherit their parent plan's project-scoped and plan-scoped resource/validation associations by default. Direct validations are collected independently based on which resources the child plan accesses (which may differ from the parent). ##### Attachment Identity Each attachment is identified by a system-assigned **ULID**. This ULID is: - Returned by `agents validation attach` when the attachment is created. - Displayed by `agents tool show ` in the "Attached To" section and by `agents project show` in the validations list. - Required by `agents validation detach ` to remove a specific attachment. The ULID is necessary because the same validation can be attached to the same resource multiple times — directly, through different projects, through different plans, and even to the same resource and scope with different arguments. The ULID uniquely identifies which specific attachment to remove. ##### Attachment Arguments When attaching a validation, optional arguments can be provided after the validation name: 

$ agents validation attach --project local/api-service local/api-repo local/run-tests --coverage-threshold 90
$ agents validation attach --project local/staging-api local/api-repo local/run-tests --coverage-threshold 70
These arguments are stored with the attachment and passed to the validation tool's `input_schema` at execution time. This enables a single validation definition to be reused across scopes with different thresholds or configurations. If no arguments are provided, the validation uses its `input_schema` defaults. #### Validation Lifecycle in Plan Execution Validation participates in the plan lifecycle at well-defined points: ##### During Strategize Validations are **not executed** during Strategize. However, the strategy actor is aware of which validations are attached (via the attachment resolution described above) and factors them into the strategy: - The strategy may allocate time/tokens for validation fix-up loops. - The strategy may note that certain validations are informational and thus non-blocking. - The decision tree may include `validation_checkpoint` decisions that mark points where validation should be run. ##### During Execute Validation is the **final step** of the Execute phase. The execution actor's workflow proceeds as follows: 1. **Perform work**: The actor executes the strategy — writing code, modifying resources, running tools — all within the sandbox. 2. **Collect applicable validations**: The system resolves all validations from the resource-direct, project, and plan scopes (as described in Attachment Resolution above). 3. **Execute validations**: Each applicable validation is invoked as a standard tool call. The validation reads the sandbox state and returns its structured result. Validations may be run in parallel since they are read-only and cannot interfere with each other. 4. **Process results**: - **All required validations pass**: Execution is complete. The plan transitions to the review/Apply phase. - **Any required validation fails**: The execution actor enters the fix-then-revalidate loop (see Validation Failure Handling below). - **Informational validations fail**: Results are recorded in the plan's validation summary. No fix attempts are made. ##### Validation is Not Run During Apply !!! warning "Apply is the Point of No Return" Validation runs during Execute, **not** during Apply. By the time a plan reaches Apply, all required validations have already passed. Apply commits the sandbox changes to the real resources. If post-apply verification is needed (e.g., integration tests against the real system), implement it as a separate plan or external CI pipeline — ==not as a validation attachment==. **Rationale**: Introducing validation during Apply would create situations where committed changes might need to be rolled back, defeating the purpose of the sandbox model. #### Validation Failure Handling Because validations are tools, their execution follows the standard tool invocation flow. Each validation returns a structured JSON result with `{ "passed": true/false, "message": "...", "data": {...} }`. The execution actor interprets these results based on the validation's `mode`. ##### Required Validation Failure When a **required** validation returns `"passed": false` during Execute: 1. **Diagnosis**: The execution actor examines the validation's `message` and `data` fields to understand the nature of the failure. A well-structured `data` field (e.g., with specific file paths, line numbers, error messages) enables more targeted fix attempts. 2. **Self-fix attempt**: The execution actor attempts to fix the issue within the bounds of the current strategy. For example: - A failing test: the actor reads the test output, identifies the broken assertion, and fixes the code. - A lint error: the actor reads the lint report and corrects the formatting or style violation. - A type error: the actor reads the type checker output and fixes the type mismatch. 3. **Re-validation**: After each fix attempt, the actor re-invokes the failing validation. If it passes, the loop ends. If it still fails, the actor examines the new `message` and `data` for the updated failure state. 4. **Retry limit**: The fix-then-revalidate loop runs up to the configured retry limit (default: 3 attempts, configurable per plan or in the automation profile). After the limit is reached, self-fix stops. 5. **Strategy revision**: If the actor determines that the failure cannot be resolved within the current strategy's constraints (e.g., the strategy says "modify only `handler.py`" but the test failure requires changes to `model.py`), it may request a **strategy revision**. This triggers a re-run of the Strategize phase for the affected subtree of the decision tree. Whether this happens automatically or requires user approval depends on the automation profile's `delete_content` flag. 6. **Escalation**: If strategy revision also fails, or if the automation profile requires human approval for strategy changes, the plan pauses and requests user guidance via `agents plan prompt`: 

   agents plan prompt <plan_id> "Try using mock objects for the database tests"
7. **Terminal failure**: If the user does not intervene (or explicitly cancels), the plan fails with `state: failed`. The sandbox is preserved for inspection. The flow can be summarized as: 

validate → fail → fix → re-validate → fail → fix → re-validate → ... → retry limit
  → request strategy revision → re-strategize → re-execute → validate
  → still failing → escalate to user → user provides guidance → resume
  → still failing → plan fails
##### Informational Validation Failure When an **informational** validation returns `"passed": false`: 1. The result (including `message` and `data`) is recorded in the plan's `validation_summary`. 2. Execution continues normally — no fix attempts, no blocking, no escalation. 3. The informational failure is visible in `agents plan show`, plan summaries, and any rendering format. 4. Informational failures may trigger notifications (if configured) but never block plan progression. ##### Validation Error vs. Validation Failure !!! note "Important Distinction" | Condition | Meaning | Handling | | :-------- | :------ | :------- | | **Validation failure** (`passed: false`) | Validation ran successfully, condition not met | Mode-specific (fix loop for required, record for informational) | | **Validation error** | Validation itself failed to execute (runtime exception, timeout, malformed return) | ==Always treated as required failure== regardless of mode | When a validation error occurs: - The result is recorded with `passed: false`, a system-generated `message` describing the error, and the raw error details in `data`. - If the validation is required, the fix-then-revalidate loop attempts to resolve the error (e.g., by fixing a broken test configuration). - If the validation is informational, the error is still recorded but does not block. - Repeated validation errors (e.g., the validation tool itself is misconfigured) are surfaced prominently in the plan summary. #### Validation in Actor Graphs Because Validations are Tools, they can appear as **tool nodes** in actor graphs. This enables explicit, deterministic validation steps within workflows: 

# Actor graph with explicit validation nodes
graph:
  nodes:
    - name: implement
      type: agent
      actor: local/code-writer
    - name: run_tests
      type: tool
      tool: local/run-tests       # This is a Validation (subtype of Tool)
    - name: lint_check
      type: tool
      tool: local/lint-check      # Also a Validation
    - name: fix_issues
      type: agent
      actor: local/code-fixer
  edges:
    - [implement, run_tests]
    - [implement, lint_check]
    - condition: "not run_tests.passed or not lint_check.passed"
      from: [run_tests, lint_check]
      to: fix_issues
    - [fix_issues, run_tests]    # Retry loop
    - [fix_issues, lint_check]
When a Validation appears as a tool node, its return value is available to downstream nodes via the standard graph data flow. The `passed`, `message`, and `data` fields can be used in edge conditions, passed as input to subsequent nodes, or logged for the plan summary. This graph-based approach complements the attachment model: attached validations run automatically at the end of Execute (the system handles collection and invocation), while graph-embedded validations run at explicitly defined points in the workflow (the actor author controls placement). Both approaches can coexist — a plan may have attached validations that run at the end plus graph-embedded validations that run at intermediate checkpoints. #### Validation and Skills Validations can be **included in skills** just like any other tool. Since a Validation is a Tool, a skill YAML can reference it by name: 

# Skill: local/python-quality
skill:
  name: local/python-quality
  description: "Python code quality tools and validations"
  tools:
    - local/run-tests         # Validation (required)
    - local/lint-check        # Validation (required)
    - local/type-check        # Validation (required)
    - local/format-code       # Plain Tool (writes)
    - local/run-benchmarks    # Validation (informational)
When an actor references this skill, the Validations are available as tools that the LLM agent can call. This is distinct from validation attachment — being included in a skill makes the validation *callable* by the actor's LLM, but does not make it a *required gate*. Attachment determines gating; skill inclusion determines availability. A common pattern: a team's skill includes their validations for on-demand use by the LLM (the actor can run tests proactively during development), while the same validations are also attached to the project (ensuring they run as a mandatory gate at the end of Execute even if the LLM forgot to run them). #### Tool Wrapping A Validation can **wrap an existing Tool**, reusing its implementation without duplicating code. This is the recommended approach when a plain Tool already performs the work a Validation needs (e.g., running tests, generating a report, scanning for vulnerabilities) and the Validation only needs to interpret the Tool's output as pass/fail. ##### The Problem Consider a team that already has a registered Tool called `local/run-tests` — it runs the test suite and returns a structured report (test counts, coverage data, output logs). Now they want a Validation that gates execution on all tests passing. Without wrapping, they would need to duplicate the entire test-running implementation inside a new Validation YAML, differing only in the final pass/fail interpretation. This duplication creates maintenance burden: if the test runner configuration changes, both the Tool and the Validation must be updated. ##### The Solution: `wraps` + `transform` A Validation YAML can declare a `wraps` field that references an existing registered Tool by name. At execution time, the system invokes the wrapped Tool, captures its output, and passes that output through a `transform` function that produces the Validation's structured return format (`{ "passed", "message", "data" }`). 

# validations/tests-pass.yaml
# Wraps the existing local/run-tests tool — no test logic duplicated

name: local/tests-pass
description: "Validate that all unit tests pass (wraps local/run-tests)"

wraps: local/run-tests

transform: |
  def transform(tool_output):
      passed = tool_output.get("returncode") == 0
      return {
          "passed": passed,
          "message": "All tests passed" if passed else f"Tests failed (exit {tool_output.get('returncode')})",
          "data": tool_output
      }

validation:
  mode: required

timeout: 600
When `local/tests-pass` is invoked (either by attachment or direct call): 1. The system resolves `wraps: local/run-tests` to the registered Tool. 2. The Validation's input arguments are mapped to the wrapped Tool's input arguments using the `argument_mapping` (see below). If no `argument_mapping` is defined, the Validation's input arguments are passed through to the wrapped Tool as-is. 3. The wrapped Tool is invoked with the mapped arguments. 4. The wrapped Tool's output is captured (whatever it returns — JSON, text, etc.). 5. The `transform` function is called with the captured output. 6. The `transform` function returns the Validation's structured result (`{ "passed", "message", "data" }`). This is opaque to the consumer — the caller sees only a standard Validation with its structured return format. The wrapping is an implementation detail. ##### What Gets Inherited When a Validation uses `wraps`, the following properties are **inherited from the wrapped Tool** unless explicitly overridden in the Validation YAML: | Property | Inherited? | Override behavior | |----------|-----------|-------------------| | `input_schema` | Yes | If the Validation YAML defines `input_schema`, it replaces the wrapped Tool's schema entirely. If omitted, the Validation accepts the same inputs as the wrapped Tool. When a custom `input_schema` is defined, an `argument_mapping` should also be provided to map the Validation's inputs to the wrapped Tool's expected inputs. | | `argument_mapping` | No | Not inherited. When present, maps the Validation's input arguments to the wrapped Tool's input arguments. When absent, input arguments are passed through unchanged. See the Argument Mapping section. | | `resource_slots` | Yes | If the Validation YAML defines `resource_slots`, they replace the wrapped Tool's slots. If omitted, the Validation inherits the same resource bindings. | | `timeout` | Yes | If the Validation YAML specifies `timeout`, it overrides. If omitted, the wrapped Tool's timeout is used. | | `description` | No | The Validation must provide its own description (it serves a different purpose than the wrapped Tool). | | `source` | No | Ignored — the source is implicitly `wrapped`. The Validation does not declare `source` or `code`. | | `capability` | No | Overridden — `writes` and `checkpointable` are forced to `false` regardless of the wrapped Tool's values. | ##### The `transform` Function The `transform` field contains a Python function that converts the wrapped Tool's output to the Validation's return format. The function signature is: 

def transform(tool_output) -> dict:
    """
    Args:
        tool_output: The wrapped Tool's return value. The type depends on the
                     Tool's implementation — typically a dict (for JSON-returning
                     tools) but may be a string or other type.
    Returns:
        A dict with at minimum {"passed": bool}. May also include
        "message" (str) and "data" (any).
    """
The `transform` function runs in a sandboxed Python environment with no write access to the filesystem or network. It is a pure data transformation — it receives the Tool's output and produces the Validation's result. If the `transform` function raises an exception, the Validation is treated as an error (see Validation Error vs. Validation Failure). If `transform` is omitted, the system applies a **default transform** that expects the wrapped Tool's output to already contain a `passed` field: - If the output is a dict with a `passed` boolean, it is used as-is (pass-through). - If the output is a dict without `passed`, the validation errors with a message indicating the wrapped tool's output is not in validation format and a `transform` function is required. - If the output is not a dict, the validation errors similarly. ##### Argument Mapping (`argument_mapping`) When a Validation wraps a Tool, the Validation may accept different input arguments than the wrapped Tool. The `argument_mapping` field specifies how the Validation's input arguments map to the wrapped Tool's expected input arguments. This is necessary when: - The Validation's `input_schema` defines different field names than the wrapped Tool's `input_schema`. - The Validation accepts a subset of the wrapped Tool's arguments and wants to provide fixed values for the rest. - The Validation renames arguments for clarity in the validation context. The `argument_mapping` is a dictionary where keys are the wrapped Tool's input parameter names and values are either: - A string referencing a Validation input parameter name (forwarded as-is). - A fixed literal value (string, number, boolean) that is always passed to the wrapped Tool regardless of the Validation's inputs. 

# Example: Validation wraps local/run-tests but renames arguments
name: local/tests-pass
wraps: local/run-tests

argument_mapping:
  test_directory: source_dir        # Forward Validation's "source_dir" → Tool's "test_directory"
  coverage_enabled: true            # Always pass true for coverage_enabled
  verbose: false                    # Always pass false for verbose

transform: |
  def transform(tool_output):
      return {"passed": tool_output.get("returncode") == 0, "message": "Tests completed"}

validation:
  mode: required
When `argument_mapping` is **omitted**, the Validation's input arguments are passed through to the wrapped Tool unchanged. This is the common case when the Validation inherits the wrapped Tool's `input_schema` without modification (i.e., the Validation YAML does not define its own `input_schema`). When `argument_mapping` is **present**, only the mapped arguments are forwarded to the wrapped Tool. Any Validation input arguments not referenced in the mapping are not passed to the wrapped Tool. Any wrapped Tool arguments not listed as keys in the mapping receive no value (and must either be optional in the Tool's schema or have defaults). ##### Read-Only Semantics for Wrapped Tools Validations are always read-only, but the wrapped Tool may not be. The wrapping enforces read-only semantics: - The wrapped Tool is invoked within the Validation's read-only execution context. Resource bindings are resolved with `access: read_only` regardless of what the wrapped Tool's `resource_slots` specify. - If the wrapped Tool's implementation attempts to write (e.g., mutate files, insert database rows), the sandbox enforces the read-only constraint and the invocation fails as a validation error. - At registration time, if the wrapped Tool has `writes: true`, the system emits a **warning** (not an error) advising the user that the wrapped Tool is marked as writing and may fail at runtime under read-only enforcement. This allows wrapping tools that are conservatively marked `writes: true` but whose actual behavior for the given inputs is read-only. This design means wrapping is always safe from the Validation perspective — the worst case is a runtime error, never an unintended write. ##### Multiple Validations Wrapping the Same Tool The same Tool can be wrapped by multiple Validations with different `transform` functions and different modes. This is a common pattern: 

# The base tool runs tests and produces a comprehensive report
# Tool: local/run-tests (already registered)

# Validation 1: All tests must pass (required)
# validations/tests-pass.yaml
name: local/tests-pass
description: "All unit tests must pass"
wraps: local/run-tests
transform: |
  def transform(tool_output):
      return {
          "passed": tool_output.get("returncode") == 0,
          "message": f"{tool_output.get('tests_passed', 0)}/{tool_output.get('tests_run', 0)} tests passed",
          "data": tool_output
      }
validation:
  mode: required


# Validation 2: Coverage must exceed threshold (informational for now)
# validations/coverage-check.yaml
name: local/coverage-check
description: "Coverage must exceed threshold (advisory)"
wraps: local/run-tests
transform: |
  def transform(tool_output):
      coverage = tool_output.get("coverage_percent", 0)
      threshold = 80
      return {
          "passed": coverage >= threshold,
          "message": f"Coverage: {coverage}% (threshold: {threshold}%)",
          "data": {"coverage_percent": coverage, "threshold": threshold}
      }
validation:
  mode: informational
Both validations wrap the same `local/run-tests` tool but extract different signals. When both are attached to the same project, each Validation independently invokes the wrapped Tool and applies its own `transform` function. A future optimization may deduplicate these invocations when the forwarded arguments are identical (see Validation Ordering and Parallelism). ##### When to Wrap vs. When to Write From Scratch | Scenario | Approach | |----------|----------| | An existing Tool already does the work; you just need pass/fail | **Wrap it** — use `wraps` + `transform` | | Multiple Validations need different interpretations of the same Tool's output | **Wrap it** multiple times with different transforms | | The validation logic is simple and self-contained (e.g., run a shell command, check exit code) | **Write from scratch** — use `source: custom` with inline `code` | | The validation needs logic that the existing Tool doesn't provide (different inputs, different execution) | **Write from scratch** — the Tool's implementation isn't relevant | | The existing Tool has side effects that are incompatible with read-only enforcement | **Write from scratch** — wrapping would fail at runtime | #### Validation Data Model The validation-related fields stored in the plan data model: | Field | Location | Description | |-------|----------|-------------| | `validation_summary` | `plan.execution` | Array of validation results collected during Execute. Each entry includes the validation name, mode, `passed`, `message`, `data`, execution duration, and attempt number. | | `final_validation_results` | `plan.apply` | Snapshot of the final validation state at the time execution completed (all required validations passing). Identical to the last state of `validation_summary` but stored separately for quick reference. | | `validation_attempts` | `plan.execution` | Total number of validation invocations across all fix-then-revalidate loops. Useful for understanding how much effort was spent on validation remediation. | | `validation_fix_history` | `plan.execution` | Per-validation log of fix attempts. Each entry records: the validation that failed, the fix the actor applied, and whether the subsequent re-validation passed. Enables auditing of the fix-then-revalidate process. | A validation result entry in `validation_summary`: 

{
  "validation": "local/run-tests",
  "mode": "required",
  "passed": true,
  "message": "All 247 tests passed, 94% coverage",
  "data": {
    "tests_run": 247,
    "tests_passed": 247,
    "coverage_percent": 94.2
  },
  "duration_ms": 12400,
  "attempt": 2,
  "attachment_id": "01HXM5A1B2C3D4E5F6G7H8J9K0",
  "attachment_resource": "local/api-repo",
  "attachment_scope": "project",
  "attachment_scope_target": "local/api-service"
}
#### Validation Ordering and Parallelism Since validations are read-only, they are inherently safe to run in parallel. The execution runtime may parallelize validation invocations subject to: - **Resource constraints**: Validations that require significant compute (e.g., full test suites) may be serialized to avoid resource exhaustion. - **Timeout budgets**: Each validation has its own `timeout` (from the tool configuration). The total validation phase has an implicit budget derived from the sum of individual timeouts, but the runtime may use parallelism to finish faster. - **Dependency hints**: A future extension may allow declaring ordering dependencies between validations (e.g., "run lint before tests" to fail fast on formatting issues). Currently, all validations run independently. **Wrapped Tool deduplication (deferred)**: When multiple Validations wrap the same Tool (via `wraps`), a future optimization could invoke the wrapped Tool once and fan out its output to each Validation's `transform` function. However, deduplication is only valid when multiple Validations wrap the same Tool **and** receive the exact same forwarded arguments (after `argument_mapping` resolution) **and** are evaluated in the same calling chain. This complexity — particularly around argument equivalence and cache invalidation during fix-then-revalidate loops — means deduplication is **deferred for future design**. The current implementation invokes the wrapped Tool separately for each Validation that wraps it. The recommended execution strategy is: 1. Run all validations in parallel (each Validation independently invokes its wrapped Tool if applicable). 2. Collect results. 3. If any required validation fails, fix and re-run only the failing validations (not all of them). 4. Repeat until all pass or retry limit is reached. #### Registering and Managing Validations Validations are **registered** via `agents validation add` and **attached** via `agents validation attach`. These are the only validation-specific CLI commands. All other management operations use the standard `agents tool` commands: | Operation | Command | Notes | |-----------|---------|-------| | **Register** | `agents validation add --config ` | Validation-specific. Config file defines all properties including mode (`required`/`informational`). | | **Update** | `agents validation add --config --update` | Uses the `--update` flag to overwrite existing registration. | | **Attach** | `agents validation attach [--project\|--plan] [-- ]...` | Returns an attachment ULID. Resource is always required; project/plan scope is optional. | | **Detach** | `agents validation detach [--yes] ` | Uses the attachment ULID, not the validation name. | | **List** | `agents tool list --type validation` | Shared with tools. Use `--type validation` to filter. | | **Show** | `agents tool show ` | Shows validation-specific fields when the entry is a Validation. | | **Remove** | `agents tool remove ` | Shared with tools. Automatically detaches from all scopes. | See the **agents validation** and **agents tool** CLI Reference sections for full command details and examples. #### Typical Validation Workflow A typical workflow for setting up validations on a project: 

# 1. Define validation YAML files
# (see Configuration > Validation Configuration Files for schema and examples)

# 2. Register validations
agents validation add --config ./validations/run-tests.yaml
agents validation add --config ./validations/lint-check.yaml
agents validation add --config ./validations/type-check.yaml
agents validation add --config ./validations/check-bundle-size.yaml

# 3. Attach to resource through a project (active only when this resource is accessed through this project)
agents validation attach --project local/api-service local/api-repo local/run-tests
agents validation attach --project local/api-service local/api-repo local/type-check
agents validation attach --project local/api-service local/api-repo local/check-bundle-size

# 4. Attach directly to a resource (always active for any plan accessing this resource)
agents validation attach local/api-repo local/lint-check

# 5. Verify setup
agents tool list --type validation --namespace local
agents tool show local/run-tests

# 6. Run a plan — validations execute automatically at end of Execute phase
agents plan use local/implement-feature local/api-service
#### Design Rationale **Why Validation extends Tool rather than being a separate concept**: - Reuses the entire tool infrastructure (registry, bindings, lifecycle, sources, schemas) without duplication. - Validations can be composed into skills, used in actor graphs, and invoked by LLM agents — all for free. - A single namespace and registry avoids the complexity of managing two parallel systems. - Tool-aware features (resource bindings, MCP integration, Agent Skills) apply to validations automatically. **Why read-only is enforced rather than advisory**: - Validations that modify state defeat the purpose of the sandbox model. - Read-only guarantees enable safe parallelization and retry without side effects. - It makes validations categorically safe — no risk analysis needed for running a validation. **Why attachments use ULIDs rather than name+scope pairs**: - A validation may be attached to the same scope multiple times with different arguments. - ULIDs provide an unambiguous handle for removal without complex composite keys. - Consistent with the ULID-based identity model used for plans, resources, and decisions. **Why validation runs during Execute, not Apply**: - Apply is a controlled commit step. Validation failures during Apply would require rolling back committed changes. - The sandbox model ensures all verification occurs before the point of no return. - Post-apply verification (integration tests, smoke tests) is a separate concern best handled by external CI or follow-up plans. ### Skills !!! adr "Architecture Decision" The skill composition model, skill inclusion, and tool bundling are defined in [ADR-012: Skill System](adr/ADR-012-skill-system.md). #### What a Skill Is !!! adr "Architecture Decision" The canonical definition of a skill — its four tool sources, flattening model, and role as the unit of capability assignment — is formalized in [ADR-030: Skill Abstraction Definition](adr/ADR-030-skill-abstraction-definition.md). A **skill** is a namespaced, reusable **collection of tools** that is registered in the system via its own YAML configuration file and managed through `agents skill` CLI commands. Skills are the unit of capability composition in CleverAgents — they define *what an actor can do* by assembling tools into coherent, reusable bundles. A skill is **not** a single tool. It is a **container** that references one or more tools (by name from the Tool Registry) and/or defines anonymous inline tools, along with metadata describing the collection's purpose, capabilities, and safety characteristics. Tools are independently registered, callable operations (see the **Tools** section above). Skills organize them into reusable groups. **Key properties of a skill:** * **Named and namespaced**: Skills follow the same `/` naming convention as actors, tools, actions, and plans (e.g., `local/github-ops`, `cleverthis/file-management`, `local/deploy-tools`). * **Defined in their own YAML files**: Skills are NOT defined inline in actor configurations. They have their own configuration files and are managed as independent, reusable entities. * **A collection of tools**: Each skill references named tools from the Tool Registry and/or defines anonymous inline tools. Skills can also expose tools from MCP servers, Agent Skills Standard folders, and built-in tool groups. * **Hierarchically composable**: A skill can include other skills by reference, inheriting all of their tools. This enables layered composition — a "full-stack" skill might include a "file-ops" skill, a "git-ops" skill, and a "github" skill. When including a sub-skill, individual tool metadata can optionally be overridden. * **Referenced by actors**: Actors reference skills by fully-qualified name. The actor's graph gains access to all tools within the referenced skills. #### The Skill / Tool Distinction !!! adr "Architecture Decision" The formal distinction between skills (containers) and tools (atomic operations), and the source-agnostic flattening model, are defined in [ADR-030: Skill Abstraction Definition](adr/ADR-030-skill-abstraction-definition.md). ```kroki-plantuml @startuml skinparam packageStyle rectangle skinparam defaultFontSize 12 skinparam componentFontSize 12 package "Skill: local/devops-toolkit" as Skill { package "builtin: file_operations" as FileOps { component [read_file()] as T1 component [write_file()] as T2 component [edit_file()] as T3 } package "builtin: git_operations" as GitOps { component [git_status()] as T4 component [git_diff()] as T5 } package "mcp: github-server" as GH { component [create_issue()] as T6 component [create_pr()] as T7 component [list_repos()] as T8 } package "custom" as Custom { component [run_migrations()] as T9 } package "Included Skills" as Includes { component [local/pdf-processing\n(adds pdf tools)] as I1 component [local/data-analysis\n(adds analysis tools)] as I2 } } @enduml ``` **Tools** are independently registered, atomic units of execution (see the **Tools** section above for full details). Each tool has: * A namespaced name, description, and JSON Schema for inputs/outputs * Its own YAML configuration file, registered via `agents tool add` * A source type (mcp, agent_skill, builtin, custom) * Capability metadata (read_only, writes, checkpointable, etc.) * A lifecycle: `discover()`, `activate()`, `execute(params, ctx)`, `deactivate()` **Skills** are the organizational units. Each skill has: * A namespaced name * A YAML configuration file defining its tool composition * Zero or more **named tool references** (pointing to independently registered tools in the Tool Registry) * Zero or more **anonymous inline tools** (one-off tools defined directly in the skill YAML) * Zero or more included child skills (whose tools are merged in, with optional per-tool metadata overrides) * Tool sources: MCP servers, Agent Skills folders, built-in tool groups * Metadata (description, capability summary) When an actor references a skill, it gains access to the **flattened set of all tools** — named tool references, anonymous tools, tools from MCP/Agent Skills/builtins, and those inherited from included child skills. #### Skill Configuration (YAML) Skills are defined in their own YAML configuration files, separate from tool and actor configurations. A skill YAML file declares which registered tools it includes (by name), which other skills it includes, and optionally defines anonymous inline tools: 

# File: skills/devops-toolkit.yaml
cleveragents:
  version: "3.0"

skill:
  name: local/devops-toolkit
  description: "Full-stack development tools for file ops, git, GitHub, and deployment"

  # ── Named Tool References ───────────────────────────────
  # Reference independently registered tools by name.
  # These tools must already be registered via `agents tool add`.
  # Optional metadata overrides can be applied per tool.
  tools:
    - local/run-migrations                  # Simple reference, use as registered
    - name: local/deploy-staging            # Reference with metadata override
      override:
        capability:
          human_approval_required: true # Require approval in this skill context

  # ── Include other skills ─────────────────────────────────
  # All tools from included skills become part of this skill.
  # Included skills must already be registered in the system.
  # Individual tools from included skills can have metadata overridden.
  includes:
    - local/file-ops           # built-in file + directory + search tools
    - local/git-ops            # built-in git tools
    - name: local/github       # MCP-based GitHub tools, with per-tool overrides
      tool_overrides:
        - tool: local/create-github-issue
          override:
            capability:
              write_scope: [github:issues:org-only]

  # ── MCP Server Tools ─────────────────────────────────────
  # Connect to MCP servers and expose their tools.
  # Tools discovered from MCP servers are auto-registered in the
  # Tool Registry if not already present.
  mcp_servers:
    - name: linear
      command: "npx @anthropic/mcp-linear"
      env:
        LINEAR_API_KEY: "${LINEAR_API_KEY}"
      # Optional: override inferred capability metadata per tool
      overrides:
        - tool: create_issue
          writes: true
          write_scope: [linear:issues]
        - tool: list_issues
          read_only: true

  # ── Agent Skills (SKILL.md folders) ──────────────────────
  # Each Agent Skill folder is loaded as a composite tool.
  # The agent discovers it via metadata, activates it by
  # loading SKILL.md instructions, and follows them.
  agent_skills:
    - path: ./skills/code-review-checklist
      sandbox_policy: none

  # ── Built-in Tool Groups ─────────────────────────────────
  # Opt-in to built-in tool groups provided by CleverAgents.
  builtins:
    - group: shell_operations

  # ── Anonymous Tools ──────────────────────────────────────
  # Inline tool definitions for one-off, skill-specific operations.
  # Same format as a named tool YAML body but without a name.
  # These are NOT registered in the Tool Registry and are NOT reusable.
  anonymous_tools:
    - description: "One-off cleanup for legacy migration artifacts"
      input_schema:
        type: object
        properties:
          directory: { type: string }
      capability:
        writes: true
        checkpointable: true
        checkpoint_scope: file
      code: |
        import os, glob
        directory = params["directory"]
        removed = []
        for f in glob.glob(os.path.join(ctx.sandbox.root, directory, "*.legacy")):
            os.remove(f)
            removed.append(f)
        return {"removed": removed, "count": len(removed)}
Here is an example of a simpler skill that wraps only built-in tools, suitable for common reuse: 

# File: skills/file-ops.yaml
cleveragents:
  version: "3.0"

skill:
  name: local/file-ops
  description: "File and directory operations"

  builtins:
    - group: file_operations      # read, write, edit, delete, move, copy
    - group: directory_operations  # create, list, delete dirs
And an example of a skill that is purely MCP-based: 

# File: skills/github.yaml
cleveragents:
  version: "3.0"

skill:
  name: local/github
  description: "GitHub operations via MCP"

  mcp_servers:
    - name: github
      command: "npx @anthropic/mcp-github"
      env:
        GITHUB_TOKEN: "${GITHUB_TOKEN}"
      overrides:
        - tool: create_issue
          writes: true
          write_scope: [github:issues]
          checkpointable: false
        - tool: create_pull_request
          writes: true
          write_scope: [github:pulls]
          checkpointable: false
        - tool: list_repos
          read_only: true
        - tool: get_file_contents
          read_only: true
#### Skill Hierarchy and Composition Skills can include other skills via the `includes` field. When a skill includes another, all tools from the child skill (and transitively, all tools from any skills *it* includes) become part of the parent skill's flattened tool set. 

local/full-stack-dev
  ├── includes: local/file-ops
  │     └── builtins: file_operations, directory_operations
  ├── includes: local/git-ops
  │     └── builtins: git_operations
  ├── includes: local/github
  │     └── mcp_servers: github (create_issue, create_pr, list_repos, ...)
  ├── agent_skills: code-review-checklist
  └── tools: local/run-migrations, local/deploy-staging  (named tool refs)

  Flattened tool set available to actors referencing local/full-stack-dev:
    read_file, write_file, edit_file, delete_file, move_file, copy_file,
    create_directory, list_directory, delete_directory,
    git_status, git_diff, git_log, git_blame,
    create_issue, create_pr, list_repos, get_file_contents,
    code-review-checklist (agent skill),
    local/run-migrations, local/deploy-staging (named tools)
**Rules for skill composition:** 1. **Circular includes are forbidden.** The system validates the include graph at registration time and rejects cycles. 2. **Tool name conflicts**: If two included skills provide tools with the same name, the conflict is resolved by qualification — the tool must be referenced as `.` (e.g., `local/github.create_issue` vs `local/linear.create_issue`). Direct tools (defined in the skill itself) take precedence over included tools. 3. **Included skills must be registered** before the including skill can be added. The `agents skill add` command validates this. 4. **Depth is unlimited** but the flattened tool set is computed at registration time and cached. Deep hierarchies do not incur runtime overhead. #### Skill Registration and Management Skills are managed through the `agents skill` CLI commands. Named tools referenced by skills must first be registered via `agents tool add` (see the **Tools** section): 

# First, register any named tools the skill will reference
agents tool add --config ./tools/run-migrations.yaml
agents tool add --config ./tools/deploy-staging.yaml

# Then register the skill (which references those tools by name)
agents skill add --config ./skills/devops-toolkit.yaml

# Update an existing skill (re-reads the config file, overwrites registration)
agents skill add --config ./skills/devops-toolkit.yaml --update

# List all registered skills
agents skill list

# Show details for a skill (tools, includes, metadata)
agents skill show local/devops-toolkit

# List all tools provided by a skill (flattened, including from child skills)
agents skill tools local/devops-toolkit

# Remove a skill
agents skill remove local/devops-toolkit
Once registered, a skill is available to be referenced by any actor configuration. Skills persist in the database (local or server) and follow the same namespace rules as actors, tools, and actions. #### Actor References to Skills and Tools Actors reference skills **by name** to make collections of tools available for LLM tool-calling. Additionally, actor graphs can include **tool nodes** that directly reference named tools or define anonymous inline tools (see **Nodes in the Graph** in the Actor section). The actor's configuration lists which skills it should have access to: 

# File: actors/code-assistant.yaml
cleveragents:
  version: "3.0"
  default_actor: code_assistant

actors:
  code_assistant:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      temperature: 0.3
      system_prompt: |
        You are a code assistant with access to file, git, and GitHub tools.
        Current task: {{ context.task_description }}

    # Reference skills by fully-qualified name.
    # All tools from these skills become available to this actor.
    skills:
      - local/file-ops
      - local/git-ops
      - local/github

  # Or reference a single composite skill that includes all of the above
  full_stack_assistant:
    type: llm
    config:
      actor: anthropic/claude-3-opus
      system_prompt: |
        You are a full-stack development assistant.

    skills:
      - local/full-stack-dev    # includes file-ops, git-ops, github, etc.
**Server-qualified skill references**: When connected to multiple servers, skills can be disambiguated with a server prefix, same as actors: 

skills:
  - dev:freemo/custom-analysis     # from dev server, personal namespace
  - prod:cleverthis/deploy-tools   # from prod server, org namespace
  - local/file-ops                 # local skill
#### Skill Registry To enable plan validation and discovery at scale, CleverAgents maintains two registries that work together: 1. **Tool Registry** — a persistent catalog of all independently registered tools (described in the **Tools** section above). Managed via `agents tool add/remove/list/show`. 2. **Skill Registry** — a persistent catalog of all registered skills and their flattened tool sets. The Skill Registry composes its tool sets by resolving named tool references from the Tool Registry, incorporating anonymous inline tools, and merging tools from included child skills. ```kroki-plantuml @startuml skinparam classAttributeIconSize 0 skinparam classFontSize 13 skinparam defaultFontSize 12 class SkillRegistry { - skillIndex : Map -- + add(config_path) : SkillRecord + update(name, config_path) : SkillRecord + remove(name) : void + lookup(name) : SkillRecord + list(filters) : SkillRecord[] + tools(name) : ToolDescriptor[] + validate_plan(plan) : ValidationResult + refresh(name) : void } class SkillRecord { + name : String + description : String + config_path : String + includes : List + tool_refs : List + anonymous_tools : List + flattened_tools : List + overrides : Map + capability_summary : CapabilitySummary } SkillRegistry "1" *-- "0..*" SkillRecord : indexes > note right of SkillRegistry **Populated by:** - agents skill add CLI command - Dynamic refresh on MCP notifications **Depends on:** - Tool Registry (resolve named tool references) **Consumed by:** - Actor activation - Plan validation - Agent context injection end note @enduml ``` Both registries persist in the database (local SQLite or server). MCP server tools are refreshed dynamically when `notifications/tools/list_changed` events are received. ### Session !!! adr "Architecture Decision" Session persistence, session lifecycle, and session-plan relationships are defined in [ADR-020: Session Model](adr/ADR-020-session-model.md). #### What a Session Is A **session** is a user's interactive thread with CleverAgents across time. !!! abstract "Session Responsibilities" - [x] Maintain ==conversational continuity== across interactions - [x] Store plan references for active and past plans - [x] Persist memory (if enabled) across CLI invocations - [x] Provide a UI anchor (CLI invocation, TUI workspace, web session) #### Session and Memory Persistence The notes include a known issue: conversation history can be lost between CLI invocations depending on connection string configuration, implying the system needs a stable memory service backend. !!! warning "Persistence Requirements" - Sessions must have ==stable IDs== - Sessions must be ==resumable== across CLI invocations - Session storage backend must be ==configured explicitly== - If session persistence is disabled, the UX must be explicit about it — ==no silent history loss== ### Server !!! adr "Architecture Decision" The server architecture, multi-user support, and local/server mode duality are defined in [ADR-023: Server Mode](adr/ADR-023-server-mode.md). The server application architecture is defined in [ADR-048: Server Application Architecture](adr/ADR-048-server-application-architecture.md). The A2A standard adoption is defined in [ADR-047: A2A Standard Adoption](adr/ADR-047-acp-standard-adoption.md). #### What a Server Is A server is an **optional, separate application** that enables: * multi-user access * shared org namespaces (`/` and `/`) * persistent plan records (PostgreSQL) * remote plan execution (via LangGraph Platform) * governance and auditing * entity synchronization across devices and team members The server shares the same **Domain and Application layers** as the client (per ADR-001), differing only in Infrastructure and Presentation layers. Its sole client-facing interface is an **A2A JSON-RPC 2.0 endpoint** — there is no REST API. **Single-user local mode is the default** (so setup is easy), but the architecture anticipates server mode for shared skills, org-level actions, and collaborative workflows. #### Client-Only vs Server Mode | Mode | Description | Protocol | Plan Execution | |------|-------------|----------|----------------| | **Client-only** | No server connection. All data in local database. Agent runs as local subprocess. | A2A over stdio | Always local | | **Server mode** | Connected to a CleverAgents server. Namespaced items sync. | A2A over HTTP | Local or server (via LangGraph Platform RemoteGraph) | **It is possible to run a client with no server at all.** Server is optional. #### Server Configuration and Connection Connecting to a server requires two configuration keys: | Key | Env Var | Purpose | |-----|---------|---------| | `server.url` | `CLEVERAGENTS_SERVER_URL` | URL of the CleverAgents A2A server endpoint | | `server.token` | `CLEVERAGENTS_SERVER_TOKEN` | Authentication token (obtained via server registration or team invite) | When `server.url` is set, the client switches to server mode: A2A methods flow over HTTP instead of stdio, and server namespaces become available. The connection lifecycle follows the A2A standard: the client discovers the server's Agent Card (capability exchange), authenticates via the declared HTTP auth scheme, and begins sending `message/send` or `message/stream` requests. #### Cloud Plan Execution In server mode, actor graphs are deployed to **LangGraph Platform** and invoked via **RemoteGraph**. This means different actors for different plan phases (strategy, execution, estimation) each deploy as separate RemoteGraphs, enabling independent scaling without limiting plan capabilities. When an agent executing on the server needs to access **client-local resources** (files, terminals), it uses `_cleveragents/` extension methods (`fs/read_text_file`, `fs/write_text_file`, `terminal/*`) which the client handles locally via the A2A multi-turn interaction pattern (Task enters `input-required` state). This enables server-hosted plan execution even when some resources exist only on the client machine. #### Entity Sync and Sharing Entity synchronization between client and server uses A2A extension methods (`_cleveragents/sync/*`): * **Auto-sync** (`server.sync.auto`): Entities sync on connection and at `server.sync.interval` (default: 300s) * **Pull**: Server namespace entities are downloaded to local cache * **Push**: Local entity definitions can be explicitly pushed to a server namespace * **Status**: Compare local and server entity versions to detect drift * The `local/` namespace is **never** synced — it exists only on the client #### Multi-Device Experience With server mode, a user can: * Start a plan on their laptop, close the lid, and monitor progress from another device * Share entity definitions (actors, skills, actions) across team members via server namespaces * Run long-running plans on server infrastructure without keeping a client connected * Access the same session history from CLI, TUI, or IDE plugin on different machines #### IDE Integration via A2A IDE plugins (e.g., VS Code, JetBrains) communicate with CleverAgents exclusively through A2A — the same protocol used by CLI and TUI. The IDE plugin can operate in either local mode (spawning an agent subprocess over stdio) or server mode (connecting to a remote CleverAgents server over HTTP). The `_cleveragents/` extension methods for file and terminal operations (`fs/*`, `terminal/*`) allow the agent to interact with the IDE's workspace and integrated terminal. #### Agent-to-Agent Protocol (A2A) !!! adr "Architecture Decision" The Agent-to-Agent Protocol is defined in [ADR-026: Agent-to-Agent Protocol (A2A)](adr/ADR-026-agent-client-protocol.md). The adoption of the A2A standard is defined in [ADR-047: A2A Standard Adoption](adr/ADR-047-acp-standard-adoption.md). CleverAgents adopts the **Agent-to-Agent Protocol** standard ([a2a-protocol.org](https://a2a-protocol.org)) as the **sole** communication protocol for all client-server interaction. A2A is built on **JSON-RPC 2.0** and serves as the **fundamental boundary between the Presentation and Application layers** — every client operation flows through A2A regardless of deployment mode. No client ever bypasses A2A to touch storage, repositories, or internal domain services directly. A2A solves a fundamental architectural problem: CleverAgents has *multiple presentation surfaces* (CLI, TUI, IDE plugin) and *multiple deployment modes* (local and server), but every client must observe identical behavior regardless of how or where it connects. The A2A standard provides a mature, ecosystem-aligned protocol surface that third parties can implement against. !!! tip "For the complete architectural deep-dive — transport modes, method catalog, extension methods, wire format, authentication, and error handling — see the [Server and Client Architecture](#server-and-client-architecture) section under Architecture." ##### A2A Standard Operations The A2A standard defines operations for the core agent interaction lifecycle. These map directly to CleverAgents concepts: | A2A Operation | Direction | CleverAgents Mapping | | :------------ | :-------- | :------------------- | | Agent Card discovery | Client → Server | Capability negotiation — advertises supported `_cleveragents/` extensions, automation profiles, tool registries | | HTTP auth (OAuth2 / API key) | Client → Server | Token-based authentication (`server.token`) via auth schemes declared in Agent Card | | `message/send` | Client → Server | `SessionWorkflow.tell()` — send user message to orchestrator actor; creates or updates a Task | | `message/stream` | Client → Server | `SessionWorkflow.tell()` with streaming — returns `TaskStatusUpdateEvent` / `TaskArtifactUpdateEvent` via SSE | A2A uses a **Task-centric model**: each `message/send` or `message/stream` creates or updates a Task that tracks the lifecycle of the interaction. Tasks transition through states: `submitted` → `working` → `completed` (or `failed`, `canceled`, `input-required`). ##### A2A Streaming Events The A2A standard defines Server-Sent Events (SSE) for real-time streaming from server to client during `message/stream`: | Event Type | CleverAgents Mapping | | :--------- | :------------------- | | `TaskStatusUpdateEvent` | Task state transitions, streaming agent response tokens during plan execution | | `TaskArtifactUpdateEvent` | Plan artifacts, tool invocation results, generated outputs | Events within a single plan lifecycle preserve **causal ordering**: a phase transition event always arrives after the corresponding prior phase completion. ##### Multi-Turn Interactions (Server → Client) A2A supports multi-turn interactions for operations that require client-side input. When the server-hosted agent needs client-local resources or human approval, the Task enters `input-required` state: | Interaction Pattern | Purpose | | :------------------ | :------ | | Task `input-required` state | Human-in-the-loop approval — maps to automation profile gates | | `_cleveragents/fs/read_text_file` | Agent reads a file on the client machine (local project resources) | | `_cleveragents/fs/write_text_file` | Agent writes a file on the client machine | | `_cleveragents/terminal/create` | Agent requests a terminal on the client machine (sandbox execution) | | `_cleveragents/terminal/output` | Terminal output streaming | | `_cleveragents/terminal/release` / `wait_for_exit` / `kill` | Terminal lifecycle management | These multi-turn interactions enable a server-hosted agent to access client-local resources without requiring the server to have direct access to the user's filesystem or terminal. ##### CleverAgents Extension Methods Platform operations beyond the core agent conversation use A2A **extension methods** — declared in the Agent Card's extensions section per the A2A extensibility mechanism. All CleverAgents extensions use the `_cleveragents/` namespace: | Extension Group | Methods | Service(s) | | :-------------- | :------ | :--------- | | **Plan lifecycle** | `_cleveragents/plan/use`, `execute`, `apply`, `cancel`, `status`, `tree`, `explain`, `correct`, `diff`, `artifacts`, `prompt`, `rollback`, `list` | `PlanService`, `PlanLifecycle`, `CorrectionFlow` | | **Registries** | `_cleveragents/registry/{entity}/list`, `show`, `add`, `update`, `remove` (for each entity type: actor, skill, tool, validation, resource, resource_type, project, action, automation_profile, invariant, lsp) | `ActorService`, `ToolService`, `SkillService`, `ResourceService`, `ProjectService` | | **Context** | `_cleveragents/context/show`, `inspect`, `simulate`, `set` | `ContextService` | | **Sync** | `_cleveragents/sync/pull`, `push`, `status` | `SyncService` | | **Namespace** | `_cleveragents/namespace/list`, `show`, `members` | `NamespaceService` | | **Health** | `_cleveragents/health/check`, `_cleveragents/diagnostics/run` | Health/diagnostic services | Every CLI command listed in the [CLI Commands](#cli-commands) section maps to either a standard A2A operation or a `_cleveragents/` extension method. When a user runs `agents plan status `, the CLI sends a `_cleveragents/plan/status` JSON-RPC request through the active transport and renders the response. The CLI is a thin rendering layer — it contains no business logic. ##### Transport Modes A2A operates over two transports provided by the A2A Python SDK: | Mode | Transport | How It Works | Authentication | | :--- | :-------- | :----------- | :------------- | | **Local** | A2A over **stdio** | Client spawns agent as subprocess; JSON-RPC messages flow over stdin/stdout. Platform extension methods are resolved in-process via `A2aLocalFacade`. | Bypassed (local user permissions) | | **Server** | A2A over **HTTP** | Client connects to CleverAgents server via A2A SDK HTTP transport. All methods (standard + extensions) flow through the single A2A endpoint. | HTTP auth schemes declared in Agent Card (OAuth2, API key) + `Authorization: Bearer` header | In **local mode**, the agent runs as a subprocess. Standard A2A operations (`message/send`, `message/stream`) drive the conversation. Extension methods (`_cleveragents/*`) are intercepted by `A2aLocalFacade` and routed to in-process Application-layer services. No serialization beyond JSON-RPC framing, no network, no authentication overhead. In **server mode**, the client connects to the CleverAgents server. All communication — both agent conversations and platform operations — flows through the single A2A JSON-RPC 2.0 endpoint. The server delegates actor execution to LangGraph Platform via RemoteGraph. A third configuration supports **external A2A agents**: standard A2A operations go to the external agent's server, while `_cleveragents/` extension methods go to the CleverAgents server. This enables interoperability with any A2A-compliant agent. ```kroki-mermaid sequenceDiagram participant U as User participant C as CLI / TUI / IDE participant A2A as A2A Client (SDK) participant S as A2A Server participant LG as LangGraph Platform rect rgb(220, 240, 255) Note over C,A2A: Local Mode (stdio) U->>C: agents plan status C->>A2A: _cleveragents/plan/status {JSON-RPC 2.0} A2A->>A2A: A2aLocalFacade → PlanService.get_status() A2A-->>C: JSON-RPC result C-->>U: Rendered output end rect rgb(255, 235, 220) Note over C,LG: Server Mode (HTTP) U->>C: agents session tell "Refactor auth" C->>A2A: message/send {JSON-RPC 2.0} A2A->>S: HTTP POST (JSON-RPC) S->>LG: RemoteGraph.invoke(actor_graph) LG-->>S: Actor result S-->>A2A: TaskStatusUpdateEvent / TaskArtifactUpdateEvent (SSE) A2A-->>C: Streaming response C-->>U: Rendered output end ``` ##### Wire Format All A2A communication uses **JSON-RPC 2.0** framing as defined by the [JSON-RPC 2.0 specification](https://www.jsonrpc.org/specification). The internal `A2aRequest` and `A2aResponse` domain objects use the **standard JSON-RPC 2.0 field names** — `jsonrpc`, `method`, `id`, `params`, `result`, and `error` — ensuring full protocol compliance and interoperability with any JSON-RPC 2.0 client or tooling. ###### Envelope Field Reference | Field | Appears In | Type | Description | | :---- | :--------- | :--- | :---------- | | `jsonrpc` | Request & Response | `"2.0"` (string literal) | Always `"2.0"`. Identifies the JSON-RPC protocol version. | | `method` | Request, Notification | string | The A2A operation name (e.g. `message/send`) or `_cleveragents/` extension method. | | `id` | Request & Response | integer \| string \| null | Correlates a response to its request. Omitted in notifications (fire-and-forget). | | `params` | Request, Notification | object \| array | Method-specific input parameters. Always an object for CleverAgents methods. | | `result` | Success Response | any | Present on success; mutually exclusive with `error`. | | `error` | Error Response | object | Present on failure; mutually exclusive with `result`. Contains `code` (integer), `message` (string), and optional `data`. | **Request:** ```json { "jsonrpc": "2.0", "id": 1, "method": "message/send", "params": { "message": { "role": "user", "parts": [{ "kind": "text", "text": "Refactor the auth module" }] }, "taskId": "task_01HXR..." } } ``` **Success response:** ```json { "jsonrpc": "2.0", "id": 1, "result": { "status": "accepted" } } ``` **Streaming event (SSE notification via `message/stream`):** ```json { "jsonrpc": "2.0", "method": "task/statusUpdate", "params": { "taskId": "task_01HXR...", "status": { "state": "working" }, "message": { "role": "agent", "parts": [{ "kind": "text", "text": "I'll start by..." }] } } } ``` **Extension method request:** ```json { "jsonrpc": "2.0", "id": 42, "method": "_cleveragents/plan/status", "params": { "plan_id": "01HXRCF1..." } } ``` **Error response:** ```json { "jsonrpc": "2.0", "id": 42, "error": { "code": -32001, "message": "Plan not found", "data": { "plan_id": "01HXRCF1..." } } } ``` ###### A2aVersionNegotiator The `A2aVersionNegotiator` component handles backward compatibility when a client and server are running different versions of the CleverAgents A2A extension protocol. On connection establishment, the negotiator: 1. Reads the `_cleveragents.version` field from the server's Agent Card. 2. Compares it against the client's supported version range. 3. Selects the highest mutually supported minor version. 4. Downgrades the request envelope shape if the server is on an older minor version (e.g. omitting fields added in a later minor version). This ensures that a newer CLI can still communicate with an older server (and vice versa) within the same major version, without requiring simultaneous upgrades of all components. ##### Authentication Authentication uses HTTP auth schemes declared in the server's Agent Card: 1. Client fetches the server's Agent Card (via `/.well-known/agent.json` or configured URL) 2. Agent Card declares supported authentication schemes (OAuth2, API key, Bearer token) 3. Client authenticates using the declared scheme — typically `Authorization: Bearer ` header 4. All subsequent requests carry the authentication credentials Local mode (stdio) bypasses authentication entirely — the agent subprocess runs with the user's local permissions. ##### Versioning - The JSON-RPC protocol version is always `"2.0"` (in the `jsonrpc` field) - A2A protocol version is declared in the Agent Card and sent via the `A2A-Version` HTTP header - CleverAgents extension version is declared in the Agent Card's extensions section under `_cleveragents.version` - Servers support the current extension version plus one prior minor version - Backward-compatible additions (new optional params, new extension methods) are permitted within a major version; breaking changes require a major version bump #### Plan Execution Location Where a plan executes depends on the project type: | Project Type | Client Execution | Server Execution | |--------------|-----------------|------------------| | **Local** (has local-only resources) | ✅ Yes | ❌ No (server can't access local resources) | | **Remote** (all resources remotely accessible) | ✅ Yes | ✅ Yes | When acting on **local projects**, the client must be running because only the client can access local resources. **Remote projects** can execute on either: - The client (if user prefers local execution) - The server (for long-running plans, since client may be transient) #### Server Execution Benefits Server execution is useful when: * Plans take a long time to execute * Client may disconnect (laptop closes, network issues) * Multiple team members need to monitor plan progress * Centralized logging and auditing required #### No Plan Queuing **Plans are not queued.** When a plan is used on projects and executed, it runs immediately. There is no worker queue or delayed execution model. #### Multi-user Risks and Prompt Injection Prompt injection isn't critical in single-user mode but becomes important for multi-user server environments. Server mode must include: * access boundaries * prompt sanitization / safe templating * resource access controls * auditing ### Resources !!! adr "Architecture Decision" The resource model, resource types, DAG structure, and resource lifecycle are defined in [ADR-008: Resource System](adr/ADR-008-resource-system.md). A **resource** is an independently registered entity representing anything that a plan can reason about or manipulate — git repositories, filesystems, databases, APIs, documents, and more. Resources are **first-class citizens** in CleverAgents, managed through the `agents resource` CLI commands and stored in the **Resource Registry**. **CleverAgents extends the MCP resource concept** to support both read AND write operations (MCP resources are read-only). Unlike MCP's flat resource model, CleverAgents resources form a **directed acyclic graph (DAG)** with parent/child relationships, support **physical vs virtual** distinction for content identity tracking, and are governed by a **resource type system** that constrains their structure and behavior. Resources are registered independently of projects. Projects **link** to resources from the Resource Registry — a resource can be linked to multiple projects, enabling shared resources across teams and workflows. #### What a Resource Is A resource has: * **Name and namespace**: User-added resources follow the same `/` naming convention as actors, tools, skills, and other entities (e.g., `local/api-repo`, `cleverthis/staging-db`). Auto-discovered child resources do not have names — they are identified by ULID only. Every resource (whether user-added or auto-discovered) always has a system-assigned ULID. * **Resource type**: Every resource has a type (e.g., `git`, `fs-mount`, `git-branch`, `fs-file`) that determines its properties, CLI arguments, allowed parent/child relationships, sandbox strategy, and handler implementation. * **Physical or virtual nature**: Resources are either **physical** (a specific, concrete manifestation) or **virtual** (an abstract identity linking equivalent physical resources). This is determined by the resource type. * **Value/properties**: Type-specific properties (a file path, a URL, a connection string, a commit hash, etc.). * **Parent/child relationships**: Resources form a DAG. A resource can have multiple parents and multiple children, subject to type constraints. * **Capabilities**: Whether the resource is readable, writable, sandboxable, and checkpointable. #### Resource Types A **resource type** is a schema-level definition that constrains a category of resources. Resource types define: * **CLI arguments**: What arguments `agents resource add ` accepts (for user-addable types), including which are required vs optional and validation rules. * **Physical or virtual**: Whether instances of this type are physical or virtual resources. * **Allowed parent types**: What resource types are valid parents. * **Allowed child types**: What resource types are valid children, and whether they are auto-discovered or manually linkable. * **Auto-discovery behavior**: What child resources are automatically created when an instance of this type is registered (e.g., registering a `git-checkout` resource auto-discovers a `git` child and an `fs-directory` child for the worktree root; the `git` child in turn auto-discovers remotes, branches, commits, and tree entries). * **User addable**: Whether users can create instances of this type directly via `agents resource add `. Types with `user_addable: false` are only generated as auto-discovered children of other resources. * **Sandbox strategy**: The default sandboxing approach for instances of this type. * **Handler**: The resource handler implementation that provides read/write/sandbox/checkpoint operations. * **Inheritance**: Optionally, a parent type from which this type inherits all of the above via the `inherits` field. ##### Resource Type Inheritance !!! adr "Architecture Decision" Resource type inheritance is defined in [ADR-042: Resource Type Inheritance](adr/ADR-042-resource-type-inheritance.md). Resource types support **single-inheritance specialization** via an `inherits` field. A subtype inherits all properties, capabilities, child type constraints, sandbox strategy, and handler behavior from its parent type, and can selectively override or extend any inherited field. **Core polymorphism guarantee:** Tools bound to a parent type automatically work with all subtypes. Auto-discovery child type matching and DAG queries that reference a parent type automatically include subtypes. **Field resolution:** When the system resolves a field for a resource type, it walks the inheritance chain from the most specific type to the root. If the subtype declares the field, the subtype's value is used (override). If omitted, the parent's value is inherited. **Collection field merging:** Fields that are collections (`cli_args`, `child_types`, `parent_types`) use additive merging by default — the subtype's entries are appended to the parent's, with same-name entries replaced. A subtype can use `_replace: true` to replace a collection entirely. **Inheritance rules:** 1. Single inheritance only (no diamond). 2. Maximum chain depth of 5 levels. 3. No circular inheritance (validated at registration time). 4. Built-in types may not inherit from custom (namespaced) types. 5. Removing a parent type is prohibited while subtypes exist. Example: 

# A subtype that inherits from container-instance
name: devcontainer-instance
inherits: container-instance
description: "A container provisioned from a devcontainer.json configuration"

# Only fields that differ from or extend container-instance need to be declared.
# All other fields (capabilities, sandbox_strategy, child_types, etc.) are inherited.
cli_args:
  # Inherited args from container-instance remain available.
  # Additional args specific to devcontainer:
  - name: config-path
    type: path
    required: false
    description: "Path to .devcontainer/devcontainer.json or .devcontainer/ directory"

handler:
  class: DevcontainerHandler
  module: cleveragents.resource.handlers.devcontainer
##### Built-in Resource Types Built-in types are organized into four layers: **git** (version control structure), **git-checkout** (a composition that bridges git metadata with a local directory), **filesystem** (physical files on disk), and **container** (containerized execution environments). Virtual types link equivalent physical resources across these layers through content/identity matching. There are 34 built-in types total (24 physical + 1 subtype + 9 virtual), of which 4 are user-addable as top-level resources (`git-checkout`, `git`, `fs-mount`, `fs-directory`), plus container types documented in [ADR-039](adr/ADR-039-container-resource-types.md) and the `devcontainer-instance` subtype documented in [ADR-043](adr/ADR-043-devcontainer-integration.md). Each table below includes the full parent/child relationship constraints. **Allowed Parents** lists what types may be a parent of this type, with cardinality (how many parents of that type are allowed) and whether the relationship is required or optional. **Allowed Children** lists what types may be children, with cardinality and whether they are required or optional. `0..*` means zero or more, `1` means exactly one (required), `0..1` means zero or one (optional). **Physical types — Git layer** (version control structure — every instance is a concrete manifestation in a specific repository): | Type | User Addable | Sandbox | Allowed Parents | Allowed Children | Description | |------|-------------|---------|-----------------|------------------|-------------| | `git` | yes | `none` | `git-checkout` (0..1, optional) | `git-remote` (0..*, optional), `git-branch` (0..*, optional), `git-tag` (0..*, optional), `git-commit` (0..*, optional), `git-stash` (0..*, optional), `git-submodule` (0..*, optional) | A git repository — the object database, refs, and full history. Accessible via a local `.git` directory path or a remote URL. Every `git` resource is a specific, concrete repo instance (local or hosted on a remote server). | | `git-remote` | no | `none` | `git` (1, required) | (none) | A remote URL configured on a git repo (e.g., `origin → https://github.com/org/repo`). Auto-discovered child of `git`. Optionally linked as a child of a `remote` virtual resource when the same URL appears in multiple repos. | | `git-branch` | no | (inherits) | `git` (1, required) | `git-commit` (0..*, optional) | A named branch ref (e.g., `main`, `feature/auth`). Auto-discovered child of `git`. Optionally linked as a child of a `branch` virtual resource when the same branch name + HEAD exists in multiple repos. | | `git-tag` | no | (inherits) | `git` (1, required) | (none) | A tag ref — lightweight or annotated (e.g., `v1.0.0`). Auto-discovered child of `git`. Optionally linked as a child of a `tag` virtual resource when the same tag name + target exists in multiple repos. | | `git-commit` | no | (inherits) | `git-branch` (1..*, required), `git` (1, required) | `git-tree` (1, required) | A specific commit object. Auto-discovered child of `git-branch` (a commit can belong to multiple branches). Each commit contains exactly one root `git-tree`. Also a direct child of `git` for ancestry traversal. Optionally linked as a child of a `commit` virtual resource when the same commit hash exists in multiple repos (e.g., shared history between fork and upstream). | | `git-tree` | no | (inherits) | `git-commit` (1..*, required) | `git-tree-entry` (0..*, optional), `git-tree` (0..*, optional) | A tree object — a directory listing at a specific commit. Each tree contains entries (blobs and subtrees). Auto-discovered child of `git-commit`. Trees are recursive: a tree can contain subtrees as children. Optionally linked as a child of a `tree` virtual resource when the same tree hash exists across commits/repos. | | `git-tree-entry` | no | (inherits) | `git-tree` (1, required) | (none) | A blob entry in a tree — a specific file's content at a specific path and mode. Auto-discovered child of `git-tree`. Represents the leaf of git's content-addressable storage. Optionally linked as a child of a `file` virtual resource when byte-identical content with the same name and permissions exists in the filesystem layer. | | `git-stash` | no | (inherits) | `git` (1, required) | (none) | A stash entry (e.g., `stash@{0}`). Auto-discovered child of `git`. Represents work-in-progress saved via `git stash`. | | `git-submodule` | no | (inherits) | `git` (1, required) | (none) | A submodule reference — a pointer to another git repository at a specific commit and path. Auto-discovered child of `git`. Optionally linked as a child of a `submodule` virtual resource when the same submodule URL + path exists in multiple repos. | **Physical types — Git checkout** (composition: git metadata + local worktree directory): | Type | User Addable | Sandbox | Allowed Parents | Allowed Children | Description | |------|-------------|---------|-----------------|------------------|-------------| | `git-checkout` | yes | `git_worktree` | (none — always a top-level resource) | `git` (1, required), `fs-directory` (1, required) | A locally checked-out git repository. The **composition type** — auto-discovers a `git` child (the repo's object database, branches, tags, commits, trees, and remotes) and an `fs-directory` child (the worktree root directory, e.g., `/home/user/projects/my-app`). Most users register this type. The worktree root IS a directory, not a mount point, so git-checkout composes with `fs-directory` directly. | **Physical types — Filesystem layer** (files on disk, used by git checkouts and standalone directories alike): | Type | User Addable | Sandbox | Allowed Parents | Allowed Children | Description | |------|-------------|---------|-----------------|------------------|-------------| | `fs-mount` | yes | `copy_on_write` | (none — always a top-level resource) | `fs-directory` (1, required) | A physical mount point on the local system (e.g., `/mnt/data`, `/home`). Represents the mount itself — the filesystem type (ext4, btrfs, etc.) is a property. The root directory is a required auto-discovered `fs-directory` child. Used for registering entire mount points or storage volumes. | | `fs-directory` | yes | `copy_on_write` | `git-checkout` (0..1, optional), `fs-mount` (0..1, optional), `fs-directory` (0..1, optional) | `fs-directory` (0..*, optional), `fs-file` (0..*, optional), `fs-symlink` (0..*, optional), `fs-hardlink` (0..*, optional) | A directory on the filesystem. Can be the root child of `fs-mount` (mount point root), the worktree root child of `git-checkout`, a subdirectory child of another `fs-directory`, or a standalone user-registered directory. Optionally linked as a child of a `directory` virtual resource when equivalent directory content exists elsewhere. When user-addable, accepts `--path` flag. | | `fs-file` | no | (inherits) | `fs-directory` (1, required) | (none) | A regular file on the local filesystem. Auto-discovered child of `fs-directory`. Optionally linked as a child of a `file` virtual resource when byte-identical content with the same name and permissions exists elsewhere (in another `fs-file` or a `git-tree-entry`). | | `fs-symlink` | no | (inherits) | `fs-directory` (1, required) | (none) | A symbolic link on the local filesystem. Auto-discovered child of `fs-directory`. Optionally linked as a child of a `symlink` virtual resource when a symlink with the same name and target exists elsewhere. | | `fs-hardlink` | no | (inherits) | `fs-directory` (1, required) | (none) | A hard link on the local filesystem — a file with link count > 1. Auto-discovered child of `fs-directory`. The system tracks hard link relationships by inode to avoid treating the same underlying data as distinct resources. | **Virtual types** (abstract identity types that link equivalent physical resources — never user-addable, no sandbox): Virtual types use simple names that mirror their physical counterparts. A virtual resource answers the question: "where else does this same thing exist?" Two physical resources share a virtual parent when they are equivalent by the virtual type's criteria (same content, same name, same permissions, same hash, etc.). | Type | Allowed Children | Description | |------|-----------------|-------------| | `file` | `fs-file` (0..*, optional), `git-tree-entry` (0..*, optional) | Cross-layer file identity. Links physical `fs-file` and `git-tree-entry` resources that represent the same file — identical content bytes, filename, and permissions. Answers: "this file in the working tree and this blob in git's tree are the same file." | | `directory` | `fs-directory` (0..*, optional), `git-tree` (0..*, optional) | Cross-layer directory identity. Links physical `fs-directory` and `git-tree` resources whose recursive contents are equivalent. Answers: "this directory on disk matches this tree object in git." | | `symlink` | `fs-symlink` (0..*, optional), `git-tree-entry` (0..*, optional) | Cross-layer symlink identity. Links physical `fs-symlink` and `git-tree-entry` (mode 120000) resources with the same name and target. | | `commit` | `git-commit` (0..*, optional) | Cross-repo commit identity. Links `git-commit` resources across different repos that share the same commit hash — typically a fork and its upstream. Answers: "this commit exists in both repos." | | `branch` | `git-branch` (0..*, optional) | Cross-repo branch identity. Links `git-branch` resources across different repos with the same branch name and HEAD commit hash. | | `tag` | `git-tag` (0..*, optional) | Cross-repo tag identity. Links `git-tag` resources across different repos with the same tag name and target object. | | `remote` | `git-remote` (0..*, optional) | Cross-repo remote identity. Links `git-remote` resources across different repos that point to the same URL. Answers: "these repos share the same upstream." | | `submodule` | `git-submodule` (0..*, optional) | Cross-repo submodule identity. Links `git-submodule` resources across different repos with the same submodule URL and path. | | `tree` | `git-tree` (0..*, optional) | Cross-repo/cross-commit tree identity. Links `git-tree` resources across different commits or repos that have the same tree hash — identical directory structure and contents. | **Key design notes:** * Virtual types are **never user-addable** — they are created and maintained automatically by the system when equivalent physical resources are detected. * Virtual types have **no sandbox strategy** because they represent abstract identities, not concrete locations. Tools always operate on the physical children. * **Physical types list virtual parents in their Allowed Parents column** (via the "optionally linked" descriptions). For example, an `fs-file` can be linked as a child of a `file` virtual resource when its content matches a `git-tree-entry`. This is how the DAG connects physical and virtual layers. * `git` represents a specific git repository instance — whether hosted remotely (e.g., on GitHub's servers) or locally (a `.git` directory on disk). It is **physical** because it is a concrete manifestation that exists somewhere, not an abstract identity. A `git` resource can be created from a remote URL alone (accessing the object database via the git protocol) or from a local `.git` directory. * `git-checkout` is the type most users register for repos they've cloned. It composes a `git` child (repo metadata) and an `fs-directory` child (the worktree root directory). The worktree root is a directory on an existing filesystem — NOT a separate mount point — so `git-checkout` links directly to `fs-directory`, not `fs-mount`. This means the worktree's files use the **same `fs-directory` and `fs-file` types** regardless of how they were created. * `git-commit` has a `git-tree` child (the root tree object), which in turn has `git-tree-entry` and nested `git-tree` children. This properly models git's internal object structure: commits point to trees, trees contain entries (blobs) and subtrees. * `fs-mount` represents a physical mount point, not a directory. The filesystem type (ext4, btrfs, etc.) is a property on the mount. The root directory is an auto-discovered `fs-directory` child. Use `fs-mount` for registering mount points and storage volumes. Use `fs-directory` (user-addable) for registering arbitrary directories. * `fs-directory` is user-addable, allowing users to register standalone directories (e.g., a build output folder, a config directory) without wrapping them in an `fs-mount`. An `fs-directory` registered standalone or as a child of `fs-mount`/`git-checkout` uses the same type and auto-discovers the same `fs-file`, `fs-symlink`, `fs-hardlink`, and nested `fs-directory` children. * `git-tree-entry` represents a blob in git's tree — a specific file's content at a specific path and mode. The corresponding file on disk (if checked out) is an `fs-file`. The `file` virtual type bridges these two when their content, name, and permissions are identical. * **4 user-addable types**: `git-checkout` (local repo), `git` (remote or local metadata-only), `fs-mount` (mount point), `fs-directory` (arbitrary directory). ##### Built-in Type Hierarchy The parent-child relationships between built-in resource types form three layers — git structure, git checkout (composition), and filesystem — bridged by virtual identity types: ```kroki-plantuml @startuml skinparam defaultFontSize 11 skinparam objectFontSize 11 skinparam packageStyle rectangle package "GIT-CHECKOUT (composition)" as GC #LightBlue { object "git-checkout" as gc { /home/user/projects/myapp } } package "GIT STRUCTURE" as GS #LightYellow { object "git" as git { repo object DB } object "git-remote" as remote { origin } object "git-tag" as tag { v1.0.0 } object "git-submodule" as submod { lib/shared } object "git-branch" as branch { main } object "git-stash" as stash { stash@0 } object "git-commit" as commit { a1b2c3d } object "git-tree" as tree { e8f1... root } object "git-tree-entry" as entry1 { README.md } object "git-tree" as subtree { src/ subtree } object "git-tree-entry" as entry2 { src/app.ts } object "git-tree-entry" as entry3 { src/main.ts } } package "FILESYSTEM (worktree)" as FS #LightGreen { object "fs-directory" as fsroot { worktree root } object "fs-directory" as srcdir { src/ } object "fs-file" as readme { README.md } object "fs-file" as app { app.ts } object "fs-file" as main { main.ts } } package "STANDALONE FS-DIRECTORY" as SFS #Wheat { object "fs-directory" as sfs { /opt/deploy/myapp } object "fs-directory" as ssrcdir { src/ } object "fs-file" as sreadme { README.md } object "fs-file" as sapp { app.ts } object "fs-file" as smain { main.ts } object "fs-symlink" as symlink { link.txt } } package "STANDALONE FS-MOUNT" as SM #LightCoral { object "fs-mount" as mount { /mnt/data } object "fs-directory" as mountroot { root: / } } package "VIRTUAL LAYER (abstract identities)" as VL #Lavender { object "file" as vfile { app.ts @ sha256:9f8e... } object "directory" as vdir { src/ @ merkle:3d4f... } object "commit" as vcommit { a1b2c3d } object "branch" as vbranch { main @ a1b2c3d } object "remote" as vremote { github.com/org/repo } object "tree" as vtree { e8f1...9d2a } } gc --> git gc --> fsroot mount --> mountroot git --> remote git --> tag git --> submod git --> branch git --> stash branch --> commit commit --> tree tree --> entry1 tree --> subtree subtree --> entry2 subtree --> entry3 fsroot --> srcdir fsroot --> readme srcdir --> app srcdir --> main sfs --> ssrcdir sfs --> sreadme sfs --> symlink ssrcdir --> sapp ssrcdir --> smain app ..> vfile : equivalent sapp ..> vfile : equivalent entry2 ..> vfile : equivalent srcdir ..> vdir : equivalent ssrcdir ..> vdir : equivalent subtree ..> vdir : equivalent commit ..> vcommit : equivalent branch ..> vbranch : equivalent remote ..> vremote : equivalent tree ..> vtree : equivalent @enduml ``` **Reading the diagram:** * **Top left**: A `git-checkout` resource decomposes into a `git` child (left — the repository's full structure) and an `fs-directory` child (center — the worktree root directory at `/home/user/projects/myapp`). The worktree root is a directory, not a mount point. * **Git structure** (left column): The `git` child contains `git-remote` (origin), `git-tag` (v1.0.0), `git-submodule` (lib/shared), `git-stash` (stash@{0}), and `git-branch` (main). The branch contains `git-commit` objects, each commit contains a root `git-tree`, and trees contain `git-tree-entry` (blobs) and nested `git-tree` (subtrees). This properly models git's internal object structure. * **Filesystem** (center/right): The worktree's `fs-directory` contains `src/` (an `fs-directory`), `README.md` (an `fs-file`), and files including `fs-symlink` resources. A standalone `fs-directory` (`/opt/deploy/myapp`) with the same structure. A standalone `fs-mount` (`/mnt/data`) with a root `fs-directory` child. * **Virtual layer** (boxed area): Shows how virtual types link equivalent physical resources: - A `file` virtual resource links `fs-file` and `git-tree-entry` resources that have the same content, filename, and permissions — bridging the filesystem and git layers. - A `directory` virtual resource links `fs-directory` and `git-tree` resources with the same recursive content. - A `commit` virtual resource links `git-commit` resources across repos with the same commit hash. - A `branch` virtual resource links `git-branch` resources across repos with the same name and HEAD. - A `remote` virtual resource links `git-remote` resources across repos with the same URL. - A `tree` virtual resource links `git-tree` resources across repos/commits with the same tree hash. **Key separations:** * **`git` vs `git-checkout`**: A `git` resource represents a specific repository instance (local or remote). It can exist without any local directory (created from a remote URL — the repo exists on the remote server). A `git-checkout` always has both a `git` child and an `fs-directory` child — it represents a locally cloned repo with files on disk. * **`git-tree-entry` vs `fs-file`**: A `git-tree-entry` is a blob entry in git's tree (path + content hash + mode). An `fs-file` is a physical file on disk. When a repo is checked out, both exist and typically have matching content — the `file` virtual type links them when content, name, and permissions match. * **`git-tree` vs `fs-directory`**: A `git-tree` is a tree object in git's object database (a directory listing at a commit). An `fs-directory` is a physical directory on disk. The `directory` virtual type links them when their recursive contents match. * **`git-commit` → `git-tree` → `git-tree-entry`**: This chain properly models git internals. Commits point to a root tree, trees contain entries (blobs) and subtrees. The old design skipped the tree level; the current design preserves it. * **`fs-mount` vs `fs-directory`**: An `fs-mount` is a mount point (e.g., `/mnt/data`). The filesystem type (ext4, btrfs, etc.) is a property. The root directory is an `fs-directory` child. An `fs-directory` is a directory — it can be a child of `fs-mount`, `git-checkout`, or another `fs-directory`, or it can be registered standalone by the user. * **`git-checkout` composes with `fs-directory`, not `fs-mount`**: A git checkout's worktree is a directory on an existing filesystem, not a separate mount point. This is why `git-checkout`'s required child is `fs-directory` (the worktree root), not `fs-mount`. * **Virtual types bridge physical equivalents**: `file` bridges `fs-file` + `git-tree-entry` (cross-layer). `directory` bridges `fs-directory` + `git-tree` (cross-layer). `commit`, `branch`, `tag`, `remote`, `submodule`, and `tree` link the same git structural element across different repos. ##### Concrete Example: A Made-Up Project Consider a web application called "Acme Dashboard" with three registered resources: 1. **`local/acme-app`** — a checked-out git repo at `/home/alice/projects/acme-dashboard` (type: `git-checkout`) 2. **`local/acme-upstream`** — a git repo accessed via remote URL, not cloned (type: `git`) 3. **`local/acme-deploy`** — a standalone directory at `/opt/deploy/acme-dashboard` containing a production build snapshot (type: `fs-directory`) **Registration:** 

# 1) Checked-out git repo (has local files on disk)
agents resource add git-checkout local/acme-app \
  --path /home/alice/projects/acme-dashboard --branch main

# 2) Git repo via remote URL (no local checkout — metadata only)
agents resource add git local/acme-upstream \
  --url git@github.com:acmecorp/dashboard.git

# 3) Standalone directory (not a git repo — just files on disk)
agents resource add fs-directory local/acme-deploy \
  --path /opt/deploy/acme-dashboard
**What gets auto-discovered for each:** **`local/acme-app`** (type: `git-checkout`) discovers two children — a `git` and an `fs-directory` (the worktree root): ```kroki-plantuml @startwbs * local/acme-app\n(git-checkout / physical) ** local/acme-app:repo\n(git / physical) *** acme-app:repo:origin\n(git-remote)\ngit@github.com:acmecorp/dashboard.git *** acme-app:repo:v1.0.0\n(git-tag) *** acme-app:repo:lib/shared\n(git-submodule @ c4d5e6f) *** acme-app:repo:stash@0\n(git-stash) *** acme-app:repo:main\n(git-branch) **** main:a7f3e21\n(git-commit) ***** main:a7f3e21:tree\n(git-tree / root) ****** a7f3e21:README.md\n(git-tree-entry) ****** a7f3e21:package.json\n(git-tree-entry) ****** a7f3e21:src/\n(git-tree / subtree) ******* a7f3e21:src/app.ts\n(git-tree-entry) ******* a7f3e21:src/api.ts\n(git-tree-entry) ******* a7f3e21:src/utils.ts\n(git-tree-entry) *** acme-app:repo:develop\n(git-branch) **** develop:b2c4d8e\n(git-commit) ***** develop:b2c4d8e:tree\n(git-tree) ****** b2c4d8e:src/\n(git-tree) ******* b2c4d8e:src/app.ts\n(git-tree-entry) ******* b2c4d8e:src/api.ts\n(git-tree-entry / modified) ** local/acme-app:worktree\n(fs-directory / physical)\n/home/alice/projects/acme-dashboard/ *** worktree:src/\n(fs-directory) **** worktree:src/app.ts\n(fs-file) **** worktree:src/api.ts\n(fs-file) **** worktree:src/utils.ts\n(fs-file) *** worktree:package.json\n(fs-file) *** worktree:README.md\n(fs-file) *** worktree:docs -> ../docs\n(fs-symlink) @endwbs ``` When the `git-checkout` contains a `.devcontainer/devcontainer.json`, an additional `devcontainer-instance` child is auto-discovered: ```kroki-plantuml @startwbs * local/acme-app\n(git-checkout / physical) ** local/acme-app:repo\n(git / physical) *** (branches, commits, trees, ...) ** local/acme-app:worktree\n(fs-directory / physical) *** worktree:.devcontainer/\n(fs-directory) **** worktree:.devcontainer/devcontainer.json\n(fs-file) *** worktree:src/\n(fs-directory) **** worktree:src/app.ts\n(fs-file) *** worktree:package.json\n(fs-file) ** local/acme-app:devcontainer\n(devcontainer-instance / discovered) *** [container-mount — pending activation] *** [container-exec-env — pending activation] *** [container-port — pending activation] @endwbs ``` The `devcontainer-instance` is in `discovered` state — its container-mount, container-exec-env, and container-port children are only created when the container is activated during plan execution. This is consistent with lazy sandboxing: no container is built until a tool actually needs to execute inside it. The `git-checkout` cleanly separates two concerns: the `git` child contains version control structure (remotes, branches, tags, stashes, submodules, commits, trees, and tree entries — git's full object model), while the `fs-directory` child is the worktree root directory containing the actual files on disk. Note how git's internal structure is fully modeled: `git-commit` → `git-tree` (root tree object) → `git-tree-entry` (blobs) and nested `git-tree` (subtrees). The worktree root is a directory (`fs-directory`), not a mount point — `git-checkout` does not own an `fs-mount` resource because a git checkout's worktree is just a directory on an existing filesystem. When content matches (as it does for a clean checkout), virtual types link the `fs-file` and `git-tree-entry` resources. **`local/acme-upstream`** (type: `git`, remote URL — NOT checked out) discovers: ```kroki-plantuml @startwbs * local/acme-upstream\n(git / physical)\ngit@github.com:acmecorp/dashboard.git ** acme-upstream:origin\n(git-remote) ** acme-upstream:v1.0.0\n(git-tag) ** acme-upstream:main\n(git-branch) *** main:a7f3e21\n(git-commit) **** main:a7f3e21:tree\n(git-tree) ***** a7f3e21:src/\n(git-tree) ****** a7f3e21:src/app.ts\n(git-tree-entry) ****** a7f3e21:src/api.ts\n(git-tree-entry) ** acme-upstream:develop\n(git-branch) *** ...\n(remaining structure) @endwbs ``` A standalone `git` resource has **full access to branches, tags, commits, trees, and tree entries** — everything in the git object database — but **no `fs-directory` child** and **no `fs-file` resources**. There are no files on the local disk (the repo exists on GitHub's servers). Tools that need local file access cannot bind to it. This is the key difference from `git-checkout`: a `git` resource represents a specific repo instance. Plans can reason about history, diffs between branches, remote relationships — without a local clone. A `git-checkout` adds the local worktree directory on top. **`local/acme-deploy`** (type: `fs-directory`, standalone) discovers: ```kroki-plantuml @startwbs * local/acme-deploy\n(fs-directory / physical)\n/opt/deploy/acme-dashboard/ ** acme-deploy:src/\n(fs-directory) *** acme-deploy:src/app.ts\n(fs-file) *** acme-deploy:src/api.ts\n(fs-file) *** acme-deploy:src/utils.ts\n(fs-file) ** acme-deploy:package.json\n(fs-file) ** acme-deploy:README.md\n(fs-file) @endwbs ``` A standalone `fs-directory` — no git metadata, no branches, no commits, no tree entries. Just a directory containing files and subdirectories. Uses the **same `fs-directory` and `fs-file` types** as the git checkout's worktree root. **Virtual resource linking across all three:** After all three resources are registered, the system detects equivalent physical resources and creates virtual parents to link them: ```kroki-plantuml @startuml skinparam defaultFontSize 10 skinparam objectFontSize 10 skinparam packageStyle rectangle left to right direction package "PHYSICAL: local/acme-app" as P1 #LightBlue { object "fs-directory" as acmeWtSrc { worktree:src/ } object "fs-file" as acmeWtApp { worktree:src/app.ts } object "fs-file" as acmeWtUtils { worktree:src/utils.ts } object "fs-file" as acmeWtApi { worktree:src/api.ts } object "git-tree" as acmeGitSrc { main:a7f3e21:src/ } object "git-tree-entry" as acmeGitApp { main:src/app.ts } object "git-tree-entry" as acmeGitUtils { main:src/utils.ts } object "git-tree-entry" as acmeGitApi { main:src/api.ts } object "git-commit" as acmeCommit { main:a7f3e21 } object "git-branch" as acmeBranch { main } object "git-tag" as acmeTag { v1.0.0 } object "git-remote" as acmeRemote { origin } object "git-tree" as acmeTree { main:a7f3e21:tree } object "git-submodule" as acmeSubmod { lib/shared } } package "PHYSICAL: local/acme-deploy" as P2 #LightGreen { object "fs-directory" as deploySrc { src/ } object "fs-file" as deployApp { src/app.ts } object "fs-file" as deployUtils { src/utils.ts } object "fs-file" as deployApi { src/api.ts } } package "PHYSICAL: local/acme-upstream" as P3 #LightYellow { object "git-tree" as upstreamSrc { main:a7f3e21:src/ } object "git-tree-entry" as upstreamApp { main:src/app.ts } object "git-tree-entry" as upstreamUtils { main:src/utils.ts } object "git-tree-entry" as upstreamApi { main:src/api.ts } object "git-commit" as upstreamCommit { main:a7f3e21 } object "git-branch" as upstreamBranch { main } object "git-tag" as upstreamTag { v1.0.0 } object "git-remote" as upstreamRemote { origin } object "git-tree" as upstreamTree { main:a7f3e21:tree } } package "VIRTUAL LAYER\n(auto-created by equivalence)" as VL #Lavender { object "directory" as vDir { src/ (merkle:3d4f...) } object "file" as vAppTs { app.ts (sha256:9f8e...) } object "file" as vUtilsTs { utils.ts (sha256:a2b1...) } object "file" as vApiTs { api.ts (sha256:e1d3...) } object "commit" as vCommit { a7f3e21 } object "branch" as vBranch { main @ a7f3e21 } object "tag" as vTag { v1.0.0 } object "remote" as vRemote { github.com:acmecorp/dashboard.git } object "tree" as vTree { e8f1...9d2a } object "submodule" as vSubmod { lib/shared } } acmeWtSrc ..> vDir deploySrc ..> vDir acmeGitSrc ..> vDir upstreamSrc ..> vDir acmeWtApp ..> vAppTs deployApp ..> vAppTs acmeGitApp ..> vAppTs upstreamApp ..> vAppTs acmeWtUtils ..> vUtilsTs deployUtils ..> vUtilsTs acmeGitUtils ..> vUtilsTs upstreamUtils ..> vUtilsTs acmeWtApi ..> vApiTs deployApi ..> vApiTs acmeGitApi ..> vApiTs upstreamApi ..> vApiTs note "NOT linked: develop:b2c4d8e:src/api.ts\n(different content on develop branch)" as N1 acmeCommit ..> vCommit upstreamCommit ..> vCommit acmeBranch ..> vBranch upstreamBranch ..> vBranch acmeTag ..> vTag upstreamTag ..> vTag acmeRemote ..> vRemote upstreamRemote ..> vRemote acmeTree ..> vTree upstreamTree ..> vTree acmeSubmod ..> vSubmod @enduml ``` **How the `directory` virtual type works:** The `directory` virtual resource for `src/` exists because the `src/` directory has identical recursive content across multiple physical locations. Its children include both `fs-directory` resources (physical directories on disk) and `git-tree` resources (tree objects in git's object database). The system detects directory equivalence by computing a Merkle hash over the sorted child content hashes. If someone adds a file to the deploy directory but not the git checkout's worktree, the Merkle hashes diverge, and `local/acme-deploy:src/` is unlinked from the `directory` virtual parent. **How the `file` virtual type works:** The `file` virtual type links physical resources that represent the same file — identical content bytes, filename, and permissions. It bridges across layers: an `fs-file` on disk and a `git-tree-entry` in git's tree are linked when they have matching content. This is the primary cross-layer bridge. When content diverges (e.g., an uncommitted edit), the virtual link is broken. **How `commit` works across repos:** When two `git` resources share history (e.g., a fork and its upstream), the same commit hash will appear in both repos' branches. The `commit` virtual type links these — the commit object `a7f3e21` in the local repo and `a7f3e21` in the upstream repo are the same commit, and the virtual parent captures this identity. **Divergence scenario:** If a developer edits `src/api.ts` in the deploy directory (`/opt/deploy/acme-dashboard/src/api.ts`), the system detects the content hash change and: 1. Unlinks `local/acme-deploy:src/api.ts` from `file: api.ts (sha256:e1d3...8a9b)` (content no longer matches). 2. Unlinks `local/acme-deploy:src/` from `directory: src/ (merkle:3d4f...a2b1)` (directory contents no longer identical — the Merkle hash has changed). 3. The git checkout's worktree files and git-tree-entry resources remain linked (their content hasn't changed). 4. If the edit makes the deploy file match some *other* known content hash, a new virtual link may be created. Additional resource types (databases, APIs, cloud infrastructure, etc.) can be added as **custom resource types** via `agents resource type add`. ##### Cloud Infrastructure Resource Types Cloud infrastructure types follow a hierarchical model with two layers: 1. **Generic cloud base types** (`cloud-*`) — provider-agnostic abstractions for common cloud concepts (compute, network, storage, IAM, observability, messaging, containers). These are abstract (not user-addable) and serve as inheritance roots. 2. **Provider-specific types** (e.g., `aws-*`) — concrete types that inherit from the generic base layer and model a specific provider's resource hierarchy. **Generic Cloud Base Types** (19 types — abstract, not user-addable): | Type | Category | Description | |------|----------|-------------| | `cloud-account` | Structure | Cloud provider account or subscription | | `cloud-region` | Structure | Geographic region within an account | | `cloud-network` | Network | Virtual network (VPC, VNet, etc.) | | `cloud-subnet` | Network | Subnet within a virtual network | | `cloud-security-group` | Network | Network security rules / firewall group | | `cloud-load-balancer` | Network | Network load balancer | | `cloud-compute-instance` | Compute | Virtual machine or compute instance | | `cloud-object-store` | Storage | Object / blob storage bucket | | `cloud-block-storage` | Storage | Block storage volume | | `cloud-identity-principal` | IAM | IAM user or service principal | | `cloud-role` | IAM | IAM role | | `cloud-policy` | IAM | IAM or access policy document | | `cloud-log-group` | Observability | Log aggregation group | | `cloud-alarm` | Observability | Monitoring alarm or alert | | `cloud-queue` | Messaging | Message queue | | `cloud-topic` | Messaging | Pub/sub notification topic | | `cloud-container-repo` | Containers | Container image registry / repository | | `cloud-container-cluster` | Containers | Container orchestration cluster | | `cloud-container-service` | Containers | Container workload / service | **AWS Provider Types** (39 types — inheriting from generic base where applicable): | Type | Inherits | User Addable | Parent Types | Category | |------|----------|-------------|--------------|----------| | `aws-account` | `cloud-account` | **yes** | (root) | Account | | `aws-region` | `cloud-region` | no | `aws-account` | Structure | | `aws-vpc` | `cloud-network` | no | `aws-region` | Network | | `aws-subnet` | `cloud-subnet` | no | `aws-vpc` | Network | | `aws-igw` | — | no | `aws-vpc` | Network | | `aws-nat-gw` | — | no | `aws-subnet`, `aws-vpc` | Network | | `aws-route-table` | — | no | `aws-vpc` | Network | | `aws-nacl` | — | no | `aws-vpc` | Network | | `aws-security-group` | `cloud-security-group` | no | `aws-vpc` | Network | | `aws-alb` | `cloud-load-balancer` | no | `aws-vpc` | Network | | `aws-nlb` | `cloud-load-balancer` | no | `aws-vpc` | Network | | `aws-target-group` | — | no | `aws-vpc` | Network | | `aws-listener` | — | no | `aws-alb`, `aws-nlb` | Network | | `aws-ec2-instance` | `cloud-compute-instance` | no | `aws-subnet`, `aws-region` | Compute | | `aws-ami` | — | no | `aws-region` | Compute | | `aws-launch-template` | — | no | `aws-region` | Compute | | `aws-asg` | — | no | `aws-region` | Compute | | `aws-s3-bucket` | `cloud-object-store` | no | `aws-region` | Storage | | `aws-ebs-volume` | `cloud-block-storage` | no | `aws-region` | Storage | | `aws-efs-filesystem` | — | no | `aws-region` | Storage | | `aws-iam-user` | `cloud-identity-principal` | no | `aws-account` | IAM | | `aws-iam-role` | `cloud-role` | no | `aws-account` | IAM | | `aws-iam-policy` | `cloud-policy` | no | `aws-account` | IAM | | `aws-iam-instance-profile` | — | no | `aws-account` | IAM | | `aws-cloudwatch-log-group` | `cloud-log-group` | no | `aws-region` | Observability | | `aws-cloudwatch-alarm` | `cloud-alarm` | no | `aws-region` | Observability | | `aws-cloudwatch-metric` | — | no | `aws-region` | Observability | | `aws-eventbridge-bus` | — | no | `aws-region` | Observability | | `aws-eventbridge-rule` | — | no | `aws-eventbridge-bus` | Observability | | `aws-eventbridge-target` | — | no | `aws-eventbridge-rule` | Observability | | `aws-sqs-queue` | `cloud-queue` | no | `aws-region` | Messaging | | `aws-sns-topic` | `cloud-topic` | no | `aws-region` | Messaging | | `aws-sns-subscription` | — | no | `aws-sns-topic` | Messaging | | `aws-ecr-repo` | `cloud-container-repo` | no | `aws-region` | Containers | | `aws-ecs-cluster` | `cloud-container-cluster` | no | `aws-region` | Containers | | `aws-ecs-service` | `cloud-container-service` | no | `aws-ecs-cluster` | Containers | | `aws-ecs-task-def` | — | no | `aws-region` | Containers | | `aws-eks-cluster` | `cloud-container-cluster` | no | `aws-region` | Containers | | `aws-eks-nodegroup` | — | no | `aws-eks-cluster` | Containers | **GCP and Azure** are registered as flat provider-level types inheriting from `cloud-account`. Full hierarchies for these providers are deferred to future PRs. Only `aws-account` is user-addable — it is the top-level entry point carrying credential CLI args (`--access-key-id`, `--secret-access-key`, `--session-token`, `--region`, `--profile`). All other AWS types are children discovered or created within the account/region/VPC containment hierarchy. Cloud resource execution is **stubbed** — the handler validates configuration and resolves credentials but raises `NotImplementedError` for actual sandbox provisioning. Cloud SDK integration is planned for a future milestone. ##### Database Resource Types Built-in database types use the `transaction_rollback` sandbox strategy: | Type | User Addable | Sandbox | Description | |------|-------------|---------|-------------| | `postgres` | yes | `transaction_rollback` | PostgreSQL database connection | | `mysql` | yes | `transaction_rollback` | MySQL database connection | | `sqlite` | yes | `transaction_rollback` | SQLite database file | | `duckdb` | yes | `transaction_rollback` | DuckDB database (file-based or in-memory) | Networked databases (`postgres`, `mysql`) accept `--connection-string`, `--host`, `--port`, `--dbname`, `--user`, `--password` CLI args. File-based databases (`sqlite`, `duckdb`) accept `--path`. Database hierarchy restructuring (inheritance from a generic `database` base type) is deferred to a separate effort. ##### Custom Resource Types Custom resource types are defined in YAML configuration files and registered via `agents resource type add`. Once registered, a custom type automatically becomes available as a new subcommand under `agents resource add`. 

# File: resource-types/database.yaml
cleveragents:
  version: "3.0"

resource_type:
  name: local/database
  description: "A SQL database (PostgreSQL, MySQL, SQLite, etc.)"
  physical_or_virtual: physical
  user_addable: true

  # CLI arguments for `agents resource add local/database`
  cli_arguments:
    - name: connection-string
      type: string
      required: true
      description: "Database connection string (e.g., postgresql://host/dbname)"
      validation:
        pattern: "^(postgresql|mysql|sqlite)://"
    - name: schema
      type: string
      required: false
      description: "Default schema to use"
    - name: read-only
      type: boolean
      required: false
      default: false
      description: "Whether the database should be treated as read-only"

  # Sandbox and handler
  sandbox_strategy: transaction_rollback
  handler: DatabaseHandler
  checkpointable: true

  # Allowed parent types (empty means can be top-level)
  allowed_parent_types: []

  # Child types
  child_types:
    - type: local/db-schema
      auto_discover: true
      manual_link: false
      description: "Discovered database schemas"
    - type: local/db-table
      auto_discover: true
      manual_link: false
      description: "Discovered tables within schemas"

  # Capabilities
  capabilities:
    readable: true
    writable: true
    sandboxable: true
    checkpointable: true
When this type is registered: 

agents resource type add --config ./resource-types/database.yaml
# Now available: agents resource add local/database <NAME> --connection-string CONN [--schema SCHEMA] [--read-only]
The `user_addable` field determines whether the type appears as a subcommand. Types with `user_addable: false` are only auto-generated as children — for example, `git-remote`, `git-branch`, `git-commit`, and `git-tree-entry` are never created directly by users but are discovered when a `git` (or `git-checkout`) resource is registered. #### The Resource DAG Resources form a **directed acyclic graph** (DAG), not a simple tree. A resource can have **multiple parents** and **multiple children**, subject to type constraints. The diagram below shows how a `git-checkout`, a standalone `git` repo (remote), a standalone `fs-directory`, and virtual resources interconnect: ```kroki-plantuml @startuml skinparam defaultFontSize 10 skinparam objectFontSize 10 skinparam packageStyle rectangle package "GIT-CHECKOUT: local/app" as GCO #LightBlue { object "git-checkout" as gco { local/app } object "git" as gcoGit { local/app:repo } object "git-remote" as gcoRemote { origin } object "git-tag" as gcoTag { v1.0.0 } object "git-branch" as gcoBranch { main } object "git-commit" as gcoCommit { a1b2c3d } object "git-tree" as gcoTree { e8f1... root } object "git-tree-entry" as gcoEntry1 { README.md } object "git-tree" as gcoSubtree { src/ } object "git-tree-entry" as gcoEntry2 { src/app.ts } object "git-tree-entry" as gcoEntry3 { src/main.ts } object "fs-directory" as gcoFs { local/app:worktree } object "fs-directory" as gcoSrcDir { src/ } object "fs-file" as gcoReadme { README.md } object "fs-file" as gcoApp { app.ts } object "fs-file" as gcoMain { main.ts } } package "GIT (remote): local/upstream" as GR #LightYellow { object "git" as gr { local/upstream } object "git-remote" as grRemote { origin } object "git-tag" as grTag { v1.0.0 } object "git-branch" as grBranch { main } object "git-commit" as grCommit { a1b2c3d } object "git-tree" as grTree { e8f1... root } object "git-tree-entry" as grEntry1 { README.md } object "git-tree" as grSubtree { src/ } object "git-tree-entry" as grEntry2 { src/app.ts } object "git-tree-entry" as grEntry3 { src/main.ts } } package "STANDALONE FS-DIRECTORY: local/deploy" as SFD #LightGreen { object "fs-directory" as sfd { /opt/deploy/myapp } object "fs-directory" as sfdSrcDir { src/ } object "fs-file" as sfdReadme { README.md } object "fs-file" as sfdApp { app.ts } object "fs-file" as sfdMain { main.ts } } package "VIRTUAL LAYER" as VL #Lavender { object "file" as vFile { app.ts@v1 } object "directory" as vDir { src/@v1 } object "commit" as vCommit { a1b2c3d } object "branch" as vBranch { main@a1b... } object "tag" as vTag { v1.0.0 } object "remote" as vRemote { github.com/org/repo } object "tree" as vTree { e8f1...9d2a } } ' Physical hierarchy gco --> gcoGit gco --> gcoFs gcoGit --> gcoRemote gcoGit --> gcoTag gcoGit --> gcoBranch gcoBranch --> gcoCommit gcoCommit --> gcoTree gcoTree --> gcoEntry1 gcoTree --> gcoSubtree gcoSubtree --> gcoEntry2 gcoSubtree --> gcoEntry3 gcoFs --> gcoSrcDir gcoFs --> gcoReadme gcoSrcDir --> gcoApp gcoSrcDir --> gcoMain gr --> grRemote gr --> grTag gr --> grBranch grBranch --> grCommit grCommit --> grTree grTree --> grEntry1 grTree --> grSubtree grSubtree --> grEntry2 grSubtree --> grEntry3 sfd --> sfdSrcDir sfd --> sfdReadme sfdSrcDir --> sfdApp sfdSrcDir --> sfdMain ' Virtual equivalence links gcoApp ..> vFile sfdApp ..> vFile gcoEntry2 ..> vFile grEntry2 ..> vFile gcoSrcDir ..> vDir sfdSrcDir ..> vDir gcoSubtree ..> vDir grSubtree ..> vDir gcoCommit ..> vCommit grCommit ..> vCommit gcoBranch ..> vBranch grBranch ..> vBranch gcoTag ..> vTag grTag ..> vTag gcoRemote ..> vRemote grRemote ..> vRemote gcoTree ..> vTree grTree ..> vTree @enduml ``` **Key properties of the DAG:** 1. **Multiple parents**: A `git-tree-entry` has a `git-tree` parent (git structure) and potentially a `file` virtual parent (content identity). An `fs-file` has an `fs-directory` parent (filesystem hierarchy) and potentially a `file` virtual parent. An `fs-directory` can be a child of `git-checkout` (as its worktree root), a child of `fs-mount` (as the mount root), a child of another `fs-directory` (as a subdirectory), a child of a `directory` virtual (identity), or a standalone user-registered resource. 2. **Multiple children**: A `git-checkout` has a `git` child and an `fs-directory` child. A `git` resource has `git-remote`, `git-branch`, `git-tag`, `git-stash`, `git-submodule`, and `git-commit` children. A `git-commit` has a `git-tree` child. A `git-tree` has `git-tree-entry` and nested `git-tree` children. 3. **Cycles are forbidden**: The graph is always a DAG. The system validates this when links are created. 4. **Type constraints**: Not any resource can be a child of any other — the parent's resource type defines which child types are allowed (see the Allowed Parents / Allowed Children columns in the built-in types tables). 5. **Cross-layer bridge**: Virtual resources link equivalent physical resources from different layers (git structure, filesystem, different repos). The `file` virtual type bridges `fs-file` + `git-tree-entry`. The `directory` virtual type bridges `fs-directory` + `git-tree`. The `commit`, `branch`, `tag`, `remote`, `submodule`, and `tree` virtual types link the same git structural element across different repositories. ##### Purpose of the Resource DAG !!! adr "Architecture Decision" The operational semantics of the resource DAG — what the DAG is for at runtime — are defined in [ADR-036: Resource DAG Operational Semantics](adr/ADR-036-resource-dag-operational-semantics.md). Tool reachability and access projection are defined in [ADR-037](adr/ADR-037-tool-reachability-and-access-projection.md). Cross-mechanism coordination is defined in [ADR-038](adr/ADR-038-cross-mechanism-sandbox-coordination.md). The DAG is not just a structural record of resource relationships — it is the **topology of the system's operational world**. Every runtime decision about how to reach a resource, how to safely change it, and what else is affected flows through the DAG. The DAG answers five fundamental questions: | Question | DAG Feature | Runtime Operation | |----------|-------------|-------------------| | **What is this?** | Virtual resource identity (hub node linking equivalents) | Equivalence class queries, divergence detection | | **Where does it live?** | Physical manifestations and containment hierarchy | Auto-discovery, resource registration | | **How do I reach it?** | Tool binding → containment edges → access projection | Forward/inverse reachability, read/write routing | | **How do I safely change it?** | Sandbox boundaries and cross-mechanism coordination | Sandbox boundary algebra, coherence-aware commit | | **What else is affected?** | Descendant invalidation, ancestor propagation, sibling sync | Change propagation, access control propagation | These decompose into ten specific operational purposes: 1. **Tool reachability**: Knowing which tools can reach a resource transitively through containment. A tool bound to a `git-checkout` can reach every `fs-file` descendant. The inverse query — given a file, what tools can reach it — requires walking up containment edges. 2. **Equivalence and alternative paths**: Virtual resources link physical resources that represent the same logical identity. When one path is unavailable, the system finds alternatives through equivalence. 3. **Read/write routing**: Different physical manifestations of the same virtual resource offer different access richness. An `lsp-document` provides semantic reads (types, diagnostics); an `fs-file` via `git-checkout` provides sandbox-tracked writes. The DAG enables routing reads through the richest path and writes through the canonical sandbox-tracked path. 4. **Sandbox boundary algebra**: Not every resource is independently sandboxable. A file's sandbox boundary is its containing `git-checkout` or `fs-directory`. All resources sharing a sandbox boundary share one sandbox instance. The function `sandbox_boundary(r)` walks up containment edges to find the nearest sandboxable ancestor. 5. **Cross-mechanism sandbox coordination**: When the same virtual resource has physical manifestations in different sandbox domains (e.g., git-checkout and container mount), writes through one path must be coordinated with the other at commit time. The coherence property (`transparent`, `cached`, `independent`) on physical-to-virtual edges determines what coordination is needed. 6. **Dependency ordering**: The DAG provides topological orderings for lifecycle operations — sandbox creation (top-down), commit (bottom-up), rollback (top-down), cleanup (bottom-up), auto-discovery (top-down). 7. **Change propagation**: When a file changes, the DAG determines what else is affected: parent directories need status updates, virtual parents need identity re-evaluation, equivalent physical siblings need cache invalidation. 8. **Access control propagation**: A `read_only` constraint on a `git-checkout` propagates to all descendant files. The effective writability of a resource is the conjunction of its own writability and all its containment ancestors' writability. 9. **Auto-discovery scope**: The DAG defines the cascade structure for resource auto-discovery — directories before files, git repos before branches, containers before mounts. 10. **Tool capability inference**: A tool's effective write scope is bounded by the sandbox domain of its bound resource. A tool bound to an `fs-file` cannot create sibling directories; a tool bound to a `git-checkout` can reach the entire worktree. #### Physical vs Virtual Resources Resources are either **physical** or **virtual**, a distinction determined by their resource type. **Physical resources** are specific, concrete manifestations. Each physical resource is a particular instance that exists somewhere — a file at a particular path on a particular machine, a git repository at a particular URL on a particular server, a commit in a particular repo. Physical resources can be directly read and written by tools. Most resources are physical. **Virtual resources** represent an abstract identity that links equivalent physical resources. They answer the question: "where else does this same thing exist?" A `file` virtual resource links all the physical `fs-file` and `git-tree-entry` resources that have the same content, filename, and permissions. A `commit` virtual resource links `git-commit` resources across repos that share the same commit hash. Virtual resources have no location of their own and cannot be directly read or written. **Rules for the physical/virtual boundary:** 1. The **children of a virtual resource** can be physical resources, other virtual resources, or a combination of both. 2. A **physical resource's parents** can be either physical or virtual resources. 3. **Not all physical resources need a virtual parent**. Virtual resource linking is optional and only applies when equivalence tracking is meaningful. **Equivalence linking:** Two physical resources share a virtual parent when they are equivalent by the virtual type's criteria. Each virtual type has its own equivalence semantics: * **`file`**: Physical files (`fs-file` or `git-tree-entry`) share a `file` parent when they have the same content bytes (SHA-256), the same filename, and the same permissions. This is the primary cross-layer bridge — it links filesystem files with git blob entries. Example: `local/app:worktree:src/main.py` (an `fs-file`) and `local/app:repo:main:a1b...:src/main.py` (a `git-tree-entry`) both have the same content in a clean checkout, so they share a `file` virtual parent. * **`directory`**: Physical directories (`fs-directory`) and git trees (`git-tree`) share a `directory` parent when their full recursive contents are equivalent. This bridges the filesystem and git layers — the `src/` directory on disk and the `src/` subtree in git's tree object can be linked when their contents match. * **`symlink`**: Physical symlinks (`fs-symlink`) and git tree entries with symlink mode (`git-tree-entry` mode 120000) share a `symlink` parent when they have the same name and target. * **`commit`**: Physical commits (`git-commit`) in different repos share a `commit` parent when they have the same commit hash. This is common when repos share history (e.g., a fork and its upstream). * **`branch`**: Physical branches (`git-branch`) in different repos share a `branch` parent when they have the same name and the same HEAD commit hash. A push or local commit on one repo causes divergence. * **`tag`**: Physical tags (`git-tag`) in different repos share a `tag` parent when they have the same tag name and target object. * **`remote`**: Physical remotes (`git-remote`) in different repos share a `remote` parent when they point to the same URL. Answers: "these repos share the same upstream." * **`submodule`**: Physical submodules (`git-submodule`) in different repos share a `submodule` parent when they have the same submodule URL and path. * **`tree`**: Physical tree objects (`git-tree`) in different commits or repos share a `tree` parent when they have the same tree hash — identical directory structure and contents. **Divergence detection:** When a physical resource's content changes (e.g., a file is edited, a directory gains a new file, a branch advances), the system detects that it may no longer match its virtual parent's identity. At that point: * If the edit causes the physical resource to diverge from all other physical siblings under the same virtual parent, the physical resource is unlinked from that virtual parent. * If the edit makes it match a *different* virtual resource's identity, it may be re-linked. * Content equivalence is tracked via content hashing: SHA-256 for files, Merkle hashes for directories, tree hashes for git trees, commit hashes for commits, HEAD+name for branches, name+target for tags, URL for remotes. * **Cascading divergence**: When a `file` link breaks, the parent `directory` virtual resource is also re-evaluated (since its identity depends on all child identities). This enables powerful queries like: * "What physical locations exist for this file content?" → Find all physical resources sharing the `file` virtual parent. * "What tools can edit this file?" → Find all tools with resource bindings compatible with the physical resource types. * "Has this file been modified in any location?" → Check if all physical siblings still share the same `file` virtual parent. * "Are these two repos in sync?" → Check if their branches share a `branch` virtual parent. * "Which directories are identical across deployments?" → Find `directory` virtual resources with multiple physical children. * "What submodules are shared across projects?" → Find `submodule` virtual resources with multiple physical children. ##### Lazy Virtual Node Materialization !!! adr "Architecture Decision" Lazy virtual node materialization is defined in [ADR-038: Cross-Mechanism Sandbox Coordination](adr/ADR-038-cross-mechanism-sandbox-coordination.md). Virtual resource nodes are **not created eagerly** for every physical resource. They are materialized lazily when a second physical manifestation sharing the same identity is discovered. **Lifecycle:** 1. **Single manifestation**: A physical resource exists with no virtual parent. It has a content hash but no equivalence link. This is the common case — most files exist in only one location. 2. **Second manifestation discovered**: When a new physical resource is registered (or auto-discovered) and its identity matches an existing physical resource's identity (per the virtual type's equivalence rule), a virtual node is created and both physical resources are linked as children. 3. **Additional manifestations**: Subsequent physical resources matching the same identity are linked to the existing virtual node. 4. **Manifestation removed**: When a physical resource is deregistered or diverges, its edge to the virtual parent is removed. If only one physical child remains, the virtual node is removed (collapsed back to single manifestation). If zero remain, the virtual node is removed entirely. Each virtual type defines an **identity function** mapping physical resources to canonical identity keys: | Virtual Type | Identity Key | |-------------|--------------| | `file` | SHA-256(content) + filename + permissions | | `directory` | Merkle hash of recursive child identities | | `commit` | Commit hash | | `branch` | Branch name + HEAD commit hash | | `tag` | Tag name + target object | | `remote` | Normalized URL | | `submodule` | Submodule URL + path | | `tree` | Tree hash | | `symlink` | Symlink name + target path | Materialization is triggered by: resource registration, auto-discovery, content change detection, and on-demand refresh. ##### Coherence Property !!! adr "Architecture Decision" The coherence property and cross-mechanism coordination protocol are defined in [ADR-038: Cross-Mechanism Sandbox Coordination](adr/ADR-038-cross-mechanism-sandbox-coordination.md). Every edge from a physical resource to its virtual parent carries a **coherence** property describing how changes to this physical manifestation relate to other manifestations of the same virtual identity: | Coherence | Meaning | Sync Action at Commit | |-----------|---------|----------------------| | `transparent` | Changes are immediately visible in sibling manifestations (shared storage). | No action — verify by content hash. | | `cached` | The sibling caches content; changes require an explicit refresh signal. | Send invalidation signal (e.g., LSP `workspace/didChangeWatchedFiles`). | | `independent` | Siblings are fully independent copies; changes are invisible until explicit sync. | Copy content from canonical target, or unlink the sibling (accept divergence). | Common coherence assignments: | Scenario | Coherence | |----------|-----------| | `fs-file` via git-checkout ↔ `fs-file` via container bind mount | `transparent` (same inode through bind mount) | | `fs-file` via git-checkout ↔ `fs-file` via devcontainer workspace bind mount | `transparent` (default devcontainer behavior: bind mount) | | `fs-file` via git-checkout ↔ `fs-file` via devcontainer workspace volume mount | `independent` (configurable via `workspaceMount` in devcontainer.json) | | `fs-file` ↔ `lsp-document` | `cached` (LSP buffers file content) | | `fs-file` via git-checkout ↔ `fs-file` via container volume mount | `independent` (separate copy) | | `git-commit` in repo A ↔ `git-commit` in repo B | `independent` (same hash but separate stores) | ##### Cross-Mechanism Write Coordination When a plan modifies a physical resource that has siblings under the same virtual parent (i.e., equivalent physical resources in different sandbox domains), the system coordinates at **sandbox commit time** using a write-then-sync protocol: 1. **During execution**: Tools write through their bound physical resource into its sandbox domain. No cross-domain propagation occurs. Other manifestations see pre-sandbox content. 2. **At commit time**: The system identifies dirty virtual resources (virtual resources with at least one modified physical child), checks for conflicts (multiple dirty children of the same virtual), and propagates changes based on coherence. 3. **Conflict resolution**: If multiple physical manifestations of the same virtual resource were modified during the same plan: - **canonical-wins** (default): The canonical write target's changes are accepted; others are discarded with a warning. - **merge**: Three-way merge for text content. - **fail**: Reject the commit; surface the conflict for human resolution. - **last-writer-wins**: Accept the most recent modification. The **canonical write target** for a virtual resource is the physical manifestation in the strongest sandbox domain (`git_worktree` > `snapshot` > `copy_on_write` > `transaction_rollback`), with user override available. Writes should be routed to the canonical target whenever possible to avoid conflicts. #### Resource Registration (CLI) Resources are created via `agents resource add ` with type-specific arguments. Auto-discovered children are created automatically: 

# Register a checked-out git repository (most common)
agents resource add git-checkout local/api-repo --path /home/user/projects/api-service --branch main
# Auto-discovers: git child (repo metadata, remotes, branches, commits, tree entries)
#                 + fs-directory child (worktree root directory, subdirectories, files)

# Register a git repo via remote URL (no local checkout — exists on remote server)
agents resource add git local/upstream --url git@github.com:org/upstream.git
# Auto-discovers: remotes, branches, tags, commits, trees, tree entries, stashes, submodules
#                 (no fs-directory — not checked out locally)

# Register a standalone directory (not a git repo — just files on disk)
agents resource add fs-directory local/docs --path /opt/docs/api-reference
# Auto-discovers: subdirectories, files, symlinks, hardlinks

# Register a standalone filesystem mount (entire volume)
agents resource add fs-mount local/data-volume --mount-path /mnt/data
# Auto-discovers: root fs-directory, subdirectories, files, symlinks, hardlinks

# Link resources to projects (resources must be registered first)
agents project link-resource local/api-service local/api-repo
agents project link-resource local/api-service local/docs --read-only
#### Auto-Discovery When a resource is registered, its resource type's handler **auto-discovers child resources**. This process: 1. **Scans** the resource to identify children (e.g., a `git-checkout` handler creates a `git` child and an `fs-directory` child for the worktree root; a `git` handler lists remotes, branches, tags, commits, stashes, and submodules; a `git-commit` handler creates a root `git-tree` child; a `git-tree` handler lists tree entries and subtrees; an `fs-mount` handler creates a root `fs-directory` and discovers its contents; an `fs-directory` handler discovers subdirectories, files, symlinks, and hardlinks; a `git-checkout` or `fs-directory` handler additionally detects `.devcontainer/devcontainer.json` and creates a `devcontainer-instance` child in `discovered` state — see [ADR-043](adr/ADR-043-devcontainer-integration.md)). 2. **Creates** child resource records in the Resource Registry identified by auto-generated ULIDs. Auto-discovered children do not receive names — they are identified by ULID only, even if their resource type is user-addable. 3. **Reuses existing resources**: If a discovered child matches an already-registered resource (same type + same value/location), the existing resource is **linked** as a child rather than creating a duplicate. For example, if `local/docs` (an `fs-directory` resource at `/home/user/projects/api-service`) is already registered and the `git-checkout` handler discovers its worktree root at the same path, it links to the existing `local/docs` resource instead of creating a new one. 4. **Links virtual resources**: When auto-discovery detects that a physical resource's content matches an existing virtual resource (via content hashing), it links the physical resource as a child of the virtual resource. Auto-discovered children are marked as `auto: true` in the DAG, distinguishing them from manually linked children. Auto-discovered links cannot be manually unlinked (they are managed by the handler), while manually created links can be freely managed. Auto-discovery runs: * At registration time (`agents resource add`) * On refresh (when the system detects changes, e.g., new commits, new files) * On demand (when a tool accesses the resource and the handler detects staleness) ##### Devcontainer Auto-Discovery !!! adr "Architecture Decision" Devcontainer auto-discovery is defined in [ADR-043: Devcontainer Integration and Container-Project Association](adr/ADR-043-devcontainer-integration.md). When `git-checkout` or `fs-directory` auto-discovery scans the filesystem tree, if a `.devcontainer/devcontainer.json` file is found, a `devcontainer-instance` child resource is created with `provisioning_state: discovered`. The devcontainer.json is parsed to populate configuration properties (image, features, workspace mount, ports), but **no container is built or started** — consistent with the system's lazy sandboxing philosophy. Key behaviors: * **Lazy activation**: The container is only built when a plan first needs to execute a tool inside it. Child resources (`container-mount`, `container-exec-env`, `container-port`) are created on activation, not at discovery time. * **Multiple devcontainers**: Nested `.devcontainer/` directories (e.g., per-service devcontainers in a monorepo) each produce separate `devcontainer-instance` resources. The devcontainer spec supports [multiple named configurations](https://containers.dev/implementors/spec/#devcontainerjson) via `.devcontainer//devcontainer.json`. * **Workspace mount**: The devcontainer's workspace mount defaults to the parent `git-checkout` path (or `fs-directory` path). The `container-mount` relationship is recorded at discovery time but not materialized until activation. * **Auto-detected execution environment**: The discovered devcontainer automatically becomes the default execution environment for tools operating on the parent resource, subject to execution environment precedence rules (see [Execution Environment Routing](#execution-environment-routing)). #### Resource Capabilities Each resource declares its capabilities, derived from its resource type: | Capability | Description | |-----------|-------------| | `readable` | Whether the resource can be read | | `writable` | Whether the resource can be modified | | `sandboxable` | Whether the resource supports sandbox isolation | | `checkpointable` | Whether the resource supports checkpoint/rollback | These capabilities are used by the **tool execution flow** to validate that a tool's resource binding is compatible — a tool declaring `access: read_write` on a resource slot cannot be bound to a read-only resource. #### Resource Registry CleverAgents maintains a **Resource Registry** — a persistent catalog of all registered resources and their DAG relationships: ```kroki-plantuml @startuml skinparam classAttributeIconSize 0 skinparam classFontSize 13 skinparam defaultFontSize 12 class ResourceRegistry { - resourceIndex : Map - typeIndex : Map -- + add(type, name, properties) : ResourceRecord + update(name, properties) : ResourceRecord + remove(name) : void + lookup(name) : ResourceRecord + list(filters) : ResourceRecord[] + tree(name, depth) : DAG_subtree + link_child(parent, child) : void + unlink_child(parent, child) : void + refresh(name) : void + find_by_content(hash) : ResourceRecord[] + find_virtual_parent(resource) : ResourceRecord } class ResourceRecord { + name : String + type : String + physical_or_virtual : PhysVirt + properties : Map + capabilities : Capabilities + parents : List + children : List + content_hash : String + linked_projects : List + created_at : DateTime + updated_at : DateTime } class ResourceTypeRecord { + name : String + description : String + source : String + physical_or_virtual : PhysVirt + user_addable : Boolean + cli_arguments : List + allowed_parent_types : List + child_types : Map + sandbox_strategy : String + handler : String + capabilities : Capabilities + config_path : String } enum PhysVirt { physical virtual } ResourceRegistry "1" *-- "0..*" ResourceRecord : indexes resources > ResourceRegistry "1" *-- "0..*" ResourceTypeRecord : indexes types > ResourceRecord --> PhysVirt ResourceTypeRecord --> PhysVirt note right of ResourceRegistry **Populated by:** - agents resource add CLI - Auto-discovery during registration - Content-identity linking **Consumed by:** - Tool binding resolution - Sandbox creation - Change tracking - Project linking - Plan validation end note @enduml ``` The Resource Registry persists in the database (local SQLite or server). It works alongside the Tool Registry and Skill Registry. #### Resource Sandbox Strategy **Each resource defines its own sandbox strategy**, determined by its resource type. This is critical because: 1. The same resource may be accessed through different tools and skills 2. Different resource types require different sandboxing approaches 3. Some resources cannot be sandboxed at all | Resource Type | Sandbox Strategy | Rollback Mechanism | |--------------|------------------|-------------------| | `git-checkout` | `git_worktree` | Git reset/checkout | | `git` | `none` | N/A (represents a repo instance — not directly sandboxable) | | `fs-mount` | `copy_on_write`, `filesystem_copy`, or `overlay` | Restore from snapshot or delete copy | | `fs-directory` | `copy_on_write` or `filesystem_copy` | Restore from snapshot or delete copy | | Custom database types | `transaction_rollback` | Transaction rollback | | Custom API types | `none` (often not sandboxable) | N/A | **Filesystem sandbox strategies** differ in their prerequisites and tradeoffs: - **`copy_on_write`**: Leverages the filesystem's native copy-on-write capability (e.g., BTRFS, ZFS). The filesystem preserves original data blocks when edits occur, creating lightweight snapshots without duplicating data upfront. Only available on CoW-capable filesystems. - **`filesystem_copy`**: Performs an explicit full copy of the resource directory (e.g., via `cp`). Works on all writable filesystems regardless of CoW support, at the cost of duplicating data upfront. - **`overlay`**: Uses an overlay filesystem (e.g., OverlayFS) to layer changes on top of the original directory. Writes go to the upper layer while the lower layer remains untouched. Requires OS-level overlay mount support. The sandbox strategy is inherited by child resources from their parent unless the child type defines its own. For example, `git-branch`, `git-commit`, `git-tree`, and `git-tree-entry` all inherit from their `git` ancestor. `fs-file`, `fs-symlink`, and `fs-hardlink` inherit from their `fs-directory` parent. | Resource Type | Sandbox Strategy | Rollback Mechanism | |--------------|------------------|-------------------| | `container-instance` | `snapshot` | Container commit/checkpoint | | `devcontainer-instance` (inherits `container-instance`) | `snapshot` (inherited) | Container commit/checkpoint (inherited) | | `container-volume` | `snapshot` | Volume snapshot | | `container-mount` | (inherits from `container-instance`) | (inherits) | | `container-exec-env` | (inherits from `container-instance`) | (inherits) | | `lsp-server` | `none` | N/A (server process, not directly sandboxable) | | `lsp-workspace` | `none` (delegates to backing resource) | N/A | | `lsp-document` | `none` (delegates to backing file) | N/A | ##### Sandbox Boundary Algebra !!! adr "Architecture Decision" The sandbox boundary algebra is defined in [ADR-036: Resource DAG Operational Semantics](adr/ADR-036-resource-dag-operational-semantics.md). Not every resource in the DAG is independently sandboxable — a file cannot be sandboxed in isolation. Instead, the DAG has **sandbox boundaries**: specific nodes at which sandboxing is physically implementable. All resources within a sandbox boundary's domain share one sandbox instance. **Definitions:** * **Sandbox boundary**: A resource `b` where `b.capabilities.sandboxable == true` and `b.sandbox_strategy != none`. Examples: `git-checkout` (git_worktree), `fs-directory` (copy_on_write), `container-instance` (snapshot). * **`sandbox_boundary(r)`**: The nearest ancestor of `r` (inclusive) along `contains` edges that is a sandbox boundary. If `r` itself is a boundary, returns `r`. If no boundary exists in `r`'s ancestor chain, returns `None` (unsandboxable). * **Sandbox domain**: The set of all resources `{r : sandbox_boundary(r) == b}` — resources whose nearest sandbox boundary is `b`. All resources in a domain share the same sandbox instance during plan execution. **Properties:** 1. Sandbox domains **partition** all sandboxable resources into disjoint groups. 2. The `SandboxManager` keys sandboxes by `(plan_id, sandbox_boundary_id)`, not by individual resource ID. 3. Multiple files in the same git checkout share one git_worktree sandbox. 4. When a virtual resource has physical manifestations in **different sandbox domains** (e.g., a file in both a git-checkout domain and a container-instance domain), cross-mechanism coordination is needed at commit time (see Cross-Mechanism Write Coordination above). **Dependency ordering for lifecycle operations:** | Operation | Traversal Direction | Rationale | |-----------|-------------------|-----------| | Sandbox creation | Top-down (parent before child) | Parent must be sandboxed before children can be accessed within it | | Sandbox commit | Bottom-up (child before parent) | Child changes finalized before parent incorporates them | | Sandbox rollback | Top-down (parent before child) | Rolling back parent implicitly rolls back children | | Sandbox cleanup | Bottom-up (child before parent) | Clean up children before removing parent | #### Lazy Sandboxing Resources are **sandboxed lazily when accessed**, not upfront. This is different from indexing — resources are indexed immediately when registered, but sandboxes are only created when execution needs to modify a resource: 1. A project may link many resources (e.g., git repo + databases + cloud accounts) 2. A plan may only need to modify one resource 3. Only the accessed resources are sandboxed 4. Each plan/child plan has its own sandbox containing only edited resources This is efficient for large projects where most resources remain untouched. #### Resource Access Tracking The system tracks **which tools access which resources** through the tool-resource binding system. This tracking happens at multiple levels: 1. **Declaration-time**: Tool YAML declares resource slots with type and access mode (see **Resource Bindings** in the Tools section). 2. **Activation-time**: When a tool is activated for a plan, its resource slots are bound to specific resources. The system records these bindings. 3. **Execution-time**: Every tool invocation logs which bound resources were actually accessed, what operations were performed (read/write/delete), and what paths or objects were touched. This enables: * **Accurate sandbox scoping**: Only sandbox resources that will actually be modified. * **Rollback feasibility analysis**: Know exactly which resources were modified and whether they support rollback. * **Security auditing**: Complete record of which tools accessed which resources and how. * **Cross-resource impact analysis**: Determine if changes to a resource affect tools bound to sibling or child resources. * **Virtual resource consistency**: Detect when a physical resource diverges from its virtual parent. #### Unified Resource Abstraction Layer CleverAgents provides a unified abstraction that allows tools to work with any resource type through a consistent interface. This enables: 1. **Resource-agnostic tools**: A tool like `read_content(path)` works whether the path refers to a file, database record, or API endpoint. 2. **Consistent sandbox semantics**: All resources support the same sandbox lifecycle (create, read, write, checkpoint, rollback). 3. **Pluggable resource handlers**: New resource types can be added by registering custom resource types without modifying existing tools. 4. **Unified change tracking**: All resource modifications flow into the same ChangeSet model. ##### Resource Handler Interface Every resource type provides a handler that implements this interface: 

class ResourceHandler(Protocol):
    """Handler for a specific resource type."""

    def read(self, path: str, sandbox: Sandbox) -> Content:
        """Read content from the sandboxed resource."""
        ...

    def write(self, path: str, content: Content, sandbox: Sandbox) -> Change:
        """Write content and return the Change record."""
        ...

    def delete(self, path: str, sandbox: Sandbox) -> Change:
        """Delete resource and return the Change record."""
        ...

    def list(self, pattern: str, sandbox: Sandbox) -> list[str]:
        """List paths matching pattern."""
        ...

    def diff(self, path: str, sandbox: Sandbox) -> str:
        """Generate diff between sandbox and original state."""
        ...

    def supports_operation(self, operation: OperationType) -> bool:
        """Check if this resource supports the given operation."""
        ...

    def discover_children(self, resource: ResourceRecord) -> list[ResourceRecord]:
        """Auto-discover child resources (called at registration and refresh)."""
        ...

    def content_hash(self, path: str, sandbox: Sandbox) -> str:
        """Compute content hash for identity tracking."""
        ...

    def create_sandbox(self, resource: ResourceRecord) -> Sandbox:
        """Create a sandbox for this resource using its type's strategy."""
        ...

    def create_checkpoint(self, sandbox: Sandbox) -> Checkpoint:
        """Create a checkpoint within the sandbox."""
        ...

    def rollback_to(self, sandbox: Sandbox, checkpoint: Checkpoint) -> None:
        """Roll back sandbox state to a checkpoint."""
        ...

    def project_access(
        self,
        binding_resource: ResourceRecord,
        target_resource: ResourceRecord,
        containment_path: list[ResourceRecord],
        sandbox: Sandbox | None,
    ) -> AccessProjection | None:
        """Compute how to reach target_resource from binding_resource.

        Returns an AccessProjection with access_path, protocol,
        crosses_sandbox flag, and read_richness score. Returns None
        if this handler cannot project access to the target type.
        Used by the tool reachability and read/write routing system.
        """
        ...
##### Built-in Resource Handlers | Resource Type | Handler | Read | Write | Delete | Sandbox Strategy | |--------------|---------|------|-------|--------|------------------| | `git-checkout` | `GitCheckoutHandler` | ✓ | ✓ | ✓ | `git_worktree` | | `git` | `GitHandler` | ✓ | ✗ | ✗ | `none` | | `git-commit`, `git-tree`, `git-tree-entry` | `GitObjectHandler` | ✓ | ✗ | ✗ | (inherits) | | `git-branch`, `git-tag`, `git-stash` | `GitRefHandler` | ✓ | ✓ | ✓ | (inherits) | | `git-remote`, `git-submodule` | `GitConfigHandler` | ✓ | ✗ | ✗ | (inherits) | | `fs-mount` | `FilesystemHandler` | ✓ | ✓ | ✓ | `copy_on_write` | | `fs-directory` | `FilesystemHandler` | ✓ | ✓ | ✓ | `copy_on_write` | | `fs-file`, `fs-symlink`, `fs-hardlink` | `FilesystemHandler` | ✓ | ✓ | ✓ | (inherits) | | `container-runtime` | `ContainerRuntimeHandler` | ✓ | ✗ | ✗ | `none` | | `container-image` | `ContainerImageHandler` | ✓ | ✗ | ✗ | `none` | | `container-instance` | `ContainerInstanceHandler` | ✓ | ✓ | ✓ | `snapshot` | | `devcontainer-instance` (inherits `container-instance`) | `DevcontainerHandler` | ✓ | ✓ | ✓ | `snapshot` (inherited) | | `container-mount`, `container-exec-env`, `container-port` | `ContainerChildHandler` | ✓ | varies | ✗ | (inherits) | | `container-volume` | `ContainerVolumeHandler` | ✓ | ✓ | ✓ | `snapshot` | | `container-network` | `ContainerNetworkHandler` | ✓ | ✗ | ✗ | `none` | | `executable` | `ExecutableHandler` | ✓ | ✗ | ✗ | `none` | | `lsp-server` | `LSPServerHandler` | ✓ | ✗ | ✗ | `none` | | `lsp-workspace` | `LSPWorkspaceHandler` | ✓ | ✗ | ✗ | `none` | | `lsp-document` | `LSPDocumentHandler` | ✓ | ✓ | ✗ | `none` | Additional handlers are provided by custom resource types when they are registered. !!! adr "Architecture Decision" Container resource types are defined in [ADR-039: Container and Execution Environment Resource Types](adr/ADR-039-container-resource-types.md). The `devcontainer-instance` subtype, container-project association patterns, and execution environment routing are defined in [ADR-043: Devcontainer Integration and Container-Project Association](adr/ADR-043-devcontainer-integration.md). Resource type inheritance (the `inherits` mechanism) is defined in [ADR-042: Resource Type Inheritance](adr/ADR-042-resource-type-inheritance.md). LSP resource types are defined in [ADR-040: LSP Resource Types](adr/ADR-040-lsp-resource-types.md). ##### Resource Path Resolution Paths in tool invocations are resolved through a resource routing system that uses tool-resource bindings to determine the target resource: ```kroki-mermaid sequenceDiagram participant Tool as Tool Invocation participant Router as Resource Router participant Handler as GitCheckoutHandler Tool->>Router: edit_file(path='src/main.py', ...) Router->>Router: Check tool's resource bindings Note right of Router: slot 'repo' bound to
local/api-repo (git-checkout) Router->>Router: Resolve path within bound resource Note right of Router: local/api-repo:worktree:src/main.py Router->>Handler: Route to resource handler Handler->>Handler: Resolve path to sandbox worktree Handler->>Handler: Operate on sandboxed state Handler-->>Tool: Return Change record ``` When a tool has multiple resource slots bound, the path scheme or slot name disambiguates: 

# Explicit slot reference
path://repo/src/main.py      → routes to the "repo" slot's bound resource
path://docs/api/readme.md    → routes to the "docs" slot's bound resource

# Default: unqualified paths route to the tool's primary resource slot
src/main.py                  → routes to the first (or only) resource slot
### Context !!! adr "Architecture Decision" The Advanced Context Management System, UKO ontology, CRP protocol, and context strategies are defined in [ADR-014: Context Management (ACMS)](adr/ADR-014-context-management-acms.md). The Advanced Context Management System (ACMS) is CleverAgents' fully pluggable, strategy-driven framework for assembling context for actors. It replaces and subsumes the basic context tier system with a comprehensive architecture built around three core innovations: 1. **A Universal Knowledge Ontology (UKO)** -- an inheritance-based RDF ontology hierarchy that represents *any* resource (source code, documents, databases, infrastructure) at multiple levels of abstraction, with full provenance back to the originating resource and temporal versioning across revisions. 2. **A Context Request Protocol (CRP)** -- a structured vocabulary through which actors (via skills) declare what information they need, at what level of detail, and with what scope, while they are reasoning. This replaces static "context view" approaches with a dynamic, demand-driven model. 3. **A Context Assembly Pipeline** -- a pluggable, 10-component pipeline that replaces the former monolithic Strategy Coordinator and Fusion Engine. Multiple independent context strategies can be registered, each working with different data backends and different abstraction levels of the UKO. The pipeline orchestrates strategy selection, budget allocation, parallel execution, fragment deduplication, depth resolution, scoring, budget packing, ordering, preamble generation, and skeleton compression -- each step backed by a replaceable Protocol implementation configurable at global, project, or plan scope. The system is designed around the hierarchical nature of plans: parent plans see wide, shallow context (breadth); child plans see narrow, deep context (depth). Context inheritance flows parent-to-child with progressive focusing, and every context assembly respects a dynamically-changing token budget. This architecture is domain-agnostic: the same breadth/depth/DetailDepth mechanics work identically whether the underlying resources are source code repositories, technical documents, database schemas, or infrastructure configurations. **Critical Design Decision**: All indexing happens immediately when resources are added to projects or when code changes. There is no "on-demand" indexing during agent execution. This ensures that agents always have instant access to search capabilities without any indexing delays. The computational cost is paid once upfront, not repeatedly during agent operations. > The full architectural design of the ACMS -- including the UKO ontology hierarchy, backend abstraction layer, Context Assembly Pipeline (the 10-component pluggable pipeline that replaced the former Strategy Coordinator and Fusion Engine), index synchronization, performance characteristics, and plugin architecture -- is specified in the **Architecture > ACMS Architecture** section. #### Core Data Types The ACMS defines several data types that are used throughout the system by actors, skills, strategies, and the plan lifecycle. ##### DetailDepth and DetailLevelMap At the most general level (UKO Layer 0), detail depth is simply a **non-negative integer** — 0 being the most minimal representation and each increment revealing more. There is no fixed upper bound; the maximum meaningful depth depends on the domain and the complexity of the information unit. This is the `DetailDepth` type. Each UKO domain extension then registers a **DetailLevelMap** — a table of named labels mapped to specific integer depths. This allows domain users to work with meaningful names (like `MODULE_LISTING` or `TABLE_OF_CONTENTS`) rather than raw integers, while the underlying system always operates on the universal integer scale. Maps are inherited: a language-specific map includes all levels from its parent paradigm map, which includes all levels from the general code map. 

DetailDepth = int  # Non-negative integer, 0 = most minimal, no upper bound

@dataclass
class DetailLevelMap:
    """Maps named detail levels to integer depths for a UKO domain.
    Inherited: a child map includes all entries from its parent map,
    and may insert additional levels at any integer position."""
    domain: str                          # UKO namespace (e.g., "uko-code:", "uko-py:")
    parent: DetailLevelMap | None         # Parent map to inherit from
    levels: dict[str, int]               # Named level -> integer depth
    max_depth: int                       # Maximum meaningful depth for this domain

    def resolve(self, depth: int | str) -> int:
        """Resolve a named level or integer to an integer depth."""
        if isinstance(depth, int):
            return min(depth, self.max_depth)
        # Look up named level in this map, then parent maps
        if depth in self.levels:
            return self.levels[depth]
        if self.parent:
            return self.parent.resolve(depth)
        raise ValueError(f"Unknown detail level: {depth}")
**Universal (Layer 0) Semantics:** At the universal level, each integer depth has a domain-agnostic meaning. The principle is that depth 0 answers *"what exists?"*, and each subsequent depth answers progressively more detailed questions: | Depth | Universal Question Answered | What Gets Included | |-------|-----------------------------|--------------------| | 0 | *What exists?* | Just the name/identifier of the information unit. | | 1 | *How is it organized?* | Names of immediate children (structural skeleton). | | 2 | *What are the key relationships?* | Children + dependency/reference edges to other units. | | 3 | *What is each thing's purpose?* | + Short descriptions/summaries for each child. | | 4 | *What is the structural shape?* | + Type information, size/count metadata, categories. | | 5+ | *How does it work? What does it say?* | Progressively more content, up to complete verbatim content at max depth. | | max | *Everything.* | Complete content — nothing omitted. | The exact number of meaningful depths varies by domain (source code may have 12+ levels, a flat config file may only have 4). The system never forces content into a fixed number of buckets. **Source Code DetailLevelMap (`uko-code:`, extended by `uko-oo:`, `uko-py:`, etc.):** The general software domain defines a base set of named levels. Paradigm-specific and language-specific extensions insert additional levels where their semantics provide meaningful distinctions. | Depth | `uko-code:` Name | Content Shown | |-------|-------------------|---------------| | 0 | `MODULE_LISTING` | Module/package names only, no internal structure. | | 1 | `MODULE_GRAPH` | Module names + inter-module dependency edges (imports graph). | | 2 | `MEMBER_LISTING` | + Names of top-level members within each module (classes, functions, constants) — no signatures. | | 3 | `MEMBER_SUMMARY` | + One-line docstring or LLM-generated summary for each member. | | 4 | `SIGNATURES` | + Full type signatures (parameter names, types, return types) for all callables and type definitions. | | 5 | `SIGNATURES_WITH_DOCS` | + Complete docstrings/comments attached to each member. | | 6 | `STRUCTURAL_OUTLINE` | + Control flow structure within callable bodies (branches, loops, try/except) shown as outline, no expressions. | | 7 | `KEY_LOGIC` | + Key expressions: return statements, assertions, assignments to important variables. | | 8 | `NEAR_COMPLETE` | + All statements except comments, logging, and boilerplate (imports, `__all__`, etc.). | | 9 | `FULL_SOURCE` | Complete source code — nothing omitted. | *Object-Oriented effective map (`uko-oo:`) — inherits from `uko-code:`, inserts `CLASS_HIERARCHY` and `VISIBILITY_ANNOTATED`:* When the `uko-oo:` extension is active, the effective DetailLevelMap is re-numbered with consecutive integers. The two inserted levels shift all subsequent depths upward: | Depth | Name | Origin | Content Shown | |-------|------|--------|---------------| | 0 | `MODULE_LISTING` | `uko-code:` | Module/package names only, no internal structure. | | 1 | `MODULE_GRAPH` | `uko-code:` | Module names + inter-module dependency edges (imports graph). | | 2 | `MEMBER_LISTING` | `uko-code:` | + Names of top-level members within each module (classes, functions, constants) — no signatures. | | 3 | `CLASS_HIERARCHY` | **`uko-oo:`** | **Inheritance chains and interface implementation relationships between classes.** | | 4 | `MEMBER_SUMMARY` | `uko-code:` | + One-line docstring or LLM-generated summary for each member. | | 5 | `SIGNATURES` | `uko-code:` | + Full type signatures (parameter names, types, return types) for all callables and type definitions. | | 6 | `SIGNATURES_WITH_DOCS` | `uko-code:` | + Complete docstrings/comments attached to each member. | | 7 | `VISIBILITY_ANNOTATED` | **`uko-oo:`** | **Public/protected/private modifiers on all members + abstract/final markers.** | | 8 | `STRUCTURAL_OUTLINE` | `uko-code:` | + Control flow structure within callable bodies (branches, loops, try/except) shown as outline, no expressions. | | 9 | `KEY_LOGIC` | `uko-code:` | + Key expressions: return statements, assertions, assignments to important variables. | | 10 | `NEAR_COMPLETE` | `uko-code:` | + All statements except comments, logging, and boilerplate (imports, `__all__`, etc.). | | 11 | `FULL_SOURCE` | `uko-code:` | Complete source code — nothing omitted. | *Python-specific effective map (`uko-py:`) — inherits from `uko-oo:`, inserts `DECORATED_SIGNATURES`, `TYPE_STUBS`, and appends `WITH_TESTS`:* When the `uko-py:` extension is active, the effective map builds on `uko-oo:` and re-numbers again: | Depth | Name | Origin | Content Shown | |-------|------|--------|---------------| | 0 | `MODULE_LISTING` | `uko-code:` | Module/package names only, no internal structure. | | 1 | `MODULE_GRAPH` | `uko-code:` | Module names + inter-module dependency edges (imports graph). | | 2 | `MEMBER_LISTING` | `uko-code:` | + Names of top-level members within each module (classes, functions, constants) — no signatures. | | 3 | `CLASS_HIERARCHY` | `uko-oo:` | Inheritance chains and interface implementation relationships between classes. | | 4 | `MEMBER_SUMMARY` | `uko-code:` | + One-line docstring or LLM-generated summary for each member. | | 5 | `SIGNATURES` | `uko-code:` | + Full type signatures (parameter names, types, return types) for all callables and type definitions. | | 6 | `SIGNATURES_WITH_DOCS` | `uko-code:` | + Complete docstrings/comments attached to each member. | | 7 | `DECORATED_SIGNATURES` | **`uko-py:`** | **`@property`, `@staticmethod`, `@classmethod`, custom decorator chains shown on each member.** | | 8 | `VISIBILITY_ANNOTATED` | `uko-oo:` | Public/protected/private modifiers on all members + abstract/final markers. | | 9 | `STRUCTURAL_OUTLINE` | `uko-code:` | + Control flow structure within callable bodies (branches, loops, try/except) shown as outline, no expressions. | | 10 | `KEY_LOGIC` | `uko-code:` | + Key expressions: return statements, assertions, assignments to important variables. | | 11 | `TYPE_STUBS` | **`uko-py:`** | **Type annotations from `.pyi` stub files merged with source, `typing` module usage.** | | 12 | `NEAR_COMPLETE` | `uko-code:` | + All statements except comments, logging, and boilerplate (imports, `__all__`, etc.). | | 13 | `FULL_SOURCE` | `uko-code:` | Complete source code — nothing omitted. | | 14 | `WITH_TESTS` | **`uko-py:`** | **Full source + associated test cases for each callable (from `uko-code:testsCallable` edges).** | **Document DetailLevelMap (`uko-doc:`):** | Depth | `uko-doc:` Name | Content Shown | |-------|-------------------|---------------| | 0 | `TITLE_ONLY` | Document title / section heading only. | | 1 | `TABLE_OF_CONTENTS_L1` | Title + top-level (depth-1) section/chapter headings. | | 2 | `TABLE_OF_CONTENTS_L2` | + Second-level subsection headings. | | 3 | `FULL_TOC` | Complete table of contents to all heading depths. | | 4 | `TOC_WITH_SUMMARIES` | Full TOC + one-sentence abstract per section (LLM-generated or extracted from first paragraph). | | 5 | `SECTION_OVERVIEWS` | + Topic keywords per section + cross-reference targets (which other sections this section discusses). | | 6 | `TOPIC_SENTENCES` | + First sentence of every paragraph within each section. | | 7 | `PARAGRAPH_SUMMARIES` | + LLM-generated summary for each paragraph (2-3 sentences compressed to 1). | | 8 | `STRUCTURAL_DETAIL` | + All figure/table captions + code block headers + list item first lines + blockquote sources. | | 9 | `NEAR_COMPLETE` | + Full paragraph text, but with inline formatting stripped and code blocks truncated to first/last 3 lines. | | 10 | `FULL_CONTENT` | Complete document content — all text, formatting, code blocks, figures, footnotes. | **Database DetailLevelMap (`uko-data:`):** | Depth | `uko-data:` Name | Content Shown | |-------|-------------------|---------------| | 0 | `SCHEMA_LISTING` | Schema/database names only. | | 1 | `TABLE_LISTING` | + Table and view names within each schema. | | 2 | `COLUMN_LISTING` | + Column names within each table (no types). | | 3 | `TYPED_COLUMNS` | + Column data types + nullability. | | 4 | `CONSTRAINTS` | + Primary keys, unique constraints, check constraints, defaults. | | 5 | `RELATIONSHIPS` | + Foreign key relationships (full referential graph between tables). | | 6 | `INDEXES_AND_STATS` | + Index definitions + estimated row counts + basic statistics (cardinality, avg row size). | | 7 | `DDL` | Full CREATE TABLE / CREATE VIEW DDL (reconstructed from metadata). | | 8 | `DDL_WITH_TRIGGERS` | + Trigger definitions + stored procedure signatures that reference each table. | | 9 | `FULL_PROCEDURES` | + Complete stored procedure and function bodies. | | 10 | `WITH_SAMPLE_DATA` | + Sample rows (configurable N, default 5) for each table. | | 11 | `FULL_CATALOG` | Complete catalog: DDL + all procedure bodies + triggers + sample data + value distribution histograms + query plan statistics. | **Infrastructure DetailLevelMap (`uko-infra:`):** | Depth | `uko-infra:` Name | Content Shown | |-------|---------------------|---------------| | 0 | `SERVICE_LISTING` | Service/component names only. | | 1 | `SERVICE_GRAPH` | + Service dependency edges (which services connect to which). | | 2 | `ENDPOINT_LISTING` | + Endpoint paths/ports for each service. | | 3 | `ENDPOINT_DETAIL` | + HTTP methods, parameters, authentication requirements per endpoint. | | 4 | `CONFIG_KEYS` | + Configuration key names and their sections. | | 5 | `CONFIG_VALUES` | + Configuration values (with secrets masked). | | 6 | `RESOURCE_LIMITS` | + Resource allocations (CPU, memory, replicas, storage). | | 7 | `FULL_CONFIG` | Complete configuration files for each service. | | 8 | `WITH_DEPLOYMENT` | + Deployment descriptors (Dockerfiles, Kubernetes manifests, Compose files). | **How depth resolution works in practice**: When a context request specifies `depth="SIGNATURES"` and the target node is a `uko-py:Module`, the system looks up `SIGNATURES` in the `uko-py:` DetailLevelMap first. If found, it uses that integer. If not, it walks up to `uko-oo:`, then `uko-code:`, then `uko:` until it finds a match. If the request specifies `depth=4` (a raw integer), it is used directly — the system renders the target node at integer depth 4 regardless of what named level that corresponds to. ##### ContextRequest A structured request for context, issued by an actor or skill via the CRP. 

@dataclass
class ContextRequest:
    """A structured request for context, issued by an actor or skill."""

    # === What to find ===
    query: str | None = None          # Natural language query
    entities: list[str] = field(default_factory=list)  # Named entities to focus on
    uko_types: list[str] = field(default_factory=list)  # UKO types to filter

    # === Scope control ===
    focus: list[str] = field(default_factory=list)
    # URIs or identifiers of specific items to focus on

    breadth: int = 2
    # How many hops outward in the dependency/reference graph.

    depth: int | str = 3
    # How much detail to include for each item found.
    # May be a raw integer (0-N) or a named level string (e.g., "SIGNATURES")
    # resolved via the active DetailLevelMap for the target node's UKO type.

    # === Focus depth gradient ===
    depth_gradient: bool = True
    # When True, items closer to the focus get more detail.

    # === Temporal scope ===
    temporal: TemporalScope = TemporalScope.CURRENT

    # === Budget ===
    max_tokens: int | None = None

    # === Strategy hints ===
    preferred_strategies: list[str] = field(default_factory=list)
    required_backends: list[str] = field(default_factory=list)

    # === Priority and purpose ===
    priority: float = 0.5           # 0.0 = background, 1.0 = critical
    purpose: str = ""               # Why is this context needed?
##### ContextFragment The atomic unit of context returned by strategies and consumed by the Context Assembly Pipeline's fusion phase (FragmentDeduplicator, DetailDepthResolver, FragmentScorer, BudgetPacker, FragmentOrderer). 

@dataclass
class ContextFragment:
    """A single piece of context assembled by a strategy."""
    uko_node: str                     # UKO URI of the source node
    content: str                      # Rendered text content
    detail_depth: int                 # Resolved integer depth of this fragment
    token_count: int                  # Token count of content
    relevance_score: float            # 0.0-1.0 relevance to the request
    provenance: FragmentProvenance     # Trace back to resource + location
    metadata: dict = field(default_factory=dict)
##### AssembledContext The output of a context assembly cycle -- the final, budget-respecting payload delivered to an actor. 

@dataclass
class AssembledContext:
    """The fused, budget-respecting context payload."""
    fragments: list[ContextFragment]   # Ordered context fragments
    total_tokens: int                  # Total token count
    budget_used: float                 # Fraction of budget consumed (0.0-1.0)
    strategies_used: list[str]         # Which strategies contributed
    context_hash: str                  # Cryptographic hash for snapshot
    preamble: str | None               # Optional structure summary
    provenance_map: dict               # Fragment -> resource/location mapping
    skeleton_fragments: tuple[ContextFragment, ...] = ()  # Compressed parent context for child plan inheritance
#### Context Request Protocol (CRP) Instead of static context views, actors (through their skills) **actively request** context as they reason. The CRP defines a structured vocabulary for these requests. This is fundamentally different from existing approaches where context is assembled once before the actor runs. With CRP: 1. The actor starts with an **initial context** (assembled from the plan's context view, parent context inheritance, and strategy defaults). 2. As the actor reasons, skills can issue **refinement requests** to pull in additional context dynamically. 3. Each request triggers a new context assembly cycle with the remaining token budget. ##### The `builtin/context` Skill Actors issue context requests through a **context skill** that is automatically injected into every actor's skill set: 
# Built-in skill, always available
skill:
  name: builtin/context
  description: "Request additional context during reasoning"

  anonymous_tools:
    - name: request_context
      description: "Request specific context to be added to the conversation"
      input_schema:
        type: object
        properties:
          query: { type: string, description: "What information do you need?" }
          focus: { type: array, items: { type: string },
                   description: "Specific files, classes, or functions to focus on" }
          breadth: { type: integer, default: 2,
                     description: "How many dependency hops outward (0-5)" }
          depth: { oneOf: [{ type: integer, minimum: 0 }, { type: string }],
                   default: 3,
                   description: "Detail depth — integer (0-N) or named level from the active DetailLevelMap (e.g., 'SIGNATURES', 'FULL_SOURCE')" }
          purpose: { type: string, description: "Why do you need this context?" }
        required: [purpose]

    - name: query_history
      description: "Query historical context about past decisions and changes"
      input_schema:
        type: object
        properties:
          query: { type: string }
          scope: { type: string, enum: ["current_plan", "plan_tree", "all_plans"],
                   default: "plan_tree" }
        required: [query]

    - name: get_context_budget
      description: "Check remaining context token budget"
      input_schema:
        type: object
        properties: {}
#### Context Strategy Protocol Every context strategy implements this protocol. Strategies are pluggable -- built-in strategies ship with CleverAgents, and custom strategies can be registered via configuration. 
@runtime_checkable
class ContextStrategy(Protocol):
    """A pluggable context assembly strategy."""

    @property
    def name(self) -> str: ...

    @property
    def capabilities(self) -> StrategyCapabilities: ...

    def can_handle(self, request: ContextRequest,
                   backends: BackendSet) -> float:
        """Returns 0.0-1.0 confidence that this strategy can usefully
        contribute to this request."""
        ...

    def assemble(self, request: ContextRequest,
                 backends: BackendSet,
                 budget: int,
                 plan_context: PlanContext) -> list[ContextFragment]:
        """Execute the strategy. Must respect the budget."""
        ...

    def explain(self) -> str: ...

@dataclass
class StrategyCapabilities:
    """Declares what a strategy is capable of."""
    uses_text: bool = False
    uses_vector: bool = False
    uses_graph: bool = False
    uses_temporal: bool = False
    uko_levels: list[str] = field(default_factory=list)
    resource_types: list[str] = field(default_factory=list)
    supports_depth_breadth: bool = False
    supports_plan_hierarchy: bool = False
    supports_temporal: bool = False
    quality_score: float = 0.5
##### Built-in Strategies | Strategy | Quality | Backends Required | Description | |----------|---------|------------------|-------------| | `simple-keyword` | 0.3 | Text only | Basic keyword/regex text search. Universal fallback. | | `semantic-embedding` | 0.6 | Vector | Vector similarity search for semantically related content. | | `breadth-depth-navigator` | 0.85 | Graph | Graph-aware UKO traversal with depth/breadth projection. Primary strategy for code-aware context. | | `arce` | 0.95 | All | Multi-modal pipeline combining text, vector, and graph with intent analysis. Highest quality. | | `temporal-archaeology` | 0.5 | Graph + Cold tier | Historical pattern discovery from past decisions and archived context. | | `plan-decision-context` | 0.7 | Warm/Cold tiers | Retrieves context from parent/ancestor plan decisions. | ##### Strategy Registration Strategies are registered through configuration. The context assembly pipeline itself is also fully pluggable — see **Architecture > ACMS > Context Assembly Pipeline** for the ten pluggable pipeline components. 
[context.strategies]
enabled = ["simple-keyword", "semantic-embedding", "arce", "breadth-depth-navigator"]

[context.strategies.custom]
"my-domain-strategy" = "my_package.strategies.DomainStrategy"

# Pipeline component overrides (see Architecture > ACMS > Context Assembly Pipeline)
[context.pipeline]
strategy-selector     = "builtin:ConfidenceWeightedSelector"   # default
budget-allocator      = "builtin:ProportionalBudgetAllocator"   # default
fragment-scorer       = "my_extensions.scorers:DomainAwareScorer"  # custom override
#### Hierarchical Plan Context In a plan hierarchy, each level sees a different slice of the project's resources. Context inheritance flows parent-to-child with progressive focusing. This applies universally across all UKO domains — the same breadth/depth mechanics work for codebases, documents, databases, and infrastructure. **Source Code Example:** | Level | Breadth | Depth | Example Content | |-------|---------|-------|-----------------| | Root | Entire project | 0 (`MODULE_LISTING`) | Module names, dependency graph edges | | Subplan A | `src/auth/` module + direct deps | 4 (`SIGNATURES`) | Function signatures with types, class inheritance chains | | Sub-subplan A1 | `AuthManager` class + 2-hop deps | 9 (`FULL_SOURCE`) | Complete function bodies, all parameters, all call sites | **Document Example** (e.g., a technical specification): | Level | Breadth | Depth | Example Content | |-------|---------|-------|-----------------| | Root | Entire document | 1 (`TABLE_OF_CONTENTS_L1`) | Document title + top-level chapter headings | | Subplan A | "Architecture" chapter + sections that `discussesTopic` it | 5 (`SECTION_OVERVIEWS`) | Section headings + topic keywords + cross-reference targets + one-sentence abstracts | | Sub-subplan A1 | "ACMS Architecture" section + 2-hop topic references | 10 (`FULL_CONTENT`) | Complete section text with all paragraphs, figures, code blocks | **Database Example** (e.g., schema migration planning): | Level | Breadth | Depth | Example Content | |-------|---------|-------|-----------------| | Root | Entire database | 1 (`TABLE_LISTING`) | Schema names + table and view names | | Subplan A | `auth` schema + tables with foreign keys into it | 5 (`RELATIONSHIPS`) | Table names + typed columns + constraints + foreign key graph | | Sub-subplan A1 | `users` table + dependent views and stored procedures | 9 (`FULL_PROCEDURES`) | Complete DDL + triggers + stored procedure bodies + sample data | The **skeleton** is a compact, low-depth representation (typically depth 0-1) of the parent's context window that is passed to every child. This ensures children always have the "big picture" available, even though they focus on a narrow area. The skeleton typically consumes 5-15% of the child's token budget (controlled by `skeleton_ratio`). For a source code resource, the skeleton is a `MODULE_LISTING` (depth 0) — just module names. For a document resource, the skeleton is a `TABLE_OF_CONTENTS_L1` (depth 1) — the table of contents. For a database resource, it is a `TABLE_LISTING` (depth 1) — schema and table names. #### Depth/Breadth Projection The depth/breadth projection system allows fine-grained control over how much of the knowledge graph is materialized into context. It operates on the UKO graph structure. - **Breadth** (integer, 0-N): How many hops in the `uko:references` / `uko:dependsOn` / `uko:contains^-1` graph to traverse from the focus items. - **Depth** (integer or named level): How much content to include for each item found. Specified as a raw integer or a named level resolved via the active DetailLevelMap. - **Depth gradient**: When enabled, detail decreases with distance from focus. **Source Code Projection Example:** 

Request: focus=["class://AuthManager"], breadth=2, depth=9 (FULL_SOURCE), gradient=True

Result (token costs approximate):

Distance 0 — depth 9 (FULL_SOURCE):
  class AuthManager:                               # 800 tokens
      """Manages user authentication..."""
      def authenticate(self, username, password):
          ...full body...
      def validate_token(self, token):
          ...full body...

Distance 1 — depth 4 (SIGNATURES):
  class BaseManager:                               # 120 tokens
      def connect(self) -> Connection: ...
      def disconnect(self) -> None: ...
  class CryptoUtils:                               # 80 tokens
      def hash_password(pwd: str) -> str: ...
      def verify_hash(pwd: str, hash: str) -> bool: ...
  class UserDB:                                    # 100 tokens
      def find_user(username: str) -> User | None: ...
      def create_user(user: User) -> None: ...

Distance 2 — depth 0 (MODULE_LISTING):
  class Connection                                 # 20 tokens
  class User                                       # 15 tokens
  class DatabasePool                               # 15 tokens

Total: ~1,150 tokens (vs ~15,000 if everything were depth 9)
**Document Projection Example:** 

Request: focus=["uko-doc:section/security-architecture"], breadth=2, depth=10 (FULL_CONTENT), gradient=True

Result (token costs approximate):

Distance 0 — depth 10 (FULL_CONTENT):
  ## 5. Security Architecture                      # 2,400 tokens
      Complete section text including all paragraphs,
      code examples, diagrams, and subsections:
      5.1 Authentication Flow
      5.2 Authorization Model
      5.3 Token Management

Distance 1 — depth 6 (TOPIC_SENTENCES — sections that discuss security topics):
  ## 3. API Design                                  # 180 tokens
      Section headings + first sentence of each paragraph:
      "The API uses JWT tokens for authentication..."
      "Rate limiting is enforced per-client..."
  ## 8. Deployment                                   # 120 tokens
      "TLS termination occurs at the load balancer..."
      "Secrets are injected via Vault..."

Distance 2 — depth 0 (TITLE_ONLY — sections referenced by distance-1 sections):
  ## 2. System Overview                              # 30 tokens
  ## 9. Monitoring                                   # 25 tokens
  ## Appendix A: Threat Model                        # 20 tokens

Total: ~2,775 tokens (vs ~18,000 if the entire document were depth 10)
**Database Projection Example:** 

Request: focus=["uko-data:table/auth.users"], breadth=2, depth=11 (FULL_CATALOG), gradient=True

Result (token costs approximate):

Distance 0 — depth 11 (FULL_CATALOG):
  CREATE TABLE auth.users (                        # 650 tokens
      id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
      email VARCHAR(255) UNIQUE NOT NULL,
      password_hash VARCHAR(60) NOT NULL,
      ...complete DDL + triggers + sample rows + statistics...
  );

Distance 1 — depth 7 (DDL — tables with foreign keys to/from users):
  CREATE TABLE auth.sessions (                     # 180 tokens
      id UUID PRIMARY KEY,
      user_id UUID REFERENCES auth.users(id),
      ...DDL with constraints...
  );
  CREATE TABLE auth.roles (                         # 120 tokens
      ...DDL with constraints...
  );
  CREATE VIEW auth.active_users AS ...             # 90 tokens

Distance 2 — depth 1 (TABLE_LISTING — tables referenced by distance-1 tables):
  auth.permissions                                  # 20 tokens
  auth.audit_log                                    # 15 tokens
  public.organizations                              # 15 tokens

Total: ~1,090 tokens (vs ~8,500 if the entire schema were depth 11)
#### Integration with Plan Lifecycle 

Plan Lifecycle                        ACMS Actions
─────────────────                     ────────────────────────────
Plan created (agents plan use)        ResourceScope resolved.
                                      ScopedBackendViews created.

Strategize phase begins               InitialContextAssembler runs:
                                         - Inherits parent context (if subplan)
                                         - Runs Context Assembly Pipeline
                                         - Produces AssembledContext
                                         - Injects into actor's system prompt

Strategy actor reasons                 Actor may issue ContextRequests via
                                       builtin/context skill.
                                       Each request triggers re-assembly
                                       with remaining budget.

Strategy actor produces decisions      Each Decision's context_snapshot
                                       captures AssembledContext hash +
                                       provenance map.

Execute phase begins                   New InitialContextAssembler run
                                       with execute-phase view.
                                       Decisions from Strategize are in
                                       warm tier.

Execution actor works                  Dynamic ContextRequests as needed.

Subplan spawned                        PlanContextInheritance computes
                                        child context from parent.
                                        SkeletonCompressor propagates parent
                                        context as skeleton.
                                        New ResourceScope (possibly narrower).

Apply phase                            Minimal context assembly
                                       (validation results, diff summary).

Plan completes                         Hot context archived to warm.
                                       Warm context ages to cold based
                                       on retention policy.
### Output Rendering Framework !!! adr "Architecture Decision" The output rendering framework, format system, and reactive output sessions are defined in [ADR-021: CLI and Output Rendering](adr/ADR-021-cli-and-output-rendering.md). #### Overview CleverAgents uses a unified **Output Rendering Framework** to decouple command output data from its visual presentation. Every CLI command produces structured output through a common abstraction layer, and the active **format** determines how that output is rendered to the terminal (or piped to external consumers). The format is set via the global `--format` flag, the `format` config key, or defaults to `rich`. The framework is **reactive-first**: commands do not build a static data structure and hand it to a renderer. Instead, commands open an **output session**, create **element handles** for each piece of output (a panel, a table, a progress indicator), and write data to those handles — potentially from multiple concurrent producers. The session coordinates with a **materialization strategy** selected by the active format, which decides *when* and *how* each element's content reaches the terminal. A `rich` session renders updates in-place as they arrive; a `plain` session buffers each element and flushes sequentially; a `json` session accumulates everything and serializes once at the end. **Producer code is format-agnostic** — it writes to handles without knowing which format is active. This architecture is designed for modularity, extensibility, and future-proofing — the same session-based output can be consumed by the CLI, a future TUI, a web frontend, or programmatic integrations. The design uses a pipeline of composable stages: **session lifecycle management**, **typed element handles**, **event-driven materialization**, and **format-specific element rendering**. #### Architecture ##### Rendering Pipeline All CLI output flows through a five-stage reactive pipeline: ```kroki-mermaid flowchart LR A["Command Logic"] --> B["OutputSession\n(lifecycle)"] B --> C["ElementHandles\n(typed producers)"] C --> D["MaterializationStrategy\n(format-driven policy)"] D --> E["Terminal / Pipe\n(stdout/stderr)"] ``` 1. **Command Logic** opens an `OutputSession` and creates typed **element handles** — `PanelHandle`, `TableHandle`, `ProgressHandle`, etc. — for each piece of output the command will produce. Handles are created in **declaration order**, which determines the canonical order in which elements appear in sequential formats. 2. **OutputSession** is the central coordinator. It owns the set of active handles, tracks their lifecycle (open → writing → closed), emits `ElementEvent` objects to the active materialization strategy, and provides a `snapshot()` method that returns a static `StructuredOutput` representing the accumulated state at any point in time. 3. **ElementHandles** are the producer-facing API. Each handle is typed for a specific element kind (panel, table, tree, etc.) and exposes write methods appropriate to that kind (`add_row()`, `set_entry()`, `set_step_status()`, etc.). Handles are **thread-safe** — multiple concurrent coroutines or threads can write to different handles simultaneously. Handles are **format-agnostic** — the producer never knows or cares which format is active. 4. **MaterializationStrategy** is a polymorphic observer selected by the active format. It receives `ElementEvent` notifications from the session and decides *when* and *how* to render content. Each strategy delegates the actual visual rendering of an element's accumulated state to a paired **ElementRenderer**. 5. **Terminal/Pipe** receives the final byte stream. The framework auto-detects whether stdout is a TTY and degrades gracefully (e.g., `rich` falls back to `table` when piped to a non-TTY unless `--format rich` was explicitly set). ##### OutputSession The `OutputSession` is the core abstraction that replaces direct construction of static output objects. Commands receive a session (typically injected by the CLI framework) and interact with it throughout their execution: 

class OutputSession:
    """A live output document that coordinates element production and materialization.
    
    The session manages the lifecycle of all output elements for a single command
    invocation. It is the bridge between format-agnostic producer code and the
    format-specific materialization strategy.
    
    Thread Safety:
        The session is thread-safe. Multiple producers may create and write to
        handles concurrently. The session serializes event delivery to the
        materialization strategy using an internal event queue.
    
    Lifecycle:
        session = OutputSession.open(command, strategy)
        handle_a = session.panel("Title")       # create handles
        handle_b = session.table("Results", ...) 
        handle_a.set_entry(...)                  # write to handles (concurrent OK)
        handle_b.add_row(...)
        handle_a.close()                         # close handles when done
        handle_b.close()
        session.close()                          # finalize the session
    """

    # --- Session lifecycle ---

    command: str                                  # The command that owns this session
    session_id: str                               # Unique session identifier (ULID)
    created_at: datetime                          # Session creation timestamp

    _strategy: MaterializationStrategy            # The active materialization strategy
    _handles: OrderedDict[str, ElementHandle]     # handle_id → handle, in declaration order
    _event_queue: asyncio.Queue[ElementEvent]     # Internal event queue for serialization
    _state: SessionState                          # "open" | "closing" | "closed"
    _lock: threading.Lock                         # Protects handle creation/removal

    @classmethod
    def open(cls, command: str, strategy: MaterializationStrategy,
             metadata: dict | None = None) -> "OutputSession":
        """Open a new output session.
        
        Called by the CLI framework before command execution. The strategy is
        selected based on the resolved format (see Format Resolution).
        
        Args:
            command: The command string (e.g., "project show").
            strategy: The materialization strategy for the active format.
            metadata: Optional command metadata (user, timestamp, etc.).
        
        Returns:
            A new OutputSession ready for element creation.
        """
        ...

    # --- Element handle factories ---
    # Each factory creates a typed handle, registers it with the session in
    # declaration order, and emits an ElementCreated event to the strategy.

    def panel(self, title: str, *,
              border_style: str = "rounded",
              priority: str = "normal",
              collapse_hint: str = "auto",
              metadata: dict | None = None) -> "PanelHandle":
        """Create a panel element handle for key-value pair output."""
        ...

    def table(self, title: str | None, *,
              columns: list["ColumnDef"],
              summary: dict | None = None,
              max_rows_hint: int | None = None,
              sort_key: str | None = None,
              priority: str = "normal",
              collapse_hint: str = "auto",
              metadata: dict | None = None) -> "TableHandle":
        """Create a table element handle for tabular data."""
        ...

    def tree(self, root_label: str, *,
             root_style: str | None = None,
             max_depth_hint: int | None = None,
             show_guides: bool = True,
             priority: str = "normal",
             collapse_hint: str = "auto",
             metadata: dict | None = None) -> "TreeHandle":
        """Create a tree element handle for hierarchical data."""
        ...

    def progress(self, label: str, *,
                 total: int | None = None,
                 indeterminate: bool = False,
                 steps: list[str] | None = None,
                 priority: str = "normal",
                 metadata: dict | None = None) -> "ProgressHandle":
        """Create a progress indicator handle.
        
        Args:
            label: Display label for the progress indicator.
            total: Total units of work (None for indeterminate).
            indeterminate: If True, show a spinner instead of a progress bar.
            steps: Named steps to track (creates ProgressStep objects with
                   initial status "pending").
        """
        ...

    def status(self, message: str, *,
               level: str = "info",
               detail: str | None = None,
               priority: str = "normal",
               metadata: dict | None = None) -> "StatusHandle":
        """Create a status message handle."""
        ...

    def text(self, content: str = "", *,
             wrap: bool = True,
             indent: int = 0,
             priority: str = "normal",
             metadata: dict | None = None) -> "TextHandle":
        """Create a text block handle."""
        ...

    def code(self, content: str = "", *,
             language: str | None = None,
             line_numbers: bool = False,
             highlight_lines: list[int] | None = None,
             priority: str = "normal",
             metadata: dict | None = None) -> "CodeHandle":
        """Create a code block handle."""
        ...

    def diff(self, *,
             file_a: str | None = None,
             file_b: str | None = None,
             priority: str = "normal",
             metadata: dict | None = None) -> "DiffHandle":
        """Create a diff block handle."""
        ...

    def separator(self, style: str = "line") -> "SeparatorHandle":
        """Create a visual separator. Separators are auto-closed on creation."""
        ...

    def action_hint(self, commands: list[str],
                    description: str | None = None) -> "ActionHintHandle":
        """Create an action hint. Action hints are auto-closed on creation."""
        ...

    # --- Session operations ---

    def snapshot(self) -> "StructuredOutput":
        """Return a static snapshot of all elements accumulated so far.
        
        The snapshot captures the current state of every handle (open or closed)
        as a StructuredOutput object. This is used by accumulate-mode strategies
        (json/yaml) at session end, and is available at any time for logging,
        debugging, or programmatic inspection.
        """
        ...

    def close(self, *, exit_code: int = 0) -> "StructuredOutput":
        """Close the session and finalize all output.
        
        Any handles still open are force-closed (with a warning logged).
        Emits a SessionEnd event to the strategy. Returns the final
        StructuredOutput snapshot.
        
        Args:
            exit_code: The command's exit code (included in the snapshot).
        
        Returns:
            The final StructuredOutput snapshot.
        """
        ...

    # --- Context manager support ---

    def __enter__(self) -> "OutputSession":
        return self

    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
        """Auto-close session on context exit.
        
        If exiting due to an exception, sets exit_code to 1 and emits an
        error status element before closing.
        """
        ...
##### Element Handles Element handles are the producer-facing API. Each handle type wraps a specific element kind and provides methods appropriate to that kind. All handles share a common base: 

class ElementHandle(Generic[E]):
    """Base class for all element handles.
    
    An element handle is a write-only view of an output element. Producers use
    handles to incrementally build element content without knowledge of the
    active format or materialization strategy.
    
    Type Parameter:
        E: The OutputElement subclass this handle wraps (e.g., Panel, Table).
    
    Thread Safety:
        Individual handle methods are thread-safe. Multiple threads may call
        methods on *different* handles concurrently. Concurrent writes to the
        *same* handle are serialized via an internal lock.
    
    Lifecycle:
        handle = session.table(...)    # Created by session factory
        handle.add_row(...)            # Write operations (zero or more)
        handle.close()                 # Finalize (required unless auto-closed)
    
    Closed Handle Behavior:
        Calling any write method on a closed handle raises ElementClosedError.
    """

    handle_id: str                       # Unique handle identifier (ULID)
    element_type: str                    # Semantic type ("panel", "table", etc.)
    declaration_index: int               # Position in session's declaration order

    _session: OutputSession              # Owning session (for event emission)
    _element: E                          # The accumulated element state
    _state: HandleState                  # "open" | "closed"
    _lock: threading.Lock                # Serializes writes to this handle

    def close(self) -> None:
        """Close this handle, signaling that no more data will be written.
        
        Emits an ElementClosed event to the materialization strategy.
        For buffered strategies, this triggers rendering of the element.
        """
        ...

    @property
    def is_open(self) -> bool:
        """Whether this handle is still accepting writes."""
        ...

    @property
    def element(self) -> E:
        """The accumulated element state (read-only snapshot)."""
        ...

    def __enter__(self) -> Self:
        return self

    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
        """Auto-close handle on context exit."""
        if self.is_open:
            self.close()


class PanelHandle(ElementHandle[Panel]):
    """Handle for building a Panel element incrementally.
    
    Panels are titled groups of key-value pairs. Entries can be added,
    updated, or removed after creation.
    """

    def set_entry(self, key: str, value: str, *,
                  style_hint: str | None = None,
                  icon: str | None = None) -> None:
        """Set or update a key-value entry in the panel.
        
        If an entry with the given key already exists, it is updated.
        Otherwise, a new entry is appended.
        
        Emits an ElementUpdated event.
        """
        ...

    def set_entries(self, entries: dict[str, str], *,
                    style_hints: dict[str, str] | None = None) -> None:
        """Set multiple entries at once (batch update). Emits a single event."""
        ...

    def remove_entry(self, key: str) -> None:
        """Remove an entry by key. Emits an ElementUpdated event."""
        ...


class TableHandle(ElementHandle[Table]):
    """Handle for building a Table element incrementally.
    
    Tables are the primary element for streamed data. Rows can be added
    one at a time or in batches as data becomes available from queries,
    API calls, or concurrent operations.
    """

    def add_row(self, row: dict) -> None:
        """Append a single row to the table.
        
        The row dict maps column names to cell values. Missing columns
        are filled with None. Extra columns not in the schema are ignored.
        
        Emits an ElementUpdated event (type=row_added).
        """
        ...

    def add_rows(self, rows: list[dict]) -> None:
        """Append multiple rows in a batch. Emits a single ElementUpdated event."""
        ...

    def set_summary(self, summary: dict) -> None:
        """Set or update the summary/aggregation row. Emits an ElementUpdated event."""
        ...

    def set_sort_key(self, column: str, *, descending: bool = False) -> None:
        """Change the sort key. Emits an ElementUpdated event."""
        ...


class TreeHandle(ElementHandle[Tree]):
    """Handle for building a Tree element incrementally.
    
    Trees are built by adding child nodes to existing nodes. The root node
    is created with the handle. Subtrees can be constructed incrementally
    as hierarchical data is discovered.
    """

    def add_child(self, parent_path: str | None, label: str, *,
                  style_hint: str | None = None,
                  collapsed: bool = False,
                  metadata: dict | None = None) -> str:
        """Add a child node to the tree.
        
        Args:
            parent_path: Slash-separated path to the parent node (None = root).
            label: Display label for the new node.
            style_hint: Optional color/style hint.
            collapsed: Whether this node starts collapsed in interactive renderers.
            metadata: Arbitrary data attached to the node.
        
        Returns:
            The full path to the newly created node (for use as parent_path
            in subsequent add_child calls).
        
        Emits an ElementUpdated event.
        """
        ...

    def set_node_style(self, path: str, style_hint: str) -> None:
        """Update the style of an existing node. Emits an ElementUpdated event."""
        ...


class ProgressHandle(ElementHandle[ProgressIndicator]):
    """Handle for updating a ProgressIndicator element.
    
    Progress handles are unique in that they are expected to receive many
    rapid updates. The materialization strategy may throttle update events
    to avoid overwhelming the terminal (e.g., limiting redraws to 10/sec).
    """

    def set_progress(self, current: int, total: int | None = None) -> None:
        """Update the progress counter.
        
        Args:
            current: Current progress value.
            total: Total value (can change, e.g., when total is discovered late).
        
        Emits an ElementUpdated event (may be throttled by the strategy).
        """
        ...

    def set_step_status(self, step_label: str, status: str) -> None:
        """Update the status of a named step.
        
        Args:
            step_label: The label of the step to update.
            status: New status — "pending" | "active" | "done" | "error" | "skipped".
        
        Emits an ElementUpdated event.
        """
        ...

    def set_label(self, label: str) -> None:
        """Update the progress label text. Emits an ElementUpdated event."""
        ...

    def increment(self, delta: int = 1) -> None:
        """Increment progress by delta. Convenience wrapper around set_progress."""
        ...


class StatusHandle(ElementHandle[StatusMessage]):
    """Handle for a status message.
    
    Status handles are typically created and immediately closed (fire-and-forget
    messages). However, they can be kept open for messages that may be revised
    (e.g., a "Working..." status that becomes "Done" or "Failed").
    """

    def set_message(self, message: str) -> None:
        """Update the status message text. Emits an ElementUpdated event."""
        ...

    def set_level(self, level: str) -> None:
        """Change the status level. Emits an ElementUpdated event."""
        ...

    def set_detail(self, detail: str | None) -> None:
        """Set or clear the detail text. Emits an ElementUpdated event."""
        ...


class TextHandle(ElementHandle[TextBlock]):
    """Handle for a text block. Supports appending text incrementally."""

    def append(self, text: str) -> None:
        """Append text to the block. Emits an ElementUpdated event."""
        ...

    def set_content(self, content: str) -> None:
        """Replace the entire content. Emits an ElementUpdated event."""
        ...


class CodeHandle(ElementHandle[CodeBlock]):
    """Handle for a code block."""

    def set_content(self, content: str) -> None:
        """Set the code content. Emits an ElementUpdated event."""
        ...

    def set_language(self, language: str) -> None:
        """Set the language for syntax highlighting. Emits an ElementUpdated event."""
        ...

    def set_highlight_lines(self, lines: list[int]) -> None:
        """Set lines to highlight. Emits an ElementUpdated event."""
        ...


class DiffHandle(ElementHandle[DiffBlock]):
    """Handle for a diff block. Hunks can be added incrementally."""

    def add_hunk(self, header: str, lines: list["DiffLine"]) -> None:
        """Add a diff hunk. Emits an ElementUpdated event."""
        ...

    def set_stats(self, insertions: int, deletions: int, **extra: int) -> None:
        """Set diff statistics. Emits an ElementUpdated event."""
        ...
##### Element Events Element handles communicate with the materialization strategy through a typed event system. Events are the sole interface between production (handles) and consumption (strategy) — this indirection is what enables format-agnostic producer code: 

class ElementEvent:
    """Base class for all events emitted by element handles."""
    event_type: str                      # "created" | "updated" | "closed"
    handle_id: str                       # The handle that emitted this event
    element_type: str                    # The element kind ("panel", "table", etc.)
    timestamp: datetime                  # When the event occurred
    session_id: str                      # The owning session


class ElementCreated(ElementEvent):
    """Emitted when a new element handle is created via a session factory."""
    event_type = "created"
    declaration_index: int               # Position in session declaration order
    initial_state: OutputElement         # The element's initial state


class ElementUpdated(ElementEvent):
    """Emitted when data is written to an element handle."""
    event_type = "updated"
    update_type: str                     # Kind-specific: "entry_set", "row_added",
                                         #   "progress_changed", "step_status_changed", etc.
    delta: dict                          # The change payload (what was added/modified)
    element_snapshot: OutputElement      # The full element state after this update


class ElementClosed(ElementEvent):
    """Emitted when an element handle is closed (no more data will arrive)."""
    event_type = "closed"
    final_state: OutputElement           # The element's final accumulated state


class SessionEnd(ElementEvent):
    """Emitted when the session itself is closed."""
    event_type = "session_end"
    exit_code: int
    snapshot: "StructuredOutput"         # The complete accumulated output
##### Element Data Model (Snapshot Types) Each element handle accumulates state into a typed **snapshot object**. These are the data classes that represent a fully-built element — they are what the `ElementRenderer` receives when it is time to paint. They are also the building blocks of the `StructuredOutput` returned by `session.snapshot()`: 

class OutputElement:
    """Base class for all output element snapshot types."""
    element_type: str                    # Semantic type identifier
    metadata: dict                       # Arbitrary metadata (timestamps, IDs, etc.)
    priority: str = "normal"             # "critical" | "normal" | "supplementary"
    collapse_hint: str = "auto"          # "always" | "auto" | "never" — guidance for renderers
                                         #   on whether this element can be collapsed/hidden

class Panel(OutputElement):
    """A titled group of key-value pairs."""
    element_type = "panel"
    title: str
    entries: list[PanelEntry]            # Each entry: key, value, style_hint (color, icon, etc.)
    border_style: str = "rounded"        # "rounded" | "square" | "heavy" | "none"

class PanelEntry:
    """A single key-value pair within a Panel."""
    key: str
    value: str
    style_hint: str | None = None        # Color/style for the value (e.g., "success", "warning")
    icon: str | None = None              # Optional icon/prefix character

class Table(OutputElement):
    """A tabular data set with typed columns."""
    element_type = "table"
    title: str | None
    columns: list[ColumnDef]             # name, type, alignment, width_hint, sortable
    rows: list[dict]                     # Column name → cell value
    summary: dict | None                 # Optional aggregation row (totals, counts)
    max_rows_hint: int | None            # Suggest truncation for large datasets
    sort_key: str | None                 # Default sort column

class ColumnDef:
    """Schema for a single table column."""
    name: str                            # Column display name
    type: str = "string"                 # "string" | "number" | "boolean" | "datetime" | "id"
    alignment: str = "left"              # "left" | "right" | "center"
    width_hint: int | None = None        # Suggested character width (None = auto)
    sortable: bool = False               # Whether this column can be sorted
    style_hint: str | None = None        # Default style for cells in this column

class Tree(OutputElement):
    """A hierarchical tree structure."""
    element_type = "tree"
    root: TreeNode                       # Recursive node structure
    max_depth_hint: int | None           # Suggest depth truncation
    show_guides: bool = True             # Whether to show tree guide lines

class TreeNode:
    """A node in a tree structure."""
    label: str
    style_hint: str | None               # Color/style for this node
    children: list["TreeNode"]
    collapsed: bool = False              # Hint: start collapsed in interactive renderers
    metadata: dict                       # Arbitrary data attached to the node

class StatusMessage(OutputElement):
    """A status line (success, warning, error, info)."""
    element_type = "status"
    level: str                           # "ok" | "warn" | "error" | "info"
    message: str
    detail: str | None                   # Optional detail text

class ProgressIndicator(OutputElement):
    """A progress bar or spinner for long-running operations."""
    element_type = "progress"
    label: str
    current: int | None
    total: int | None
    indeterminate: bool = False          # Spinner mode vs. progress bar mode
    steps: list[ProgressStep] | None     # Named steps with status (pending/active/done)

class ProgressStep:
    """A named step within a progress indicator."""
    label: str
    status: str                          # "pending" | "active" | "done" | "error" | "skipped"

class CodeBlock(OutputElement):
    """A block of source code with optional syntax highlighting."""
    element_type = "code"
    content: str
    language: str | None                 # For syntax highlighting
    line_numbers: bool = False
    highlight_lines: list[int] | None    # Lines to emphasize

class DiffBlock(OutputElement):
    """A unified diff display."""
    element_type = "diff"
    hunks: list[DiffHunk]
    file_a: str | None
    file_b: str | None
    stats: dict | None                   # insertions, deletions, etc.

class DiffHunk:
    """A single hunk within a diff."""
    header: str                          # @@ line range @@
    lines: list[DiffLine]

class DiffLine:
    """A single line in a diff hunk."""
    type: str                            # "context" | "add" | "remove"
    content: str
    line_number_old: int | None
    line_number_new: int | None

class TextBlock(OutputElement):
    """A free-form text block (descriptions, rationale, etc.)."""
    element_type = "text"
    content: str
    wrap: bool = True
    indent: int = 0

class Separator(OutputElement):
    """A visual separator between logical groups."""
    element_type = "separator"
    style: str = "line"                  # "line" | "blank" | "double"

class ActionHint(OutputElement):
    """A suggested next-step action for the user."""
    element_type = "action_hint"
    commands: list[str]                  # Suggested CLI commands
    description: str | None

class StructuredOutput:
    """Static snapshot of a complete command output.
    
    This is the accumulated state of all elements at a point in time.
    It is produced by OutputSession.snapshot() and OutputSession.close().
    
    Uses:
    - Final serialization for json/yaml formats
    - Logging and audit trails
    - Programmatic inspection and testing
    - TUI widget data binding (initial state)
    """
    command: str                         # The command that produced this output
    session_id: str                      # The session that produced this output
    elements: list[OutputElement]        # Ordered list of element snapshots
    exit_code: int = 0
    timing: dict | None                  # start_time, end_time, duration
    metadata: dict                       # command-specific metadata
##### Materialization Strategies The materialization strategy is the format-side counterpart to the output session. It receives element events and decides *when* and *how* to render content. Each strategy is paired with an `ElementRenderer` that handles the actual visual formatting of individual elements. The strategy pattern creates a clean separation between **timing/ordering policy** (when to render) and **visual formatting** (how to render). This means the same `PlainElementRenderer` can be used whether elements arrive all-at-once or are streamed concurrently — the strategy handles the coordination. 

class MaterializationStrategy(Protocol):
    """Interface for format-driven output materialization.
    
    A materialization strategy receives element lifecycle events from the
    OutputSession and decides when to render element content to the output
    stream. Strategies do not render elements themselves — they delegate
    to a paired ElementRenderer at the appropriate time.
    
    The strategy is the mechanism by which format-agnostic producer code
    produces correct output regardless of format. The producer writes to
    handles; the strategy decides what reaches the terminal and when.
    """

    strategy_name: str                   # "live" | "sequential_buffer" | "accumulate"

    def bind(self, renderer: "ElementRenderer",
             terminal_caps: "TerminalCapabilities") -> None:
        """Bind this strategy to a renderer and terminal capabilities.
        
        Called once during format resolution, before the session opens.
        The strategy retains a reference to the renderer for use during
        event handling. The output stream is provided separately via
        on_session_begin, since the session owns the stream.
        """
        ...

    def on_session_begin(self, session: OutputSession, stream: IO) -> None:
        """Called when the session opens. The strategy receives the output
        stream and may write preamble (e.g., opening JSON bracket)."""
        ...

    def on_element_created(self, event: ElementCreated) -> None:
        """Called when a new element handle is created."""
        ...

    def on_element_updated(self, event: ElementUpdated) -> None:
        """Called when data is written to an element handle."""
        ...

    def on_element_closed(self, event: ElementClosed) -> None:
        """Called when an element handle is closed."""
        ...

    def on_session_end(self, event: SessionEnd) -> None:
        """Called when the session closes. The strategy may write epilogue."""
        ...


class LiveMaterializer(MaterializationStrategy):
    """Materialization strategy for the `rich` format.
    
    Renders element updates in real-time using terminal cursor movement.
    Multiple elements can be visually active and updating simultaneously.
    The terminal display is a live document that is rewritten in place.
    
    Behavior:
    - on_element_created: Allocates screen region for the element, renders
      initial (possibly empty) visual state.
    - on_element_updated: Re-renders the element in place using cursor
      movement. For progress indicators, updates may be throttled to a
      maximum refresh rate (default: 15 fps) to avoid terminal flooding.
    - on_element_closed: Renders the final state and freezes the screen
      region (no further updates). May apply a visual transition (e.g.,
      spinner resolves to a checkmark).
    - on_session_end: Finalizes the display, moves cursor to end, and
      restores normal terminal scrolling.
    
    Screen Layout:
    Elements are arranged vertically in declaration order. Each element
    occupies a contiguous block of terminal lines. The materializer tracks
    the line offset and height of each element's region. When an element's
    height changes (e.g., a table gains rows), subsequent elements are
    shifted down.
    
    Concurrent Updates:
    Updates from multiple handles are coalesced into a single frame refresh
    at the target frame rate. The materializer maintains a dirty-element set
    and redraws all dirty elements in a single pass per frame.
    """
    strategy_name = "live"

    _frame_rate: float = 15.0            # Maximum redraws per second
    _element_regions: OrderedDict[str, ScreenRegion]  # handle_id → screen region
    _dirty_set: set[str]                 # handle_ids that need redraw
    _frame_timer: asyncio.TimerHandle    # Coalescing timer for frame redraws


class SequentialBufferMaterializer(MaterializationStrategy):
    """Materialization strategy for `plain`, `color`, and `table` formats.
    
    Buffers element content and renders elements sequentially in declaration
    order. An element's content is rendered to the output stream only when
    its handle is closed. If handles are closed out of declaration order,
    the out-of-order element's rendered content is held in a buffer until
    all preceding elements have been rendered.
    
    This strategy ensures that static, scrolling output formats produce
    coherent sequential output even when producers write to handles
    concurrently and close them in arbitrary order.
    
    Behavior:
    - on_element_created: Records the element's declaration index. No output.
    - on_element_updated: Buffers the update internally. No output.
    - on_element_closed: If this element is the next in declaration order,
      renders it immediately (and any buffered subsequent elements that are
      also closed). Otherwise, buffers the rendered content.
    - on_session_end: Force-renders any remaining buffered elements (handles
      that were never closed, in declaration order).
    
    Example (two tables populated concurrently):
    1. Handle A (index 0) created — table "Resources"
    2. Handle B (index 1) created — table "Validations"
    3. Handle B receives rows, Handle A receives rows (interleaved)
    4. Handle B closes (index 1) — rendered content buffered (waiting for A)
    5. Handle A closes (index 0) — A is rendered to stream, then buffered B
       is rendered to stream
    
    Result: Output shows table A followed by table B, regardless of the
    order in which data arrived or handles closed.
    """
    strategy_name = "sequential_buffer"

    _next_render_index: int = 0          # The declaration index to render next
    _rendered_buffers: dict[int, str]     # index → pre-rendered content (waiting)
    _closed_set: set[int]                # Declaration indices of closed elements


class AccumulateMaterializer(MaterializationStrategy):
    """Materialization strategy for `json` and `yaml` formats.
    
    Accumulates all element data silently until the session ends, then
    serializes the complete StructuredOutput as a single JSON or YAML
    document.
    
    Behavior:
    - on_element_created: No output.
    - on_element_updated: No output.
    - on_element_closed: No output.
    - on_session_end: Calls session.snapshot() to get the final
      StructuredOutput, then delegates to the ElementRenderer's
      serialize() method for complete document serialization.
    
    This strategy is the simplest — it ignores all intermediate events and
    only acts on session_end. It exists as a distinct strategy (rather than
    a special case) to maintain the uniform strategy interface.
    """
    strategy_name = "accumulate"
##### ElementRenderer Protocol While the `MaterializationStrategy` controls *when* elements are rendered, the `ElementRenderer` controls *how* each element type is visually formatted. Each format has a paired `ElementRenderer` implementation: 

class ElementRenderer(Protocol):
    """Interface for format-specific element rendering.
    
    An ElementRenderer knows how to paint each element type for a specific
    output format. It is called by the MaterializationStrategy when it is
    time to render an element.
    
    Implementations:
    - PlainElementRenderer: ASCII text, no escapes
    - ColorElementRenderer: ANSI-colored text, same layout as plain
    - TableElementRenderer: Unicode box-drawing with color
    - RichElementRenderer: Advanced terminal features (cursor, animation)
    - JsonElementRenderer: JSON serialization
    - YamlElementRenderer: YAML serialization
    """

    format_name: str                     # "plain", "color", "table", "rich", "json", "yaml"

    def render_panel(self, panel: Panel, stream: IO) -> None:
        """Render a panel element to the stream."""
        ...

    def render_table(self, table: Table, stream: IO) -> None:
        """Render a table element to the stream."""
        ...

    def render_tree(self, tree: Tree, stream: IO) -> None:
        """Render a tree element to the stream."""
        ...

    def render_status(self, status: StatusMessage, stream: IO) -> None:
        """Render a status message to the stream."""
        ...

    def render_progress(self, progress: ProgressIndicator, stream: IO) -> None:
        """Render a progress indicator to the stream."""
        ...

    def render_code(self, code: CodeBlock, stream: IO) -> None:
        """Render a code block to the stream."""
        ...

    def render_diff(self, diff: DiffBlock, stream: IO) -> None:
        """Render a diff block to the stream."""
        ...

    def render_text(self, text: TextBlock, stream: IO) -> None:
        """Render a text block to the stream."""
        ...

    def render_separator(self, separator: Separator, stream: IO) -> None:
        """Render a visual separator to the stream."""
        ...

    def render_action_hint(self, hint: ActionHint, stream: IO) -> None:
        """Render an action hint to the stream."""
        ...

    def render_element(self, element: OutputElement, stream: IO) -> None:
        """Dispatch to the appropriate render method based on element type.
        
        This is the primary entry point used by materialization strategies.
        It uses a dispatch table to route to the correct typed method.
        """
        dispatch = {
            "panel": self.render_panel,
            "table": self.render_table,
            "tree": self.render_tree,
            "status": self.render_status,
            "progress": self.render_progress,
            "code": self.render_code,
            "diff": self.render_diff,
            "text": self.render_text,
            "separator": self.render_separator,
            "action_hint": self.render_action_hint,
        }
        handler = dispatch.get(element.element_type)
        if handler:
            handler(element, stream)

    def serialize(self, output: StructuredOutput, stream: IO) -> None:
        """Serialize a complete StructuredOutput to the stream.
        
        Used by AccumulateMaterializer for json/yaml formats. For visual
        formats (plain/color/table/rich), this method iterates over
        output.elements and calls render_element for each.
        """
        ...

    def can_render(self, terminal_caps: "TerminalCapabilities") -> bool:
        """Whether this renderer can operate in the given terminal environment."""
        ...
##### Format Resolution The active format is resolved using a precedence chain: 1. **CLI flag**: `--format ` on the command line (highest priority). 2. **Environment variable**: `CLEVERAGENTS_FORMAT=`. 3. **Config file**: The `core.format` key in the global config (`agents config set core.format `). 4. **TTY detection**: If stdout is not a TTY and no explicit format was set, fall back to `plain` (not `rich`), since non-TTY consumers cannot interpret ANSI codes or cursor movement. 5. **Default**: `rich`. Once the format is resolved, the CLI framework selects the corresponding `(MaterializationStrategy, ElementRenderer)` pair from the `RendererRegistry`, opens an `OutputSession` bound to that strategy, and passes the session to the command implementation. #### Format Specifications ##### `plain` — Plain Text **Philosophy**: Maximum portability. Output is pure ASCII text with no escape codes, no box-drawing characters, and no color. Suitable for piping to files, logs, grep, awk, or any non-terminal consumer. **Rendering rules**: - **Panels**: Rendered as indented key-value pairs with a header line. - **Tables**: Rendered as aligned columns separated by whitespace (no box drawing). Column headers are separated from data by a dashed line. - **Trees**: Rendered with ASCII indentation using `+--` and `|` characters. - **Status messages**: Prefixed with `[OK]`, `[WARN]`, `[ERROR]`, `[INFO]`. - **Progress**: Rendered as static status lines (no animation). Steps shown as `[x]` (done), `[ ]` (pending), `[>]` (active). - **Diffs**: Standard unified diff format. - **Code blocks**: Raw text with optional line numbers. - **No ANSI escape codes** of any kind. - **No Unicode characters** beyond basic ASCII (no box drawing, no checkmarks, no arrows). **Example** (`agents --format plain project show local/api-service`): 

$ agents --format plain project show local/api-service

Project Details
  Name: local/api-service
  Description: Backend API
  Resources: 2
  Remote: no
  Created: 2026-02-08 12:46

Linked Resources
  Resource          Type            Sandbox               Read-Only
  ----------------  --------------  --------------------  ---------
  local/api-repo    git-checkout    git_worktree          no
  local/staging-db  local/database  transaction_rollback  yes

Validations (3)
  local/run-tests    pytest --cov=src --cov-fail-under=80  required
  local/lint-check   ruff check .                          required
  local/check-bundle-size  node scripts/check-bundle-size.js     informational

Context
  Include: repo
  Exclude: **/node_modules/**
  Max File Size: 1 MB

Indexing Status
  Text Index: ready
  Vector Index: ready
  Graph Store: disabled
  Indexed Files: 347
  Last Indexed: 12:48

Active Plans
  Plan ID   Action               Phase
  --------  -------------------  -------
  01HXM7A9  local/code-coverage  execute

[OK] Project loaded
**Example** (`agents --format plain plan list`): 

$ agents --format plain plan list --phase execute

Plans
  ID        Phase    State       Action               Project            Elapsed
  --------  -------  ----------  -------------------  -----------------  ---------
  01HXM7A9  execute  processing  local/code-coverage  local/api-service  00:01:12

Filters
  Phase: execute
  State: (any)
  Project: (any)
  Action: (any)

Summary
  Total: 1
  Processing: 1
  Completed: 0
  Errored: 0

[OK] 1 plan listed
##### `color` — Colored Plain Text **Philosophy**: Same structural layout as `plain`, but with ANSI color codes applied to improve readability. No box-drawing characters, no cursor movement, no animation. **Rendering rules**: - **Identical layout to `plain`**, but with color applied: - **Headers/titles**: Bold cyan. - **Keys**: Bold blue. - **Values**: Default color, with semantic coloring: - Success/positive: Green. - Warnings/attention: Yellow. - Errors/failures: Red. - Identifiers/names: Cyan. - Counts/numbers: Default (white). - **Table headers**: Bold cyan with underlines rendered as dim dashes. - **Status prefixes**: `[OK]` in green, `[WARN]` in yellow, `[ERROR]` in red, `[INFO]` in blue. - **Diff lines**: `+` lines green, `-` lines red, `@@` headers cyan. - **No box-drawing characters** — uses the same whitespace/dash layout as `plain`. - **No cursor movement or animation** — pure scrolling output. - **Respects `NO_COLOR` environment variable**: If `NO_COLOR` is set, `color` format falls back to `plain`. **Example** (`agents --format color project show local/api-service`): 

$ agents --format color project show local/api-service

Project Details
  Name: local/api-service
  Description: Backend API
  Resources: 2
  Remote: no
  Created: 2026-02-08 12:46

Linked Resources
  Resource          Type            Sandbox              Read-Only
  ----------------  --------------  --------------------  ---------
  local/api-repo    git-checkout    git_worktree          no
  local/staging-db  local/database  transaction_rollback  yes

Validations (3)
  local/run-tests    pytest --cov=src --cov-fail-under=80  required
  local/lint-check   ruff check .                          required
  local/check-bundle-size  node scripts/check-bundle-size.js     info

Context
  Include: repo
  Exclude: **/node_modules/**
  Max File Size: 1 MB

Indexing Status
  Text Index: ready
  Vector Index: ready
  Graph Store: disabled
  Indexed Files: 347
  Last Indexed: 12:48

Active Plans
  Plan ID   Action               Phase
  --------  -------------------  -------
  01HXM7A9  local/code-coverage  execute

[OK] Project loaded
##### `table` — ASCII Box-Drawing Tables **Philosophy**: Structured, visually distinct panels and tables using Unicode box-drawing characters (╭──────────────────╮╰╯│─). Uses color. This is the style shown in the existing CLI examples throughout this document. **Rendering rules**: - **Panels**: Rendered as bordered boxes with title in the top border. Uses `╭─╮│╰──────────────────╯` characters for rounded corners. - **Tables**: Rendered inside bordered boxes with column-aligned headers and separator lines using `─` and `│`. - **Trees**: Rendered inside a bordered box using `├──`, `└──`, `│` tree guide characters. - **Status messages**: Use Unicode indicators: `✓` (green) for OK, `⚠` (yellow) for WARN, `✗` (red) for ERROR, `ℹ` (blue) for INFO. - **Progress**: Rendered as a step list inside a panel with `✓`, `⏳`, `•` markers. - **Color scheme**: Same semantic coloring as `color` format, applied within box structures. - **No animation or cursor movement** — the boxes are static, scrolling output. **Distinction from `rich`**: The `table` format uses the same box-drawing panels and color as `rich` for static content, but it does **not** use any dynamic or interactive terminal features. There are no animated spinners, no live-updating progress bars, no cursor movement, and no in-place redraws. All output is static and scrolls sequentially. Where `rich` would show a spinning `⠋` and a live progress bar, `table` renders a static snapshot using fixed markers (`✓`, `⏳`, `•`). This makes `table` suitable for terminals without advanced capabilities, and for output that will be reviewed after the fact (e.g., scrollback buffers). **Example** (`agents --format table project show local/api-service`): 

$ agents --format table project show local/api-service

╭─ Project Details ──────────────╮
│ Name: local/api-service        │
│ Description: Backend API       │
│ Resources: 2                   │
│ Remote: no                     │
│ Created: 2026-02-08 12:46      │
╰────────────────────────────────╯

╭─ Linked Resources ──────────────────────────────────────────────────────╮
│ Resource          Type            Sandbox              Read-Only        │
│ ────────────────  ──────────────  ────────────────────  ─────────       │
│ local/api-repo   git-checkout    git_worktree         no                │
│ local/staging-db local/database  transaction_rollback yes               │
╰─────────────────────────────────────────────────────────────────────────╯

╭─ Validations (3) ───────────────────────────────────────────────────────────────╮
│ local/run-tests    pytest --cov=src --cov-fail-under=80  required               │
│ local/lint-check   ruff check .                          required               │
│ local/check-bundle-size  node scripts/check-bundle-size.js     informational    │
╰─────────────────────────────────────────────────────────────────────────────────╯

╭─ Context ───────────────────╮
│ Include: repo               │
│ Exclude: **/node_modules/** │
│ Max File Size: 1 MB         │
╰─────────────────────────────╯

╭─ Indexing Status ──────────╮
│ Text Index: ready          │
│ Vector Index: ready        │
│ Graph Store: disabled      │
│ Indexed Files: 347         │
│ Last Indexed: 12:48        │
╰────────────────────────────╯

╭─ Active Plans ──────────────────────────╮
│ Plan ID   Action               Phase    │
│ ────────  ───────────────────  ───────  │
│ 01HXM7A9  local/code-coverage  execute  │
╰─────────────────────────────────────────╯

✓ OK Project loaded
**Example** (`agents --format table plan execute 01HXM8C2ZK`): Unlike `rich` mode which would show animated spinners and a live progress bar, the `table` format renders a static snapshot of execution state: 

$ agents --format table plan execute 01HXM8C2ZK

╭─ Execution ──────────────────────╮
│ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
│ Phase: execute                   │
│ Sandbox: git_worktree            │
│ Worker: local/executor           │
│ Started: 12:58:10                │
│ Attempt: 1                       │
╰──────────────────────────────────╯

╭─ Strategy Summary ─────────────────────╮
│ Decisions: 8                           │
│ Invariants: 2                          │
│ Planned Child Plans: 2+                │
│ Estimated Files: ~12                   │
│ Risk: low                              │
╰────────────────────────────────────────╯

╭─ Progress ─────────╮
│ ✓ Collect context  │
│ ✓ Run tools        │
│ ⏳ Build changeset │
│ • Validate         │
╰────────────────────╯

✓ OK Execution started
##### `rich` — Modern Rich CLI Elements **Philosophy**: The premium interactive terminal experience. Uses advanced terminal capabilities: cursor movement, inline updates, animated spinners, live-updating progress bars, collapsible sections, syntax highlighting, and dynamic layout. This is the default format. **Rendering rules**: - **Panels**: Rich bordered panels with rounded corners, title bars, and optional collapse/expand behavior. Panels may animate into view. - **Tables**: Full-featured tables with automatic column sizing, truncation with ellipsis, sortable column indicators, alternating row shading, and horizontal scrolling for wide tables. - **Trees**: Interactive collapsible trees. Nodes expand/collapse with visual animation. Color-coded by node type. Depth guides use dotted lines. - **Status messages**: Use animated checkmarks/spinners that resolve to final state. Success messages may briefly flash or highlight. - **Progress**: Live-updating progress bars with: - Animated spinners (Braille, dots, or bars depending on terminal capability). - Elapsed time and ETA. - Per-step status with animated transitions (pending → active → done). - Multi-line progress for parallel operations. - **Diffs**: Syntax-highlighted side-by-side or unified diffs with line numbers, change highlighting at the character level (not just line level), and navigable hunks. - **Code blocks**: Full syntax highlighting using terminal colors (256-color or truecolor when available). Line numbers in dim color. Highlighted lines with background color. - **Dynamic layout**: Adapts to terminal width. Narrow terminals get a stacked layout; wide terminals get side-by-side panels. - **Live updates**: Long-running commands (plan execute, plan status) use live-updating displays that redraw in place rather than scrolling. - **Graceful degradation**: If the terminal does not support required capabilities (e.g., no truecolor, no cursor movement), the renderer automatically falls back to `table` rendering for those elements. **Example** (`agents --format rich plan execute 01HXM8C2ZK`): The `rich` format produces output that cannot be fully represented in static documentation — animated spinners cycle in place, progress bars fill smoothly, and elements update without scrolling. The rendering below is a static snapshot of what the terminal would display at a given moment: 

$ agents --format rich plan execute 01HXM8C2ZK

╭─ Execution ──────────────────────╮
│ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
│ Phase: execute                   │
│ Sandbox: git_worktree            │
│ Worker: local/executor           │
│ Started: 12:58:10                │
╰──────────────────────────────────╯

⠋ Collecting context...                      (⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏ animates in place)
  ├── repo: local/api-repo ✓
  └── db: local/staging-db ✓

╭─ Strategy Summary ──────────────────────────────────────────────────────╮
│ 8 decisions │ 2 invariants │ 2+ child plans │ ~12 files │ risk: low     │
╰─────────────────────────────────────────────────────────────────────────╯

Progress ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━  42%  elapsed 0:01:12  ETA 0:01:40
  ✓ Collect context .................. 0.8s
  ✓ Run tools (8 calls) ............. 12.4s
  ⠙ Build changeset ................. (running)     (animates in place)
  ○ Validate ........................ (pending)

╭─ Live Tool Calls ───────────────────────────────────────╮
│ #6 read_file   src/auth/__init__.py   ✓  0.1s           │
│ #7 write_file  tests/test_auth.py     ✓  0.2s           │
│ #8 edit_file   src/auth/session.py    ⠙  ...            │
╰─────────────────────────────────────────────────────────╯
In `rich` mode: - The Braille spinner characters (`⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏`) animate in real-time, cycling in place without scrolling. - The progress bar (`━━━`) fills smoothly as work completes. - Completed steps appear with a green `✓` via in-place line update (the line rewrites, it does not scroll). - The "Live Tool Calls" panel scrolls its content internally, showing only the most recent N calls. - The terminal is not flooded with scrolling text — elements update in place using cursor movement. **Example** (`agents --format rich version`): 

$ agents --format rich version

╭─────────────────────────────────────╮
│  CleverAgents CLI  v1.0.0           │
│  channel: stable                    │
╰─────────────────────────────────────╯

╭─ Build ─────────────────────────────╮
│ Build Date: 2026-02-08              │
│ Commit: a17c3f9                     │
│ Schema: v3                          │
│ Platform: linux-x86_64              │
│ Python: 3.13.1                      │
╰─────────────────────────────────────╯

╭─ Dependencies ─────────────────────────────────────────────────────────╮
│ LangGraph 0.2.60 │ LangChain 0.3.18 │ MCP SDK 1.4.0 │ Pydantic 2.10.4  │
╰────────────────────────────────────────────────────────────────────────╯

✓ OK Version reported
In `rich` mode, the version card may use background colors, bold gradients, or subtle box shadows (depending on terminal truecolor support). Elements may animate into view with a brief slide or fade transition. ##### `json` — JSON Data Structure **Philosophy**: Machine-readable output for programmatic consumption. Every command produces a well-defined JSON object. No ANSI color codes in the structural data. Color codes may appear only **within** text values that represent verbatim content (such as code blocks or diff output where the original text contained ANSI sequences), but all structural keys, labels, and metadata are plain strings. **Rendering rules**: - **Top-level structure**: Always a JSON object with a standard envelope: 

  {
    "command": "project show",
    "status": "ok",
    "exit_code": 0,
    "data": { ... },
    "timing": { "duration_ms": 42 },
    "metadata": { ... }
  }
- **Panels**: Rendered as nested objects within `data`. - **Tables**: Rendered as arrays of objects within `data`. - **Trees**: Rendered as nested objects with `children` arrays. - **Status messages**: Included in a `messages` array within the envelope. - **Progress**: Not rendered (JSON output is non-interactive; progress is omitted). - **Diffs**: Rendered as structured objects with `hunks` arrays. - **No ANSI codes** in any structural element. Raw ANSI codes are preserved only in string values that represent verbatim terminal output. - **Pretty-printed** by default (indented). Compact mode available via `--json-compact` (future option). - **Consistent schema per command**: Each command's JSON schema is stable and documented, enabling reliable programmatic parsing. **Example** (`agents --format json project show local/api-service`): 

{
  "command": "project show",
  "status": "ok",
  "exit_code": 0,
  "data": {
    "project": {
      "name": "local/api-service",
      "description": "Backend API",
      "type": "local",
      "remote": false,
      "created_at": "2026-02-08T12:46:00Z"
    },
    "linked_resources": [
      {
        "name": "local/api-repo",
        "type": "git-checkout",
        "sandbox_strategy": "git_worktree",
        "read_only": false
      },
      {
        "name": "local/staging-db",
        "type": "local/database",
        "sandbox_strategy": "transaction_rollback",
        "read_only": true
      }
    ],
    "validations": [
      {
        "name": "local/run-tests",
        "command": "pytest --cov=src --cov-fail-under=80",
        "mode": "required",
        "timeout": 600,
        "resource": "repo"
      },
      {
        "name": "local/lint-check",
        "command": "ruff check .",
        "mode": "required",
        "timeout": 300,
        "resource": null
      },
      {
        "name": "local/check-bundle-size",
        "command": "node scripts/check-bundle-size.js",
        "mode": "informational",
        "timeout": 300,
        "resource": null
      }
    ],
    "context": {
      "include_resources": ["repo"],
      "exclude_paths": ["**/node_modules/**"],
      "max_file_size_bytes": 1048576
    },
    "indexing": {
      "text_index": "ready",
      "vector_index": "ready",
      "graph_store": "disabled",
      "indexed_files": 347,
      "last_indexed_at": "2026-02-08T12:48:00Z"
    },
    "active_plans": [
      {
        "plan_id": "01HXM7A9",
        "action": "local/code-coverage",
        "phase": "execute"
      }
    ]
  },
  "timing": {
    "duration_ms": 42
  },
  "messages": [
    { "level": "ok", "text": "Project loaded" }
  ]
}
**Example** (`agents --format json plan list --phase execute`): 

{
  "command": "plan list",
  "status": "ok",
  "exit_code": 0,
  "data": {
    "plans": [
      {
        "id": "01HXM7A9",
        "phase": "execute",
        "state": "processing",
        "action": "local/code-coverage",
        "project": "local/api-service",
        "elapsed": "00:01:12"
      }
    ],
    "filters": {
      "phase": "execute",
      "state": null,
      "project": null,
      "action": null
    },
    "summary": {
      "total": 1,
      "processing": 1,
      "completed": 0,
      "errored": 0
    }
  },
  "timing": {
    "duration_ms": 18
  },
  "messages": [
    { "level": "ok", "text": "1 plan listed" }
  ]
}
##### `yaml` — YAML Data Structure **Philosophy**: Same data as `json` but in YAML format. Preferred by users who find YAML more readable for configuration and scripting workflows. Follows the same structural conventions as `json`. **Rendering rules**: - **Same data envelope** as JSON (`command`, `status`, `exit_code`, `data`, `timing`, `messages`). - **YAML 1.2 compliant** output. - **Multi-line strings** use YAML block scalars (`|` for literal, `>` for folded) when appropriate. - **No ANSI codes** in structural elements (same rule as JSON). - **Sorted keys** for deterministic output. **Example** (`agents --format yaml project show local/api-service`): 

command: project show
status: ok
exit_code: 0
data:
  project:
    name: local/api-service
    description: Backend API
    type: local
    remote: false
    created_at: "2026-02-08T12:46:00Z"
  linked_resources:
    - name: local/api-repo
      type: git-checkout
      sandbox_strategy: git_worktree
      read_only: false
    - name: local/staging-db
      type: local/database
      sandbox_strategy: transaction_rollback
      read_only: true
  validations:
    - name: local/run-tests
      command: "pytest --cov=src --cov-fail-under=80"
      mode: required
      timeout: 600
      resource: repo
    - name: local/lint-check
      command: "ruff check ."
      mode: required
      timeout: 300
      resource: null
    - name: local/check-bundle-size
      command: "node scripts/check-bundle-size.js"
      mode: informational
      timeout: 300
      resource: null
  context:
    include_resources:
      - repo
    exclude_paths:
      - "**/node_modules/**"
    max_file_size_bytes: 1048576
  indexing:
    text_index: ready
    vector_index: ready
    graph_store: disabled
    indexed_files: 347
    last_indexed_at: "2026-02-08T12:48:00Z"
  active_plans:
    - plan_id: 01HXM7A9
      action: local/code-coverage
      phase: execute
timing:
  duration_ms: 42
messages:
  - level: ok
    text: Project loaded
#### Format Comparison Matrix | Capability | `plain` | `color` | `table` | `rich` | `json` | `yaml` | |---|---|---|---|---|---|---| | Color codes | No | Yes | Yes | Yes | No | No | | Box drawing | No | No | Yes | Yes | No | No | | Animation/spinners | No | No | No | Yes | No | No | | Live updates | No | No | No | Yes | No | No | | Cursor movement | No | No | No | Yes | No | No | | Syntax highlighting | No | No | No | Yes | No | No | | Collapsible sections | No | No | No | Yes | No | No | | Machine-parseable | Partially | Partially | No | No | Yes | Yes | | Pipe-safe | Yes | No* | No | No | Yes | Yes | | Unicode required | No | No | Yes | Yes | No | No | | TTY required | No | No | No | Yes** | No | No | \* `color` output can be piped if the consumer understands ANSI codes (e.g., `less -R`). \** `rich` gracefully degrades to `table` when stdout is not a TTY. #### Renderer Registration and Extension The framework uses a **registry pattern** for format renderers, enabling third-party or plugin renderers. Each format is registered as a `(MaterializationStrategy, ElementRenderer)` pair — the strategy controls timing/ordering, and the renderer controls visual formatting: 

@dataclass
class FormatRegistration:
    """A registered format: its strategy factory, renderer factory, and fallback."""
    strategy_factory: Callable[[TerminalCapabilities], MaterializationStrategy]
    renderer_factory: Callable[[TerminalCapabilities], ElementRenderer]
    fallback: str | None                 # Format name to fall back to, or None


class RendererRegistry:
    """Central registry for format (strategy, renderer) pairs.
    
    Formats are registered by name and resolved at runtime based on the
    active format and terminal capabilities. The registry supports dynamic
    registration, enabling plugins to add custom formats (e.g., 'html',
    'csv', 'markdown').
    
    Built-in registrations:
        "rich"  → (LiveMaterializer, RichElementRenderer), fallback="table"
        "table" → (SequentialBufferMaterializer, TableElementRenderer), fallback="color"
        "color" → (SequentialBufferMaterializer, ColorElementRenderer), fallback="plain"
        "plain" → (SequentialBufferMaterializer, PlainElementRenderer), fallback=None
        "json"  → (AccumulateMaterializer, JsonElementRenderer), fallback=None
        "yaml"  → (AccumulateMaterializer, YamlElementRenderer), fallback=None
    """

    _formats: dict[str, FormatRegistration] = {}

    @classmethod
    def register(cls, format_name: str,
                 strategy_factory: Callable[[TerminalCapabilities], MaterializationStrategy],
                 renderer_factory: Callable[[TerminalCapabilities], ElementRenderer],
                 fallback: str | None = None) -> None:
        """Register a format.
        
        Args:
            format_name: The format identifier (e.g., 'rich', 'json').
            strategy_factory: Callable that creates a MaterializationStrategy,
                given terminal capabilities.
            renderer_factory: Callable that creates an ElementRenderer,
                given terminal capabilities.
            fallback: Optional fallback format name if this format cannot
                operate in the current terminal environment.
        """
        cls._formats[format_name] = FormatRegistration(
            strategy_factory=strategy_factory,
            renderer_factory=renderer_factory,
            fallback=fallback,
        )

    @classmethod
    def resolve(cls, format_name: str,
                terminal_caps: TerminalCapabilities
                ) -> tuple[MaterializationStrategy, ElementRenderer]:
        """Resolve the best (strategy, renderer) pair for the given format.
        
        Walks the fallback chain if the requested format's renderer cannot
        operate in the current terminal environment. Returns the first pair
        where the renderer reports can_render(terminal_caps) == True.
        
        Raises:
            ValueError: If no usable format is found (should never happen
                since 'plain' has no fallback and always works).
        """
        current = format_name
        visited: set[str] = set()

        while current and current not in visited:
            visited.add(current)
            registration = cls._formats.get(current)
            if registration is None:
                break

            renderer = registration.renderer_factory(terminal_caps)
            if renderer.can_render(terminal_caps):
                strategy = registration.strategy_factory(terminal_caps)
                strategy.bind(renderer, terminal_caps=terminal_caps)
                return strategy, renderer

            current = registration.fallback

        # Ultimate fallback is always plain
        plain = cls._formats["plain"]
        renderer = plain.renderer_factory(terminal_caps)
        strategy = plain.strategy_factory(terminal_caps)
        strategy.bind(renderer, terminal_caps=terminal_caps)
        return strategy, renderer

    @classmethod
    def available_formats(cls) -> list[str]:
        """Return all registered format names."""
        return sorted(cls._formats.keys())

    @classmethod
    def is_registered(cls, format_name: str) -> bool:
        """Check if a format is registered."""
        return format_name in cls._formats
##### Terminal Capability Detection The framework detects terminal capabilities to guide format resolution, strategy selection, and renderer fallback: 

@dataclass
class TerminalCapabilities:
    """Detected capabilities of the output terminal.
    
    This dataclass is populated once at CLI startup and passed to the
    RendererRegistry for format resolution. It is also available to
    individual strategies and renderers for fine-grained adaptation
    (e.g., adjusting column widths to terminal width, choosing between
    256-color and truecolor palettes).
    """
    is_tty: bool                         # Is stdout a TTY?
    width: int                           # Terminal width in columns
    height: int                          # Terminal height in rows
    supports_ansi: bool                  # Supports basic ANSI escape codes?
    supports_256_color: bool             # Supports 256-color palette?
    supports_truecolor: bool             # Supports 24-bit truecolor?
    supports_unicode: bool               # Supports Unicode (box-drawing, etc.)?
    supports_cursor_movement: bool       # Supports cursor repositioning?
    supports_alternate_screen: bool      # Supports alternate screen buffer?
    no_color: bool                       # Is NO_COLOR environment variable set?
    term_program: str | None             # TERM_PROGRAM value (e.g., "iTerm2", "vscode")

    @classmethod
    def detect(cls) -> "TerminalCapabilities":
        """Auto-detect terminal capabilities from the environment.
        
        Detection logic:
        - is_tty: os.isatty(sys.stdout.fileno())
        - width/height: os.get_terminal_size() with fallback to (80, 24)
        - supports_ansi: True if is_tty and not Windows legacy console
        - supports_256_color: True if TERM contains "256color" or COLORTERM is set
        - supports_truecolor: True if COLORTERM is "truecolor" or "24bit"
        - supports_unicode: True if locale encoding is UTF-8
        - supports_cursor_movement: True if is_tty and TERM is not "dumb"
        - supports_alternate_screen: True if supports_cursor_movement
        - no_color: True if NO_COLOR environment variable is set (any value)
        - term_program: Value of TERM_PROGRAM environment variable
        """
        ...
##### Plugin Format Registration Third-party plugins can register custom formats using the registry: 

# Example: Registering a custom 'csv' format plugin
from cleveragents.output import RendererRegistry, SequentialBufferMaterializer

class CsvElementRenderer(ElementRenderer):
    """Renders tables as CSV, other elements as plain text."""
    format_name = "csv"

    def render_table(self, table: Table, stream: IO) -> None:
        writer = csv.writer(stream)
        writer.writerow([col.name for col in table.columns])
        for row in table.rows:
            writer.writerow([row.get(col.name, "") for col in table.columns])

    def can_render(self, terminal_caps: TerminalCapabilities) -> bool:
        return True  # CSV works everywhere

# Register at plugin load time
RendererRegistry.register(
    format_name="csv",
    strategy_factory=lambda caps: SequentialBufferMaterializer(),
    renderer_factory=lambda caps: CsvElementRenderer(),
    fallback="plain",
)
#### Edge Cases and Special Behaviors ##### Error Output Errors are rendered through the same framework. When a command raises an exception or signals an error, the session's context manager (`__exit__`) catches the exception, creates a `StatusMessage` with `level="error"` and an optional `TextBlock` with details, and closes the session with `exit_code=1`. In `json`/`yaml` formats, errors produce: 

{
  "command": "project show",
  "status": "error",
  "exit_code": 1,
  "error": {
    "code": "NOT_FOUND",
    "message": "Project 'local/nonexistent' not found",
    "detail": "No project with name 'local/nonexistent' exists. Run 'agents project list' to see available projects.",
    "suggestions": [
      "agents project list",
      "agents project create local/nonexistent"
    ]
  },
  "timing": { "duration_ms": 5 }
}
##### Empty Results When a list command returns no results, all formats handle it gracefully: - **plain/color**: Prints a message like `No projects found.` - **table**: Renders an empty table with headers and a `(empty)` message. - **rich**: Renders a dimmed panel with an empty-state message and suggested actions. - **json/yaml**: Returns an empty array in the appropriate data field. ##### Large Data Sets For commands that may return large result sets (e.g., `resource list` with thousands of resources): - **plain/color/table** (SequentialBufferMaterializer): The table handle accumulates rows as the producer adds them. Since the buffer is in-memory, very large result sets benefit from the `max_rows_hint` — the renderer truncates display at N rows with a `(... and N more rows)` indicator. The full data is still available in the snapshot for json/yaml. - **rich** (LiveMaterializer): Uses a virtual-scrolling table that renders only visible rows. Shows a count indicator (e.g., "Showing 1-50 of 2,847"). New rows animate into view as they are added. - **json/yaml** (AccumulateMaterializer): Accumulates and emits a complete array at session end. Streaming JSON lines (one JSON object per row) for very large sets is a future consideration. ##### Nested/Recursive Structures Tree-like data (resource trees, decision trees, plan hierarchies) may be arbitrarily deep. Renderers respect `max_depth_hint`: - **plain/color**: Truncate at depth N with a `... (N more levels)` indicator. - **table**: Same truncation, rendered inside a box. - **rich**: Collapsible tree nodes — deep levels start collapsed. User can expand interactively if the terminal supports it. - **json/yaml**: Full depth — no truncation (programmatic consumers need complete data). ##### Mixed Content Some commands produce mixed output (e.g., `plan status` has panels, tables, progress bars, and status messages). Each element is created via its own handle on the session, and the materialization strategy renders them in declaration order. The `ElementRenderer` is responsible for visual spacing and grouping between heterogeneous elements (e.g., inserting blank lines between a panel and a table in `plain` format, or adding visual margins in `rich` format). ##### Producer Error Mid-Stream When a producer encounters an error while writing to a handle (e.g., an API call fails while populating a table), the framework handles it as follows: 1. **The handle is closed with partial data** — the producer catches its exception, optionally calls `handle.close()` (or lets the context manager close it), and then creates a `StatusMessage` handle with `level="error"` to report the failure. 2. **The materialization strategy renders whatever was accumulated** — a table with 3 of an expected 10 rows is rendered with those 3 rows, followed by the error message. This is better than rendering nothing. 3. **The session's exit code is set to 1** — indicating partial failure. 4. **For `json`/`yaml` formats**, the accumulated snapshot includes both the partial data and the error message in the `messages` array, giving programmatic consumers full visibility. Example of producer error handling: 

async def list_resources(session: OutputSession, client: ApiClient) -> None:
    table = session.table("Resources", columns=[
        ColumnDef(name="Name"), ColumnDef(name="Type"), ColumnDef(name="Status"),
    ])

    try:
        async for resource in client.list_resources():
            table.add_row({
                "Name": resource.name,
                "Type": resource.type,
                "Status": resource.status,
            })
    except ApiError as e:
        table.close()  # Close with partial data
        session.status(f"Error fetching resources: {e}", level="error")
        return

    table.close()
    session.status(f"{table.element.row_count} resources listed", level="ok")
##### Abandoned Handles If a handle is never explicitly closed and the session ends (either normally via `session.close()` or via the context manager's `__exit__`), the session force-closes all remaining open handles: 1. A warning is logged (not rendered to the user): `"Handle {handle_id} ({element_type}) was not explicitly closed; force-closing at session end."` 2. The handle is closed with its current accumulated state. 3. The materialization strategy processes the `ElementClosed` event normally. This ensures that no data is silently lost, even if producer code forgets to close a handle due to an unhandled code path. ##### Back-Pressure and Throttling The `LiveMaterializer` (used by `rich` format) limits terminal redraws to its configured frame rate (default 15 fps). When handles emit updates faster than the frame rate: 1. Updates are coalesced — the materializer tracks a **dirty set** of handle IDs that have been updated since the last frame. 2. On each frame tick, all dirty elements are redrawn in a single pass, and the dirty set is cleared. 3. The event queue between session and strategy uses bounded capacity. If the queue fills (producer is vastly faster than rendering), the session's `_emit_event` method drops `ElementUpdated` events for handles that are already in the dirty set (since the next frame will redraw them anyway). `ElementCreated` and `ElementClosed` events are never dropped. For `SequentialBufferMaterializer` and `AccumulateMaterializer`, there is no back-pressure concern — updates are buffered in memory and never rendered incrementally. ##### Cancellation Semantics When a command is cancelled (e.g., user presses Ctrl+C): 1. The session receives a cancellation signal and enters the `"closing"` state. 2. All open handles are force-closed with their current state. 3. A `StatusMessage` with `level="warn"` and message `"Operation cancelled"` is emitted. 4. The session closes with `exit_code=130` (standard SIGINT exit code). 5. **For `rich` format**: The `LiveMaterializer` freezes the display, resolves any active spinners to a cancellation indicator (e.g., yellow `⚠`), and moves the cursor to the end of the output. 6. **For buffered formats**: Any elements that have been rendered stay on screen. Pending buffered elements are flushed in order, followed by the cancellation message. 7. **For `json`/`yaml`**: The accumulated snapshot is serialized with `"status": "cancelled"` and the appropriate exit code. ##### Interleaved Status Messages During Concurrent Production When multiple producers are running concurrently (e.g., populating two tables), status messages may be created at any time by any producer. The materialization strategy handles these based on format: - **`rich`** (LiveMaterializer): Status messages are rendered immediately in a dedicated status region at the bottom of the display (below all element regions). Multiple concurrent status messages stack vertically. - **`plain`/`color`/`table`** (SequentialBufferMaterializer): Status messages created during concurrent production are treated as elements in declaration order, just like tables and panels. A status message created between two table creations will be rendered between those tables. Status messages created *after* all tables will render after all tables are flushed. - **`json`/`yaml`** (AccumulateMaterializer): All status messages are collected in the `messages` array of the final snapshot, ordered by timestamp. #### Integration with Future TUI The reactive `OutputSession` architecture is intentionally designed to serve as the data layer for a future TUI (text user interface). The session's event-driven model maps directly to TUI widget patterns: 1. **Element handles become observable data sources.** A TUI `MaterializationStrategy` (e.g., `TuiMaterializer`) would subscribe to element events and route them to TUI widgets. The producer code (command logic) is completely unaware of whether it is driving a CLI, TUI, or web frontend — it writes to handles identically in all cases. 2. **Element types map to TUI widgets:** - `PanelHandle` → info pane or detail card widget - `TableHandle` → sortable, filterable data grid widget (rows arrive incrementally via `add_row` events) - `TreeHandle` → collapsible tree view widget (nodes arrive incrementally via `add_child` events) - `ProgressHandle` → animated progress bar or step-list widget - `StatusHandle` → toast notification or status bar message - `CodeHandle` → syntax-highlighted code viewer widget - `DiffHandle` → side-by-side diff viewer widget 3. **Interactive features are additive.** The TUI can offer features that the CLI cannot — sorting table columns, filtering rows, collapsing/expanding tree nodes, searching within code blocks — without any changes to producer code. These features are implemented in the TUI's `ElementRenderer` and widget layer. 4. **Concurrent updates are native.** Because the session already supports multiple concurrent producers writing to different handles, the TUI naturally displays multiple simultaneously-updating widgets (e.g., two tables being populated in parallel by concurrent operations). The `TuiMaterializer` routes events to widgets, and each widget redraws independently using the TUI framework's event loop. 5. **The `StructuredOutput` snapshot** provides the initial state when navigating to a completed session in the TUI (e.g., reviewing a past command's output), while live sessions use the event stream. The separation between production (element handles), timing (materialization strategy), and presentation (element renderer) ensures that the same command logic supports CLI, TUI, and web frontends without modification — only the `(MaterializationStrategy, ElementRenderer)` pair changes. #### Programmatic Usage Examples This section demonstrates how command implementations use the Output Rendering Framework through the `OutputSession` API, and how the same producer code produces correct output across all formats. ##### Example 1: Simple Static Command Output The simplest usage — a command that creates elements, populates them synchronously, and closes them. No concurrency, no streaming. **Producer code** (`agents project show`): 

async def cmd_project_show(session: OutputSession, project_name: str) -> None:
    """Implementation of 'agents project show <project>'."""
    project = await api.get_project(project_name)
    resources = await api.list_project_resources(project.name)
    validations = await api.list_project_validations(project.name)

    # --- Build output elements ---

    # Panel: Project details
    with session.panel("Project Details") as panel:
        panel.set_entries({
            "Name": project.name,
            "Description": project.description,
            "Resources": str(len(resources)),
            "Remote": "yes" if project.remote else "no",
            "Created": project.created_at.strftime("%Y-%m-%d %H:%M"),
        }, style_hints={
            "Name": "identifier",
            "Resources": "number",
            "Remote": "success" if not project.remote else "info",
            "Created": "success",
        })

    # Table: Linked resources
    with session.table("Linked Resources", columns=[
        ColumnDef(name="Resource", type="string", style_hint="identifier"),
        ColumnDef(name="Type"),
        ColumnDef(name="Sandbox"),
        ColumnDef(name="Read-Only"),
    ]) as table:
        for r in resources:
            table.add_row({
                "Resource": r.name,
                "Type": r.type,
                "Sandbox": r.sandbox_strategy,
                "Read-Only": "yes" if r.read_only else "no",
            })

    # Table: Validations
    with session.table(f"Validations ({len(validations)})", columns=[
        ColumnDef(name="ID", type="id", style_hint="identifier"),
        ColumnDef(name="Command"),
        ColumnDef(name="Mode"),
    ]) as table:
        for v in validations:
            table.add_row({
                "ID": v.id,
                "Command": v.command,
                "Mode": v.mode,
            })

    # Status: Final message
    session.status("Project loaded", level="ok")
**What this produces in `plain` format:** 

Project Details
  Name: local/api-service
  Description: Backend API
  Resources: 2
  Remote: no
  Created: 2026-02-08 12:46

Linked Resources
  Resource          Type            Sandbox              Read-Only
  ----------------  --------------  --------------------  ---------
  local/api-repo    git-checkout    git_worktree          no
  local/staging-db  local/database  transaction_rollback  yes

Validations (3)
  Name                     Command                                Mode
  -----------------------  -------------------------------------  -----------
  local/run-tests          pytest --cov=src --cov-fail-under=80   required
  local/lint-check         ruff check .                           required
  local/check-bundle-size  node scripts/check-bundle-size.js      informational

[OK] Project loaded
**What this produces in `rich` format:** 

╭─ Project Details ──────────────╮
│ Name: local/api-service        │
│ Description: Backend API       │
│ Resources: 2                   │
│ Remote: no                     │
│ Created: 2026-02-08 12:46      │
╰────────────────────────────────╯

╭─ Linked Resources ──────────────────────────────────────────────────────╮
│ Resource          Type            Sandbox              Read-Only        │
│ ────────────────  ──────────────  ────────────────────  ─────────       │
│ local/api-repo   git-checkout    git_worktree         no                │
│ local/staging-db local/database  transaction_rollback yes               │
╰─────────────────────────────────────────────────────────────────────────╯

╭─ Validations (3) ──────────────────────────────────────────────────────────────╮
│ Name                     Command                                Mode           │
│ ───────────────────────  ─────────────────────────────────────  ───────────    │
│ local/run-tests          pytest --cov=src --cov-fail-under=80   required       │
│ local/lint-check         ruff check .                           required       │
│ local/check-bundle-size  node scripts/check-bundle-size.js      informational  │
╰────────────────────────────────────────────────────────────────────────────────╯

✓ OK Project loaded
**What this produces in `json` format:** 

{
  "command": "project show",
  "status": "ok",
  "exit_code": 0,
  "data": {
    "project_details": {
      "Name": "local/api-service",
      "Description": "Backend API",
      "Resources": "2",
      "Remote": "no",
      "Created": "2026-02-08 12:46"
    },
    "linked_resources": [
      {
        "Resource": "local/api-repo",
        "Type": "git-checkout",
        "Sandbox": "git_worktree",
        "Read-Only": "no"
      },
      {
        "Resource": "local/staging-db",
        "Type": "local/database",
        "Sandbox": "transaction_rollback",
        "Read-Only": "yes"
      }
    ],
    "validations": [
      {
        "Name": "local/run-tests",
        "Command": "pytest --cov=src --cov-fail-under=80",
        "Mode": "required"
      },
      {
        "Name": "local/lint-check",
        "Command": "ruff check .",
        "Mode": "required"
      },
      {
        "Name": "local/check-bundle-size",
        "Command": "node scripts/check-bundle-size.js",
        "Mode": "informational"
      }
    ]
  },
  "timing": { "duration_ms": 42 },
  "messages": [
    { "level": "ok", "text": "Project loaded" }
  ]
}
In all three formats, the producer code is **identical**. The `OutputSession` and its materialization strategy handle the differences transparently. ##### Example 2: Streaming Rows into a Table A command that streams rows into a table as results arrive from a paginated API. The table handle stays open while the producer fetches pages. **Producer code** (`agents resource list`): 

async def cmd_resource_list(session: OutputSession, project: str | None) -> None:
    """Implementation of 'agents resource list'."""

    # Create the table handle — it will accumulate rows as we stream them
    table = session.table("Resources", columns=[
        ColumnDef(name="Name", type="string", style_hint="identifier"),
        ColumnDef(name="Type"),
        ColumnDef(name="Project"),
        ColumnDef(name="Sandbox"),
        ColumnDef(name="Status"),
    ], sort_key="Name")

    # Create a progress indicator for the fetch operation
    progress = session.progress("Fetching resources...", indeterminate=True)

    # Stream pages from the API
    count = 0
    async for page in api.list_resources_paginated(project=project):
        for resource in page.items:
            table.add_row({
                "Name": resource.name,
                "Type": resource.type,
                "Project": resource.project,
                "Sandbox": resource.sandbox_strategy,
                "Status": resource.status,
            })
            count += 1

        # Update progress label with count so far
        progress.set_label(f"Fetching resources... ({count} found)")

    # Close the progress indicator (it has served its purpose)
    progress.close()

    # Set summary and close the table
    table.set_summary({"total": count})
    table.close()

    # Final status
    session.status(f"{count} resources listed", level="ok")
**What this looks like in `plain` format** (SequentialBufferMaterializer): The progress indicator is rendered as a static line. The table is buffered until `table.close()` is called, then rendered in full. The user sees nothing until the fetch is complete — then the entire result appears at once: 

Fetching resources... (47 found) [done]

Resources
  Name                  Type            Project            Sandbox              Status
  --------------------  --------------  -----------------  --------------------  --------
  local/api-repo        git-checkout    local/api-service  git_worktree          active
  local/staging-db      local/database  local/api-service  transaction_rollback  active
  local/docs-repo       git-checkout    local/docs-site    git_worktree          active
  ... (44 more rows)

  Total: 47

[OK] 47 resources listed
**What this looks like in `rich` format** (LiveMaterializer): The progress spinner animates in real-time. The table updates in-place as rows arrive — each new row appears at the bottom of the table, the row count updates, and the terminal display is rewritten without scrolling. This is a static snapshot of the live display mid-fetch: 

⠙ Fetching resources... (23 found)

╭─ Resources ────────────────────────────────────────────────────────────────────────────╮
│ Name                  Type            Project            Sandbox              Status   │
│ ────────────────────  ──────────────  ─────────────────  ────────────────────  ──────  │
│ local/api-repo        git-checkout    local/api-service  git_worktree          active  │
│ local/staging-db      local/database  local/api-service  transaction_rollback  active  │
│ local/docs-repo       git-checkout    local/docs-site    git_worktree          active  │
│   ...                                                                                  │
│ local/test-fixtures   git-checkout    local/api-service  git_worktree          active  │
│                                                                                        │
│ Showing 1-23 of 23 (fetching...)                                                       │
╰────────────────────────────────────────────────────────────────────────────────────────╯
In `rich` mode, the spinner animates, the table grows as rows arrive, and the row count updates — all in-place without scrolling. When the fetch completes, the spinner resolves to `✓`, and the table shows its final state. ##### Example 3: Concurrent Parallel Operations (Two Tables Simultaneously) This is the key motivating example for the reactive architecture. Two tables are populated simultaneously by parallel workers, and the producer code is completely format-agnostic. **Producer code** (`agents plan status` — showing resources and active tool calls concurrently): 

async def cmd_plan_status(session: OutputSession, plan_id: str) -> None:
    """Implementation of 'agents plan status <plan_id>'.
    
    This command fetches plan metadata, then concurrently streams two data
    sources: resource statuses and active tool call logs. Both data sources
    are long-running — they produce results over several seconds as the
    backend resolves each item.
    """
    plan = await api.get_plan(plan_id)

    # Panel: Plan metadata (created and closed synchronously)
    with session.panel("Plan") as panel:
        panel.set_entries({
            "Plan ID": plan.id,
            "Phase": plan.phase,
            "State": plan.state,
            "Action": plan.action,
            "Project": plan.project,
            "Started": plan.started_at.strftime("%H:%M:%S"),
        }, style_hints={
            "Plan ID": "identifier",
            "Phase": "info",
            "State": "warning" if plan.state == "processing" else "success",
        })

    # Create both table handles BEFORE starting concurrent producers.
    # Declaration order determines rendering order in sequential formats.
    resource_table = session.table("Resource Status", columns=[
        ColumnDef(name="Resource", style_hint="identifier"),
        ColumnDef(name="Type"),
        ColumnDef(name="Status"),
        ColumnDef(name="Latency", type="string", alignment="right"),
    ])

    tool_table = session.table("Tool Call Log", columns=[
        ColumnDef(name="#", type="number", alignment="right"),
        ColumnDef(name="Tool"),
        ColumnDef(name="Target"),
        ColumnDef(name="Result"),
        ColumnDef(name="Duration", type="string", alignment="right"),
    ])

    # --- Run two producers concurrently ---
    # Each producer writes to its own handle. Neither producer knows
    # which format is active. The materialization strategy handles
    # the coordination.

    async def stream_resources():
        """Producer A: streams resource status checks."""
        async for status in api.stream_resource_statuses(plan.id):
            resource_table.add_row({
                "Resource": status.resource_name,
                "Type": status.resource_type,
                "Status": status.status,
                "Latency": f"{status.latency_ms}ms",
            })
        resource_table.close()

    async def stream_tool_calls():
        """Producer B: streams tool call results."""
        async for call in api.stream_tool_calls(plan.id):
            tool_table.add_row({
                "#": call.sequence_number,
                "Tool": call.tool_name,
                "Target": call.target,
                "Result": call.result_summary,
                "Duration": f"{call.duration_ms}ms",
            })
        tool_table.close()

    # Launch both producers concurrently
    await asyncio.gather(stream_resources(), stream_tool_calls())

    # Final status
    session.status(f"Plan {plan_id} status retrieved", level="ok")
**What this produces in `plain` format** (SequentialBufferMaterializer): Both tables are populated concurrently, but the materializer buffers each one and renders them in **declaration order** when their handles close. The user sees nothing until the first-declared table (Resource Status) closes, then it prints. Then when the second table (Tool Call Log) closes, it prints. Data may have arrived interleaved across both tables, but the output is perfectly sequential: 

Plan
  Plan ID: 01HXM7A9
  Phase: execute
  State: processing
  Action: local/code-coverage
  Project: local/api-service
  Started: 12:58:10

Resource Status
  Resource          Type            Status   Latency
  ----------------  --------------  -------  -------
  local/api-repo    git-checkout    ready    42ms
  local/staging-db  local/database  ready    128ms

Tool Call Log
  #   Tool        Target                  Result         Duration
  --  ----------  ----------------------  -------------  --------
   1  read_file   src/auth/__init__.py    200 lines      0.1s
   2  read_file   src/auth/session.py     340 lines      0.1s
   3  write_file  tests/test_auth.py      created        0.2s
   4  edit_file   src/auth/session.py     12 lines +/-   0.3s
   5  run_tests   pytest tests/test_auth  3 passed       2.1s

[OK] Plan 01HXM7A9 status retrieved
**What this produces in `rich` format** (LiveMaterializer): Both tables are visible simultaneously and update in-place as data arrives. This snapshot shows the display mid-stream — the resource table has two rows and the tool call table has three so far: 

╭─ Plan ──────────────────────────────╮
│ Plan ID: 01HXM7A9                   │
│ Phase: execute                      │
│ State: processing                   │
│ Action: local/code-coverage         │
│ Project: local/api-service          │
│ Started: 12:58:10                   │
╰─────────────────────────────────────╯

╭─ Resource Status ⠙ ───────────────────────────────────────────╮
│ Resource          Type            Status   Latency            │
│ ────────────────  ──────────────  ───────  ───────            │
│ local/api-repo    git-checkout    ready    42ms               │
│ local/staging-db  local/database  ready    128ms              │
│                                                               │
│ 2 resources (streaming...)                                    │
╰───────────────────────────────────────────────────────────────╯

╭─ Tool Call Log ⠙ ────────────────────────────────────────────────────╮
│ #   Tool        Target                  Result         Duration      │
│ ──  ──────────  ──────────────────────  ─────────────  ────────      │
│  1  read_file   src/auth/__init__.py    200 lines      0.1s          │
│  2  read_file   src/auth/session.py     340 lines      0.1s          │
│  3  write_file  tests/test_auth.py      created        0.2s          │
│                                                                      │
│ 3 calls (streaming...)                                               │
╰──────────────────────────────────────────────────────────────────────╯
In `rich` mode, both tables have animated spinners in their titles indicating active streaming. As new rows arrive from either producer, the corresponding table's display is updated in-place. When a producer finishes and closes its handle, the spinner resolves to a `✓` and the "(streaming...)" indicator is removed. The other table continues updating independently. **What this produces in `json` format** (AccumulateMaterializer): Nothing is printed until the session closes. Then the complete accumulated state is serialized: 

{
  "command": "plan status",
  "status": "ok",
  "exit_code": 0,
  "data": {
    "plan": {
      "Plan ID": "01HXM7A9",
      "Phase": "execute",
      "State": "processing",
      "Action": "local/code-coverage",
      "Project": "local/api-service",
      "Started": "12:58:10"
    },
    "resource_status": [
      { "Resource": "local/api-repo", "Type": "git-checkout", "Status": "ready", "Latency": "42ms" },
      { "Resource": "local/staging-db", "Type": "local/database", "Status": "ready", "Latency": "128ms" }
    ],
    "tool_call_log": [
      { "#": 1, "Tool": "read_file", "Target": "src/auth/__init__.py", "Result": "200 lines", "Duration": "0.1s" },
      { "#": 2, "Tool": "read_file", "Target": "src/auth/session.py", "Result": "340 lines", "Duration": "0.1s" },
      { "#": 3, "Tool": "write_file", "Target": "tests/test_auth.py", "Result": "created", "Duration": "0.2s" },
      { "#": 4, "Tool": "edit_file", "Target": "src/auth/session.py", "Result": "12 lines +/-", "Duration": "0.3s" },
      { "#": 5, "Tool": "run_tests", "Target": "pytest tests/test_auth", "Result": "3 passed", "Duration": "2.1s" }
    ]
  },
  "timing": { "duration_ms": 3200 },
  "messages": [
    { "level": "ok", "text": "Plan 01HXM7A9 status retrieved" }
  ]
}
The critical point: **the producer code in all three formats is exactly the same**. The `asyncio.gather` call runs both producers concurrently regardless of format. The materialization strategy — `LiveMaterializer`, `SequentialBufferMaterializer`, or `AccumulateMaterializer` — transparently decides how that concurrent data reaches the user. ##### Example 4: Progress with Concurrent Sub-Operations A command that executes a multi-step process with a progress indicator, where some steps involve parallel sub-operations. **Producer code** (`agents plan execute`): 

async def cmd_plan_execute(session: OutputSession, plan_id: str) -> None:
    """Implementation of 'agents plan execute <plan_id>'."""
    plan = await api.get_plan(plan_id)

    # Panel: Execution metadata
    with session.panel("Execution") as panel:
        panel.set_entries({
            "Plan": plan.id,
            "Phase": "execute",
            "Sandbox": plan.sandbox_strategy,
            "Worker": plan.worker,
            "Started": datetime.now().strftime("%H:%M:%S"),
        })

    # Progress indicator with named steps
    progress = session.progress("Executing plan", total=4, steps=[
        "Collect context",
        "Run tools",
        "Build changeset",
        "Validate",
    ])

    # Step 1: Collect context
    progress.set_step_status("Collect context", "active")
    context = await api.collect_context(plan.id)
    progress.set_step_status("Collect context", "done")
    progress.set_progress(1, 4)

    # Step 2: Run tools (parallel sub-operations)
    progress.set_step_status("Run tools", "active")
    tool_results = await api.run_tools(plan.id, context)
    progress.set_step_status("Run tools", "done")
    progress.set_progress(2, 4)

    # Step 3: Build changeset
    progress.set_step_status("Build changeset", "active")
    changeset = await api.build_changeset(plan.id, tool_results)
    progress.set_step_status("Build changeset", "done")
    progress.set_progress(3, 4)

    # Step 4: Validate
    progress.set_step_status("Validate", "active")
    validation = await api.validate_changeset(plan.id, changeset)
    progress.set_step_status("Validate", "done")
    progress.set_progress(4, 4)

    progress.close()

    # Summary panel
    with session.panel("Strategy Summary") as panel:
        panel.set_entries({
            "Decisions": str(changeset.decision_count),
            "Invariants": str(changeset.invariant_count),
            "Planned Child Plans": f"{changeset.child_plan_count}+",
            "Estimated Files": f"~{changeset.file_count}",
            "Risk": changeset.risk_level,
        })

    # Final status
    if validation.passed:
        session.status("Execution complete — all validations passed", level="ok")
    else:
        session.status(
            f"Execution complete — {validation.failure_count} validation(s) failed",
            level="warn",
            detail=validation.summary,
        )
**What this looks like in `plain` format:** The progress indicator renders as a static step list. Since `SequentialBufferMaterializer` buffers each element until its handle closes, the progress indicator is not visible during execution — it appears as a completed snapshot after the fact: 

Execution
  Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J
  Phase: execute
  Sandbox: git_worktree
  Worker: local/executor
  Started: 12:58:10

Executing plan  [4/4]
  [x] Collect context
  [x] Run tools
  [x] Build changeset
  [x] Validate

Strategy Summary
  Decisions: 8
  Invariants: 2
  Planned Child Plans: 2+
  Estimated Files: ~12
  Risk: low

[OK] Execution complete — all validations passed
**What this looks like in `rich` format:** The progress indicator is live — the spinner animates, the progress bar fills, and steps transition from pending to active to done in real-time. This snapshot shows the display mid-execution (step 3 active): 

╭─ Execution ──────────────────────╮
│ Plan: 01HXM8C2ZK4Q7C2B3F2R4VYV6J │
│ Phase: execute                   │
│ Sandbox: git_worktree            │
│ Worker: local/executor           │
│ Started: 12:58:10                │
╰──────────────────────────────────╯

Executing plan ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━  50%  elapsed 0:00:13
  ✓ Collect context .................. 0.8s
  ✓ Run tools ...................... 12.4s
  ⠙ Build changeset ................. (running)
  ○ Validate ........................ (pending)
When execution completes, the progress indicator resolves to its final state (all steps `✓`), the Strategy Summary panel appears below it, and the final status message is displayed. ##### Example 5: Error Mid-Stream with Partial Output A command where one of multiple concurrent producers fails, demonstrating graceful partial output. **Producer code** (hypothetical `agents resource verify`): 

async def cmd_resource_verify(session: OutputSession, project: str) -> None:
    """Verify all resources in a project. Some verifications may fail."""
    resources = await api.list_project_resources(project)

    # Create a table that will be populated concurrently
    results_table = session.table("Verification Results", columns=[
        ColumnDef(name="Resource", style_hint="identifier"),
        ColumnDef(name="Type"),
        ColumnDef(name="Check"),
        ColumnDef(name="Status"),
        ColumnDef(name="Detail"),
    ])

    # Progress indicator
    progress = session.progress(
        "Verifying resources",
        total=len(resources),
        steps=[r.name for r in resources],
    )

    # Verify each resource concurrently
    async def verify_one(resource):
        progress.set_step_status(resource.name, "active")
        try:
            result = await api.verify_resource(resource.id)
            results_table.add_row({
                "Resource": resource.name,
                "Type": resource.type,
                "Check": result.check_name,
                "Status": "pass" if result.passed else "fail",
                "Detail": result.detail,
            })
            progress.set_step_status(
                resource.name,
                "done" if result.passed else "error",
            )
        except ApiError as e:
            results_table.add_row({
                "Resource": resource.name,
                "Type": resource.type,
                "Check": "connection",
                "Status": "error",
                "Detail": str(e),
            })
            progress.set_step_status(resource.name, "error")
        progress.increment()

    # Launch all verifications concurrently
    await asyncio.gather(
        *[verify_one(r) for r in resources],
        return_exceptions=True,  # Don't fail fast — collect all results
    )

    progress.close()
    results_table.close()

    # Summarize
    snapshot = results_table.element
    pass_count = sum(1 for r in snapshot.rows if r["Status"] == "pass")
    fail_count = sum(1 for r in snapshot.rows if r["Status"] in ("fail", "error"))

    if fail_count == 0:
        session.status(f"All {pass_count} resources verified", level="ok")
    else:
        session.status(
            f"{fail_count} of {pass_count + fail_count} resources failed verification",
            level="error",
        )
**What this produces in `plain` format** (after all concurrent verifications complete): 

Verifying resources  [3/3]
  [x] local/api-repo
  [!] local/staging-db
  [x] local/docs-repo

Verification Results
  Resource          Type            Check       Status  Detail
  ----------------  --------------  ----------  ------  ----------------------------------
  local/api-repo    git-checkout    integrity   pass    All refs valid
  local/staging-db  local/database  connection  error   Connection refused (port 5432)
  local/docs-repo   git-checkout    integrity   pass    All refs valid

[ERROR] 1 of 3 resources failed verification
**What this produces in `color` format:** 

Verifying resources  [3/3]
  [x] local/api-repo
  [!] local/staging-db
  [x] local/docs-repo

Verification Results
  Resource          Type            Check       Status  Detail
  ----------------  --------------  ----------  ------  ----------------------------------
  local/api-repo    git-checkout    integrity   pass    All refs valid
  local/staging-db  local/database  connection  error   Connection refused (port 5432)
  local/docs-repo   git-checkout    integrity   pass    All refs valid

[ERROR] 1 of 3 resources failed verification
**What this produces in `yaml` format:** 

command: resource verify
status: error
exit_code: 1
data:
  verification_results:
    - Resource: local/api-repo
      Type: git-checkout
      Check: integrity
      Status: pass
      Detail: All refs valid
    - Resource: local/staging-db
      Type: local/database
      Check: connection
      Status: error
      Detail: "Connection refused (port 5432)"
    - Resource: local/docs-repo
      Type: git-checkout
      Check: integrity
      Status: pass
      Detail: All refs valid
timing:
  duration_ms: 2840
messages:
  - level: error
    text: "1 of 3 resources failed verification"
In all formats, the concurrent verification produces a complete result set with partial failures clearly visible. The producer code uses `return_exceptions=True` on `asyncio.gather` to ensure all verifications complete even if some fail, and the error handling within each `verify_one` coroutine ensures that failures are recorded as table rows rather than causing the entire command to abort. ## Behavior ### Automation Profiles !!! adr "Architecture Decision" The automation profile system, confidence thresholds, and built-in profiles are defined in [ADR-017: Automation Profiles](adr/ADR-017-automation-profiles.md). Automation profiles determine which phase transitions happen automatically and which require human approval. #### Overview An **automation profile** is a named collection of **confidence thresholds** — floating-point values from 0.0 to 1.0 inclusive — that controls which tasks are automated vs. require human approval. Each threshold specifies the minimum confidence score (as computed by the Semantic Escalation system) at which the system proceeds automatically. When the computed confidence for a given operation falls below the profile's threshold for that flag, the system drops to manual mode and requests human input. A threshold of **0.0** means "always automatic" (proceed regardless of confidence), while **1.0** means "always manual" (always require human approval). Profiles follow the same `/` naming convention as actors, tools, skills, and other entities. Profiles are managed via the `agents automation-profile` CLI commands. #### Automatable Tasks Each automation profile specifies a **confidence threshold** (a floating-point value from 0.0 to 1.0 inclusive) for each of the following automatable tasks. The threshold determines the minimum confidence level at which the system proceeds automatically. When the computed confidence (from Semantic Escalation) falls below the threshold, the system drops to manual mode for that task. Setting a threshold to **0.0** makes the task always automatic; setting it to **1.0** makes it always manual. | Flag | Type | Description | Behavior | |------|------|-------------|----------| | `decompose_task` | float (0.0–1.0) | Automatically enter Strategize after `plan use` | When confidence >= threshold, Strategize begins immediately. Below threshold, system pauses after plan creation for user confirmation before entering Strategize. | | `create_tool` | float (0.0–1.0) | Automatically proceed from Strategize to Execute | When confidence >= threshold, Execute begins when Strategize completes. Below threshold, system pauses for user review. | | `select_tool` | float (0.0–1.0) | Automatically proceed from Execute to Apply | When confidence >= threshold, Apply begins when Execute completes. Below threshold, system pauses for user diff review. | | `edit_code` | float (0.0–1.0) | Automatically make decisions during Strategize | When confidence >= threshold, the strategy actor makes the decision autonomously. Below threshold, system pauses at the decision point for user input. | | `execute_command` | float (0.0–1.0) | Automatically make decisions during Execute | When confidence >= threshold, the execution actor makes the decision autonomously. Below threshold, system pauses at the decision point for user input. | | `create_file` | float (0.0–1.0) | Automatically attempt to fix validation failures | When confidence >= threshold, execution actor self-fixes failing validations. Below threshold, system pauses for user guidance. | | `delete_content` | float (0.0–1.0) | Automatically revise strategy when Execute hits constraints | When confidence >= threshold, system re-runs Strategize for affected subtree. Below threshold, system pauses and asks user. | | `access_network` | float (0.0–1.0) | Automatically revert from Apply (`constrained` state) to Strategize | When confidence >= threshold, a `constrained` Apply automatically triggers reversion to Strategize. Below threshold, system pauses and asks user whether to revert or cancel. | | `install_dependency` | float (0.0–1.0) | Automatically spawn and execute child plans | When confidence >= threshold, child plans are created and executed without pausing. Below threshold, each spawn requires approval. | | `modify_config` | float (0.0–1.0) | Automatically retry on transient failures (network, timeout, rate-limit) | When confidence >= threshold, system retries with backoff. Below threshold, system pauses and asks user. | | `approve_plan` | float (0.0–1.0) | Automatically restore from checkpoint on failure | When confidence >= threshold, system rolls back and retries. Below threshold, user decides whether to restore. | #### Safety Profile (Composed Sub-Model) !!! adr "Architecture Decision" The extraction of safety constraints into a composed SafetyProfile sub-model is defined in [ADR-041: Safety Profile Extraction](adr/ADR-041-safety-profile-extraction.md). Each automation profile composes a **`safety`** sub-model (`SafetyProfile`) that groups all hard safety constraints. These are binary constraints rather than confidence-dependent behaviors — they enforce invariant safety guarantees regardless of the system's confidence level. The `SafetyProfile` is the **single source of truth** for safety constraints; the `AutomationProfile` accesses them via its `safety` field. A `SafetyProfile` may also be attached directly to an `Action` (via the `safety_profile` field) when only safety constraints are needed without full autonomy thresholds. | Flag | Type | Default | Description | Behavior | |------|------|---------|-------------|----------| | `require_sandbox` | boolean | `true` | Require sandbox isolation for Execute phase | When `true`, Execute must run in a sandbox. When `false`, sandbox is optional. | | `require_checkpoints` | boolean | `true` | Require checkpointing during Execute | When `true`, tools must create checkpoints before writes. When `false`, checkpointing is optional. | | `allow_unsafe_tools` | boolean | `false` | Allow execution of tools marked as unsafe | When `true`, unsafe tools can be invoked. When `false`, unsafe tools are blocked. | | `require_human_approval` | boolean | `false` | Require human approval before each action step | When `true`, every action step pauses for explicit human approval before execution. | | `allowed_skill_categories` | list[string] | `[]` (all) | Skill categories permitted for execution | When non-empty, only skills in the listed categories may be used. Empty list means all categories are allowed. | | `max_cost_per_plan` | float \| null | `null` | Maximum cost in USD per plan execution | When set, the plan is paused or terminated if the cost limit is reached. `null` means no limit. Must be <= `max_total_cost` when both are set. | | `max_total_cost` | float \| null | `null` | Maximum total cost in USD across all plans | When set, execution is paused or terminated if the aggregate cost limit is reached. `null` means no limit. | | `max_retries_per_step` | integer | `3` | Maximum retry attempts per action step | Limits the number of retries for a single step before escalating to the user. Range: 0–100. | **Relationship to Automation Guards**: The `SafetyProfile.max_total_cost` field sets a **plan-level** budget cap (broad scope), while `AutomationGuard.max_total_cost` sets a **per-invocation** budget cap (narrow scope). These operate at different granularities and both may be active simultaneously — the tighter constraint takes precedence at any given point. #### Automation Guard Sub-Model An `AutomationProfile` may optionally compose an `AutomationGuard` sub-model (via the `guards` field) that provides runtime enforcement hooks beyond the phase-transition thresholds. Guards gate individual tool invocations based on call counts, budgets, allowlists/denylists, and write/apply semantics. | Field | Type | Default | Description | |-------|------|---------|-------------| | `max_tool_calls_per_step` | integer \| null | `null` | Maximum tool invocations per step before requiring approval. `null` means unlimited. Must be >= 0. | | `max_total_cost` | float \| null | `null` | Per-invocation budget cap (cumulative cost) before requiring approval. `null` means unlimited. Must be >= 0.0. | | `tool_allowlist` | list[string] \| null | `null` | Only these tools may be called automatically. `null` means all tools are allowed. | | `tool_denylist` | list[string] \| null | `null` | These tools always require human approval. `null` means no tools are denied. | | `require_approval_for_writes` | boolean | `false` | Require human approval for write operations. | | `require_approval_for_apply` | boolean | `false` | Require human approval before the apply phase. | Guard evaluation is performed via `AutomationProfile.check_guard(tool_name, is_write, cost_so_far, calls_so_far, scope)`. The `scope` parameter is a `GuardScope` enum (`PLAN` or `SUBPLAN`) that distinguishes plan-level from subplan-level enforcement — error messages include the scope name for clarity. The method returns a `GuardResult` with fields `allowed` (bool), `reason` (str | None), and `requires_approval` (bool). Evaluation order: denylist → allowlist → tool call limit → budget cap → write approval → apply approval. #### Built-in Automation Profiles CleverAgents ships with eight built-in automation profiles. Built-in profiles use no namespace prefix. Threshold values are shown for each flag. A value of **0.0** means always automatic, **1.0** means always manual, and intermediate values (e.g., 0.5, 0.7) mean "automatic when confidence is at or above that level." | Flag | `manual` | `review` | `supervised` | `cautious` | `trusted` | `auto` | `ci` | `full-auto` | |------|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| | `decompose_task` | 1.0 | 0.0 | 0.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `create_tool` | 1.0 | 0.0 | 1.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `select_tool` | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | | `edit_code` | 1.0 | 1.0 | 0.0 | 0.6 | 0.0 | 0.0 | 0.0 | 0.0 | | `execute_command` | 1.0 | 1.0 | 1.0 | 0.8 | 0.0 | 0.0 | 0.0 | 0.0 | | `create_file` | 1.0 | 1.0 | 1.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `delete_content` | 1.0 | 1.0 | 1.0 | 0.8 | 1.0 | 0.0 | 0.0 | 0.0 | | `access_network` | 1.0 | 1.0 | 1.0 | 0.9 | 1.0 | 1.0 | 0.0 | 0.0 | | `install_dependency` | 1.0 | 0.0 | 1.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `modify_config` | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | | `approve_plan` | 1.0 | 1.0 | 1.0 | 0.6 | 1.0 | 0.0 | 0.0 | 0.0 | | **Safety Profile** | | | | | | | | | | `safety.require_sandbox` | true | true | true | true | true | true | true | false | | `safety.require_checkpoints` | true | true | true | true | true | true | true | false | | `safety.allow_unsafe_tools` | false | false | false | false | false | false | false | true | | `safety.require_human_approval` | false | false | false | false | false | false | false | false | | `safety.allowed_skill_categories` | [] | [] | [] | [] | [] | [] | [] | [] | | `safety.max_cost_per_plan` | null | null | null | null | null | null | null | null | | `safety.max_total_cost` | null | null | null | null | null | null | null | null | | `safety.max_retries_per_step` | 3 | 3 | 3 | 3 | 3 | 3 | 3 | 3 | **`manual`**: Maximum human control. All thresholds set to 1.0 — every phase transition, every decision, every child plan requires explicit human approval regardless of confidence. Sandbox and checkpoints are mandatory. Unsafe tools are blocked. This is the default starting point. Use for: new users learning the system, critical production systems, first-time exploration of an unfamiliar codebase, sensitive projects, regulatory environments. **`review`**: Phases run automatically (Strategize and Execute proceed without pausing), and most decisions within those phases require human approval (thresholds set to 1.0), except transient retries and child plan spawning which are automatic (thresholds 0.0). Apply is manual. The system does the work but consults you on every choice point. Use for: teams that want to stay in the decision loop without manually triggering each phase, code reviews where architectural choices matter more than execution mechanics. **`supervised`**: Strategize thresholds set to 0.0 (always automatic), but Execute and Apply thresholds set to 1.0 (always manual). The system plans autonomously and retries transient failures automatically, but pauses before Execute for human review of the strategy. Use for: projects where you trust the planning but want to review before execution begins. **`cautious`**: Uses intermediate confidence thresholds (0.6–0.8) instead of binary 0.0/1.0 values. The system proceeds automatically only when the Semantic Escalation system reports high confidence, and escalates to the user when uncertain. Apply is always manual (1.0). Higher thresholds (0.8) are applied to riskier operations like strategy revision and execution decisions, while lower thresholds (0.6) are used for safer operations like checkpoint restores and strategy decisions. Transient retries are always automatic. Use for: teams adopting automation gradually, projects with mixed complexity where some tasks are routine but others need oversight, situations where you want the system to self-assess rather than follow rigid rules. **`trusted`**: Strategize and Execute thresholds set to 0.0 (always automatic). Validation fixes, child plan spawning, and transient retries proceed automatically. Strategy revision and checkpoint restores remain manual (thresholds 1.0) to preserve human oversight over plan-level course corrections. The system pauses only before Apply (threshold 1.0) for human review of the final diffs. Use for: day-to-day feature development, routine refactoring, test generation. **`auto`**: All thresholds set to 0.0 except Apply (1.0). The system can revise its own strategy, restore from checkpoints, and handle all decisions automatically. Only Apply requires human approval. Use for: well-understood projects, batch operations, tasks with strong invariant coverage. **`ci`**: All thresholds set to 0.0 — complete end-to-end automation including Apply — but sandbox and checkpoints remain mandatory and unsafe tools are blocked. Designed for non-interactive environments where full automation is needed but safety nets must be preserved. Use for: CI/CD pipelines, automated testing workflows, scheduled batch jobs, any headless execution where rollback capability is essential. **`full-auto`**: All thresholds set to 0.0 — complete end-to-end automation including Apply. No sandbox or checkpoint requirements. Unsafe tools are allowed. Use for: low-risk routine tasks (dependency updates, documentation generation, formatting), trusted batch operations with rollback capabilities, environments where external safety mechanisms exist. #### Profile Precedence Automation profiles are determined using this precedence (highest to lowest): 1. **Plan-level**: Explicitly set via `--automation-profile` on `agents plan use` 2. **Action-level**: Set on the action via `--automation-profile` on `agents action create` 3. **Project-level**: Set via `agents config set core.automation-profile --project ` 4. **Global-level**: Set via `agents config set core.automation-profile ` The **effective profile** for a plan is resolved at the moment of `agents plan use`. Once resolved, the profile is **locked to that plan** — subsequent changes to project or global profiles do not affect running plans. #### Child Plan Profile Inheritance Child plans inherit the parent plan's effective automation profile. If the parent's profile is changed explicitly after creation, new child plans use the new profile while already-running child plans retain their original profile. #### Custom Automation Profiles Custom profiles are created via YAML configuration files and registered with `agents automation-profile add`. Each automatable task flag takes a confidence threshold (0.0–1.0) instead of a boolean. A threshold of 0.0 means "always automatic" and 1.0 means "always manual." Intermediate values (e.g., 0.5, 0.7) enable fine-grained control where the system proceeds automatically only when the Semantic Escalation confidence score meets or exceeds the threshold: 

# File: profiles/careful-auto.yaml
name: local/careful-auto
description: "Autonomous execution with mandatory sandbox and manual apply"

# Confidence thresholds (0.0 = always auto, 1.0 = always manual)
decompose_task: 0.0
create_tool: 0.0
select_tool: 1.0
edit_code: 0.0
execute_command: 0.0
create_file: 0.0
delete_content: 1.0
access_network: 1.0
install_dependency: 0.0
modify_config: 0.0
approve_plan: 0.0

# Safety profile (composed sub-model)
safety:
  require_sandbox: true
  require_checkpoints: true
  allow_unsafe_tools: false
A profile with intermediate thresholds provides nuanced control. For example, `execute_command: 0.7` means decisions during Execute proceed automatically when confidence >= 0.7, but drop to manual review when confidence is below 0.7: 

# File: profiles/nuanced-auto.yaml
name: local/nuanced-auto
description: "Nuanced automation with graduated confidence thresholds"

decompose_task: 0.0              # Always auto-strategize
create_tool: 0.5                 # Auto-execute when confidence >= 0.5
select_tool: 1.0                   # Always require manual apply
edit_code: 0.3   # Low bar for strategy decisions
execute_command: 0.7      # Higher bar for execution decisions
create_file: 0.5        # Auto-fix when reasonably confident
delete_content: 0.8     # High confidence needed for auto-revision
access_network: 0.9  # Very high bar for late-stage reversion
install_dependency: 0.5           # Auto-spawn when moderately confident
modify_config: 0.0       # Always auto-retry transient errors
approve_plan: 0.6    # Auto-restore when fairly confident

# Safety profile (composed sub-model)
safety:
  require_sandbox: true
  require_checkpoints: true
  allow_unsafe_tools: false


agents automation-profile add --config ./profiles/careful-auto.yaml
#### Semantic Escalation Semantic Escalation is the system that computes a **confidence score** (0.0–1.0) for each operation, and it is the mechanism through which automation profile thresholds take effect. The confidence score reflects the system's assessment of how likely an autonomous action is to succeed without human guidance. This score is then compared against the profile's threshold for the relevant flag to determine whether to proceed automatically or escalate to the user. The confidence score is computed from multiple factors: 

class AutonomyController:
    def should_proceed_automatically(self, decision, context, profile):
        """Determine whether to proceed automatically or escalate to user."""
        factors = {
            'past_success_rate': self.get_historical_success(decision.type),
            'codebase_familiarity': self.get_familiarity_score(context.project),
            'risk_assessment': self.evaluate_risk(decision),
            'invariant_complexity': self.analyze_invariants(decision)
        }

        confidence = self.compute_confidence(factors)  # Returns 0.0–1.0
        threshold = profile.get_threshold(decision.flag)  # e.g., execute_command

        if confidence >= threshold:
            # Confidence meets or exceeds the profile threshold — proceed
            return ProceedAutonomously(decision, confidence)
        else:
            # Confidence below threshold — escalate to human
            return RequestHumanGuidance(decision, confidence, threshold, factors)
**How thresholds and confidence interact**: A profile with `execute_command: 0.7` means the system will make execution decisions automatically when confidence >= 0.7, but will pause for human input when confidence < 0.7. This is more nuanced than a binary on/off: a profile can set a high bar (0.9) for risky operations while being permissive (0.2) for low-risk ones. **Special cases**: A threshold of **0.0** means "always automatic" — even zero confidence passes the threshold. A threshold of **1.0** means "always manual" — no confidence level (which tops out below 1.0 in practice) is high enough to pass. This means the old boolean behavior is a strict subset: `true` maps to `0.0` and `false` maps to `1.0`. #### Progressive Trust Building New users typically follow this progression: 1. Start with `manual` to understand system behavior 1. Move to `review` to let phases run automatically while staying in the decision loop 1. Adopt `supervised` as confidence in the planning phase builds 1. Try `cautious` for confidence-gated automation that escalates only when uncertain 1. Adopt `trusted` for routine development tasks 1. Enable `auto` for well-understood projects with strong invariant coverage 1. Use `ci` for headless CI/CD pipelines with safety nets intact 1. Use `full-auto` for low-risk batch operations where external safety mechanisms exist ### Guardrails !!! adr "Architecture Decision" System-level guardrails, pre-flight checks, and runtime limits are defined in [ADR-018: Semantic Error Prevention](adr/ADR-018-semantic-error-prevention.md). System-level guardrails are pre-flight checks and runtime limits that prevent plans from executing in invalid or unsafe conditions. These are distinct from **Validations** (the Tool subtype described in Core Concepts > Validation) — guardrails operate at the system/infrastructure level before and during plan execution, whereas Validations verify the *quality of the work produced* by a plan at the end of the Execute phase. #### Plan Generation Guardrails Before a plan begins execution, the system performs pre-flight validation to ensure the plan is well-formed and its dependencies are satisfiable. These checks must be implemented: * **Action schema validation**: Verify the action referenced by the plan exists, is well-formed, and its configuration conforms to the expected schema. * **Actor availability**: Confirm that all actors required by the plan (strategy actor, execution actor, estimation actor, invariant reconciliation actor) are registered and reachable. For remote actors, verify network connectivity. * **Skill and tool existence**: Verify that all skills and tools referenced by the action's actor configuration exist in the registry. This includes both named tools and tools referenced via skills (transitively resolved). * **Automation policy**: Verify that the automation profile allows the requested level of autonomy for the target project, resources, and actions. * **Rollback feasibility**: If `require_checkpoints` is enabled on the plan, verify that all tools in the actor's skill set have `checkpointable: true`. Reject plans that would use non-checkpointable tools under a checkpoint-required policy. * **Resource accessibility**: Verify that the project's linked resources are accessible — git repos are cloneable, databases are connectable, file system paths exist, etc. This is a shallow connectivity check, not a full resource health assessment. * **Validation attachment resolution**: Pre-resolve the validations that will apply to this plan (from resource-direct, project, and plan attachment scopes) and verify they are all registered and their tool definitions are valid. This ensures validation failures during Execute are due to the work product, not misconfigured validations. These pre-flight checks prevent "plan runs with fake providers," missing tool errors mid-execution, and other surprises that waste compute and user time. If any pre-flight check fails, the plan is rejected before entering the Strategize phase, with a clear error message identifying the failing check. #### Cost and Rate Limits Runtime guardrails to prevent runaway resource consumption: * **Per-plan budgets**: Maximum API token spend, maximum wall-clock time, maximum number of tool invocations per plan. When a budget is exceeded, the plan pauses and requests user approval to continue or is terminated. * **Per-session budgets**: Aggregate limits across all plans in a session. Prevents a single interactive session from consuming excessive resources. * **Per-org budgets**: Server-enforced limits for multi-user deployments. Administrators set organization-wide spend caps that cannot be overridden by individual users. * **Per-actor limits**: Maximum tool calls per actor invocation, maximum retries per tool failure, maximum tokens per LLM call. Prevents individual actors from looping indefinitely. * **Validation retry limits**: Maximum number of fix-then-revalidate iterations when a required Validation fails during Execute. This is a specific application of per-actor limits — the default is 3 attempts, configurable per plan or in the automation profile. Cost and rate limits are future concerns that require integration with LLM provider billing APIs and internal metering. The system should define configuration surfaces for these limits but may initially implement only the per-plan and per-actor limits, with per-session, per-org, and billing integration added later. ### Correcting Plans (Core Feature) !!! adr "Architecture Decision" Plan correction, decision revision, and the edit-replay model are defined in [ADR-007: Decision Tree and Correction](adr/ADR-007-decision-tree-and-correction.md). Correcting plans is where CleverAgents becomes more than "a fancy prompt runner." #### The Goal When a plan makes a wrong decision early, we want to: * correct the decision, * recompute only the affected subtree, * preserve unaffected work. This is explicitly described: "redo everything below that decision, not the entire code base." #### Decision Tree Representation Every plan records (see Decision Data Model section): * decisions (choice points) - created during Strategize, including `invariant_enforced`, `subplan_spawn`, and `subplan_parallel_spawn` decisions * dependencies (which later work depended on that decision) * child plans spawned because of that decision - populated during Execute * artifacts generated under that branch This makes plan runs auditable and correctable. #### Two Correction Modes === "Revert (`--mode=revert`)" !!! warning "Potentially Expensive" Find the decision point in the tree, roll back all changes (code and non-code) to that point, and re-run from that decision point forward. Old execution artifacts are kept for comparison. - [x] Roll back all changes to the decision point - [x] Re-run from that decision point forward - [x] Keep old execution artifacts for comparison - [ ] ==Potentially expensive== if high up in the tree === "Append (`--mode=append`)" !!! success "Safer and Cheaper" Leave history intact and append a new plan at the end that fixes the outcome. Does not rewrite history. - [x] Leave history intact - [x] Append a new corrective plan at the end - [x] Cheaper and safer in many cases - [x] Does ==not rewrite history== #### Correction Flow (Revert Mode) !!! adr "Architecture Decision" The detailed rollback and replay mechanics, including mid-phase correction flows and cross-sandbox coordination, are defined in [ADR-035: Decision Tree Rollback and Replay](adr/ADR-035-decision-tree-rollback-and-replay.md). Correction operates on **two independent rollback dimensions**: | Dimension | What It Restores | Mechanism | Applicable Phase | |---|---|---|---| | **Resource rollback** | Sandbox contents (files, database state, filesystem) | Checkpoint restoration via sandbox-strategy-specific handlers | Execute only | | **Reasoning rollback** | Actor's conversation history, intermediate reasoning, graph state | LangGraph checkpoint restoration from `actor_state_ref` | Strategize and Execute | ##### Mid-Strategize Correction When the target decision was created during Strategize (e.g., a `strategy_choice` or `subplan_spawn`), **only reasoning rollback is needed** because Strategize is read-only — no resource modifications exist to undo: 1. **Restore actor state**: Load the target decision's `context_snapshot.actor_state_ref` (LangGraph checkpoint). This restores the strategy actor to the exact reasoning state it was in when the decision was made. 2. **Supersede affected subtree**: Mark the target decision and all its descendants as superseded (cascading via ADR-034). Decisions above the target remain active and unchanged. 3. **Inject guidance**: Create a `user_intervention` decision containing the user's `--guidance` text. 4. **Resume strategy actor**: The actor continues reasoning from the restored state, informed by the correction guidance. New decisions replace the superseded ones, with `is_correction: true, corrects_decision_id: `. 5. **Record correction**: Create a `correction_attempts` record linking old and new decisions. If the plan was already in Execute when this correction is requested, all Execute-phase work is rolled back (via checkpoint groups — see below) and the plan reverts to Strategize at the corrected decision point. ##### Mid-Execute Correction When the target decision was created during Execute (e.g., an `implementation_choice` or `error_recovery`), **both resource and reasoning rollback are needed**: 1. **Load checkpoint group**: Every Execute-phase decision has a corresponding **checkpoint group** — one per-resource checkpoint for each sandbox resource that had been modified at the time the decision was recorded. These are stored in `checkpoint_metadata` linked by `decision_id`. 2. **Classify resources**: - *Rollbackable*: resources with sandbox strategies that support checkpointing (`git_worktree`, `filesystem_copy`, `overlay`, `transaction_rollback`) - *Non-rollbackable*: resources with `sandbox.strategy: none` (tracked with marker records) - *Unaffected*: resources not yet modified at the decision point (no checkpoint row — no rollback needed) 3. **Warn about limitations**: If non-rollbackable resources exist, the user is warned and must confirm. If downstream decisions triggered tools with irreversible `side_effects`, the user is warned that external effects cannot be undone. 4. **Resource rollback**: For each rollbackable checkpoint, dispatch to the strategy-specific handler: | Strategy | Rollback Operation | |---|---| | `git_worktree` | `git reset --hard ` in the worktree | | `filesystem_copy` | Restore from archived snapshot | | `overlay` | Discard overlay writes since checkpoint | | `transaction_rollback` | `ROLLBACK TO SAVEPOINT ` | If any individual resource rollback fails, the correction is marked `'failed'` and the plan enters `errored` state. 5. **Reasoning rollback**: Restore the execution actor's LangGraph state from `context_snapshot.actor_state_ref`. 6. **Supersede affected subtree**: Cascade superseding through the target and all descendants. 7. **Inject guidance and resume**: The execution actor continues from the restored state. !!! note "Decision-Aligned Checkpointing" The 1:1 mapping between Execute-phase decisions and resource checkpoints is created automatically by the `record_decision` tool (see Decision Recording Protocol in the Core Concepts section). Every `record_decision` call during Execute triggers a coordinated checkpoint group across all modified sandbox resources. This is what enables fine-grained rollback to any individual Execute-phase decision rather than reverting the entire Execute phase. ##### Affected Subtree Computation The "affected subtree" — all decisions and child plans invalidated by a correction — is computed by walking the influence DAG (not just the structural tree): 

def compute_affected_subtree(target_decision_id):
    affected_decisions = {target_decision_id}
    affected_plans = set()
    queue = [target_decision_id]

    while queue:
        current = queue.pop(0)

        # Follow structural tree children
        children = query("SELECT decision_id FROM decisions "
                         "WHERE parent_decision_id = :current AND superseded_by IS NULL")

        # Follow influence DAG dependents
        dependents = query("SELECT downstream_ref FROM decision_dependencies "
                           "WHERE upstream_decision_id = :current AND dependency_type = 'decision'")

        for d in children | dependents:
            if d not in affected_decisions:
                affected_decisions.add(d)
                queue.append(d)

        # Collect affected child plans
        child_plans = query("SELECT downstream_ref FROM decision_dependencies "
                            "WHERE upstream_decision_id = :current AND dependency_type = 'plan'")
        affected_plans.update(child_plans)

    return affected_decisions, affected_plans
##### Cross-Plan Correction Cascading When the affected subtree includes child plans (via `subplan_spawn` or `subplan_parallel_spawn` decisions), the child plan's state determines the behavior: | Child Plan State | Action | |---|---| | Not yet started | Cancel the child plan | | In progress (Strategize or Execute) | Cancel the child plan, roll back its sandbox | | Completed but not applied | Cancel the child plan, roll back its sandbox | | **Already applied** | **Correction rejected** — applied changes cannot be unilaterally reverted; correct the child plan independently or use `--mode=append` on the parent | ##### Rollback Tiers The system's rollback capability depends on the plan's checkpoint and sandbox configuration: | Tier | Prerequisites | Capability | |---|---|---| | **Full decision-level** | Checkpointing enabled + sandboxable resources | Roll back to any individual Execute-phase decision | | **Phase-level** | Checkpointing disabled or unsupported resources | Revert entire Execute phase → Strategize; re-execute from scratch | | **No rollback** | `sandbox.strategy: none` + checkpointing disabled | Only `--mode=append` corrections available | The system detects the available tier automatically and informs the user when a requested correction exceeds the available capability. ##### Phase Boundary Interaction `agents plan correct` is **orthogonal** to phase reversion (Execute → Strategize): - **Phase reversion** is *actor-triggered* when execution constraints are too tight — the actor signals that the strategy needs adjustment. - **Decision correction** is *user-triggered* via `plan correct` — the user identifies a wrong decision. They can interact: correcting a Strategize-phase decision while the plan is in Execute causes both resource rollback (of Execute-phase work) and phase reversion to Strategize. Correcting an Execute-phase decision while still in Execute performs resource rollback within Execute without a phase change. ##### Long-Running Database Transactions The `transaction_rollback` sandbox strategy uses SAVEPOINTs for decision-aligned checkpoints within a single transaction spanning Execute. For plans with extended execution times, this may exceed database transaction timeouts. Recommended mitigations: - **Decompose into child plans**: Each child plan gets a shorter transaction (aligns with hierarchical decomposition). - **Use `none` strategy with `--mode=append`**: Accept non-rollbackable database changes; fix issues via append corrections. - **Implement a custom snapshot-based strategy**: A custom `database-snapshot` resource type using point-in-time snapshots instead of long transactions. #### History Cleanup **History can only be flagged for cleanup after a plan reaches the `applied` state.** Once a plan is applied: - It can no longer be rolled back - Old correction artifacts can be archived or deleted based on retention policy - The decision tree is preserved for audit purposes (superseded decisions are never deleted, per ADR-034) #### CLI Commands for Correction 

# View decision tree
agents plan tree <plan_id>
agents --format=json plan tree <plan_id>  # For visualization tools

# View decision tree including superseded branches
agents plan tree --show-superseded <plan_id>

# Inspect a specific decision
agents plan explain <decision_id>
# Shows: question, chosen option, alternatives, rationale, downstream impact

# Correct via revert-and-replay
agents plan correct <decision_id> --mode=revert --guidance "<what the decision should be>"
# Re-executes from that point with the new guidance

# Correct via append (add fix at end)  
agents plan correct <decision_id> --mode=append --guidance "<description of the fix>"
# Creates a new child plan to fix the outcome without rewriting history

# Compare old vs new after correction
agents plan diff --correction <correction_attempt_id>
#### Correction Safety !!! success "Safety Guarantees" Corrections always: - [x] Create a new attempt revision (increment `plan.attempt`) - [x] Preserve old artifacts for diff/compare - [x] Run execute in sandbox again - [x] Require apply gating again - [x] ==Never modify already-applied changes== - [x] Warn about irreversible side effects before proceeding - [x] Reject correction of decisions whose affected subtree includes applied child plans This keeps history reproducible and prevents accidental destructive edits. ### Human-in-the-Loop Collaboration !!! adr "Architecture Decision" Human-in-the-loop controls, interruptibility, and approval gates are defined in [ADR-017: Automation Profiles](adr/ADR-017-automation-profiles.md). Even though the direction is "more autonomous," the transcript explicitly recognizes that real workflows require engineers to collaborate with the system, editing code while it works, and using better UX integration (TUI/web/IDE). !!! tip "Design Principles for Human-in-the-Loop" | Principle | Description | | :-------- | :---------- | | **Visibility** | What is the system doing ==right now==? | | **Interruptibility** | Pause / cancel / retry at any point | | **Editability** | Allow user to modify strategy before execute | | **Reconciliation** | Detect if user changed sandbox files mid-run and handle it | ### UI / Interaction Model !!! adr "Architecture Decision" The CLI-first interaction model, TUI, and output rendering are defined in [ADR-021: CLI and Output Rendering](adr/ADR-021-cli-and-output-rendering.md). #### CLI-first + TUI + Web App + IDE !!! abstract "Multi-Frontend Architecture" The system is ==CLI-first==, with a single UI codebase powering multiple frontends: - [x] **CLI** — Primary interface for all operations - [x] **TUI** — Built using Textual for rich terminal experiences - [x] **Web App** — Generated from TUI "for free" - [ ] **IDE Plugin** — Future: embeds the TUI in the IDE #### Plan Tree Visualization The TUI should show: * plan list * plan details * plan tree (ASCII) * diff view * approvals And should later allow exporting the tree as image (PNG) or JSON for other visualization tools. ## TUI ### TUI Architecture Overview !!! adr "Architecture Decision" The TUI architecture, framework selection (Textual >= 1.0), screen hierarchy, TuiMaterializer integration, and A2A event subscription model are defined in [ADR-044: TUI Architecture and Framework](adr/ADR-044-tui-architecture-and-framework.md). The TUI (Terminal User Interface) is the second Presentation-layer surface for CleverAgents, built on **Textual** (>= 1.0). It provides real-time plan monitoring, multi-session management, interactive decision tree navigation, and rich conversation with actors — capabilities impractical in the stateless CLI. The TUI communicates with the Application layer exclusively through A2A (ADR-026). It subscribes to A2A events for real-time updates and uses the existing Output Rendering Framework (ADR-021) via a `TuiMaterializer` that maps `ElementHandle` events to Textual widget operations — enabling all CLI command producers to render in the TUI without modification. Key architectural principles: - **Direct-to-chat launch** — no launcher screen; opens directly to the main chat interface - **Right-side collapsible sidebar** — three states cycled by `shift+tab`: hidden → visible → fullscreen - **Multi-session tabs** — independent sessions with separate personas, conversations, and A2A bindings - **Escape-cascading navigation** — `escape` always moves toward the main screen from any state - **Keyboard-first** — every operation achievable without a mouse; mouse is supplementary - **Single UI codebase** — the same Textual widget tree serves standalone TUI, Web (via Textual Web), and IDE plugin #### MainScreen Layout — Sidebar Hidden When the sidebar is hidden, the conversation takes the full terminal width: 
┌──────────────────────────────────────────────────────────────────────────────────────────────┐
│═══════════════════════════════════════════ ◆ ═══════════════════════════════════════════     │
│ Session 1  ┃ Session 2 ┃  Session 3                                                          │
│              ┗━━━━━━━━━━━━┛                                                                  │
├──────────────────────────────────────────────────────────────────────────────────────────────┤
│                                                                                              │
│ ┃ You                                                          14:01                         │
│ ┃ Can you review the auth module in the                                                      │
│ ┃ API service?                                                                               │
│ ┃ @project:api-service:src/auth/handler.py                                                   │
│ ┃                                                                                            │
│ │                                                                                            │
│ │ Actor                                                       14:02                          │
│ │ I'll review the authentication handler.                                                    │
│ │ Let me analyze the code structure and                                                      │
│ │ identify potential issues.                                                                 │
│ │                                                                                            │
│ │  🔧 local/code-analysis ✔                                         ▶                        │
│ │                                                                                            │
│ │ Found 3 issues in the auth module:                                                         │
│ │                                                                                            │
│ │ 1. **Missing rate limiting**                                                               │
│ │ 2. **JWT token** not validated                                                             │
│ │ 3. **Session cleanup** missing                                                             │
│ │                                                                                            │
│ │  🔧 local/file-read ✔                                            ▼                         │
│ │  ┌─ src/auth/handler.py ─────────────┐                                                     │
│ │  │  45 │ def login(self, req):      │                                                      │
│ │  │  46 │     creds = extract(req)   │                                                      │
│ │  │  47 │     return auth(creds)     │                                                      │
│ │  └──────────────────────────────────┘                                                      │
│                                                                                              │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ Agent connected                                                                              │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ ┌─────────────────────────────────────────────────────────────────────────────────────┐      │
│ │ ❯ What would you like to do?                                                        │      │
│ │   ▌@▐ refs  ▌/▐ commands  ▌!▐ shell                                                 │      │
│ └─────────────────────────────────────────────────────────────────────────────────────┘      │
│ feature-dev │ claude-4-sonnet │ think: high │ 2 projects │ $0.12                             │
├──────────────────────────────────────────────────────────────────────────────────────────────┤
│ F1 Help │ shift+tab Sidebar │ tab Persona │ ctrl+tab Preset │ ctrl+s Sessions │ ctrl+q Quit  │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
Key elements in this layout: - **Throbber** (top edge): rainbow gradient bar, visible only when the actor is processing. Collapses to zero height when idle. - **Session Tabs** (below throbber): tab bar with underline indicator on the active session. Hidden when only one session exists. Session labels show state icons: `⌛` (actor working), `❯` (awaiting input), plain (idle). - **Conversation** (center): scrollable message stream with block cursor navigation. - **Prompt** (bottom): PromptTextArea with mode-dependent symbol (❯ normal, $ shell, ☰ multi-line), overlays for @ references and / commands, and the PersonaBar. - **Footer**: context-sensitive hotkey reference, always visible. #### MainScreen Layout — Sidebar Visible When the sidebar is visible (shift+tab from hidden), it docks to the right at 32-40 chars wide: 
┌──────────────────────────────────────────────────────────────────────────────────────────────┐
│═══════════════════════════════════════════ ◆ ═══════════════════════════════════════════     │
│ Session 1  ┃ Session 2 ┃  Session 3                                                          │
│              ┗━━━━━━━━━━━━┛                                                                  │
├─────────────────────────────────────────────────────────────┬────────────────────────────────┤
│                                                             │ ▼ PLANS                        │
│ ┃ You                                  14:01                │ ┌────────────────────────────┐ │
│ ┃ Can you review the auth module in the                     │ │ ► fix-auth-bug             │ │
│ ┃ API service?                                              │ │   Phase: Execute ●●●○      │ │
│ ┃ @project:api-service:src/auth/handler.py                  │ │   Profile: trusted         │ │
│ ┃                                                           │ │   Actor: claude-4-sonnet   │ │
│ │                                                           │ │   Cost: $0.08              │ │
│ │ Actor                                  14:02              │ │                            │ │
│ │ I'll review the authentication handler.                   │ │ ► refactor-models          │ │
│ │ Let me analyze the code structure and                     │ │   Phase: Strategize ●○○○   │ │
│ │ identify potential issues.                                │ │   Profile: cautious        │ │
│ │                                                           │ │   Depth: 2 (3 subplans)    │ │
│ │  🔧 local/code-analysis ✔         ▶                       │ │   Actor: gpt-4o            │ │
│ │                                                           │ │   ├─ users   (execute)     │ │
│ │ Found 3 issues in the auth module:                        │ │   ├─ orders  (strategize)  │ │
│ │                                                           │ │   └─ auth    (pending)     │ │
│ │ 1. **Missing rate limiting**                              │ │                            │ │
│ │ 2. **JWT token** not validated                            │ │ ◌ update-deps              │ │
│ │ 3. **Session cleanup** missing                            │ │   Phase: Idle              │ │
│ │                                                           │ │   Profile: auto            │ │
│ │  🔧 local/file-read ✔             ▼                       │ └────────────────────────────┘ │
│ │  ┌─ src/auth/handler.py ─────────────┐                    │                                │
│ │  │  45 │ def login(self, req):       │                     │ ▼ PROJECTS                     │
│ │  │  46 │     creds = extract(req)    │                     │ ┌────────────────────────────┐ │
│ │  │  47 │     return auth(creds)      │                     │ │ ◆ cleveragents        [2p] │ │
│ │  └───────────────────────────────────┘                     │ │ ◆ api-service         [1p] │ │
│                                                             │ │   frontend-app        [0p] │ │
│─────────────────────────────────────────────────────────────│ │   infra-terraform     [0p] │ │
│ Agent connected                                             │ └────────────────────────────┘ │
│─────────────────────────────────────────────────────────────│                                │
│ ┌────────────────────────────────────────────────────────┐  │                                │
│ │ ❯ What would you like to do?                           │  │                                │
│ │   ▌@▐ refs  ▌/▐ commands  ▌!▐ shell                    │  │                                │
│ └────────────────────────────────────────────────────────┘  │                                │
│ feature-dev │ claude-4-sonnet │ think: med │ 2 proj │ $0.12 │                                │
├─────────────────────────────────────────────────────────────┴────────────────────────────────┤
│ F1 Help │ shift+tab Sidebar │ tab Persona │ ctrl+tab Preset │ ctrl+s Sessions │ ctrl+q Quit  │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
Key elements in this layout: - **Throbber** (top edge): rainbow gradient bar, visible only when the actor is processing. Collapses to zero height when idle. - **Session Tabs** (below throbber): tab bar with underline indicator on the active session. Hidden when only one session exists. Session labels show state icons: `⌛` (actor working), `❯` (awaiting input), plain (idle). - **Conversation** (center): scrollable message stream with block cursor navigation. - **Sidebar** (right, 32-40 chars wide): Plans panel and Projects panel in collapsible containers. - **Prompt** (bottom of left panel): same prompt components as hidden mode, constrained to the conversation column width. - **PersonaBar** (below prompt): shows persona name, actor, preset, scope, and cost. #### MainScreen Layout — Sidebar Fullscreen Fullscreen mode (shift+tab from visible) covers the entire terminal for plan/project/persona management: 
┌──────────────────────────────────────────────────────────────────────────────────────────────┐
│ PLANS & PROJECTS BROWSER                                                                     │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ PLANS                                         │ PROJECTS                                     │
│ ┌───────────────────────────────────────────┐ │ ┌──────────────────────────────────────────┐ │
│ │                                           │ │ │                                          │ │
│ │ [x] ► fix-auth-bug                        │ │ │ [x] cleveragents                         │ │
│ │     Phase: Execute ●●●○                   │ │ │     Namespace: local/                    │ │
│ │     State: in_progress                    │ │ │     Resources: 5                         │ │
│ │     Profile: trusted                      │ │ │     Plans: 2 active                      │ │
│ │     Actor: anthropic/claude-4-sonnet      │ │ │     Invariants: 3                        │ │
│ │     Started: 2m ago    Cost: $0.08        │ │ │     Validations: 2                       │ │
│ │     Decisions: 6 (4 done, 2 pending)      │ │ │                                          │ │
│ │                                           │ │ │ [ ] api-service                          │ │
│ │ [ ] refactor-models                       │ │ │     Namespace: local/                    │ │
│ │     Phase: Strategize ●○○○                │ │ │     Resources: 3                         │ │
│ │     State: in_progress                    │ │ │     Plans: 1 active                      │ │
│ │     Profile: cautious                     │ │ │     Invariants: 1                        │ │
│ │     Actor: openai/gpt-4o                  │ │ │     Validations: 4                       │ │
│ │     Started: 5m ago    Cost: $0.03        │ │ │                                          │ │
│ │     Decisions: 3 (2 done, 1 active)       │ │ │ [ ] frontend-app                         │ │
│ │     Subplans: 3 (depth 2)                 │ │ │     Namespace: local/                    │ │
│ │       ├─ users    Execute ●●●○            │ │ │     Resources: 2                         │ │
│ │       ├─ orders   Strategize ●○○○         │ │ │     Plans: 0                             │ │
│ │       └─ auth     Pending                 │ │ │                                          │ │
│ │                                           │ │ │ [ ] infra-terraform                      │ │
│ │ [ ] update-deps                           │ │ │     Namespace: local/                    │ │
│ │     Phase: Idle                           │ │ │     Resources: 8                         │ │
│ │     Profile: auto                         │ │ │     Plans: 0                             │ │
│ │                                           │ │ │                                          │ │
│ └───────────────────────────────────────────┘ │ └──────────────────────────────────────────┘ │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ PERSONA CYCLE LIST (tab order)                                                               │
│ ┌──────────────────────────────────────────────────────────────────────────────────────┐     │
│ │  1. feature-dev (claude-4-sonnet, 2 projects)                                        │     │
│ │  2. reviewer (gpt-4o, 1 project)                                                     │     │
│ │  3. infra-admin (claude-4-opus, 1 project)                                           │     │
│ │  [+] Add current selection as persona...                                             │     │
│ └──────────────────────────────────────────────────────────────────────────────────────┘     │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ Selected: 1 plan, 1 project                                                                  │
│ space Select │ enter Details │ ctrl+p Create Persona │ / Search │ d Delete │ esc Back        │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
In fullscreen mode: - **Selection mode**: `space` toggles selection on the highlighted plan or project. Selected items show `[x]`, deselected show `[ ]`. - **Persona creation**: `ctrl+p` opens the PersonaEditorModal with the selected plans and projects pre-populated as the scope. - **Detail inspection**: `enter` on a plan opens the PlanDetailModal; `enter` on a project opens the ProjectDetailModal. - **Persona cycle list**: The bottom panel shows the ordered list of personas that `tab` cycles through. Users can reorder (`ctrl+up`/`ctrl+down`), remove (`d`), or add new personas from the current selection. #### Sidebar State Transitions | State | Layout | Input Focus | Content | |-------|--------|-------------|---------| | **Hidden** | Sidebar `display: none`; conversation full width | Prompt retains focus | No sidebar content visible | | **Visible** | Sidebar docked right, 32-40 chars wide | Prompt retains focus; `ctrl+b` focuses sidebar | Plans and Projects panels in collapsible containers | | **Fullscreen** | Covers entire screen | Sidebar takes input focus | Extended details, selection mode, persona management | State transitions: ``` Hidden ──shift+tab──► Visible ──shift+tab──► Fullscreen ▲ │ └──────────────── escape (×1-2) ───────────────┘ ``` ### Persona System !!! adr "Architecture Decision" The persona abstraction, argument preset cycling, scope behavior, and persona lifecycle are defined in [ADR-045: TUI Persona System](adr/ADR-045-tui-persona-system.md). A **persona** is a TUI-only abstraction that bundles: 1. **Actor reference** — a namespaced actor name (e.g., `anthropic/claude-4-sonnet`) 2. **Base arguments** — default arguments passed to the actor on every invocation 3. **Scoped projects** — projects always included in the session's context 4. **Scoped plans** — plans always included in the session's context 5. **Argument presets** — named argument overrides cycled with `ctrl+tab` 6. **Display metadata** — short name, accent color, description Personas are stored as YAML files in `~/.config/cleveragents/personas/` and are strictly a Presentation-layer concept — they never appear in the domain model, A2A protocol, or database schema. #### PersonaBar The PersonaBar always shows the current state: 
┌──────────────────────────────────────────────────────────────────────┐
│ ❯ What would you like to do?                                         │
│   ▌@▐ refs  ▌/▐ commands  ▌!▐ shell                                  │
└──────────────────────────────────────────────────────────────────────┘
  feature-dev │ claude-4-sonnet │ think: high │ 2 projects       │ $0.12
  ─────────── ─ ─────────────── ─ ─────────── ─ ──────────────── ─ ─────
  persona       actor             preset        scope              cost
| PersonaBar Segment | Style | Updates When | |--------------------|-------|--------------| | Persona name | `$text-primary` on `$primary 10%` bg | `tab` cycle | | Actor name | `$text-secondary` | `tab` cycle | | Preset label | `$text-warning` (non-default) / `$text-muted` (default) | `ctrl+tab` cycle | | Scope indicator | `$text-muted` | Persona change or `/scope:add/remove` | | Session cost | `$secondary 70%`, right-aligned | After each actor response | #### Persona Cycling `tab` cycles through personas in the configured cycle list. `ctrl+tab` cycles through the current persona's argument presets: ``` tab: persona_1 → persona_2 → persona_3 → persona_1 → ... ctrl+tab: default → think: high → think: max → quick → default → ... ``` When cycling, the PersonaBar updates immediately. The actor binding for the session is updated — subsequent prompts use the new persona's actor and scope. #### First-Run Experience On first launch (no personas configured), a centered overlay guides actor selection: 
┌──────────────────────────────────────────────────────────────────────┐
│ Welcome to CleverAgents                                              │
│                                                                      │
│ Select an actor to get started:                                      │
│                                                                      │
│   ❯ anthropic/claude-4-sonnet   (recommended)                        │
│     anthropic/claude-4-opus                                          │
│     openai/gpt-4o                                                    │
│     openai/o3                                                        │
│     google/gemini-2                                                  │
│     / to search...                                                   │
│                                                                      │
│ A default persona will be created with this actor.                   │
│ You can add more actors and personas later.                          │
│                                                                      │
│──────────────────────────────────────────────────────────────────────│
│ enter Select │ j/k Navigate │ / Search                               │
└──────────────────────────────────────────────────────────────────────┘
Selection creates a `"default"` persona with the chosen actor and auto-generated argument presets (thinking effort levels are auto-detected from the actor's argument schema). Subsequent launches restore the last active persona. ### Reference and Command System !!! adr "Architecture Decision" The @ reference notation grammar, fuzzy search algorithm, / command system, ! shell mode, and ACMS integration are defined in [ADR-046: TUI Reference and Command System](adr/ADR-046-tui-reference-and-command-system.md). The TUI prompt supports three input modes, each activated by a distinct prefix: | First Character | Mode | Prompt Symbol | Sent To | Overlay | |-----------------|------|---------------|---------|---------| | *(any other)* | Normal | `❯` | Actor via A2A | — | | `@` *(inline)* | Normal + Reference | `❯` | Actor (with CRP directives) | ReferencePickerOverlay | | `/` | Command | `/` | TUI command processor | SlashCommandOverlay | | `!` | Shell | `$` | Host OS subprocess | — | #### Reference Picker (@) Typing `@` anywhere in a normal-mode prompt activates the Reference Picker — a fuzzy-search overlay for projects, plans, and resources: 
┌─ Reference Picker ───────────────────────────────────────────────────┐
│ @hand                                                                │
│ ──────────────────────────────────────────────────────────────────── │
│  PROJECT  api-service:src/auth/handler.py                            │
│           local/api-service • Python • 245 lines                     │
│                                                                      │
│  PROJECT  cleveragents:git_dir/src/cli/commands/handler.py           │
│           local/cleveragents • Python • 189 lines                    │
│                                                                      │
│  PROJECT  api-service:src/auth/middleware/handler_base.py            │
│           local/api-service • Python • 67 lines                      │
│                                                                      │
│  PLAN     fix-auth-handler (01HXM8C2...)                             │
│           Phase: Execute • Actor: claude-4-sonnet                    │
│                                                                      │
│ ──────────────────────────────────────────────────────────────────── │
│ enter Select │ tab Tree │ ctrl+p Projects │ ctrl+l Plans             │
└──────────────────────────────────────────────────────────────────────┘
Resolved references use a canonical notation: `@project:local/api-service:src/auth/handler.py`. Fuzzy input like `@handler.py` auto-expands to the canonical form on selection. Resolved `@` references are translated into CRP (Context Request Protocol) directives before the prompt reaches the actor — they semantically direct the ACMS to prioritize referenced resources in context assembly. #### Reference Picker — Tree Browser Mode Pressing `tab` in the Reference Picker switches to tree browser mode for hierarchical navigation: 
┌─ Reference Picker (Tree) ────────────────────────────────────────────┐
│                                                                      │
│  ▼ Projects                                                          │
│    ▼ local/cleveragents                                              │
│      ▼ git_dir (git-checkout)                                        │
│        ▸ src/                                                        │
│        ▸ tests/                                                      │
│        ▸ docs/                                                       │
│        ─ pyproject.toml                                              │
│        ─ README.md                                                   │
│      ▸ database (sqlite-db)                                          │
│    ▸ local/api-service                                               │
│    ▸ local/frontend-app                                              │
│  ▼ Plans                                                             │
│    ▸ fix-auth-bug (01HXM8C2)                                         │
│    ▸ refactor-models (01HXM9D3)                                      │
│                                                                      │
│ enter Select │ tab Search │ space Expand │ / Filter                  │
└──────────────────────────────────────────────────────────────────────┘
#### Slash Command Overlay (/) Typing `/` as the first character activates command mode. Commands are TUI operations executed locally — they are **not** sent to the actor. ##### Slash Command Overlay 
┌─ Commands ─────────────────────────────────────────────────────────────┐
│ /se                                                                    │
│ ───────────────────────────────────────────────────────────────────────│
│  /session:create         Create a new session tab                      │
│  /session:list           Show all sessions                             │
│  /session:show           Show session details                          │
│  /session:switch         Switch to session by ID                       │
│  /session:close          Close current session                         │
│  /session:delete         Delete a saved session                        │
│  /session:rename         Rename current session                        │
│  /session:export         Export session to file                        │
│  /session:import         Import session from file                      │
│  /settings               Open settings screen                          │
│                                                                        │
│ enter Execute │ tab Complete │ escape Dismiss                          │
└────────────────────────────────────────────────────────────────────────┘
TUI slash commands mirror CLI command patterns where applicable. The CLI uses `agents `; the TUI uses `/:`. Commands that exist in both CLI and TUI use the same verb names. TUI-only commands (persona, scope, TUI utilities) have no CLI equivalent. ##### Complete Command Reference **Session Commands** — *mirrors CLI `agents session `* | Command | Arguments | Description | |---------|-----------|-------------| | `/session:create` | `[--persona ]` | Create a new session tab | | `/session:list` | — | Display all sessions | | `/session:show ` | `` | Show session details | | `/session:switch ` | `` | Switch to session by ID or tab index | | `/session:close` | `[--force]` | Close the current session tab | | `/session:delete ` | ``, `[--yes/-y]` | Delete a saved session | | `/session:rename ` | `` | Rename the current session | | `/session:export [path]` | `[path]` | Export session to JSON | | `/session:import ` | `` | Import session from JSON | **Persona Commands** — *TUI-only* | Command | Arguments | Description | |---------|-----------|-------------| | `/persona:list` | — | Display all personas | | `/persona:set ` | `` | Switch to persona | | `/persona:create` | — | Open PersonaEditorModal | | `/persona:edit [name]` | `[name]` | Edit persona | | `/persona:delete ` | `` | Delete persona | | `/persona:export ` | `` | Export persona YAML | | `/persona:import ` | `` | Import persona YAML | **Scope Commands** — *TUI-only* | Command | Arguments | Description | |---------|-----------|-------------| | `/scope:add ` | `` | Add project/plan to session scope | | `/scope:remove ` | `` | Remove from session scope | | `/scope:clear` | — | Clear session-level scope additions | | `/scope:show` | — | Show effective scope | **Plan Commands** — *mirrors CLI `agents plan `* | Command | Arguments | Description | |---------|-----------|-------------| | `/plan:use ` | ``, `[projects...]`, `[--arg/-a ]` | Start a new plan | | `/plan:list` | `[--phase]` `[--state]` `[--project]` `[--action]` | List plans | | `/plan:status [id]` | `[id]` | Show plan status | | `/plan:tree ` | ``, `[--show-superseded]` `[--depth]` | Show decision tree | | `/plan:execute [id]` | `[id]` | Execute a plan | | `/plan:apply [id]` | `[id]` | Apply a completed plan | | `/plan:cancel ` | ``, `[--reason/-r]` | Cancel a plan | | `/plan:diff ` | ``, `[--correction]` | Show plan diff | | `/plan:correct ` | ``, `--mode`, `--guidance` | Correct a decision | | `/plan:resume ` | ``, `[--dry-run]` | Resume a plan | | `/plan:revert ` | ``, `[--to-phase]` | Revert a plan | | `/plan:rollback ` | both required | Rollback to checkpoint | | `/plan:explain ` | ``, `[--show-context]` | Explain a decision | | `/plan:errors ` | `` | Show plan errors | | `/plan:artifacts ` | `` | Show plan artifacts | | `/plan:inspect [id]` | `[id]` | Open PlanDetailModal | **Project Commands** — *mirrors CLI `agents project `* | Command | Arguments | Description | |---------|-----------|-------------| | `/project:list` | `[--namespace/-n]` | List all projects | | `/project:create ` | ``, `[--description/-d]` `[--resource/-r]` | Create project | | `/project:show ` | `` | Show project details | | `/project:delete ` | ``, `[--yes/-y]` | Delete project | | `/project:inspect ` | `` | Open ProjectDetailModal | | `/project:context:show ` | `` | Show project context config | **Actor, Resource, Config, Tool, Skill, Invariant, Profile Commands** — *mirrors CLI* | Command | Description | |---------|-------------| | `/actor:list`, `/actor:show`, `/actor:set-default` | Actor management | | `/resource:list`, `/resource:show`, `/resource:tree`, `/resource:inspect` | Resource management | | `/config:list`, `/config:get`, `/config:set` | Configuration management | | `/tool:list`, `/tool:show` | Tool management | | `/skill:list`, `/skill:show` | Skill management | | `/invariant:list`, `/invariant:add`, `/invariant:remove` | Invariant management | | `/profile:list`, `/profile:show` | Automation profile management | | `/context:inspect`, `/context:set`, `/context:simulate` | Context management (inspect state, set policy, simulate assembly) | **TUI Utility Commands** — *TUI-only* | Command | Arguments | Description | |---------|-----------|-------------| | `/clear` | — | Clear conversation display | | `/theme [name]` | `[name]` | Switch color theme | | `/settings` | — | Open SettingsScreen | | `/help [command]` | `[command]` | Show help | | `/about` | — | Show version and system info | | `/debug` | — | Toggle debug mode | #### Shell Mode (!) Shell mode provides direct OS command execution from the TUI prompt. Typing `!` as the first character changes the prompt symbol to `$` and enables shell syntax highlighting, file/directory tab completion, and separate shell history. 
┌────────────────────────────────────────────────────────────────────┐
│ $ git status                                                       │
│ ┌────────────────────────────────────────────────────────────────┐ │
│ │ On branch main                                                 │ │
│ │ Your branch is up to date with 'origin/main'.                  │ │
│ │                                                                │ │
│ │ Changes not staged for commit:                                 │ │
│ │   modified:   src/auth/handler.py                              │ │
│ │   modified:   src/auth/middleware.py                           │ │
│ └────────────────────────────────────────────────────────────────┘ │
│ (exit code: 0)                                                     │
└────────────────────────────────────────────────────────────────────┘
Shell results appear as `ShellResult` blocks in the conversation stream with a `$primary` left border and `$foreground 4%` background. Long-running commands stream output in real-time; `ctrl+c` sends SIGINT. ### Plan Detail Modal The PlanDetailModal shows a plan's decision tree alongside decision details: 
┌───────────────────────────────────── Plan: fix-auth-bug ─────────────────────────────────────┐
│ ID: 01HXM8C2ABCD     Phase: Execute       State: in_progress                                 │
│ Profile: trusted      Actor: claude-4-sonnet   Started: 2m ago    Cost: $0.08                │
│ Projects: local/api-service                                                                  │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ DECISION TREE                            │ DECISION DETAIL                                   │
│ ┌──────────────────────────────────────┐ │ ┌────────────────────────────────────────┐        │
│ │                                      │ │ │ Decision: D3                           │        │
│ │ ▼ D1 strategy_choice           ✔     │ │ │ Type: implementation_choice            │        │
│ │   ├─ D2 invariant_enforced     ✔     │ │ │ Phase: Execute                         │        │
│ │   ├─▶D3 implementation_choice  ⚡    │ │ │                                        │        │
│ │   │   ├─ D4 tool_invocation    ✔     │ │ │ Question:                              │        │
│ │   │   ├─ D5 tool_invocation    ⌛    │ │ │ How should rate limiting be            │        │
│ │   │   └─ D6 tool_invocation    ⌛    │ │ │ implemented on the login endpoint?     │        │
│ │   ├─ D7 resource_selection     ⌛    │ │ │                                        │        │
│ │   └─ D8 subplan_spawn          ⌛    │ │ │ Chosen: Token bucket algorithm         │        │
│ │                                      │ │ │ with Redis backing store               │        │
│ │ / Search decisions...                │ │ │                                        │        │
│ │                                      │ │ │ Alternatives:                          │        │
│ └──────────────────────────────────────┘ │ │ • Sliding window counter               │        │
│                                          │ │ • Fixed window counter                 │        │
│ Legend:                                  │ │ • IP-based blocking                    │        │
│  ✔ completed  ⚡ active                  │ │                                        │        │
│  ⌛ pending   ✗ failed                   │ │ Confidence: 0.85                       │        │
│  ⊘ superseded                            │ │ Rationale: Token bucket provides       │        │
│                                          │ │ fine-grained control with burst        │        │
│ ───────────────────────────────────────  │ │ allowance and Redis enables            │        │
│ Phase: ●●●○                              │ │ distributed rate limiting...           │        │
│ Decisions: 8 total                       │ │                                        │        │
│  4 completed, 1 active, 3 pending        │ │ Dependencies:                          │        │
│                                          │ │  ← D1 (strategy_choice)                │        │
│                                          │ │  → D4, D5, D6 (tool_invocations)       │        │
│                                          │ │                                        │        │
│                                          │ │ Context Snapshot: 2.3 KB               │        │
│                                          │ └────────────────────────────────────────┘        │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ j/k Nav │ enter Inspect │ c Correct │ d Diff │ h History │ t Toggle │ / Search               │
│ s Superseded │ x Expand all │ z Collapse all │ escape Close                                  │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
#### Decision Tree Interaction | Key | Action | |-----|--------| | `j` / `down` | Move to next decision | | `k` / `up` | Move to previous decision | | `enter` | Select decision → show detail in right panel | | `space` | Expand/collapse subtree | | `c` | Correct selected decision (opens correction dialog) | | `d` | Show diff for selected decision | | `h` | Show decision history / superseded chain | | `t` | Toggle detail panel visibility | | `x` | Expand all nodes | | `z` | Collapse all nodes | | `s` | Show superseded decisions (hidden by default) | | `/` | Search decisions by type, content, or ID | | `escape` | Close modal | ### Project Detail Modal The ProjectDetailModal shows a project's resource DAG, invariants, and running plans: 
┌───────────────────────────────── Project: local/api-service ─────────────────────────────────┐
│ Namespace: local/        Resources: 3          Plans: 1 active                               │
│ Invariants: 1            Validations: 4        Automation: trusted                           │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ RESOURCES                                │ DETAIL                                            │
│ ┌──────────────────────────────────────┐ │ ┌────────────────────────────────────────┐        │
│ │                                      │ │ │ Resource: api-repo                     │        │
│ │ ▼ api-repo (git-checkout)            │ │ │ Type: git-checkout                     │        │
│ │   ├─ src/ (fs-directory)             │ │ │ ID: 01HXYZ...                          │        │
│ │   │   ├─ auth/                       │ │ │                                        │        │
│ │   │   │   ├─ handler.py              │ │ │ URL: git@github.com:org/api.git        │        │
│ │   │   │   ├─ middleware.py           │ │ │ Branch: main                           │        │
│ │   │   │   └─ limiter.py              │ │ │ Commit: a1b2c3d (2h ago)               │        │
│ │   │   ├─ models/                     │ │ │                                        │        │
│ │   │   └─ routes/                     │ │ │ Sandbox: git_worktree                  │        │
│ │   ├─ tests/ (fs-directory)           │ │ │ Checkpoint: enabled                    │        │
│ │   └─ pyproject.toml                  │ │ │                                        │        │
│ │ ─ api-db (container-instance)        │ │ │ Children: 2 (src/, tests/)             │        │
│ │ ─ api-cache (container-instance)     │ │ │ Validations: 2 attached                │        │
│ │                                      │ │ │                                        │        │
│ └──────────────────────────────────────┘ │ └────────────────────────────────────────┘        │
│                                          │                                                   │
│ INVARIANTS                               │ RUNNING PLANS                                     │
│ ┌──────────────────────────────────────┐ │ ┌────────────────────────────────────────┐        │
│ │ 1. All API endpoints must have       │ │ │ fix-auth-bug  Execute ●●●○  $0.08      │        │
│ │    rate limiting (project-level)     │ │ │                                        │        │
│ └──────────────────────────────────────┘ │ └────────────────────────────────────────┘        │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ j/k Nav │ enter Drill │ i Invariants │ v Validations │ p Plans │ / Search │ esc Close        │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
### Persona Editor Modal The PersonaEditorModal is used for creating and editing personas: 
┌─────────────────────────────────────── Create Persona ───────────────────────────────────────┐
│                                                                                              │
│ Name:        ┌──────────────────────────────────────┐                                        │
│              │ feature-dev                          │                                        │
│              └──────────────────────────────────────┘                                        │
│                                                                                              │
│ Description: ┌────────────────────────────────────────────────────────┐                      │
│              │ Feature development with Claude on main projects       │                      │
│              └────────────────────────────────────────────────────────┘                      │
│                                                                                              │
│ Actor:       ┌──────────────────────────────────────────┐                                    │
│              │ ❯ anthropic/claude-4-sonnet              │ ▼                                  │
│              └──────────────────────────────────────────┘                                    │
│                                                                                              │
│ Color:   ● $primary   ○ $secondary   ○ $success   ○ $warning   ○ $error                      │
│                                                                                              │
│ ── Base Arguments (from actor schema) ──────────────────────────────────────                 │
│ thinking_effort:  ┌──────────┐   temperature:  ┌──────────┐                                  │
│                   │ medium   │ ▼               │ 0.7      │                                  │
│                   └──────────┘                 └──────────┘                                  │
│ max_tokens:       ┌──────────┐                                                               │
│                   │ 16384    │                                                               │
│                   └──────────┘                                                               │
│                                                                                              │
│ ── Scoped Projects ─────────────────────────────────────────────────────────                 │
│ [x] local/cleveragents        [x] local/api-service                                          │
│ [ ] local/frontend-app        [ ] local/infra-terraform                                      │
│                                                                                              │
│ ── Scoped Plans ────────────────────────────────────────────────────────────                 │
│ [ ] fix-auth-bug (01HXM8C2)   [ ] refactor-models (01HXM9D3)                                 │
│                                                                                              │
│ ── Argument Presets (ctrl+tab cycling) ─────────────────────────────────────                 │
│ ┌────────────────────────────────────────────────────────────────────────────────────┐       │
│ │  1. default      │ (base arguments)                                                │       │
│ │  2. think: high  │ thinking_effort=high                                            │       │
│ │  3. think: max   │ thinking_effort=max, temperature=0.3                            │       │
│ │  4. quick        │ thinking_effort=low, max_tokens=4096                            │       │
│ │  [+] Add preset                                                                    │       │
│ └────────────────────────────────────────────────────────────────────────────────────┘       │
│                                                                                              │
│ Cycle Order: ┌──────┐  (0 = not in tab cycle)                                                │
│              │  1   │                                                                        │
│              └──────┘                                                                        │
│                                                                                              │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ tab Next field │ enter Save │ escape Cancel                                                  │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
### Permissions Screen When a tool requests permission to modify resources, the PermissionsScreen shows the requested changes with a diff view: 
┌───────────────────────────────────── Permission Request ─────────────────────────────────────┐
│                                                                                              │
│ local/file-write wants to modify 3 files in local/api-service:                               │
│                                                                                              │
│ ┌─────────────────────────────┐ ┌──────────────────────────────────────────────────────┐     │
│ │Files (3 changes):           │ │src/auth/handler.py                                   │     │
│ │                             │ │──────────────────────────────────────────────────────│     │
│ │❯ src/auth/handler.py [M]    │ │ @@ -45,6 +45,12 @@                                   │     │
│ │  src/auth/middleware.py [M] │ │  def login(self, request):                           │     │
│ │  src/auth/limiter.py   [A]  │ │ +    @rate_limit(max_calls=5, period=60)             │     │
│ │                             │ │      credentials = self.extract(request)             │     │
│ │                             │ │ -    return self.authenticate(credentials)           │     │
│ │                             │ │ +    result = self.authenticate(credentials)         │     │
│ │                             │ │ +    self.log_attempt(request, result)               │     │
│ │                             │ │ +    return result                                   │     │
│ │                             │ │                                                      │     │
│ │                             │ │ @@ -78,3 +84,8 @@                                    │     │
│ │                             │ │  def logout(self, request):                          │     │
│ │                             │ │ +    self.cleanup_session(request)                   │     │
│ │                             │ │      return Response(status=200)                     │     │
│ │                             │ │                                                      │     │
│ └─────────────────────────────┘ └──────────────────────────────────────────────────────┘     │
│──────────────────────────────────────────────────────────────────────────────────────────────│
│ [M] Modified  [A] Added  [D] Deleted                                                         │
│ a Allow │ A Allow Always │ r Reject │ R Reject Always │ j/k Nav │ d Diff │ esc               │
└──────────────────────────────────────────────────────────────────────────────────────────────┘
The diff view supports three display modes, toggled with `d`: | Mode | Behavior | |------|----------| | **Unified** | Standard unified diff with +/- lines (default) | | **Side-by-side** | Two-column view with old content left, new content right | | **Context** | Shows only changed lines with surrounding context (3 lines default) | ### Inline Permission Question Widget For **single-file** permission requests, the TUI renders a `PermissionQuestionWidget` inline in the conversation stream rather than pushing the full `PermissionsScreen`. This avoids interrupting the conversation flow for simple allow/reject decisions. The widget displays: - The actor name and requested operation type - The target file path - Inline diff content (when available) - Four decision options with keyboard shortcuts | Key | Decision | Scope | |-----|----------|-------| | `a` | Allow once | This operation only | | `A` | Allow always | All operations this session | | `r` | Reject once | This operation only | | `R` | Reject always | All operations this session | Navigate options with `up`/`down` and confirm with `enter`, or use the single-key shortcuts directly. Press `v` to open the full `PermissionsScreen` for multi-file diff review. **Permission request types**: `file_write`, `file_delete`, `file_read`, `shell_exec`, `network`. **Routing logic**: - Single-file operations → `PermissionQuestionWidget` inline in conversation stream - Multi-file operations → `PermissionsScreen` pushed directly (no inline widget) The widget emits a `PermissionDecisionEvent` when a decision is made, which the TUI processes to either allow or reject the pending tool operation. **Domain models**: - `InlinePermissionQuestion` — carries `file_path`, `request_type` (`PermissionRequestType`), `diff_content`, and `actor_name` - `PermissionRequestType` enum: `FILE_WRITE`, `FILE_DELETE`, `FILE_READ`, `SHELL_EXEC`, `NETWORK` - `PermissionDecision` enum: `ALLOW_ONCE`, `ALLOW_ALWAYS`, `REJECT_ONCE`, `REJECT_ALWAYS` ### Additional UI Components #### Throbber A rainbow gradient animated bar spans the full width at the top, visible only when the actor is processing: 
┌───────────────────────────────────────────────────────────────────────────┐
│ ════════════════════════════════════ ◆ ═══════════════════════════════════│
│ (actor processing...)                                                     │
│                                                                           │
│ (idle — throbber collapses to zero height)                                │
└───────────────────────────────────────────────────────────────────────────┘
The gradient cycles through 12 colors at 15fps: `#881177` → `#aa3355` → `#cc6666` → `#ee9944` → `#eedd00` → `#99dd55` → `#44dd88` → `#22ccbb` → `#00bbcc` → `#0099cc` → `#3366bb` → `#663399` #### Session Tabs 
┌────────────────────────────────────────────────────────────────────────────┐
│ Session 1  ┃ Session 2 ┃  Session 3  ┃  ⌛ Session 4                       │
│              ┗━━━━━━━━━━━┛                                                 │
│                                                                            │
│ ctrl+[ Previous │ ctrl+] Next │ ctrl+n New │ ctrl+w Close                  │
│ ctrl+s Sessions screen │ 1-9 Jump to tab                                   │
│                                                                            │
│ Indicators:  ⌛ actor working  │  ❯ awaiting input  │  (plain) idle        │
│              ━━━ active tab underline                                      │
└────────────────────────────────────────────────────────────────────────────┘
#### Notifications (Flash) Notifications appear as a single-line Flash bar above the prompt, auto-dismissing after a configurable timeout (default 5s): 
┌────────────────────────────────────────┐
│ ✔ Plan fix-auth-bug completed          │
│ (auto-dismiss in 5s)                   │
│                                        │
│ ✗ Plan refactor-models failed          │
└────────────────────────────────────────┘
#### Help Panel (F1) `F1` opens a context-sensitive help overlay showing available hotkeys for the current screen/widget: 
┌─ Help: Main Screen ─────────────────────────────────────────────────────┐
│                                                                         │
│ Navigation                                                              │
│  shift+tab     Cycle sidebar: hidden → visible → fullscreen             │
│  tab           Cycle to next persona                                    │
│  ctrl+tab      Cycle to next argument preset                            │
│  ctrl+[/]      Switch session tab                                       │
│  escape        Close overlay / sidebar / return to prompt               │
│                                                                         │
│ Prompt                                                                  │
└─────────────────────────────────────────────────────────────────────────┘
#### Escape Cascade The escape key always cascades toward the main screen: 
┌───────────────────────────────────────────────────────────────────────┐
│ Modal (PlanDetail, ProjectDetail, PersonaEditor, ...)                 │
│   ↓ escape                                                            │
│ Overlay (ReferencePicker, SlashCommand)                               │
│   ↓ escape                                                            │
│ Sidebar Fullscreen                                                    │
│   ↓ escape                                                            │
│ Sidebar Visible                                                       │
└───────────────────────────────────────────────────────────────────────┘
Multiple escape presses from any state eventually reach the main chat prompt. No modal or screen may trap the user without an escape path. ### Conversation Stream The conversation displays a chronological stream of typed message blocks: | Block Type | Visual Treatment | Source | |------------|-----------------|--------| | `Welcome` | ASCII art + instructions in `$text-success` | App startup (first message) | | `UserInput` | Left border `$secondary`, 15% background tint, Markdown | User prompt submission | | `ActorResponse` | Streaming Markdown with syntax-highlighted code fences | `session.message` events | | `ActorThought` | `$primary-muted` 20% bg, max 10 lines (expandable), italic | Actor reasoning | | `ToolCall` | Expandable: icon + status pill header, collapsible content | `tool.invoked` / `tool.completed` | | `PlanProgress` | Grid layout with status icons per step | Plan phase changes | | `DiffView` | Unified or side-by-side diff, syntax highlighting | Tool results with diffs | | `TerminalEmbed` | Bordered terminal, `$primary 50%` border, green/red tint | Shell or tool terminal output | | `ShellResult` | Left border `$primary`, 4% foreground bg | User shell command (!) output | | `Note` | Semantic: info (`$primary`), warning (`$warning`), error (`$error`) | System notifications | The conversation uses a 2-column grid: a 1-character cursor column (left, navigable via `alt+up`/`alt+down`) and the content stream (right). The block cursor provides keyboard-driven message navigation — `enter` or `space` expands/collapses a block. ### Theme and Styling The TUI uses Textual's CSS (TCSS) system with semantic color tokens: | Token | Usage | |-------|-------| | `$primary` | Active elements, sidebar borders, plan status | | `$secondary` | User input highlights, prompt accent | | `$success` | Completed states, passed validations | | `$error` | Failed states, error notifications | | `$warning` | Caution states, cost warnings | | `$text`, `$text-muted` | Primary and secondary text | Default theme is **Dracula**. All 17+ Textual built-in themes are supported and switchable via `/theme `. The TCSS file hierarchy follows the screen/widget module structure. ### Block Cursor and Context Menu The conversation uses a 2-column grid: a 1-character-wide cursor column on the left and the content stream on the right. The block cursor (a `▌` gutter indicator) is navigated with `alt+up`/`alt+down` and provides keyboard-driven interaction with message blocks. #### Cursor Navigation | Key | Action | |-----|--------| | `alt+up` | Move cursor to previous block | | `alt+down` | Move cursor to next block | | `space` | Expand or collapse the focused block (if expandable) | | `enter` | Open context menu for the focused block | | `escape` | Clear cursor selection, return focus to prompt | | Click on block | Position cursor on clicked block | Blocks that implement the `ExpandProtocol` (ToolCall, ActorThought, DiffView) can be toggled with `space`. The `▶` indicator (collapsed) changes to `▼` (expanded) on toggle. #### Context Menu Pressing `enter` with the block cursor on any conversation block opens a floating context menu: 
┌─ Block Actions ──────────────────────────────────────────────────────┐
│                                                                      │
│  c   Copy to clipboard                                               │
│  p   Copy to prompt                                                  │
│  e   Export as Markdown                                              │
│  v   Export as SVG (opens browser)                                   │
│  m   Maximize / restore block                                        │
│  r   Retry (ActorResponse only)                                      │
│  d   Show raw data                                                   │
│                                                                      │
│──────────────────────────────────────────────────────────────────────│
│ escape Dismiss                                                       │
└──────────────────────────────────────────────────────────────────────┘
| Action | Key | Applies To | Description | |--------|-----|-----------|-------------| | Copy to clipboard | `c` | All blocks | Copies the block's text content (Markdown source for ActorResponse, plain text for others) to the system clipboard | | Copy to prompt | `p` | All blocks | Inserts the block's text content into the prompt TextArea at the cursor position | | Export as Markdown | `e` | All blocks | Exports the block's content to a `.md` file in the current working directory | | Export as SVG | `v` | All blocks | Renders the block to an SVG file and opens it in the default browser | | Maximize / restore | `m` | ActorThought, ToolCall, DiffView | Toggles between collapsed/default height and full-screen height for the block | | Retry | `r` | ActorResponse | Re-sends the preceding user prompt to the actor, replacing this response | | Show raw data | `d` | All blocks | Shows the raw A2A message data for debugging | ### Conversation Block Details #### Tool Call States Tool calls progress through pending → completed/failed states. The expand behavior is controlled by the `tools.expand` setting: 
┌────────────────────────────────────────────────────────────────────────┐
│  Pending:                                                              │
│   🔧 local/code-analysis ⌛                         ▶                  │
│                                                                        │
│  Completed (collapsed):                                                │
│   🔧 local/code-analysis ✔                         ▶                   │
│                                                                        │
│  Completed (expanded):                                                 │
│   🔧 local/code-analysis ✔                         ▼                   │
│   ┌─ src/auth/handler.py ────────────────────────────────────────────┐ │
│   │  45 │ def login(self, req):                                      │ │
│   │  46 │     creds = extract(req)                                   │ │
│   │  47 │     return auth(creds)                                     │ │
│   └──────────────────────────────────────────────────────────────────┘ │
│                                                                        │
│  Failed:                                                               │
│   🔧 local/code-analysis ✗ failed                    ▶                 │
└────────────────────────────────────────────────────────────────────────┘
| `tools.expand` Setting | Behavior | |------------------------|----------| | `never` | All tool calls start collapsed | | `always` | All tool calls auto-expand on completion | | `success` | Only successful tool calls auto-expand | | `fail` (default) | Only failed tool calls auto-expand | | `both` | Both successful and failed auto-expand | Tool calls with `kind: "read"` (e.g., file reads, directory listings) never auto-expand regardless of setting, as they produce verbose output that would dominate the conversation. #### Actor Thought Block Actor thoughts (reasoning traces) display in a muted container with configurable visibility: 
┌──────────────────────────────────────────────────────────────────────┐
│  Collapsed (default, max 10 lines):                                  │
│  ┌──────────────────────────────────────────────────────────────┐    │
│  │ I need to analyze the authentication flow. The handler     │      │
│  │ uses a custom JWT implementation that may have...         │       │
│  │                    (8 more lines — space to expand)      │        │
│  └──────────────────────────────────────────────────────────────┘    │
│                                                                      │
│  Expanded (space or m to maximize):                                  │
│  ┌──────────────────────────────────────────────────────────────┐    │
│  │ I need to analyze the authentication flow. The handler     │      │
│  │ uses a custom JWT implementation that may have timing     │       │
│  │ vulnerabilities. Let me check the token validation...    │        │
│  │ ...(full content shown)...                              │         │
│  └──────────────────────────────────────────────────────────────┘    │
└──────────────────────────────────────────────────────────────────────┘
| Property | Value | |----------|-------| | Default height | Max 10 lines (CSS `max-height: 10`) | | Expanded height | Full content (CSS `max-height: 100vh`) | | Background | `$primary-muted 20%` | | Text style | Italic | | Toggle visibility | `agent.thoughts` setting or `ctrl+shift+t` | | Expand/collapse | `space` with block cursor, or `m` in context menu | #### Permission Question Widget When an actor requests permission for a single-file operation, a `Question` widget replaces the prompt area temporarily. For multi-file operations (diffs), the full `PermissionsScreen` is pushed instead. 
┌──────────────────────────────────────────────────────────────────────┐
│ Permission Required                                                  │
│                                                                      │
│ The actor wants to write to:                                         │
│   src/auth/handler.py                                                │
│                                                                      │
│   ❯ a  Allow once                                                    │
│     A  Allow always (this session)                                   │
│     r  Reject once                                                   │
│     R  Reject always (this session)                                  │
│                                                                      │
│ For multi-file diffs, press v to open full PermissionsScreen         │
└──────────────────────────────────────────────────────────────────────┘
| Key | Action | |-----|--------| | `a` | Allow this operation once | | `A` | Allow all operations of this type for the remainder of the session | | `r` | Reject this operation once | | `R` | Reject all operations of this type for the remainder of the session | | `v` | Open full PermissionsScreen with diff view (for file writes) | | `up` / `down` | Navigate between options | | `enter` | Select the highlighted option | The Question widget uses a blinking caret animation on the selected option to draw attention. Multiple permission requests are queued and presented sequentially — the next question appears immediately after the current one is answered. ### Prompt Architecture Detail #### History Navigation The prompt maintains two independent JSONL history files per project: | History | File Location | Trigger | |---------|--------------|---------| | Prompt history | `~/.local/state/cleveragents/history//prompt.jsonl` | `up`/`down` arrows when cursor is at first/last row of the TextArea | | Shell history | `~/.local/state/cleveragents/history//shell.jsonl` | `up`/`down` arrows in shell mode (`!`/`$` prompt) | History navigation rules: - `up` at row 0, column 0: replaces TextArea content with the previous history entry - `down` at the last row: replaces TextArea content with the next history entry (or clears to the original input if at the end) - History entries are stored as-is (including multi-line prompts) - History files are capped at 10,000 entries; oldest entries are pruned on write - Each prompt mode (normal, shell) has independent history and independent cursor position within that history #### Key Passthrough When the conversation `Window` widget has focus (e.g., during block cursor navigation), any printable character typed is forwarded to the prompt `TextArea`. This ensures the user can always start typing without explicitly focusing the prompt — the focus shifts automatically on the first printable keypress. #### Multiline Detection The prompt auto-detects multiline input and switches the prompt symbol to `☰`: | Condition | Result | |-----------|--------| | Input contains `\n` (newline character) | Switch to multiline mode | | Input contains triple backticks (` ``` `) | Switch to multiline mode | | `shift+enter` or `ctrl+j` pressed | Insert newline, switch to multiline | | All newlines removed | Revert to single-line mode | In multiline mode, `enter` inserts a newline; `ctrl+enter` submits. In single-line mode, `enter` submits. #### Shell Danger Detection When shell mode is active (`!`/`$` prefix), the prompt performs heuristic analysis of the command to detect potentially destructive operations. Dangerous commands are highlighted with `$error` styling and a warning indicator appears below the prompt: | Pattern | Risk Level | Example | |---------|-----------|---------| | `rm -rf` / `rm -r` | High | `rm -rf /` | | `chmod 777` | Medium | `chmod 777 /var/www` | | `> /dev/sda` / `dd if=` | High | `dd if=/dev/zero of=/dev/sda` | | `:(){ :\|:& };:` (fork bomb) | High | Fork bomb patterns | | `mkfs` / `fdisk` / `parted` | High | Disk formatting tools | | `kill -9` / `killall` | Medium | Process termination | | `sudo` / `su` | Low | Privilege escalation (warning only) | Danger detection is controlled by the `shell.warn_dangerous` setting (default: `true`). The detection is advisory only — it never prevents command execution. The warning text reads: `⚠ Potentially destructive command detected`. ### Notification System The TUI uses a multi-tier notification system to keep users informed across different attention contexts: #### Flash Messages (In-App) Flash messages are single-line notifications displayed between the conversation and the prompt. They auto-dismiss after the configured `ui.flash_duration` (default: 5s). | Style | CSS Class | Use Case | Example | |-------|-----------|----------|---------| | Default | `-default` | Informational | `Press ctrl+f to focus terminal` | | Success | `-success` | Positive outcomes | `✔ Plan fix-auth-bug completed ($0.08)` | | Warning | `-warning` | Caution | `⚠ Plan approaching cost limit ($4.50/$5.00)` | | Error | `-error` | Failures | `✗ Plan refactor-models failed: validation error` | #### Desktop Notifications Desktop notifications alert the user when the TUI is not in the foreground. They are delivered via the OS notification system (using `notifypy` on Linux/macOS, native `win10toast` on Windows). | Setting Value | Behavior | |--------------|----------| | `never` | Desktop notifications are disabled entirely | | `on-blur` (default) | Notifications are sent only when the terminal window does not have focus | | `always` | Notifications are sent regardless of focus state | Events that trigger desktop notifications: - Actor turn completed (response finished) - Permission requested (actor wants to perform a gated action) - Plan phase transition (idle → strategize, execute → completed, etc.) - Plan error or failure - Session cost threshold exceeded (configurable) Each notification includes: the CleverAgents icon, a title (event type), and a body (session name + brief detail). Low-severity events (informational, routine phase transitions) are suppressed by default (`notifications.hide_low_severity: true`). #### Terminal Title Management The TUI updates the terminal window title via VT escape sequences (`\033]0;...\007`) to provide at-a-glance status: | State | Title Format | Example | |-------|-------------|---------| | Idle | `◆ CleverAgents — ` | `◆ CleverAgents — Session 2` | | Actor working | `⌛ CleverAgents — ` | `⌛ CleverAgents — Session 2` | | Awaiting input | Alternates between `◆` and `👉` at 0.5s interval | Blinking title draws attention | | Permission requested | Alternates between `◆` and `🔐` at 0.5s interval | Urgent attention for permission | Title blinking is controlled by the `notifications.blink_title` setting (default: `true`). When disabled, the title updates but does not blink. #### Sound Effects Optional sound effects play on significant events (controlled by `notifications.enable_sounds` setting, default: `true`): - `turn_complete.wav` — Actor finished a response - `permission_required.wav` — Permission requested - `plan_complete.wav` — Plan reached terminal state - `error.wav` — Error or failure occurred Sound files are bundled in `src/cleveragents/tui/data/sounds/`. The notification system gracefully degrades if audio playback is unavailable (e.g., headless server). ### Clipboard Operations The TUI provides clipboard integration for copying content from the conversation and other widgets: | Operation | Trigger | Behavior | |-----------|---------|----------| | Auto-copy on selection | Mouse text selection | When `ui.auto_copy` is `true` (default), any text selected with the mouse is automatically copied to the system clipboard | | Block copy | `c` in block context menu | Copies the focused block's text content to the clipboard | | Block copy to prompt | `p` in block context menu | Inserts the focused block's text into the prompt TextArea at the cursor | | Manual copy | OS-native selection + copy (e.g., `ctrl+shift+c` in most terminals) | Standard terminal copy behavior | Clipboard access uses `pyperclip` when available, with fallback to OSC 52 escape sequences for terminal-native clipboard access (works over SSH and in tmux/screen). If neither is available, copy operations display a flash message with the content for manual copying. ### Session Persistence and Resume TUI sessions are persisted to enable resumption across TUI restarts: #### Storage Sessions are stored in an SQLite database at `~/.local/state/cleveragents/tui.db`: | Column | Type | Description | |--------|------|-------------| | `id` | TEXT (PK) | UUID matching the domain Session entity ID | | `persona_name` | TEXT | Name of the persona active when the session was last used | | `actor_identity` | TEXT | Namespaced actor identity (e.g., `anthropic/claude-4-sonnet`) | | `title` | TEXT | User-assigned or auto-generated session title | | `prompt_count` | INTEGER | Number of user prompts sent in this session | | `total_cost` | REAL | Cumulative cost in USD for this session | | `created_at` | TEXT (ISO 8601) | Session creation timestamp | | `last_used` | TEXT (ISO 8601) | Last interaction timestamp | | `project_path` | TEXT | Working directory at session creation (nullable) | | `meta_json` | TEXT | JSON blob for extensible metadata (preset, sidebar state, scroll position) | #### Resume Workflow 1. User presses `ctrl+r` (from SessionsScreen) or uses `/session:import` 2. The TUI reads the session record from SQLite 3. A new A2A Task is initiated with the stored session ID — the Application layer recognizes this as a resume request and loads the existing Session entity 4. The actor receives the session's conversation history via A2A's multi-turn interaction pattern 5. The conversation stream is populated with historical messages (rendered from stored A2A message data) 6. The persona is restored to the one stored in the session record Not all actors support session resume — actors that do not support it will start a fresh conversation. A flash warning is shown: `⚠ This actor does not support session resume. Starting fresh conversation.` ### Sessions Screen The Sessions screen (`ctrl+s`) is a modal overlay showing all active and saved sessions: 
┌─ Sessions ─────────────────────────────────────────────────────────────────────────────┐
│                                                                                        │
│  ❯ Session 2  • feature-dev  • claude-4-sonnet  • ❯ awaiting input     14:02           │
│    Last: Can you review the auth module...                                             │
│                                                                                        │
│    Session 1  • reviewer     • gpt-4o           • ⌛ working              13:58        │
│    Last: Analyze the test coverage for...                                              │
│                                                                                        │
│    Session 3  • infra-admin   • claude-4-opus    • idle                    13:45       │
│    Last: Update the terraform modules...                                               │
│                                                                                        │
│────────────────────────────────────────────────────────────────────────────────────────│
│  Saved Sessions (from previous runs)                                                   │
│                                                                                        │
│    debug-session  • feature-dev  • claude-4-sonnet  • 23 prompts  • Mar 10 09:15       │
│    refactor-v2   • reviewer     • gpt-4o           • 8 prompts   • Mar 9 16:30         │
│                                                                                        │
│────────────────────────────────────────────────────────────────────────────────────────│
│ enter Switch │ ctrl+r Resume saved │ ctrl+n New │ d Delete │ r Rename │ esc Back       │
└────────────────────────────────────────────────────────────────────────────────────────┘
The screen is divided into two sections: - **Active Sessions** (top): Currently open session tabs with their state indicators, persona, actor, and last prompt preview. The current session is highlighted with `❯`. - **Saved Sessions** (bottom): Previously persisted sessions from the SQLite database, showing prompt count and last-used timestamp. These can be resumed with `ctrl+r` or `enter`. Time formatting follows human-readable relative time: `just now`, `2m ago`, `1h ago`, or full date for >24h. ### Settings Screen The Settings screen (`F2` or `ctrl+,`) is a modal overlay with search-driven navigation through all TUI settings: 
┌─ Settings ─────────────────────────────────────────────────────────────────────────┐
│  🔍 Search: flash                                                                  │
│────────────────────────────────────────────────────────────────────────────────────│
│                                                                                    │
│  ▼ UI                                                                              │
│    Theme                   [ dracula          ]  17 themes available               │
│    Column width            [ 100              ]  Fixed column width (40-300)       │
│    Scrollbar               [ normal           ]  normal / thin / hidden            │
│    Flash duration           [ 5.0              ]  Seconds (0.5-30)                 │
│    Auto-copy on select     [ ✔                ]  Copy selected text to clipboard   │
│                                                                                    │
│  ▼ Notifications                                                                   │
│    Desktop notifications   [ on-blur          ]  never / on-blur / always          │
│    Blink terminal title    [ ✔                ]  Blink when input needed           │
│    Sound effects           [ ✔                ]  Play sounds on events             │
│                                                                                    │
│────────────────────────────────────────────────────────────────────────────────────│
│ enter Edit │ tab Next │ ctrl+s Focus search │ esc Back (auto-saves)                │
└────────────────────────────────────────────────────────────────────────────────────┘
Settings are schema-driven: each setting has a type, default value, validation rules, and description. The schema is used to auto-generate the settings UI — new settings added to the schema automatically appear in the screen. Settings are persisted as JSON in `~/.config/cleveragents/tui-settings.json` and saved automatically when the settings screen is dismissed. #### Complete Settings Schema **UI Settings** (`ui.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `ui.theme` | choices | `dracula` | 17+ Textual themes | Color theme for the entire TUI | | `ui.column` | boolean | `true` | — | Enable fixed column width for conversation content | | `ui.column_width` | integer | `100` | 40–300 | Maximum column width in characters (when `column` is true) | | `ui.scrollbar` | choices | `normal` | `normal` / `thin` / `hidden` | Scrollbar appearance for all scrollable widgets | | `ui.compact_input` | boolean | `false` | — | Remove prompt border and margin for minimal appearance | | `ui.sessions_bar` | choices | `multiple` | `always` / `multiple` / `never` | When to show the session tab bar (`multiple` = only when ≥2 sessions) | | `ui.footer` | boolean | `true` | — | Show the hotkey footer bar at the bottom | | `ui.info_bar` | boolean | `true` | — | Show the info bar below the prompt (PersonaBar) | | `ui.status_line` | boolean | `true` | — | Show token count and cost in the info bar | | `ui.flash_duration` | number | `5.0` | 0.5–30.0 | Seconds before flash messages auto-dismiss | | `ui.auto_copy` | boolean | `true` | — | Automatically copy mouse-selected text to clipboard | | `ui.prune_low_mark` | integer | `1500` | 100–10000 | Target conversation line count after pruning | | `ui.prune_excess` | integer | `1000` | 100–5000 | Lines over `prune_low_mark` that trigger pruning | | `ui.throbber` | choices | `rainbow` | `rainbow` / `quotes` | Throbber style: animated gradient or rotating text quotes | **Notification Settings** (`notifications.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `notifications.desktop` | choices | `on-blur` | `never` / `on-blur` / `always` | When to send desktop notifications | | `notifications.blink_title` | boolean | `true` | — | Blink terminal window title when input is needed | | `notifications.enable_sounds` | boolean | `true` | — | Play sound effects on events | | `notifications.turn_complete` | boolean | `true` | — | Notify when actor finishes a response | | `notifications.hide_low_severity` | boolean | `true` | — | Suppress desktop notifications for low-severity events | **Sidebar Settings** (`sidebar.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `sidebar.auto_hide` | boolean | `false` | — | Auto-hide sidebar when it loses focus (slides back on `ctrl+b`) | | `sidebar.width` | integer | `36` | 24–60 | Sidebar width in characters when in visible state | **Agent Settings** (`agent.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `agent.thoughts` | boolean | `true` | — | Show actor thinking/reasoning blocks in conversation | **Tool Settings** (`tools.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `tools.expand` | choices | `fail` | `never` / `always` / `success` / `fail` / `both` | When to auto-expand tool call results | **Shell Settings** (`shell.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `shell.command` | string | `/bin/sh` | — | Shell executable for `!` mode | | `shell.startup_commands` | text | `PS1=""` | — | Commands run at shell startup (newline-separated) | | `shell.warn_dangerous` | boolean | `true` | — | Highlight potentially dangerous commands | | `shell.allow_commands` | text | `git,ls,cat,...` | — | Commands recognized as shell (auto-switch to `$` mode) | | `shell.directory_commands` | text | `cd,rmdir` | — | Commands whose arguments are directories (for tab completion) | | `shell.file_commands` | text | `cat,less,head` | — | Commands whose arguments are files (for tab completion) | **Diff Settings** (`diff.*`) | Setting | Type | Default | Range / Choices | Description | |---------|------|---------|----------------|-------------| | `diff.view` | choices | `auto` | `unified` / `split` / `auto` | Diff display mode (`auto` selects based on available width) | ### Conversation Content Pruning Long conversations accumulate widgets that consume memory and degrade rendering performance. The TUI implements automatic content pruning to maintain responsiveness: | Parameter | Setting | Default | Description | |-----------|---------|---------|-------------| | Target line count | `ui.prune_low_mark` | 1500 | After pruning, the conversation is trimmed to approximately this many lines | | Trigger threshold | `ui.prune_excess` | 1000 | Pruning activates when the conversation exceeds `prune_low_mark + prune_excess` lines | Pruning behavior: 1. When the conversation stream exceeds 2500 lines (1500 + 1000), pruning activates 2. The oldest message blocks are removed from the DOM (not just hidden) until the line count drops to approximately `prune_low_mark` 3. A `Note` block is inserted at the top: `(Earlier messages pruned — see session history for full conversation)` 4. Pruning never removes the most recent 500 lines regardless of settings 5. Pruned messages remain in the session history (SQLite) and can be viewed via `/session:export` 6. Welcome blocks, system notes, and the current actor response are never pruned ### Safety Behaviors #### Double-Tap Quit `ctrl+c` does not immediately quit the TUI. Instead: 1. **First press**: If an actor is processing, sends an interrupt/cancel signal to the actor. If idle, shows a flash message: `Press ctrl+c again within 5s to quit` 2. **Second press within 5s**: Quits the TUI (after saving session state) 3. **Second press after 5s**: Resets — treated as a new first press `ctrl+q` always quits immediately (after saving session state) without requiring a double-tap. #### Double-Tap Escape for Terminal When a terminal widget (TerminalEmbed or ShellTerminal) has focus, a single `escape` press is ambiguous — the terminal itself may use escape sequences. The TUI requires a double-tap within 400ms: 1. **First `escape`**: Starts a 400ms timer 2. **Second `escape` within 400ms**: Exits terminal focus, returns focus to the prompt 3. **No second `escape` within 400ms**: The escape keypress is forwarded to the terminal as a normal escape sequence A flash hint appears on the first escape: `Press escape again to exit terminal`. ### Loading States The TUI supports two loading indicator styles, configurable via `ui.throbber`: | Style | Setting Value | Description | |-------|--------------|-------------| | Rainbow gradient | `rainbow` (default) | Animated horizontal bar cycling through 12 colors at 15fps (see Throbber diagram) | | Rotating quotes | `quotes` | Displays shuffled quotes from a curated collection, rotating every 3 seconds | The quotes collection contains ~200 entries drawn from science fiction (curated for relevance to AI/coding themes). Example quotes: - `"I'm sorry, Dave. I'm afraid I can't do that." — HAL 9000` - `"The only way to do great work is to love what you do." — Steve Jobs` - `"Any sufficiently advanced technology is indistinguishable from magic." — Arthur C. Clarke` Both styles occupy 1 row at the top of the screen and collapse to zero height when idle. ### Conversation Export Conversations can be exported in multiple formats: | Format | Command / Trigger | Output | |--------|------------------|--------| | JSON | `/session:export [path]` | Full session data including A2A messages, metadata, timestamps | | Markdown | `/session:export --format md [path]` | Human-readable conversation transcript with Markdown formatting | | SVG | Context menu → `v` (per block) | Single block rendered as SVG image | The JSON export format is the canonical format for `/session:import` — it contains all data needed to fully restore a session. The Markdown format is a lossy export intended for sharing and documentation. ### Hotkey Reference Hotkeys vary by the current screen and focused widget. The help panel (`F1`) always reflects the currently applicable hotkeys. #### Global Hotkeys (Available Everywhere) | Key | Action | |-----|--------| | `ctrl+q` | Quit TUI immediately (saves session state) | | `ctrl+c` | Interrupt actor / double-tap to quit (5s window) | | `F1` | Toggle help panel | | `F2` / `ctrl+,` | Open settings | | `ctrl+s` | Open Sessions screen | | `ctrl+n` | Create new session tab | | `ctrl+w` | Close current session tab | | `ctrl+[` / `ctrl+]` | Switch to previous / next session tab | | `shift+tab` | Cycle sidebar: hidden → visible → fullscreen | | `escape` | Close current overlay / modal / sidebar toward main screen | #### MainScreen — Prompt Focused | Key | Action | |-----|--------| | `enter` | Submit prompt (single-line mode) / insert newline (multi-line mode) | | `ctrl+enter` | Submit prompt (multi-line mode) | | `shift+enter` / `ctrl+j` | Insert newline (switch to multi-line mode) | | `tab` | Cycle to next persona | | `ctrl+tab` | Cycle to next argument preset | | `up` (at row 0) | Previous prompt history entry | | `down` (at last row) | Next prompt history entry | | `@` | Open Reference Picker overlay | | `/` (at position 0) | Open Slash Command overlay | | `!` or `$` (at position 0) | Activate shell mode | | `backspace` (at position 0 in shell mode) | Deactivate shell mode, return to normal | | `tab` (in shell mode) | Tab-complete file/directory path | | `ctrl+b` | Focus sidebar (when visible) | #### MainScreen — Conversation / Block Cursor | Key | Action | |-----|--------| | `alt+up` | Move block cursor to previous block | | `alt+down` | Move block cursor to next block | | `space` | Expand / collapse focused block | | `enter` | Open context menu for focused block | | `escape` | Clear block cursor, return focus to prompt | | Any printable character | Forward to prompt (key passthrough) | #### MainScreen — Block Context Menu | Key | Action | |-----|--------| | `c` | Copy block content to clipboard | | `p` | Copy block content to prompt | | `e` | Export block as Markdown file | | `v` | Export block as SVG (opens browser) | | `m` | Maximize / restore block height | | `r` | Retry prompt (ActorResponse blocks only) | | `d` | Show raw A2A message data | | `escape` | Dismiss menu | #### MainScreen — Terminal Focused | Key | Action | |-----|--------| | `escape` `escape` (within 400ms) | Exit terminal focus, return to prompt | | `ctrl+c` | Send SIGINT to terminal process | | All other keys | Forwarded to terminal PTY | #### Sidebar — Visible (Partial) | Key | Action | |-----|--------| | `tab` / `shift+tab` (within sidebar) | Navigate between Plans and Projects panels | | `enter` | Expand / collapse the highlighted collapsible section | | `up` / `down` | Navigate items within a panel | | `escape` | Dismiss sidebar, return focus to prompt | | `shift+tab` (global) | Transition to fullscreen sidebar | #### Sidebar — Fullscreen | Key | Action | |-----|--------| | `space` | Toggle selection on highlighted plan/project | | `enter` | Open detail modal (PlanDetailModal or ProjectDetailModal) | | `up` / `down` | Navigate items | | `left` / `right` | Switch between Plans and Projects columns | | `ctrl+p` | Create persona from current selection | | `ctrl+up` / `ctrl+down` | Reorder personas in the cycle list | | `d` | Delete highlighted persona from cycle list | | `/` | Open search/filter within sidebar | | `escape` | Return to visible sidebar state | #### Reference Picker Overlay | Key | Action | |-----|--------| | *typing* | Fuzzy search across projects, plans, and resources | | `enter` | Insert selected reference into prompt | | `up` / `down` | Navigate results | | `tab` | Switch between fuzzy search and tree browser modes | | `ctrl+p` | Filter to projects only | | `ctrl+l` | Filter to plans only | | `escape` | Dismiss picker, remove `@` trigger character | #### Reference Picker — Tree Browser Mode | Key | Action | |-----|--------| | `enter` | Select highlighted item as reference | | `space` | Expand / collapse tree node | | `up` / `down` | Navigate tree | | `/` | Open inline filter | | `tab` | Switch back to fuzzy search mode | | `escape` | Dismiss picker | #### Slash Command Overlay | Key | Action | |-----|--------| | *typing* | Fuzzy search commands | | `enter` | Execute selected command | | `tab` | Auto-complete command name | | `up` / `down` | Navigate command list | | `escape` | Dismiss overlay | #### Plan Detail Modal | Key | Action | |-----|--------| | `up` / `down` | Navigate decision tree nodes | | `enter` | Select decision node (show detail in right panel) | | `space` | Expand / collapse subtree | | `/` | Search within decision tree | | `c` | Correct the selected decision (opens correction dialog) | | `a` | Approve pending decision | | `r` | Reject pending decision | | `d` | Show diff for the selected decision | | `e` | Explain decision (show reasoning) | | `x` | Cancel the plan | | `escape` | Close modal | #### Project Detail Modal | Key | Action | |-----|--------| | `up` / `down` | Navigate resource tree | | `enter` | View resource details (right panel) | | `space` | Expand / collapse resource tree node | | `/` | Search within resource tree | | `i` | Show invariants for selected resource | | `v` | Show validations for selected resource | | `escape` | Close modal | #### Persona Editor Modal | Key | Action | |-----|--------| | `tab` / `shift+tab` | Navigate form fields | | `enter` | Edit the focused field / confirm selection | | `ctrl+a` | Add a new argument preset | | `ctrl+d` | Delete the selected argument preset | | `ctrl+s` | Save persona and close editor | | `escape` | Cancel and close editor (prompts to save if modified) | #### Permissions Screen | Key | Action | |-----|--------| | `j` / `down` | Next file diff | | `k` / `up` | Previous file diff | | `tab` / `shift+tab` | Cycle focus: file list → diff view → action buttons | | `a` | Allow once | | `A` | Allow always (this session) | | `r` | Reject once | | `R` | Reject always (this session) | | `d` | Toggle diff view mode: unified → split → auto | | `escape` | Reject and close (equivalent to `r`) | #### Settings Screen | Key | Action | |-----|--------| | `ctrl+s` | Focus search input | | `tab` / `shift+tab` | Navigate settings fields | | `enter` | Edit the focused setting | | `escape` | Close settings (auto-saves) | #### Sessions Screen | Key | Action | |-----|--------| | `up` / `down` | Navigate session list | | `enter` | Switch to highlighted active session / resume saved session | | `ctrl+r` | Resume a saved (historical) session | | `ctrl+n` | Create new session | | `d` | Delete highlighted session | | `r` | Rename highlighted session | | `escape` | Close sessions screen | #### Question / Permission Widget (Inline) | Key | Action | |-----|--------| | `a` | Allow once | | `A` | Allow always (this session) | | `r` | Reject once | | `R` | Reject always (this session) | | `v` | Open full Permissions Screen (for file writes) | | `up` / `down` | Navigate options | | `enter` | Select highlighted option | #### Help Panel (F1) | Key | Action | |-----|--------| | `F1` | Close help panel | | `escape` | Close help panel | | `up` / `down` | Scroll help content | ## Configuration !!! adr "Architecture Decision" The configuration system design principles, YAML-first approach, and config file conventions are defined in [ADR-024: Configuration System](adr/ADR-024-configuration-system.md). This section provides a complete reference for the YAML configuration files used to define the major configurable objects in CleverAgents: **Actors**, **Skills**, **Tools**, **Actions**, **Resource Types**, **Context Views**, and **Automation Profiles**. Projects are created via CLI commands rather than standalone configuration files, but their context views are configured through YAML and are documented here as well. It also documents the global configuration keys that control system-wide behavior. ### Global Configuration Keys !!! adr "Architecture Decision" Global configuration keys, hierarchical key structure, and config precedence are defined in [ADR-024: Configuration System](adr/ADR-024-configuration-system.md). Global configuration keys control system-wide defaults and behavior. They are stored in the global configuration file (default: `~/.cleveragents/config.toml`) and managed via the `agents config set`, `agents config get`, and `agents config list` commands. #### Hierarchical Key Structure Configuration keys use **dot-separated hierarchical names**, similar to `git config`. Each dot introduces a level of nesting, grouping related keys under a common parent. For example: 

core.format              # top-level "core" group, "format" key
core.log.level           # "core" group, "log" subgroup, "level" key
index.text.backend       # "index" group, "text" subgroup, "backend" key
The key `plan.concurrency` is **not** the same as a top-level key `concurrency` — the dot path is the full identity of the key. This means you can have `plan.concurrency` and `session.concurrency` as distinct keys without conflict. On the CLI, the full dot path is always used: 

$ agents config set core.format table
$ agents config get plan.budget.per-plan
$ agents config list plan.*
The `agents config list` command accepts an optional glob pattern to filter keys by subtree. For example, `agents config list index.*` lists all keys under the `index` group, and `agents config list provider.*` lists all provider credential keys. In the TOML configuration file, the hierarchy maps directly to TOML's native table structure. The dot-path key `index.text.backend` can be expressed equivalently as: 

# Inline dot notation (convenient for single keys)
index.text.backend = "tantivy"

# Or as nested TOML tables (better for groups)
[index.text]
backend = "tantivy"

[index.vector]
backend = "faiss"
Both forms are valid and can be mixed. The TOML parser normalizes them to the same internal representation. !!! note "Configuration Precedence (highest to lowest)" 1. ==CLI flag== (`--format`, `--data-dir`, etc.) 2. ==Environment variable== (`CLEVERAGENTS_FORMAT`, etc.) 3. ==Project-scoped config== (per-project overrides) 4. ==Global config file== (`~/.cleveragents/config.toml`) 5. ==Built-in default== #### Key Reference Keys are organized by their top-level group. Within each group, the full dot-path, type, default, corresponding environment variable, and description are provided. ##### `core.*` — Core System Settings | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `core.data-dir` | string | `~/.cleveragents` | `CLEVERAGENTS_DATA_DIR` | Root directory for all CleverAgents persistent state: database, logs, cache, sessions, checkpoints, and backups. All other paths are derived relative to this directory unless individually overridden. Overridden per-invocation by the `--data-dir` CLI flag. | | `core.config-path` | string | `/config.toml` | `CLEVERAGENTS_CONFIG_PATH` | Path to the global configuration file itself. Typically only set via environment variable or CLI flag to bootstrap an alternate configuration. Overridden per-invocation by the `--config-path` CLI flag. | | `core.format` | string | `rich` | `CLEVERAGENTS_FORMAT` | Default output rendering format for all CLI commands. Accepted values: `rich`, `color`, `table`, `plain`, `json`, `yaml`. Overridden per-invocation by the `--format` CLI flag. | | `core.namespace` | string | `local` | `CLEVERAGENTS_NAMESPACE` | The default namespace prefix applied when creating entities without an explicit namespace. For local-only usage, this is `local`. In server mode, typically the user's username or organization name. | | `core.automation-profile` | string | `supervised` | `CLEVERAGENTS_AUTOMATION_PROFILE` | The default automation profile applied to new plans when no profile is specified at the plan, action, or project level. Accepts any built-in profile name (`manual`, `review`, `supervised`, `cautious`, `trusted`, `auto`, `ci`, `full-auto`) or a custom profile name in `/` format. **Project-scopable.** | | `core.log.level` | string | `FATAL` | `CLEVERAGENTS_LOG_LEVEL` | Base logging verbosity level. Accepted values (from least to most verbose): `FATAL`, `ERROR`, `WARN`, `INFO`, `DEBUG`, `TRACE`. The default `FATAL` means only fatal errors (where the application exits) produce log output; all other log messages are suppressed. The `-v` CLI flag can be repeated (`-v` through `-vvvvv`) to raise the effective level for a single invocation: `-v` = ERROR, `-vv` = WARN, `-vvv` = INFO, `-vvvv` = DEBUG, `-vvvvv` = TRACE. The effective level applies to both log file output and terminal log output (subject to `core.log.terminal` and `core.log.file-enabled` settings). | | `core.log.dir` | string | `/logs` | `CLEVERAGENTS_LOG_DIR` | Directory where log files are written. Can be set to an alternative path to redirect log storage. | | `core.log.file-enabled` | boolean | `true` | `CLEVERAGENTS_LOG_FILE_ENABLED` | Whether log output is written to log files. When `true`, log messages at or above the effective verbosity level are written to the log directory. When `false`, log file output is suppressed entirely (useful when log output should only go to the terminal). | | `core.log.terminal` | string | `auto` | `CLEVERAGENTS_LOG_TERMINAL` | Controls whether log output raised by `-v` is also displayed on the terminal. Accepted values: `auto` (show on terminal when `-v` is used, suppress otherwise), `always` (always show log output on terminal at the effective level), `never` (suppress terminal log output entirely — log only to file). This keeps log output separate from normal program output, which goes to stdout. | | `core.log.terminal-stream` | string | `stderr` | `CLEVERAGENTS_LOG_TERMINAL_STREAM` | The stream used for terminal log output. Accepted values: `stderr` (default, keeps logs separate from normal stdout output), `stdout` (merge with normal output), or a file path / device path (e.g., `/dev/null`, `/dev/pts/1`, or a file path) to redirect terminal log output to an alternative destination. | | `core.log.retention-days` | integer | `30` | `CLEVERAGENTS_LOG_RETENTION_DAYS` | Number of days to retain log files before automatic cleanup. | | `core.backup.dir` | string | `/backups` | `CLEVERAGENTS_BACKUP_DIR` | Directory where backup snapshots are stored. | | `core.backup.retention-days` | integer | `7` | `CLEVERAGENTS_BACKUP_RETENTION_DAYS` | Number of days to retain backup snapshots created during project deletion, `agents init` resets, and plan correction history cleanup. Backups older than this are automatically purged. | | `core.cache.dir` | string | `/cache` | `CLEVERAGENTS_CACHE_DIR` | Directory for transient caches (downloaded models, tool artifacts, temporary files). | ##### `server.*` — Server Mode | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `server.url` | string | *(not set)* | `CLEVERAGENTS_SERVER_URL` | URL of the CleverAgents server for multi-user collaborative mode. When set, the CLI operates in server mode, syncing namespaced entities (actors, actions, skills, projects) with the remote server. When unset, the CLI operates in local-only mode. | | `server.token` | string | *(not set)* | `CLEVERAGENTS_SERVER_TOKEN` | Authentication token for server mode. Required when `server.url` is set. Obtained via server registration or team invite flow. Prefer the environment variable for CI environments. | | `server.sync.auto` | boolean | `true` | `CLEVERAGENTS_SERVER_SYNC_AUTO` | Whether to automatically sync entity definitions (actors, actions, skills) with the server on startup and after registration changes. When `false`, sync must be triggered manually. | | `server.sync.interval` | integer | `300` | `CLEVERAGENTS_SERVER_SYNC_INTERVAL` | Interval in seconds between automatic background syncs with the server. Only applies when `server.sync.auto` is `true`. | ##### `actor.*` — Actor Defaults | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `actor.default.strategy` | string | *(not set)* | `CLEVERAGENTS_DEFAULT_STRATEGY_ACTOR` | Default strategy actor used for plans when not specified on the action or `plan use` invocation. Must reference a registered actor in `/` format. When unset, the action's `strategy_actor` field is required. | | `actor.default.execution` | string | *(not set)* | `CLEVERAGENTS_DEFAULT_EXECUTION_ACTOR` | Default execution actor used for plans when not specified on the action or `plan use` invocation. Must reference a registered actor. When unset, the action's `execution_actor` field is required. | | `actor.default.estimation` | string | *(not set)* | `CLEVERAGENTS_DEFAULT_ESTIMATION_ACTOR` | Default estimation actor used for cost and effort estimation. Estimation is optional; when unset, plans skip the estimation step. | | `actor.default.invariant` | string | *(not set)* | `CLEVERAGENTS_DEFAULT_INVARIANT_ACTOR` | Default Invariant Reconciliation Actor used globally. When a plan enters Strategize and neither the plan, action, nor project specifies an invariant actor, this actor reconciles invariant conflicts across scopes. Must reference a registered actor. | | `actor.default.orchestrator` | string | *(not set)* | `CLEVERAGENTS_DEFAULT_ORCHESTRATOR` | Default orchestrator actor for new sessions created without an explicit `--actor` flag. | ##### `plan.*` — Plan Execution | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `plan.concurrency` | integer | `4` | `CLEVERAGENTS_PLAN_CONCURRENCY` | Maximum number of plans that can execute concurrently. When this limit is reached, new `plan execute` commands queue until a slot opens. Child plans count toward the parent's concurrency allocation, not toward the global limit. **Project-scopable.** | | `plan.max-child-depth` | integer | `5` | `CLEVERAGENTS_PLAN_MAX_CHILD_DEPTH` | Maximum nesting depth for child plan spawning. Prevents runaway recursive plan decomposition. A value of 1 means no child plans; 5 means up to 5 levels of parent-child nesting. **Project-scopable.** | | `plan.budget.per-plan` | float | *(not set)* | `CLEVERAGENTS_PLAN_BUDGET` | Maximum estimated API cost (in USD) allowed per plan. When the running cost estimate exceeds this budget, the plan pauses and requests human approval to continue. When unset, no per-plan cost limit is enforced. **Project-scopable.** | | `plan.budget.per-session` | float | *(not set)* | `CLEVERAGENTS_SESSION_BUDGET` | Maximum estimated API cost (in USD) allowed per session. When cumulative session cost exceeds this budget, all plan operations in the session pause. When unset, no per-session cost limit is enforced. | | `plan.budget.warn-threshold` | float | `0.8` | `CLEVERAGENTS_PLAN_BUDGET_WARN` | Fraction of the per-plan budget at which a warning is emitted. For example, `0.8` means a warning fires at 80% of the budget. Only effective when `plan.budget.per-plan` is set. | | `plan.tool.max-calls-per-step` | integer | `25` | `CLEVERAGENTS_TOOL_MAX_CALLS` | Maximum number of tool invocations allowed in a single actor step (one LLM turn). Prevents runaway tool loops. When the limit is reached, the actor step is interrupted and the plan pauses for human review. | | `plan.tool.max-retries` | integer | `3` | `CLEVERAGENTS_TOOL_MAX_RETRIES` | Maximum number of retry attempts for a single failing tool invocation before escalating. Applies to transient errors (network timeouts, rate limits). Non-transient errors fail immediately. | | `plan.tool.retry-backoff` | string | `exponential` | `CLEVERAGENTS_TOOL_RETRY_BACKOFF` | Retry backoff strategy for transient tool failures. Accepted values: `exponential` (doubling delay starting at 1s), `linear` (fixed 2s delay), `none` (immediate retry). | ##### `sandbox.*` — Sandbox and Checkpointing | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `sandbox.strategy` | string | `git_worktree` | `CLEVERAGENTS_SANDBOX_STRATEGY` | Default sandbox isolation strategy for the Execute phase. Accepted values: `git_worktree` (create a git worktree for isolation), `filesystem_copy` (copy the project directory), `transaction_rollback` (for database resources), `none` (no isolation — requires `require_sandbox: false` in the automation profile). Per-resource-type strategies override this default. **Project-scopable.** | | `sandbox.cleanup` | string | `on_apply` | `CLEVERAGENTS_SANDBOX_CLEANUP` | When to clean up sandbox working directories. Accepted values: `on_apply` (clean up after successful apply), `on_terminal` (clean up when plan reaches any terminal state — applied, cancelled, or failed), `manual` (never auto-clean; user must delete). | | `sandbox.checkpoint.enabled` | boolean | `true` | `CLEVERAGENTS_CHECKPOINT_ENABLED` | Whether checkpointing is enabled globally. When `true`, the Execute phase creates checkpoints before write operations, enabling rollback. When `false`, checkpointing is skipped (requires `require_checkpoints: false` in the automation profile). **Project-scopable.** | | `sandbox.checkpoint.dir` | string | `/checkpoints` | `CLEVERAGENTS_CHECKPOINT_DIR` | Directory where plan execution checkpoints are stored. Each plan gets a subdirectory named by its ULID. | | `sandbox.checkpoint.max-per-plan` | integer | `50` | `CLEVERAGENTS_CHECKPOINT_MAX` | Maximum number of checkpoints retained per plan. When exceeded, the oldest checkpoints are pruned (keeping the first and most recent). | | `sandbox.checkpoint.auto-create-on` | list | `["before_tool_execute", "after_tool_execute", "on_subplan_spawn", "on_error"]` | `CLEVERAGENTS_CHECKPOINT_AUTO_CREATE_ON` | List of automatic checkpoint triggers. `before_tool_execute` fires before each write-tool execution, `after_tool_execute` fires after, `on_subplan_spawn` fires before first subplan execution attempt, `on_error` fires when the Execute phase fails. Set to `[]` to disable all automatic checkpoints. | ##### `audit.*` — Audit Logging | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `audit.retention-days` | integer | `0` | `CLEVERAGENTS_AUDIT_RETENTION_DAYS` | Days to retain audit log entries before pruning. `0` means keep indefinitely (default for compliance). | | `audit.async` | boolean | `true` | `CLEVERAGENTS_AUDIT_ASYNC` | When `true` (default), audit entries are written asynchronously via a write-behind queue on a background daemon thread, so that `AuditService.record()` does not block the calling domain operation. Set to `false` to restore synchronous behaviour (useful for debugging or when strict ordering is required). | | `audit.queue-maxsize` | integer | `10000` | `CLEVERAGENTS_AUDIT_QUEUE_MAXSIZE` | Maximum number of pending audit entries in the write-behind queue. When the queue is full, `record()` blocks until space is available, providing back-pressure. Increase for very high-throughput workloads. Only effective when `audit.async` is `true`. | ##### `index.*` — Code Intelligence and Indexing | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `index.text.backend` | string | `tantivy` | `CLEVERAGENTS_INDEX_TEXT_BACKEND` | Backend for full-text search indexing of project resources. Accepted values: `tantivy` (recommended, high-performance Rust-based engine), `sqlite_fts` (built-in SQLite FTS5, no additional dependencies). | | `index.text.dir` | string | `/index/text` | `CLEVERAGENTS_INDEX_TEXT_DIR` | Directory where the full-text search index is stored. | | `index.vector.backend` | string | `faiss` | `CLEVERAGENTS_INDEX_VECTOR_BACKEND` | Backend for vector similarity search (semantic code search). Accepted values: `faiss` (Facebook AI Similarity Search, CPU or GPU), `qdrant` (requires a running Qdrant server), `none` (disable vector search). | | `index.vector.dir` | string | `/index/vector` | `CLEVERAGENTS_INDEX_VECTOR_DIR` | Directory where the vector index is stored (for local backends). | | `index.vector.qdrant-url` | string | *(not set)* | `CLEVERAGENTS_QDRANT_URL` | URL of the Qdrant server. Required when `index.vector.backend` is `qdrant`. | | `index.graph.backend` | string | `none` | `CLEVERAGENTS_INDEX_GRAPH_BACKEND` | Backend for the knowledge graph store (structural code relationships, RDF triples). Accepted values: `neo4j` (requires a running Neo4j server), `rdflib` (in-process Python RDF library), `none` (disable graph queries). | | `index.graph.neo4j-url` | string | *(not set)* | `CLEVERAGENTS_NEO4J_URL` | URL of the Neo4j server. Required when `index.graph.backend` is `neo4j`. | | `index.graph.neo4j-auth` | string | *(not set)* | `CLEVERAGENTS_NEO4J_AUTH` | Authentication for Neo4j in `user:password` format. Required when `index.graph.backend` is `neo4j`. | | `index.embedding.provider` | string | `openai` | `CLEVERAGENTS_EMBEDDING_PROVIDER` | Provider used for generating vector embeddings. Accepted values: `openai`, `anthropic`, `local` (uses a local sentence-transformers model). When `local`, no API key is required for embedding generation. | | `index.embedding.model` | string | `text-embedding-3-small` | `CLEVERAGENTS_EMBEDDING_MODEL` | Model identifier used for generating vector embeddings when indexing project resources. Must be a valid model for the configured `index.embedding.provider`. | | `index.embedding.dimensions` | integer | *(provider default)* | `CLEVERAGENTS_EMBEDDING_DIMENSIONS` | Number of dimensions for generated embeddings. When unset, the provider's default dimensionality for the chosen model is used. Can be reduced for faster search at the cost of accuracy. | | `index.auto-reindex` | boolean | `true` | `CLEVERAGENTS_AUTO_REINDEX` | Whether to automatically re-index project resources when files change on disk. When `true`, indexes are updated on resource add and before each Strategize phase. When `false`, re-indexing must be triggered manually. | ##### `context.*` — Context Tier Defaults These keys set the default context policy for all projects. Project-level context policies (set via `agents project context set`) override these defaults. All keys in this group are **project-scopable**. | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `context.hot.max-tokens` | integer | `16000` | `CLEVERAGENTS_CTX_HOT_TOKENS` | Default maximum token budget for hot context (the current working set loaded into the LLM context window). This is a soft cap; the actor's model context window is the hard limit. | | `context.warm.max-decisions` | integer | `100` | `CLEVERAGENTS_CTX_WARM_DECISIONS` | Default maximum number of recent decisions retained in warm context (available for retrieval but not loaded by default). | | `context.cold.max-decisions` | integer | `500` | `CLEVERAGENTS_CTX_COLD_DECISIONS` | Default maximum number of historical decisions retained in cold context (archived for audit and correction). | | `context.query.limit` | integer | `20` | `CLEVERAGENTS_CTX_QUERY_LIMIT` | Default maximum number of retrieval results returned per context query during Strategize and Execute. | | `context.query.min-relevance` | float | `0.3` | `CLEVERAGENTS_CTX_QUERY_MIN_RELEVANCE` | Minimum relevance score (0.0–1.0) for retrieval results to be included in context. Results below this threshold are discarded even if the query limit is not reached. | | `context.file.max-size` | integer | `1048576` | `CLEVERAGENTS_CTX_MAX_FILE_SIZE` | Default maximum file size (in bytes) for files included in context. Files exceeding this size are summarized or excluded. Default is 1 MB (1,048,576 bytes). | | `context.file.max-total-size` | integer | `52428800` | `CLEVERAGENTS_CTX_MAX_TOTAL_SIZE` | Default maximum total size (in bytes) across all files included in context. Default is 50 MB. | | `context.summarize.enabled` | boolean | `true` | `CLEVERAGENTS_CTX_SUMMARIZE` | Whether to summarize large context segments that exceed token limits rather than truncating them. When `true`, an LLM summarization pass produces a condensed version. When `false`, content is hard-truncated. | | `context.summarize.max-tokens` | integer | `1000` | `CLEVERAGENTS_CTX_SUMMARY_TOKENS` | Maximum number of tokens in a generated context summary. Controls the verbosity of summaries produced when `context.summarize.enabled` is `true`. | | `context.summarize.model` | string | *(uses actor's model)* | `CLEVERAGENTS_CTX_SUMMARY_MODEL` | Model to use for context summarization. When unset, the active actor's own model is used. Set this to a faster/cheaper model (e.g., a smaller variant) to reduce summarization cost. | | `context.strategies.enabled` | list | `["simple-keyword", "semantic-embedding", "breadth-depth-navigator"]` | `CLEVERAGENTS_CTX_STRATEGIES` | Ordered list of ACMS context strategies enabled globally. Strategies are run in parallel and their results fused by the Context Assembly Pipeline. | | `context.strategies.custom.*` | object | *(none)* | — | Registration block for custom context strategies. Each key under `custom` names a strategy; the value specifies its `module`, `class`, `max_quality`, and optional `config`. | | `context.strategies.arce.model` | string | *(uses actor's model)* | `CLEVERAGENTS_CTX_ARCE_MODEL` | Model used by the ARCE (Autonomous Reasoning Context Extraction) strategy for its internal reasoning loop. | | `context.strategies.arce.max-rounds` | integer | `3` | `CLEVERAGENTS_CTX_ARCE_ROUNDS` | Maximum number of search-refine rounds the ARCE strategy performs before returning results. | | `context.strategies.breadth-depth-navigator.max-hops` | integer | `4` | `CLEVERAGENTS_CTX_BDN_HOPS` | Maximum graph traversal depth for the breadth-depth-navigator strategy. | | `context.budget.response-reserve-tokens` | integer | `4096` | `CLEVERAGENTS_CTX_RESPONSE_RESERVE` | Number of tokens reserved from the model's context window for the response. Subtracted before computing the context budget. | | `context.budget.tool-definition-estimate` | integer | *(auto-computed)* | `CLEVERAGENTS_CTX_TOOL_ESTIMATE` | Estimated tokens consumed by tool definitions in the prompt. When unset, computed from the active skill set. | | `context.budget.skeleton-ratio` | float | `0.15` | `CLEVERAGENTS_CTX_SKELETON_RATIO` | Default fraction of the context budget reserved for inherited plan skeleton context. | | `context.budget.refresh-threshold` | float | `0.30` | `CLEVERAGENTS_CTX_REFRESH_THRESHOLD` | Fractional change in available budget that triggers automatic context re-assembly. E.g., `0.30` means re-assemble when budget changes by more than 30%. | | `context.budget.min-useful-budget` | integer | `500` | `CLEVERAGENTS_CTX_MIN_BUDGET` | Minimum useful context budget in tokens. If the computed budget falls below this, context assembly is skipped and a warning is emitted. | | `context.tiers.warm.retention-hours` | integer | `24` | `CLEVERAGENTS_CTX_WARM_HOURS` | Number of hours warm-tier context entries are retained before demotion to cold tier. | | `context.tiers.cold.retention-days` | integer | `90` | `CLEVERAGENTS_CTX_COLD_DAYS` | Number of days cold-tier context entries are retained before archival/expiry. | | `context.uko.default-analyzers` | list | `["python", "typescript", "rust", "java", "markdown", "json-schema"]` | `CLEVERAGENTS_CTX_UKO_ANALYZERS` | List of UKO analyzers enabled by default for resource indexing. Each analyzer extracts language-specific UKO nodes from resources. | | `context.uko.analyzers.custom.*` | object | *(none)* | — | Registration block for custom UKO analyzers. Each key under `custom` names an analyzer; the value specifies its `module`, `class`, `languages`, and optional `config`. | | `context.pipeline.strategy-selector` | string | `"builtin:ConfidenceWeightedSelector"` | `CLEVERAGENTS_CTX_PIPELINE_SELECTOR` | Implementation class for the StrategySelector pipeline component. Decides which strategies to invoke and with what confidence. Value is `"module:ClassName"`. | | `context.pipeline.budget-allocator` | string | `"builtin:ProportionalBudgetAllocator"` | `CLEVERAGENTS_CTX_PIPELINE_ALLOCATOR` | Implementation class for the BudgetAllocator pipeline component. Distributes token budget across selected strategies. | | `context.pipeline.strategy-executor` | string | `"builtin:ParallelStrategyExecutor"` | `CLEVERAGENTS_CTX_PIPELINE_EXECUTOR` | Implementation class for the StrategyExecutor pipeline component. Controls parallelism, timeouts, and circuit breaking for strategy invocation. | | `context.pipeline.fragment-deduplicator` | string | `"builtin:ContentHashDeduplicator"` | `CLEVERAGENTS_CTX_PIPELINE_DEDUP` | Implementation class for the FragmentDeduplicator pipeline component. Removes duplicate fragments via content-hash, UKO-identity, or semantic similarity. | | `context.pipeline.detail-depth-resolver` | string | `"builtin:MaxDepthResolver"` | `CLEVERAGENTS_CTX_PIPELINE_DEPTH` | Implementation class for the DetailDepthResolver pipeline component. Resolves conflicts when the same UKO node appears at different detail depths. | | `context.pipeline.fragment-scorer` | string | `"builtin:WeightedCompositeScorer"` | `CLEVERAGENTS_CTX_PIPELINE_SCORER` | Implementation class for the FragmentScorer pipeline component. Computes composite relevance scores for ranking during budget packing. | | `context.pipeline.budget-packer` | string | `"builtin:GreedyKnapsackPacker"` | `CLEVERAGENTS_CTX_PIPELINE_PACKER` | Implementation class for the BudgetPacker pipeline component. Fits scored fragments into the token budget with depth fallback support. | | `context.pipeline.fragment-orderer` | string | `"builtin:RelevanceCoherenceOrderer"` | `CLEVERAGENTS_CTX_PIPELINE_ORDERER` | Implementation class for the FragmentOrderer pipeline component. Orders packed fragments for optimal coherence in the context window. | | `context.pipeline.preamble-generator` | string | `"builtin:ProvenancePreambleGenerator"` | `CLEVERAGENTS_CTX_PIPELINE_PREAMBLE` | Implementation class for the PreambleGenerator pipeline component. Generates provenance summaries prepended to assembled context. | | `context.pipeline.skeleton-compressor` | string | `"builtin:DepthReductionCompressor"` | `CLEVERAGENTS_CTX_PIPELINE_COMPRESSOR` | Implementation class for the SkeletonCompressor pipeline component. Compresses parent context into skeleton for child plan inheritance. | | `context.pipeline.strategy-executor.timeout-seconds` | integer | `30` | `CLEVERAGENTS_CTX_PIPELINE_EXEC_TIMEOUT` | Timeout in seconds for each strategy execution within the StrategyExecutor. | | `context.pipeline.strategy-executor.max-workers` | integer | `4` | `CLEVERAGENTS_CTX_PIPELINE_EXEC_WORKERS` | Maximum number of parallel workers for concurrent strategy execution. | | `context.pipeline.strategy-executor.circuit-breaker-threshold` | integer | `3` | `CLEVERAGENTS_CTX_PIPELINE_EXEC_CB` | Number of consecutive failures before the circuit breaker opens for a strategy. | | `context.pipeline.fragment-scorer.relevance-weight` | float | `0.4` | `CLEVERAGENTS_CTX_PIPELINE_SCORER_REL` | Weight of relevance score in composite fragment scoring. | | `context.pipeline.fragment-scorer.hierarchy-weight` | float | `0.3` | `CLEVERAGENTS_CTX_PIPELINE_SCORER_HIER` | Weight of hierarchy position in composite fragment scoring. | | `context.pipeline.fragment-scorer.quality-weight` | float | `0.2` | `CLEVERAGENTS_CTX_PIPELINE_SCORER_QUAL` | Weight of strategy quality in composite fragment scoring. | | `context.pipeline.fragment-scorer.recency-weight` | float | `0.1` | `CLEVERAGENTS_CTX_PIPELINE_SCORER_REC` | Weight of recency bonus in composite fragment scoring. | | `context.pipeline.budget-packer.depth-fallback-steps` | list | `[9, 4, 2, 0]` | `CLEVERAGENTS_CTX_PIPELINE_PACKER_STEPS` | Ordered list of detail depths to try during depth fallback when a fragment doesn't fit at its current depth. | | `context.pipeline.budget-packer.min-fragment-tokens` | integer | `10` | `CLEVERAGENTS_CTX_PIPELINE_PACKER_MIN` | Minimum token size for a fragment to be included. Fragments below this threshold are excluded. | | `context.pipeline.preamble-generator.enabled` | boolean | `true` | `CLEVERAGENTS_CTX_PIPELINE_PREAMBLE_ON` | Whether the PreambleGenerator produces a preamble. When `false`, no preamble is prepended to assembled context. | | `context.pipeline.preamble-generator.max-tokens` | integer | `200` | `CLEVERAGENTS_CTX_PIPELINE_PREAMBLE_TOK` | Maximum tokens allocated to the context preamble. | ##### `provider.*` — LLM Provider Credentials Provider credential keys follow the pattern `provider..`. Each provider has an `api-key` field and may have additional fields for endpoint configuration. Environment variables for provider keys use standard naming conventions compatible with existing tooling (e.g., `OPENAI_API_KEY`). | Key | Type | Default | Env Variable | Description | |-----|------|---------|-------------|-------------| | `provider.openai.api-key` | string | *(not set)* | `OPENAI_API_KEY` | API key for OpenAI models. Required when using OpenAI-based actors or the default embedding provider. The standard `OPENAI_API_KEY` environment variable is checked for compatibility with existing tooling. | | `provider.openai.org-id` | string | *(not set)* | `OPENAI_ORG_ID` | OpenAI organization ID. Optional; used when the API key belongs to multiple organizations. | | `provider.openai.base-url` | string | *(not set)* | `OPENAI_BASE_URL` | Custom base URL for OpenAI-compatible APIs (e.g., a local proxy or alternative provider). When unset, the official OpenAI API URL is used. | | `provider.anthropic.api-key` | string | *(not set)* | `ANTHROPIC_API_KEY` | API key for Anthropic models. Required when using Anthropic-based actors. | | `provider.google.api-key` | string | *(not set)* | `GOOGLE_API_KEY` | API key for Google AI models. Required when using Google-based actors. | | `provider.azure.endpoint` | string | *(not set)* | `AZURE_OPENAI_ENDPOINT` | Azure OpenAI endpoint URL. Required when using Azure-hosted OpenAI models. | | `provider.azure.api-key` | string | *(not set)* | `AZURE_OPENAI_API_KEY` | API key for Azure OpenAI. Required alongside `provider.azure.endpoint`. | | `provider.azure.api-version` | string | `2024-02-01` | `AZURE_OPENAI_API_VERSION` | Azure OpenAI API version string. | | `provider.google.gemini-api-key` | string | *(not set)* | `GEMINI_API_KEY` | API key for Google Gemini models. Required when using Gemini-based actors. The standard `GEMINI_API_KEY` environment variable is checked for compatibility with Google's tooling. | | `provider.huggingface.token` | string | *(not set)* | `HF_TOKEN` | Access token for Hugging Face Inference API. Required when using Hugging Face-hosted models. The standard `HF_TOKEN` environment variable is checked for compatibility with Hugging Face tooling. | | `provider.openrouter.api-key` | string | *(not set)* | `OPENROUTER_API_KEY` | API key for OpenRouter. Required when using OpenRouter as a provider. | #### Configuration Scoping Several keys support **project-scoped** values in addition to the global default. When a project-scoped value is set, it applies only to plans targeting that project. Keys marked **Project-scopable** in the reference above support this feature. The full dot path is used identically in both global and project-scoped contexts: 

# Set a global default
$ agents config set core.automation-profile trusted

# Override for a specific project — same key, scoped to the project
$ agents config set core.automation-profile manual --project local/production-api

# Project-scoped keys under any group work the same way
$ agents config set plan.budget.per-plan 2.00 --project local/production-api
$ agents config set sandbox.strategy git_worktree --project local/production-api
$ agents config set context.hot.max-tokens 32000 --project local/large-codebase
The full list of project-scopable keys: `core.automation-profile`, `plan.concurrency`, `plan.max-child-depth`, `plan.budget.per-plan`, `sandbox.strategy`, `sandbox.checkpoint.enabled`, and all keys under `context.*`. #### Resolution Order When resolving the effective value of a configuration key, the following precedence applies (highest to lowest): 1. **CLI flag**: Per-invocation overrides (e.g., `--format` maps to `core.format`, `--data-dir` maps to `core.data-dir`). Highest priority. 2. **Environment variable**: The mapped `CLEVERAGENTS_*` variable or provider-specific variable (e.g., `OPENAI_API_KEY` for `provider.openai.api-key`). 3. **Project-scoped config**: For project-scopable keys, the value set via `agents config set --project `. Only applies in contexts where a project is known (e.g., during plan execution). 4. **Global config file**: The value in the config file at the path specified by `core.config-path`. 5. **Built-in default**: The hardcoded default value. The `agents config get ` command displays the full resolution chain, showing which level provided the winning value. Listing subtrees is supported: 

# Show the full resolution chain for a single key
$ agents config get sandbox.checkpoint.enabled

# List all keys in a group
$ agents config list index.*

# List all keys with their current effective values
$ agents config list
#### Configuration File Format The global configuration file uses TOML format. The hierarchical key structure maps naturally to TOML tables. A typical `config.toml` after initial setup: 

# ~/.cleveragents/config.toml

[core]
data-dir = "/home/alex/.cleveragents"
format = "rich"
namespace = "local"
automation-profile = "supervised"

[core.log]
level = "FATAL"
terminal = "auto"
terminal-stream = "stderr"
file-enabled = true
retention-days = 30

[core.backup]
retention-days = 7

[server]
# url = "https://agents.example.com"
# token = "tok_01HXR..."

[actor.default]
strategy = "local/strategist"
execution = "local/executor"
invariant = "local/invariant-resolver"
# estimation = "local/estimator"
# orchestrator = "local/orchestrator"

[plan]
concurrency = 4
max-child-depth = 5

[plan.budget]
per-plan = 5.00
per-session = 25.00
warn-threshold = 0.8

[plan.tool]
max-calls-per-step = 25
max-retries = 3
retry-backoff = "exponential"

[sandbox]
strategy = "git_worktree"
cleanup = "on_apply"

[sandbox.checkpoint]
enabled = true
max-per-plan = 50

[index.text]
backend = "tantivy"

[index.vector]
backend = "faiss"

[index.graph]
backend = "none"

[index.embedding]
provider = "openai"
model = "text-embedding-3-small"

[context.hot]
max-tokens = 16000

[context.warm]
max-decisions = 100

[context.cold]
max-decisions = 500

[context.query]
limit = 20
min-relevance = 0.3

[context.file]
max-size = 1048576
max-total-size = 52428800

[context.summarize]
enabled = true
max-tokens = 1000

# Provider keys — prefer environment variables for secrets
[provider.openai]
# api-key = "sk-..."

[provider.anthropic]
# api-key = "sk-ant-..."

# Project-scoped overrides
[project."local/production-api"]
"core.automation-profile" = "manual"
"plan.budget.per-plan" = 2.00
"sandbox.strategy" = "git_worktree"
"sandbox.checkpoint.enabled" = true

[project."local/docs"]
"core.automation-profile" = "auto"
"plan.budget.per-plan" = 10.00
"context.hot.max-tokens" = 32000
### Design Principles All CleverAgents configuration files share a consistent set of design principles: 1. **YAML-first**: All configuration files use YAML syntax. JSON is also accepted where a configuration file is loaded (since valid JSON is valid YAML), but YAML is the canonical format for human-authored configurations. 2. **Namespace/Name convention**: Every configurable entity follows the `/` naming convention. The `local/` namespace is reserved for local-only items. User namespaces (`/`) and organization namespaces (`/`) are stored on the server. Built-in entities use provider namespaces (e.g., `openai/`, `anthropic/`). 3. **Config-as-complete-definition pattern**: For entity registration commands (`actor add`, `skill add`, `tool add`, `validation add`, `resource type add`, `action create`, `automation-profile add`), the YAML configuration file is the **sole source of truth** — the `--config` file fully defines the entity. For runtime commands that reference existing entities (e.g., `plan use`), CLI options may override entity defaults to customize behavior per-invocation. **Exception**: `validation add` accepts `--required`/`--informational` flags that override the YAML `mode` field, as described in the Validation Mode section under Core Concepts. 4. **Environment variable interpolation**: All configuration files support `${ENV_VAR}` and `${ENV_VAR:default_value}` syntax for environment variable interpolation. If a variable is not set and no default is provided, an error is raised. Boolean strings (`true`/`false`) and numeric strings are automatically converted to their native types. 5. **Jinja2 template support**: Actor configuration files support Jinja2 template syntax within string values (particularly `system_prompt` fields). Template placeholders like `{{ context.project_name }}` are preserved during YAML parsing and rendered at runtime. 6. **Idempotent registration**: Adding an entity that already exists fails unless `--update` is provided. This prevents accidental overwrites while allowing intentional updates. 7. **Declarative structure**: Configuration files are declarative — they describe *what* should exist, not *how* to create it. The system handles all lifecycle management. 8. **Schema version**: Configuration files may include a top-level `cleveragents.version` field to indicate which schema version they target (currently `"3.0"`). When omitted, the latest schema version is assumed. --- ### Actor Configuration Files !!! adr "Architecture Decision" The actor configuration schema and actor registration model are defined in [ADR-010: Actor and Agent Architecture](adr/ADR-010-actor-and-agent-architecture.md). Actor configuration files define intelligent agents — anything conversational, from a single LLM to an entire graph of interconnected actors and tools. Actors are registered via `agents actor add --config `. For behavioral documentation including Jinja2 template preprocessing, actor composition, multi-actor workflows, and field-level descriptions, see the [Actor](#actor) section. For the Jinja2 preprocessing pipeline specifically, see [Jinja2 Template Preprocessing](#jinja2-template-preprocessing) and [ADR-032](adr/ADR-032-jinja2-yaml-template-preprocessing.md). #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for actor configuration files. Since YAML is a superset of JSON, this schema can be used directly to validate actor YAML files using any JSON Schema validator. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/actor-config.json",
  "title": "CleverAgents Actor Configuration",
  "description": "Configuration file schema for defining CleverAgents actors — intelligent agents composed of LLMs, tools, and graph topologies.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-z0-9_-]+/[a-z0-9_-]+$",
      "description": "Namespaced actor name in <namespace>/<name> format (e.g., 'local/reviewer', 'myorg/deploy-agent'). Required. When the actor is added via the CLI, this value is used as the registered name."
    },
    "cleveragents": {
      "type": "object",
      "description": "Metadata block containing schema version, logging, template engine, and safety settings.",
      "properties": {
        "version": {
          "type": "string",
          "description": "Schema version for this configuration file.",
          "default": "3.0"
        },
        "logging": {
          "type": "object",
          "properties": {
            "level": {
              "type": "string",
              "enum": ["DEBUG", "INFO", "WARNING", "ERROR"],
              "default": "INFO",
              "description": "Logging level."
            }
          },
          "additionalProperties": false
        },
        "template_engine": {
          "type": "string",
          "enum": ["JINJA2", "NONE"],
          "default": "JINJA2",
          "description": "Template engine for string interpolation."
        },
        "unsafe": {
          "type": "boolean",
          "default": false,
          "description": "When true, allows actors to perform operations flagged as unsafe. Requires --unsafe CLI flag."
        },
        "default_actor": {
          "type": "string",
          "description": "Name of the default actor when multiple actors are defined."
        }
      },
      "additionalProperties": false
    },
    "actors": {
      "$ref": "#/$defs/actorMap"
    },
    "agents": {
      "$ref": "#/$defs/actorMap",
      "description": "Alias for 'actors'. Both keys are accepted; use one or the other."
    },
    "routes": {
      "type": "object",
      "description": "Map of route names to their definitions. Routes connect actors via stream or graph topologies.",
      "additionalProperties": {
        "$ref": "#/$defs/route"
      }
    },
    "merges": {
      "type": "array",
      "description": "Stream merge operations combining multiple streams into one.",
      "items": {
        "type": "object",
        "properties": {
          "sources": {
            "type": "array",
            "items": { "type": "string" },
            "description": "Source stream names to merge."
          },
          "target": {
            "type": "string",
            "description": "Target stream name for merged output."
          }
        },
        "required": ["sources", "target"],
        "additionalProperties": false
      }
    },
    "splits": {
      "type": "array",
      "description": "Stream split operations dividing one stream into multiple.",
      "items": {
        "type": "object",
        "properties": {
          "source": {
            "type": "string",
            "description": "Source stream name to split."
          },
          "targets": {
            "type": "array",
            "items": { "type": "string" },
            "description": "Target stream names for split output."
          }
        },
        "required": ["source", "targets"],
        "additionalProperties": false
      }
    },
    "templates": {
      "type": "object",
      "description": "Reusable template definitions for Jinja2 template inheritance.",
      "additionalProperties": true
    },
    "instances": {
      "type": "object",
      "description": "Instantiated templates with bound parameters.",
      "additionalProperties": true
    },
    "global_context": {
      "type": "object",
      "description": "Key-value pairs available to all actors via {{ context.key }} in templates.",
      "additionalProperties": true
    },
    "prompts": {
      "type": "object",
      "description": "Named prompt templates that can be referenced by actors.",
      "additionalProperties": { "type": "string" }
    },
    "pipelines": {
      "type": "object",
      "description": "Hybrid pipeline definitions combining stream and graph stages.",
      "additionalProperties": {
        "type": "object",
        "properties": {
          "stages": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "name": { "type": "string" },
                "type": { "type": "string" },
                "config": { "type": "object", "additionalProperties": true }
              },
              "required": ["name", "type"]
            }
          },
          "metadata": { "type": "object", "additionalProperties": true }
        },
        "required": ["stages"]
      }
    }
  },
  "required": ["name"],
  "oneOf": [
    { "required": ["actors"] },
    { "required": ["agents"] }
  ],
  "additionalProperties": false,
  "$defs": {
    "actorMap": {
      "type": "object",
      "description": "Map of actor names to their definitions.",
      "additionalProperties": {
        "$ref": "#/$defs/actorDefinition"
      }
    },
    "actorDefinition": {
      "type": "object",
      "description": "A single actor definition.",
      "properties": {
        "type": {
          "type": "string",
          "enum": ["llm", "tool"],
          "description": "Actor type: 'llm' for language model actors, 'tool' for tool-based actors."
        },
        "config": {
          "type": "object",
          "description": "Actor configuration. Fields depend on actor type.",
          "properties": {
            "provider": {
              "type": "string",
              "description": "LLM provider identifier: openai, anthropic, google, azure, openrouter, etc."
            },
            "model": {
              "type": "string",
              "description": "Model identifier within the provider: gpt-4, claude-3.5-sonnet, gemini-pro, etc."
            },
            "actor": {
              "type": "string",
              "description": "Combined provider/model format (e.g., 'anthropic/claude-3.5-sonnet'). Alternative to specifying provider and model separately."
            },
            "system_prompt": {
              "type": "string",
              "description": "System prompt text. Supports Jinja2 template syntax for dynamic content."
            },
            "temperature": {
              "type": "number",
              "minimum": 0.0,
              "maximum": 2.0,
              "description": "Sampling temperature. Lower values are more deterministic."
            },
            "max_tokens": {
              "type": "integer",
              "minimum": 1,
              "description": "Maximum number of tokens in the generated response."
            },
            "memory_enabled": {
              "type": "boolean",
              "default": false,
              "description": "Enable conversation memory for multi-turn interactions."
            },
            "max_history": {
              "type": "integer",
              "default": 50,
              "minimum": 1,
              "description": "Maximum number of conversation turns retained in memory."
            },
            "unsafe": {
              "type": "boolean",
              "default": false,
              "description": "Allow this specific actor to perform unsafe operations."
            },
            "options": {
              "type": "object",
              "description": "Provider-specific options passed through to the underlying LLM API.",
              "additionalProperties": true
            },
            "tools": {
              "type": "array",
              "description": "List of inline tool definitions for tool-type actors.",
              "items": {
                "type": "object",
                "properties": {
                  "name": {
                    "type": "string",
                    "description": "Tool name."
                  },
                  "code": {
                    "type": "string",
                    "description": "Inline Python code defining the tool's behavior."
                  }
                },
                "required": ["name", "code"],
                "additionalProperties": false
              }
            },
            "response_format": {
              "type": "object",
              "description": "JSON schema for structured output from the LLM. When set, the model is constrained to produce output matching this schema.",
              "additionalProperties": true
            }
          },
          "additionalProperties": false
        },
        "skills": {
          "type": "array",
          "description": "List of skill names this actor can use. Each entry is a namespaced skill name (e.g., 'local/file-ops'). Skills provide tool capabilities to the actor.",
          "items": { "type": "string", "pattern": "^[a-z0-9_-]+/[a-z0-9_-]+$" }
        },
        "lsp": {
          "description": "LSP server bindings for language intelligence. Can be a list of server names (explicit), an object with languages (language-based), or an object with auto: true (resource-auto).",
          "oneOf": [
            {
              "type": "array",
              "items": { "type": "string", "pattern": "^[a-z0-9_-]+/[a-z0-9_-]+$" },
              "description": "Explicit binding: list of namespaced LSP server names."
            },
            {
              "type": "object",
              "properties": {
                "languages": {
                  "type": "array",
                  "items": { "type": "string" },
                  "description": "Language-based binding: resolve LSP servers for these languages from the registry."
                },
                "auto": {
                  "type": "boolean",
                  "description": "Resource-auto binding: discover languages from project resources and resolve servers automatically."
                }
              },
              "additionalProperties": false
            }
          ]
        },
        "lsp_capabilities": {
          "description": "Controls which LSP capabilities are exposed as tools. When 'all' or omitted, all capabilities are available.",
          "oneOf": [
            {
              "type": "string",
              "enum": ["all"]
            },
            {
              "type": "array",
              "items": {
                "type": "string",
                "enum": ["diagnostics", "hover", "completions", "definitions", "references", "rename", "code_actions", "formatting", "signature_help", "document_symbols", "workspace_symbols"]
              }
            }
          ]
        },
        "lsp_context_enrichment": {
          "type": "object",
          "description": "Controls automatic LSP context enrichment (diagnostic and type info injection into ACMS context).",
          "properties": {
            "diagnostics": { "type": "boolean", "default": true, "description": "Auto-inject LSP diagnostics into context." },
            "type_annotations": { "type": "boolean", "default": false, "description": "Auto-inject type information into context." },
            "max_diagnostics_per_file": { "type": "integer", "default": 50, "minimum": 1, "description": "Maximum diagnostics per file to avoid context bloat." }
          },
          "additionalProperties": false
        }
      },
      "required": ["type", "config"],
      "additionalProperties": false
    },
    "route": {
      "type": "object",
      "description": "A route definition — either a stream or a graph topology.",
      "properties": {
        "type": {
          "type": "string",
          "enum": ["stream", "graph"],
          "description": "Route type."
        },
        "stream_type": {
          "type": "string",
          "enum": ["cold", "hot", "replay"],
          "default": "cold",
          "description": "Stream type (stream routes only)."
        },
        "operators": {
          "type": "array",
          "description": "Processing operators (stream routes).",
          "items": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": ["map", "graph_execute"],
                "description": "Operator type."
              },
              "params": {
                "type": "object",
                "properties": {
                  "agent": { "type": "string", "description": "Actor name for map operators." },
                  "graph": { "type": "string", "description": "Graph route name for graph_execute operators." }
                },
                "additionalProperties": true
              }
            },
            "required": ["type"]
          }
        },
        "subscriptions": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Input stream subscriptions."
        },
        "publications": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Output stream publications."
        },
        "agents": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Actor names used by this route."
        },
        "initial_value": {
          "description": "Initial stream value."
        },
        "buffer_size": {
          "type": "integer",
          "default": 10,
          "minimum": 1,
          "description": "Stream buffer size."
        },
        "template_config": {
          "type": "object",
          "description": "Template-specific configuration.",
          "additionalProperties": true
        },
        "bridge": {
          "type": "object",
          "description": "Bridge configuration for stream-to-graph upgrades.",
          "properties": {
            "upgrade_conditions": { "type": "object", "additionalProperties": true },
            "downgrade_conditions": { "type": "object", "additionalProperties": true },
            "state_extractor": { "type": "string" },
            "state_flattener": { "type": "string" },
            "preserve_subscriptions": { "type": "boolean", "default": true },
            "preserve_checkpointing": { "type": "boolean", "default": true }
          },
          "additionalProperties": false
        },
        "metadata": {
          "type": "object",
          "additionalProperties": true
        },
        "nodes": {
          "type": "object",
          "description": "Graph nodes (required for graph routes).",
          "additionalProperties": {
            "$ref": "#/$defs/graphNode"
          }
        },
        "edges": {
          "type": "array",
          "description": "Graph edges (required for graph routes).",
          "items": {
            "$ref": "#/$defs/graphEdge"
          }
        },
        "entry_point": {
          "type": "string",
          "description": "Entry point node name (required for graph routes)."
        },
        "checkpointing": {
          "type": "boolean",
          "default": false,
          "description": "Enable graph checkpointing."
        },
        "checkpoint_dir": {
          "type": "string",
          "description": "Directory for checkpoint storage."
        },
        "enable_time_travel": {
          "type": "boolean",
          "default": false,
          "description": "Enable time travel debugging."
        },
        "parallel_execution": {
          "type": "boolean",
          "default": false,
          "description": "Allow parallel node execution."
        },
        "state_class": {
          "type": "string",
          "description": "Custom state class name."
        }
      },
      "required": ["type"],
      "additionalProperties": false
    },
    "graphNode": {
      "type": "object",
      "description": "A graph node definition.",
      "properties": {
        "type": {
          "type": "string",
          "enum": ["agent", "function", "tool", "conditional", "subgraph", "start", "end", "message_router"],
          "description": "Node type."
        },
        "agent": { "type": "string", "description": "Actor name for agent nodes." },
        "function": { "type": "string", "description": "Function name for function nodes." },
        "tools": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Tool references for tool nodes."
        },
        "condition": { "type": "object", "additionalProperties": true, "description": "Condition for conditional nodes." },
        "subgraph": { "type": "string", "description": "Route name for subgraph nodes." },
        "retry_policy": { "type": "object", "additionalProperties": true, "description": "Retry configuration." },
        "timeout": { "type": "integer", "minimum": 1, "description": "Timeout in seconds." },
        "parallel": { "type": "boolean", "default": false, "description": "Allow parallel execution." },
        "metadata": { "type": "object", "additionalProperties": true }
      },
      "required": ["type"],
      "additionalProperties": false
    },
    "graphEdge": {
      "type": "object",
      "description": "A graph edge connecting two nodes.",
      "properties": {
        "source": { "type": "string", "description": "Source node name." },
        "target": { "type": "string", "description": "Target node name." },
        "condition": { "type": "object", "additionalProperties": true, "description": "Edge condition for conditional routing." },
        "metadata": { "type": "object", "additionalProperties": true }
      },
      "required": ["source", "target"],
      "additionalProperties": false
    }
  }
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations (comments, `` syntax, and `|` alternatives) to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Name ───────────────────────────────────────────────────────────
name: <namespace>/<actor-name>       # Namespaced actor name (required). Used as the registered name.
                                    # Must follow <namespace>/<name> format (e.g., local/reviewer).

# ─── Metadata ───────────────────────────────────────────────────────
cleveragents:
  version: "3.0"                    # Schema version (optional, default: latest)
  logging:
    level: "INFO"                   # Log level: DEBUG, INFO, WARNING, ERROR (optional)
  template_engine: "JINJA2"         # Template engine: JINJA2 or NONE (optional, default: JINJA2)
  unsafe: false                     # Allow unsafe operations (optional, default: false)
  default_actor: <actor_name>       # Default actor to use when multiple are defined (optional)

# ─── Actor Definitions ──────────────────────────────────────────────
# The top-level key can be either "actors" or "agents" (both accepted).
actors:
  <actor_name>:
    type: llm | tool                # Actor type (required)
    config:
      # ── For type: llm ──────────────────────────────────────────
      provider: <string>            # Provider identifier: openai, anthropic, google, azure, openrouter, etc. (required for LLM)
      model: <string>               # Model identifier: gpt-4, claude-3.5-sonnet, etc. (required for LLM)
      # OR use the combined format:
      actor: "<provider>/<model>"   # Combined provider/model (alternative to provider + model)

      system_prompt: |              # System prompt text, supports Jinja2 templates (optional)
        You are a helpful assistant.
        Project: {{ context.project_name }}
      temperature: 0.7              # Sampling temperature 0.0-2.0 (optional, default: provider default)
      max_tokens: 4096              # Maximum output tokens (optional, default: provider default)
      memory_enabled: true          # Enable conversation memory (optional, default: false)
      max_history: 50               # Maximum conversation turns to retain (optional, default: 50)
      unsafe: false                 # Allow unsafe operations for this actor (optional, default: false)
      options:                      # Additional provider-specific options (optional)
        top_p: 1.0
        frequency_penalty: 0.0
        presence_penalty: 0.0
        stop_sequences: ["END"]
        seed: 42

      # ── For type: tool ─────────────────────────────────────────
      tools:
        - name: <tool_name>         # Tool name (required per tool)
          code: |                   # Inline Python code (required per tool)
            def run(input_data):
                return {"result": input_data["query"]}

      response_format: {}            # JSON schema for structured LLM output (optional, LLM only)

    # ── Skills (both LLM and tool actors) ────────────────────────
    skills:                           # Skill references providing tool capabilities (optional)
      - <namespace>/<skill-name>    # e.g., local/file-ops, local/git-ops

    # ── LSP Binding (language intelligence for actor nodes) ─────
    # Three binding modes — pick one:

    # Mode 1: Explicit — list specific registered LSP servers
    lsp:                              # LSP server binding (optional)
      - <namespace>/<server-name>  # e.g., local/pyright, local/typescript-language-server

    # Mode 2: Language-based — runtime resolves servers from registry
    # lsp:
    #   languages: [python, typescript]

    # Mode 3: Auto-discovery — detect languages from project resources
    # lsp:
    #   auto: true

    lsp_capabilities: all              # Which LSP capabilities to expose (optional, default: all)
                                      # "all" | list of: diagnostics, hover, completions, references,
                                      #   definitions, symbols, formatting, code_actions, rename

    lsp_context_enrichment:            # ACMS context enrichment from LSP (optional)
      diagnostics: true               # Auto-inject diagnostics into code context windows
      type_annotations: true          # Auto-inject inferred types into code context windows
      max_diagnostics_per_file: 50   # Limit diagnostics per file (default: 50)

# ─── Routes ─────────────────────────────────────────────────────────
routes:
  <route_name>:
    type: stream | graph            # Route type (required)

    # ── Stream route fields ──────────────────────────────────────
    stream_type: cold | hot | replay  # Stream type (optional, default: cold)
    operators:                      # Processing operators (optional)
      - type: map | graph_execute   # Operator type
        params:                     # Operator parameters
          agent: <actor_name>       # Actor to use (for map)
          graph: <route_name>       # Graph to execute (for graph_execute)
    subscriptions:                  # Input subscriptions (optional)
      - <stream_name>
    publications:                   # Output publications (optional)
      - <stream_name>
    agents:                         # Actors used by this route (optional)
      - <actor_name>
    initial_value: <any>            # Initial stream value (optional)
    buffer_size: 10                 # Stream buffer size (optional, default: 10)
    template_config: {}             # Template-specific configuration (optional)
    bridge:                         # Bridge configuration for stream↔graph upgrades (optional)
      upgrade_conditions: {}        # Conditions to upgrade from stream to graph
      downgrade_conditions: {}      # Conditions to downgrade from graph to stream
      state_extractor: <string>     # Function to extract state during upgrade
      state_flattener: <string>     # Function to flatten state during downgrade
      preserve_subscriptions: true  # Keep subscriptions during transition (optional)
      preserve_checkpointing: true  # Keep checkpoints during transition (optional)
    metadata: {}                    # Arbitrary metadata (optional)

    # ── Graph route fields ───────────────────────────────────────
    nodes:                          # Graph nodes (required for graph routes)
      <node_name>:
        type: agent | function | tool | conditional | subgraph | start | end | message_router
        agent: <actor_name>         # Actor for agent nodes
        function: <function_name>   # Function for function nodes
        tools:                      # Tools for tool nodes
          - <tool_ref>
        condition: {}               # Condition for conditional nodes
        subgraph: <route_name>      # Subgraph for subgraph nodes
        retry_policy: {}            # Retry configuration (optional)
        timeout: 30                 # Timeout in seconds (optional)
        parallel: false             # Allow parallel execution (optional)
        metadata: {}                # Arbitrary metadata (optional)
    edges:                          # Graph edges (required for graph routes)
      - source: <node_name>         # Source node (required)
        target: <node_name>         # Target node (required)
        condition: {}               # Edge condition (optional)
        metadata: {}                # Arbitrary metadata (optional)
    entry_point: <node_name>        # Entry point node (required for graph routes)
    checkpointing: false            # Enable graph checkpointing (optional, default: false)
    checkpoint_dir: <path>          # Checkpoint directory (optional)
    enable_time_travel: false       # Enable time travel debugging (optional, default: false)
    parallel_execution: false       # Allow parallel node execution (optional, default: false)
    state_class: <string>           # Custom state class name (optional)
    metadata: {}                    # Arbitrary metadata (optional)

# ─── Merges & Splits ────────────────────────────────────────────────
merges:                             # Stream merge definitions (optional)
  - sources:                        # Source streams to merge
      - <stream_name>
    target: <stream_name>           # Target stream for merged output

splits:                             # Stream split definitions (optional)
  - source: <stream_name>           # Source stream to split
    targets:                        # Target streams for split output
      - <stream_name>

# ─── Templates & Context ────────────────────────────────────────────
templates: {}                       # Reusable template definitions (optional)
instances: {}                       # Template instances (optional)
global_context: {}                  # Global context available to all actors (optional)
prompts: {}                         # Named prompt templates (optional)

# ─── Pipelines ──────────────────────────────────────────────────────
pipelines:                          # Hybrid pipeline definitions (optional)
  <pipeline_name>:
    stages:
      - name: <stage_name>
        type: <stage_type>
        config: {}
    metadata: {}
#### Structure Reference **Top-Level Keys** | Key | Type | Required | Description | |-----|------|----------|-------------| | `cleveragents` | object | No | Metadata block containing version, logging, template engine, and safety settings. | | `actors` (or `agents`) | object | Yes | Map of actor names to their definitions. Both `actors` and `agents` are accepted as the key name. | | `routes` | object | No | Map of route names to their definitions. Routes connect actors via stream or graph topologies. | | `merges` | list | No | Stream merge operations combining multiple streams into one. | | `splits` | list | No | Stream split operations dividing one stream into multiple. | | `templates` | object | No | Reusable template definitions for Jinja2 template inheritance. | | `instances` | object | No | Instantiated templates with bound parameters. | | `global_context` | object | No | Key-value pairs available to all actors via `{{ context.key }}` in templates. | | `prompts` | object | No | Named prompt templates that can be referenced by actors. | | `pipelines` | object | No | Hybrid pipelines combining stream and graph stages into sequential workflows. | **`cleveragents` Block** | Field | Type | Default | Description | |-------|------|---------|-------------| | `version` | string | `"3.0"` | Schema version for this configuration file. | | `logging.level` | string | `"INFO"` | Logging level: `DEBUG`, `INFO`, `WARNING`, `ERROR`. | | `template_engine` | string | `"JINJA2"` | Template engine for string interpolation: `JINJA2` or `NONE`. | | `unsafe` | boolean | `false` | When `true`, allows actors to perform operations flagged as unsafe. Requires `--unsafe` CLI flag. | | `default_actor` | string | (first actor) | Name of the default actor when multiple actors are defined. | **Actor Definition Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `type` | string | Yes | Actor type. `llm` for language model actors, `tool` for tool-based actors. | | `config.provider` | string | Yes (LLM) | LLM provider identifier: `openai`, `anthropic`, `google`, `azure`, `openrouter`, etc. | | `config.model` | string | Yes (LLM) | Model identifier within the provider: `gpt-4`, `claude-3.5-sonnet`, `gemini-pro`, etc. | | `config.actor` | string | No | Combined `provider/model` format. Alternative to specifying `provider` and `model` separately. | | `config.system_prompt` | string | No | System prompt text. Supports Jinja2 template syntax for dynamic content. | | `config.temperature` | float | Provider default | Sampling temperature (0.0 to 2.0). Lower values are more deterministic. | | `config.max_tokens` | integer | Provider default | Maximum number of tokens in the generated response. | | `config.memory_enabled` | boolean | `false` | Enable conversation memory for multi-turn interactions. | | `config.max_history` | integer | `50` | Maximum number of conversation turns retained in memory. | | `config.unsafe` | boolean | `false` | Allow this specific actor to perform unsafe operations. | | `config.options` | object | `{}` | Provider-specific options passed through to the underlying LLM API. | | `config.tools` | list | Yes (tool) | List of inline tool definitions for tool-type actors. Each tool has `name` and `code`. | | `config.response_format` | object | No | JSON schema for structured output from the LLM. Constrains model output to match the schema. | | `skills` | list | No | List of namespaced skill names (e.g., `local/file-ops`) providing tool capabilities to the actor. | | `lsp` | list or object | No | LSP server binding. List of namespaced server names (explicit mode), object with `languages` list (language-based mode), or object with `auto: true` (auto-discovery mode). | | `lsp_capabilities` | string or list | No | Which LSP capabilities to expose. `"all"` (default) or a list from: `diagnostics`, `hover`, `completions`, `references`, `definitions`, `symbols`, `formatting`, `code_actions`, `rename`. | | `lsp_context_enrichment` | object | No | ACMS context enrichment from LSP. Fields: `diagnostics` (bool), `type_annotations` (bool), `max_diagnostics_per_file` (int, default 50). | **Node Types (Graph Routes)** | Type | Description | |------|-------------| | `agent` | A node backed by an actor. Requires `agent` field pointing to an actor name. | | `function` | A node backed by a Python function. Requires `function` field. | | `tool` | A node that invokes one or more tools. Requires `tools` list. | | `conditional` | A branching node that routes based on conditions. Requires `condition` field. | | `subgraph` | A node that delegates to another graph route. Requires `subgraph` field. | | `start` | The explicit start node (alternative to `entry_point`). | | `end` | A terminal node that ends graph execution. | | `message_router` | Routes messages to different nodes based on message content or metadata. | #### Examples **Example 1: Minimal Chat Actor (Simple)** A bare-minimum actor configuration for a simple conversational agent: 

# minimal-chat.yaml
# Register: agents actor add --config minimal-chat.yaml

name: local/chat

actors:
  chat:
    type: llm
    config:
      provider: anthropic
      model: claude-3.5-sonnet
      system_prompt: "You are a helpful assistant."

routes:
  main:
    type: stream
    operators:
      - type: map
        params:
          agent: chat
    publications:
      - output

merges:
  - sources: [output]
    target: final
This is the simplest possible actor: one LLM actor, one stream route, one merge. No graph complexity, no tools, no templates. --- **Example 2: Code Reviewer with Tools (Medium)** An actor that can read files and search code to perform code reviews: 

# code-reviewer.yaml
# Register: agents actor add --config code-reviewer.yaml

name: local/reviewer

cleveragents:
  version: "3.0"
  logging:
    level: "INFO"

actors:
  reviewer:
    type: llm
    config:
      provider: openai
      model: gpt-4
      temperature: 0.2
      max_tokens: 4096
      system_prompt: |
        You are a senior code reviewer. Analyze code for:
        - Security vulnerabilities
        - Performance issues
        - Code style violations
        - Missing error handling
        Provide specific, actionable feedback with file and line references.

  file_reader:
    type: tool
    config:
      tools:
        - name: read_file
          code: |
            def run(input_data):
                path = input_data.get("path", "")
                with open(path, "r") as f:
                    return {"content": f.read(), "path": path}

routes:
  review_graph:
    type: graph
    nodes:
      analyze:
        type: agent
        agent: reviewer
      read:
        type: tool
        tools: [read_file]
      report:
        type: agent
        agent: reviewer
    edges:
      - source: analyze
        target: read
      - source: read
        target: report
      - source: analyze
        target: report
        condition:
          no_files_needed: true
    entry_point: analyze
    checkpointing: false

  output_stream:
    type: stream
    operators:
      - type: graph_execute
        params:
          graph: review_graph
    publications:
      - review_output

merges:
  - sources: [review_output]
    target: final
This actor defines an LLM reviewer and a file-reading tool, connected via a graph route with conditional edges. --- **Example 3: Multi-Agent Research Pipeline with Templates (Complex)** A complex actor configuration with multiple LLM actors, Jinja2 templates, environment variable interpolation, memory, and hybrid routing: 

# research-pipeline.yaml
# Register: agents actor add --config research-pipeline.yaml --unsafe

name: local/research

cleveragents:
  version: "3.0"
  logging:
    level: "DEBUG"
  template_engine: "JINJA2"
  unsafe: true
  default_actor: orchestrator

actors:
  orchestrator:
    type: llm
    config:
      provider: anthropic
      model: claude-3.5-sonnet
      temperature: 0.7
      max_tokens: 8192
      memory_enabled: true
      max_history: 100
      system_prompt: |
        You are an orchestrator managing a research pipeline for {{ context.project_name }}.
        Topic: {{ context.research_topic }}

        Your job is to:
        1. Break down the research question into sub-questions
        2. Delegate to specialist researchers
        3. Synthesize findings into a coherent report

        {% if context.deadline %}
        Deadline: {{ context.deadline }}. Prioritize breadth over depth.
        {% endif %}

  researcher:
    type: llm
    config:
      provider: openai
      model: gpt-4
      temperature: 0.3
      max_tokens: 4096
      system_prompt: |
        You are a domain expert researcher. Provide thorough, factual analysis.
        Always cite sources and note confidence levels.

  synthesizer:
    type: llm
    config:
      provider: anthropic
      model: claude-3.5-sonnet
      temperature: 0.5
      max_tokens: 16384
      system_prompt: |
        You are an expert at synthesizing multiple research reports into coherent narratives.
        Resolve contradictions, highlight consensus, and note gaps.

  web_searcher:
    type: tool
    config:
      tools:
        - name: search_web
          code: |
            import os, json
            def run(input_data):
                api_key = os.environ.get("SEARCH_API_KEY", "")
                query = input_data.get("query", "")
                # Simulated web search
                return {"results": [], "query": query}

        - name: fetch_url
          code: |
            def run(input_data):
                url = input_data.get("url", "")
                return {"content": f"Content from {url}", "url": url}

routes:
  research_graph:
    type: graph
    nodes:
      plan:
        type: agent
        agent: orchestrator
      research_parallel:
        type: agent
        agent: researcher
        parallel: true
      search:
        type: tool
        tools: [search_web, fetch_url]
      synthesize:
        type: agent
        agent: synthesizer
      review:
        type: agent
        agent: orchestrator
    edges:
      - source: plan
        target: research_parallel
      - source: plan
        target: search
      - source: research_parallel
        target: synthesize
      - source: search
        target: synthesize
      - source: synthesize
        target: review
      - source: review
        target: plan
        condition:
          needs_more_research: true
    entry_point: plan
    checkpointing: true
    checkpoint_dir: "${CHECKPOINT_DIR:/tmp/research_checkpoints}"
    enable_time_travel: true
    parallel_execution: true

  progress_stream:
    type: stream
    stream_type: hot
    operators:
      - type: map
        params:
          agent: orchestrator
    subscriptions:
      - research_updates
    publications:
      - progress_output
    buffer_size: 50

  output_stream:
    type: stream
    operators:
      - type: graph_execute
        params:
          graph: research_graph
    publications:
      - research_output

merges:
  - sources: [progress_output, research_output]
    target: final

global_context:
  project_name: "AI Safety Research"
  research_topic: "Alignment techniques in large language models"
  deadline: "2026-03-01"

prompts:
  deep_dive: "Provide an in-depth analysis of {topic} with at least 5 sources."
  summary: "Summarize the following research in 500 words: {content}"

templates:
  research_section:
    template: |
      ## {{ section_title }}
      {{ section_content }}
      **Confidence:** {{ confidence_level }}
      **Sources:** {{ sources | join(', ') }}
This configuration demonstrates multi-actor orchestration, graph routing with parallel execution, hot stream monitoring, Jinja2 templates with conditionals, environment variables, checkpointing, and global context. --- **Example 4: Simple Echo/Tool Actor (Simple)** A non-LLM actor that processes input with pure Python code: 

# echo-actor.yaml
# Register: agents actor add --config echo-actor.yaml

name: local/echo

cleveragents:
  version: "3.0"

actors:
  echo:
    type: tool
    config:
      tools:
        - name: echo_tool
          code: |
            def run(input_data):
                message = input_data.get("content", "")
                return {"response": f"Echo: {message}"}

routes:
  main:
    type: stream
    operators:
      - type: map
        params:
          agent: echo
    publications:
      - output

merges:
  - sources: [output]
    target: final
--- **Example 5: Graph Actor with Conditional Routing (Medium)** An actor that routes between different specialists based on input classification: 

# classifier-router.yaml
# Register: agents actor add --config classifier-router.yaml

name: local/smart-router

actors:
  classifier:
    type: llm
    config:
      provider: openai
      model: gpt-4
      temperature: 0.0
      max_tokens: 100
      system_prompt: |
        Classify the user's request into exactly one category:
        CODING, WRITING, ANALYSIS, or GENERAL.
        Respond with only the category name.

  coding_expert:
    type: llm
    config:
      provider: anthropic
      model: claude-3.5-sonnet
      temperature: 0.2
      system_prompt: "You are an expert software engineer. Write clean, well-tested code."

  writing_expert:
    type: llm
    config:
      provider: openai
      model: gpt-4
      temperature: 0.7
      system_prompt: "You are a professional writer. Produce clear, engaging prose."

  analyst:
    type: llm
    config:
      provider: anthropic
      model: claude-3.5-sonnet
      temperature: 0.3
      system_prompt: "You are a data analyst. Provide thorough, evidence-based analysis."

  generalist:
    type: llm
    config:
      provider: openai
      model: gpt-4
      temperature: 0.5
      system_prompt: "You are a helpful general-purpose assistant."

routes:
  router_graph:
    type: graph
    nodes:
      classify:
        type: agent
        agent: classifier
      code:
        type: agent
        agent: coding_expert
      write:
        type: agent
        agent: writing_expert
      analyze:
        type: agent
        agent: analyst
      general:
        type: agent
        agent: generalist
    edges:
      - source: classify
        target: code
        condition:
          category: "CODING"
      - source: classify
        target: write
        condition:
          category: "WRITING"
      - source: classify
        target: analyze
        condition:
          category: "ANALYSIS"
      - source: classify
        target: general
        condition:
          category: "GENERAL"
    entry_point: classify

  main:
    type: stream
    operators:
      - type: graph_execute
        params:
          graph: router_graph
    publications:
      - output

merges:
  - sources: [output]
    target: final
--- **Example 6: Environment-Aware Actor with Jinja2 Conditionals (Simple Jinja2)** A single-actor configuration demonstrating the most common Jinja2 preprocessing features: `{{ variable }}` interpolation, `{% if %}` conditionals, the `| default` filter, and `${VAR:default}` environment variable substitution. See [ADR-032](adr/ADR-032-jinja2-yaml-template-preprocessing.md) for the full Jinja2 preprocessing specification. 

# support-bot.yaml
# Register: agents actor add --config support-bot.yaml
#
# Jinja2 preprocessing (Phase 1) resolves {{ }} and {% %} at load time.
# Phase 2: env var interpolation resolves ${VAR} after parsing.

name: local/support-bot

cleveragents:
  version: "3.0"
  template_engine: "JINJA2"

actors:
  support:
    type: llm
    config:
      # Phase 2: environment variables with defaults and type coercion
      provider: ${LLM_PROVIDER:anthropic}
      model: ${LLM_MODEL:claude-3.5-sonnet}
      temperature: 0.4
      max_tokens: ${MAX_TOKENS:4096}       # coerced to int automatically
      memory_enabled: ${ENABLE_MEMORY:true}  # coerced to bool automatically
      system_prompt: |
        You are a {{ context.role }} for {{ context.company }}.

        {% if context.tier == "enterprise" %}
        This is an enterprise customer. Provide priority support with
        detailed technical explanations and offer to escalate issues
        to the engineering team when needed.
        {% else %}
        Provide friendly, concise support. Direct complex issues to
        the documentation at {{ context.docs_url }}.
        {% endif %}

        Always respond in {{ context.language | default("English") }}.

routes:
  main:
    type: stream
    operators:
      - type: map
        params:
          agent: support
    publications:
      - output

merges:
  - sources: [output]
    target: final

# global_context populates the {{ context.* }} namespace at load time
global_context:
  company: "Acme Corp"
  role: "technical support specialist"
  tier: "enterprise"
  docs_url: "https://docs.acme.example.com"
This example shows the three most common Jinja2 preprocessing patterns: variable interpolation (`{{ context.company }}`), conditional blocks (`{% if context.tier == "enterprise" %}`), and the `| default` filter for safe fallbacks. Environment variables (`${LLM_PROVIDER:anthropic}`) are resolved in Phase 2 after YAML parsing, with automatic type coercion converting `"4096"` to `int` and `"true"` to `bool`. --- **Example 7: Multi-Actor Paper Writer with Advanced Jinja2 (Advanced Jinja2)** A comprehensive multi-actor configuration exercising the full Jinja2 preprocessing feature set. Crucially, this example places `{% for %}` and `{% if %}` directives **outside any YAML value** — directly at the structural level where YAML keys and list items would normally appear. The raw file is **not valid YAML** until after Jinja2 Phase 1 preprocessing renders it into static YAML text. Features demonstrated include: structural `{% for %}` loops that generate actor definitions, graph nodes, and graph edges; structural `{% if %}` conditionals that include or exclude entire actor blocks, route definitions, and merge sources; `{% if %}` nested inside `{% for %}` at the structural level; `loop.index`; Jinja2 type tests (`is mapping`); `.get()` with defaults; string slicing (`[:200]`); ternary expressions; arithmetic; `| tojson` / `| length` / `| upper` / `| join` filters; `{# comment #}` blocks; and deeply nested `global_context`. See [ADR-032](adr/ADR-032-jinja2-yaml-template-preprocessing.md) for full details. 

# paper-writer.yaml
# Register: agents actor add --config paper-writer.yaml
#
# IMPORTANT: This file is NOT valid YAML as written. Jinja2 directives
# ({% for %}, {% if %}, {% endif %}, {% endfor %}) appear at the structural
# level — where YAML keys and list items would normally be — making the
# raw file unparseable by any YAML parser. Phase 1 (Jinja2 preprocessing)
# renders these directives into static YAML text BEFORE the YAML parser
# ever sees the file. Jinja2 syntax inside system_prompt fields is
# preserved for deferred runtime rendering.

name: local/paper-writer

cleveragents:
  version: "3.0"
  template_engine: "JINJA2"
  logging:
    level: "${LOG_LEVEL:INFO}"
  unsafe: ${ALLOW_UNSAFE:false}       # Phase 2: coerced to bool
  default_actor: orchestrator

{# ─── Template comment: stripped from output, never reaches YAML parser ─── #}

actors:
  # ── Orchestrator: uses deferred Jinja2 in system_prompt ─────────────
  orchestrator:
    type: llm
    config:
      provider: ${LLM_PROVIDER:anthropic}
      model: ${PRIMARY_MODEL:claude-3.5-sonnet}
      temperature: 0.7
      max_tokens: ${MAX_TOKENS:8192}
      memory_enabled: true
      max_history: ${MAX_HISTORY:100}
      system_prompt: |
        You are the lead orchestrator for a research paper.
        Topic: {{ context.paper_details.topic | tojson }}
        Audience: {{ context.paper_details.audience | tojson }}
        Max length: {{ context.paper_details.length | tojson }} words

        {# ── Vetted sources: for-loop with type test, .get(), slicing ── #}
        {% if context.vetted_sources and context.vetted_sources|length > 0 %}
        The following {{ context.vetted_sources|length }} vetted sources:
        {% for source in context.vetted_sources %}
        {{ loop.index }}.
        {% if source is mapping %}
          {{ source.get('citation', 'Untitled') }}
          {% if source.get('summary') %}
          — {{ source.get('summary')[:200] }}
          {% if source.get('summary')|length > 200 %}
          ...
          {% endif %}
          {% endif %}
        {% else %}
          {{ source }}
        {% endif %}
        {% endfor %}
        {% else %}
        No vetted sources are available yet. Begin with the discovery phase.
        {% endif %}

        {% if context.deadline %}
        DEADLINE: {{ context.deadline }}. Prioritize accordingly.
        {% endif %}

        {# ── Section plan: ternary expression highlights current section ── #}
        Section plan:
        {% for section in context.sections %}
        {% set m = ">>> " if section == context.current_section else "    " %}
        {{ m }}{{ loop.index }}. {{ section }}
        {% endfor %}

        {# ── Arithmetic in expressions ── #}
        Progress: section {{ context.current_section_index + 1 }}
        of {{ context.sections|length }}.

  # ── Writer: deferred templates with nested conditionals ─────────────
  writer:
    type: llm
    config:
      provider: ${LLM_PROVIDER:anthropic}
      model: ${PRIMARY_MODEL:claude-3.5-sonnet}
      temperature: 0.5
      max_tokens: 16384
      system_prompt: |
        You are writing section "{{ context.current_section }}" of a paper
        on {{ context.paper_details.topic }}.

        {% if context.section_content %}
        Previous draft:
        {% set sec = context.current_section %}
        {{ context.section_content.get(sec, 'No prior draft.') }}
        {% endif %}

        {# ── Nested: loop inside conditional ── #}
        {% if context.review_feedback and context.review_feedback|length > 0 %}
        Reviewer feedback to address:
        {% for fb in context.review_feedback %}
        [{{ fb.reviewer }}] ({{ fb.severity }}): {{ fb.comment }}
        {% endfor %}
        {% endif %}

        Format: {{ context.paper_details.get('format', 'markdown') | upper }}

  # ── STRUCTURAL {% if %}: the entire assembler actor definition — its YAML
  # ── key and all nested content — is conditionally included. The {% if %}
  # ── and {% endif %} lines occupy positions where YAML keys would be,
  # ── making this raw text invalid YAML. After Phase 1 rendering, either
  # ── the full assembler: block appears or nothing does.
  {% if context.enable_assembly %}
  assembler:
    type: llm
    config:
      actor: anthropic/claude-3.5-sonnet
      temperature: 0.3
      max_tokens: 32768
      system_prompt: |
        Assemble the final paper from these completed sections:
        {% for path in context.sections %}
        --- {{ path }} ---
        {{ context.section_content.get(path, '[MISSING]') }}
        {% endfor %}

        Total sections: {{ context.sections|length }}
        Target length: {{ context.paper_details.length }} words

        {% if context.latex_errors %}
        Previous compilation errors (last 2000 chars):
        {{ context.latex_errors[-2000:] }}
        {% endif %}
  {% endif %}

  # ── STRUCTURAL {% for %}: GENERATE one reviewer actor per entry in
  # ── context.reviewers. The {% for %} line sits where a YAML key would
  # ── be — not inside any string value. A YAML parser would reject this.
  # This {% for %} runs at Phase 1 and produces static YAML actor definitions.
  # With 3 reviewers in global_context, the rendered YAML contains 3 actors:
  # reviewer_methods, reviewer_domain, reviewer_style.
  {% for reviewer in context.reviewers %}
  reviewer_{{ reviewer.id }}:
    type: llm
    config:
      provider: {{ reviewer.get('provider', 'openai') }}
      model: {{ reviewer.get('model', 'gpt-4') }}
      temperature: 0.2
      max_tokens: 4096
      system_prompt: |
        You are {{ reviewer.name }}, an expert reviewer
        specializing in {{ reviewer.specialty }}.

        Evaluate the paper section for:
        {# ── Nested loop: iterate criteria inside reviewer loop ── #}
        {% for criterion in reviewer.criteria %}
        - {{ criterion }}
        {% endfor %}

        Severity ratings: Critical, Major, Minor, Suggestion.

        {% if context.review_mode == "strict" %}
        Apply strict academic standards. Flag all unsupported claims.
        {% else %}
        Focus on substantive issues. Ignore minor style preferences.
        {% endif %}
  {% endfor %}

# ── Routes: load-time loop generates graph nodes and edges ──────────
routes:
  writing_graph:
    type: graph
    nodes:
      plan:
        type: agent
        agent: orchestrator
      draft:
        type: agent
        agent: writer
      # STRUCTURAL {% for %}: generates review_methods, review_domain,
      # review_style as concrete YAML keys — invalid YAML until rendered
      {% for reviewer in context.reviewers %}
      review_{{ reviewer.id }}:
        type: agent
        agent: reviewer_{{ reviewer.id }}
      {% endfor %}
      # STRUCTURAL {% if %}: the assemble node only exists when assembly
      # is enabled — matches the conditional assembler actor above
      {% if context.enable_assembly %}
      assemble:
        type: agent
        agent: assembler
      {% endif %}
    edges:
      - source: plan
        target: draft
      # STRUCTURAL {% for %}: generates edge sets for each reviewer.
      # Contains a NESTED STRUCTURAL {% if %} — the assemble edge only
      # appears when enable_assembly is true. Both directives sit where
      # YAML list items would be — completely invalid YAML until rendered.
      {% for reviewer in context.reviewers %}
      - source: draft
        target: review_{{ reviewer.id }}
      - source: review_{{ reviewer.id }}
        target: draft
        condition:
          has_critical_feedback: true
      # {% if %} NESTED inside {% for %}: each reviewer gets an edge
      # to assemble only when the assembler exists
      {% if context.enable_assembly %}
      - source: review_{{ reviewer.id }}
        target: assemble
        condition:
          review_passed: true
      {% endif %}
      {% endfor %}
    entry_point: plan
    checkpointing: true
    checkpoint_dir: "${CHECKPOINT_DIR:/tmp/paper_checkpoints}"
    parallel_execution: true

  output_stream:
    type: stream
    operators:
      - type: graph_execute
        params:
          graph: writing_graph
    publications:
      - paper_output

  # ── STRUCTURAL {% if %}: this entire route definition — the YAML key
  # ── "progress_stream:" and all its children — only exists in the
  # ── rendered output when enable_monitoring is true. A YAML parser
  # ── would choke on the bare {% if %} line sitting where it expects
  # ── a mapping key.
  {% if context.enable_monitoring %}
  progress_stream:
    type: stream
    stream_type: hot
    operators:
      - type: map
        params:
          agent: orchestrator
    subscriptions:
      - writing_updates
    publications:
      - progress_output
    buffer_size: 50
  {% endif %}

merges:
  - sources:
      - paper_output
      # STRUCTURAL {% if %} inside a YAML list: this list item only
      # appears in the rendered YAML when the condition is true.
      # The raw file has a {% if %} line where a "- value" is expected.
      {% if context.enable_monitoring %}
      - progress_output
      {% endif %}
    target: final

# ── global_context: deeply nested structures drive all template rendering ──
global_context:
  paper_details:
    topic: "Alignment techniques in large language models"
    audience: "ML researchers"
    length: 8000
    publication: "NeurIPS 2026"
    format: "latex"
  sections:
    - "Abstract"
    - "Introduction"
    - "Related Work"
    - "Methodology"
    - "Experiments"
    - "Results > Quantitative"
    - "Results > Qualitative"
    - "Discussion"
    - "Conclusion"
  current_section: "Introduction"
  current_section_index: 1
  deadline: "2026-06-01"
  review_mode: "strict"
  # These flags drive the structural {% if %} conditionals above.
  # Set to false to exclude the assembler actor and monitoring route entirely.
  enable_assembly: true
  enable_monitoring: true
  # The reviewers list drives the structural {% for %} loops that generate
  # actor definitions, graph nodes, and graph edges at load time.
  reviewers:
    - id: methods
      name: "Dr. Methods"
      specialty: "research methodology"
      provider: "openai"
      model: "gpt-4"
      criteria:
        - "Statistical validity"
        - "Reproducibility of experiments"
        - "Clarity of methodology description"
    - id: domain
      name: "Dr. Domain"
      specialty: "AI alignment"
      provider: "anthropic"
      model: "claude-3.5-sonnet"
      criteria:
        - "Technical accuracy"
        - "Completeness of literature review"
        - "Novelty of contributions"
    - id: style
      name: "Prof. Style"
      specialty: "academic writing"
      criteria:
        - "Clarity and readability"
        - "Logical flow between sections"
        - "Proper citation format"
This configuration demonstrates every major Jinja2 preprocessing feature: | Feature | Where Used | |---------|-----------| | **Structural `{% if %}`** wrapping entire YAML blocks | Assembler actor def, `assemble` graph node, `progress_stream` route, merge source list item | | **Structural `{% for %}`** generating YAML keys/items | Reviewer actor defs, graph nodes, graph edges | | **`{% if %}` nested inside `{% for %}`** at structural level | Reviewer→assemble edge (conditional per-reviewer) | | `{{ context.X.Y }}` — nested variable access | Orchestrator, writer, assembler `system_prompt` | | `{{ X \| tojson }}` — safe serialization filter | Orchestrator prompt: topic, audience, length | | `{{ X \| length }}` — collection length | Source count, section count | | `{{ X \| upper }}` — string transformation | Writer prompt: format output | | `{{ X \| default("Y") }}` — fallback defaults | Reviewer `.get('provider', 'openai')` | | `{% if X and X\|length > 0 %}` — compound conditions | Vetted sources, review feedback, deadline | | `{% for X in Y %}` / `loop.index` — iteration | Sources list, sections list, reviewers list | | `{# comment #}` — template comments | Stripped from rendered output | | `source is mapping` — Jinja2 type test | Vetted sources loop | | `.get('key', 'default')` — safe dict access | Section content, paper format | | `[:200]` / `[-2000:]` — string/list slicing | Source summaries, LaTeX errors | | `"X" if cond else "Y"` — ternary expressions | Section plan current-section marker | | `{{ index + 1 }}` — arithmetic | Section progress counter | | Nested `{% for %}` inside `{% for %}` | Reviewer criteria inside reviewer loop | | `${VAR:default}` — env var with type coercion | Provider, model, tokens, unsafe flag | | `global_context` with nested dicts/lists | `paper_details`, `sections`, `reviewers` | | Deferred rendering in `system_prompt` | All `system_prompt` fields preserve `{{ }}` for runtime | **Why the raw file is not valid YAML**: The `{% for %}`, `{% endfor %}`, `{% if %}`, and `{% endif %}` directives in this file appear at positions where the YAML parser expects mapping keys or list items — for example, `{% if context.enable_assembly %}` sits at the same indentation level as `assembler:` under the `actors:` mapping, and `{% if context.enable_monitoring %}` sits where a route name key would be under `routes:`. A YAML parser would reject these lines as syntax errors. Jinja2 Phase 1 preprocessing resolves all directives into plain text *before* the YAML parser ever runs, producing a valid static YAML document. **Load-time vs. runtime rendering**: The structural `{% for %}` and `{% if %}` directives in the `actors`, `routes`, and `merges` sections run at **load time** (Phase 1) and produce static YAML — the three reviewer entries expand into three concrete actor definitions (`reviewer_methods`, `reviewer_domain`, `reviewer_style`), their corresponding graph nodes and edges, and the assembler and monitoring route conditionally appear or disappear. In contrast, Jinja2 syntax inside `system_prompt` fields is **preserved** through the load-parse cycle (via the template protection mechanism) and evaluated at **runtime** when the actor's execution context is available. --- ### Skill Configuration Files !!! adr "Architecture Decision" The skill configuration schema, tool references, and skill inclusion are defined in [ADR-012: Skill System](adr/ADR-012-skill-system.md). Skill configuration files define reusable, namespaced collections of tools. Skills assemble tools by referencing named tools from the Tool Registry, defining anonymous inline tools, and including other skills. Skills are registered via `agents skill add --config `. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for skill configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/skill-config.json",
  "title": "CleverAgents Skill Configuration",
  "description": "Configuration file schema for defining CleverAgents skills — reusable, namespaced collections of tools.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified skill name in <namespace>/<name> format."
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of what this skill provides."
    },
    "tools": {
      "type": "array",
      "description": "References to named tools from the Tool Registry.",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
            "description": "Fully qualified name of a tool registered in the Tool Registry."
          },
          "description": {
            "type": "string",
            "description": "Override the tool's registered description within this skill context."
          },
          "writes": {
            "type": "boolean",
            "description": "Override the tool's writes capability flag."
          },
          "checkpointable": {
            "type": "boolean",
            "description": "Override the tool's checkpointable capability flag."
          }
        },
        "required": ["name"],
        "additionalProperties": false
      }
    },
    "inline_tools": {
      "type": "array",
      "description": "Anonymous tool definitions that exist only within this skill. Not registered in the Tool Registry.",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "description": "Tool name, unique within this skill."
          },
          "description": {
            "type": "string",
            "description": "Human-readable description of the tool's purpose."
          },
          "source": {
            "type": "string",
            "const": "custom",
            "description": "Source type. Always 'custom' for inline tools."
          },
          "code": {
            "type": "string",
            "description": "Python code defining the tool's behavior. Must contain a run(input_data) function."
          },
          "input_schema": {
            "$ref": "https://json-schema.org/draft/2020-12/schema",
            "description": "JSON Schema describing the tool's input parameters."
          },
          "writes": {
            "type": "boolean",
            "default": false,
            "description": "Whether this tool performs write operations."
          },
          "checkpointable": {
            "type": "boolean",
            "default": false,
            "description": "Whether this tool supports checkpointing."
          },
          "side_effects": {
            "type": "array",
            "items": { "type": "string" },
            "default": [],
            "description": "Descriptions of side effects (e.g., 'network_call', 'schema_mutation')."
          }
        },
        "required": ["name", "source", "code"],
        "additionalProperties": false
      }
    },
    "includes": {
      "type": "array",
      "description": "Other skills whose tools are merged into this skill.",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
            "description": "Fully qualified skill name to include."
          },
          "description": {
            "type": "string",
            "description": "Override the included skill's description."
          }
        },
        "required": ["name"],
        "additionalProperties": false
      }
    },
    "mcp_servers": {
      "type": "array",
      "description": "MCP server specifications for exposing remote tools.",
      "items": {
        "$ref": "#/$defs/mcpServer"
      }
    },
    "agent_skill_folders": {
      "type": "array",
      "description": "Agent Skills Standard folders to include.",
      "items": {
        "type": "object",
        "properties": {
          "path": {
            "type": "string",
            "description": "Path to the folder containing SKILL.md."
          },
          "name": {
            "type": "string",
            "description": "Override the skill bundle name."
          }
        },
        "required": ["path"],
        "additionalProperties": false
      }
    }
  },
  "required": ["name"],
  "additionalProperties": false,
  "$defs": {
    "mcpServer": {
      "type": "object",
      "description": "An MCP server specification.",
      "properties": {
        "name": {
          "type": "string",
          "description": "Identifier for the MCP server."
        },
        "transport": {
          "type": "string",
          "enum": ["stdio", "sse", "streamable-http"],
          "description": "Transport protocol."
        },
        "command": {
          "type": "string",
          "description": "Command to start the server (required for stdio transport)."
        },
        "args": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Command-line arguments for the server command."
        },
        "env": {
          "type": "object",
          "additionalProperties": { "type": "string" },
          "description": "Environment variables to set when starting the server."
        },
        "url": {
          "type": "string",
          "format": "uri",
          "description": "Server URL (required for sse and streamable-http transports)."
        },
        "headers": {
          "type": "object",
          "additionalProperties": { "type": "string" },
          "description": "HTTP headers for remote server connections."
        },
        "tool_filter": {
          "type": "object",
          "properties": {
            "include": {
              "type": "array",
              "items": { "type": "string" },
              "description": "Whitelist of tool names to expose."
            },
            "exclude": {
              "type": "array",
              "items": { "type": "string" },
              "description": "Blacklist of tool names to hide."
            }
          },
          "additionalProperties": false
        }
      },
      "required": ["name", "transport"],
      "additionalProperties": false
    }
  }
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Skill Metadata ─────────────────────────────────────────────────
name: <namespace>/<name>            # Fully qualified skill name (required)
description: <string>               # Human-readable description (optional)

# ─── Tool References ────────────────────────────────────────────────
# Named tools from the Tool Registry, referenced by fully-qualified name.
tools:
  - name: <namespace>/<tool_name>   # Reference to a registered tool (required)
    description: <string>           # Override the tool's description (optional)
    writes: <boolean>               # Override the tool's writes flag (optional)
    checkpointable: <boolean>       # Override the tool's checkpointable flag (optional)

# ─── Inline (Anonymous) Tools ───────────────────────────────────────
# Tools defined directly within this skill. These are NOT registered
# in the Tool Registry and cannot be reused outside this skill.
inline_tools:
  - name: <string>                  # Tool name (unique within this skill, required)
    description: <string>           # Tool description (optional)
    source: custom                  # Source type (required, always "custom" for inline)
    code: |                         # Inline Python code (required)
      def run(input_data):
          return {"result": "value"}
    input_schema:                   # JSON Schema for tool inputs (optional)
      type: object
      properties:
        param_name:
          type: string
          description: "Parameter description"
      required: ["param_name"]
    writes: false                   # Whether this tool writes (optional, default: false)
    checkpointable: false           # Whether this tool supports checkpointing (optional, default: false)
    side_effects: []                # List of side effect descriptions (optional)

# ─── Included Skills ────────────────────────────────────────────────
# Other skills whose tools are merged into this skill.
includes:
  - name: <namespace>/<skill_name>  # Fully qualified skill name to include (required)
    description: <string>           # Override the included skill's description (optional)

# ─── MCP Server Specifications ──────────────────────────────────────
# MCP servers whose tools are exposed through this skill.
mcp_servers:
  - name: <string>                  # Server name for identification (required)
    transport: stdio | sse | streamable-http  # Transport protocol (required)
    command: <string>               # Server command (required for stdio)
    args:                           # Command arguments (optional)
      - <string>
    env:                            # Environment variables for the server (optional)
      KEY: "value"
    url: <string>                   # Server URL (required for sse/streamable-http)
    headers: {}                     # HTTP headers (optional, for sse/streamable-http)
    tool_filter:                    # Filter which tools to expose (optional)
      include:                      # Include only these tools (optional)
        - <tool_name>
      exclude:                      # Exclude these tools (optional)
        - <tool_name>

# ─── Agent Skills Standard Folders ──────────────────────────────────
# References to Agent Skills Standard (SKILL.md-based) tool bundles.
agent_skill_folders:
  - path: <string>                  # Path to the folder containing SKILL.md (required)
    name: <string>                  # Override the skill bundle name (optional)
#### Structure Reference **Top-Level Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified skill name in `/` format. This value is used as the skill's registered name. | | `description` | string | No | Human-readable description of what this skill provides. | | `tools` | list | No | References to named tools from the Tool Registry. | | `inline_tools` | list | No | Anonymous tool definitions that exist only within this skill. | | `includes` | list | No | Other skills to include (their tools are merged in). | | `mcp_servers` | list | No | MCP server specifications for exposing remote tools. | | `agent_skill_folders` | list | No | Agent Skills Standard folders to include. | **Tool Reference Fields (`tools[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified name of a tool registered in the Tool Registry. | | `description` | string | No | Override the tool's registered description within this skill context. | | `writes` | boolean | No | Override the tool's `writes` capability flag. | | `checkpointable` | boolean | No | Override the tool's `checkpointable` capability flag. | **Inline Tool Fields (`inline_tools[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Tool name, unique within this skill. | | `description` | string | No | Human-readable description of the tool's purpose. | | `source` | string | Yes | Always `custom` for inline tools. | | `code` | string | Yes | Python code defining the tool's behavior. Must contain a `run(input_data)` function. | | `input_schema` | object | No | JSON Schema describing the tool's input parameters. | | `writes` | boolean | No | Whether this tool performs write operations. Default: `false`. | | `checkpointable` | boolean | No | Whether this tool supports checkpointing. Default: `false`. | | `side_effects` | list | No | Descriptions of any side effects (e.g., `["network_call"]`, `["schema_mutation"]`). | **MCP Server Fields (`mcp_servers[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Identifier for the MCP server. | | `transport` | string | Yes | Transport protocol: `stdio`, `sse`, or `streamable-http`. | | `command` | string | Conditional | Command to start the server (required for `stdio` transport). | | `args` | list | No | Command-line arguments for the server command. | | `env` | object | No | Environment variables to set when starting the server. | | `url` | string | Conditional | Server URL (required for `sse` and `streamable-http` transports). | | `headers` | object | No | HTTP headers for remote server connections. | | `tool_filter.include` | list | No | Whitelist of tool names to expose. When set, only these tools are available. | | `tool_filter.exclude` | list | No | Blacklist of tool names to hide. Applied after `include`. | #### Examples **Example 1: Minimal Read-Only Skill (Simple)** A skill that bundles a few built-in file operations: 

# file-reader-skill.yaml
# Register: agents skill add --config file-reader-skill.yaml

name: local/file-reader
description: "Basic file reading operations"

tools:
  - name: builtin/read_file
  - name: builtin/list_directory
  - name: builtin/search_files
--- **Example 2: Git Operations Skill with MCP (Medium)** A skill that combines built-in git tools with GitHub tools via an MCP server: 

# git-and-github-skill.yaml
# Register: agents skill add --config git-and-github-skill.yaml

name: local/git-github
description: "Git operations and GitHub integration"

tools:
  - name: builtin/git_status
  - name: builtin/git_diff
  - name: builtin/git_log
  - name: builtin/git_blame

includes:
  - name: local/file-reader

mcp_servers:
  - name: github
    transport: stdio
    command: npx
    args:
      - "-y"
      - "@modelcontextprotocol/server-github"
    env:
      GITHUB_PERSONAL_ACCESS_TOKEN: "${GITHUB_TOKEN}"
    tool_filter:
      include:
        - create_issue
        - create_pull_request
        - list_repos
        - get_file_contents
This skill includes another skill (`local/file-reader`) and adds GitHub tools from an MCP server, filtered to only expose four specific tools. --- **Example 3: Full DevOps Toolkit (Complex)** A comprehensive skill with multiple includes, MCP servers, inline tools, and agent skill folders: 

# devops-toolkit.yaml
# Register: agents skill add --config devops-toolkit.yaml

name: local/devops-toolkit
description: "Full-stack development and operations toolkit"

tools:
  - name: builtin/shell_execute
    description: "Execute shell commands in the project sandbox"
  - name: local/validate-api-compat
    description: "Check API backward compatibility"

includes:
  - name: local/file-reader
  - name: local/git-github
  - name: local/docker-tools

inline_tools:
  - name: run_migrations
    description: "Run database migrations with rollback support"
    source: custom
    code: |
      import subprocess
      def run(input_data):
          direction = input_data.get("direction", "up")
          count = input_data.get("count", 1)
          result = subprocess.run(
              ["alembic", direction, str(count)],
              capture_output=True, text=True
          )
          return {
              "success": result.returncode == 0,
              "stdout": result.stdout,
              "stderr": result.stderr
          }
    input_schema:
      type: object
      properties:
        direction:
          type: string
          enum: ["up", "down"]
          description: "Migration direction"
        count:
          type: integer
          default: 1
          description: "Number of migrations to run"
      required: ["direction"]
    writes: true
    checkpointable: true
    side_effects: ["schema_mutation"]

  - name: health_check
    description: "Check service health endpoints"
    source: custom
    code: |
      import urllib.request
      def run(input_data):
          url = input_data.get("url", "http://localhost:8000/health")
          try:
              resp = urllib.request.urlopen(url, timeout=10)
              return {"status": resp.status, "healthy": resp.status == 200}
          except Exception as e:
              return {"status": 0, "healthy": False, "error": str(e)}
    input_schema:
      type: object
      properties:
        url:
          type: string
          description: "Health check URL"
    writes: false

mcp_servers:
  - name: linear
    transport: stdio
    command: npx
    args: ["-y", "@modelcontextprotocol/server-linear"]
    env:
      LINEAR_API_KEY: "${LINEAR_API_KEY}"

agent_skill_folders:
  - path: ./skills/deploy-to-staging
    name: deploy-staging
  - path: ./skills/code-review-bundle
    name: code-review
--- **Example 4: Skill with Only Inline Tools (Simple)** A self-contained skill that defines everything inline, with no external dependencies: 

# text-processing-skill.yaml
# Register: agents skill add --config text-processing-skill.yaml

name: local/text-processing
description: "Simple text transformation utilities"

inline_tools:
  - name: word_count
    description: "Count words in text"
    source: custom
    code: |
      def run(input_data):
          text = input_data.get("text", "")
          return {"count": len(text.split())}
    input_schema:
      type: object
      properties:
        text:
          type: string
          description: "Text to count words in"
      required: ["text"]
    writes: false

  - name: to_uppercase
    description: "Convert text to uppercase"
    source: custom
    code: |
      def run(input_data):
          return {"result": input_data.get("text", "").upper()}
    input_schema:
      type: object
      properties:
        text:
          type: string
      required: ["text"]
    writes: false

  - name: extract_urls
    description: "Extract URLs from text"
    source: custom
    code: |
      import re
      def run(input_data):
          text = input_data.get("text", "")
          urls = re.findall(r'https?://[^\s<>"{}|\\^`\[\]]+', text)
          return {"urls": urls, "count": len(urls)}
    writes: false
--- ### Action Configuration Files !!! adr "Architecture Decision" The action configuration schema and action-to-plan lifecycle are defined in [ADR-006: Plan Lifecycle](adr/ADR-006-plan-lifecycle.md). Action configuration files define reusable plan templates — complete specifications for work that can be applied to projects. Actions are created via `agents action create --config `. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for action configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/action-config.json",
  "title": "CleverAgents Action Configuration",
  "description": "Configuration file schema for defining CleverAgents actions — reusable plan templates that specify work to be applied to projects.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified action name in <namespace>/<name> format."
    },
    "description": {
      "type": "string",
      "description": "Short (one-line) description of the action."
    },
    "long_description": {
      "type": "string",
      "description": "Detailed multi-line description explaining purpose, usage, and expected outcomes."
    },
    "strategy_actor": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Actor to use during the Strategize phase. Must reference a registered actor."
    },
    "execution_actor": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Actor to use during the Execute phase. Must reference a registered actor."
    },
    "estimation_actor": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Actor for effort and cost estimation before execution."
    },
    "review_actor": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Actor for reviewing execution results."
    },
    "apply_actor": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Actor to use during the Apply phase."
    },
    "invariant_actor": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Actor for reconciling conflicting invariants across scopes."
    },
    "definition_of_done": {
      "type": "string",
      "description": "Clear, measurable criteria that define when the action's work is complete."
    },
    "reusable": {
      "type": "boolean",
      "default": true,
      "description": "Whether the action persists after being used."
    },
    "read_only": {
      "type": "boolean",
      "default": false,
      "description": "Whether the action is restricted to read-only operations."
    },
    "state": {
      "type": "string",
      "enum": ["available", "archived"],
      "default": "available",
      "description": "State of the action."
    },
    "arguments": {
      "type": "array",
      "description": "Typed parameters that users supply when using the action via agents plan use --arg name=value.",
      "items": {
        "$ref": "#/$defs/argument"
      }
    },
    "automation_profile": {
      "type": "string",
      "description": "Default automation profile for plans created from this action."
    },
    "invariants": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Constraints carried forward as plan-level invariants when the action is used."
    }
  },
  "required": ["name", "description", "strategy_actor", "execution_actor", "definition_of_done"],
  "additionalProperties": false,
  "$defs": {
    "argument": {
      "type": "object",
      "description": "A typed parameter for the action.",
      "properties": {
        "name": {
          "type": "string",
          "description": "Argument name. Used as the key in --arg name=value."
        },
        "type": {
          "type": "string",
          "enum": ["string", "integer", "float", "boolean", "list"],
          "description": "Data type of the argument."
        },
        "required": {
          "type": "boolean",
          "default": false,
          "description": "Whether the argument must be provided."
        },
        "description": {
          "type": "string",
          "description": "Human-readable description shown in help text."
        },
        "default": {
          "description": "Default value when the argument is not provided. Type must match the 'type' field."
        },
        "validation_pattern": {
          "type": "string",
          "description": "Regex pattern for validating string arguments."
        },
        "min_value": {
          "type": "number",
          "description": "Minimum acceptable value for integer and float arguments."
        },
        "max_value": {
          "type": "number",
          "description": "Maximum acceptable value for integer and float arguments."
        }
      },
      "required": ["name", "type"],
      "additionalProperties": false
    }
  }
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Action Identity ────────────────────────────────────────────────
name: <namespace>/<name>            # Fully qualified action name (required)
description: <string>               # Short description (required)
long_description: |                 # Detailed description (optional)
  Multi-line detailed explanation of what this action does,
  when to use it, and what outcomes to expect.

# ─── Lifecycle Actors ───────────────────────────────────────────────
strategy_actor: <namespace>/<name>  # Actor for the Strategize phase (required)
execution_actor: <namespace>/<name> # Actor for the Execute phase (required)
estimation_actor: <namespace>/<name> # Actor for effort/cost estimation (optional)
review_actor: <namespace>/<name>    # Actor for reviewing results (optional)
apply_actor: <namespace>/<name>     # Actor for the Apply phase (optional)
invariant_actor: <namespace>/<name> # Invariant Reconciliation Actor (optional)

# ─── Completion Criteria ────────────────────────────────────────────
definition_of_done: |               # Criteria for when the action is complete (required)
  Clear, measurable criteria that define success.
  Multiple criteria can be listed.

# ─── Action Properties ──────────────────────────────────────────────
reusable: true                      # Keep action after use (optional, default: true)
read_only: false                    # Restrict to read-only operations (optional, default: false)
state: available                    # State of the action: available or archived (optional, default: available)
# ─── Arguments ──────────────────────────────────────────────────────
# Arguments are typed parameters that must be supplied when using
# the action via `agents plan use --arg name=value`.
arguments:
  - name: <string>                  # Argument name (required)
    type: string | integer | float | boolean | list  # Argument type (required)
    required: true                  # Whether the argument must be provided (optional, default: false)
    description: <string>           # Human-readable description (optional)
    default: <value>                # Default value when not provided (optional)
    validation_pattern: <regex>     # Regex pattern for string validation (optional)
    min_value: <number>             # Minimum value for numeric types (optional)
    max_value: <number>             # Maximum value for numeric types (optional)

# ─── Automation ─────────────────────────────────────────────────────
automation_profile: <string>        # Default automation profile name (optional)

# ─── Invariants ─────────────────────────────────────────────────────
# Invariants carried forward as plan-level invariants when this action is used.
invariants:
  - <string>                        # Invariant text
#### Structure Reference **Top-Level Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified action name in `/` format. This value is used as the action's registered name. | | `description` | string | Yes | Short (one-line) description of the action. | | `long_description` | string | No | Detailed multi-line description explaining purpose, usage, and expected outcomes. | | `strategy_actor` | string | Yes | Actor to use during the Strategize phase. Must reference a registered actor. | | `execution_actor` | string | Yes | Actor to use during the Execute phase. Must reference a registered actor. | | `estimation_actor` | string | No | Actor to use for effort and cost estimation before execution. | | `review_actor` | string | No | Actor to use for reviewing execution results. | | `apply_actor` | string | No | Actor to use during the Apply phase. | | `invariant_actor` | string | No | Actor for reconciling conflicting invariants across scopes. Carried forward to plans. | | `definition_of_done` | string | Yes | Clear, measurable criteria that define when the action's work is complete. | | `reusable` | boolean | No | Whether the action persists after being used. Default: `true`. | | `read_only` | boolean | No | Whether the action is restricted to read-only operations. Default: `false`. | | `state` | string | No | State of the action: `available` or `archived`. Default: `available`. | | `arguments` | list | No | Typed parameters that users supply when using the action. | | `automation_profile` | string | No | Default automation profile for plans created from this action. | | `invariants` | list | No | Constraints carried forward as plan-level invariants when the action is used. | **Argument Fields (`arguments[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Argument name. Used as the key in `--arg name=value`. | | `type` | string | Yes | Data type: `string`, `integer`, `float`, `boolean`, `list`. | | `required` | boolean | No | Whether the argument must be provided. Default: `false`. | | `description` | string | No | Human-readable description shown in help text and `agents action show`. | | `default` | any | No | Default value when the argument is not provided. Type must match `type`. | | `validation_pattern` | string | No | Regex pattern for validating string arguments. | | `min_value` | number | No | Minimum acceptable value for `integer` and `float` arguments. | | `max_value` | number | No | Maximum acceptable value for `integer` and `float` arguments. | #### Examples **Example 1: Simple Linting Action (Simple)** A minimal action for running linters on a project: 

# lint-check.yaml
# Create: agents action create --config lint-check.yaml

name: local/lint-check
description: "Run linting checks on the project"

strategy_actor: local/strategist
execution_actor: local/executor

definition_of_done: |
  All linting checks pass with zero errors.

reusable: true
read_only: true
state: available
Usage: `agents plan use local/lint-check local/api-service` --- **Example 2: Code Coverage Action with Arguments (Medium)** An action with typed arguments, invariants, and a specific automation profile: 

# code-coverage.yaml
# Create: agents action create --config code-coverage.yaml

name: local/code-coverage
description: "Increase test coverage to a target percentage"
long_description: |
  Analyzes the current test coverage of a project, identifies
  modules with low coverage, and generates comprehensive test
  suites to meet the target coverage percentage.

  The action prioritizes:
  1. Business-critical modules (auth, payments)
  2. Recently modified code
  3. Error-prone areas based on git history

strategy_actor: local/strategist
execution_actor: local/executor
estimation_actor: local/estimator

definition_of_done: |
  Test coverage reaches the target_coverage_percent threshold
  across all specified modules. All generated tests pass.
  No existing tests are broken by the changes.

reusable: true
read_only: false
arguments:
  - name: target_coverage_percent
    type: integer
    required: true
    description: "Target test coverage percentage (1-100)"
    min_value: 1
    max_value: 100

  - name: test_command
    type: string
    required: false
    description: "Test framework command to use"
    default: "pytest --cov"

  - name: exclude_patterns
    type: list
    required: false
    description: "File patterns to exclude from coverage analysis"
    default: ["**/migrations/**", "**/conftest.py"]

  - name: focus_modules
    type: list
    required: false
    description: "Specific modules to prioritize for coverage"

automation_profile: trusted

invariants:
  - "Generated tests must not import production secrets or credentials"
  - "Test files must follow the project's existing test naming conventions"
  - "All database interactions in tests must use mocks or fixtures"
Usage: `agents plan use local/code-coverage local/api-service --arg target_coverage_percent=85` --- **Example 3: Security Audit Action (Complex)** A comprehensive security audit action with multiple actors, extensive arguments, and strong invariants: 

# security-audit.yaml
# Create: agents action create --config security-audit.yaml

name: local/security-audit
description: "Comprehensive security audit of a project"
long_description: |
  Performs a thorough security audit covering:
  - Dependency vulnerability scanning (CVEs)
  - Static Application Security Testing (SAST)
  - Authentication and authorization review
  - Input validation and injection prevention
  - Secrets detection and credential scanning
  - API security (rate limiting, CORS, headers)
  - Data handling and privacy compliance

  Generates a detailed report with severity ratings (Critical,
  High, Medium, Low, Informational) and remediation guidance.
  Optionally creates fix plans for identified issues.

strategy_actor: local/security-strategist
execution_actor: local/security-scanner
estimation_actor: local/estimator
review_actor: local/security-reviewer
invariant_actor: local/invariant-resolver

definition_of_done: |
  All critical and high severity findings have been identified.
  A complete security report has been generated with:
  - Severity classification for each finding
  - Remediation steps for each finding
  - Risk score for the overall project
  If auto_fix is enabled, all critical findings have remediation
  plans created as child plans.

reusable: true
read_only: false
state: available

arguments:
  - name: severity_threshold
    type: string
    required: false
    description: "Minimum severity to include in report"
    default: "low"
    validation_pattern: "^(critical|high|medium|low|informational)$"

  - name: auto_fix
    type: boolean
    required: false
    description: "Automatically create fix plans for critical findings"
    default: false

  - name: scan_dependencies
    type: boolean
    required: false
    description: "Include dependency vulnerability scanning"
    default: true

  - name: compliance_frameworks
    type: list
    required: false
    description: "Compliance frameworks to check against"
    default: ["owasp-top-10"]

  - name: max_findings
    type: integer
    required: false
    description: "Maximum number of findings to report"
    default: 100
    min_value: 1
    max_value: 1000

  - name: ignore_paths
    type: list
    required: false
    description: "Paths to exclude from scanning"
    default: ["**/node_modules/**", "**/vendor/**", "**/.git/**"]

automation_profile: supervised

invariants:
  - "Never modify production database schemas during audit"
  - "Never execute discovered exploit code against live systems"
  - "All findings must include reproducible steps"
  - "Secrets found during scanning must be redacted in reports"
  - "Remediation fixes must not break existing tests"
Usage: `agents plan use local/security-audit local/api-service local/web-app --arg auto_fix=true --arg severity_threshold=medium` --- **Example 4: Database Migration Action (Medium)** An action for managing database schema migrations: 

# db-migrate.yaml
# Create: agents action create --config db-migrate.yaml

name: local/db-migrate
description: "Plan and execute database schema migrations"

strategy_actor: local/db-strategist
execution_actor: local/db-executor

definition_of_done: |
  All migration scripts are generated and pass dry-run validation.
  Rollback scripts are generated for each migration.
  The migration can be applied without data loss.

reusable: true
read_only: false

arguments:
  - name: migration_tool
    type: string
    required: false
    description: "Migration tool to use"
    default: "alembic"
    validation_pattern: "^(alembic|flyway|django|knex)$"

  - name: dry_run
    type: boolean
    required: false
    description: "Only generate and validate, do not apply"
    default: true

  - name: target_schema
    type: string
    required: false
    description: "Target schema version identifier"

automation_profile: supervised

invariants:
  - "All migrations must include corresponding rollback scripts"
  - "Data migrations must preserve existing data integrity"
  - "Schema changes must maintain backward compatibility for 24 hours"
--- ### Tool Configuration Files !!! adr "Architecture Decision" The tool configuration schema, source types, and capability metadata are defined in [ADR-011: Tool System](adr/ADR-011-tool-system.md). Tool configuration files define namespaced, independently registered, callable operations. Tools are the atomic unit of execution — each has a name, input/output schemas, capability metadata, and an implementation. Tools are registered via `agents tool add --config ` and can then be referenced by name in skills and actor graphs. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for tool configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/tool-config.json",
  "title": "CleverAgents Tool Configuration",
  "description": "Configuration file schema for defining CleverAgents tools — namespaced, independently registered, callable operations.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified tool name in <namespace>/<name> format."
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of the tool's purpose and behavior."
    },
    "source": {
      "type": "string",
      "enum": ["custom", "mcp", "agent_skill", "builtin"],
      "description": "Tool source type. Determines which implementation fields are required."
    },
    "code": {
      "type": "string",
      "description": "Python code implementing the tool. Required when source is 'custom'. Must define a run(input_data) function."
    },
    "mcp_server": {
      "type": "string",
      "description": "Name of the MCP server exposing this tool. Required when source is 'mcp'."
    },
    "mcp_tool_name": {
      "type": "string",
      "description": "Name of the tool on the MCP server. Required when source is 'mcp'."
    },
    "agent_skill_path": {
      "type": "string",
      "description": "Path to the Agent Skills Standard folder containing SKILL.md. Required when source is 'agent_skill'."
    },
    "input_schema": {
      "$ref": "https://json-schema.org/draft/2020-12/schema",
      "description": "JSON Schema describing the tool's input parameters."
    },
    "output_schema": {
      "$ref": "https://json-schema.org/draft/2020-12/schema",
      "description": "JSON Schema describing the tool's output format."
    },
    "writes": {
      "type": "boolean",
      "default": false,
      "description": "Whether the tool performs any write operations."
    },
    "write_scope": {
      "type": "string",
      "description": "Scope of write operations (e.g., 'filesystem', 'database:migrations', 'api:github')."
    },
    "checkpointable": {
      "type": "boolean",
      "default": false,
      "description": "Whether the tool supports checkpointing — saving state before execution and restoring on failure."
    },
    "checkpoint_scope": {
      "type": "string",
      "enum": ["file", "transaction", "snapshot", "composite"],
      "description": "The checkpointing strategy."
    },
    "side_effects": {
      "type": "array",
      "items": { "type": "string" },
      "default": [],
      "description": "Side effects that cannot be undone by checkpointing alone (e.g., 'network_call', 'schema_mutation', 'email_sent')."
    },
    "idempotent": {
      "type": "boolean",
      "default": false,
      "description": "Whether the tool is safe to retry — calling it multiple times with the same input produces the same result."
    },
    "read_only": {
      "type": "boolean",
      "default": false,
      "description": "Whether the tool only reads data without modifying anything."
    },
    "unsafe": {
      "type": "boolean",
      "default": false,
      "description": "Whether the tool is flagged as unsafe. Requires allow_unsafe_tools: true in the automation profile."
    },
    "timeout": {
      "type": "integer",
      "default": 300,
      "minimum": 1,
      "description": "Default execution timeout in seconds."
    },
    "resource_slots": {
      "type": "array",
      "description": "Declared resource dependencies for this tool.",
      "items": {
        "$ref": "#/$defs/resourceSlot"
      }
    },
    "lifecycle": {
      "type": "object",
      "description": "Lifecycle hook implementations.",
      "properties": {
        "discover": {
          "type": "string",
          "description": "Python code or function name run during tool discovery."
        },
        "activate": {
          "type": "string",
          "description": "Python code or function name run when the tool is activated."
        },
        "deactivate": {
          "type": "string",
          "description": "Python code or function name run when the tool is deactivated."
        }
      },
      "additionalProperties": false
    },
  },
  "required": ["name", "description", "source"],
  "allOf": [
    {
      "if": { "properties": { "source": { "const": "custom" } } },
      "then": { "required": ["code"] }
    },
    {
      "if": { "properties": { "source": { "const": "mcp" } } },
      "then": { "required": ["mcp_server", "mcp_tool_name"] }
    },
    {
      "if": { "properties": { "source": { "const": "agent_skill" } } },
      "then": { "required": ["agent_skill_path"] }
    }
  ],
  "additionalProperties": false,
  "$defs": {
    "resourceSlot": {
      "type": "object",
      "description": "A declared resource dependency slot.",
      "properties": {
        "name": {
          "type": "string",
          "description": "Identifier for this resource slot."
        },
        "resource_type": {
          "type": "string",
          "description": "The resource type this slot requires (e.g., 'git-checkout', 'fs-directory')."
        },
        "access": {
          "type": "string",
          "enum": ["read_only", "read_write"],
          "description": "Access level needed."
        },
        "description": {
          "type": "string",
          "description": "Human-readable description of how the tool uses this resource."
        },
        "binding": {
          "type": "string",
          "enum": ["contextual", "static", "parameter"],
          "default": "contextual",
          "description": "How the slot is resolved at runtime."
        },
        "static_resource": {
          "type": "string",
          "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
          "description": "Fully qualified name of a specific resource. Required when binding is 'static'."
        }
      },
      "required": ["name", "resource_type", "access"],
      "if": { "properties": { "binding": { "const": "static" } } },
      "then": { "required": ["name", "resource_type", "access", "static_resource"] },
      "additionalProperties": false
    }
  }
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Tool Identity ──────────────────────────────────────────────────
name: <namespace>/<name>            # Fully qualified tool name (required)
description: <string>               # Human-readable description (required)

# ─── Source and Implementation ──────────────────────────────────────
source: custom | mcp | agent_skill | builtin  # Tool source type (required)

# For source: custom — inline Python implementation
code: |                             # Python code with a run(input_data) function (required for custom)
  def run(input_data):
      param = input_data.get("param_name", "default")
      # ... tool logic ...
      return {"result": "value"}

# For source: mcp — tool exposed by an MCP server
mcp_server: <string>                # MCP server name (required for mcp)
mcp_tool_name: <string>             # Tool name on the MCP server (required for mcp)

# For source: agent_skill — tool from an Agent Skills Standard folder
agent_skill_path: <string>          # Path to the SKILL.md folder (required for agent_skill)

# ─── Input/Output Schema ────────────────────────────────────────────
input_schema:                       # JSON Schema for tool inputs (optional but recommended)
  type: object
  properties:
    param_name:
      type: string
      description: "Parameter description"
      enum: ["value1", "value2"]    # Enumerated valid values (optional)
      default: "value1"             # Default value (optional)
    numeric_param:
      type: integer
      description: "A numeric parameter"
      minimum: 0                    # Minimum value (optional)
      maximum: 100                  # Maximum value (optional)
  required: ["param_name"]          # Required parameters

output_schema:                      # JSON Schema for tool outputs (optional)
  type: object
  properties:
    result:
      type: string
    success:
      type: boolean

# ─── Capability Metadata ────────────────────────────────────────────
writes: false                       # Whether the tool performs write operations (optional, default: false)
write_scope: <string>               # Scope of writes, e.g. "filesystem", "database:migrations" (optional)
checkpointable: false               # Whether the tool supports checkpointing (optional, default: false)
checkpoint_scope: <string>          # Checkpointing strategy: "file", "transaction", "snapshot", "composite" (optional)
side_effects:                       # List of side effect types (optional)
  - <string>                        # e.g. "network_call", "schema_mutation", "process_spawn"
idempotent: false                   # Whether the tool is safe to retry (optional, default: false)
read_only: false                    # Whether the tool only reads (optional, default: false)
unsafe: false                       # Whether the tool is flagged as unsafe (optional, default: false)
timeout: 300                        # Default execution timeout in seconds (optional, default: 300)

# ─── Resource Bindings ──────────────────────────────────────────────
# Declare which resources this tool operates on.
resource_slots:
  - name: <string>                  # Slot name for reference (required)
    resource_type: <string>         # Required resource type, e.g. "git-checkout", "fs-directory" (required)
    access: read_only | read_write  # Access level needed (required)
    description: <string>           # Description of how the resource is used (optional)
    binding: contextual | static | parameter  # How the slot is resolved (optional, default: contextual)
    static_resource: <namespace>/<name>       # Specific resource (required when binding is static)

# ─── Lifecycle Hooks ────────────────────────────────────────────────
lifecycle:
  discover: <string>                # Python function or code for tool discovery (optional)
  activate: <string>                # Python function or code run when tool is activated (optional)
  deactivate: <string>              # Python function or code run when tool is deactivated (optional)
#### Structure Reference **Top-Level Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified tool name in `/` format. This value is used as the tool's registered name. | | `description` | string | Yes | Human-readable description of the tool's purpose and behavior. | | `source` | string | Yes | Tool source type. Determines which implementation fields are required: `custom` (inline Python), `mcp` (MCP server), `agent_skill` (SKILL.md folder), `builtin` (first-party operations). | | `code` | string | Conditional | Python code implementing the tool. Required when `source` is `custom`. Must define a `run(input_data)` function that accepts a dict and returns a dict. | | `mcp_server` | string | Conditional | Name of the MCP server exposing this tool. Required when `source` is `mcp`. | | `mcp_tool_name` | string | Conditional | Name of the tool on the MCP server. Required when `source` is `mcp`. | | `agent_skill_path` | string | Conditional | Path to the Agent Skills Standard folder containing `SKILL.md`. Required when `source` is `agent_skill`. | | `input_schema` | object | No | JSON Schema describing the tool's input parameters. Strongly recommended for all tools. | | `output_schema` | object | No | JSON Schema describing the tool's output format. | **Capability Metadata Fields** | Field | Type | Default | Description | |-------|------|---------|-------------| | `writes` | boolean | `false` | Whether the tool performs any write operations (file writes, database mutations, API calls with side effects). | | `write_scope` | string | — | Describes the scope of write operations, e.g. `"filesystem"`, `"database:migrations"`, `"api:github"`. Used for access checks and audit logging. | | `checkpointable` | boolean | `false` | Whether the tool supports checkpointing — the ability to save state before execution and restore it on failure. | | `checkpoint_scope` | string | — | The checkpointing strategy: `file` (file-level backup), `transaction` (database transaction), `snapshot` (full state snapshot), `composite` (multi-resource checkpoint). | | `side_effects` | list | `[]` | Descriptions of side effects that cannot be undone by checkpointing alone, e.g. `"network_call"`, `"schema_mutation"`, `"email_sent"`, `"process_spawn"`. | | `idempotent` | boolean | `false` | Whether the tool is safe to retry — calling it multiple times with the same input produces the same result. | | `read_only` | boolean | `false` | Whether the tool only reads data without modifying anything. When `true`, `writes` must be `false`. | | `unsafe` | boolean | `false` | Whether the tool is flagged as unsafe. Unsafe tools require `allow_unsafe_tools: true` in the automation profile. | | `timeout` | integer | `300` | Default execution timeout in seconds. Can be overridden per invocation. | **Resource Slot Fields (`resource_slots[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Identifier for this resource slot, used for reference in code and logs. | | `resource_type` | string | Yes | The resource type this slot requires, e.g. `git-checkout`, `fs-directory`, `fs-file`. | | `access` | string | Yes | Access level: `read_only` or `read_write`. | | `description` | string | No | Human-readable description of how the tool uses this resource. | | `binding` | string | No | How the slot is resolved at runtime. `contextual` (default): resolved from the plan's project. `static`: hardcoded to a specific resource. `parameter`: passed as a tool argument at invocation time. | | `static_resource` | string | Conditional | Fully qualified name of a specific resource. Required when `binding` is `static`. | **Lifecycle Hook Fields (`lifecycle`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `discover` | string | No | Code or function name run during tool discovery to check prerequisites and report capabilities. | | `activate` | string | No | Code or function name run when the tool is activated (e.g., establish connections, validate credentials). | | `deactivate` | string | No | Code or function name run when the tool is deactivated (e.g., close connections, release resources). | #### Examples **Example 1: Simple Read-Only Tool (Simple)** A tool that reads a file and returns its contents: 

# read-config-file.yaml
# Register: agents tool add --config read-config-file.yaml

name: local/read-config
description: "Read and parse a configuration file (JSON, YAML, or TOML)"

source: custom
code: |
  import json, os
  def run(input_data):
      path = input_data["path"]
      if not os.path.exists(path):
          return {"error": f"File not found: {path}", "success": False}
      with open(path, "r") as f:
          content = f.read()
      ext = os.path.splitext(path)[1].lower()
      if ext == ".json":
          parsed = json.loads(content)
      elif ext in (".yaml", ".yml"):
          import yaml
          parsed = yaml.safe_load(content)
      else:
          parsed = None
      return {"content": content, "parsed": parsed, "path": path, "success": True}

input_schema:
  type: object
  properties:
    path:
      type: string
      description: "Path to the configuration file"
  required: ["path"]

output_schema:
  type: object
  properties:
    content:
      type: string
    parsed:
      type: object
    success:
      type: boolean

writes: false
read_only: true
idempotent: true
--- **Example 2: Database Migration Tool (Medium)** A tool that runs database migrations with rollback support: 

# run-migrations.yaml
# Register: agents tool add --config run-migrations.yaml

name: local/run-migrations
description: "Run database migrations with direction control and rollback support"

source: custom
code: |
  import subprocess
  def run(input_data):
      direction = input_data.get("direction", "up")
      count = input_data.get("count", 1)
      dry_run = input_data.get("dry_run", False)

      cmd = ["alembic"]
      if dry_run:
          cmd.append("--sql")
      cmd.extend([direction, str(count)])

      result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
      return {
          "success": result.returncode == 0,
          "stdout": result.stdout,
          "stderr": result.stderr,
          "direction": direction,
          "count": count,
          "dry_run": dry_run,
          "return_code": result.returncode
      }

input_schema:
  type: object
  properties:
    direction:
      type: string
      enum: ["up", "down"]
      description: "Migration direction: 'up' to apply, 'down' to rollback"
    count:
      type: integer
      default: 1
      minimum: 1
      maximum: 50
      description: "Number of migrations to run"
    dry_run:
      type: boolean
      default: false
      description: "Generate SQL without executing"
  required: ["direction"]

writes: true
write_scope: "database:migrations"
checkpointable: true
checkpoint_scope: "transaction"
side_effects:
  - "schema_mutation"
idempotent: false
timeout: 120

resource_slots:
  - name: database
    resource_type: "local/database"
    access: read_write
    description: "The database to run migrations against"
    binding: contextual
--- **Example 3: MCP-Backed GitHub Tool (Simple)** A tool that delegates to a GitHub MCP server: 

# github-create-issue.yaml
# Register: agents tool add --config github-create-issue.yaml

name: local/github-create-issue
description: "Create a GitHub issue via the GitHub MCP server"

source: mcp
mcp_server: github
mcp_tool_name: create_issue

input_schema:
  type: object
  properties:
    owner:
      type: string
      description: "Repository owner"
    repo:
      type: string
      description: "Repository name"
    title:
      type: string
      description: "Issue title"
    body:
      type: string
      description: "Issue body (Markdown)"
    labels:
      type: array
      items:
        type: string
      description: "Labels to apply"
  required: ["owner", "repo", "title"]

writes: true
write_scope: "api:github"
checkpointable: false
side_effects:
  - "network_call"
idempotent: false
--- **Example 4: Deployment Tool with Resource Bindings (Complex)** A comprehensive deployment tool with multiple resource slots, lifecycle hooks, and safety metadata: 

# deploy-staging.yaml
# Register: agents tool add --config deploy-staging.yaml

name: local/deploy-staging
description: "Deploy the current build to the staging environment with health checks"

source: custom
code: |
  import subprocess, time, urllib.request, json

  def run(input_data):
      service = input_data["service"]
      version = input_data.get("version", "latest")
      wait_healthy = input_data.get("wait_healthy", True)
      health_timeout = input_data.get("health_timeout", 120)

      # Build the deployment command
      cmd = ["kubectl", "set", "image",
             f"deployment/{service}",
             f"{service}={service}:{version}",
             "--namespace=staging"]
      result = subprocess.run(cmd, capture_output=True, text=True, timeout=60)
      if result.returncode != 0:
          return {"success": False, "error": result.stderr, "phase": "deploy"}

      # Wait for rollout
      rollout = subprocess.run(
          ["kubectl", "rollout", "status", f"deployment/{service}",
           "--namespace=staging", f"--timeout={health_timeout}s"],
          capture_output=True, text=True, timeout=health_timeout + 10
      )
      if rollout.returncode != 0:
          return {"success": False, "error": rollout.stderr, "phase": "rollout"}

      # Health check
      if wait_healthy:
          health_url = f"http://{service}.staging.svc.cluster.local/health"
          start = time.time()
          while time.time() - start < health_timeout:
              try:
                  resp = urllib.request.urlopen(health_url, timeout=5)
                  if resp.status == 200:
                      body = json.loads(resp.read())
                      if body.get("status") == "healthy":
                          return {
                              "success": True,
                              "service": service,
                              "version": version,
                              "health": body
                          }
              except Exception:
                  pass
              time.sleep(5)
          return {"success": False, "error": "Health check timeout", "phase": "health"}

      return {"success": True, "service": service, "version": version}

input_schema:
  type: object
  properties:
    service:
      type: string
      description: "Name of the service to deploy"
    version:
      type: string
      default: "latest"
      description: "Docker image version tag"
    wait_healthy:
      type: boolean
      default: true
      description: "Wait for health check to pass"
    health_timeout:
      type: integer
      default: 120
      minimum: 10
      maximum: 600
      description: "Health check timeout in seconds"
  required: ["service"]

output_schema:
  type: object
  properties:
    success:
      type: boolean
    service:
      type: string
    version:
      type: string
    error:
      type: string
    phase:
      type: string

writes: true
write_scope: "infrastructure:kubernetes"
checkpointable: true
checkpoint_scope: "composite"
side_effects:
  - "network_call"
  - "process_spawn"
  - "infrastructure_mutation"
idempotent: false
unsafe: true
timeout: 300

resource_slots:
  - name: repo
    resource_type: git-checkout
    access: read_only
    description: "Source repository for build artifacts"
    binding: contextual
  - name: cluster_config
    resource_type: fs-file
    access: read_only
    description: "Kubernetes cluster configuration (kubeconfig)"
    binding: static
    static_resource: local/staging-kubeconfig

lifecycle:
  activate: |
    def activate(context):
        import subprocess
        result = subprocess.run(["kubectl", "cluster-info"], capture_output=True, text=True)
        if result.returncode != 0:
            raise RuntimeError("Cannot connect to Kubernetes cluster")
        return {"cluster": "connected"}
  deactivate: |
    def deactivate(context):
        pass  # No cleanup needed
--- **Example 5: API Compatibility Checker (Medium)** A tool that validates API backward compatibility: 

# validate-api-compat.yaml
# Register: agents tool add --config validate-api-compat.yaml

name: local/validate-api-compat
description: "Validate that API changes maintain backward compatibility with existing clients"

source: custom
code: |
  import subprocess, json

  def run(input_data):
      spec_path = input_data.get("spec_path", "openapi.yaml")
      base_branch = input_data.get("base_branch", "main")

      # Get the base spec from the main branch
      base_result = subprocess.run(
          ["git", "show", f"{base_branch}:{spec_path}"],
          capture_output=True, text=True
      )
      if base_result.returncode != 0:
          return {"compatible": True, "reason": "No base spec found (new API)", "changes": []}

      # Run OpenAPI diff
      diff_result = subprocess.run(
          ["oasdiff", "breaking", "--format", "json",
           "--base", "/dev/stdin", "--revision", spec_path],
          input=base_result.stdout,
          capture_output=True, text=True
      )

      if diff_result.returncode == 0:
          return {"compatible": True, "changes": [], "reason": "No breaking changes"}

      try:
          breaking = json.loads(diff_result.stdout)
      except json.JSONDecodeError:
          breaking = [{"description": diff_result.stdout}]

      return {
          "compatible": False,
          "changes": breaking,
          "reason": f"Found {len(breaking)} breaking change(s)"
      }

input_schema:
  type: object
  properties:
    spec_path:
      type: string
      default: "openapi.yaml"
      description: "Path to the OpenAPI specification file"
    base_branch:
      type: string
      default: "main"
      description: "Branch to compare against for backward compatibility"
  required: []

writes: false
read_only: true
checkpointable: false
idempotent: true
timeout: 60

resource_slots:
  - name: repo
    resource_type: git-checkout
    access: read_only
    description: "Git repository containing the API spec"
    binding: contextual
--- ### Validation Configuration Files !!! adr "Architecture Decision" The validation configuration schema and read-only enforcement are defined in [ADR-013: Validation Abstraction](adr/ADR-013-validation-abstraction.md). Validation configuration files define Validations — a specialized subtype of Tool. A Validation YAML file uses the **same format** as a Tool YAML file, with an additional `validation` block containing the validation-specific metadata. Because Validation extends Tool, all tool fields (`name`, `description`, `source`, `code`, `input_schema`, `output_schema`, capability metadata, resource bindings, lifecycle hooks) are available and behave identically. Validations are registered via `agents validation add --config `. **Read-only enforcement**: Validations are always read-only. The `writes` and `checkpointable` fields are always forced to `false` regardless of what the YAML file specifies — if a validation YAML includes `writes: true` or `checkpointable: true`, these values are silently overridden to `false` at registration time. Because this is enforced, it is idiomatic to omit `read_only`, `writes`, and `checkpointable` from validation YAML files entirely (they are unnecessary). The examples below include `read_only: true` for documentation clarity, but it is not required. **Shared namespace**: The `name` field in a validation YAML occupies the same namespace as tools. Registration will fail if a tool with the same name already exists. #### Validation-Specific Fields In addition to all fields from the Tool Configuration schema, a Validation YAML adds: | Field | Type | Default | Description | |-------|------|---------|-------------| | `validation.mode` | string | `"required"` | `"required"` or `"informational"`. Required validations must pass for execution to proceed; informational validations report results without blocking. | | `wraps` | string | (none) | Name of an existing registered Tool to wrap. When set, the Validation delegates execution to the wrapped Tool and passes its output through the `transform` function. Mutually exclusive with `source` and `code`. | | `transform` | string | (none) | Python function that converts the wrapped Tool's output to the Validation return format. Required when `wraps` is set (unless the wrapped Tool already returns validation-format output). The function receives the Tool's output as its argument and must return `{ "passed": bool, ... }`. | | `argument_mapping` | object | (none) | Dictionary mapping the wrapped Tool's input parameter names to either a Validation input parameter name (string) or a fixed literal value. When present, only mapped arguments are forwarded to the wrapped Tool. When absent, the Validation's input arguments are passed through unchanged. Only valid when `wraps` is set. | When `wraps` is used, the `source` and `code` fields must be omitted — the Validation's implementation is the wrapped Tool plus the transform. The Validation inherits the wrapped Tool's `input_schema`, `resource_slots`, and `timeout` unless explicitly overridden. When the Validation defines a custom `input_schema`, an `argument_mapping` should be provided to specify how the Validation's inputs map to the wrapped Tool's expected inputs. See the **Tool Wrapping** subsection under Core Concepts > Validation for full semantics. The output of a validation tool must conform to a structured JSON format: | Field | Type | Required | Description | |-------|------|----------|-------------| | `passed` | boolean | Yes | Whether the validation passed (`true`) or failed (`false`). | | `message` | string | No | Human-readable summary of the validation result. | | `data` | object | No | Arbitrary structured data in any format the validation chooses to convey informational output about the result. | #### Examples **Example 1: Unit Test Validation (Required)** 

# validations/run-tests.yaml
# Register: agents validation add --config validations/run-tests.yaml

name: local/run-tests
description: "Run unit tests with coverage and report pass/fail"

source: custom
code: |
  import subprocess, json
  def run(input_data):
      threshold = input_data.get("coverage_threshold", 80)
      result = subprocess.run(
          ["pytest", "--cov=src", f"--cov-fail-under={threshold}", "--tb=short", "-q"],
          capture_output=True, text=True
      )
      passed = result.returncode == 0
      return {
          "passed": passed,
          "message": "All tests passed" if passed else f"Tests failed (exit code {result.returncode})",
          "data": {
              "stdout": result.stdout,
              "stderr": result.stderr,
              "returncode": result.returncode,
              "coverage_threshold": threshold
          }
      }

validation:
  mode: required

input_schema:
  type: object
  properties:
    coverage_threshold:
      type: integer
      default: 80
      description: "Minimum coverage percentage required"

read_only: true
idempotent: true
timeout: 600

resource_slots:
  - name: repo
    resource_type: git-checkout
    access: read_only
    binding: contextual
--- **Example 2: Lint Check Validation (Required, Simple)** 

# validations/lint-check.yaml

name: local/lint-check
description: "Run linter and report pass/fail"

source: custom
code: |
  import subprocess
  def run(input_data):
      result = subprocess.run(["ruff", "check", "."], capture_output=True, text=True)
      passed = result.returncode == 0
      return {
          "passed": passed,
          "message": "Lint clean" if passed else f"Lint errors found",
          "data": {"stdout": result.stdout, "stderr": result.stderr}
      }

validation:
  mode: required

read_only: true
idempotent: true
timeout: 300
--- **Example 3: Bundle Size Check (Informational)** 

# validations/check-bundle-size.yaml

name: local/check-bundle-size
description: "Check bundle size (advisory — does not block execution)"

source: custom
code: |
  import subprocess, json
  def run(input_data):
      result = subprocess.run(["node", "scripts/check-bundle-size.js"], capture_output=True, text=True)
      try:
          size_data = json.loads(result.stdout)
      except json.JSONDecodeError:
          size_data = {"raw_output": result.stdout}
      passed = result.returncode == 0
      return {
          "passed": passed,
          "message": "Bundle size within limits" if passed else "Bundle size exceeds advisory threshold",
          "data": size_data
      }

validation:
  mode: informational

read_only: true
timeout: 120
--- **Example 4: MCP-Backed Validation** A validation that uses an MCP server to perform security scanning: 

# validations/security-scan.yaml

name: local/security-scan
description: "Run security vulnerability scan via MCP"

source: mcp
mcp_server: "npx @security/mcp-scanner"
mcp_tool_name: scan_vulnerabilities

validation:
  mode: required

read_only: true
timeout: 300
--- **Example 5: Wrapping an Existing Tool** A validation that wraps an existing `local/run-tests` tool, reusing its implementation and interpreting its output as pass/fail. No test-running logic is duplicated — only the pass/fail interpretation is defined. 

# validations/tests-pass.yaml
# Assumes local/run-tests is already registered as a Tool that runs
# the test suite and returns {returncode, tests_run, tests_passed, ...}

name: local/tests-pass
description: "Validate that all unit tests pass (wraps local/run-tests)"

wraps: local/run-tests

transform: |
  def transform(tool_output):
      passed = tool_output.get("returncode") == 0
      tests_run = tool_output.get("tests_run", 0)
      tests_passed = tool_output.get("tests_passed", 0)
      return {
          "passed": passed,
          "message": f"{tests_passed}/{tests_run} tests passed" if passed
                     else f"{tests_run - tests_passed} tests failed",
          "data": tool_output
      }

validation:
  mode: required

timeout: 600
Note: `source`, `code`, `input_schema`, and `resource_slots` are omitted — they are inherited from the wrapped `local/run-tests` tool. Only the `transform`, `validation.mode`, and optional overrides (like `timeout`) are needed. If the Validation defines a custom `input_schema`, an `argument_mapping` should also be provided to map the Validation's inputs to the wrapped Tool's expected inputs. --- **Example 6: Wrapping with Different Interpretation (Informational)** A second validation wrapping the same tool but extracting a different signal — coverage threshold — as an advisory check: 

# validations/coverage-check.yaml

name: local/coverage-check
description: "Check test coverage exceeds threshold (advisory)"

wraps: local/run-tests

transform: |
  def transform(tool_output):
      coverage = tool_output.get("coverage_percent", 0)
      threshold = 80
      return {
          "passed": coverage >= threshold,
          "message": f"Coverage: {coverage:.1f}% (threshold: {threshold}%)",
          "data": {
              "coverage_percent": coverage,
              "threshold": threshold,
              "above_threshold": coverage >= threshold
          }
      }

validation:
  mode: informational
--- ### Resource Type Configuration Files !!! adr "Architecture Decision" The resource type system, custom type registration, and type hierarchy are defined in [ADR-008: Resource System](adr/ADR-008-resource-system.md). Resource type configuration files define custom resource type schemas that extend the built-in resource types (`git-checkout`, `git`, `fs-mount`, `fs-directory`, etc.). A resource type defines what CLI arguments `agents resource add ` accepts, whether instances are physical or virtual, allowed child/parent types, auto-discovery behavior, sandbox strategy, and handler implementation. Custom types are registered via `agents resource type add --config `. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for resource type configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/resource-type-config.json",
  "title": "CleverAgents Resource Type Configuration",
  "description": "Configuration file schema for defining custom resource types that extend the built-in resource types.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified resource type name in <namespace>/<name> format."
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of what this resource type represents."
    },
    "physical": {
      "type": "boolean",
      "description": "true for physical types (concrete manifestations), false for virtual types (abstract identity linking equivalent physical resources)."
    },
    "user_addable": {
      "type": "boolean",
      "default": true,
      "description": "Whether users can create instances directly via 'agents resource add <type>'."
    },
    "cli_args": {
      "type": "array",
      "description": "Arguments accepted by 'agents resource add <type>'.",
      "items": {
        "$ref": "#/$defs/cliArg"
      }
    },
    "child_types": {
      "type": "array",
      "description": "Resource types that can be children of this type.",
      "items": {
        "$ref": "#/$defs/childType"
      }
    },
    "parent_types": {
      "type": "array",
      "description": "Resource types that can be parents of this type. If omitted, the resource can be top-level.",
      "items": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "description": "Parent resource type name."
          },
          "description": {
            "type": "string",
            "description": "Description of the parent-child relationship from the child's perspective."
          }
        },
        "required": ["type"],
        "additionalProperties": false
      }
    },
    "sandbox_strategy": {
      "type": "string",
      "enum": ["git_worktree", "copy_on_write", "transaction_rollback", "snapshot", "none"],
      "description": "Sandbox strategy for instances of this type."
    },
    "handler": {
      "type": "object",
      "description": "The Python handler class that implements resource operations.",
      "properties": {
        "class": {
          "type": "string",
          "description": "Python class name that implements the resource handler interface."
        },
        "module": {
          "type": "string",
          "description": "Python module path where the handler class is defined."
        },
        "config": {
          "type": "object",
          "description": "Arbitrary configuration passed to the handler constructor.",
          "additionalProperties": true
        }
      },
      "required": ["class", "module"],
      "additionalProperties": false
    },
    "auto_discovery": {
      "type": "object",
      "description": "Controls automatic child resource discovery when a resource of this type is created.",
      "properties": {
        "enabled": {
          "type": "boolean",
          "default": true,
          "description": "Whether auto-discovery runs when a resource of this type is created."
        },
        "scan_depth": {
          "type": "integer",
          "default": 3,
          "minimum": 1,
          "description": "Maximum recursion depth for scanning."
        },
        "include_patterns": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Glob patterns for resources to discover."
        },
        "exclude_patterns": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Glob patterns for resources to skip during discovery."
        }
      },
      "additionalProperties": false
    },
    "equivalence": {
      "type": "object",
      "description": "Equivalence criteria for virtual types. Only applicable when physical is false.",
      "properties": {
        "criteria": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Fields used to determine equivalence (e.g., 'content_hash', 'filename', 'permissions', 'url')."
        },
        "description": {
          "type": "string",
          "description": "Human-readable description of the equivalence rule."
        }
      },
      "required": ["criteria"],
      "additionalProperties": false
    },
  },
  "required": ["name", "description", "physical", "sandbox_strategy", "handler"],
  "if": {
    "properties": { "physical": { "const": false } }
  },
  "then": {
    "required": ["name", "description", "physical", "sandbox_strategy", "handler", "equivalence"]
  },
  "additionalProperties": false,
  "$defs": {
    "cliArg": {
      "type": "object",
      "description": "A CLI argument definition for 'agents resource add <type>'.",
      "properties": {
        "name": {
          "type": "string",
          "description": "Argument name. Becomes --<name> on the CLI."
        },
        "type": {
          "type": "string",
          "enum": ["string", "path", "integer", "boolean", "url"],
          "description": "Argument type. 'path' validates that the path exists; 'url' validates URL format."
        },
        "required": {
          "type": "boolean",
          "default": false,
          "description": "Whether the argument must be provided."
        },
        "description": {
          "type": "string",
          "description": "Description shown in --help."
        },
        "default": {
          "description": "Default value when the argument is not provided."
        },
        "validation_pattern": {
          "type": "string",
          "description": "Regex pattern for validating string and url type arguments."
        }
      },
      "required": ["name", "type"],
      "additionalProperties": false
    },
    "childType": {
      "type": "object",
      "description": "An allowed child resource type relationship.",
      "properties": {
        "type": {
          "type": "string",
          "description": "Child resource type name."
        },
        "auto_discover": {
          "type": "boolean",
          "default": false,
          "description": "Whether children of this type are automatically created when the parent resource is registered."
        },
        "manual_link": {
          "type": "boolean",
          "default": true,
          "description": "Whether manual 'agents resource link-child' is allowed for this relationship."
        },
        "description": {
          "type": "string",
          "description": "Description of the parent-child relationship."
        },
        "max_count": {
          "type": ["integer", "null"],
          "minimum": 1,
          "description": "Maximum number of children of this type. null or omitted means unlimited."
        }
      },
      "required": ["type"],
      "additionalProperties": false
    }
  }
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Resource Type Identity ─────────────────────────────────────────
name: <namespace>/<name>            # Fully qualified resource type name (required)
description: <string>               # Human-readable description (required)

# ─── Type Classification ────────────────────────────────────────────
physical: true                      # Whether instances are physical or virtual (required)
                                    # Physical: a specific, concrete manifestation (this file at this path)
                                    # Virtual: an abstract identity linking equivalent physical resources
user_addable: true                  # Whether users can create instances directly (optional, default: true)

# ─── Type Inheritance ───────────────────────────────────────────────
inherits: <parent-type-name>        # Parent resource type to inherit from (optional)
                                    # Subtypes inherit all fields from the parent type.
                                    # Only fields that differ from or extend the parent need to be declared.
                                    # See ADR-042 for full inheritance semantics.

# ─── CLI Arguments ──────────────────────────────────────────────────
# Define the arguments accepted by `agents resource add <type>`.
cli_args:
  - name: <string>                  # Argument name (becomes --<name> on CLI) (required)
    type: string | path | integer | boolean | url  # Argument type (required)
    required: true                  # Whether the argument is required (optional, default: false)
    description: <string>           # Description shown in help text (optional)
    default: <value>                # Default value (optional)
    validation_pattern: <regex>     # Regex validation for string/url types (optional)

# ─── Parent/Child Type Relationships ────────────────────────────────
# Define which resource types can be children of this type.
child_types:
  - type: <string>                  # Child resource type name (required)
    auto_discover: true             # Automatically create children when parent is created (optional, default: false)
    manual_link: true               # Allow manual parent-child linking (optional, default: true)
    description: <string>           # Description of the relationship (optional)
    max_count: <integer>            # Maximum number of children of this type (optional, null = unlimited)

# Define which resource types can be parents of this type.
parent_types:
  - type: <string>                  # Parent resource type name (required)
    description: <string>           # Description of the relationship (optional)
# If parent_types is omitted, the resource can be top-level (no parent required).

# ─── Sandbox Strategy ──────────────────────────────────────────────
sandbox_strategy: <string>          # Sandbox strategy for instances of this type (required)
                                    # Built-in strategies: "git_worktree", "copy_on_write",
                                    # "transaction_rollback", "snapshot", "none"

# ─── Handler Implementation ────────────────────────────────────────
handler:
  class: <string>                   # Python class implementing the resource handler (required)
  module: <string>                  # Python module path (required)
  config: {}                        # Handler-specific configuration (optional)

# ─── Auto-Discovery Configuration ──────────────────────────────────
auto_discovery:
  enabled: true                     # Whether child auto-discovery runs on creation (optional, default: true)
  scan_depth: <integer>             # Max depth for recursive scanning (optional, default: 3)
  include_patterns:                 # Glob patterns for resources to auto-discover (optional)
    - <string>
  exclude_patterns:                 # Glob patterns to exclude from auto-discovery (optional)
    - <string>

# ─── Virtual Type Configuration ─────────────────────────────────────
# Only applicable when physical: false (virtual types).
equivalence:
  criteria:                         # Fields used to determine equivalence (required for virtual)
    - <string>                      # e.g. "content_hash", "filename", "permissions", "url"
  description: <string>             # Human-readable description of the equivalence rule (optional)
#### Structure Reference **Top-Level Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified resource type name in `/` format. This value is used as the resource type's registered name. | | `description` | string | Yes | Human-readable description of what this resource type represents. | | `physical` | boolean | Yes | `true` for physical types (concrete manifestations), `false` for virtual types (abstract identity linking equivalent physical resources). | | `user_addable` | boolean | No | Whether users can create instances directly via `agents resource add `. Default: `true`. When `false`, instances are only created via auto-discovery as children of other resources. | | `inherits` | string | No | Parent resource type name to inherit from. Subtypes inherit all properties, capabilities, child types, sandbox strategy, and handler behavior from the parent. Only fields that differ from or extend the parent need to be declared. Collection fields (`cli_args`, `child_types`, `parent_types`) use additive merging by default; use `_replace: true` to replace entirely. Single inheritance only; maximum chain depth of 5. See [ADR-042](adr/ADR-042-resource-type-inheritance.md). | | `sandbox_strategy` | string | Yes (unless inherited) | The sandbox strategy used when executing within this resource type. Inherited from parent type if `inherits` is set and field is omitted. | | `handler` | object | Yes (unless inherited) | The Python handler class that implements resource operations. Inherited from parent type if `inherits` is set and field is omitted; subtypes typically override with a subclass handler. | **CLI Argument Fields (`cli_args[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Argument name. Becomes `--` on the CLI. | | `type` | string | Yes | Argument type: `string`, `path`, `integer`, `boolean`, `url`. The `path` type validates that the path exists; `url` type validates URL format. | | `required` | boolean | No | Whether the argument must be provided. Default: `false`. | | `description` | string | No | Description shown in `--help` and `agents resource type show`. | | `default` | any | No | Default value when the argument is not provided. | | `validation_pattern` | string | No | Regex pattern for validating `string` and `url` type arguments. | **Child Type Fields (`child_types[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `type` | string | Yes | Name of the allowed child resource type (e.g., `fs-directory`, `svn-file`). | | `auto_discover` | boolean | No | Whether children of this type are automatically created when the parent resource is registered. Default: `false`. | | `manual_link` | boolean | No | Whether manual `agents resource link-child` is allowed for this relationship. Default: `true`. | | `description` | string | No | Description of the parent-child relationship. | | `max_count` | integer | No | Maximum number of children of this type. `null` or omitted means unlimited. | **Parent Type Fields (`parent_types[]`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `type` | string | Yes | Name of the allowed parent resource type. | | `description` | string | No | Description of the parent-child relationship from the child's perspective. | **Handler Fields (`handler`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `class` | string | Yes | Python class name that implements the resource handler interface. | | `module` | string | Yes | Python module path where the handler class is defined. | | `config` | object | No | Arbitrary configuration passed to the handler constructor. | **Auto-Discovery Fields (`auto_discovery`)** | Field | Type | Required | Description | |-------|------|----------|-------------| | `enabled` | boolean | No | Whether auto-discovery runs when a resource of this type is created. Default: `true`. | | `scan_depth` | integer | No | Maximum recursion depth for scanning. Default: `3`. | | `include_patterns` | list | No | Glob patterns for resources to discover. | | `exclude_patterns` | list | No | Glob patterns for resources to skip during discovery. | **Equivalence Fields (`equivalence`) — Virtual Types Only** | Field | Type | Required | Description | |-------|------|----------|-------------| | `criteria` | list | Yes (virtual) | Fields used to determine whether two physical resources are equivalent. Common criteria: `content_hash`, `filename`, `permissions`, `url`, `commit_hash`, `tree_hash`. | | `description` | string | No | Human-readable description of the equivalence rule. | **Built-in Sandbox Strategies** | Strategy | Description | |----------|-------------| | `git_worktree` | Creates a git worktree for isolated execution. Changes are committed to a branch and merged on apply. | | `copy_on_write` | Creates a CoW copy of the resource. Changes are applied by replacing the original. | | `transaction_rollback` | Wraps operations in a database transaction. Rolled back on failure, committed on apply. | | `snapshot` | Takes a full snapshot before execution. Restored on rollback. | | `none` | No sandbox. Changes are applied directly. Use only for read-only or idempotent operations. | #### Examples **Example 1: Simple SVN Repository Type (Simple)** A custom resource type for Subversion repositories: 

# svn-type.yaml
# Register: agents resource type add --config svn-type.yaml

name: local/svn
description: "A Subversion (SVN) repository checkout"

physical: true
user_addable: true

cli_args:
  - name: url
    type: url
    required: true
    description: "SVN repository URL"
    validation_pattern: "^svn(\\+ssh)?://.*|^https?://.*"
  - name: checkout-path
    type: path
    required: true
    description: "Local checkout directory"
  - name: revision
    type: string
    required: false
    description: "Specific revision to checkout"
    default: "HEAD"

child_types:
  - type: fs-directory
    auto_discover: true
    description: "Working copy directory tree"
  - type: local/svn-revision
    auto_discover: true
    description: "SVN revision history"

sandbox_strategy: copy_on_write

handler:
  class: SVNHandler
  module: cleveragents.resource.handlers.svn
  config:
    svn_binary: "svn"
    trust_server_cert: true

auto_discovery:
  enabled: true
  scan_depth: 2
  exclude_patterns:
    - "**/.svn/**"
Usage: `agents resource add local/svn local/legacy-repo --url svn://svn.example.com/trunk --checkout-path /repos/legacy` --- **Example 2: S3 Bucket Resource Type (Medium)** A resource type for Amazon S3 buckets with prefix-based child discovery: 

# s3-bucket-type.yaml
# Register: agents resource type add --config s3-bucket-type.yaml

name: local/s3-bucket
description: "An Amazon S3 bucket with prefix-based object organization"

physical: true
user_addable: true

cli_args:
  - name: bucket
    type: string
    required: true
    description: "S3 bucket name"
    validation_pattern: "^[a-z0-9][a-z0-9.-]{1,61}[a-z0-9]$"
  - name: region
    type: string
    required: false
    description: "AWS region"
    default: "us-east-1"
  - name: prefix
    type: string
    required: false
    description: "Key prefix to scope resource to a 'subdirectory'"
    default: ""
  - name: profile
    type: string
    required: false
    description: "AWS CLI profile name"
    default: "default"

child_types:
  - type: local/s3-prefix
    auto_discover: true
    description: "S3 key prefixes (virtual directories)"
    max_count: 1000
  - type: local/s3-object
    auto_discover: true
    description: "S3 objects (files)"

sandbox_strategy: copy_on_write

handler:
  class: S3BucketHandler
  module: cleveragents.resource.handlers.s3
  config:
    max_object_size: 104857600  # 100 MB
    default_acl: "private"

auto_discovery:
  enabled: true
  scan_depth: 3
  include_patterns:
    - "**/*.json"
    - "**/*.yaml"
    - "**/*.yml"
    - "**/*.py"
    - "**/*.sql"
  exclude_patterns:
    - "**/*.log"
    - "**/*.tmp"
    - "**/node_modules/**"
--- **Example 3: Database Resource Type (Medium)** A resource type for relational databases: 

# database-type.yaml
# Register: agents resource type add --config database-type.yaml

name: local/database
description: "A relational database (PostgreSQL, MySQL, SQLite)"

physical: true
user_addable: true

cli_args:
  - name: connection-string
    type: string
    required: true
    description: "Database connection string (e.g., postgresql://user:pass@host/db)"
  - name: engine
    type: string
    required: false
    description: "Database engine"
    default: "postgresql"
    validation_pattern: "^(postgresql|mysql|sqlite|mssql)$"
  - name: read-only
    type: boolean
    required: false
    description: "Connect in read-only mode"
    default: false
  - name: schema
    type: string
    required: false
    description: "Database schema to scope to"
    default: "public"

child_types:
  - type: local/db-table
    auto_discover: true
    description: "Database tables"
  - type: local/db-view
    auto_discover: true
    description: "Database views"
  - type: local/db-migration
    auto_discover: false
    manual_link: true
    description: "Migration scripts linked to this database"

parent_types:
  - type: git-checkout
    description: "Repository containing the application that owns this database"

sandbox_strategy: transaction_rollback

handler:
  class: DatabaseHandler
  module: cleveragents.resource.handlers.database
  config:
    connection_pool_size: 5
    statement_timeout: 30000  # 30 seconds
    log_queries: true

auto_discovery:
  enabled: true
  scan_depth: 1
--- **Example 4: Virtual File Type (Simple)** A virtual resource type that links equivalent physical files across repositories: 

# virtual-config-file-type.yaml
# Register: agents resource type add --config virtual-config-file-type.yaml

name: local/config-file
description: "Virtual type linking equivalent configuration files across repositories"

physical: false
user_addable: false

child_types:
  - type: fs-file
    auto_discover: false
    manual_link: true
    description: "Physical file instances"
  - type: git-tree-entry
    auto_discover: false
    manual_link: true
    description: "Git tree entries representing the same config file"

sandbox_strategy: none

handler:
  class: VirtualConfigFileHandler
  module: cleveragents.resource.handlers.virtual_config
  config:
    track_content_drift: true

equivalence:
  criteria:
    - content_hash
    - filename
  description: "Two physical resources represent the same config file when they share the same filename and content hash"
--- **Example 5: Docker Registry Resource Type (Complex)** A resource type for Docker container registries with full auto-discovery and lifecycle hooks: 

# docker-registry-type.yaml
# Register: agents resource type add --config docker-registry-type.yaml

name: local/docker-registry
description: "A Docker container registry with image and tag discovery"

physical: true
user_addable: true

cli_args:
  - name: registry-url
    type: url
    required: true
    description: "Docker registry URL (e.g., registry.example.com, ghcr.io/org)"
    validation_pattern: "^[a-zA-Z0-9][a-zA-Z0-9.-]+(:[0-9]+)?(/[a-zA-Z0-9._-]+)*$"
  - name: username
    type: string
    required: false
    description: "Registry username for authentication"
  - name: password-env
    type: string
    required: false
    description: "Environment variable name containing the registry password"
  - name: namespace
    type: string
    required: false
    description: "Image namespace or organization filter"

child_types:
  - type: local/docker-image
    auto_discover: true
    description: "Docker images in the registry"
    max_count: 500
  - type: local/docker-tag
    auto_discover: true
    description: "Image tags"

sandbox_strategy: none

handler:
  class: DockerRegistryHandler
  module: cleveragents.resource.handlers.docker
  config:
    api_version: "v2"
    page_size: 100
    cache_ttl: 300

auto_discovery:
  enabled: true
  scan_depth: 2
  include_patterns:
    - "**/latest"
    - "**/main"
    - "**/release-*"
  exclude_patterns:
    - "**/sha256:*"
     - "**/*-dirty"
**Example 6: Devcontainer Instance Resource Type (Inherited)** This example demonstrates the `devcontainer-instance` type, which inherits from `container-instance` via the resource type inheritance mechanism ([ADR-042](adr/ADR-042-resource-type-inheritance.md)). Fields not shown here are inherited from the parent type. Only the additional fields and overrides specific to devcontainer semantics are defined. 
# devcontainer-instance inherits from container-instance (ADR-039)
# See ADR-042 for inheritance rules, ADR-043 for devcontainer lifecycle

name: "devcontainer-instance"
inherits: "container-instance"
description: "A container instance defined by a devcontainer.json configuration file. Auto-discovered as a child of git-checkout resources containing a .devcontainer/ directory. Supports lazy activation — detected at discovery time but built only on first access."
physical_virtual: "physical"

fields:
  # Inherited from container-instance: image, engine, ports, environment, volumes
  # Additional fields specific to devcontainer semantics:
  devcontainer_json_path:
    type: "string"
    required: true
    description: "Relative path to devcontainer.json from the parent resource root (e.g., .devcontainer/devcontainer.json)"
  workspace_folder:
    type: "string"
    required: false
    default: "/workspaces/${localWorkspaceFolderBasename}"
    description: "Container-side workspace path, parsed from devcontainer.json workspaceFolder field"
  features:
    type: "map<string, object>"
    required: false
    description: "Dev Container Features to install, parsed from devcontainer.json features field"
  post_create_command:
    type: "string | list<string>"
    required: false
    description: "Command(s) to run after container creation, from devcontainer.json postCreateCommand"
  post_start_command:
    type: "string | list<string>"
    required: false
    description: "Command(s) to run after container start, from devcontainer.json postStartCommand"
  activation_state:
    type: "enum(detected, building, running, stopping, stopped, failed)"
    required: true
    default: "detected"
    description: "Lifecycle state. Starts as 'detected' (lazy); transitions to 'building' then 'running' on first access. The 'stopping' state tracks in-progress shutdown before reaching 'stopped'."

handler: "DevcontainerHandler"

sandbox_strategy: "container_snapshot"
# Overrides the parent's sandbox_strategy; devcontainers use container snapshots
# for checkpoint/rollback rather than the generic container strategy.

capabilities:
  readable: true
  writable: true
  sandboxable: true
  checkpointable: true
  executable: true

auto_discovery:
  enabled: true
  parent_types:
    - "git-checkout"
  detection:
    scan_paths:
      - ".devcontainer/devcontainer.json"
      - ".devcontainer.json"
    activation: "lazy"
    # Container is NOT built at discovery time.
    # State remains "detected" until the execution environment router
    # selects this devcontainer for tool execution.
--- ### Context View Configuration !!! adr "Architecture Decision" The context view configuration, resource filtering, and phase-specific context assembly are defined in [ADR-014: Context Management (ACMS)](adr/ADR-014-context-management-acms.md). Context views control how project resources are filtered and presented to actors during different plan phases. They are managed via `agents project context set` and its associated CLI flags, but can also be defined declaratively in YAML for portability and version control. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for context view configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/context-view-config.json",
  "title": "CleverAgents Context View Configuration",
  "description": "Configuration file schema for defining context views that control how project resources are filtered and presented to actors during plan phases.",
  "type": "object",
  "properties": {
    "project": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified project name this view applies to."
    },
    "view": {
      "type": "string",
      "enum": ["default", "strategize", "execute", "apply"],
      "description": "Phase view. 'default' is the fallback for all phases; phase-specific views override 'default'."
    },
    "include_resources": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Whitelist of resource names to include. When specified, only these resources provide context."
    },
    "exclude_resources": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Blacklist of resource names to exclude. Applied after include_resources."
    },
    "include_paths": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Glob patterns for file paths to include. When specified, only matching files are included."
    },
    "exclude_paths": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Glob patterns for file paths to exclude. Applied after include_paths."
    },
    "hot_max_tokens": {
      "type": ["integer", "null"],
      "minimum": 1,
      "description": "Soft cap on the number of tokens in hot (immediate) context. null means no soft cap."
    },
    "warm_max_decisions": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum number of decisions retained in warm context."
    },
    "cold_max_decisions": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum number of decisions retained in cold context."
    },
    "query_limit": {
      "type": "integer",
      "default": 20,
      "minimum": 1,
      "description": "Maximum number of retrieval results per query against the cold tier."
    },
    "max_file_size": {
      "type": "integer",
      "default": 1048576,
      "minimum": 1,
      "description": "Maximum individual file size in bytes that will be included in context. Default: 1 MB."
    },
    "max_total_size": {
      "type": "integer",
      "default": 52428800,
      "minimum": 1,
      "description": "Maximum aggregate size in bytes across all included files. Default: 50 MB."
    },
    "summarize": {
      "type": "boolean",
      "default": false,
      "description": "When true, large context segments are automatically summarized rather than excluded."
    },
    "summary_max_tokens": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum tokens for each generated summary. Only applies when summarize is true."
    },
    "strategy": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Ordered list of ACMS context strategies to use for this view. Overrides the global strategy list. Valid built-in values: simple-keyword, semantic-embedding, breadth-depth-navigator, arce, temporal-archaeology, plan-decision-context."
    },
    "default_breadth": {
      "type": "integer",
      "minimum": 0,
      "default": 2,
      "description": "Default number of hops from focus nodes in the UKO graph for context expansion. 0 = focus nodes only."
    },
    "default_depth": {
      "oneOf": [
        { "type": "integer", "minimum": 0 },
        { "type": "string", "pattern": "^[A-Z][A-Z0-9_]*$" }
      ],
      "default": 3,
      "description": "Default detail depth for context fragments. May be a non-negative integer or a named level string from the active domain's DetailLevelMap (e.g., 'SIGNATURES', 'FULL_SOURCE'). Named levels are resolved to integers via the DetailLevelMap inheritance chain. Default: 3."
    },
    "depth_gradient": {
      "type": "object",
      "additionalProperties": {
        "oneOf": [
          { "type": "integer", "minimum": 0 },
          { "type": "string", "pattern": "^[A-Z][A-Z0-9_]*$" }
        ]
      },
      "description": "Per-hop detail depth overrides. Key is the hop distance (0 = focus node), value is an integer depth or named level string. Hops not listed use default_depth."
    },
    "skeleton_ratio": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "default": 0.15,
      "description": "Fraction of the context budget reserved for inherited plan skeleton context. 0.0 = no skeleton inheritance; 1.0 = all budget to skeleton."
    },
    "temporal_scope": {
      "type": "string",
      "enum": ["current", "recent", "all"],
      "default": "current",
      "description": "Temporal scope for UKO node resolution. 'current' = only isCurrent nodes; 'recent' = current + nodes valid within warm retention window; 'all' = include historical versions."
    },
    "auto_refresh": {
      "type": "boolean",
      "default": true,
      "description": "When true, the ACMS automatically re-assembles context when the available budget changes by more than the refresh threshold (default 30%). When false, context is only assembled on explicit request."
    }
  },
  "required": ["project", "view"],
  "additionalProperties": false
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Context View Identity ──────────────────────────────────────────
project: <namespace>/<name>         # Project this context view applies to (required)
view: default | strategize | execute | apply  # Which phase view (required)

# ─── Resource Filtering ─────────────────────────────────────────────
include_resources:                  # Resources to include (whitelist, optional)
  - <resource_name>
exclude_resources:                  # Resources to exclude (blacklist, optional)
  - <resource_name>

# ─── Path Filtering ─────────────────────────────────────────────────
include_paths:                      # Glob patterns for files to include (optional)
  - "src/**/*.py"
  - "tests/**/*.py"
exclude_paths:                      # Glob patterns for files to exclude (optional)
  - "**/node_modules/**"
  - "**/__pycache__/**"
  - "**/.git/**"
  - "**/dist/**"

# ─── Token and Size Budgets ─────────────────────────────────────────
hot_max_tokens: <integer>           # Soft cap on hot context tokens (optional, null = no limit)
warm_max_decisions: <integer>       # Max decisions in warm context (optional)
cold_max_decisions: <integer>       # Max decisions in cold context (optional)
query_limit: <integer>              # Max retrieval results per query (optional, default: 20)
max_file_size: <integer>            # Max file size in bytes to include (optional, default: 1048576)
max_total_size: <integer>           # Max total size across all included files (optional, default: 52428800)

# ─── Summarization ──────────────────────────────────────────────────
summarize: true                     # Enable summarization for large context segments (optional)
summary_max_tokens: <integer>       # Token limit for generated summaries (optional)

# ─── ACMS Strategy & Context Assembly ───────────────────────────────
strategy:                            # ACMS strategies to use (optional, overrides global list)
  - simple-keyword
  - semantic-embedding
  - breadth-depth-navigator
default_breadth: <integer>          # Default hop count for UKO graph expansion (optional, default: 2)
default_depth: 3                        # Default detail depth — integer or named level (optional, default: 3)
depth_gradient:                     # Per-hop detail depth overrides (optional)
  0: 9                               # Focus nodes get depth 9 (FULL_SOURCE for code)
  1: 4                               # 1-hop neighbors get depth 4 (SIGNATURES for code)
  2: 0                               # 2-hop neighbors get depth 0 (MODULE_LISTING for code)
skeleton_ratio: <float>             # Fraction of budget for inherited plan skeleton (optional, default: 0.15)
temporal_scope: current | recent | all  # Temporal scope for UKO node resolution (optional, default: current)
auto_refresh: true                   # Auto re-assemble context on budget change (optional, default: true)
#### Structure Reference **Top-Level Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `project` | string | Yes | Fully qualified project name this view applies to. | | `view` | string | Yes | Phase view: `default` (fallback for all phases), `strategize`, `execute`, or `apply`. Phase-specific views override the `default` view. | | `include_resources` | list | No | Whitelist of resource names to include. When specified, only these resources provide context. | | `exclude_resources` | list | No | Blacklist of resource names to exclude. Applied after `include_resources`. | | `include_paths` | list | No | Glob patterns for file paths to include. When specified, only matching files are included. | | `exclude_paths` | list | No | Glob patterns for file paths to exclude. Applied after `include_paths`. | | `hot_max_tokens` | integer | No | Soft cap on the number of tokens in hot (immediate) context. The effective limit is the lesser of this value and the actor's hard context window limit. When `null`, no soft cap is applied. | | `warm_max_decisions` | integer | No | Maximum number of decisions retained in warm context (recent decisions available for reference). | | `cold_max_decisions` | integer | No | Maximum number of decisions retained in cold context (older decisions queryable via search). | | `query_limit` | integer | No | Maximum number of retrieval results per query against the cold tier. Default: 20. | | `max_file_size` | integer | No | Maximum individual file size in bytes that will be included in context. Files exceeding this are either excluded or summarized. Default: 1 MB (1,048,576). | | `max_total_size` | integer | No | Maximum aggregate size in bytes across all included files. Default: 50 MB (52,428,800). | | `summarize` | boolean | No | When `true`, large context segments are automatically summarized rather than excluded. Default: `false`. | | `summary_max_tokens` | integer | No | Maximum tokens for each generated summary. Only applies when `summarize` is `true`. | | `strategy` | list | No | Ordered list of ACMS context strategies to use for this view. Overrides the global `context.strategies.enabled` list. Built-in strategies: `simple-keyword`, `semantic-embedding`, `breadth-depth-navigator`, `arce`, `temporal-archaeology`, `plan-decision-context`. | | `default_breadth` | integer | No | Default number of hops from focus nodes in the UKO graph for context expansion. `0` = focus nodes only. Default: `2`. | | `default_depth` | integer or string | No | Default detail depth for context fragments. Accepts a non-negative integer or a named level string from the active domain's DetailLevelMap (e.g., `SIGNATURES`, `FULL_SOURCE`). Default: `3`. | | `depth_gradient` | object | No | Per-hop detail depth overrides. Keys are hop distances (0 = focus node), values are integers or named level strings. Hops not listed use `default_depth`. | | `skeleton_ratio` | number | No | Fraction of context budget reserved for inherited plan skeleton context. Range: 0.0–1.0. Default: `0.15`. | | `temporal_scope` | string | No | Temporal scope for UKO node resolution: `current` (only `isCurrent` nodes), `recent` (current + warm retention window), `all` (include historical versions). Default: `current`. | | `auto_refresh` | boolean | No | When `true`, ACMS automatically re-assembles context when the available budget changes by more than the refresh threshold. Default: `true`. | **Context Tiers** CleverAgents uses a three-tier context architecture: | Tier | Description | Controlled By | |------|-------------|---------------| | **Hot** | Immediate context sent in the LLM prompt. Includes active files, recent changes, and current task description. | `hot_max_tokens`, `include_paths`, `exclude_paths` | | **Warm** | Recent decisions and intermediate results. Available for reference but not always in the prompt. | `warm_max_decisions` | | **Cold** | Historical decisions, full project index, and archived artifacts. Queryable via retrieval. | `cold_max_decisions`, `query_limit` | **View Resolution Order** When a plan enters a phase, the context view is resolved as follows: 1. Check for a phase-specific view (e.g., `strategize`). 2. Fall back to the `default` view. 3. Fall back to system defaults (include all resources, no path filtering, default budgets). #### Examples **Example 1: Basic Default View (Simple)** A default context view with minimal filtering: 

# context-default.yaml
# Apply: agents project context set --view default --include-path "src/**" \
#        --exclude-path "**/node_modules/**" local/api-service
# Or import this file and apply via the CLI.

project: local/api-service
view: default

exclude_paths:
  - "**/node_modules/**"
  - "**/__pycache__/**"
  - "**/.git/**"

max_file_size: 1048576   # 1 MB
--- **Example 2: Strategize-Optimized View (Medium)** A focused view for the Strategize phase that limits context to essential architecture files: 

# context-strategize.yaml

project: local/api-service
view: strategize

include_resources:
  - local/api-repo

exclude_resources:
  - local/staging-db

include_paths:
  - "src/**/*.py"
  - "docs/architecture/**"
  - "README.md"
  - "pyproject.toml"

exclude_paths:
  - "**/node_modules/**"
  - "**/test_fixtures/**"
  - "**/__pycache__/**"
  - "**/migrations/**"

hot_max_tokens: 12000
warm_max_decisions: 50
cold_max_decisions: 200
query_limit: 20

max_file_size: 524288     # 512 KB
max_total_size: 10485760  # 10 MB

summarize: true
summary_max_tokens: 800
This view keeps the Strategize phase focused on source code and architecture docs, limits hot context to 12K tokens, and enables summarization for files that exceed the size limits. --- **Example 3: Execute-Phase View with Full Resources (Medium)** An execution view with broader access for implementing changes: 

# context-execute.yaml

project: local/api-service
view: execute

include_resources:
  - local/api-repo
  - local/staging-db

include_paths:
  - "src/**"
  - "tests/**"
  - "config/**"
  - "scripts/**"
  - "Makefile"
  - "pyproject.toml"
  - "requirements*.txt"

exclude_paths:
  - "**/node_modules/**"
  - "**/__pycache__/**"
  - "**/dist/**"
  - "**/*.pyc"

hot_max_tokens: 24000
warm_max_decisions: 100
cold_max_decisions: 500
query_limit: 30

max_file_size: 2097152     # 2 MB
max_total_size: 104857600  # 100 MB

summarize: true
summary_max_tokens: 1200
--- **Example 4: Apply-Phase Minimal View (Simple)** A minimal view for the Apply phase, focused only on changed files and validation: 

# context-apply.yaml

project: local/api-service
view: apply

include_paths:
  - "src/**"
  - "tests/**"

exclude_paths:
  - "**/__pycache__/**"

hot_max_tokens: 8000
warm_max_decisions: 20
cold_max_decisions: 50

summarize: false
--- **Example 5: Large Monorepo View with Aggressive Filtering (Complex)** A context view designed for a large monorepo where careful filtering is essential: 

# context-monorepo-strategize.yaml

project: local/platform
view: strategize

include_resources:
  - local/platform-repo

include_paths:
  - "packages/auth/**/*.ts"
  - "packages/auth/**/*.tsx"
  - "packages/shared/**/*.ts"
  - "packages/api-gateway/**/*.ts"
  - "docs/architecture/**"
  - "package.json"
  - "tsconfig.json"
  - "lerna.json"

exclude_paths:
  - "**/node_modules/**"
  - "**/dist/**"
  - "**/coverage/**"
  - "**/*.test.ts"
  - "**/*.spec.ts"
  - "**/*.stories.tsx"
  - "**/fixtures/**"
  - "**/__snapshots__/**"
  - "**/generated/**"

hot_max_tokens: 16000
warm_max_decisions: 30
cold_max_decisions: 150
query_limit: 15

max_file_size: 262144     # 256 KB - aggressive for a monorepo
max_total_size: 5242880   # 5 MB

summarize: true
summary_max_tokens: 600
This configuration is tailored for a TypeScript monorepo, focusing on specific packages and excluding generated code, tests, and build artifacts to keep context within manageable bounds. --- ### Automation Profile Configuration Files !!! adr "Architecture Decision" The automation profile configuration schema, threshold model, and built-in profiles are defined in [ADR-017: Automation Profiles](adr/ADR-017-automation-profiles.md). Automation profile configuration files define named collections of **confidence thresholds** (floating-point values from 0.0 to 1.0) and boolean safety flags controlling which operations are automated vs. requiring human approval. Each threshold specifies the minimum confidence score at which the system proceeds automatically; below the threshold, the system drops to manual mode. A threshold of 0.0 means "always automatic" and 1.0 means "always manual." Built-in profiles (`manual`, `review`, `supervised`, `cautious`, `trusted`, `auto`, `ci`, `full-auto`) are always available. Custom profiles are registered via `agents automation-profile add --config `. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for automation profile configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/automation-profile-config.json",
  "title": "CleverAgents Automation Profile Configuration",
  "description": "Configuration file schema for defining automation profiles — named collections of confidence thresholds (0.0-1.0) and boolean safety flags controlling which operations are automated vs. requiring human approval.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified profile name in <namespace>/<name> format."
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of the profile's purpose and behavior."
    },
    "decompose_task": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically transitioning from Action to Strategize. 0.0 = always automatic, 1.0 = always manual."
    },
    "create_tool": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically transitioning from Strategize to Execute. 0.0 = always automatic, 1.0 = always manual."
    },
    "select_tool": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically applying changes after execution completes. 0.0 = always automatic, 1.0 = always manual."
    },
    "edit_code": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for autonomously making decisions during Strategize. 0.0 = always automatic, 1.0 = always manual."
    },
    "execute_command": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for autonomously making decisions during Execute. 0.0 = always automatic, 1.0 = always manual."
    },
    "create_file": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically attempting to fix validation failures. 0.0 = always automatic, 1.0 = always manual."
    },
    "delete_content": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically revising the strategy when execution reveals issues. 0.0 = always automatic, 1.0 = always manual."
    },
    "access_network": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically reverting from a constrained Apply phase to Strategize. 0.0 = always automatic, 1.0 = always manual."
    },
    "modify_config": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically retrying operations that fail due to transient errors. 0.0 = always automatic, 1.0 = always manual."
    },
    "approve_plan": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically restoring from the most recent checkpoint on failure. 0.0 = always automatic, 1.0 = always manual."
    },
    "install_dependency": {
      "type": "number",
      "minimum": 0.0,
      "maximum": 1.0,
      "description": "Confidence threshold (0.0-1.0) for automatically spawning child plans decided during Strategize. 0.0 = always automatic, 1.0 = always manual."
    },
    "require_sandbox": {
      "type": "boolean",
      "description": "When true, all write operations must execute within a sandbox. Execution fails if no sandbox strategy is available."
    },
    "require_checkpoints": {
      "type": "boolean",
      "description": "When true, checkpoints must be created before any write operation, enabling rollback."
    },
    "allow_unsafe_tools": {
      "type": "boolean",
      "description": "When true, tools flagged as unsafe can be invoked. When false, unsafe tool invocations are blocked."
    }
  },
  "required": [
    "name",
    "description",
    "decompose_task",
    "create_tool",
    "select_tool",
    "edit_code",
    "execute_command",
    "create_file",
    "delete_content",
    "access_network",
    "modify_config",
    "approve_plan",
    "install_dependency",
    "require_sandbox",
    "require_checkpoints",
    "allow_unsafe_tools"
  ],
  "additionalProperties": false
}
#### Informal YAML Schema The following annotated YAML provides an easier-to-read overview of the same schema defined formally above. It is **not** a validatable schema — it uses informal annotations to describe the structure. Refer to the JSON Schema above for the authoritative, machine-validatable definition. 

# ─── Profile Identity ───────────────────────────────────────────────
name: <namespace>/<name>            # Fully qualified profile name (required)
description: <string>               # Human-readable description (required)

# ─── Phase Transition Thresholds ────────────────────────────────────
# Confidence thresholds controlling phase transitions.
# 0.0 = always automatic, 1.0 = always manual.
decompose_task: <float: 0.0–1.0>          # Confidence threshold for Action → Strategize (required, 0.0=auto, 1.0=manual)
create_tool: <float: 0.0–1.0>             # Confidence threshold for Strategize → Execute (required, 0.0=auto, 1.0=manual)
select_tool: <float: 0.0–1.0>               # Confidence threshold for Execute → Apply (required, 0.0=auto, 1.0=manual)

# ─── Decision Thresholds ────────────────────────────────────────────
# Confidence thresholds controlling decisions within each phase.
# 0.0 = always automatic, 1.0 = always manual.
edit_code: <float: 0.0–1.0>  # Confidence threshold for decisions during Strategize (required, 0.0=auto, 1.0=manual)
execute_command: <float: 0.0–1.0>     # Confidence threshold for decisions during Execute (required, 0.0=auto, 1.0=manual)

# ─── Self-Repair Thresholds ─────────────────────────────────────────
create_file: <float: 0.0–1.0>      # Confidence threshold for auto-fixing validation failures (required, 0.0=auto, 1.0=manual)
delete_content: <float: 0.0–1.0>   # Confidence threshold for auto-revising strategy when Execute hits constraints (required, 0.0=auto, 1.0=manual)
access_network: <float: 0.0–1.0> # Confidence threshold for auto-reverting from constrained Apply to Strategize (required, 0.0=auto, 1.0=manual)
modify_config: <float: 0.0–1.0>     # Confidence threshold for auto-retrying transient errors (required, 0.0=auto, 1.0=manual)
approve_plan: <float: 0.0–1.0>  # Confidence threshold for auto-restoring from checkpoints (required, 0.0=auto, 1.0=manual)

# ─── Execution Control Thresholds ──────────────────────────────────
install_dependency: <float: 0.0–1.0>         # Confidence threshold for auto-spawning child plans (required, 0.0=auto, 1.0=manual)

# ─── Safety Requirements ────────────────────────────────────────────
require_sandbox: <boolean>          # Require sandbox for all write operations (required)
require_checkpoints: <boolean>      # Require checkpoint creation before write operations (required)
allow_unsafe_tools: <boolean>       # Allow tools flagged as unsafe (required)
#### Structure Reference **Top-Level Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified profile name. This value is used as the profile's registered name. | | `description` | string | Yes | Human-readable description of the profile's purpose and behavior. | **Phase Transition Thresholds** | Field | Type | Required | Description | |-------|------|----------|-------------| | `decompose_task` | number (0.0–1.0) | Yes | Confidence threshold for transitioning from Action to Strategize. When computed confidence >= threshold, Strategize begins automatically. 0.0 = always automatic, 1.0 = always manual. | | `create_tool` | number (0.0–1.0) | Yes | Confidence threshold for transitioning from Strategize to Execute. When computed confidence >= threshold, Execute begins automatically. 0.0 = always automatic, 1.0 = always manual. | | `select_tool` | number (0.0–1.0) | Yes | Confidence threshold for transitioning from Execute to Apply. When computed confidence >= threshold, Apply begins automatically. 0.0 = always automatic, 1.0 = always manual. **A threshold of 0.0 means changes are committed without human review.** | **Decision Automation Thresholds** | Field | Type | Required | Description | |-------|------|----------|-------------| | `edit_code` | number (0.0–1.0) | Yes | Confidence threshold for autonomous decision-making during Strategize. When computed confidence >= threshold, the strategy actor decides autonomously. 0.0 = always automatic, 1.0 = always manual. | | `execute_command` | number (0.0–1.0) | Yes | Confidence threshold for autonomous decision-making during Execute. When computed confidence >= threshold, the execution actor decides autonomously. 0.0 = always automatic, 1.0 = always manual. | **Self-Repair Thresholds** | Field | Type | Required | Description | |-------|------|----------|-------------| | `create_file` | number (0.0–1.0) | Yes | Confidence threshold for automatically fixing validation failures (e.g., failing tests, lint errors). When computed confidence >= threshold, fix is attempted automatically. 0.0 = always automatic, 1.0 = always manual. | | `delete_content` | number (0.0–1.0) | Yes | Confidence threshold for automatically revising the strategy when execution reveals issues. When computed confidence >= threshold, revision proceeds automatically. 0.0 = always automatic, 1.0 = always manual. | | `access_network` | number (0.0–1.0) | Yes | Confidence threshold for automatically reverting from a `constrained` Apply phase to Strategize. When computed confidence >= threshold, reversion proceeds automatically. 0.0 = always automatic, 1.0 = always manual. | | `modify_config` | number (0.0–1.0) | Yes | Confidence threshold for automatically retrying operations that fail due to transient errors (network timeouts, rate limits). When computed confidence >= threshold, retry proceeds automatically. 0.0 = always automatic, 1.0 = always manual. | | `approve_plan` | number (0.0–1.0) | Yes | Confidence threshold for automatically restoring from the most recent checkpoint on failure. When computed confidence >= threshold, restore proceeds automatically. 0.0 = always automatic, 1.0 = always manual. | **Execution Control Thresholds** | Field | Type | Required | Description | |-------|------|----------|-------------| | `install_dependency` | number (0.0–1.0) | Yes | Confidence threshold for automatically spawning child plans decided during Strategize. When computed confidence >= threshold, child plans spawn automatically during Execute. 0.0 = always automatic, 1.0 = always manual. | **Safety Flags** | Field | Type | Required | Description | |-------|------|----------|-------------| | `require_sandbox` | boolean | Yes | When `true`, all write operations must execute within a sandbox (git worktree, copy-on-write, transaction). Execution fails if no sandbox strategy is available. | | `require_checkpoints` | boolean | Yes | When `true`, checkpoints must be created before any write operation. This enables rollback. | | `allow_unsafe_tools` | boolean | Yes | When `true`, tools flagged as `unsafe` can be invoked. When `false`, unsafe tool invocations are blocked. | **Built-in Profile Reference** | Threshold | `manual` | `review` | `supervised` | `cautious` | `trusted` | `auto` | `ci` | `full-auto` | |-----------------|----------|----------|--------------|------------|-----------|--------|------|-------------| | `auto_strat` | 1.0 | 0.0 | 0.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `auto_exec` | 1.0 | 0.0 | 1.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `select_tool` | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | | `auto_dec_strat` | 1.0 | 1.0 | 0.0 | 0.6 | 0.0 | 0.0 | 0.0 | 0.0 | | `auto_dec_exec` | 1.0 | 1.0 | 1.0 | 0.8 | 0.0 | 0.0 | 0.0 | 0.0 | | `auto_val_fix` | 1.0 | 1.0 | 1.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `auto_strat_rev` | 1.0 | 1.0 | 1.0 | 0.8 | 1.0 | 0.0 | 0.0 | 0.0 | | `auto_rev_apply` | 1.0 | 1.0 | 1.0 | 0.9 | 1.0 | 1.0 | 0.0 | 0.0 | | `auto_child` | 1.0 | 0.0 | 1.0 | 0.7 | 0.0 | 0.0 | 0.0 | 0.0 | | `require_sandbox` | true | true | true | true | true | true | true | false | | `allow_unsafe` | false | false | false | false | false | false | false | true | #### Examples **Example 1: Careful Autonomous Profile (Simple)** A profile for autonomous execution with mandatory sandboxing and manual apply: 

# careful-auto.yaml
# Register: agents automation-profile add --config careful-auto.yaml

name: local/careful-auto
description: "Autonomous execution with mandatory sandbox and manual apply"

decompose_task: 0.0
create_tool: 0.0
select_tool: 1.0

edit_code: 0.0
execute_command: 0.0

create_file: 0.0
delete_content: 1.0
access_network: 1.0
modify_config: 0.0
approve_plan: 0.0

install_dependency: 0.0

require_sandbox: true
require_checkpoints: true
allow_unsafe_tools: false
This is essentially the `auto` built-in profile but with `approve_plan` set to 0.0 (always automatic) for more aggressive self-repair. --- **Example 2: CI/CD Pipeline Profile (Medium)** A profile designed for automated CI/CD pipelines where everything runs autonomously: 

# ci-pipeline.yaml
# Register: agents automation-profile add --config ci-pipeline.yaml

name: local/ci-pipeline
description: "Full automation for CI/CD pipelines. All phases automated, sandbox required."

decompose_task: 0.0
create_tool: 0.0
select_tool: 0.0

edit_code: 0.0
execute_command: 0.0

create_file: 0.0
delete_content: 0.0
access_network: 0.0
modify_config: 0.0
approve_plan: 0.0

install_dependency: 0.0

require_sandbox: true
require_checkpoints: true
allow_unsafe_tools: false
This profile is similar to `full-auto` but with mandatory sandboxing and checkpoints enabled — suitable for CI/CD environments where you want full automation but with safety nets. --- **Example 3: Review-Heavy Profile (Medium)** A profile for regulated environments where every decision must be reviewed: 

# review-heavy.yaml
# Register: agents automation-profile add --config review-heavy.yaml

name: local/review-heavy
description: "Maximum human oversight. Every decision and phase requires approval."

decompose_task: 0.0
create_tool: 1.0
select_tool: 1.0

edit_code: 1.0
execute_command: 1.0

create_file: 1.0
delete_content: 1.0
access_network: 1.0
modify_config: 1.0
approve_plan: 1.0

install_dependency: 1.0

require_sandbox: true
require_checkpoints: true
allow_unsafe_tools: false
This profile auto-starts strategize but requires human approval for every decision, every phase transition, and every child plan spawn. Useful in regulated industries (finance, healthcare) where audit trails and human review are mandatory. --- **Example 4: Development Sandbox Profile (Simple)** A fast-iteration profile for local development where safety is relaxed: 

# dev-sandbox.yaml
# Register: agents automation-profile add --config dev-sandbox.yaml

name: local/dev-sandbox
description: "Fast iteration for local development. Relaxed safety, auto execution."

decompose_task: 0.0
create_tool: 0.0
select_tool: 1.0

edit_code: 0.0
execute_command: 0.0

create_file: 0.0
delete_content: 0.0
access_network: 1.0
modify_config: 0.0
approve_plan: 0.0

install_dependency: 0.0

require_sandbox: false
require_checkpoints: false
allow_unsafe_tools: true
This profile removes sandbox and checkpoint requirements for speed during local development. It still requires manual apply to prevent accidental commits. Unsafe tools are allowed for full flexibility. --- **Example 5: Production Deployment Profile (Complex)** A profile for production deployments combining autonomous execution with maximum safety: 

# production-deploy.yaml
# Register: agents automation-profile add --config production-deploy.yaml

name: local/production-deploy
description: |
  Production deployment profile. Fully autonomous execution
  with maximum safety guarantees. All phases require sandbox
  and checkpoint. Apply requires manual approval. Strategy
  revision is enabled to adapt to deployment issues.

decompose_task: 0.0
create_tool: 0.0
select_tool: 1.0

edit_code: 0.0
execute_command: 0.0

create_file: 0.0
delete_content: 0.0
access_network: 1.0
modify_config: 0.0
approve_plan: 0.0

install_dependency: 0.0

require_sandbox: true
require_checkpoints: true
allow_unsafe_tools: false
### LSP Server Configuration Files !!! adr "Architecture Decision" The LSP Registry, actor LSP binding, capability exposure, and server lifecycle are defined in [ADR-027: Language Server Protocol (LSP) Integration](adr/ADR-027-language-server-protocol.md). LSP server configuration files define Language Server Protocol servers that provide language intelligence to actors. LSP servers are Infrastructure-layer components — they have nothing to do with IDE integration. Each server has a namespaced name, a launch command, supported languages, initialization options, and capability declarations. LSP servers are registered via `agents lsp add --config ` and can then be referenced by actors in their `lsp:` configuration field. #### JSON Schema The following is the formal [JSON Schema](https://json-schema.org/) definition for LSP server configuration files. 

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://cleveragents.dev/schemas/lsp-server-config.json",
  "title": "CleverAgents LSP Server Configuration",
  "description": "Configuration file schema for defining LSP servers registered in the LSP Registry and attached to actors for language intelligence.",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^([a-zA-Z0-9_-]+:)?[a-zA-Z0-9_-]+/[a-zA-Z0-9_-]+$",
      "description": "Fully qualified LSP server name in [[server:]namespace/]name format."
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of the LSP server's purpose."
    },
    "languages": {
      "type": "array",
      "items": { "type": "string" },
      "minItems": 1,
      "description": "Programming languages this server supports. Used for language-based and auto-discovery binding resolution."
    },
    "command": {
      "type": "string",
      "description": "Shell command to launch the LSP server process. Must support --stdio or equivalent for stdin/stdout JSON-RPC communication."
    },
    "args": {
      "type": "array",
      "items": { "type": "string" },
      "default": [],
      "description": "Additional arguments appended to the command."
    },
    "env": {
      "type": "object",
      "additionalProperties": { "type": "string" },
      "default": {},
      "description": "Environment variables set when launching the server process."
    },
    "root_path": {
      "type": "string",
      "default": "{{ project.root }}",
      "description": "Workspace root path sent in the LSP initialize request. Supports Jinja2 template variables."
    },
    "init_options": {
      "type": "object",
      "additionalProperties": true,
      "default": {},
      "description": "Initialization options sent in the LSP initialize request. Server-specific; passed through verbatim."
    },
    "capabilities": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": ["diagnostics", "hover", "completions", "references", "definitions", "symbols", "formatting", "code_actions", "rename"]
      },
      "default": ["diagnostics", "hover", "completions", "references", "definitions", "symbols", "formatting", "code_actions", "rename"],
      "description": "LSP capabilities this server advertises. The runtime uses this to determine which tool adapters and context enrichment features are available. Defaults to all capabilities; restrict to a subset if the server does not support certain features."
    },
    "health_check": {
      "type": "object",
      "properties": {
        "enabled": {
          "type": "boolean",
          "default": true,
          "description": "Whether to perform periodic health checks on the running server process."
        },
        "interval_seconds": {
          "type": "integer",
          "default": 60,
          "minimum": 10,
          "description": "Seconds between health check probes."
        },
        "restart_on_failure": {
          "type": "boolean",
          "default": true,
          "description": "Whether to automatically restart the server if health checks fail."
        },
        "max_restarts": {
          "type": "integer",
          "default": 3,
          "minimum": 0,
          "description": "Maximum number of automatic restarts before marking the server as failed."
        }
      },
      "additionalProperties": false,
      "description": "Health check configuration for the running server process."
    }
  },
  "required": ["name", "languages", "command"],
  "additionalProperties": false
}
#### Informal YAML Schema 

# ─── LSP Server Configuration ────────────────────────────────────────
# Registered via: agents lsp add --config <this-file>
# Referenced by actors via: lsp: [<namespace>/<name>]

name: <namespace>/<server-name>     # Namespaced identifier (required)
description: "..."                   # Human-readable description (optional)

languages:                              # Supported languages (required, min 1)
  - python
  - pyi                                  # e.g., Python stub files

command: pyright-langserver             # Launch command (required)
args:                                    # Additional arguments (optional)
  - --stdio

env:                                     # Environment variables (optional)
  PYTHONPATH: /app/src

root_path: "{{ project.root }}"       # Workspace root, Jinja2 supported (optional, default: {{ project.root }})

init_options:                            # LSP initialize request options (optional)
  python.analysis.typeCheckingMode: standard
  python.analysis.autoSearchPaths: true
  python.analysis.diagnosticSeverityOverrides:
    reportMissingImports: warning
    reportUnusedVariable: information

capabilities:                            # Advertised capabilities (optional, default: all)
  - diagnostics
  - hover
  - completions
  - references
  - definitions
  - symbols
  - formatting
  - code_actions
  - rename

health_check:                            # Health monitoring (optional)
  enabled: true                        # Periodic health probes (default: true)
  interval_seconds: 60                 # Probe interval (default: 60, min: 10)
  restart_on_failure: true             # Auto-restart on failure (default: true)
  max_restarts: 3                      # Max auto-restarts before marking failed (default: 3)
#### Structure Reference **LSP Server Configuration Fields** | Field | Type | Required | Description | |-------|------|----------|-------------| | `name` | string | Yes | Fully qualified LSP server name in `[[server:]namespace/]name` format. | | `description` | string | No | Human-readable description of the server's purpose. | | `languages` | list | Yes | Programming languages this server supports (min 1). Used for language-based and auto-discovery binding resolution. | | `command` | string | Yes | Shell command to launch the LSP server process. Must support stdio JSON-RPC communication. | | `args` | list | No | Additional arguments appended to the command. | | `env` | object | No | Environment variables set when launching the server process. | | `root_path` | string | No | Workspace root path sent in the LSP `initialize` request. Supports Jinja2 template variables. Default: `{{ project.root }}`. | | `init_options` | object | No | Initialization options sent in the LSP `initialize` request. Server-specific; passed through verbatim. | | `capabilities` | list | No | LSP capabilities this server advertises: `diagnostics`, `hover`, `completions`, `references`, `definitions`, `symbols`, `formatting`, `code_actions`, `rename`. Default: all. | | `health_check` | object | No | Health monitoring configuration. | | `health_check.enabled` | boolean | No | Whether to perform periodic health checks. Default: `true`. | | `health_check.interval_seconds` | integer | No | Seconds between health check probes. Default: `60`, min: `10`. | | `health_check.restart_on_failure` | boolean | No | Auto-restart server on health check failure. Default: `true`. | | `health_check.max_restarts` | integer | No | Maximum automatic restarts before marking server as failed. Default: `3`, min: `0`. | #### Examples **Example 1: Pyright (Python type checker and language server)** 

name: local/pyright
description: "Pyright language server for Python type checking and intelligence"
languages:
  - python
  - pyi
command: pyright-langserver
args: ["--stdio"]
init_options:
  python.analysis.typeCheckingMode: standard
  python.analysis.autoSearchPaths: true
  python.analysis.useLibraryCodeForTypes: true
**Example 2: TypeScript Language Server** 

name: local/ts-server
description: "TypeScript/JavaScript language server"
languages:
  - typescript
  - javascript
  - tsx
  - jsx
command: typescript-language-server
args: ["--stdio"]
init_options:
  preferences:
    includeInlayParameterNameHints: all
    includeInlayVariableTypeHints: true
**Example 3: gopls (Go language server) with restricted capabilities** 

name: local/gopls
description: "Go language server (diagnostics and navigation only)"
languages:
  - go
command: gopls
args: ["serve"]
capabilities:
  - diagnostics
  - hover
  - references
  - definitions
  - symbols
health_check:
  interval_seconds: 120
  max_restarts: 5
**Example 4: Rust Analyzer with custom environment** 

name: local/rust-analyzer
description: "Rust Analyzer language server"
languages:
  - rust
command: rust-analyzer
env:
  CARGO_HOME: /home/user/.cargo
  RUSTUP_HOME: /home/user/.rustup
init_options:
  cargo:
    allFeatures: true
  checkOnSave:
    command: clippy
## Workflow Examples This section presents complete, end-to-end workflow examples showing how CleverAgents is used in practice. Each example starts from initial setup and walks through every command and decision point. The examples progress from simple single-action workflows to complex multi-project, multi-actor orchestrations. ### Example 1: Hello World — Fix a Single Bug **Scenario**: A developer finds a bug in their Python web API where the `/health` endpoint returns a 500 error instead of 200 when the database connection is unavailable. They want CleverAgents to fix it with full human oversight. **Complexity**: Beginner. Single project, single action, manual automation profile. #### Step 1: Initialize Environment and Register Resources 

# Initialize CleverAgents (first-time setup)
$ agents init --yes

╭─ Initialized ────────────────────────────────────────────╮
│ Data Dir: /home/dev/.cleveragents (created)              │
│ Config: /home/dev/.cleveragents/config.toml              │
│ Database: initialized (schema v3)                        │
│ Directories: logs, cache, sessions, contexts             │
╰──────────────────────────────────────────────────────────╯

✓ OK Initialized (non-interactive)


# Register the git checkout as a resource
$ agents resource add git-checkout local/api-repo \
    --path /home/dev/projects/api-service \
    --branch main

╭─ Resource ──────────────────────────────────────────╮
│ Name: local/api-repo                                │
│ ID: 01HXR1A1B2C3D4E5F6G7H8J9K0                      │
│ Type: git-checkout                                  │
│ Physical/Virtual: physical                          │
│ Path: /home/dev/projects/api-service                │
│ Branch: main                                        │
│ Created: 2026-02-11 09:15                           │
╰─────────────────────────────────────────────────────╯

╭─ Auto-discovered Children ─────────────────────────────────────────╮
│ ID               Type            Status                            │
│ ───────────────  ──────────────  ─────────────────                 │
│ 01HXR1A1B2C3…   git             created                            │
│ 01HXR1A1B2C4…   git-remote      created                            │
│ 01HXR1A1B2C5…   git-branch      created                            │
│ 01HXR1A1B2C6…   fs-directory    created                            │
│   + 32 git-commit resources                                        │
│   + 187 git-tree-entry resources                                   │
│   + 5 fs-directory + 41 fs-file                                    │
╰────────────────────────────────────────────────────────────────────╯

╭─ Capabilities ─────────────────╮
│ Readable: yes                  │
│ Writable: yes                  │
│ Sandboxable: yes               │
│ Checkpointable: yes            │
│ Sandbox Strategy: git_worktree │
╰────────────────────────────────╯

✓ OK Resource registered (270 child resources discovered)


# Create the project and link the resource
$ agents project create \
    --description "REST API service" \
    --resource local/api-repo \
    local/api-service

╭─ Project Created ──────────────────────────╮
│ Name: local/api-service                    │
│ Description: REST API service              │
│ Type: local                                │
│ Created: 2026-02-11 09:15                  │
╰────────────────────────────────────────────╯

╭─ Linked Resources ───────────────────────────────────────╮
│ Name               Type            Read-Only             │
│ ─────────────────  ──────────────  ─────────             │
│ local/api-repo     git-checkout    no                    │
╰──────────────────────────────────────────────────────────╯

╭─ Defaults ──────────────────────────────╮
│ Sandbox: git_worktree                   │
│ Validations: 0                          │
│ Context Filters: none                   │
│ Automation Profile: (inherits global)   │
╰─────────────────────────────────────────╯

✓ OK Project created


# Register a required validation (tests must pass)
$ agents validation add \
    --config validations/unit-tests.yaml \
    --required

╭─ Validation Registered ─────────────────────────────────────╮
│ Name: local/unit-tests                                      │
│ Command: pytest tests/                                      │
│ Description: Unit tests                                     │
│ Mode: required                                              │
│ Timeout: 300s (default)                                     │
╰─────────────────────────────────────────────────────────────╯

✓ OK Validation registered

# Attach the validation to the project
$ agents validation attach --project local/api-service local/unit-tests

✓ OK Validation attached to project local/api-service
#### Step 2: Create an Action Create a file `actions/fix-bug.yaml`: 

name: local/fix-bug
description: "Fix a reported bug in the codebase"
long_description: |
  Analyze the bug description, locate the relevant code,
  implement a fix, and add or update tests to cover the fix.
definition_of_done: |
  - The described bug no longer reproduces
  - All existing tests pass
  - At least one new test covers the fixed behavior
  - No unrelated code is modified
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
reusable: true
state: available
args:
  - name: bug_description
    type: string
    required: true
    description: "Description of the bug to fix"
  - name: affected_file
    type: string
    required: false
    description: "File path where the bug is suspected (optional hint)"


# Register the action
$ agents action create --config ./actions/fix-bug.yaml

╭─ Action Created ─────────────────────────────╮
│ Name: local/fix-bug                          │
│ ID: 01HXR1B1C2D3E4F5G6H7I8J9K0               │
│ State: available                             │
│ Strategy Actor: anthropic/claude-3.5-sonnet  │
│ Execution Actor: anthropic/claude-3.5-sonnet │
│ Reusable: yes                                │
│ Read Only: no                                │
│ Created: 2026-02-11 09:16                    │
╰──────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────╮
│ - The described bug no longer reproduces              │
│ - All existing tests pass                             │
│ - At least one new test covers the fixed behavior     │
│ - No unrelated code is modified                       │
╰───────────────────────────────────────────────────────╯

╭─ Arguments ───────────────────────────────────────────────────────────────╮
│ Name             Type    Required  Description                            │
│ ───────────────  ──────  ────────  ────────────────────────────────────── │
│ bug_description  string  yes       Description of the bug to fix          │
│ affected_file    string  no        File path where the bug is suspected   │
╰───────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: (inherits global)            │
│ Source: default                       │
╰───────────────────────────────────────╯

╭─ Usage ──────────────────────────────────────────────────────────────────╮
│ agents plan use local/fix-bug local/api-service                          │
│   --arg bug_description="..."                                            │
╰──────────────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 3: Create and Execute a Plan 

# Bind the action to the project with the manual profile for full oversight
$ agents plan use \
    --automation-profile manual \
    --arg bug_description="The /health endpoint returns HTTP 500 when the database \
connection is unavailable. It should return HTTP 200 with {\"status\": \"degraded\", \
\"database\": \"unavailable\"} instead of crashing." \
    --arg affected_file="src/routes/health.py" \
    local/fix-bug local/api-service

╭─ Plan Created ──────────────────────────╮
│ Plan ID: 01HXR1C1D2E3F4G5H6I7J8K9L0     │
│ Phase: strategize                       │
│ Action: local/fix-bug                   │
│ Project: local/api-service              │
│ Automation: manual                      │
│ Attempt: 1                              │
╰─────────────────────────────────────────╯

╭─ Inputs ──────────────────────────────────────────────────────────────╮
│ - bug_description="The /health endpoint returns HTTP 500 when the     │
│   database connection is unavailable. It should return HTTP 200 with  │
│   {\"status\": \"degraded\", \"database\": \"unavailable\"} instead   │
│   of crashing."                                                       │
│ - affected_file="src/routes/health.py"                                │
│ - automation_profile=manual                                           │
╰───────────────────────────────────────────────────────────────────────╯

╭─ Actors ──────────────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet         │
│ Execution: anthropic/claude-3.5-sonnet        │
│ Estimation: (none)                            │
╰───────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: manual                       │
│ Source: plan override                 │
│ Read-Only: no                         │
╰───────────────────────────────────────╯

╭─ Context ─────────────────────────╮
│ Resources: 1 (git-checkout)       │
│ Indexed Files: 41                 │
│ View: strategize                  │
│ Hot Token Budget: 8,000           │
╰───────────────────────────────────╯

╭─ Next Steps ───────────────────────────────────────╮
│ - agents plan execute 01HXR1C1D2E3F4G5H6I7J8K9L0   │
│ - agents plan status 01HXR1C1D2E3F4G5H6I7J8K9L0    │
│ - agents plan tree 01HXR1C1D2E3F4G5H6I7J8K9L0      │
╰────────────────────────────────────────────────────╯

✓ OK Plan created
Because the automation profile is `manual`, the plan stops and waits after creation. The developer must explicitly trigger each phase. 

# Manually trigger Strategize → the strategy actor analyzes the codebase
$ agents plan execute 01HXR1C1D2E3F4G5H6I7J8K9L0

╭─ Execution ─────────────────────────────╮
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0        │
│ Phase: strategize                       │
│ Sandbox: git_worktree                   │
│ Worker: anthropic/claude-3.5-sonnet     │
│ Started: 09:17:02                       │
│ Attempt: 1                              │
╰─────────────────────────────────────────╯

╭─ Sandbox ───────────────────────────────────────────────────────╮
│ Strategy: git_worktree                                          │
│ Path: /home/dev/projects/api-service/.worktrees/plan-01HXR1C1   │
│ Branch: cleveragents/plan-01HXR1C1D2                            │
│ Status: active                                                  │
╰─────────────────────────────────────────────────────────────────╯

╭─ Strategy Summary ────────────────╮
│ Decisions: 4                      │
│ Invariants: 0                     │
│ Planned Child Plans: 0            │
│ Estimated Files: ~2               │
│ Risk: low                         │
╰───────────────────────────────────╯

╭─ Progress ────────╮
│ ✓ Collect context │
│ ✓ Build strategy  │
│ • Awaiting review │
╰───────────────────╯

✓ OK Strategize complete — awaiting manual approval
The strategy actor has read the codebase, identified the relevant files, and produced decisions. Since `edit_code` is 1.0 (manual), the plan pauses for review: 

# Review the decision tree
$ agents plan tree 01HXR1C1D2E3F4G5H6I7J8K9L0

╭─ Decision Tree ───────────────────────────────────────────────────────────────────────────╮
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0                                                          │
│ ├─ [prompt_definition] "Fix /health endpoint to return 200 when DB unavailable"           │
│ ├─ [strategy_choice] "Wrap DB call in try/except, return degraded status" (conf: 0.95)    │
│ ├─ [strategy_choice] "Modify src/routes/health.py only" (conf: 0.91)                      │
│ └─ [strategy_choice] "Add test_health_db_unavailable to tests/test_health.py" (conf: 0.93)│
╰───────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Tree Summary ─────────────╮
│ Nodes: 4                   │
│ Depth: 1                   │
│ Child Plans: 0             │
│ Invariants: 0              │
│ Superseded: 0 (hidden)     │
╰────────────────────────────╯

╭─ Decision IDs (for correction) ──────────────────╮
│ Root: 01HXR1D1A2B3C4D5E6F7G8H9                   │
│ Strategy 1: 01HXR1D2A2B3C4D5E6F7G8H9             │
│ Strategy 2: 01HXR1D3A2B3C4D5E6F7G8H9             │
│ Strategy 3: 01HXR1D4A2B3C4D5E6F7G8H9             │
╰──────────────────────────────────────────────────╯

✓ OK Decision tree rendered


# Inspect the main strategy decision in detail
$ agents plan explain 01HXR1D2A2B3C4D5E6F7G8H9

╭─ Decision ──────────────────────────────────────────────────────────────╮
│ ID: 01HXR1D2A2B3C4D5E6F7G8H9                                            │
│ Type: strategy_choice                                                   │
│ Question: How should the /health endpoint handle database failures?     │
│ Chosen: Wrap DB call in try/except, return degraded status              │
│ Confidence: 0.95                                                        │
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0                                        │
│ Sequence: 1 of 3                                                        │
│ Created: 2026-02-11 09:17                                               │
╰─────────────────────────────────────────────────────────────────────────╯

╭─ Alternatives Considered ──────────────────────────────────────────────────╮
│ 1. Wrap DB call in try/except, return degraded status (chosen)             │
│ 2. Add a circuit breaker middleware for all DB-dependent routes            │
│ 3. Return HTTP 503 Service Unavailable with retry-after header             │
╰────────────────────────────────────────────────────────────────────────────╯

╭─ Impact ──────────────────────╮
│ Downstream Decisions: 2       │
│ Downstream Child Plans: 0     │
│ Artifacts Produced: 2         │
│ Correction Impact: low        │
╰───────────────────────────────╯

╭─ Rationale ──────────────────────────────────────────────────╮
│ The bug description explicitly requires HTTP 200 with a      │
│ degraded status JSON body. A try/except around the DB call   │
│ in the health endpoint is the minimal, targeted fix. A       │
│ circuit breaker would be over-engineering for a single       │
│ endpoint. HTTP 503 contradicts the requested behavior.       │
╰──────────────────────────────────────────────────────────────╯

╭─ Correction ─────────────────────────────────────────────────╮
│ agents plan correct 01HXR1D2A2B3C4D5E6F7G8H9                 │
│   --mode revert --guidance "Use a different approach..."     │
╰──────────────────────────────────────────────────────────────╯

✓ OK Decision explained


# Approve and proceed to Execute (manual profile requires explicit trigger)
$ agents plan execute 01HXR1C1D2E3F4G5H6I7J8K9L0

╭─ Execution ─────────────────────────────╮
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0        │
│ Phase: execute                          │
│ Sandbox: git_worktree                   │
│ Worker: anthropic/claude-3.5-sonnet     │
│ Started: 09:18:30                       │
│ Attempt: 1                              │
╰─────────────────────────────────────────╯

╭─ Sandbox ───────────────────────────────────────────────────────╮
│ Strategy: git_worktree                                          │
│ Path: /home/dev/projects/api-service/.worktrees/plan-01HXR1C1   │
│ Branch: cleveragents/plan-01HXR1C1D2                            │
│ Status: active                                                  │
╰─────────────────────────────────────────────────────────────────╯

╭─ Progress ────────────────────────────────╮
│ ✓ Collect context (0.4s)                  │
│ ✓ Modify src/routes/health.py (1.2s)      │
│ ✓ Add tests/test_health.py test (2.1s)    │
│ ✓ Validate: pytest tests/ (3.8s)          │
╰───────────────────────────────────────────╯

✓ OK Execution complete — awaiting apply
The execution actor worked in the sandbox (git worktree), modifying `src/routes/health.py` and adding a test in `tests/test_health.py`. Validations ran automatically within the sandbox and passed. #### Step 4: Review and Apply 

# Review the changes
$ agents plan diff 01HXR1C1D2E3F4G5H6I7J8K9L0

╭─ Diff Summary ──────────────────────────────────╮
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0                │
│ Project: local/api-service                      │
│ Files Changed: 2                                │
│ Insertions: 19                                  │
│ Deletions: 3                                    │
│ Net Change: +16 lines                           │
╰─────────────────────────────────────────────────╯

╭─ Files ────────────────────────────────────╮
│ Path                     Change  Status    │
│ ───────────────────────  ──────  ────────  │
│ src/routes/health.py     +8 -3   modified  │
│ tests/test_health.py     +11 -0  modified  │
╰────────────────────────────────────────────╯

╭─ Patch Preview ──────────────────────────────────────────────────╮
│ --- a/src/routes/health.py                                       │
│ +++ b/src/routes/health.py                                       │
│ @@ -8,6 +8,11 @@                                                 │
│  @app.get("/health")                                             │
│  def health_check():                                             │
│ -    db_status = check_database_connection()                     │
│ -    return {"status": "ok", "database": db_status}              │
│ +    try:                                                        │
│ +        db_status = check_database_connection()                 │
│ +        return {"status": "ok", "database": "available"}        │
│ +    except ConnectionError:                                     │
│ +        return {"status": "degraded", "database": "unavailable"}│
│ --- a/tests/test_health.py                                       │
│ +++ b/tests/test_health.py                                       │
│ @@ -15,0 +16,11 @@                                               │
│ +def test_health_db_unavailable(client, monkeypatch):            │
│ +    def mock_check():                                           │
│ +        raise ConnectionError("DB unreachable")                 │
│ +    monkeypatch.setattr("src.routes.health.check_database…")    │
│ +    response = client.get("/health")                            │
│ +    assert response.status_code == 200                          │
│ +    data = response.json()                                      │
│ +    assert data["status"] == "degraded"                         │
│ +    assert data["database"] == "unavailable"                    │
╰──────────────────────────────────────────────────────────────────╯

╭─ Risk Assessment ────────────────╮
│ API Compatibility: preserved     │
│ Test Coverage: increased         │
│ Breaking Changes: none detected  │
╰──────────────────────────────────╯

✓ OK Diff generated


# Check plan status (should be execute/complete, awaiting apply)
$ agents plan status 01HXR1C1D2E3F4G5H6I7J8K9L0

╭─ Plan Status ───────────────────────────╮
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0        │
│ Phase: execute                          │
│ State: complete                         │
│ Action: local/fix-bug                   │
│ Project: local/api-service              │
│ Automation: manual                      │
│ Attempt: 1                              │
╰─────────────────────────────────────────╯

╭─ Progress ───────────╮
│ ✓ Strategize         │
│ ✓ Execute            │
│ • Apply (awaiting)   │
╰──────────────────────╯

╭─ Timing ───────────────────────────╮
│ Started: 2026-02-11 09:17:02       │
│ Elapsed: 00:01:42                  │
│ ETA: awaiting manual apply         │
╰────────────────────────────────────╯

╭─ Execution Detail ──────────╮
│ Sandbox: git_worktree       │
│ Tool Calls: 5               │
│ Files Modified: 2           │
│ Child Plans: 0              │
│ Checkpoints: 1 created      │
╰─────────────────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 6,840   │
│ Cost So Far: $0.023  │
│ Estimated: $0.025    │
╰──────────────────────╯

✓ OK Status refreshed


# Apply the changes to the real repository
$ agents plan apply --yes 01HXR1C1D2E3F4G5H6I7J8K9L0

╭─ Apply Summary ──────────────────────────╮
│ Plan: 01HXR1C1D2E3F4G5H6I7J8K9L0         │
│ Artifacts: 2 files updated               │
│ Changes: 19 insertions, 3 deletions      │
│ Project: local/api-service               │
│ Applied At: 2026-02-11 09:19             │
╰──────────────────────────────────────────╯

╭─ Validation ───────────────────╮
│ Tests: passed (14/14)          │
│ Duration: 3.8s                 │
╰────────────────────────────────╯

╭─ Sandbox Cleanup ──────────────────────╮
│ Worktree: removed                      │
│ Branch: merged to main                 │
│ Checkpoint: archived                   │
╰────────────────────────────────────────╯

╭─ Plan Lifecycle ──────────────────────╮
│ Phase: apply                          │
│ State: applied                        │
│ Total Duration: 00:01:58              │
│ Total Cost: $0.025                    │
│ Decisions Made: 4                     │
│ Child Plans: 0                        │
╰───────────────────────────────────────╯

╭─ Next Steps ──────╮
│ - Review git diff │
│ - Commit changes  │
╰───────────────────╯

✓ OK Changes applied
The sandbox changes are merged into the main working tree. The bug is fixed. --- ### Example 2: Automated Test Generation for a Module **Scenario**: A team wants to increase test coverage for their `auth` module from 45% to 80%. They trust CleverAgents to generate tests autonomously, but want to review before applying. **Complexity**: Intermediate. Single project, trusted automation profile, validation-driven. #### Step 1: Setup (Assuming Project Exists) 

# Register a coverage validation
# (project local/api-service and resource local/api-service-repo already exist)
$ agents validation add \
    --config validations/auth-coverage.yaml \
    --required \
    local/auth-coverage

╭─ Validation Registered ──────────────────────────────────────╮
│ Name: local/auth-coverage                                    │
│ Command: pytest --cov=src/auth --cov-fail-under=80           │
│         tests/test_auth/                                     │
│ Description: Coverage must be at least 80%                   │
│ Mode: required                                               │
│ Timeout: 600s                                                │
╰──────────────────────────────────────────────────────────────╯

✓ OK Validation registered

$ agents validation attach --project local/api-service local/auth-coverage

✓ OK Validation attached to project local/api-service

# Automation profile will be set per-plan via --automation-profile on plan use
#### Step 2: Create the Test Generation Action Create `actions/generate-tests.yaml`: 

name: local/generate-tests
description: "Generate comprehensive tests for a module"
long_description: |
  Analyze the target module's code paths, identify untested branches,
  edge cases, and error conditions, then generate thorough test cases.
  Uses the project's existing test framework and conventions.
definition_of_done: |
  - Coverage of the target module reaches the specified threshold
  - All new tests pass
  - All existing tests continue to pass
  - Tests follow existing project conventions (fixtures, naming, structure)
  - No production code is modified
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
reusable: true
state: available
read_only: false
args:
  - name: target_module
    type: string
    required: true
    description: "Module path to generate tests for (e.g., src/auth)"
  - name: coverage_target
    type: integer
    required: false
    description: "Target coverage percentage"
    default: 80
invariants:
  - "Do not modify any production code — only add or modify test files"
  - "Follow the existing test file naming convention (test_<module>.py)"
  - "Use the project's existing test fixtures and conftest.py patterns"


$ agents action create --config ./actions/generate-tests.yaml

╭─ Action Created ───────────────────────────────────╮
│ Name: local/generate-tests                         │
│ ID: 01HXR2B1C2D3E4F5G6H7I8J9K0                     │
│ State: available                                   │
│ Strategy Actor: anthropic/claude-3.5-sonnet        │
│ Execution Actor: anthropic/claude-3.5-sonnet       │
│ Reusable: yes                                      │
│ Read Only: no                                      │
│ Config: ./actions/generate-tests.yaml              │
│ Created: 2026-02-11 09:15                          │
╰────────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────────────╮
│ - Coverage of the target module reaches the specified threshold   │
│ - All new tests pass                                              │
│ - All existing tests continue to pass                             │
│ - Tests follow existing project conventions                       │
│ - No production code is modified                                  │
╰───────────────────────────────────────────────────────────────────╯

╭─ Arguments ───────────────────────────────────────────────────────────────────╮
│ Name              Type     Required  Description                              │
│ ────────────────  ───────  ────────  ───────────────────────────────────────  │
│ target_module     string   yes       Module path to generate tests for        │
│ coverage_target   integer  no        Target coverage percentage (default 80)  │
╰───────────────────────────────────────────────────────────────────────────────╯

╭─ Invariants ──────────────────────────────────────────────────────────────────╮
│ 1. Do not modify any production code — only add or modify test files          │
│ 2. Follow the existing test file naming convention (test_<module>.py)         │
│ 3. Use the project's existing test fixtures and conftest.py patterns          │
╰───────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: supervised                   │
│ Source: default                       │
╰───────────────────────────────────────╯

✓ OK Action created
#### Step 3: Execute 

# With trusted profile: Strategize and Execute run automatically,
# only Apply requires human approval
$ agents plan use \
    --automation-profile trusted \
    --arg target_module="src/auth" \
    --arg coverage_target=80 \
    local/generate-tests local/api-service

╭─ Plan Created ──────────────────────────────────────╮
│ Plan: 01HXR2B3C4D5E6F7G8H9J0K1L2                    │
│ Phase: strategize                                   │
│ State: processing                                   │
│ Action: local/generate-tests                        │
│ Project: local/api-service                          │
│ Automation: trusted                                 │
│ Attempt: 1                                          │
╰─────────────────────────────────────────────────────╯

╭─ Inputs ────────────────────────────╮
│ - target_module=src/auth            │
│ - coverage_target=80                │
│ - automation_profile=trusted        │
╰─────────────────────────────────────╯

╭─ Actors ────────────────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet           │
│ Execution: anthropic/claude-3.5-sonnet          │
│ Estimation: (none)                              │
╰─────────────────────────────────────────────────╯

╭─ Automation ───────────────────────────╮
│ Profile: trusted                       │
│ Source: plan override                  │
│ Read-Only: no                          │
╰────────────────────────────────────────╯

╭─ Context ────────────────────────╮
│ Resources: 1 (repo)              │
│ Indexed Files: 214               │
│ View: strategize                 │
│ Hot Token Budget: 8,000          │
╰──────────────────────────────────╯

╭─ Next Steps ─────────────────────────────────────────────────────────╮
│ Trusted profile — strategize and execute will proceed automatically. │
│ - agents plan status 01HXR2B3C4D5E6F7G8H9J0K1L2                      │
│ - agents plan tree 01HXR2B3C4D5E6F7G8H9J0K1L2                        │
╰──────────────────────────────────────────────────────────────────────╯

✓ OK Plan created
The system runs through Strategize and Execute automatically. The strategy actor analyzes coverage gaps, identifies 12 untested code paths, and plans test cases. The execution actor writes tests in the sandbox. Validations run. If coverage reaches 80%, the plan reaches `execute/complete` and waits for apply. 

# Check progress while it runs
$ agents plan status 01HXR2B3C4D5E6F7G8H9J0K1L2

╭─ Plan Status ───────────────────────────────╮
│ Plan: 01HXR2B3C4D5E6F7G8H9J0K1L2            │
│ Phase: execute                              │
│ State: processing                           │
│ Action: local/generate-tests                │
│ Project: local/api-service                  │
│ Automation: trusted                         │
│ Attempt: 1                                  │
╰─────────────────────────────────────────────╯

╭─ Progress ───────╮
│ ✓ Strategize     │
│ ⏳ Execute        │
│ • Apply (queued) │
╰──────────────────╯

╭─ Timing ──────────╮
│ Started: 09:15:42 │
│ Elapsed: 00:02:18 │
│ ETA: 00:04:30     │
╰───────────────────╯

╭─ Execution Detail ──────────╮
│ Sandbox: git_worktree       │
│ Tool Calls: 14              │
│ Files Modified: 5           │
│ Child Plans: 0              │
│ Checkpoints: 3 created      │
╰─────────────────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 18,740  │
│ Cost So Far: $0.062  │
│ Estimated: $0.110    │
╰──────────────────────╯

✓ OK Status refreshed


# When complete, review the generated tests
$ agents plan diff 01HXR2B3C4D5E6F7G8H9J0K1L2

╭─ Diff Summary ─────────────────────────────────────╮
│ Plan: 01HXR2B3C4D5E6F7G8H9J0K1L2                   │
│ Project: local/api-service                         │
│ Files Changed: 5                                   │
│ Insertions: 287                                    │
│ Deletions: 3                                       │
│ Net Change: +284 lines                             │
╰────────────────────────────────────────────────────╯

╭─ Files ────────────────────────────────────────────────╮
│ Path                            Change    Status       │
│ ──────────────────────────────  ────────  ──────────   │
│ tests/test_auth/test_login.py   +72 -0    new file     │
│ tests/test_auth/test_tokens.py  +68 -0    new file     │
│ tests/test_auth/test_session.py +54 -0    new file     │
│ tests/test_auth/test_rbac.py    +41 -0    new file     │
│ tests/test_auth/conftest.py     +52 -3    modified     │
╰────────────────────────────────────────────────────────╯

╭─ Patch Preview ───────────────────────────────────────────╮
│ --- /dev/null                                             │
│ +++ b/tests/test_auth/test_login.py                       │
│ @@ -0,0 +1,72 @@                                          │
│ + import pytest                                           │
│ + from src.auth.login import authenticate, verify_mfa     │
│ + ...                                                     │
│ --- a/tests/test_auth/conftest.py                         │
│ +++ b/tests/test_auth/conftest.py                         │
│ @@ -1,5 +1,54 @@                                          │
│ - # minimal fixtures                                      │
│ + # shared auth test fixtures                             │
│ + @pytest.fixture                                         │
│ + def mock_user_db(): ...                                 │
╰───────────────────────────────────────────────────────────╯

╭─ Risk Assessment ────────────────╮
│ API Compatibility: preserved     │
│ Test Coverage: 45% → 83%         │
│ Breaking Changes: none detected  │
╰──────────────────────────────────╯

✓ OK Diff generated


$ agents plan artifacts 01HXR2B3C4D5E6F7G8H9J0K1L2

╭─ Artifacts ──────────────────────────────────────────────────────────╮
│ Path                              Type   Size    Change  Child Plan  │
│ ────────────────────────────────  ─────  ──────  ──────  ───────     │
│ tests/test_auth/test_login.py     write  3.8 KB  +72 -0  root        │
│ tests/test_auth/test_tokens.py    write  3.4 KB  +68 -0  root        │
│ tests/test_auth/test_session.py   write  2.7 KB  +54 -0  root        │
│ tests/test_auth/test_rbac.py      write  2.1 KB  +41 -0  root        │
│ tests/test_auth/conftest.py       edit   2.6 KB  +52 -3  root        │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Summary ────────────╮
│ Total: 5             │
│ Writes: 4 (new)      │
│ Edits: 1 (modified)  │
│ Deletes: 0           │
│ Total Size: 14.6 KB  │
╰──────────────────────╯

✓ OK 5 artifacts listed


# Apply the generated tests to the real repository
$ agents plan apply --yes 01HXR2B3C4D5E6F7G8H9J0K1L2

╭─ Apply Summary ──────────────────────────╮
│ Plan: 01HXR2B3C4D5E6F7G8H9J0K1L2         │
│ Artifacts: 5 files updated               │
│ Changes: 287 insertions, 3 deletions     │
│ Project: local/api-service               │
│ Applied At: 2026-02-11 09:22             │
╰──────────────────────────────────────────╯

╭─ Validation ──────────────────────────╮
│ ✓ Coverage: passed (83% ≥ 80%)        │
│ ✓ All tests: passed (47/47)           │
│ Duration: 18.2s                       │
╰───────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ─────────────────────────╮
│ Phase: apply                             │
│ State: applied                           │
│ Total Duration: 00:06:38                 │
│ Total Cost: $0.107                       │
│ Decisions Made: 12                       │
│ Child Plans: 0                           │
╰──────────────────────────────────────────╯

╭─ Next Steps ──────╮
│ - Review git diff │
│ - Commit changes  │
╰───────────────────╯

✓ OK Changes applied
--- ### Example 3: Multi-File Refactoring with Invariants **Scenario**: A senior engineer wants to refactor the authentication module to replace raw SQL queries with an ORM. The refactoring must maintain API backward compatibility and all existing tests must pass. Multiple invariants constrain the work. **Complexity**: Intermediate-Advanced. Single project, multiple invariants, decision tree review. #### Step 1: Define Invariants 

$ agents invariant add --global "All public APIs must maintain backward compatibility"

╭─ Invariant Added ──────────────────────────────────────────────────────╮
│ Invariant: All public APIs must maintain backward compatibility        │
│ Scope: global                                                          │
│ ID: inv_01HXR3A1B                                                      │
╰────────────────────────────────────────────────────────────────────────╯

✓ OK Invariant added

$ agents invariant add --project local/api-service \
    "Database queries must use the SQLAlchemy ORM, not raw SQL"

╭─ Invariant Added ───────────────────────────────────────────────────────╮
│ Project: local/api-service                                              │
│ Invariant: Database queries must use the SQLAlchemy ORM, not raw SQL    │
│ Scope: project                                                          │
│ ID: inv_01HXR3A2C                                                       │
╰─────────────────────────────────────────────────────────────────────────╯

✓ OK Invariant added

$ agents invariant list --project local/api-service --effective

╭─ Effective Invariants (Project local/api-service) ─────────────────────────────────────╮
│ ID              Source    Text                                                         │
│ ──────────────  ────────  ──────────────────────────────────────────────────────       │
│ inv_01HXR3A1B  global    All public APIs must maintain backward compatibility          │
│ inv_01HXR3A2C  project   Database queries must use the SQLAlchemy ORM, not raw SQL     │
╰────────────────────────────────────────────────────────────────────────────────────────╯

✓ OK 2 effective invariants (1 global, 1 project)
#### Step 2: Create a Refactoring Action with Custom Actors Create `actors/refactoring-strategist.yaml`: 
name: local/refactoring-strategist
cleveragents:
  version: "3.0"
actors:
  strategist:
    type: llm
    config:
      provider: anthropic
      model: claude-3.5-sonnet
      temperature: 0.2
      system_prompt: |
        You are an expert software architect specializing in database layer refactoring.
        You analyze codebases to plan safe, incremental refactoring strategies.
        You always preserve backward compatibility and plan for comprehensive testing.
        Project: {{ context.project_name }}
        Resources: {{ context.resources | join(', ') }}
      memory_enabled: true
      max_history: 100


$ agents actor add --config ./actors/refactoring-strategist.yaml

╭─ Actor Added ────────────────────────────────────╮
│ Name: local/refactoring-strategist               │
│ Provider: anthropic                              │
│ Model: claude-3.5-sonnet                         │
│ Default: yes                                     │
│ Unsafe: no                                       │
│ Type: graph                                      │
╰──────────────────────────────────────────────────╯

╭─ Config ────────────────────────────────────────────────────╮
│ Path: ./actors/refactoring-strategist.yaml                  │
│ Hash: 7a1e4c9                                               │
│ Options: 3                                                  │
│ Nodes: 1                                                    │
│ Edges: 0                                                    │
╰─────────────────────────────────────────────────────────────╯

╭─ Capabilities ────────────────╮
│ - database layer refactoring  │
│ - incremental strategy        │
│ - backward compatibility      │
╰───────────────────────────────╯

✓ OK Actor added
Create `actions/refactor-to-orm.yaml`: 
name: local/refactor-to-orm
description: "Refactor raw SQL queries to use SQLAlchemy ORM"
long_description: |
  Systematically replace all raw SQL queries in the target module with
  SQLAlchemy ORM equivalents. Create ORM model definitions, replace
  query construction, update transaction handling, and ensure all
  existing behavior is preserved.
definition_of_done: |
  - Zero raw SQL strings remain in the target module
  - All ORM models are defined with proper relationships
  - All existing tests pass without modification
  - New integration tests verify ORM query correctness
  - API response formats are unchanged
  - Database migration script is generated
strategy_actor: local/refactoring-strategist
execution_actor: anthropic/claude-3.5-sonnet
estimation_actor: anthropic/claude-3.5-sonnet
reusable: true
state: available
automation_profile: cautious
args:
  - name: target_module
    type: string
    required: true
    description: "Module to refactor"
invariants:
  - "Each file must be refactored in a separate commit-sized change"
  - "ORM models must be defined before queries are converted"
  - "All raw SQL must be replaced — no partial conversion"


$ agents action create --config ./actions/refactor-to-orm.yaml

╭─ Action Created ─────────────────────────────────────────────╮
│ Name: local/refactor-to-orm                                  │
│ ID: 01HXR3B1D2E3F4G5H6J7K8L9M0                               │
│ State: available                                             │
│ Strategy Actor: local/refactoring-strategist                 │
│ Execution Actor: anthropic/claude-3.5-sonnet                 │
│ Reusable: yes                                                │
│ Read Only: no                                                │
│ Created: 2026-02-11 09:14                                    │
╰──────────────────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────────╮
│ - Zero raw SQL strings remain in the target module            │
│ - All ORM models are defined with proper relationships        │
│ - All existing tests pass without modification                │
│ - New integration tests verify ORM query correctness          │
│ - API response formats are unchanged                          │
│ - Database migration script is generated                      │
╰───────────────────────────────────────────────────────────────╯

╭─ Arguments ──────────────────────────────────────────────╮
│ Name            Type    Required  Description            │
│ ──────────────  ──────  ────────  ─────────────────────  │
│ target_module   string  yes       Module to refactor     │
╰──────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: cautious                     │
│ Source: action config                 │
╰───────────────────────────────────────╯

╭─ Action Invariants ──────────────────────────────────────────────────────╮
│ 1. Each file must be refactored in a separate commit-sized change        │
│ 2. ORM models must be defined before queries are converted               │
│ 3. All raw SQL must be replaced — no partial conversion                  │
╰──────────────────────────────────────────────────────────────────────────╯

╭─ Usage ───────────────────────────────────────────────────────────────────╮
│ agents plan use local/refactor-to-orm local/api-service                   │
│   --arg target_module="src/auth"                                          │
╰───────────────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 3: Execute with Cautious Profile 

$ agents plan use \
    --arg target_module="src/auth" \
    local/refactor-to-orm local/api-service

╭─ Plan Created ───────────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                     │
│ Action: local/refactor-to-orm                        │
│ Project: local/api-service                           │
│ Automation: cautious                                 │
│ Attempt: 1                                           │
╰──────────────────────────────────────────────────────╯

╭─ Inputs ────────────────────────╮
│ - target_module="src/auth"      │
│ - automation_profile=cautious   │
╰─────────────────────────────────╯

╭─ Actors ───────────────────────────────────────╮
│ Strategy: local/refactoring-strategist         │
│ Execution: anthropic/claude-3.5-sonnet         │
│ Estimation: anthropic/claude-3.5-sonnet        │
╰────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────────╮
│ Profile: cautious                         │
│ Source: action config                     │
│ Read-Only: no                             │
╰───────────────────────────────────────────╯

╭─ Context ───────────────────────╮
│ Resources: 2 (repo, db)         │
│ Indexed Files: 214              │
│ View: strategize                │
│ Hot Token Budget: 16,000        │
╰─────────────────────────────────╯

╭─ Next Steps ──────────────────────────────────────────╮
│ - agents plan execute 01HXR3C4D5E6F7G8H9J0K1L2M3      │
│ - agents plan status 01HXR3C4D5E6F7G8H9J0K1L2M3       │
│ - agents plan tree 01HXR3C4D5E6F7G8H9J0K1L2M3         │
╰───────────────────────────────────────────────────────╯

✓ OK Plan created
Because the `cautious` profile uses intermediate confidence thresholds, the system: 1. Enters Strategize automatically (threshold 0.7, confidence is high for well-understood tasks) 2. Makes strategy decisions automatically when confidence >= 0.6, but pauses for complex architectural choices 3. The Invariant Reconciliation Actor reconciles global ("backward compatibility"), project ("use ORM"), and action ("separate commits") invariants 

# The system pauses at a decision where confidence is below threshold.
# Review the decision tree:

$ agents plan tree 01HXR3C4D5E6F7G8H9J0K1L2M3

╭─ Decision Tree ────────────────────────────────────────────────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                                                           │
│ ├─ [prompt_definition] "Refactor raw SQL in src/auth to SQLAlchemy ORM"                    │
│ ├─ [invariant_enforced] "All public APIs must maintain backward compatibility"             │
│ ├─ [invariant_enforced] "Database queries must use the SQLAlchemy ORM"                     │
│ ├─ [invariant_enforced] "Each file refactored in a separate commit-sized change"           │
│ ├─ [invariant_enforced] "ORM models must be defined before queries are converted"          │
│ ├─ [strategy_choice] "Define ORM models first, then convert queries" (conf: 0.85)          │
│ ├─ [strategy_choice] "Place models inline in route files" (conf: 0.48) ⏸ PAUSED            │
│ └─ • (awaiting input — confidence below threshold)                                         │
╰────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Tree Summary ─────────────╮
│ Nodes: 8                   │
│ Depth: 2                   │
│ Child Plans: 0             │
│ Invariants: 4              │
│ Superseded: 0 (hidden)     │
╰────────────────────────────╯

╭─ Decision IDs (for correction) ──────────────────────╮
│ Root: 01HXR3D1A2B3C4D5E6F7G8H9                       │
│ Invariant 1: 01HXR3D1B3C4D5E6F7G8H9J0                │
│ Invariant 2: 01HXR3D1C4D5E6F7G8H9J0K1                │
│ Invariant 3: 01HXR3D1D5E6F7G8H9J0K1L2                │
│ Invariant 4: 01HXR3D1E6F7G8H9J0K1L2M3                │
│ Strategy 1: 01HXR3D2E3F4G5H6I7J8K9L0                 │
│ Strategy 2: 01HXR3D5F6G7H8I9J0K1L2M3 (paused)        │
╰──────────────────────────────────────────────────────╯

✓ OK Decision tree rendered

# The paused decision is about model placement. Inspect it:

$ agents plan explain 01HXR3D5F6G7H8I9J0K1L2M3

╭─ Decision ──────────────────────────────────────────────╮
│ ID: 01HXR3D5F6G7H8I9J0K1L2M3                            │
│ Type: strategy_choice                                   │
│ Question: Where should ORM model classes be placed?     │
│ Chosen: Place models inline in route files              │
│ Confidence: 0.48                                        │
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                        │
│ Sequence: 6 of 7                                        │
│ Created: 2026-02-11 09:15                               │
╰─────────────────────────────────────────────────────────╯

╭─ Alternatives Considered ─────────────────────────────────────╮
│ 1. Place models inline in route files (chosen)                │
│ 2. Separate models/ directory with one model per file         │
│ 3. Single models.py file alongside routes                     │
╰───────────────────────────────────────────────────────────────╯

╭─ Impact ──────────────────────╮
│ Downstream Decisions: 4       │
│ Downstream Child Plans: 0     │
│ Artifacts Produced: 0         │
│ Correction Impact: high       │
╰───────────────────────────────╯

╭─ Rationale ────────────────────────────────────────────────────────╮
│ Placing models inline minimizes import changes and keeps related   │
│ code co-located. However, this conflicts with project conventions  │
│ and may make models harder to reuse across modules. The low        │
│ confidence reflects genuine uncertainty about the trade-off.       │
╰────────────────────────────────────────────────────────────────────╯

╭─ Correction ───────────────────────────────────────────────────────╮
│ agents plan correct 01HXR3D5F6G7H8I9J0K1L2M3                       │
│   --mode revert --guidance "Use separate models/ directory..."     │
╰────────────────────────────────────────────────────────────────────╯

✓ OK Decision explained

# Provide guidance via the plan prompt command

$ agents plan prompt 01HXR3C4D5E6F7G8H9J0K1L2M3 \
    "Convert the User model first, then Session, then Token. \
     Use Alembic for the migration script."

╭─ Guidance Added ─────────────────────────────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                                         │
│ Guidance: Convert the User model first, then Session, then Token.        │
│           Use Alembic for the migration script.                          │
│ Scope: next execution step                                               │
│ Phase: strategize                                                        │
│ State: awaiting_input → processing                                       │
╰──────────────────────────────────────────────────────────────────────────╯

╭─ Decision Created ───────────────────────────╮
│ Type: user_intervention                      │
│ ID: 01HXR3E1A2B3C4D5E6F7G8H9                 │
│ Parent: 01HXR3D5F6G7H8I9J0K1L2M3             │
╰──────────────────────────────────────────────╯

╭─ Queue ────╮
│ Pending: 1 │
│ Applied: 0 │
╰────────────╯

✓ OK Guidance queued

# Execution continues. Monitor progress:

$ agents plan status 01HXR3C4D5E6F7G8H9J0K1L2M3

╭─ Plan Status ───────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                │
│ Phase: execute                                  │
│ State: processing                               │
│ Action: local/refactor-to-orm                   │
│ Project: local/api-service                      │
│ Automation: cautious                            │
│ Attempt: 1                                      │
╰─────────────────────────────────────────────────╯

╭─ Progress ───────╮
│ ✓ Strategize     │
│ ⏳ Execute       │
│ • Apply (queued) │
╰──────────────────╯

╭─ Timing ──────────╮
│ Started: 09:14:22 │
│ Elapsed: 00:02:38 │
│ ETA: 00:05:10     │
╰───────────────────╯

╭─ Execution Detail ──────────╮
│ Sandbox: git_worktree       │
│ Tool Calls: 14              │
│ Files Modified: 4           │
│ Child Plans: 0/0 complete   │
│ Checkpoints: 3 created      │
╰─────────────────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 18,740  │
│ Cost So Far: $0.062  │
│ Estimated: $0.128    │
╰──────────────────────╯

✓ OK Status refreshed
#### Step 4: Correct a Decision During execution, you notice the strategy chose to inline the ORM models in the same file as the routes. You want them in a separate `models/` directory: 

# Find the decision that chose inline models

$ agents plan tree --show-superseded 01HXR3C4D5E6F7G8H9J0K1L2M3

╭─ Decision Tree ────────────────────────────────────────────────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                                                           │
│ ├─ [prompt_definition] "Refactor raw SQL in src/auth to SQLAlchemy ORM"                    │
│ ├─ [invariant_enforced] "All public APIs must maintain backward compatibility"             │
│ ├─ [invariant_enforced] "Database queries must use the SQLAlchemy ORM"                     │
│ ├─ [invariant_enforced] "Each file refactored in a separate commit-sized change"           │
│ ├─ [invariant_enforced] "ORM models must be defined before queries are converted"          │
│ ├─ [strategy_choice] "Define ORM models first, then convert queries" (conf: 0.85)          │
│ ├─ [strategy_choice] "Place models inline in route files" (superseded)                     │
│ ├─ [user_intervention] "Convert User first, then Session, then Token"                      │
│ ├─ [strategy_choice] "Create User ORM model in routes/auth.py" (conf: 0.74)                │
│ ├─ [tool_invocation] write_file src/auth/routes/auth.py                                    │
│ └─ [tool_invocation] write_file src/auth/routes/session.py                                 │
╰────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Tree Summary ─────────────╮
│ Nodes: 11                  │
│ Depth: 3                   │
│ Child Plans: 0             │
│ Invariants: 4              │
│ Superseded: 1 (shown)      │
╰────────────────────────────╯

╭─ Decision IDs (for correction) ──────────────────────╮
│ Root: 01HXR3D1A2B3C4D5E6F7G8H9                       │
│ Strategy 1: 01HXR3D2E3F4G5H6I7J8K9L0                 │
│ Strategy 2: 01HXR3D5F6G7H8I9J0K1L2M3 (superseded)    │
│ Intervention: 01HXR3E1A2B3C4D5E6F7G8H9               │
│ Strategy 3: 01HXR3F1A2B3C4D5E6F7G8H9                 │
│ Tool 1: 01HXR3F2B3C4D5E6F7G8H9J0                     │
│ Tool 2: 01HXR3F3C4D5E6F7G8H9J0K1                     │
╰──────────────────────────────────────────────────────╯

✓ OK Decision tree rendered

# Correct it — revert mode replays from that decision

$ agents plan correct 01HXR3F1A2B3C4D5E6F7G8H9 \
    --mode revert \
    --guidance "Place ORM models in src/auth/models/ with one model per file. \
                Import them in src/auth/models/__init__.py." --yes

╭─ Correction ────────────────────────────────────────────────╮
│ Mode: revert                                                │
│ Impact: 2 decisions, 0 child plans, 2 artifacts             │
│ New Decision: 01HXR3G1A2B3C4D5E6F7G8H9                      │
│ Corrects: 01HXR3F1A2B3C4D5E6F7G8H9                          │
│ Attempt: 2                                                  │
│ Correction ID: 01HXR3CORR1A2B3C4D5E6                        │
╰─────────────────────────────────────────────────────────────╯

╭─ Affected Subtree ──────────────╮
│ Decisions Invalidated: 2        │
│ Child Plans Rolled Back: 0      │
│ Artifacts Archived: 2           │
│ Unaffected Decisions: 6         │
╰─────────────────────────────────╯

╭─ Sandbox Rollback ─────────────╮
│ Checkpoint: cp_01HXR3C4        │
│ Files Reverted: 2              │
│ Status: restored               │
╰────────────────────────────────╯

╭─ Recompute ───────────────╮
│ Queued: re-execute        │
│ ETA: 3m                   │
╰───────────────────────────╯

╭─ History ───────────────────────────────────────────────╮
│ - Original decision superseded                          │
│ - Prior artifacts archived for comparison               │
│ - agents plan diff --correction 01HXR3CORR1A2B3C4D5E6   │
╰─────────────────────────────────────────────────────────╯

✓ OK Correction applied

# The affected subtree is recomputed. Review the new approach:

$ agents plan diff --correction 01HXR3CORR1A2B3C4D5E6

╭─ Correction Diff ────────────────────────────────────────────╮
│ Correction: 01HXR3CORR1A2B3C4D5E6                            │
│ Original Decision: 01HXR3F1A2B3C4D5E6F7G8H9                  │
│ Mode: revert                                                 │
│ Files Changed: 5                                             │
│ New Insertions: 84                                           │
│ New Deletions: 36                                            │
╰──────────────────────────────────────────────────────────────╯

╭─ Comparison ──────────────────────────────────────────────────────────────╮
│ File                            Before (original)  After (corrected)      │
│ ──────────────────────────────  ────────────────  ────────────────────    │
│ src/auth/routes/auth.py         +42 -8 (inline)   +6 -8 (imports only)    │
│ src/auth/routes/session.py      +28 -6 (inline)   +4 -6 (imports only)    │
│ src/auth/models/__init__.py     (did not exist)    (new file)             │
│ src/auth/models/user.py         (did not exist)    (new file, +38)        │
│ src/auth/models/session.py      (did not exist)    (new file, +26)        │
╰───────────────────────────────────────────────────────────────────────────╯

╭─ Patch Preview (corrected vs original) ───────────────────────────╮
│ --- a/src/auth/routes/auth.py (original)                          │
│ +++ b/src/auth/routes/auth.py (corrected)                         │
│ @@ -1,42 +1,6 @@                                                  │
│ - class User(Base):  # was inline                                 │
│ -     __tablename__ = "users"                                     │
│ -     id = Column(Integer, primary_key=True)                      │
│ + from src.auth.models import User                                │
│   ...                                                             │
│ +++ b/src/auth/models/user.py (new file)                          │
│ @@ -0,0 +1,38 @@                                                  │
│ + from sqlalchemy import Column, Integer, String                  │
│ + from sqlalchemy.orm import relationship                         │
│ + class User(Base):                                               │
│ +     __tablename__ = "users"                                     │
│   ...                                                             │
╰───────────────────────────────────────────────────────────────────╯

✓ OK Correction diff generated
#### Step 5: Apply 

$ agents plan diff 01HXR3C4D5E6F7G8H9J0K1L2M3

╭─ Diff Summary ───────────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                     │
│ Project: local/api-service                           │
│ Files Changed: 9                                     │
│ Insertions: 186                                      │
│ Deletions: 94                                        │
│ Net Change: +92 lines                                │
╰──────────────────────────────────────────────────────╯

╭─ Files ───────────────────────────────────────────────╮
│ Path                            Change    Status      │
│ ──────────────────────────────  ────────  ──────────  │
│ src/auth/models/__init__.py     +8        new file    │
│ src/auth/models/user.py         +38       new file    │
│ src/auth/models/session.py      +26       new file    │
│ src/auth/models/token.py        +22       new file    │
│ src/auth/routes/auth.py         +12 -28   modified    │
│ src/auth/routes/session.py      +8 -22    modified    │
│ src/auth/routes/token.py        +6 -18    modified    │
│ src/auth/db.py                  +14 -26   modified    │
│ alembic/versions/001_orm.py     +52       new file    │
╰───────────────────────────────────────────────────────╯

╭─ Risk Assessment ────────────────╮
│ API Compatibility: preserved     │
│ Test Coverage: maintained        │
│ Breaking Changes: none detected  │
╰──────────────────────────────────╯

✓ OK Diff generated

$ agents plan apply --yes 01HXR3C4D5E6F7G8H9J0K1L2M3

╭─ Apply Summary ───────────────────────────────────╮
│ Plan: 01HXR3C4D5E6F7G8H9J0K1L2M3                  │
│ Artifacts: 9 files updated                        │
│ Changes: 186 insertions, 94 deletions             │
│ Project: local/api-service                        │
│ Applied At: 2026-02-11 09:23                      │
╰───────────────────────────────────────────────────╯

╭─ Validation ───────────────────────╮
│ Tests: passed (47/47)              │
│ Lint: passed (0 warnings)          │
│ Type Check: passed (0 errors)      │
│ Duration: 18.6s                    │
╰────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ───────────────────────────────╮
│ Phase: apply                                   │
│ State: applied                                 │
│ Total Duration: 00:08:42                       │
│ Total Cost: $0.128                             │
│ Decisions Made: 11                             │
│ Corrections: 1                                 │
│ Child Plans: 0                                 │
╰────────────────────────────────────────────────╯

╭─ Next Steps ──────╮
│ - Review git diff │
│ - Commit changes  │
╰───────────────────╯

✓ OK Changes applied
--- ### Example 4: Multi-Project Dependency Update **Scenario**: An organization has three microservices that share a common library. The library has a breaking change that requires coordinated updates across all three services. The update must be validated in each service independently before any changes are applied. **Complexity**: Advanced. Multiple projects, child plans, coordinated apply. #### Step 1: Register All Projects and Resources 
# Register the common-lib resource (full output shown)

$ agents resource add git-checkout local/common-lib-repo --path /repos/common-lib --branch main

╭─ Resource ──────────────────────────────────────╮
│ Name: local/common-lib-repo                     │
│ ID: 01HXR4A1B2C3D4E5F6G7H8J9K0                  │
│ Type: git-checkout                              │
│ Physical/Virtual: physical                      │
│ Path: /repos/common-lib                         │
│ Branch: main                                    │
│ Created: 2026-02-11 10:00                       │
╰─────────────────────────────────────────────────╯

╭─ Auto-discovered Children ─────────────────────────────────────────╮
│ ID               Type            Status                            │
│ ───────────────  ──────────────  ─────────────────                 │
│ 01HXR4A1B2C3…   git             created                            │
│ 01HXR4A1B2C4…   git-remote      created                            │
│ 01HXR4A1B2C5…   git-branch      created                            │
│   + 31 git-commit resources                                        │
│   + 186 git-tree-entry resources                                   │
│   + 2 fs-directory + 14 fs-file                                    │
╰────────────────────────────────────────────────────────────────────╯

╭─ Capabilities ─────────────────╮
│ Readable: yes                  │
│ Writable: yes                  │
│ Sandboxable: yes               │
│ Checkpointable: yes            │
│ Sandbox Strategy: git_worktree │
╰────────────────────────────────╯

✓ OK Resource registered (236 child resources discovered)

# Register the remaining 3 service resources (condensed output)

$ agents resource add git-checkout local/user-service-repo --path /repos/user-service --branch main
✓ OK Resource registered — Name: local/user-service-repo (312 children)

$ agents resource add git-checkout local/order-service-repo --path /repos/order-service --branch main
✓ OK Resource registered — Name: local/order-service-repo (287 children)

$ agents resource add git-checkout local/billing-service-repo --path /repos/billing-service --branch main
✓ OK Resource registered — Name: local/billing-service-repo (264 children)

# Create the common-lib project (full output shown)

$ agents project create -d "Shared common library" \
    --resource local/common-lib-repo local/common-lib

╭─ Project Created ─────────────────────────╮
│ Name: local/common-lib                    │
│ Description: Shared common library        │
│ Type: local                               │
│ Created: 2026-02-11 10:01                 │
╰───────────────────────────────────────────╯

╭─ Linked Resources ───────────────────────────────────────╮
│ Resource               Type            Read-Only         │
│ ─────────────────────  ──────────────  ─────────         │
│ local/common-lib-repo  git-checkout    no                │
╰──────────────────────────────────────────────────────────╯

╭─ Defaults ──────────────────────────────╮
│ Sandbox: git_worktree                   │
│ Validations: 0                          │
│ Context Filters: none                   │
│ Automation Profile: (inherits global)   │
╰─────────────────────────────────────────╯

✓ OK Project created

# Create the remaining 3 service projects (condensed output)

$ agents project create -d "User microservice" \
    --resource local/user-service-repo local/user-service
✓ OK Project created — Name: local/user-service

$ agents project create -d "Order microservice" \
    --resource local/order-service-repo local/order-service
✓ OK Project created — Name: local/order-service

$ agents project create -d "Billing microservice" \
    --resource local/billing-service-repo local/billing-service
✓ OK Project created — Name: local/billing-service

# Register a shared validation — first one with full output

$ agents validation add --config validations/pytest-mypy.yaml --required local/pytest-mypy

╭─ Validation Registered ─────────────────────────────╮
│ Name: local/pytest-mypy                             │
│ Command: pytest tests/ && mypy src/                 │
│ Mode: required                                      │
│ Timeout: 300s                                       │
╰─────────────────────────────────────────────────────╯

✓ OK Validation registered

# Attach the validation to all 4 projects

$ agents validation attach --project local/common-lib local/pytest-mypy
✓ OK Validation attached to project local/common-lib

$ agents validation attach --project local/user-service local/pytest-mypy
✓ OK Validation attached to project local/user-service

$ agents validation attach --project local/order-service local/pytest-mypy
✓ OK Validation attached to project local/order-service

$ agents validation attach --project local/billing-service local/pytest-mypy
✓ OK Validation attached to project local/billing-service
#### Step 2: Create a Coordinated Update Action Create `actions/coordinated-dependency-update.yaml`: 
name: local/coordinated-dep-update
description: "Update a shared dependency across multiple projects"
long_description: |
  When a shared library introduces a breaking change, this action coordinates
  the update across all dependent projects. It analyzes the breaking changes,
  creates per-project update plans as child plans, validates each independently,
  and produces a coordinated changeset.
definition_of_done: |
  - The shared library is updated to the target version
  - All dependent projects compile and pass tests with the new version
  - API contracts between services remain compatible
  - Migration guides are generated for each project if needed
  - All changes can be applied atomically or rolled back as a unit
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
automation_profile: supervised
reusable: true
state: available
args:
  - name: library_name
    type: string
    required: true
    description: "Name of the shared library to update"
  - name: target_version
    type: string
    required: true
    description: "Target version to update to"
  - name: changelog_url
    type: string
    required: false
    description: "URL to the library changelog or migration guide"
invariants:
  - "Each dependent project must be updated in its own child plan"
  - "All child plans must pass validation before any can be applied"
  - "The library update in common-lib must be applied first"

$ agents action create --config ./actions/coordinated-dependency-update.yaml

╭─ Action Created ─────────────────────────────────────────────╮
│ Name: local/coordinated-dep-update                           │
│ ID: 01HXR4B1D2E3F4G5H6J7K8L9M0                               │
│ State: available                                             │
│ Strategy Actor: anthropic/claude-3.5-sonnet                  │
│ Execution Actor: anthropic/claude-3.5-sonnet                 │
│ Reusable: yes                                                │
│ Read Only: no                                                │
│ Created: 2026-02-11 10:02                                    │
╰──────────────────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────────────────╮
│ - The shared library is updated to the target version                 │
│ - All dependent projects compile and pass tests with the new version  │
│ - API contracts between services remain compatible                    │
│ - Migration guides are generated for each project if needed           │
│ - All changes can be applied atomically or rolled back as a unit      │
╰───────────────────────────────────────────────────────────────────────╯

╭─ Arguments ──────────────────────────────────────────────────────────────────────╮
│ Name            Type    Required  Description                                    │
│ ──────────────  ──────  ────────  ──────────────────────────────────────────     │
│ library_name    string  yes       Name of the shared library to update           │
│ target_version  string  yes       Target version to update to                    │
│ changelog_url   string  no        URL to the library changelog or migration      │
╰──────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: supervised                   │
│ Source: action config                 │
╰───────────────────────────────────────╯

╭─ Action Invariants ──────────────────────────────────────────────────────────────╮
│ 1. Each dependent project must be updated in its own child plan                  │
│ 2. All child plans must pass validation before any can be applied                │
│ 3. The library update in common-lib must be applied first                        │
╰──────────────────────────────────────────────────────────────────────────────────╯

╭─ Usage ───────────────────────────────────────────────────────────────────────────╮
│ agents plan use local/coordinated-dep-update local/common-lib                     │
│   --arg library_name="authlib" --arg target_version="2.0.0"                       │
╰───────────────────────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 3: Execute Across Multiple Projects 
# Create a plan targeting all four projects

$ agents plan use \
    --automation-profile supervised \
    --arg library_name="authlib" \
    --arg target_version="2.0.0" \
    --arg changelog_url="https://authlib.org/changelog/2.0" \
    local/coordinated-dep-update \
    local/common-lib local/user-service local/order-service local/billing-service

╭─ Plan Created ────────────────────────────────────────────╮
│ Plan: 01HXR4D5E6F7G8H9J0K1L2M3N4                          │
│ Action: local/coordinated-dep-update                      │
│ Projects: local/common-lib, local/user-service,           │
│           local/order-service, local/billing-service      │
│ Automation: supervised                                    │
│ Attempt: 1                                                │
╰───────────────────────────────────────────────────────────╯

╭─ Inputs ───────────────────────────────────────────────────────────╮
│ - library_name="authlib"                                           │
│ - target_version="2.0.0"                                           │
│ - changelog_url="https://authlib.org/changelog/2.0"                │
│ - automation_profile=supervised                                    │
╰────────────────────────────────────────────────────────────────────╯

╭─ Actors ───────────────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet          │
│ Execution: anthropic/claude-3.5-sonnet         │
╰────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────────╮
│ Profile: supervised                       │
│ Source: CLI override                      │
│ Read-Only: no                             │
╰───────────────────────────────────────────╯

╭─ Context ──────────────────────────╮
│ Resources: 4 (git-checkout)        │
│ Indexed Files: 1,099               │
│ View: strategize                   │
│ Hot Token Budget: 24,000           │
╰────────────────────────────────────╯

╭─ Next Steps ──────────────────────────────────────────────╮
│ - agents plan tree 01HXR4D5E6F7G8H9J0K1L2M3N4             │
│ - agents plan status 01HXR4D5E6F7G8H9J0K1L2M3N4           │
│ - agents plan execute 01HXR4D5E6F7G8H9J0K1L2M3N4          │
╰───────────────────────────────────────────────────────────╯

✓ OK Plan created
The system creates a parent plan. Strategize runs automatically (supervised profile). It produces a strategy that: 1. Analyzes the breaking changes in authlib 2.0.0 2. Plans child plans for each project 3. Orders the updates: common-lib first, then services in parallel 
# Review the strategy before execution begins

$ agents plan tree 01HXR4D5E6F7G8H9J0K1L2M3N4

╭─ Decision Tree ─────────────────────────────────────────────────────────────────────────────────────╮
│ Plan: 01HXR4D5E6F7G8H9J0K1L2M3N4                                                                    │
│ ├─ [prompt_definition] "Update authlib to 2.0.0 across 4 projects"                                  │
│ ├─ [invariant_enforced] "Each dependent project must be updated in its own child plan"              │
│ ├─ [invariant_enforced] "All child plans must pass validation before any can be applied"            │
│ ├─ [invariant_enforced] "The library update in common-lib must be applied first"                    │
│ ├─ [strategy_choice] "Analyze changelog for breaking API changes" (conf: 0.92)                      │
│ ├─ [strategy_choice] "Update common-lib first, then services in parallel" (conf: 0.88)              │
│ ├─ [strategy_choice] "Create 4 child plans: common-lib, user-svc, order-svc, billing-svc"           │
│ │                     (conf: 0.90)                                                                  │
│ └─ • (awaiting execution approval — supervised profile)                                             │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Tree Summary ──────────────╮
│ Nodes: 8                    │
│ Depth: 2                    │
│ Child Plans: 0 (planned: 4) │
│ Invariants: 3               │
│ Superseded: 0 (hidden)      │
╰─────────────────────────────╯

╭─ Decision IDs (for correction) ──────────────────────────╮
│ Root: 01HXR4D6A1B2C3D4E5F6G7H8                           │
│ Invariant 1: 01HXR4D6B2C3D4E5F6G7H8J9                    │
│ Invariant 2: 01HXR4D6C3D4E5F6G7H8J9K0                    │
│ Invariant 3: 01HXR4D6D4E5F6G7H8J9K0L1                    │
│ Strategy 1: 01HXR4D7E5F6G7H8I9J0K1L2                     │
│ Strategy 2: 01HXR4D7F6G7H8I9J0K1L2M3                     │
│ Strategy 3: 01HXR4D7G7H8I9J0K1L2M3N4                     │
╰──────────────────────────────────────────────────────────╯

✓ OK Decision tree rendered

$ agents plan status 01HXR4D5E6F7G8H9J0K1L2M3N4

╭─ Plan Status ──────────────────────────────────────────╮
│ Plan: 01HXR4D5E6F7G8H9J0K1L2M3N4                       │
│ Phase: strategize → execute (pending approval)         │
│ State: awaiting_input                                  │
│ Action: local/coordinated-dep-update                   │
│ Projects: 4                                            │
│ Automation: supervised                                 │
│ Attempt: 1                                             │
╰────────────────────────────────────────────────────────╯

╭─ Progress ────────────────────────────╮
│ ✓ Strategize                          │
│ ⏸ Execute (awaiting approval)         │
│ • Apply (queued)                      │
╰───────────────────────────────────────╯

╭─ Timing ──────────╮
│ Started: 10:02:14 │
│ Elapsed: 00:01:42 │
│ ETA: 00:12:00     │
╰───────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 8,420   │
│ Cost So Far: $0.028  │
│ Estimated: $0.340    │
╰──────────────────────╯

✓ OK Status refreshed

# Manually approve execution (supervised requires explicit approval)

$ agents plan execute 01HXR4D5E6F7G8H9J0K1L2M3N4

╭─ Execution Started ──────────────────────────────────────╮
│ Plan: 01HXR4D5E6F7G8H9J0K1L2M3N4                         │
│ Phase: execute                                           │
│ State: processing                                        │
│ Automation: supervised                                   │
╰──────────────────────────────────────────────────────────╯

╭─ Child Plans Spawned ───────────────────────────────────────────────────╮
│ Plan ID                       Project              Status               │
│ ──────────────────────────  ───────────────────  ────────────────       │
│ 01HXR4C1D2E3F4G5H6I7J8K9   local/common-lib     executing               │
│ 01HXR4C2E3F4G5H6I7J8K9L0   local/user-service    waiting (common)       │
│ 01HXR4C3F4G5H6I7J8K9L0M1   local/order-service   waiting (common)       │
│ 01HXR4C4G5H6I7J8K9L0M1N2   local/billing-service waiting (common)       │
╰─────────────────────────────────────────────────────────────────────────╯

╭─ Execution Order ──────────────────────────────────────────╮
│ Phase 1: common-lib (blocking)                             │
│ Phase 2: user-service, order-service, billing-service      │
│          (parallel, after common-lib completes)            │
╰────────────────────────────────────────────────────────────╯

✓ OK Execution started (4 child plans spawned)
#### Step 4: Review and Apply in Order Once all child plans complete execution and pass validation, review and apply them in dependency order. 
# Review common-lib changes first (must be applied before services)

$ agents plan diff 01HXR4C1D2E3F4G5H6I7J8K9

╭─ Diff Summary ───────────────────────────────────────╮
│ Plan: 01HXR4C1D2E3F4G5H6I7J8K9                       │
│ Project: local/common-lib                            │
│ Files Changed: 4                                     │
│ Insertions: 62                                       │
│ Deletions: 38                                        │
│ Net Change: +24 lines                                │
╰──────────────────────────────────────────────────────╯

╭─ Files ───────────────────────────────────────────────────────╮
│ Path                              Change    Status            │
│ ────────────────────────────────  ────────  ──────────        │
│ requirements.txt                  +1 -1     modified          │
│ src/common/auth.py                +28 -19   modified          │
│ src/common/token_validator.py     +18 -12   modified          │
│ tests/test_auth.py                +15 -6    modified          │
╰───────────────────────────────────────────────────────────────╯

╭─ Patch Preview ───────────────────────────────────────────────────╮
│ --- a/requirements.txt                                            │
│ +++ b/requirements.txt                                            │
│ @@ -3,1 +3,1 @@                                                   │
│ - authlib==1.3.2                                                  │
│ + authlib==2.0.0                                                  │
│ --- a/src/common/auth.py                                          │
│ +++ b/src/common/auth.py                                          │
│ @@ -1,6 +1,8 @@                                                   │
│ - from authlib.integrations.requests_client import OAuth2Session  │
│ + from authlib.integrations.httpx_client import AsyncOAuth2Client │
│   ...                                                             │
╰───────────────────────────────────────────────────────────────────╯

╭─ Validation ────────────────────────╮
│ pytest tests/ && mypy src/: passed  │
│ Duration: 12.4s                     │
╰─────────────────────────────────────╯

✓ OK Diff generated

$ agents plan apply --yes 01HXR4C1D2E3F4G5H6I7J8K9

╭─ Apply Summary ──────────────────────────────────────╮
│ Plan: 01HXR4C1D2E3F4G5H6I7J8K9                       │
│ Artifacts: 4 files updated                           │
│ Changes: 62 insertions, 38 deletions                 │
│ Project: local/common-lib                            │
│ Applied At: 2026-02-11 10:14                         │
╰──────────────────────────────────────────────────────╯

╭─ Validation ───────────────────────╮
│ Tests: passed (24/24)              │
│ Type Check: passed (0 errors)      │
│ Duration: 12.4s                    │
╰────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ───────────────────────────────╮
│ Phase: apply                                   │
│ State: applied                                 │
│ Total Duration: 00:03:18                       │
│ Total Cost: $0.064                             │
╰────────────────────────────────────────────────╯

✓ OK Changes applied

# Once common-lib is applied, review the 3 service child plans.
# Full diff shown for user-service; order-service and billing-service condensed.

$ agents plan diff 01HXR4C2E3F4G5H6I7J8K9L0

╭─ Diff Summary ───────────────────────────────────────╮
│ Plan: 01HXR4C2E3F4G5H6I7J8K9L0                       │
│ Project: local/user-service                          │
│ Files Changed: 6                                     │
│ Insertions: 84                                       │
│ Deletions: 52                                        │
│ Net Change: +32 lines                                │
╰──────────────────────────────────────────────────────╯

╭─ Files ───────────────────────────────────────────────────────╮
│ Path                              Change    Status            │
│ ────────────────────────────────  ────────  ──────────        │
│ requirements.txt                  +1 -1     modified          │
│ src/auth/middleware.py             +22 -14   modified         │
│ src/auth/oauth.py                  +18 -12   modified         │
│ src/auth/token.py                  +16 -11   modified         │
│ tests/test_middleware.py           +14 -8    modified         │
│ tests/test_oauth.py                +13 -6    modified         │
╰───────────────────────────────────────────────────────────────╯

╭─ Validation ────────────────────────╮
│ pytest tests/ && mypy src/: passed  │
│ Duration: 18.2s                     │
╰─────────────────────────────────────╯

✓ OK Diff generated

$ agents plan diff 01HXR4C3F4G5H6I7J8K9L0M1

╭─ Diff Summary ───────────────────────────────────────╮
│ Plan: 01HXR4C3F4G5H6I7J8K9L0M1                       │
│ Project: local/order-service                         │
│ Files Changed: 5                                     │
│ Insertions: 71                                       │
│ Deletions: 46                                        │
│ Net Change: +25 lines                                │
╰──────────────────────────────────────────────────────╯

╭─ Validation ────────────────────────╮
│ pytest tests/ && mypy src/: passed  │
│ Duration: 14.7s                     │
╰─────────────────────────────────────╯

✓ OK Diff generated

$ agents plan diff 01HXR4C4G5H6I7J8K9L0M1N2

╭─ Diff Summary ───────────────────────────────────────╮
│ Plan: 01HXR4C4G5H6I7J8K9L0M1N2                       │
│ Project: local/billing-service                       │
│ Files Changed: 4                                     │
│ Insertions: 58                                       │
│ Deletions: 34                                        │
│ Net Change: +24 lines                                │
╰──────────────────────────────────────────────────────╯

╭─ Validation ────────────────────────╮
│ pytest tests/ && mypy src/: passed  │
│ Duration: 11.3s                     │
╰─────────────────────────────────────╯

✓ OK Diff generated

# Apply all 3 service child plans

$ agents plan apply --yes 01HXR4C2E3F4G5H6I7J8K9L0

╭─ Apply Summary ──────────────────────────────────────╮
│ Plan: 01HXR4C2E3F4G5H6I7J8K9L0                       │
│ Artifacts: 6 files updated                           │
│ Changes: 84 insertions, 52 deletions                 │
│ Project: local/user-service                          │
│ Applied At: 2026-02-11 10:16                         │
╰──────────────────────────────────────────────────────╯

╭─ Validation ───────────────────────╮
│ Tests: passed (89/89)              │
│ Type Check: passed (0 errors)      │
│ Duration: 18.2s                    │
╰────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ───────────────────────────────╮
│ Phase: apply                                   │
│ State: applied                                 │
│ Total Duration: 00:04:12                       │
│ Total Cost: $0.082                             │
╰────────────────────────────────────────────────╯

✓ OK Changes applied

$ agents plan apply --yes 01HXR4C3F4G5H6I7J8K9L0M1

╭─ Apply Summary ──────────────────────────────────────╮
│ Plan: 01HXR4C3F4G5H6I7J8K9L0M1                       │
│ Artifacts: 5 files updated                           │
│ Changes: 71 insertions, 46 deletions                 │
│ Project: local/order-service                         │
│ Applied At: 2026-02-11 10:17                         │
╰──────────────────────────────────────────────────────╯

╭─ Validation ───────────────────────╮
│ Tests: passed (76/76)              │
│ Type Check: passed (0 errors)      │
│ Duration: 14.7s                    │
╰────────────────────────────────────╯

╭─ Plan Lifecycle ───────────────────────────────╮
│ Phase: apply                                   │
│ State: applied                                 │
│ Total Duration: 00:03:48                       │
│ Total Cost: $0.074                             │
╰────────────────────────────────────────────────╯

✓ OK Changes applied

$ agents plan apply --yes 01HXR4C4G5H6I7J8K9L0M1N2

╭─ Apply Summary ──────────────────────────────────────╮
│ Plan: 01HXR4C4G5H6I7J8K9L0M1N2                       │
│ Artifacts: 4 files updated                           │
│ Changes: 58 insertions, 34 deletions                 │
│ Project: local/billing-service                       │
│ Applied At: 2026-02-11 10:18                         │
╰──────────────────────────────────────────────────────╯

╭─ Validation ───────────────────────╮
│ Tests: passed (63/63)              │
│ Type Check: passed (0 errors)      │
│ Duration: 11.3s                    │
╰────────────────────────────────────╯

╭─ Plan Lifecycle ───────────────────────────────╮
│ Phase: apply                                   │
│ State: applied                                 │
│ Total Duration: 00:03:22                       │
│ Total Cost: $0.068                             │
╰────────────────────────────────────────────────╯

╭─ Parent Plan Complete ──────────────────────────────────╮
│ Plan: 01HXR4D5E6F7G8H9J0K1L2M3N4                        │
│ Phase: apply                                            │
│ State: applied                                          │
│ Child Plans: 4/4 complete                               │
│ Total Duration: 00:16:04                                │
│ Total Cost: $0.340                                      │
│ All Validations: passed                                 │
╰─────────────────────────────────────────────────────────╯

✓ OK Changes applied
--- ### Example 5: Database Schema Migration with Safety Nets **Scenario**: A team needs to add a `last_login_at` column to a users table with 10 million rows, backfill it from an audit log, and update the application code — all without downtime. **Complexity**: Advanced. Mixed resource types (git + database), custom tools, checkpointing critical. #### Step 1: Register the Database as a Resource Register the custom resource type, then create a resource instance and link it to the project: 

# Register the custom postgres-db resource type
$ agents resource type add --config ./resource-types/postgres-db.yaml

╭─ Resource Type ─────────────────────────╮
│ Name: local/postgres-db                 │
│ Physical/Virtual: physical              │
│ User Addable: yes                       │
│ Registered: 2026-02-11 09:01            │
╰─────────────────────────────────────────╯

╭─ CLI Arguments ──────────────────────────────────────────╮
│ Argument      Required  Description                      │
│ ────────────  ────────  ──────────────────────────────   │
│ --host        yes       Database hostname                │
│ --port        no        Port (default: 5432)             │
│ --database    yes       Database name                    │
│ --schema      no        Schema (default: public)         │
╰──────────────────────────────────────────────────────────╯

╭─ Sandbox ──────────────────────────────╮
│ Strategy: transaction_rollback         │
│ Handler: PostgresHandler (custom)      │
╰────────────────────────────────────────╯

✓ OK Resource type registered
ℹ New subcommand available: agents resource add local/postgres-db


# Register the production database instance
$ agents resource add local/postgres-db local/prod-users-db \
    --host db.internal.example.com \
    --port 5432 \
    --database users_db \
    --schema public

╭─ Resource ───────────────────────────────────────╮
│ Name: local/prod-users-db                        │
│ ID: 01HXR5D3E4F5G6H7J8K9L0M1N2                   │
│ Type: local/postgres-db                          │
│ Physical/Virtual: physical                       │
│ Host: db.internal.example.com                    │
│ Port: 5432                                       │
│ Database: users_db                               │
│ Schema: public                                   │
│ Created: 2026-02-11 09:02                        │
╰──────────────────────────────────────────────────╯

╭─ Capabilities ──────────────────────────╮
│ Readable: yes                           │
│ Writable: yes                           │
│ Sandboxable: yes                        │
│ Checkpointable: yes                     │
│ Sandbox Strategy: transaction_rollback  │
╰─────────────────────────────────────────╯

✓ OK Resource registered


# Link the database resource to the project
$ agents project link-resource local/api-service local/prod-users-db

╭─ Resource Linked ────────────────────────────╮
│ Project: local/api-service                   │
│ Resource: local/prod-users-db                │
│ Type: local/postgres-db                      │
│ Read-Only: no                                │
╰──────────────────────────────────────────────╯

╭─ Access ─────────────────╮
│ Read: allowed            │
│ Write: allowed           │
│ Apply: requires approval │
╰──────────────────────────╯

╭─ Project Resources ─────────────────────────────────────────────╮
│ ID                            Type              Status          │
│ ──────────────────────────────  ────────────────  ──────────    │
│ 01HXR1A1B2C3D4E5F6G7H8J9K0   git-checkout      linked           │
│ 01HXR5D3E4F5G6H7J8K9L0M1N2   local/postgres-db linked (new)     │
╰─────────────────────────────────────────────────────────────────╯

✓ OK Resource linked to project
#### Step 2: Create a Custom Skill with Database Tools Create `skills/database-ops.yaml`: 

name: local/database-ops
description: "Safe database operations with transaction support"
tools:
  - name: query_db
    description: "Execute a read-only SQL query and return results"
    input_schema:
      type: object
      properties:
        sql:
          type: string
          description: "SQL SELECT query"
        params:
          type: array
          description: "Query parameters"
      required: [sql]
    writes: false
    checkpointable: false
    resource_slots:
      - name: database
        type: local/postgres-db
        binding: contextual

  - name: execute_migration
    description: "Execute a DDL migration within a transaction"
    input_schema:
      type: object
      properties:
        up_sql:
          type: string
          description: "Forward migration SQL"
        down_sql:
          type: string
          description: "Rollback migration SQL"
        description:
          type: string
          description: "Human-readable description"
      required: [up_sql, down_sql, description]
    writes: true
    checkpointable: true
    resource_slots:
      - name: database
        type: local/postgres-db
        binding: contextual

  - name: backfill_column
    description: "Batch-update a column using a source query"
    input_schema:
      type: object
      properties:
        table:
          type: string
        column:
          type: string
        source_query:
          type: string
          description: "Query that returns (id, value) pairs"
        batch_size:
          type: integer
          default: 10000
      required: [table, column, source_query]
    writes: true
    checkpointable: true
    resource_slots:
      - name: database
        type: local/postgres-db
        binding: contextual


$ agents skill add --config ./skills/database-ops.yaml

╭─ Skill Registered ─────────────────────────────────────────────╮
│ Name: local/database-ops                                       │
│ Description: Safe database operations with transaction support │
│ Config: ./skills/database-ops.yaml                             │
│ Created: 2026-02-11 09:04                                      │
╰────────────────────────────────────────────────────────────────╯

╭─ Tool Sources ──────────────────────────────────────╮
│ Source    Count  Details                            │
│ ────────  ─────  ────────────────────────────       │
│ custom    3      query_db, execute_migration,       │
│                  backfill_column                    │
│ ────────  ─────  ────────────────────────────       │
│ Total:    3                                         │
╰─────────────────────────────────────────────────────╯

╭─ Resource Slots ───────────────────────────────────╮
│ Tool               Slot      Type                  │
│ ─────────────────  ────────  ──────────────────    │
│ query_db           database   local/postgres-db    │
│ execute_migration  database   local/postgres-db    │
│ backfill_column    database   local/postgres-db    │
╰────────────────────────────────────────────────────╯

✓ OK Skill registered with 3 tools
#### Step 3: Create the Migration Action and Execute the Plan Create `actions/add-column-with-backfill.yaml`: 

name: local/add-column-with-backfill
description: "Add a column, backfill data, and update application code"
definition_of_done: |
  - Database migration adds the column with a sensible default
  - Backfill completes for all rows using the specified source
  - Application code reads/writes the new column
  - All tests pass with the new schema
  - A rollback migration is available and tested
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
automation_profile: review
reusable: true
state: available
args:
  - name: table_name
    type: string
    required: true
  - name: column_name
    type: string
    required: true
  - name: column_type
    type: string
    required: true
  - name: backfill_source
    type: string
    required: true
    description: "Description of where to source backfill data"
invariants:
  - "Migration must be backward-compatible (add column, don't rename or drop)"
  - "Backfill must be batched to avoid locking the table"
  - "Rollback migration must be provided and tested"
  - "Application code must handle both old (null) and new values gracefully"


$ agents action create --config ./actions/add-column-with-backfill.yaml

╭─ Action Created ────────────────────────────────────╮
│ Name: local/add-column-with-backfill                │
│ State: available                                    │
│ Strategy Actor: anthropic/claude-3.5-sonnet         │
│ Execution Actor: anthropic/claude-3.5-sonnet        │
│ Reusable: yes                                       │
│ Read Only: no                                       │
│ Config: ./actions/add-column-with-backfill.yaml     │
│ Created: 2026-02-11 09:05                           │
╰─────────────────────────────────────────────────────╯

╭─ Definition of Done ─────────────────────────────────────────────╮
│ - Database migration adds the column with a sensible default     │
│ - Backfill completes for all rows using the specified source     │
│ - Application code reads/writes the new column                   │
│ - All tests pass with the new schema                             │
│ - A rollback migration is available and tested                   │
╰──────────────────────────────────────────────────────────────────╯

╭─ Arguments ────────────────────────────────────────────────────────────╮
│ Name              Type    Required  Description                        │
│ ────────────────  ──────  ────────  ─────────────────────────────────  │
│ table_name        string  yes       (none)                             │
│ column_name       string  yes       (none)                             │
│ column_type       string  yes       (none)                             │
│ backfill_source   string  yes       Where to source backfill data      │
╰────────────────────────────────────────────────────────────────────────╯

╭─ Invariants ──────────────────────────────────────────────────────────────────────╮
│ 1. Migration must be backward-compatible (add column, don't rename or drop)       │
│ 2. Backfill must be batched to avoid locking the table                            │
│ 3. Rollback migration must be provided and tested                                 │
│ 4. Application code must handle both old (null) and new values gracefully         │
╰───────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────╮
│ Profile: review                   │
│ Source: action config             │
╰───────────────────────────────────╯

╭─ Usage ─────────────────────────────────────────────────────────────────────────╮
│ agents plan use local/add-column-with-backfill local/api-service                │
│   --arg table_name=TABLE --arg column_name=COL                                  │
│   --arg column_type=TYPE --arg backfill_source=SOURCE                           │
╰─────────────────────────────────────────────────────────────────────────────────╯

✓ OK Action created


$ agents plan use local/add-column-with-backfill local/api-service \
    --arg table_name="users" \
    --arg column_name="last_login_at" \
    --arg column_type="TIMESTAMP WITH TIME ZONE" \
    --arg backfill_source="audit_log table, event_type='login', max(created_at) per user_id"

╭─ Plan Created ──────────────────────────────────────╮
│ Plan ID: 01HXR5E6F7G8H9J0K1L2M3N4O5                 │
│ Phase: strategize                                   │
│ Action: local/add-column-with-backfill              │
│ Project: local/api-service                          │
│ Automation: review                                  │
│ Attempt: 1                                          │
╰─────────────────────────────────────────────────────╯

╭─ Inputs ────────────────────────────────────────────────────────────────────────────╮
│ - table_name=users                                                                  │
│ - column_name=last_login_at                                                         │
│ - column_type=TIMESTAMP WITH TIME ZONE                                              │
│ - backfill_source=audit_log table, event_type='login', max(created_at) per user_id  │
╰─────────────────────────────────────────────────────────────────────────────────────╯

╭─ Actors ───────────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet      │
│ Execution: anthropic/claude-3.5-sonnet     │
│ Estimation: (none)                         │
╰────────────────────────────────────────────╯

╭─ Plan Invariants ──────────────────────────────────────────────────────────────╮
│ Scope     Source   Invariant                                                   │
│ ────────  ───────  ──────────────────────────────────────────────────────      │
│ plan      action   Migration must be backward-compatible                       │
│ plan      action   Backfill must be batched to avoid locking the table         │
│ plan      action   Rollback migration must be provided and tested              │
│ plan      action   Application code must handle both old (null) and new values │
╰────────────────────────────────────────────────────────────────────────────────╯

╭─ Context ──────────────────────────────╮
│ Resources: 2 (git-checkout, postgres)  │
│ Indexed Files: 347                     │
│ View: strategize                       │
│ Hot Token Budget: 12,000               │
╰────────────────────────────────────────╯

╭─ Next Steps ───────────────────────────────────────╮
│ - agents plan execute 01HXR5E6F7G8H9J0K1L2M3N4O5   │
│ - agents plan status 01HXR5E6F7G8H9J0K1L2M3N4O5    │
│ - agents plan tree 01HXR5E6F7G8H9J0K1L2M3N4O5      │
╰────────────────────────────────────────────────────╯

✓ OK Plan created
The strategy produces a phased plan with child plans: 1. Generate Alembic migration (add column with NULL default) 2. Generate rollback migration 3. Backfill from audit_log in batches of 10,000 4. Update ORM model and application code 5. Run tests with new schema Each phase creates checkpoints. If the backfill fails at batch 850 of 1,000, the system can restore to the pre-backfill checkpoint rather than starting over. #### Step 4: Monitor Execution and Rollback if Needed 

# Monitor the migration execution
$ agents plan status 01HXR5E6F7G8H9J0K1L2M3N4O5

╭─ Plan Status ───────────────────────────────────────╮
│ Plan: 01HXR5E6F7G8H9J0K1L2M3N4O5                    │
│ Phase: execute                                      │
│ State: processing                                   │
│ Action: local/add-column-with-backfill              │
│ Project: local/api-service                          │
│ Automation: review                                  │
│ Attempt: 1                                          │
╰─────────────────────────────────────────────────────╯

╭─ Progress ─────────────────╮
│ ✓ Strategize               │
│ ⏳ Execute (phase 3 of 5)  │
│ • Apply (queued)           │
╰────────────────────────────╯

╭─ Child Plans ────────────────────────────────────────────────────────────╮
│ Phase  Description                          Status                       │
│ ─────  ───────────────────────────────────  ──────────────────────       │
│ 1      Generate Alembic migration              ✓ complete                │
│ 2      Generate rollback migration             ✓ complete                │
│ 3      Backfill from audit_log                 ⏳ batch 620/1,000        │
│ 4      Update ORM model and application code   ○ waiting                 │
│ 5      Run tests with new schema               ○ waiting                 │
╰──────────────────────────────────────────────────────────────────────────╯

╭─ Execution Detail ──────────────────────╮
│ Sandbox: transaction_rollback           │
│ Tool Calls: 14                          │
│ Files Modified: 2                       │
│ Rows Backfilled: 6,200,000 / 10,000,000 │
│ Checkpoints: 4 created                  │
╰─────────────────────────────────────────╯

╭─ Timing ──────────────╮
│ Started: 09:06:01     │
│ Elapsed: 00:04:32     │
│ ETA: 00:02:50         │
╰───────────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 18,940  │
│ Cost So Far: $0.063  │
│ Estimated: $0.110    │
╰──────────────────────╯

✓ OK Status refreshed


# If something goes wrong during backfill, rollback to the pre-backfill checkpoint
$ agents plan rollback --yes 01HXR5E6F7G8H9J0K1L2M3N4O5 cp_01HXR5CP3

╭─ Rollback Summary ───────────────────────────────────╮
│ Plan: 01HXR5E6F7G8H9J0K1L2M3N4O5                     │
│ Checkpoint: cp_01HXR5CP3                             │
│ Label: before backfill (after migration applied)     │
│ Files: 2 reverted                                    │
╰──────────────────────────────────────────────────────╯

╭─ Changes Reverted ──────────────────────────────────────────╮
│ File                                         Action         │
│ ───────────────────────────────────────────  ──────────     │
│ alembic/versions/20260211_add_last_login.py  restored       │
│ alembic/versions/20260211_rollback.py        restored       │
╰─────────────────────────────────────────────────────────────╯

╭─ Database Rollback ─────────────────────────────────────────╮
│ Transaction: rolled back                                    │
│ Rows Affected: 6,200,000 updates reverted                   │
│ Schema State: restored to pre-backfill                      │
╰─────────────────────────────────────────────────────────────╯

╭─ Impact ──────────────────────────────────────╮
│ Child Plans Invalidated: 1 (backfill phase)   │
│ Sandbox: restored to cp_01HXR5CP3             │
│ Decisions After CP: 3 discarded               │
│ Tool Calls After CP: 8 undone                 │
╰───────────────────────────────────────────────╯

╭─ Post-Rollback State ──────────╮
│ Phase: execute                 │
│ State: queued (awaiting input) │
│ Checkpoints Remaining: 3       │
╰────────────────────────────────╯

✓ OK Rollback complete
--- ### Example 6: Writing Technical Documentation from Codebase Analysis **Scenario**: A project has grown to 50,000 lines of code with minimal documentation. The team wants CleverAgents to generate comprehensive API documentation, architecture guides, and developer onboarding docs by analyzing the actual codebase. **Complexity**: Intermediate. Read-only action, large context usage, no sandbox modifications to source code. #### Step 1: Create a Read-Only Documentation Action Create `actions/generate-docs.yaml`: 

name: local/generate-docs
description: "Generate comprehensive documentation from codebase analysis"
long_description: |
  Analyze the project codebase to produce developer documentation:
  API reference, architecture overview, module guides, and onboarding
  material. Uses code intelligence (search, vector similarity, graph
  queries) to understand structure and relationships.
definition_of_done: |
  - API reference covers all public endpoints/functions
  - Architecture document shows module dependencies and data flow
  - Each major module has a developer guide
  - An onboarding document provides setup and contribution instructions
  - All generated docs are accurate to the current codebase
  - Documentation is written in Markdown format
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
read_only: false
reusable: true
state: available
args:
  - name: doc_types
    type: string
    required: true
    description: "Comma-separated list: api-reference, architecture, module-guides, onboarding"
  - name: output_dir
    type: string
    required: false
    default: "docs/"
    description: "Output directory for generated docs"
invariants:
  - "Do not modify any source code files — only create or update files in the output directory"
  - "All code examples in documentation must be actual code from the project, not fabricated"
  - "Architecture diagrams must reflect actual module dependencies, not aspirational ones"


$ agents action create --config ./actions/generate-docs.yaml

╭─ Action Created ──────────────────────────────────────────────────────────────────╮
│ Name: local/generate-docs                                                         │
│ State: available                                                                  │
│ Strategy Actor: anthropic/claude-3.5-sonnet                                       │
│ Execution Actor: anthropic/claude-3.5-sonnet                                      │
│ Reusable: yes                                                                     │
│ Read Only: no                                                                     │
│ Created: 2026-02-11 10:30                                                         │
╰───────────────────────────────────────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────────────────────────────╮
│ - API reference covers all public endpoints/functions                             │
│ - Architecture document shows module dependencies and data flow                   │
│ - Each major module has a developer guide                                         │
│ - An onboarding document provides setup and contribution instructions             │
│ - All generated docs are accurate to the current codebase                         │
│ - Documentation is written in Markdown format                                     │
╰───────────────────────────────────────────────────────────────────────────────────╯

╭─ Arguments ───────────────────────────────────────────────────────────────────────────────────────╮
│ Name        Type    Required  Description                                                         │
│ ──────────  ──────  ────────  ──────────────────────────────────────────────────────────────      │
│ doc_types   string  yes       Comma-separated list: api-reference, architecture, module-guides…   │
│ output_dir  string  no        Output directory for generated docs (default: docs/)                │
╰───────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Invariants ───────────────────────────────────────────────────────────────────────────────────────╮
│ 1. Do not modify any source code files — only create or update files in the output directory       │
│ 2. All code examples in documentation must be actual code from the project, not fabricated         │
│ 3. Architecture diagrams must reflect actual module dependencies, not aspirational ones            │
╰────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: (inherits global)            │
│ Source: default                       │
╰───────────────────────────────────────╯

╭─ Usage ────────────────────────────────────────────────────────────────────────────╮
│ agents plan use local/generate-docs local/api-service                              │
│   --arg doc_types="api-reference,architecture,module-guides,onboarding"            │
╰────────────────────────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 2: Configure Context for Large Codebase Analysis 

# Set a generous context policy for the strategize view (needs to see architecture)
$ agents project context set --view strategize \
    --include-resource 01HXR6A1B2C3D4E5F6G7H8J9K0 \
    --exclude-path "**/node_modules/**" \
    --exclude-path "**/.git/**" \
    --exclude-path "**/dist/**" \
    --hot-max-tokens 32000 \
    --warm-max-decisions 200 \
    --query-limit 50 \
    --max-file-size 2097152 \
    --summarize \
    --summary-max-tokens 1500 \
    local/api-service

╭─ Context Policy ────────────────────────────────────────╮
│ Project: local/api-service                              │
│ View: strategize                                        │
│ Include: 01HXR6A1B2C3D4E5F6G7H8J9K0                     │
│ Exclude: **/node_modules/**, **/.git/**, **/dist/**     │
╰─────────────────────────────────────────────────────────╯

╭─ Limits ──────────────────────────╮
│ Hot Tokens: 32000 (soft cap)      │
│ Warm Decisions: 200               │
│ Query Limit: 50                   │
│ Max File Size: 2 MB               │
│ Max Total Size: 50 MB             │
╰───────────────────────────────────╯

╭─ Summarization ──────╮
│ Enabled: yes         │
│ Max Tokens: 1500     │
╰──────────────────────╯

╭─ Other Views ──────────╮
│ execute: (default)     │
│ apply: (default)       │
│ default: (unset)       │
╰────────────────────────╯

✓ OK Context policy updated


# Execution view can be narrower (writing docs, not analyzing all code)
$ agents project context set --view execute \
    --include-resource 01HXR6A1B2C3D4E5F6G7H8J9K0 \
    --hot-max-tokens 16000 \
    --query-limit 30 \
    --summarize \
    local/api-service

╭─ Context Policy ────────────────────────────────────────╮
│ Project: local/api-service                              │
│ View: execute                                           │
│ Include: 01HXR6A1B2C3D4E5F6G7H8J9K0                     │
╰─────────────────────────────────────────────────────────╯

╭─ Limits ──────────────────────────╮
│ Hot Tokens: 16000 (soft cap)      │
│ Query Limit: 30                   │
│ Max File Size: 1 MB               │
│ Max Total Size: 50 MB             │
╰───────────────────────────────────╯

╭─ Summarization ─╮
│ Enabled: yes    │
│ Max Tokens: 800 │
╰─────────────────╯

╭─ Other Views ──────────────╮
│ strategize: configured     │
│ apply: (default)           │
│ default: (unset)           │
╰────────────────────────────╯

✓ OK Context policy updated
#### Step 3: Execute 

$ agents plan use \
    --automation-profile trusted \
    --arg doc_types="api-reference,architecture,module-guides,onboarding" \
    --arg output_dir="docs/generated/" \
    local/generate-docs local/api-service

╭─ Plan Created ──────────────────────────────────────╮
│ Plan: 01HXR6F7G8H9J0K1L2M3N4O5P6                    │
│ Phase: strategize                                   │
│ State: processing                                   │
│ Action: local/generate-docs                         │
│ Project: local/api-service                          │
│ Automation: trusted                                 │
│ Attempt: 1                                          │
╰─────────────────────────────────────────────────────╯

╭─ Inputs ─────────────────────────────────────────────────────────────────────╮
│ - doc_types="api-reference,architecture,module-guides,onboarding"            │
│ - output_dir="docs/generated/"                                               │
│ - automation_profile=trusted                                                 │
╰──────────────────────────────────────────────────────────────────────────────╯

╭─ Actors ────────────────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet           │
│ Execution: anthropic/claude-3.5-sonnet          │
│ Estimation: (none)                              │
╰─────────────────────────────────────────────────╯

╭─ Automation ───────────────────────────╮
│ Profile: trusted                       │
│ Source: plan override                  │
│ Read-Only: no                          │
╰────────────────────────────────────────╯

╭─ Context ──────────────────────────╮
│ Resources: 1 (git-checkout)        │
│ Indexed Files: 487                 │
│ View: strategize                   │
│ Hot Token Budget: 32,000           │
╰────────────────────────────────────╯

╭─ Next Steps ─────────────────────────────────────────────────────────╮
│ Trusted profile — strategize and execute will proceed automatically. │
│ - agents plan status 01HXR6F7G8H9J0K1L2M3N4O5P6                      │
│ - agents plan tree 01HXR6F7G8H9J0K1L2M3N4O5P6                        │
╰──────────────────────────────────────────────────────────────────────╯

✓ OK Plan created
The system analyzes the codebase using the code intelligence indexes (full-text, vector, and graph) to understand module relationships, public APIs, and data flows. It generates documentation files in the sandbox. 

# Review generated docs
$ agents plan artifacts 01HXR6F7G8H9J0K1L2M3N4O5P6

╭─ Artifacts ───────────────────────────────────────────────────────────────────────────╮
│ Path                                      Type   Size     Change    Child Plan        │
│ ────────────────────────────────────────  ─────  ───────  ────────  ───────           │
│ docs/generated/api-reference.md           write  18.2 KB  +412 -0   root              │
│ docs/generated/architecture.md            write  12.6 KB  +284 -0   root              │
│ docs/generated/modules/auth.md            write   6.4 KB  +148 -0   root              │
│ docs/generated/modules/billing.md         write   5.8 KB  +131 -0   root              │
│ docs/generated/modules/notifications.md   write   4.2 KB  +97 -0    root              │
│ docs/generated/modules/data-pipeline.md   write   5.1 KB  +118 -0   root              │
│ docs/generated/onboarding.md              write   8.9 KB  +201 -0   root              │
╰───────────────────────────────────────────────────────────────────────────────────────╯

╭─ Summary ─────────────╮
│ Total: 7              │
│ Writes: 7 (new)       │
│ Edits: 0              │
│ Deletes: 0            │
│ Total Size: 61.2 KB   │
╰───────────────────────╯

✓ OK 7 artifacts listed


$ agents plan diff 01HXR6F7G8H9J0K1L2M3N4O5P6

╭─ Diff Summary ─────────────────────────────────────╮
│ Plan: 01HXR6F7G8H9J0K1L2M3N4O5P6                   │
│ Project: local/api-service                         │
│ Files Changed: 7                                   │
│ Insertions: 1,391                                  │
│ Deletions: 0                                       │
│ Net Change: +1,391 lines                           │
╰────────────────────────────────────────────────────╯

╭─ Files ──────────────────────────────────────────────────────────╮
│ Path                                      Change     Status      │
│ ────────────────────────────────────────  ─────────  ─────────   │
│ docs/generated/api-reference.md           +412 -0    new file    │
│ docs/generated/architecture.md            +284 -0    new file    │
│ docs/generated/modules/auth.md            +148 -0    new file    │
│ docs/generated/modules/billing.md         +131 -0    new file    │
│ docs/generated/modules/notifications.md   +97 -0     new file    │
│ docs/generated/modules/data-pipeline.md   +118 -0    new file    │
│ docs/generated/onboarding.md              +201 -0    new file    │
╰──────────────────────────────────────────────────────────────────╯

╭─ Patch Preview ───────────────────────────────────────────────────────╮
│ --- /dev/null                                                         │
│ +++ b/docs/generated/api-reference.md                                 │
│ @@ -0,0 +1,412 @@                                                     │
│ + # API Reference                                                     │
│ + ## Authentication                                                   │
│ + ### POST /auth/login                                                │
│ + ...                                                                 │
│ --- /dev/null                                                         │
│ +++ b/docs/generated/architecture.md                                  │
│ @@ -0,0 +1,284 @@                                                     │
│ + # Architecture Overview                                             │
│ + ## Module Dependency Graph                                          │
│ + ...                                                                 │
╰───────────────────────────────────────────────────────────────────────╯

╭─ Risk Assessment ─────────────────╮
│ Source Code: unmodified           │
│ Breaking Changes: none detected   │
│ New Files Only: yes               │
╰───────────────────────────────────╯

✓ OK Diff generated


# Apply the documentation to the project
$ agents plan apply --yes 01HXR6F7G8H9J0K1L2M3N4O5P6

╭─ Apply Summary ──────────────────────────────╮
│ Plan: 01HXR6F7G8H9J0K1L2M3N4O5P6             │
│ Artifacts: 7 files created                   │
│ Changes: 1,391 insertions, 0 deletions       │
│ Project: local/api-service                   │
│ Applied At: 2026-02-11 10:38                 │
╰──────────────────────────────────────────────╯

╭─ Validation ────────────────────────────────╮
│ ✓ Invariant: no source files modified       │
│ ✓ Invariant: code examples verified         │
│ ✓ Invariant: architecture matches codebase  │
│ Duration: 4.1s                              │
╰─────────────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ─────────────────────────╮
│ Phase: apply                             │
│ State: applied                           │
│ Total Duration: 00:08:12                 │
│ Total Cost: $0.184                       │
│ Decisions Made: 18                       │
│ Child Plans: 0                           │
╰──────────────────────────────────────────╯

╭─ Next Steps ──────╮
│ - Review git diff │
│ - Commit changes  │
╰───────────────────╯

✓ OK Changes applied
--- ### Example 7: CI/CD Integration — Automated PR Review and Fix **Scenario**: A CI pipeline triggers CleverAgents to automatically review incoming pull requests, run analysis, and if issues are found, create fix commits. This runs headlessly without human intervention. **Complexity**: Advanced. Non-interactive (CI profile), headless execution, full automation. #### Step 1: Configure for CI 

# Set CI-appropriate configuration

$ agents config set core.automation-profile ci

╭─ Config Updated ───────────────────────────╮
│ Key: core.automation-profile               │
│ Value: ci                                  │
│ Previous: (not set)                        │
│ Source: config                             │
│ Scope: global                              │
╰────────────────────────────────────────────╯

╭─ Effective ────────────────────────╮
│ Sessions: new sessions             │
│ Plans: future plans (unless set)   │
│ Existing: unchanged                │
╰────────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 3                             │
╰─────────────────────────────────────╯

✓ OK Config updated

$ agents config set core.format json

╭─ Config Updated ─────────────────╮
│ Key: core.format                 │
│ Value: json                      │
│ Previous: (not set)              │
│ Source: config                   │
│ Scope: global                    │
╰──────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 4                             │
╰─────────────────────────────────────╯

✓ OK Config updated

$ agents config set core.log.level WARN

╭─ Config Updated ──────────────────╮
│ Key: core.log.level               │
│ Value: WARN                       │
│ Previous: FATAL                   │
│ Source: config                    │
│ Scope: global                     │
╰───────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 5                             │
╰─────────────────────────────────────╯

✓ OK Config updated
#### Step 2: Create the PR Review Action Create `actions/review-pr.yaml`: 

name: local/review-pr
description: "Automatically review a PR and fix issues"
definition_of_done: |
  - All lint issues are resolved
  - Type checking passes
  - Test coverage does not decrease
  - Security scan passes
  - All fixes are committed to the PR branch
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
automation_profile: ci
reusable: true
state: available
args:
  - name: pr_branch
    type: string
    required: true
    description: "Branch name of the PR"
  - name: base_branch
    type: string
    required: false
    default: "main"
    description: "Base branch to compare against"
invariants:
  - "Only modify files that are already changed in the PR"
  - "Do not change the intent of any code — only fix style, types, and test issues"
  - "All fixes must include a comment explaining what was changed and why"


$ agents action create --config ./actions/review-pr.yaml

╭─ Action Created ──────────────────────────────╮
│ Name: local/review-pr                         │
│ State: available                              │
│ Strategy Actor: anthropic/claude-3.5-sonnet   │
│ Execution Actor: anthropic/claude-3.5-sonnet  │
│ Reusable: yes                                 │
│ Read Only: no                                 │
│ Created: 2026-02-11 14:00                     │
╰───────────────────────────────────────────────╯

╭─ Definition of Done ─────────────────────────────────────╮
│ - All lint issues are resolved                           │
│ - Type checking passes                                   │
│ - Test coverage does not decrease                        │
│ - Security scan passes                                   │
│ - All fixes are committed to the PR branch               │
╰──────────────────────────────────────────────────────────╯

╭─ Arguments ──────────────────────────────────────────────────────╮
│ Name        Type    Required  Description                        │
│ ──────────  ──────  ────────  ────────────────────────────────── │
│ pr_branch   string  yes       Branch name of the PR              │
│ base_branch string  no        Base branch to compare against     │
╰──────────────────────────────────────────────────────────────────╯

╭─ Invariants ─────────────────────────────────────────────────────────────────────╮
│ 1. Only modify files that are already changed in the PR                          │
│ 2. Do not change the intent of any code — only fix style, types, and test        │
│    issues                                                                        │
│ 3. All fixes must include a comment explaining what was changed and why          │
╰──────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────╮
│ Profile: ci                   │
│ Source: action config         │
╰───────────────────────────────╯

╭─ Usage ──────────────────────────────────────────────────────────────────╮
│ agents plan use local/review-pr <PROJECT>                                │
│   --arg pr_branch="..."                                                  │
╰──────────────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 3: CI Pipeline Script 

#!/bin/bash
# ci-review.sh — called by CI when a PR is opened or updated

set -euo pipefail

PR_BRANCH="${1:?Usage: ci-review.sh <branch>}"
BASE_BRANCH="${2:-main}"

# Register the resource pointing to the CI workspace.
RESOURCE_NAME="local/ci-${PR_BRANCH}"
agents resource add git-checkout "$RESOURCE_NAME" \
    --path "$GITHUB_WORKSPACE" \
    --branch "$PR_BRANCH"

echo "Registered resource: $RESOURCE_NAME"

# Create a project for this CI run, linking the resource by name.
# If the project already exists from a previous run, ignore the error.
agents --format json project create -d "CI workspace for PR $PR_BRANCH" \
    --resource "$RESOURCE_NAME" \
    local/ci-workspace 2>/dev/null || true

# Register and attach validations (idempotent — duplicates are ignored)
agents --format json validation add \
    --config validations/lint.yaml --required local/ci-lint 2>/dev/null || true
agents --format json validation add \
    --config validations/typecheck.yaml --required local/ci-typecheck 2>/dev/null || true
agents --format json validation add \
    --config validations/tests.yaml --required local/ci-tests 2>/dev/null || true
agents --format json validation attach \
    --project local/ci-workspace local/ci-lint 2>/dev/null || true
agents --format json validation attach \
    --project local/ci-workspace local/ci-typecheck 2>/dev/null || true
agents --format json validation attach \
    --project local/ci-workspace local/ci-tests 2>/dev/null || true

# Run the plan — ci profile means full automation including apply
PLAN_OUTPUT=$(agents --format json plan use \
    --automation-profile ci \
    --arg pr_branch="$PR_BRANCH" \
    --arg base_branch="$BASE_BRANCH" \
    local/review-pr local/ci-workspace)

PLAN_ID=$(echo "$PLAN_OUTPUT" | jq -r '.plan_id')
echo "Plan started: $PLAN_ID"

# Wait for completion (ci profile runs everything automatically)
while true; do
    STATUS=$(agents --format json plan status "$PLAN_ID" | jq -r '.state')
    case "$STATUS" in
        applied)
            echo "PR review complete. Changes applied."
            break
            ;;
        failed|cancelled)
            echo "PR review failed."
            agents --format json plan status "$PLAN_ID"
            exit 1
            ;;
        *)
            sleep 10
            ;;
    esac
done

# Output the diff for the CI log
agents --format json plan diff "$PLAN_ID"
Sample `--format json` output from `resource add` (captured into `$RESOURCE_JSON`): 

{
  "id": "01HXR7G1A2B3C4D5E6F7H8J9K0",
  "type": "git-checkout",
  "physical": true,
  "path": "/home/runner/work/acme-api/acme-api",
  "branch": "fix/handle-null-users",
  "created": "2026-02-11T14:05:32Z",
  "children_discovered": 247,
  "capabilities": {
    "readable": true,
    "writable": true,
    "sandboxable": true,
    "checkpointable": true,
    "sandbox_strategy": "git_worktree"
  }
}
Sample `--format json` output from `plan use` (captured into `$PLAN_OUTPUT`): 

{
  "plan_id": "01HXR7H2B3C4D5E6F7G8J9K0L1",
  "phase": "strategize",
  "action": "local/review-pr",
  "project": "local/ci-workspace",
  "automation_profile": "ci",
  "attempt": 1,
  "args": {
    "pr_branch": "fix/handle-null-users",
    "base_branch": "main"
  },
  "resources": ["01HXR7G1A2B3C4D5E6F7H8J9K0"]
}
--- ### Example 8: Cloud Infrastructure Management **Scenario**: A DevOps team manages Terraform infrastructure. They want CleverAgents to analyze their current infrastructure, propose optimizations (right-sizing, unused resources), and generate the Terraform changes. **Complexity**: Advanced. Custom resource types, custom skills, infrastructure domain. #### Step 1: Register Custom Resource Types and Skills Create `resource-types/terraform-state.yaml`: 

name: local/terraform-state
description: "Terraform state file resource type"
physical: true
user_addable: true
sandbox_strategy: filesystem_copy
cli_args:
  - name: state-path
    type: string
    required: true
    description: "Path to terraform.tfstate or remote state configuration"
  - name: workspace
    type: string
    required: false
    default: "default"
    description: "Terraform workspace name"
handler: local/terraform-state-handler
child_types:
  - type: fs-file
    relationship: contains
Create `skills/terraform-ops.yaml`: 

name: local/terraform-ops
description: "Terraform infrastructure operations"
tools:
  - name: terraform_plan
    description: "Run terraform plan and return the execution plan"
    input_schema:
      type: object
      properties:
        target:
          type: string
          description: "Specific resource to target (optional)"
      required: []
    writes: false
    checkpointable: false

  - name: terraform_show
    description: "Show current state of a Terraform resource"
    input_schema:
      type: object
      properties:
        resource_address:
          type: string
          description: "Terraform resource address (e.g., aws_instance.web)"
      required: [resource_address]
    writes: false
    checkpointable: false

  - name: cloud_metrics
    description: "Fetch CloudWatch/cloud monitoring metrics for a resource"
    input_schema:
      type: object
      properties:
        resource_id:
          type: string
        metric:
          type: string
          description: "e.g., CPUUtilization, NetworkIn, RequestCount"
        period_days:
          type: integer
          default: 30
      required: [resource_id, metric]
    writes: false
    checkpointable: false

include_skills:
  - local/file-ops


$ agents resource type add --config ./resource-types/terraform-state.yaml

╭─ Resource Type ──────────────────────────────╮
│ Name: local/terraform-state                  │
│ Physical/Virtual: physical                   │
│ User Addable: yes                            │
│ Registered: 2026-02-11 14:30                 │
╰──────────────────────────────────────────────╯

╭─ CLI Arguments ──────────────────────────────────────────────────────────────╮
│ Argument        Required  Description                                        │
│ ──────────────  ────────  ──────────────────────────────────────────────     │
│ --state-path    yes       Path to terraform.tfstate or remote state config   │
│ --workspace     no        Terraform workspace name (default: "default")      │
╰──────────────────────────────────────────────────────────────────────────────╯

╭─ Child Types ──────────────╮
│ Auto-discover: fs-file     │
╰────────────────────────────╯

╭─ Sandbox ───────────────────────────────────────────╮
│ Strategy: filesystem_copy                           │
│ Handler: local/terraform-state-handler (custom)     │
╰─────────────────────────────────────────────────────╯

✓ OK Resource type registered
ℹ New subcommand available: agents resource add local/terraform-state


$ agents skill add --config ./skills/terraform-ops.yaml

╭─ Skill ──────────────────────────────────────────╮
│ Name: local/terraform-ops                        │
│ Description: Terraform infrastructure operations │
│ Config: ./skills/terraform-ops.yaml              │
│ Created: 2026-02-11 14:31                        │
╰──────────────────────────────────────────────────╯

╭─ Includes ────────────────────╮
│ local/file-ops (registered)   │
╰───────────────────────────────╯

╭─ Tool Sources ───────────────────────────────────────────────────────╮
│ Source    Count  Details                                             │
│ ────────  ─────  ──────────────────────────────────────────────      │
│ custom    3      terraform_plan, terraform_show, cloud_metrics       │
│ included  5      local/file-ops (5)                                  │
│ ────────  ─────  ──────────────────────────────────────────────      │
│ Total:    8                                                          │
╰──────────────────────────────────────────────────────────────────────╯

✓ OK Skill registered with 8 tools
#### Step 2: Set Up the Project 

# Register the infrastructure git checkout
$ agents resource add git-checkout local/infra-repo \
    --path /repos/infrastructure --branch main

╭─ Resource ──────────────────────────────────────╮
│ Name: local/infra-repo                          │
│ ID: 01HXR8A1B2C3D4E5F6G7H8J9K0                  │
│ Type: git-checkout                              │
│ Physical/Virtual: physical                      │
│ Path: /repos/infrastructure                     │
│ Branch: main                                    │
│ Created: 2026-02-11 14:32                       │
╰─────────────────────────────────────────────────╯

╭─ Auto-discovered Children ─────────────────────────────────────────╮
│ ID               Type            Status                            │
│ ───────────────  ──────────────  ─────────────────                 │
│ 01HXR8A1B2C3…   git             created                            │
│ 01HXR8A1B2C4…   git-remote      created                            │
│ 01HXR8A1B2C5…   git-branch      created                            │
│ 01HXR8A1B2C6…   fs-directory    created                            │
│   + 18 git-commit resources                                        │
│   + 84 git-tree-entry resources                                    │
│   + 6 fs-directory + 42 fs-file                                    │
╰────────────────────────────────────────────────────────────────────╯

╭─ Capabilities ─────────────────╮
│ Readable: yes                  │
│ Writable: yes                  │
│ Sandboxable: yes               │
│ Checkpointable: yes            │
│ Sandbox Strategy: git_worktree │
╰────────────────────────────────╯

✓ OK Resource registered (155 child resources discovered)


# Register the Terraform state for the production workspace
$ agents resource add local/terraform-state local/prod-tfstate \
    --state-path /repos/infrastructure/environments/prod/terraform.tfstate \
    --workspace production

╭─ Resource ──────────────────────────────────────────────────────────────────╮
│ Name: local/prod-tfstate                                                    │
│ ID: 01HXR8B2C3D4E5F6G7H8J9K0L1                                              │
│ Type: local/terraform-state                                                 │
│ Physical/Virtual: physical                                                  │
│ State Path: /repos/infrastructure/environments/prod/terraform.tfstate       │
│ Workspace: production                                                       │
│ Created: 2026-02-11 14:32                                                   │
╰─────────────────────────────────────────────────────────────────────────────╯

╭─ Auto-discovered Children ─────────────╮
│   + 1 fs-file (terraform.tfstate)      │
╰────────────────────────────────────────╯

╭─ Capabilities ──────────────────────╮
│ Readable: yes                       │
│ Writable: yes                       │
│ Sandboxable: yes                    │
│ Checkpointable: yes                 │
│ Sandbox Strategy: filesystem_copy   │
╰─────────────────────────────────────╯

✓ OK Resource registered (1 child resource discovered)


# Create the project, linking both resources by name
$ agents project create -d "Production infrastructure" \
    --resource local/infra-repo \
    --resource local/prod-tfstate \
    --invariant "Never delete or modify resources tagged with 'critical: true'" \
    --invariant "All changes must be backward-compatible with running services" \
    --invariant "Cost changes must be documented in the PR description" \
    local/infra-prod

╭─ Project Created ─────────────────────────────╮
│ Name: local/infra-prod                        │
│ Description: Production infrastructure        │
│ Remote: no                                    │
╰───────────────────────────────────────────────╯

╭─ Linked Resources ──────────────────────────────────────────────────╮
│ Resource                       Type                    Read-Only    │
│ ────────────────────────────  ──────────────────────  ─────────     │
│ local/infra-repo              git-checkout              no          │
│ local/prod-tfstate            local/terraform-state     no          │
╰─────────────────────────────────────────────────────────────────────╯

╭─ Invariants ──────────────────────────────────────────────────────────────╮
│ 1. Never delete or modify resources tagged with 'critical: true'          │
│ 2. All changes must be backward-compatible with running services          │
│ 3. Cost changes must be documented in the PR description                  │
╰───────────────────────────────────────────────────────────────────────────╯

✓ OK Project created


$ agents validation add --config validations/tf-validate.yaml --required local/tf-validate

╭─ Validation Registered ────────────────────────────────────────────╮
│ Name: local/tf-validate                                            │
│ Command: cd environments/prod && terraform validate                │
│ Mode: required                                                     │
│ Timeout: 300s                                                      │
╰────────────────────────────────────────────────────────────────────╯

✓ OK Validation registered

$ agents validation attach --project local/infra-prod local/tf-validate
✓ OK Validation attached to project local/infra-prod


$ agents validation add --config validations/tf-plan.yaml --informational local/tf-plan

╭─ Validation Registered ─────────────────────────────────────────────────────────╮
│ Name: local/tf-plan                                                             │
│ Command: cd environments/prod && terraform plan -detailed-exitcode              │
│ Mode: informational                                                             │
│ Timeout: 300s                                                                   │
╰─────────────────────────────────────────────────────────────────────────────────╯

✓ OK Validation registered

$ agents validation attach --project local/infra-prod local/tf-plan
✓ OK Validation attached to project local/infra-prod
#### Step 3: Create and Run the Optimization Action Create `actions/infra-optimize.yaml`: 

name: local/infra-optimize
description: "Analyze and optimize cloud infrastructure costs"
definition_of_done: |
  - Unused resources are identified and removal plans generated
  - Over-provisioned resources are identified with right-sizing recommendations
  - Terraform changes implement the approved optimizations
  - terraform validate passes on all changes
  - terraform plan shows no unexpected resource deletions
  - Estimated monthly cost savings are documented
strategy_actor: local/refactoring-strategist
execution_actor: anthropic/claude-3.5-sonnet
automation_profile: supervised
reusable: true
state: available
args:
  - name: optimization_targets
    type: string
    required: false
    default: "all"
    description: "Comma-separated: compute, storage, networking, database, all"
  - name: min_savings_threshold
    type: float
    required: false
    default: 10.0
    description: "Minimum monthly savings (USD) to include an optimization"
invariants:
  - "Changes to production databases require manual approval regardless of profile"
  - "Instance type downgrades must verify current peak CPU < 70% of new capacity"


$ agents action create --config ./actions/infra-optimize.yaml

╭─ Action Created ──────────────────────────────────────╮
│ Name: local/infra-optimize                            │
│ ID: 01HXR8C3D4E5F6G7H8J9K0L1M2                        │
│ State: available                                      │
│ Strategy Actor: local/refactoring-strategist          │
│ Execution Actor: anthropic/claude-3.5-sonnet          │
│ Reusable: yes                                         │
│ Read Only: no                                         │
│ Config: ./actions/infra-optimize.yaml                 │
│ Created: 2026-02-11 14:33                             │
╰───────────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────────────────╮
│ - Unused resources are identified and removal plans generated         │
│ - Over-provisioned resources identified with right-sizing recs        │
│ - Terraform changes implement the approved optimizations              │
│ - terraform validate passes on all changes                            │
│ - terraform plan shows no unexpected resource deletions               │
│ - Estimated monthly cost savings are documented                       │
╰───────────────────────────────────────────────────────────────────────╯

╭─ Arguments ───────────────────────────────────────────────────────────────────────╮
│ Name                    Type    Required  Description                             │
│ ──────────────────────  ──────  ────────  ──────────────────────────────────      │
│ optimization_targets    string  no        Comma-separated: compute, storage, …    │
│ min_savings_threshold   float   no        Min monthly savings (USD) to include    │
╰───────────────────────────────────────────────────────────────────────────────────╯

╭─ Invariants ──────────────────────────────────────────────────────────────────────────╮
│ 1. Changes to production databases require manual approval regardless of profile      │
│ 2. Instance type downgrades must verify current peak CPU < 70% of new capacity        │
╰───────────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: supervised                   │
│ Source: action config                 │
╰───────────────────────────────────────╯

╭─ Usage ─────────────────────────────────────────────────────────────╮
│ agents plan use local/infra-optimize local/infra-prod               │
│   --arg optimization_targets=TARGET --arg min_savings_threshold=N   │
╰─────────────────────────────────────────────────────────────────────╯

✓ OK Action created


$ agents plan use \
    --arg optimization_targets="compute,storage" \
    --arg min_savings_threshold=25.0 \
    local/infra-optimize local/infra-prod

╭─ Plan Created ─────────────────────────────────────────╮
│ Plan ID: 01HXR8D4E5F6G7H8J9K0L1M2N3                    │
│ Phase: strategize                                      │
│ Action: local/infra-optimize                           │
│ Project: local/infra-prod                              │
│ Automation: supervised                                 │
│ Attempt: 1                                             │
╰────────────────────────────────────────────────────────╯

╭─ Inputs ──────────────────────────────────────╮
│ - optimization_targets=compute,storage        │
│ - min_savings_threshold=25.0                  │
╰───────────────────────────────────────────────╯

╭─ Actors ─────────────────────────────────────╮
│ Strategy: local/refactoring-strategist       │
│ Execution: anthropic/claude-3.5-sonnet       │
│ Estimation: (none)                           │
╰──────────────────────────────────────────────╯

╭─ Plan Invariants ──────────────────────────────────────────────────────────────────╮
│ Scope     Source    Invariant                                                      │
│ ────────  ────────  ─────────────────────────────────────────────────────────      │
│ plan      action    Prod DB changes require manual approval regardless             │
│ plan      action    Instance downgrades must verify peak CPU < 70% of new cap      │
│ project   config    Never delete or modify resources tagged 'critical: true'       │
│ project   config    All changes must be backward-compatible with running svcs      │
│ project   config    Cost changes must be documented in PR description              │
╰────────────────────────────────────────────────────────────────────────────────────╯

╭─ Context ──────────────────────────────────────────╮
│ Resources: 2 (git-checkout, terraform-state)       │
│ Indexed Files: 156                                 │
│ View: strategize                                   │
│ Hot Token Budget: 12,000                           │
╰────────────────────────────────────────────────────╯

╭─ Next Steps ──────────────────────────────────────────╮
│ - agents plan execute 01HXR8D4E5F6G7H8J9K0L1M2N3      │
│ - agents plan status 01HXR8D4E5F6G7H8J9K0L1M2N3       │
│ - agents plan tree 01HXR8D4E5F6G7H8J9K0L1M2N3         │
╰───────────────────────────────────────────────────────╯

✓ OK Plan created
The strategy actor queries cloud metrics via the `cloud_metrics` tool, analyzes the Terraform state using `terraform_show`, and proposes optimizations with cost estimates. Because the automation profile is `supervised`, the engineer reviews the full strategy — including any proposed instance downgrades or resource removals — before execution modifies any Terraform files. The execution actor then generates the `.tf` changes, and both validations (`terraform validate` and `terraform plan -detailed-exitcode`) run automatically before the plan can be applied. --- ### Example 9: Session-Driven Interactive Exploration **Scenario**: A developer uses a CleverAgents session to interactively explore a new codebase, ask questions, and gradually build up an action to automate a recurring task. **Complexity**: Beginner-Intermediate. Session-based, conversational, action creation through natural language. #### Step 1: Start a Session 

$ agents session create --actor anthropic/claude-3.5-sonnet

╭─ Session ────────────────────────────────╮
│ ID: 01HXR9A1B2C3D4E5F6G7H8I9J0           │
│ Actor: anthropic/claude-3.5-sonnet       │
│ Created: 2026-02-11 09:15                │
│ Namespace: local                         │
╰──────────────────────────────────────────╯

╭─ Settings ─────────────╮
│ Automation: review     │
│ Streaming: off         │
│ Context: default       │
│ Memory: enabled        │
│ Max History: 50 turns  │
╰────────────────────────╯

╭─ Actor Details ────────────────────────╮
│ Provider: anthropic                    │
│ Model: claude-3.5-sonnet               │
│ Temperature: 0.7                       │
│ Context Window: 200K tokens            │
╰────────────────────────────────────────╯

✓ OK Session created
#### Step 2: Explore the Codebase Interactively 

$ agents session tell --session 01HXR9A1B2C3D4E5F6G7H8I9J0 \
    "I just joined the team and need to understand the api-service project. What are the main modules and how do they interact?"

╭─ Plan Request ──────────────────────────────────────────────────────────────────────────╮
│ Actor: anthropic/claude-3.5-sonnet                                                      │
│ Session: 01HXR9A1B2C3D4E5F6G7H8I9J0                                                     │
│ Automation: review                                                                      │
│ Prompt: I just joined the team and need to understand the api-service project. Wha...   │
╰─────────────────────────────────────────────────────────────────────────────────────────╯

▍ The **api-service** project is organized into 5 core modules:

  1. **`src/api/routes/`** — HTTP route definitions (REST + GraphQL). Each domain
     entity has its own router file (e.g. `users.py`, `orders.py`, `products.py`).

  2. **`src/api/services/`** — Business logic layer. Services are injected into
     routes via dependency injection. Key files: `user_service.py`,
     `order_service.py`, `notification_service.py`.

  3. **`src/api/models/`** — SQLAlchemy ORM models and Pydantic schemas. The
     models map 1:1 to database tables; schemas handle request/response validation.

  4. **`src/api/auth/`** — Authentication and authorization. Implements JWT-based
     auth with role-based access control. Middleware in `auth_middleware.py`
     intercepts every request before it reaches a route handler.

  5. **`src/api/workers/`** — Background task processors using Celery. Handles
     async jobs like email dispatch, report generation, and webhook delivery.

  **Data flow**: Routes → Services → Models → Database. Auth middleware gates
  every route. Workers are dispatched by services for async operations.

╭─ Commands Executed ──────────────────────────────────────────────────────────────╮
│ - agents resource inspect local/api-service-repo --tree                          │
│ - agents resource inspect local/api-service-repo --file src/api/__init__.py      │
╰──────────────────────────────────────────────────────────────────────────────────╯

╭─ Usage ─────────────────────╮
│ Input Tokens: 2,480         │
│ Output Tokens: 846          │
│ Cost: $0.0128               │
│ Duration: 4.1s              │
│ Tool Calls: 2               │
╰─────────────────────────────╯

✓ OK Orchestrator completed 2 commands


$ agents session tell --session 01HXR9A1B2C3D4E5F6G7H8I9J0 \
    "Show me how authentication works. What's the flow from request to response?"

╭─ Plan Request ───────────────────────────────────────────────────────────────────╮
│ Actor: anthropic/claude-3.5-sonnet                                               │
│ Session: 01HXR9A1B2C3D4E5F6G7H8I9J0                                              │
│ Automation: review                                                               │
│ Prompt: Show me how authentication works. What's the flow from request to res... │
╰──────────────────────────────────────────────────────────────────────────────────╯

▍ Here is the authentication flow in **api-service**:

  **1. Request arrives** → `auth_middleware.py:34` extracts the `Authorization`
  header and parses the Bearer token.

  **2. Token validation** → `token_service.py:71` decodes the JWT using the
  public key from `config.AUTH_PUBLIC_KEY`. It verifies:
     - Signature (RS256)
     - Expiry (`exp` claim, default 3600s)
     - Issuer (`iss` must match `api-service`)

  **3. User resolution** → `user_service.py:45` loads the user record from the
  database using the `sub` claim. Returns 401 if the user is inactive or deleted.

  **4. Permission check** → `rbac.py:22` evaluates the user's roles against the
  endpoint's required permissions (defined as decorators on each route, e.g.
  `@require_role("admin")`). Returns 403 on insufficient permissions.

  **5. Context injection** → The authenticated user object is attached to
  `request.state.user` so downstream route handlers can access it without
  repeating lookups.

  **Key files**: `src/api/auth/auth_middleware.py`, `src/api/auth/token_service.py`,
  `src/api/auth/rbac.py`, `src/api/services/user_service.py`.

╭─ Commands Executed ──────────────────────────────────────────────────────────────────────╮
│ - agents resource inspect local/api-service-repo --file src/api/auth/auth_middleware.py  │
│ - agents resource inspect local/api-service-repo --file src/api/auth/token_service.py    │
│ - agents resource inspect local/api-service-repo --file src/api/auth/rbac.py             │
╰──────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Usage ─────────────────────╮
│ Input Tokens: 3,960         │
│ Output Tokens: 1,024        │
│ Cost: $0.0187               │
│ Duration: 5.3s              │
│ Tool Calls: 3               │
╰─────────────────────────────╯

✓ OK Orchestrator completed 3 commands


$ agents session tell --session 01HXR9A1B2C3D4E5F6G7H8I9J0 \
    "I notice the team manually runs a dependency lock refresh every week. Can you create an action that automates this?"

╭─ Plan Request ──────────────────────────────────────────────────────────────────────────╮
│ Actor: anthropic/claude-3.5-sonnet                                                      │
│ Session: 01HXR9A1B2C3D4E5F6G7H8I9J0                                                     │
│ Automation: review                                                                      │
│ Prompt: I notice the team manually runs a dependency lock refresh every week. Can...    │
╰─────────────────────────────────────────────────────────────────────────────────────────╯

▍ I've created a **local/refresh-locks** action that automates the weekly
  dependency lock refresh. Here's what it does:

  1. Checks out the target project's repository
  2. Runs `pip compile` / `poetry lock` (auto-detected from project config)
  3. Runs the test suite to verify nothing broke
  4. Commits the updated lock files on a new branch
  5. Opens a pull request for review

  The action is now available. You can review the generated config with
  `agents action show local/refresh-locks`.

╭─ Commands Executed ──────────────────────────────────────────────────────╮
│ - agents action create --config ./actions/refresh-locks.yaml             │
╰──────────────────────────────────────────────────────────────────────────╯

╭─ Result ──────────────────────────────╮
│ Action: local/refresh-locks           │
│ Steps: 5                              │
│ Trigger: manual                       │
╰───────────────────────────────────────╯

╭─ Usage ─────────────────────╮
│ Input Tokens: 5,210         │
│ Output Tokens: 1,380        │
│ Cost: $0.0249               │
│ Duration: 6.7s              │
│ Tool Calls: 1               │
╰─────────────────────────────╯

✓ OK Orchestrator completed 1 command
#### Step 3: Review Session History 

$ agents session show 01HXR9A1B2C3D4E5F6G7H8I9J0

╭─ Session Summary ─────────────────────────────╮
│ ID: 01HXR9A1B2C3D4E5F6G7H8I9J0                │
│ Actor: anthropic/claude-3.5-sonnet            │
│ Messages: 6                                   │
│ Created: 2026-02-11 09:15                     │
│ Updated: 2026-02-11 09:28                     │
│ Automation: review                            │
╰───────────────────────────────────────────────╯

╭─ Recent Messages ──────────────────────────────────────────────────────────────────────╮
│ user       I just joined the team and need to understand the api-service project...    │
│ assistant  The api-service project is organized into 5 core modules...                 │
│ user       Show me how authentication works...                                         │
│ assistant  Here is the authentication flow in api-service...                           │
│ user       I notice the team manually runs a dependency lock refresh...                │
│ assistant  I've created a local/refresh-locks action that automates...                 │
╰────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Linked Plans ──────────────────────────────────╮
│ Plan ID                      Phase    State     │
│ ───────────────────────────  ───────  ────────  │
│ 01HXR9K4M7N2P3Q5R6S8T9U0V1  execute  complete   │
╰─────────────────────────────────────────────────╯

╭─ Token Usage ──────────────╮
│ Input Tokens: 11,650       │
│ Output Tokens: 3,250       │
│ Estimated Cost: $0.0564    │
╰────────────────────────────╯

✓ OK Session details loaded


$ agents session export --output /tmp/onboarding-session.json 01HXR9A1B2C3D4E5F6G7H8I9J0

╭─ Session Export ────────────────────────────╮
│ Session: 01HXR9A1B2C3D4E5F6G7H8I9J0         │
│ Output: /tmp/onboarding-session.json        │
│ Messages: 6                                 │
│ Size: 38 KB                                 │
│ Format: JSON                                │
╰─────────────────────────────────────────────╯

╭─ Contents ─────────────────╮
│ Messages: 6                │
│ Plan References: 1         │
│ Metadata Keys: 3           │
│ Actor Config: included     │
│ Schema Version: v3         │
╰────────────────────────────╯

╭─ Integrity ──────────────────╮
│ Checksum: sha256:3e8f...b7d2 │
│ Encrypted: no                │
╰──────────────────────────────╯

✓ OK Export completed
--- ### Example 10: Full-Auto Batch Operations — Formatting and Linting **Scenario**: A team has 15 Python packages in a monorepo that need to be reformatted with `ruff format` and have their imports sorted. This is low-risk and can be fully automated. **Complexity**: Simple. Full-auto profile, batch execution, minimal risk. #### Step 1: Create a Formatting Action Create `actions/format-codebase.yaml`: 

name: local/format-codebase
description: "Apply code formatting and import sorting"
definition_of_done: |
  - ruff format passes with zero changes remaining
  - ruff check --select I passes (imports sorted)
  - All existing tests pass
  - No semantic changes to any code
strategy_actor: anthropic/claude-3.5-sonnet
execution_actor: anthropic/claude-3.5-sonnet
automation_profile: full-auto
reusable: true
state: available
args:
  - name: formatter_config
    type: string
    required: false
    default: "pyproject.toml"
    description: "Path to the formatter configuration file"
invariants:
  - "Only whitespace and import ordering changes — no semantic modifications"
  - "Every package must pass its own test suite after formatting"


$ agents action create --config ./actions/format-codebase.yaml

╭─ Action Created ─────────────────────────────────╮
│ Name: local/format-codebase                      │
│ State: available                                 │
│ Strategy Actor: anthropic/claude-3.5-sonnet      │
│ Execution Actor: anthropic/claude-3.5-sonnet     │
│ Reusable: yes                                    │
│ Read Only: no                                    │
│ Created: 2026-02-11 14:00                        │
╰──────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────╮
│ - ruff format passes with zero changes remaining          │
│ - ruff check --select I passes (imports sorted)           │
│ - All existing tests pass                                 │
│ - No semantic changes to any code                         │
╰───────────────────────────────────────────────────────────╯

╭─ Arguments ──────────────────────────────────────────────────────────────────╮
│ Name              Type    Required  Description                              │
│ ────────────────  ──────  ────────  ──────────────────────────────────────   │
│ formatter_config  string  no        Path to the formatter configuration file │
╰──────────────────────────────────────────────────────────────────────────────╯

╭─ Invariants ──────────────────────────────────────────────────────────────────────╮
│ 1. Only whitespace and import ordering changes — no semantic modifications        │
│ 2. Every package must pass its own test suite after formatting                    │
╰───────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: full-auto                    │
│ Source: action                        │
╰───────────────────────────────────────╯

╭─ Usage ─────────────────────────────────────────────────────────╮
│ agents plan use local/format-codebase local/<project>           │
│   --arg formatter_config="pyproject.toml"  (optional)           │
╰─────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 2: Register All Packages and Run in Batch 

# Register all 15 packages as resources and projects.
# resource add accepts a name — use it to link to project create.

for pkg in auth billing common gateway inventory notifications \
           orders payments reporting search shipping users webhooks \
           workers analytics; do
    agents resource add git-checkout "local/pkg-${pkg}-repo" \
        --path "/repos/monorepo/packages/${pkg}" --branch main
    agents project create -d "Package: ${pkg}" \
        --resource "local/pkg-${pkg}-repo" \
        "local/pkg-${pkg}"
    agents validation add --config "validations/pkg-${pkg}.yaml" --required "local/pkg-${pkg}-test"
    agents validation attach --project "local/pkg-${pkg}" "local/pkg-${pkg}-test"
done


# Loop output — first 2 iterations shown, remaining 13 condensed

# --- auth ---

$ agents resource add git-checkout local/pkg-auth-repo \
    --path /repos/monorepo/packages/auth --branch main

╭─ Resource ──────────────────────────────────────────╮
│ Name: local/pkg-auth-repo                           │
│ ID: 01HXR7B1A2B3C4D5E6F7G8H9J0                      │
│ Type: git-checkout                                  │
│ Physical/Virtual: physical                          │
│ Path: /repos/monorepo/packages/auth                 │
│ Branch: main                                        │
│ Created: 2026-02-11 14:01                           │
╰─────────────────────────────────────────────────────╯

╭─ Auto-discovered Children ─────────────────────────────────────────╮
│ ID               Type            Status                            │
│ ───────────────  ──────────────  ─────────────────                 │
│ 01HXR7B1A2B3…   git             created                            │
│ 01HXR7B1A2B4…   git-remote      created                            │
│ 01HXR7B1A2B5…   git-branch      created                            │
│   + 22 git-commit resources                                        │
│   + 134 git-tree-entry resources                                   │
│   + 2 fs-directory + 11 fs-file                                    │
╰────────────────────────────────────────────────────────────────────╯

╭─ Capabilities ─────────────────╮
│ Readable: yes                  │
│ Writable: yes                  │
│ Sandboxable: yes               │
│ Checkpointable: yes            │
│ Sandbox Strategy: git_worktree │
╰────────────────────────────────╯

✓ OK Resource registered (172 child resources discovered)

$ agents project create -d "Package: auth" \
    --resource local/pkg-auth-repo local/pkg-auth

╭─ Project Created ──────────────────────────────╮
│ Name: local/pkg-auth                           │
│ Description: Package: auth                     │
│ Type: local                                    │
│ Created: 2026-02-11 14:01                      │
╰────────────────────────────────────────────────╯

╭─ Linked Resources ───────────────────────────────────────╮
│ Resource           Type          Read-Only               │
│ ─────────────────  ──────────────  ─────────             │
│ local/pkg-auth-repo  git-checkout    no                  │
╰──────────────────────────────────────────────────────────╯

╭─ Defaults ──────────────────────────────╮
│ Sandbox: git_worktree                   │
│ Validations: 0                          │
│ Context Filters: none                   │
│ Automation Profile: (inherits global)   │
╰─────────────────────────────────────────╯

✓ OK Project created

$ agents validation add --config validations/pkg-auth.yaml --required local/pkg-auth-test

╭─ Validation Registered ─────────────────────────────────────────────────╮
│ Name: local/pkg-auth-test                                               │
│ Command: cd /repos/monorepo/packages/auth && pytest tests/              │
│ Mode: required                                                          │
│ Timeout: 300s                                                           │
╰─────────────────────────────────────────────────────────────────────────╯

✓ OK Validation registered

$ agents validation attach --project local/pkg-auth local/pkg-auth-test
✓ OK Validation attached to project local/pkg-auth

# --- billing ---

$ agents resource add git-checkout local/pkg-billing-repo \
    --path /repos/monorepo/packages/billing --branch main
✓ OK Resource registered — Name: local/pkg-billing-repo (189 children)

$ agents project create -d "Package: billing" \
    --resource local/pkg-billing-repo local/pkg-billing
✓ OK Project created — Name: local/pkg-billing

$ agents validation add --config validations/pkg-billing.yaml --required local/pkg-billing-test
✓ OK Validation registered — Name: local/pkg-billing-test

$ agents validation attach --project local/pkg-billing local/pkg-billing-test
✓ OK Validation attached to project local/pkg-billing

# ... (common, gateway, inventory, notifications, orders, payments,
#      reporting, search, shipping, users, webhooks, workers, analytics)
# Each iteration: resource add → project create → validation add → validation attach
# All 15 packages registered.


# Run formatting across all packages.
# full-auto: Strategize, Execute, AND Apply all run without human intervention.
# Capture plan IDs so we can check results afterward.

PLAN_IDS=()
for pkg in auth billing common gateway inventory notifications \
           orders payments reporting search shipping users webhooks \
           workers analytics; do
    PID=$(agents --format json plan use \
        --automation-profile full-auto \
        local/format-codebase "local/pkg-${pkg}" \
        | jq -r '.data.plan_id')
    PLAN_IDS+=("$PID")
done


# Plan creation output — first 2 shown, remaining condensed

# --- auth ---

$ agents plan use \
    --automation-profile full-auto \
    local/format-codebase local/pkg-auth

╭─ Plan Created ───────────────────────────────────╮
│ Plan ID: 01HXR7D1A2B3C4D5E6F7G8H9J0              │
│ Phase: strategize (running)                      │
│ Action: local/format-codebase                    │
│ Project: local/pkg-auth                          │
│ Automation: full-auto                            │
│ Attempt: 1                                       │
╰──────────────────────────────────────────────────╯

╭─ Invariants ─────────────────────────────────────────────────────────────╮
│ Scope   Source  Invariant                                                │
│ ──────  ──────  ─────────────────────────────────────────────────────    │
│ plan    action  Only whitespace and import ordering changes — no se…     │
│ plan    action  Every package must pass its own test suite after fo…     │
╰──────────────────────────────────────────────────────────────────────────╯

✓ OK Plan created — full-auto: strategize → execute → apply will proceed automatically

# --- billing ---

$ agents plan use \
    --automation-profile full-auto \
    local/format-codebase local/pkg-billing

╭─ Plan Created ───────────────────────────────────╮
│ Plan ID: 01HXR7D2B3C4D5E6F7G8H9J0K1              │
│ Phase: strategize (running)                      │
│ Action: local/format-codebase                    │
│ Project: local/pkg-billing                       │
│ Automation: full-auto                            │
│ Attempt: 1                                       │
╰──────────────────────────────────────────────────╯

✓ OK Plan created — full-auto: strategize → execute → apply will proceed automatically

# ... (common, gateway, inventory, notifications, orders, payments,
#      reporting, search, shipping, users, webhooks, workers, analytics)
# 15 plans launched — all running full-auto in background.


# Wait for all plans to finish, then check results

$ agents plan list --state applied

╭─ Plans ──────────────────────────────────────────────────────────────────────────────────────────────╮
│ ID        Phase    State     Action                 Project                Elapsed                   │
│ ────────  ───────  ────────  ─────────────────────  ─────────────────────  ─────────                 │
│ 01HXR7D1  apply    applied   local/format-codebase  local/pkg-auth         00:02:14                  │
│ 01HXR7D2  apply    applied   local/format-codebase  local/pkg-billing      00:02:31                  │
│ 01HXR7D3  apply    applied   local/format-codebase  local/pkg-common       00:01:47                  │
│ 01HXR7D4  apply    applied   local/format-codebase  local/pkg-gateway      00:02:08                  │
│ 01HXR7D5  apply    applied   local/format-codebase  local/pkg-inventory    00:01:55                  │
│ 01HXR7D6  apply    applied   local/format-codebase  local/pkg-notifications 00:02:42                 │
│ 01HXR7D7  apply    applied   local/format-codebase  local/pkg-orders       00:02:19                  │
│ 01HXR7D8  apply    applied   local/format-codebase  local/pkg-payments     00:01:58                  │
│ 01HXR7D9  apply    applied   local/format-codebase  local/pkg-reporting    00:02:36                  │
│ 01HXR7DA  apply    applied   local/format-codebase  local/pkg-search       00:01:41                  │
│ 01HXR7DB  apply    applied   local/format-codebase  local/pkg-shipping     00:02:22                  │
│ 01HXR7DC  apply    applied   local/format-codebase  local/pkg-users        00:01:49                  │
│ 01HXR7DD  apply    applied   local/format-codebase  local/pkg-webhooks     00:02:05                  │
│ 01HXR7DE  apply    applied   local/format-codebase  local/pkg-analytics    00:02:11                  │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Filters ───────────────────╮
│ Phase: (any)                │
│ State: applied              │
│ Project: (any)              │
│ Action: (any)               │
╰─────────────────────────────╯

╭─ Summary ─────────────╮
│ Total: 14             │
│ Processing: 0         │
│ Completed: 14         │
│ Errored: 0            │
╰───────────────────────╯

✓ OK 14 plans listed

$ agents plan list --state failed

╭─ Plans ──────────────────────────────────────────────────────────────────────────────────────────────╮
│ ID        Phase    State    Action                 Project              Elapsed                      │
│ ────────  ───────  ───────  ─────────────────────  ───────────────────  ─────────                    │
│ 01HXR7DF  execute  errored  local/format-codebase  local/pkg-workers    00:03:07                     │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Filters ───────────────────╮
│ Phase: (any)                │
│ State: failed               │
│ Project: (any)              │
│ Action: (any)               │
╰─────────────────────────────╯

╭─ Summary ─────────────╮
│ Total: 1              │
│ Processing: 0         │
│ Completed: 0          │
│ Errored: 1            │
╰───────────────────────╯

✓ OK 1 plan listed
--- ### Example 11: Complex Graph Actor for Multi-Stage Code Review **Scenario**: A team builds a custom multi-stage code review actor that performs security analysis, performance analysis, and style checking in a graph topology — with each stage running a different specialized sub-actor. **Complexity**: Expert. Custom actor graph, multiple sub-actors, advanced actor configuration. #### Step 1: Define Specialized Sub-Actors Create `actors/review-pipeline.yaml`: 

name: local/review-pipeline
cleveragents:
  version: "3.0"
  template_engine: JINJA2
  default_actor: orchestrator

global_context:
  review_standards: "Google Python Style Guide"
  severity_levels: "critical, high, medium, low, info"

actors:
  orchestrator:
    type: llm
    config:
      actor: anthropic/claude-3.5-sonnet
      temperature: 0.1
      system_prompt: |
        You are a code review orchestrator. You coordinate specialized reviewers
        and synthesize their findings into a unified review report.
        Standards: {{ context.review_standards }}
        Severity levels: {{ context.severity_levels }}
      memory_enabled: true

  security_reviewer:
    type: llm
    config:
      actor: anthropic/claude-3.5-sonnet
      temperature: 0.0
      system_prompt: |
        You are a security-focused code reviewer. Analyze code for:
        - Injection vulnerabilities (SQL, command, XSS)
        - Authentication and authorization flaws
        - Sensitive data exposure
        - Insecure cryptographic practices
        - Dependency vulnerabilities
        Report findings with severity levels: {{ context.severity_levels }}

  performance_reviewer:
    type: llm
    config:
      actor: anthropic/claude-3.5-sonnet
      temperature: 0.0
      system_prompt: |
        You are a performance-focused code reviewer. Analyze code for:
        - N+1 query patterns
        - Unbounded loops or recursion
        - Memory leaks and excessive allocation
        - Missing caching opportunities
        - Blocking operations in async contexts
        Report findings with severity levels: {{ context.severity_levels }}

  style_reviewer:
    type: llm
    config:
      actor: anthropic/claude-3.5-sonnet
      temperature: 0.0
      system_prompt: |
        You are a code style and maintainability reviewer.
        Standards: {{ context.review_standards }}
        Analyze code for:
        - Naming conventions
        - Function/class design
        - Documentation completeness
        - Test coverage patterns
        - Code duplication

routes:
  review_graph:
    type: graph
    entry_point: dispatch
    checkpointing: true
    nodes:
      dispatch:
        type: agent
        agent: orchestrator
      security:
        type: agent
        agent: security_reviewer
      performance:
        type: agent
        agent: performance_reviewer
      style:
        type: agent
        agent: style_reviewer
      synthesize:
        type: agent
        agent: orchestrator
    edges:
      - from: dispatch
        to: security
      - from: dispatch
        to: performance
      - from: dispatch
        to: style
      - from: security
        to: synthesize
      - from: performance
        to: synthesize
      - from: style
        to: synthesize
    parallel_execution: true


$ agents actor add --config ./actors/review-pipeline.yaml \
    --skill local/code-analysis \
    --skill local/file-ops

╭─ Actor Added ──────────────────────────────────╮
│ Name: local/review-pipeline                    │
│ Provider: anthropic                            │
│ Model: claude-3.5-sonnet                       │
│ Default: yes                                   │
│ Unsafe: no                                     │
│ Type: graph                                    │
╰────────────────────────────────────────────────╯

╭─ Config ─────────────────────────────────────────────╮
│ Path: ./actors/review-pipeline.yaml                  │
│ Hash: 4f7a1e3                                        │
│ Options: 6                                           │
│ Nodes: 5                                             │
│ Edges: 6                                             │
╰──────────────────────────────────────────────────────╯

╭─ Graph ────────────────────────────────────────────────────╮
│ Route: review_graph                                        │
│ Entry Point: dispatch                                      │
│ Checkpointing: yes                                         │
│ Parallel Execution: yes                                    │
│                                                            │
│ Node         Type   Agent                                  │
│ ───────────  ─────  ──────────────────────────────         │
│ dispatch     agent  orchestrator                           │
│ security     agent  security_reviewer                      │
│ performance  agent  performance_reviewer                   │
│ style        agent  style_reviewer                         │
│ synthesize   agent  orchestrator                           │
│                                                            │
│ From         To                                            │
│ ───────────  ───────────                                   │
│ dispatch     security                                      │
│ dispatch     performance                                   │
│ dispatch     style                                         │
│ security     synthesize                                    │
│ performance  synthesize                                    │
│ style        synthesize                                    │
╰────────────────────────────────────────────────────────────╯

╭─ Capabilities ──────────────────────╮
│ - multi-stage code review           │
│ - security analysis                 │
│ - performance analysis              │
│ - style and maintainability checks  │
│ - unified report synthesis          │
╰─────────────────────────────────────╯

╭─ Skills ──────────────────────────────────────────╮
│ Skill                Status                       │
│ ───────────────────  ────────────────────────     │
│ local/code-analysis  attached                     │
│ local/file-ops       attached                     │
╰───────────────────────────────────────────────────╯

✓ OK Actor added
#### Step 2: Create the Review Action Using the Graph Actor Create `actions/deep-review.yaml`: 

name: local/deep-review
description: "Multi-stage deep code review with specialized reviewers"
definition_of_done: |
  - Security analysis complete with all findings classified by severity
  - Performance analysis complete with all findings classified by severity
  - Style analysis complete with all findings classified by severity
  - Unified review report generated with prioritized action items
  - Critical and high-severity issues have suggested fixes
strategy_actor: local/review-pipeline
execution_actor: local/review-pipeline
read_only: true
reusable: true
state: available
args:
  - name: target_paths
    type: string
    required: true
    description: "Comma-separated file or directory paths to review"
  - name: review_depth
    type: string
    required: false
    default: "standard"
    description: "Review depth: quick, standard, thorough"


$ agents action create --config ./actions/deep-review.yaml

╭─ Action Created ─────────────────────────────────────────────╮
│ Name: local/deep-review                                      │
│ State: available                                             │
│ Strategy Actor: local/review-pipeline                        │
│ Execution Actor: local/review-pipeline                       │
│ Reusable: yes                                                │
│ Read Only: yes                                               │
│ Created: 2026-02-11 16:30                                    │
╰──────────────────────────────────────────────────────────────╯

╭─ Definition of Done ──────────────────────────────────────────────────────╮
│ - Security analysis complete with all findings classified by severity     │
│ - Performance analysis complete with all findings classified by severity  │
│ - Style analysis complete with all findings classified by severity        │
│ - Unified review report generated with prioritized action items           │
│ - Critical and high-severity issues have suggested fixes                  │
╰───────────────────────────────────────────────────────────────────────────╯

╭─ Arguments ───────────────────────────────────────────────────────────────────────╮
│ Name          Type    Required  Description                                       │
│ ────────────  ──────  ────────  ──────────────────────────────────────────────    │
│ target_paths  string  yes       Comma-separated file or directory paths to review │
│ review_depth  string  no        Review depth: quick, standard, thorough           │
╰───────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: supervised                   │
│ Source: default                       │
╰───────────────────────────────────────╯

╭─ Usage ────────────────────────────────────────────────────────────────────────╮
│ agents plan use local/deep-review local/<project>                              │
│   --arg target_paths="src/auth/,src/routes/"                                   │
│   --arg review_depth="thorough"  (optional, default: "standard")               │
╰────────────────────────────────────────────────────────────────────────────────╯

✓ OK Action created


$ agents plan use \
    --automation-profile trusted \
    --arg target_paths="src/auth/,src/routes/" \
    --arg review_depth="thorough" \
    local/deep-review local/api-service

╭─ Plan Created ───────────────────────────────────────╮
│ Plan: 01HXR8D2E3F4G5H6J7K8L9M0N1                     │
│ Phase: strategize                                    │
│ State: processing                                    │
│ Action: local/deep-review                            │
│ Project: local/api-service                           │
│ Automation: trusted                                  │
│ Attempt: 1                                           │
╰──────────────────────────────────────────────────────╯

╭─ Inputs ───────────────────────────────────────╮
│ - target_paths="src/auth/,src/routes/"         │
│ - review_depth="thorough"                      │
│ - automation_profile=trusted                   │
╰────────────────────────────────────────────────╯

╭─ Actors ────────────────────────────────────────╮
│ Strategy: local/review-pipeline                 │
│ Execution: local/review-pipeline                │
│ Estimation: (none)                              │
│ Actor Type: graph (5 nodes, 6 edges)            │
╰─────────────────────────────────────────────────╯

╭─ Automation ───────────────────────────╮
│ Profile: trusted                       │
│ Source: plan override                  │
│ Read-Only: yes                         │
╰────────────────────────────────────────╯

╭─ Context ──────────────────────────╮
│ Resources: 1 (git-checkout)        │
│ Indexed Files: 312                 │
│ View: strategize                   │
│ Hot Token Budget: 24,000           │
╰────────────────────────────────────╯

╭─ Next Steps ─────────────────────────────────────────────────────────╮
│ Trusted profile — strategize and execute will proceed automatically. │
│ - agents plan status 01HXR8D2E3F4G5H6J7K8L9M0N1                      │
│ - agents plan tree 01HXR8D2E3F4G5H6J7K8L9M0N1                        │
╰──────────────────────────────────────────────────────────────────────╯

✓ OK Plan created
The graph actor executes `review_graph` with parallel fan-out. The `dispatch` node (orchestrator) analyzes the target paths and prepares review context, then three edges fire concurrently: `security`, `performance`, and `style` nodes each run their specialized sub-actor in parallel. Once all three complete, their outputs converge at the `synthesize` node, where the orchestrator merges findings into a single prioritized report. Because `read_only: true`, no file modifications are produced — only the review report. --- ### Example 12: Large-Scale Feature Implementation with Hierarchical Decomposition **Scenario**: A startup is building a new notification system that spans the backend API, a message queue, a worker service, and a frontend dashboard. The feature requires changes across 4 projects and should decompose into manageable child plans. **Complexity**: Expert. Multi-project, hierarchical child plans, deep decision tree, invariant reconciliation, full plan lifecycle. #### Step 1: Set Up All Projects 
# Register the API repo resource (full output shown)

$ agents resource add git-checkout local/api-repo --path /repos/api --branch main

╭─ Resource ──────────────────────────────────────╮
│ Name: local/api-repo                            │
│ ID: 01HXRA1A2B3C4D5E6F7G8H9J0K                  │
│ Type: git-checkout                              │
│ Physical/Virtual: physical                      │
│ Path: /repos/api                                │
│ Branch: main                                    │
│ Created: 2026-02-11 14:00                       │
╰─────────────────────────────────────────────────╯

╭─ Auto-discovered Children ─────────────────────────────────────────╮
│ ID               Type            Status                            │
│ ───────────────  ──────────────  ─────────────────                 │
│ 01HXRA1A2B3C…   git             created                            │
│ 01HXRA1A2B3D…   git-remote      created                            │
│ 01HXRA1A2B3E…   git-branch      created                            │
│   + 48 git-commit resources                                        │
│   + 312 git-tree-entry resources                                   │
│   + 6 fs-directory + 42 fs-file                                    │
╰────────────────────────────────────────────────────────────────────╯

╭─ Capabilities ─────────────────╮
│ Readable: yes                  │
│ Writable: yes                  │
│ Sandboxable: yes               │
│ Checkpointable: yes            │
│ Sandbox Strategy: git_worktree │
╰────────────────────────────────╯

✓ OK Resource registered (412 child resources discovered)

# Register the remaining 3 resources (condensed output)

$ agents resource add git-checkout local/worker-repo --path /repos/worker --branch main
✓ OK Resource registered — Name: local/worker-repo (278 children)

$ agents resource add git-checkout local/frontend-repo --path /repos/frontend --branch main
✓ OK Resource registered — Name: local/frontend-repo (524 children)

$ agents resource add git-checkout local/protos-repo --path /repos/protos --branch main
✓ OK Resource registered — Name: local/protos-repo (96 children)

# Create the Backend API project (full output shown)

$ agents project create -d "Backend API" \
    --resource local/api-repo \
    --resource local/protos-repo \
    --invariant "All new endpoints must have OpenAPI docs" \
    --invariant "All database changes require migration scripts" \
    local/api

╭─ Project Created ─────────────────────────╮
│ Name: local/api                           │
│ Description: Backend API                  │
│ Type: local                               │
│ Created: 2026-02-11 14:01                 │
╰───────────────────────────────────────────╯

╭─ Linked Resources ───────────────────────────────────────╮
│ Resource           Type          Read-Only               │
│ ─────────────────  ──────────────  ─────────             │
│ local/api-repo     git-checkout    no                    │
│ local/protos-repo  git-checkout    no                    │
╰──────────────────────────────────────────────────────────╯

╭─ Invariants ─────────────────────────────────────────────╮
│ 1. All new endpoints must have OpenAPI docs              │
│ 2. All database changes require migration scripts        │
╰──────────────────────────────────────────────────────────╯

╭─ Defaults ──────────────────────────────╮
│ Sandbox: git_worktree                   │
│ Validations: 0                          │
│ Context Filters: none                   │
│ Automation Profile: (inherits global)   │
╰─────────────────────────────────────────╯

✓ OK Project created

# Create the remaining 3 projects (condensed output)

$ agents project create -d "Background worker service" \
    --resource local/worker-repo \
    --resource local/protos-repo \
    --invariant "Workers must be idempotent" \
    --invariant "All queue consumers must implement dead-letter handling" \
    local/worker
✓ OK Project created — Name: local/worker

$ agents project create -d "Frontend dashboard" \
    --resource local/frontend-repo \
    --invariant "All components must have Storybook stories" \
    --invariant "Accessibility: WCAG 2.1 AA compliance required" \
    local/frontend
✓ OK Project created — Name: local/frontend

$ agents project create -d "Shared protobuf definitions" \
    --resource local/protos-repo \
    --invariant "Proto changes must be backward-compatible (no field renumbering)" \
    local/protos
✓ OK Project created — Name: local/protos

# Register validations — first one with full output

$ agents validation add --config validations/api-tests.yaml --required local/api-tests

╭─ Validation Registered ─────────────────────────────╮
│ Name: local/api-tests                               │
│ Command: pytest tests/ && mypy src/                 │
│ Mode: required                                      │
│ Timeout: 300s                                       │
╰─────────────────────────────────────────────────────╯

✓ OK Validation registered

$ agents validation add --config validations/worker-tests.yaml --required local/worker-tests
✓ OK Validation registered — Name: local/worker-tests

$ agents validation add --config validations/frontend-tests.yaml --required local/frontend-tests
✓ OK Validation registered — Name: local/frontend-tests

$ agents validation add --config validations/proto-lint.yaml --required local/proto-lint
✓ OK Validation registered — Name: local/proto-lint

# Attach validations to their respective projects

$ agents validation attach --project local/api local/api-tests
✓ OK Validation attached to project local/api

$ agents validation attach --project local/worker local/worker-tests
✓ OK Validation attached to project local/worker

$ agents validation attach --project local/frontend local/frontend-tests
✓ OK Validation attached to project local/frontend

$ agents validation attach --project local/protos local/proto-lint
✓ OK Validation attached to project local/protos

# Global invariant for this effort

$ agents invariant add --global \
    "All inter-service communication must use the shared proto definitions"

╭─ Invariant Added ──────────────────────────────────────────────────────────────╮
│ Invariant: All inter-service communication must use the shared proto defs.     │
│ Scope: global                                                                  │
│ ID: inv_01HXRI1A                                                               │
╰────────────────────────────────────────────────────────────────────────────────╯

✓ OK Invariant added
#### Step 2: Create the Feature Action Create `actions/build-notification-system.yaml`: 

name: local/build-notification-system
description: "Build a complete notification system spanning multiple services"
long_description: |
  Implement a full notification system with:
  - Backend API: notification preferences, send endpoints, delivery tracking
  - Message Queue: notification event schemas, routing rules
  - Worker: email/SMS/push delivery workers with retry logic
  - Frontend: notification center UI, preference settings, real-time updates

  The system must be designed for reliability (at-least-once delivery),
  scalability (async processing via queue), and user control (per-channel
  preferences with quiet hours).
definition_of_done: |
  - Proto definitions for notification events are complete and compatible
  - API endpoints: CRUD for preferences, send notification, list history
  - Worker processes: email, SMS, push delivery with retry and dead-letter
  - Frontend: notification center, preference settings, real-time badge
  - Integration tests verify end-to-end notification flow
  - All per-project validations pass
  - API docs updated, Storybook stories added
strategy_actor: local/refactoring-strategist
execution_actor: anthropic/claude-3.5-sonnet
estimation_actor: anthropic/claude-3.5-sonnet
invariant_actor: local/invariant-resolver
automation_profile: cautious
reusable: false
state: available
args:
  - name: notification_channels
    type: string
    required: true
    description: "Comma-separated: email, sms, push, in-app"
  - name: priority_levels
    type: string
    required: false
    default: "critical,high,normal,low"
  - name: max_retry_attempts
    type: integer
    required: false
    default: 5
invariants:
  - "Proto definitions must be implemented and reviewed before any service code"
  - "Each service must be deployable independently after its changes"
  - "Frontend must gracefully degrade if the notification API is unavailable"
  - "All notification delivery must be async — API endpoints return immediately"

$ agents action create --config ./actions/build-notification-system.yaml

╭─ Action Created ──────────────────────────────────────────────────╮
│ Name: local/build-notification-system                             │
│ ID: 01HXRB1A2B3C4D5E6F7G8H9J0                                     │
│ State: available                                                  │
│ Strategy Actor: local/refactoring-strategist                      │
│ Execution Actor: anthropic/claude-3.5-sonnet                      │
│ Estimation Actor: anthropic/claude-3.5-sonnet                     │
│ Invariant Actor: local/invariant-resolver                         │
│ Reusable: no                                                      │
│ Read Only: no                                                     │
│ Created: 2026-02-11 14:02                                         │
╰───────────────────────────────────────────────────────────────────╯

╭─ Definition of Done ───────────────────────────────────────────────────╮
│ - Proto definitions for notification events are complete/compatible    │
│ - API endpoints: CRUD for preferences, send notification, list hist.   │
│ - Worker: email, SMS, push delivery with retry and dead-letter         │
│ - Frontend: notification center, preference settings, real-time badge  │
│ - Integration tests verify end-to-end notification flow                │
│ - All per-project validations pass                                     │
│ - API docs updated, Storybook stories added                            │
╰────────────────────────────────────────────────────────────────────────╯

╭─ Arguments ──────────────────────────────────────────────────────────────────────────╮
│ Name                    Type      Required  Description                              │
│ ──────────────────────  ────────  ────────  ──────────────────────────────────       │
│ notification_channels   string    yes       Comma-separated: email, sms, push        │
│ priority_levels         string    no        (default: critical,high,normal,low)      │
│ max_retry_attempts      integer   no        (default: 5)                             │
╰──────────────────────────────────────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────╮
│ Profile: cautious                     │
│ Source: action config                 │
╰───────────────────────────────────────╯

╭─ Action Invariants ───────────────────────────────────────────────────────────────────╮
│ 1. Proto definitions must be implemented and reviewed before any service code         │
│ 2. Each service must be deployable independently after its changes                    │
│ 3. Frontend must gracefully degrade if the notification API is unavailable            │
│ 4. All notification delivery must be async — API endpoints return immediately         │
╰───────────────────────────────────────────────────────────────────────────────────────╯

╭─ Usage ────────────────────────────────────────────────────────────────────────────╮
│ agents plan use local/build-notification-system local/protos                       │
│   --arg notification_channels="email,push,in-app"                                  │
╰────────────────────────────────────────────────────────────────────────────────────╯

✓ OK Action created
#### Step 3: Initiate the Plan 
$ agents plan use \
    --arg notification_channels="email,push,in-app" \
    --arg priority_levels="critical,high,normal,low" \
    --arg max_retry_attempts=5 \
    local/build-notification-system \
    local/protos local/api local/worker local/frontend

╭─ Plan Created ────────────────────────────────────────────────╮
│ Plan: 01HXRF1A2B3C4D5E6F7G8H9J0                               │
│ Action: local/build-notification-system                       │
│ Projects: local/protos, local/api,                            │
│           local/worker, local/frontend                        │
│ Automation: cautious                                          │
│ Attempt: 1                                                    │
╰───────────────────────────────────────────────────────────────╯

╭─ Inputs ───────────────────────────────────────────────────────────╮
│ - notification_channels="email,push,in-app"                        │
│ - priority_levels="critical,high,normal,low"                       │
│ - max_retry_attempts=5                                             │
│ - automation_profile=cautious                                      │
╰────────────────────────────────────────────────────────────────────╯

╭─ Actors ────────────────────────────────────────────╮
│ Strategy: local/refactoring-strategist              │
│ Execution: anthropic/claude-3.5-sonnet              │
│ Estimation: anthropic/claude-3.5-sonnet             │
│ Invariant: local/invariant-resolver                 │
╰─────────────────────────────────────────────────────╯

╭─ Automation ──────────────────────────────╮
│ Profile: cautious                         │
│ Source: action config                     │
│ Read-Only: no                             │
╰───────────────────────────────────────────╯

╭─ Context ──────────────────────────╮
│ Resources: 4 (git-checkout)        │
│ Indexed Files: 1,310               │
│ View: strategize                   │
│ Hot Token Budget: 32,000           │
╰────────────────────────────────────╯

╭─ Next Steps ──────────────────────────────────────────────╮
│ - agents plan tree 01HXRF1A2B3C4D5E6F7G8H9J0              │
│ - agents plan status 01HXRF1A2B3C4D5E6F7G8H9J0            │
│ - agents plan execute 01HXRF1A2B3C4D5E6F7G8H9J0           │
╰───────────────────────────────────────────────────────────╯

✓ OK Plan created
The plan (`01HXRF1A2B3C4D5E6F7G8H9J0`) enters Strategize. The strategy actor: 1. Reconciles invariants from all four projects plus global plus action-level 2. Decomposes the work into ordered child plans: - **Phase 1**: Proto definitions (local/protos) - **Phase 2** (parallel): API endpoints (local/api) + Worker skeleton (local/worker) - **Phase 3** (parallel): Worker delivery logic (local/worker) + Frontend notification center (local/frontend) - **Phase 4**: Integration wiring and end-to-end tests Because the `cautious` profile uses confidence thresholds, the system pauses on complex architectural decisions (e.g., "Should notifications use a fan-out or point-to-point queue topology?") but proceeds automatically on routine decisions. #### Step 4: Monitor and Guide the Hierarchical Execution 
# View the full plan tree with child plans

$ agents plan tree 01HXRF1A2B3C4D5E6F7G8H9J0

╭─ Decision Tree ─────────────────────────────────────────────────────────────────────────────────────────╮
│ Plan: 01HXRF1A2B3C4D5E6F7G8H9J0                                                                         │
│ ├─ [prompt_definition] "Build notification system across 4 projects"                                    │
│ ├─ [invariant_enforced] "All inter-service communication must use shared proto defs"                    │
│ ├─ [invariant_enforced] "Proto definitions must be implemented before any service code"                 │
│ ├─ [invariant_enforced] "Each service must be deployable independently after its changes"               │
│ ├─ [invariant_enforced] "Frontend must gracefully degrade if notification API unavailable"              │
│ ├─ [invariant_enforced] "All notification delivery must be async"                                       │
│ ├─ [strategy_choice] "Phase 1: proto definitions first (blocking)" (conf: 0.95)                         │
│ ├─ [strategy_choice] "Phase 2: API + worker skeleton in parallel" (conf: 0.88)                          │
│ ├─ [strategy_choice] "Phase 3: worker delivery + frontend UI in parallel" (conf: 0.84)                  │
│ ├─ [strategy_choice] "Phase 4: integration wiring and e2e tests" (conf: 0.90)                           │
│ ├─ [strategy_choice] "Queue topology: fan-out vs point-to-point?" (conf: 0.55 — PAUSED)                 │
│ ├─ [child_plan] 01HXRC1A2B3C4D5E6F7G8H9J0 (Phase 1: proto defs) [execute/complete]                      │
│ ├─ [child_plan] 01HXRC2B3C4D5E6F7G8H9J0K1 (Phase 2a: API endpoints) [execute/processing]                │
│ ├─ [child_plan] 01HXRC3C4D5E6F7G8H9J0K1L2 (Phase 2b: worker skeleton) [execute/processing]              │
│ ├─ [child_plan] 01HXRC4D5E6F7G8H9J0K1L2M3 (Phase 3a: worker delivery) [strategize/pending]              │
│ ├─ [child_plan] 01HXRC5E6F7G8H9J0K1L2M3N4 (Phase 3b: frontend UI) [strategize/pending]                  │
│ └─ [child_plan] 01HXRC6F7G8H9J0K1L2M3N4P5 (Phase 4: integration) [strategize/pending]                   │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Tree Summary ──────────────────╮
│ Nodes: 17                       │
│ Depth: 2                        │
│ Child Plans: 6 (1 done, 2 exec) │
│ Invariants: 5                   │
│ Superseded: 0 (hidden)          │
╰─────────────────────────────────╯

╭─ Decision IDs (for correction) ──────────────────────────╮
│ Root: 01HXRD1A2B3C4D5E6F7G8H9J                           │
│ Invariant 1: 01HXRD1B3C4D5E6F7G8H9J0                     │
│ Invariant 2: 01HXRD1C4D5E6F7G8H9J0K1                     │
│ Invariant 3: 01HXRD1D5E6F7G8H9J0K1L2                     │
│ Invariant 4: 01HXRD1E6F7G8H9J0K1L2M3                     │
│ Invariant 5: 01HXRD1F7G8H9J0K1L2M3N4                     │
│ Strategy 1: 01HXRD2A3B4C5D6E7F8G9H0                      │
│ Strategy 2: 01HXRD2B4C5D6E7F8G9H0J1                      │
│ Strategy 3: 01HXRD2C5D6E7F8G9H0J1K2                      │
│ Strategy 4: 01HXRD2D6E7F8G9H0J1K2L3                      │
│ Paused: 01HXRD2E7F8G9H0J1K2L3M4                          │
╰──────────────────────────────────────────────────────────╯

✓ OK Decision tree rendered

# The system paused at a decision about queue topology (confidence 0.55 < threshold 0.7)

$ agents plan explain 01HXRD2E7F8G9H0J1K2L3M4

╭─ Decision ──────────────────────────────────────────────────╮
│ ID: 01HXRD2E7F8G9H0J1K2L3M4                                 │
│ Type: strategy_choice                                       │
│ Question: Queue topology for notification delivery          │
│ Chosen: (none — paused for user input)                      │
│ Confidence: 0.55                                            │
│ Plan: 01HXRF1A2B3C4D5E6F7G8H9J0                             │
│ Sequence: 5 of 5 strategy choices                           │
│ Created: 2026-02-11 14:04                                   │
╰─────────────────────────────────────────────────────────────╯

╭─ Alternatives Considered ──────────────────────────────────────────────────────╮
│ 1. Fan-out exchange: one exchange per event type, separate queues per channel  │
│ 2. Point-to-point: single queue, worker routes by notification type            │
│ 3. Topic-based: single exchange with routing keys for channel + priority       │
╰────────────────────────────────────────────────────────────────────────────────╯

╭─ Impact ─────────────────────────╮
│ Downstream Decisions: 4          │
│ Downstream Child Plans: 3        │
│ Artifacts Produced: 0 (pending)  │
│ Correction Impact: high          │
╰──────────────────────────────────╯

╭─ Rationale ──────────────────────────────────────────────────────────╮
│ The confidence is low because both fan-out and topic-based patterns  │
│ are viable. Fan-out gives independent scaling per channel but adds   │
│ more exchanges. Topic-based is simpler but couples routing logic.    │
│ The existing codebase uses RabbitMQ but has no precedent for this    │
│ pattern — no strong signal either way.                               │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Correction ──────────────────────────────────────────────────╮
│ agents plan correct 01HXRD2E7F8G9H0J1K2L3M4                   │
│   --mode revert --guidance "Use fan-out exchange pattern..."  │
╰───────────────────────────────────────────────────────────────╯

✓ OK Decision explained

# Provide guidance to resolve the paused decision

$ agents plan prompt 01HXRF1A2B3C4D5E6F7G8H9J0 \
    "Use a fan-out exchange pattern: one exchange per notification event type, \
     with separate queues per delivery channel. This matches our existing \
     RabbitMQ setup in the order service."

╭─ Guidance Added ────────────────────────────────────────────────────────╮
│ Plan: 01HXRF1A2B3C4D5E6F7G8H9J0                                         │
│ Guidance: Use a fan-out exchange pattern: one exchange per              │
│           notification event type, with separate queues per delivery    │
│           channel. This matches our existing RabbitMQ setup.            │
│ Scope: next execution step                                              │
│ Phase: strategize                                                       │
│ State: awaiting_input → processing                                      │
╰─────────────────────────────────────────────────────────────────────────╯

╭─ Decision Created ────────────────────────╮
│ Type: user_intervention                   │
│ ID: 01HXRD3A2B3C4D5E6F7G8H9J              │
│ Parent: 01HXRD2E7F8G9H0J1K2L3M4           │
╰───────────────────────────────────────────╯

╭─ Queue ────╮
│ Pending: 1 │
│ Applied: 0 │
╰────────────╯

✓ OK Guidance queued
#### Step 5: Handle a Failure in One Child Plan The worker delivery child plan fails validation because the SMS provider SDK is not installed. Rather than failing the entire tree: 
# Check which child plan failed

$ agents plan status 01HXRC4D5E6F7G8H9J0K1L2M3

╭─ Plan Status ──────────────────────────────────────────────╮
│ Plan: 01HXRC4D5E6F7G8H9J0K1L2M3                            │
│ Phase: execute                                             │
│ State: errored                                             │
│ Action: local/build-notification-system (child plan)       │
│ Project: local/worker                                      │
│ Automation: cautious                                       │
│ Attempt: 1                                                 │
│ Parent: 01HXRF1A2B3C4D5E6F7G8H9J0                          │
╰────────────────────────────────────────────────────────────╯

╭─ Progress ───────────╮
│ ✓ Strategize         │
│ ✗ Execute            │
│ ○ Apply (skipped)    │
╰──────────────────────╯

╭─ Error Detail ──────────────────────────────────────────────────────────╮
│ Error: Validation failed: ModuleNotFoundError: No module named          │
│         'twilio' — SMS provider SDK not installed                       │
│ Tool: execute_command (pip install check)                               │
│ Step: 3 of 8                                                            │
│ Checkpoint: cp_01HXRC4D (sandbox state preserved)                       │
│ Recoverable: yes — use "agents plan prompt" to provide guidance         │
╰─────────────────────────────────────────────────────────────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 14,280  │
│ Cost So Far: $0.048  │
╰──────────────────────╯

✗ ERROR Plan errored — use `agents plan prompt` to resume or `agents plan cancel` to abort

# Correct the strategy — tell it to skip SMS for now

$ agents plan correct 01HXRD4A2B3C4D5E6F7G8H9J \
    --mode append \
    --guidance "Skip SMS delivery for the initial implementation. \
                Add a placeholder worker that logs a warning. \
                SMS support will be added in a follow-up action."

╭─ Correction ─────────────────────────────────────────────────╮
│ Mode: append                                                 │
│ Impact: adds to existing subtree, no rollback                │
│ New Decision: 01HXRD5A2B3C4D5E6F7G8H9J                       │
│ Appended After: 01HXRD4A2B3C4D5E6F7G8H9J                     │
│ Attempt: 2                                                   │
╰──────────────────────────────────────────────────────────────╯

╭─ Append Detail ────────────────────────────────────────────────────╮
│ Original decision preserved: yes                                   │
│ Existing artifacts kept: yes                                       │
│ Additional work: re-execute with SMS placeholder                   │
│ The worker delivery plan will be re-executed. Email and push       │
│ workers are kept; SMS worker replaced with a logging stub.         │
│ Other child plans (API, frontend, integration) are unaffected.     │
╰────────────────────────────────────────────────────────────────────╯

╭─ Queued ──────────────╮
│ Re-execute: 1 child   │
│ ETA: 3m               │
╰───────────────────────╯

✓ OK Append correction queued
#### Step 6: Apply in Phases 
# Apply proto definitions first (other plans depend on this)

$ agents plan apply --yes 01HXRC1A2B3C4D5E6F7G8H9J0

╭─ Apply Summary ──────────────────────────────────────────╮
│ Plan: 01HXRC1A2B3C4D5E6F7G8H9J0                          │
│ Artifacts: 3 files updated                               │
│ Changes: 84 insertions, 0 deletions                      │
│ Project: local/protos                                    │
│ Applied At: 2026-02-11 14:18                             │
╰──────────────────────────────────────────────────────────╯

╭─ Validation ──────────────────────────────────────────╮
│ buf lint: passed                                      │
│ buf breaking: passed (no breaking changes)            │
│ Duration: 2.1s                                        │
╰───────────────────────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ─────────────────────────╮
│ Phase: apply                             │
│ State: applied                           │
│ Total Duration: 00:02:41                 │
│ Total Cost: $0.024                       │
│ Decisions Made: 4                        │
│ Child Plans: 0                           │
╰──────────────────────────────────────────╯

✓ OK Changes applied

# Apply API and worker in parallel

$ agents plan apply --yes 01HXRC2B3C4D5E6F7G8H9J0K1
✓ OK Changes applied — Plan: 01HXRC2B...J0K1 Project: local/api (8 files, +246 -12)

$ agents plan apply --yes 01HXRC3C4D5E6F7G8H9J0K1L2
✓ OK Changes applied — Plan: 01HXRC3C...K1L2 Project: local/worker (5 files, +178 -4)

# Apply worker delivery and frontend

$ agents plan apply --yes 01HXRC4D5E6F7G8H9J0K1L2M3
✓ OK Changes applied — Plan: 01HXRC4D...L2M3 Project: local/worker (6 files, +312 -18)

$ agents plan apply --yes 01HXRC5E6F7G8H9J0K1L2M3N4
✓ OK Changes applied — Plan: 01HXRC5E...M3N4 Project: local/frontend (12 files, +487 -22)

# Apply integration tests

$ agents plan apply --yes 01HXRC6F7G8H9J0K1L2M3N4P5
✓ OK Changes applied — Plan: 01HXRC6F...N4P5 Projects: local/api, local/worker (4 files, +156 -0)

# Apply the parent plan (finalizes everything)

$ agents plan apply --yes 01HXRF1A2B3C4D5E6F7G8H9J0

╭─ Apply Summary ───────────────────────────────────────────╮
│ Plan: 01HXRF1A2B3C4D5E6F7G8H9J0                           │
│ Artifacts: 38 files across 4 projects                     │
│ Changes: 1,463 insertions, 56 deletions                   │
│ Projects: local/protos, local/api,                        │
│           local/worker, local/frontend                    │
│ Applied At: 2026-02-11 14:32                              │
╰───────────────────────────────────────────────────────────╯

╭─ Validation ─────────────────────────────────────────╮
│ local/protos: passed (buf lint + breaking)           │
│ local/api: passed (pytest 48/48, mypy 0 err)         │
│ local/worker: passed (pytest 31/31, mypy 0)          │
│ local/frontend: passed (tests + lint)                │
│ Duration: 34.2s                                      │
╰──────────────────────────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktrees: 4 removed      │
│ Branches: merged to main  │
│ Checkpoints: archived     │
╰───────────────────────────╯

╭─ Plan Lifecycle ────────────────────────╮
│ Phase: apply                            │
│ State: applied                          │
│ Total Duration: 00:30:14                │
│ Total Cost: $0.847                      │
│ Decisions Made: 42                      │
│ Child Plans: 6 (all completed)          │
│ Corrections: 1                          │
╰─────────────────────────────────────────╯

╭─ Next Steps ──────╮
│ - Review git diff │
│ - Commit changes  │
╰───────────────────╯

✓ OK Changes applied
--- ### Example 13: Custom Automation Profile with Semantic Escalation **Scenario**: A team wants fine-grained automation control. They trust the system with routine planning but want human oversight on any decision involving database schema changes or security-sensitive code, regardless of confidence. **Complexity**: Intermediate. Custom profile, invariant-driven escalation. #### Step 1: Create a Custom Profile Create `profiles/db-cautious.yaml`: 

name: local/db-cautious
description: "Auto for most tasks, manual for database and security decisions"

decompose_task: 0.0
create_tool: 0.3
select_tool: 1.0
edit_code: 0.4
execute_command: 0.6
create_file: 0.5
delete_content: 0.8
access_network: 0.9
install_dependency: 0.3
modify_config: 0.0
approve_plan: 0.0

require_sandbox: true
require_checkpoints: true
allow_unsafe_tools: false


$ agents automation-profile add --config ./profiles/db-cautious.yaml

╭─ Profile Registered ──────────────────────────────────────────────────────╮
│ Name: local/db-cautious                                                   │
│ Description: Auto for most tasks, manual for database and security        │
│              decisions                                                    │
│ Created: 2026-02-11 09:00                                                 │
╰───────────────────────────────────────────────────────────────────────────╯

╭─ Confidence Thresholds ────────────────╮
│ decompose_task: 0.0                   │
│ create_tool: 0.3                      │
│ select_tool: 1.0                        │
│ edit_code: 0.4         │
│ execute_command: 0.6            │
│ create_file: 0.5               │
│ delete_content: 0.8            │
│ install_dependency: 0.3                  │
│ modify_config: 0.0              │
│ approve_plan: 0.0           │
│ require_sandbox: true                  │
│ require_checkpoints: true              │
│ allow_unsafe_tools: false              │
╰────────────────────────────────────────╯

✓ OK Profile registered
#### Step 2: Apply to a Project with Database Resources 

$ agents config set core.automation-profile local/db-cautious --project local/api-service

╭─ Config Updated ─────────────────────────────────╮
│ Key: core.automation-profile                     │
│ Value: local/db-cautious                         │
│ Previous: review                                 │
│ Source: config                                   │
│ Scope: project (local/api-service)               │
╰──────────────────────────────────────────────────╯

╭─ Effective ────────────────────────────────────╮
│ Sessions: new sessions on local/api-service    │
│ Plans: future plans (unless overridden)        │
│ Existing: unchanged                            │
╰────────────────────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 24                            │
╰─────────────────────────────────────╯

✓ OK Config updated


# Add invariants that force escalation on sensitive operations
$ agents invariant add --project local/api-service \
    "Any change to database migration files requires explicit human approval"

╭─ Invariant Added ───────────────────────────────────────────────────────────────╮
│ Project: local/api-service                                                      │
│ Invariant: Any change to database migration files requires explicit human       │
│            approval                                                             │
│ Scope: project                                                                  │
│ ID: inv_01HXRBA1A                                                               │
╰─────────────────────────────────────────────────────────────────────────────────╯

✓ OK Invariant added

$ agents invariant add --project local/api-service \
    "Changes to authentication or authorization logic require security review"

╭─ Invariant Added ───────────────────────────────────────────────────────────────╮
│ Project: local/api-service                                                      │
│ Invariant: Changes to authentication or authorization logic require             │
│            security review                                                      │
│ Scope: project                                                                  │
│ ID: inv_01HXRBA2B                                                               │
╰─────────────────────────────────────────────────────────────────────────────────╯

✓ OK Invariant added
#### Step 3: Run a Plan and Observe Escalation 

$ agents plan use \
    --arg target_module="src/auth" \
    local/refactor-to-orm local/api-service

╭─ Plan Created ─────────────────────────────────────╮
│ Plan ID: 01HXRBG1H2I3J4K5L6M7N8O9P0                │
│ Phase: strategize (running)                        │
│ Action: local/refactor-to-orm                      │
│ Project: local/api-service                         │
│ Automation: local/db-cautious                      │
│ Attempt: 1                                         │
╰────────────────────────────────────────────────────╯

╭─ Inputs ─────────────────────╮
│ - target_module=src/auth     │
╰──────────────────────────────╯

╭─ Actors ───────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet  │
│ Execution: anthropic/claude-3.5-sonnet │
│ Invariant: local/invariant-resolver    │
╰────────────────────────────────────────╯

╭─ Plan Invariants ──────────────────────────────────────────────────────────────╮
│ Scope     Source   Invariant                                                   │
│ ────────  ───────  ──────────────────────────────────────────────────────      │
│ project   config   Any change to database migration files requires explicit    │
│                     human approval                                             │
│ project   config   Changes to authentication or authorization logic require    │
│                     security review                                            │
╰────────────────────────────────────────────────────────────────────────────────╯

╭─ Next Steps ─────────────────────────────────────────╮
│ - agents plan status 01HXRBG1H2I3J4K5L6M7N8O9P0      │
│ - agents plan tree 01HXRBG1H2I3J4K5L6M7N8O9P0        │
╰──────────────────────────────────────────────────────╯

✓ OK Plan created — strategize in progress
During execution, the system encounters a decision to create a new Alembic migration. The confidence score is 0.82 (the system is fairly confident), but the invariant "database migration files require explicit human approval" causes the Invariant Reconciliation Actor to enforce escalation regardless. The system pauses: 

# The plan pauses — check why
$ agents plan status 01HXRBG1H2I3J4K5L6M7N8O9P0

╭─ Plan Status ───────────────────────────────────────╮
│ Plan: 01HXRBG1H2I3J4K5L6M7N8O9P0                    │
│ Phase: execute                                      │
│ State: awaiting_input                               │
│ Action: local/refactor-to-orm                       │
│ Project: local/api-service                          │
│ Automation: local/db-cautious                       │
│ Attempt: 1                                          │
╰─────────────────────────────────────────────────────╯

╭─ Progress ────────────────╮
│ ✓ Strategize              │
│ ⏸ Execute (paused)        │
│ ○ Apply (waiting)         │
╰───────────────────────────╯

╭─ Escalation ───────────────────────────────────────────────────────────────╮
│ ⚠  Decision paused — invariant forced escalation                           │
│ Decision: 01HXRBD1E2F3G4H5I6J7K8L9                                         │
│ Type: implementation_choice                                                │
│ Question: Create Alembic migration for users table schema change?          │
│ Confidence: 0.82 (would auto-proceed, but invariant overrides)             │
│ Invariant: "Any change to database migration files requires explicit       │
│             human approval"                                                │
╰────────────────────────────────────────────────────────────────────────────╯

╭─ Timing ───────────╮
│ Started: 09:05:12  │
│ Elapsed: 00:02:48  │
│ ETA: (paused)      │
╰────────────────────╯

╭─ Cost ───────────────╮
│ Tokens Used: 18,740  │
│ Cost So Far: $0.062  │
│ Estimated: $0.095    │
╰──────────────────────╯

⚠ WARN Plan paused — awaiting human input for escalated decision


# Review the decision requiring approval
$ agents plan explain 01HXRBD1E2F3G4H5I6J7K8L9

╭─ Decision ───────────────────────────────────────────────────────────╮
│ ID: 01HXRBD1E2F3G4H5I6J7K8L9                                         │
│ Type: implementation_choice                                          │
│ Question: Create Alembic migration for users table schema change?    │
│ Chosen: Add nullable `orm_version` column with migration             │
│ Confidence: 0.82                                                     │
│ Plan: 01HXRBG1H2I3J4K5L6M7N8O9P0                                     │
│ Sequence: 4 of 7                                                     │
│ Created: 2026-02-11 09:07                                            │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Alternatives Considered ────────────────────────────────────────────╮
│ 1. Add nullable `orm_version` column with migration (chosen)         │
│ 2. Use a shadow table approach (no schema change)                    │
│ 3. In-place column rename via ALTER (risky in production)            │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Escalation Reason ──────────────────────────────────────────────────╮
│ Invariant Override: inv_01HXRBA1A                                    │
│ Text: "Any change to database migration files requires explicit      │
│       human approval"                                                │
│ Effect: Confidence 0.82 would normally auto-proceed (threshold       │
│         0.6), but invariant forces manual escalation regardless      │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Impact ─────────────────────────╮
│ Downstream Decisions: 3          │
│ Downstream Child Plans: 0        │
│ Artifacts Produced: 2            │
│ Correction Impact: medium        │
╰──────────────────────────────────╯

╭─ Rationale ──────────────────────────────────────────────────────────╮
│ The auth module currently uses raw SQL queries. Refactoring to ORM   │
│ requires an `orm_version` tracking column on the users table.        │
│ Adding as nullable first avoids downtime; the backfill + NOT NULL    │
│ constraint can follow in a second migration after data is populated. │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Correction ────────────────────────────────────────────────╮
│ agents plan prompt 01HXRBG1H2I3J4K5L6M7N8O9P0               │
│   "Approved. <guidance>"                                    │
│ agents plan correct 01HXRBD1E2F3G4H5I6J7K8L9                │
│   --mode revert --guidance "Use approach 2 instead..."      │
╰─────────────────────────────────────────────────────────────╯

✓ OK Decision explained


# Approve the migration approach with specific guidance
$ agents plan prompt 01HXRBG1H2I3J4K5L6M7N8O9P0 \
    "Approved. Use a two-phase migration: first add the column as nullable, \
     then in a separate migration add the NOT NULL constraint after backfill."

╭─ Guidance Added ──────────────────────────────────────────────────────────╮
│ Plan: 01HXRBG1H2I3J4K5L6M7N8O9P0                                          │
│ Guidance: Approved. Use a two-phase migration: first add the column as    │
│           nullable, then in a separate migration add the NOT NULL         │
│           constraint after backfill.                                      │
│ Scope: next execution step                                                │
│ Phase: execute                                                            │
│ State: awaiting_input → processing                                        │
╰───────────────────────────────────────────────────────────────────────────╯

╭─ Decision Created ──────────────────────────────╮
│ Type: user_intervention                         │
│ ID: 01HXRBE2F3G4H5I6J7K8L9M0                    │
│ Parent: 01HXRBD1E2F3G4H5I6J7K8L9                │
╰─────────────────────────────────────────────────╯

╭─ Queue ────╮
│ Pending: 1 │
│ Applied: 0 │
╰────────────╯

✓ OK Guidance queued — execution resuming
--- ### Example 14: Server Mode — Team Collaboration **Scenario**: A distributed team uses CleverAgents in server mode. Multiple engineers share actions, actors, and projects while working on the same codebase from different machines. **Complexity**: Intermediate. Server mode, multi-user, namespace management. #### Step 1: Connect to the Server 

# Configure server connection
$ agents config set server.url https://agents.example.com

╭─ Config Updated ──────────────────────────────╮
│ Key: server.url                               │
│ Value: https://agents.example.com             │
│ Previous: (not set)                           │
│ Source: config                                │
│ Scope: global                                 │
╰───────────────────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 3                             │
╰─────────────────────────────────────╯

✓ OK Config updated

$ agents config set server.token "tok_01HXR..."

╭─ Config Updated ──────────────────────────╮
│ Key: server.token                         │
│ Value: tok_01HXR... (redacted)            │
│ Previous: (not set)                       │
│ Source: config                            │
│ Scope: global                             │
╰───────────────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 4                             │
╰─────────────────────────────────────╯

✓ OK Config updated

$ agents config set core.namespace myteam

╭─ Config Updated ──────────────────────╮
│ Key: core.namespace                   │
│ Value: myteam                         │
│ Previous: local                       │
│ Source: config                        │
│ Scope: global                         │
╰───────────────────────────────────────╯

╭─ Saved To ──────────────────────────╮
│ File: ~/.cleveragents/config.toml   │
│ Line: 5                             │
╰─────────────────────────────────────╯

✓ OK Config updated


# Verify connection
$ agents diagnostics

╭─ Checks ────────────────────────────────────────────────╮
│ Check            Status  Details                        │
│ ───────────────  ──────  ───────────────────────        │
│ Config file      OK      readable                       │
│ Database         OK      writable                       │
│ Anthropic key    OK      configured                     │
│ OPENAI_API_KEY   WARN    missing                        │
│ Disk space       OK      4.8 GB free                    │
│ Text index       OK      tantivy 0.22                   │
│ Vector index     OK      faiss (CPU)                    │
│ Graph store      OK      neo4j 5.15                     │
│ File permissions OK      data dir r/w                   │
│ Git              OK      git 2.43.0                     │
│ Server           OK      connected (agents.example.com) │
│ Namespace        OK      myteam (4 members)             │
╰─────────────────────────────────────────────────────────╯

╭─ Summary ─────────╮
│ Checks: 12 total  │
│ Warnings: 1       │
│ Errors: 0         │
│ Duration: 0.8s    │
╰───────────────────╯

╭─ Server ────────────────────────────╮
│ URL: https://agents.example.com     │
│ Auth: valid (tok_01HXR...)          │
│ Namespace: myteam                   │
│ Members: 4                          │
│ Shared Actions: 7                   │
│ Shared Actors: 3                    │
│ Latency: 42ms                       │
╰─────────────────────────────────────╯

╭─ Recommendations ──────────────────────────────╮
│ - Set OPENAI_API_KEY to enable OpenAI models   │
╰────────────────────────────────────────────────╯

⚠ WARN 1 warning requires attention
#### Step 2: Publish Shared Resources 

# Publish an action to the team namespace (visible to all team members)
$ agents action create --config ./actions/generate-tests.yaml

╭─ Action Created ──────────────────────────────────────╮
│ Name: myteam/generate-tests                           │
│ ID: 01HXRC1A2B3C4D5E6F7G8H9J0K                        │
│ State: available                                      │
│ Strategy Actor: anthropic/claude-3.5-sonnet           │
│ Execution Actor: anthropic/claude-3.5-sonnet          │
│ Reusable: yes                                         │
│ Read Only: no                                         │
│ Created: 2026-02-11 09:15                             │
╰───────────────────────────────────────────────────────╯

╭─ Definition of Done ───────────────────────────────────╮
│ All target modules have test coverage above 80%        │
│ Tests pass in CI without flaky failures                │
╰────────────────────────────────────────────────────────╯

╭─ Arguments ─────────────────────────────────────────────────────╮
│ Name            Type    Required  Description                   │
│ ──────────────  ──────  ────────  ───────────────────────       │
│ target_module   string  yes       Module path to generate tests │
╰─────────────────────────────────────────────────────────────────╯

╭─ Automation ────────────────────────╮
│ Profile: supervised                 │
│ Source: action default              │
╰─────────────────────────────────────╯

╭─ Usage ───────────────────────────────────────────────────────────╮
│ agents plan use myteam/generate-tests local/my-project            │
│   --arg target_module="src/payments"                              │
╰───────────────────────────────────────────────────────────────────╯

✓ OK Action created


# Publish a shared actor
$ agents actor add --config ./actors/review-pipeline.yaml

╭─ Actor Added ──────────────────────────────────╮
│ Name: myteam/review-pipeline                   │
│ Provider: anthropic                            │
│ Model: claude-3.5-sonnet                       │
│ Default: no                                    │
│ Unsafe: no                                     │
│ Type: graph                                    │
╰────────────────────────────────────────────────╯

╭─ Config ───────────────────────────────╮
│ Path: ./actors/review-pipeline.yaml    │
│ Hash: 5a7c2e1                          │
│ Options: 3                             │
│ Nodes: 5                               │
│ Edges: 6                               │
╰────────────────────────────────────────╯

╭─ Capabilities ──────────────────╮
│ - multi-stage code review       │
│ - security analysis             │
│ - performance analysis          │
│ - style checking                │
╰─────────────────────────────────╯

╭─ Tools ────────────────────────╮
│ Tool          Read-Only  Safe  │
│ ────────────  ─────────  ────  │
│ read_file     yes        yes   │
│ search_files  yes        yes   │
│ git_diff      yes        yes   │
│ run_tests     yes        yes   │
╰────────────────────────────────╯

✓ OK Actor added


# List available actions (team namespace)
$ agents action list --namespace myteam

╭─ Actions ────────────────────────────────────────────────────────────────────────────────────────────────╮
│ Name                      State      Strategy Actor               Execution Actor              Reusable  │
│ ────────────────────────  ─────────  ───────────────────────────  ───────────────────────────  ────────  │
│ myteam/generate-tests    available  anthropic/claude-3.5-sonnet  anthropic/claude-3.5-sonnet  ✓          │
│ myteam/deep-review       available  myteam/review-pipeline       myteam/review-pipeline       ✓          │
│ myteam/format-codebase   available  anthropic/claude-3.5-sonnet  anthropic/claude-3.5-sonnet  ✓          │
│ myteam/security-audit    available  anthropic/claude-3.5-sonnet  anthropic/claude-3.5-sonnet  ✓          │
│ myteam/refactor-to-orm   available  anthropic/claude-3.5-sonnet  anthropic/claude-3.5-sonnet  ✗          │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Filters ──────────────────╮
│ State: (any)               │
│ Namespace: myteam          │
╰────────────────────────────╯

╭─ Summary ──────────────────╮
│ Total: 5                   │
│ Available: 5               │
│ Archived: 0                │
╰────────────────────────────╯

✓ OK 5 actions listed
#### Step 3: Use Shared Resources from Another Machine On a different developer's machine: 

# Configure server connection
$ agents config set server.url https://agents.example.com

╭─ Config Updated ──────────────────────────────╮
│ Key: server.url                               │
│ Value: https://agents.example.com             │
│ Previous: (not set)                           │
│ Source: config                                │
│ Scope: global                                 │
╰───────────────────────────────────────────────╯

✓ OK Config updated

$ agents config set server.token "tok_01HXS..."

╭─ Config Updated ──────────────────────────╮
│ Key: server.token                         │
│ Value: tok_01HXS... (redacted)            │
│ Previous: (not set)                       │
│ Source: config                            │
│ Scope: global                             │
╰───────────────────────────────────────────╯

✓ OK Config updated

$ agents config set core.namespace myteam

╭─ Config Updated ──────────────────────╮
│ Key: core.namespace                   │
│ Value: myteam                         │
│ Previous: local                       │
│ Source: config                        │
│ Scope: global                         │
╰───────────────────────────────────────╯

✓ OK Config updated


# Use the team's shared action
$ agents plan use \
    --arg target_module="src/payments" \
    myteam/generate-tests local/payment-service

╭─ Plan Created ─────────────────────────────────────────╮
│ Plan ID: 01HXRC2B3C4D5E6F7G8H9J0K1L2                   │
│ Phase: strategize (running)                            │
│ Action: myteam/generate-tests                          │
│ Project: local/payment-service                         │
│ Automation: supervised                                 │
│ Attempt: 1                                             │
╰────────────────────────────────────────────────────────╯

╭─ Inputs ──────────────────────╮
│ - target_module=src/payments  │
╰───────────────────────────────╯

╭─ Actors ──────────────────────────────────╮
│ Strategy: anthropic/claude-3.5-sonnet     │
│ Execution: anthropic/claude-3.5-sonnet    │
│ Source: server (myteam)                   │
╰───────────────────────────────────────────╯

╭─ Context ───────────────────────╮
│ Resources: 1 (repo)             │
│ Indexed Files: 189              │
│ View: strategize                │
│ Hot Token Budget: 12,000        │
╰─────────────────────────────────╯

╭─ Next Steps ──────────────────────────────────────────────╮
│ - agents plan status 01HXRC2B3C4D5E6F7G8H9J0K1L2          │
│ - agents plan tree 01HXRC2B3C4D5E6F7G8H9J0K1L2            │
╰───────────────────────────────────────────────────────────╯

✓ OK Plan created — strategize in progress
#### Step 4: Monitor Across the Team 

# List all plans across the team
$ agents plan list --namespace myteam

╭─ Plans ────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ID        Phase     State       Action                  Project                User     Elapsed                │
│ ────────  ────────  ──────────  ──────────────────────  ─────────────────────  ───────  ─────────              │
│ 01HXRC2B  execute   processing  myteam/generate-tests   local/payment-service  jdoe     00:04:12               │
│ 01HXRC3C  apply     applied     myteam/deep-review      local/api-service      asmith   00:08:47               │
│ 01HXRC4D  execute   processing  myteam/generate-tests   local/api-service      mwong    00:02:35               │
│ 01HXRC5E  apply     applied     myteam/format-codebase  local/frontend         blee     00:01:58               │
│ 01HXRC6F  execute   awaiting    myteam/security-audit   local/worker-service   asmith   00:06:20               │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Filters ──────────────────╮
│ Phase: (any)               │
│ State: (any)               │
│ Namespace: myteam          │
│ Project: (any)             │
│ Action: (any)              │
╰────────────────────────────╯

╭─ Summary ─────────────╮
│ Total: 5              │
│ Processing: 2         │
│ Completed: 2          │
│ Awaiting: 1           │
│ Errored: 0            │
╰───────────────────────╯

✓ OK 5 plans listed


# See who is running what — filter to executing state
$ agents plan list --namespace myteam --state processing

╭─ Plans ────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ID        Phase    State       Action                 Project                User     Elapsed                  │
│ ────────  ───────  ──────────  ─────────────────────  ─────────────────────  ───────  ─────────                │
│ 01HXRC2B  execute  processing  myteam/generate-tests  local/payment-service  jdoe     00:04:12                 │
│ 01HXRC4D  execute  processing  myteam/generate-tests  local/api-service      mwong    00:02:35                 │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Filters ──────────────────────╮
│ Phase: (any)                   │
│ State: processing              │
│ Namespace: myteam              │
│ Project: (any)                 │
│ Action: (any)                  │
╰────────────────────────────────╯

╭─ Summary ─────────────╮
│ Total: 2              │
│ Processing: 2         │
│ Completed: 0          │
│ Errored: 0            │
╰───────────────────────╯

✓ OK 2 plans listed
--- ### Example 15: Disaster Recovery — Rollback a Failed Apply **Scenario**: A plan was applied, but the changes broke production. The team needs to understand what happened and roll back. **Complexity**: Intermediate. Rollback, checkpoint restore, post-mortem analysis. #### Step 1: Investigate the Failed Apply 

# Check the plan status
$ agents plan status 01HXRCF1G2H3I4J5K6L7M8N9O0

╭─ Plan Status ───────────────────────────────────────╮
│ Plan: 01HXRCF1G2H3I4J5K6L7M8N9O0                    │
│ Phase: apply                                        │
│ State: errored                                      │
│ Action: local/optimize-db-connections               │
│ Project: local/api-service                          │
│ Automation: trusted                                 │
│ Attempt: 1                                          │
╰─────────────────────────────────────────────────────╯

╭─ Progress ─────────────────────╮
│ ✓ Strategize                   │
│ ✓ Execute                      │
│ ✗ Apply (post-apply failure)   │
╰────────────────────────────────╯

╭─ Timing ──────────────────────────╮
│ Started: 2026-02-11 08:30:00      │
│ Applied At: 2026-02-11 08:42:18   │
│ Failed At: 2026-02-11 08:44:05    │
│ Total Duration: 00:14:05          │
╰───────────────────────────────────╯

╭─ Result ───────────────────────────────────────────────╮
│ Decisions Made: 6                                      │
│ Child Plans: 0                                         │
│ Artifacts: 4 files updated                             │
│ Validations: 2/3 passed (1 FAILED post-apply)          │
│ Total Cost: $0.072                                     │
╰────────────────────────────────────────────────────────╯

╭─ Error ──────────────────────────────────────────────────────────────────────╮
│ Post-apply health check failed: connection pool exhaustion detected          │
│ Impact: API response times increased 10x, 503 errors in production           │
│ Root Cause Decision: 01HXRCD3E4F5G6H7I8J9K0L1                                │
╰──────────────────────────────────────────────────────────────────────────────╯

╭─ Recovery Options ──────────────────────────────────────────────────╮
│ - agents plan rollback — restore to a previous checkpoint           │
│ - agents plan correct — revert and re-execute with guidance         │
│ - agents plan explain — investigate the root cause decision         │
╰─────────────────────────────────────────────────────────────────────╯

✗ ERROR Plan applied but post-apply validation failed


# Review the decision tree to understand what was done
$ agents plan tree 01HXRCF1G2H3I4J5K6L7M8N9O0

╭─ Decision Tree ────────────────────────────────────────────────────────────────────────────────╮
│ Plan: 01HXRCF1G2H3I4J5K6L7M8N9O0                                                               │
│ ├─ [prompt_definition] "Optimize database connection handling"                                 │
│ ├─ [invariant_enforced] "All DB config changes must preserve existing pool limits"             │
│ ├─ [strategy_choice] "Refactor connection pool configuration" (confidence: 0.91)               │
│ ├─ [tool_invocation] write_file: src/db/pool_config.py                                         │
│ ├─ [implementation_choice] "Increase pool size to 100" (confidence: 0.78) ← ROOT CAUSE         │
│ └─ [tool_invocation] write_file: src/db/health_check.py                                        │
╰────────────────────────────────────────────────────────────────────────────────────────────────╯

╭─ Tree Summary ──────────────────╮
│ Nodes: 6                        │
│ Depth: 2                        │
│ Child Plans: 0                  │
│ Invariants: 1                   │
│ Superseded: 0 (hidden)          │
╰─────────────────────────────────╯

╭─ Decision IDs (for correction) ──────────────────────╮
│ Root: 01HXRCC1D2E3F4G5H6I7J8K9                       │
│ Invariant 1: 01HXRCC2E3F4G5H6I7J8K9L0                │
│ Strategy: 01HXRCC3F4G5H6I7J8K9L0M1                   │
│ Tool 1: 01HXRCC4G5H6I7J8K9L0M1N2                     │
│ Pool Size (root cause): 01HXRCD3E4F5G6H7I8J9K0L1     │
│ Tool 2: 01HXRCE4F5G6H7I8J9K0L1M2                     │
╰──────────────────────────────────────────────────────╯

✓ OK Decision tree rendered


# Look at the specific changes that were applied
$ agents plan diff 01HXRCF1G2H3I4J5K6L7M8N9O0

╭─ Diff Summary ─────────────────────────────────────╮
│ Plan: 01HXRCF1G2H3I4J5K6L7M8N9O0                   │
│ Project: local/api-service                         │
│ Files Changed: 4                                   │
│ Insertions: 38                                     │
│ Deletions: 12                                      │
│ Net Change: +26 lines                              │
╰────────────────────────────────────────────────────╯

╭─ Files ──────────────────────────────────────╮
│ Path                      Change  Status     │
│ ────────────────────────  ──────  ────────   │
│ src/db/pool_config.py     +14 -6  modified   │
│ src/db/health_check.py    +18 -0  new file   │
│ src/db/__init__.py         +4 -4  modified   │
│ config/database.toml       +2 -2  modified   │
╰──────────────────────────────────────────────╯

╭─ Patch Preview ──────────────────────────────────╮
│ --- a/src/db/pool_config.py                      │
│ +++ b/src/db/pool_config.py                      │
│ @@ -8,6 +8,14 @@                                 │
│ - POOL_SIZE = 20                                 │
│ - POOL_MAX_OVERFLOW = 10                         │
│ + POOL_SIZE = 100                                │
│ + POOL_MAX_OVERFLOW = 50                         │
│ + POOL_RECYCLE = 3600                            │
│ + POOL_PRE_PING = True                           │
│ --- a/config/database.toml                       │
│ +++ b/config/database.toml                       │
│ @@ -3,2 +3,2 @@                                  │
│ - pool_size = 20                                 │
│ + pool_size = 100                                │
╰──────────────────────────────────────────────────╯

╭─ Risk Assessment ──────────────────────────╮
│ API Compatibility: preserved               │
│ Test Coverage: maintained                  │
│ Breaking Changes: pool size 5x increase    │
│ Resource Impact: high (connection limit)   │
╰────────────────────────────────────────────╯

✓ OK Diff generated


# Examine the decision that led to the problematic change
$ agents plan explain 01HXRCD3E4F5G6H7I8J9K0L1 --show-context --show-reasoning

╭─ Decision ───────────────────────────────────────────────────────────╮
│ ID: 01HXRCD3E4F5G6H7I8J9K0L1                                         │
│ Type: implementation_choice                                          │
│ Question: What pool size should be configured?                       │
│ Chosen: Increase pool size from 20 to 100                            │
│ Confidence: 0.78                                                     │
│ Plan: 01HXRCF1G2H3I4J5K6L7M8N9O0                                     │
│ Sequence: 5 of 6                                                     │
│ Created: 2026-02-11 08:38                                            │
╰──────────────────────────────────────────────────────────────────────╯

╭─ Alternatives Considered ─────────────────────────────────────╮
│ 1. Increase pool size from 20 to 100 (chosen)                 │
│ 2. Keep pool at 20, add connection health checks only         │
│ 3. Increase to 50 with overflow to 75                         │
╰───────────────────────────────────────────────────────────────╯

╭─ Impact ─────────────────────────╮
│ Downstream Decisions: 1          │
│ Downstream Child Plans: 0        │
│ Artifacts Produced: 2            │
│ Correction Impact: low           │
╰──────────────────────────────────╯

╭─ Context Snapshot ────────────────────────────────────────────────╮
│ - Current pool_size=20 in config/database.toml                    │
│ - Database server: PostgreSQL 15, max_connections=150             │
│ - 3 application replicas running (total: 60 connections used)     │
│ - Slow query logs show connection wait times of 200-500ms         │
│ Hot Context Hash: sha256:9c4f...a1b2                              │
╰───────────────────────────────────────────────────────────────────╯

╭─ Rationale ─────────────────────────────────────────────────────╮
│ Connection wait times of 200-500ms suggest pool exhaustion.     │
│ Increasing to 100 connections per replica provides headroom     │
│ for burst traffic and eliminates the queueing bottleneck.       │
╰─────────────────────────────────────────────────────────────────╯

╭─ Model Reasoning (raw) ────────────────────────────────────────────────╮
│ The slow query logs show connection acquisition delays of 200-500ms    │
│ which indicates the pool is frequently exhausted. Current config:      │
│ pool_size=20, max_overflow=10 (total 30 per replica).                  │
│                                                                        │
│ With 3 replicas that's 90 connections max. The PostgreSQL server       │
│ allows 150. I'll increase to 100 per replica (300 total with           │
│ overflow). This exceeds the server's max_connections=150 but           │
│ overflow connections are temporary and unlikely to all be active       │
│ simultaneously.                                                        │
│                                                                        │
│ [NOTE: The model failed to account for 3 replicas × 100 = 300          │
│  exceeding PostgreSQL max_connections=150]                             │
╰────────────────────────────────────────────────────────────────────────╯

╭─ Correction ─────────────────────────────────────────────────╮
│ agents plan correct 01HXRCD3E4F5G6H7I8J9K0L1                 │
│   --mode revert --guidance "Keep pool at 20, add health..."  │
╰──────────────────────────────────────────────────────────────╯

✓ OK Decision explained
#### Step 2: Roll Back to a Checkpoint 

# List available checkpoints for this plan
$ agents plan artifacts 01HXRCF1G2H3I4J5K6L7M8N9O0

╭─ Artifacts ────────────────────────────────────────────────────────╮
│ Path                     Type   Size    Change   Child Plan        │
│ ───────────────────────  ─────  ──────  ───────  ──────────        │
│ src/db/pool_config.py    edit   1.4 KB  +14 -6  root               │
│ src/db/health_check.py   write  2.1 KB  +18 -0  root               │
│ src/db/__init__.py       edit   0.8 KB   +4 -4  root               │
│ config/database.toml     edit   0.3 KB   +2 -2  root               │
╰────────────────────────────────────────────────────────────────────╯

╭─ Summary ───────────╮
│ Total: 4            │
│ Writes: 1 (new)     │
│ Edits: 3 (modified) │
│ Deletes: 0          │
│ Total Size: 4.6 KB  │
╰─────────────────────╯

╭─ Checkpoints ──────────────────────────────────────────────────────╮
│ ID                  Label                        Created           │
│ ────────────────────  ───────────────────────────  ──────────────  │
│ checkpoint_01HXRCP1  before pool config changes    08:36:12        │
│ checkpoint_01HXRCP2  before health check addition  08:39:45        │
│ checkpoint_01HXRCP3  pre-apply snapshot            08:42:00        │
╰────────────────────────────────────────────────────────────────────╯

╭─ By Plan ──────────────╮
│ Root Plan: 4 artifacts │
╰────────────────────────╯

✓ OK 4 artifacts listed


# Roll back to the checkpoint before the problematic pool config change
$ agents plan rollback --yes 01HXRCF1G2H3I4J5K6L7M8N9O0 checkpoint_01HXRCP1

╭─ Rollback Summary ─────────────────────────────────╮
│ Plan: 01HXRCF1G2H3I4J5K6L7M8N9O0                   │
│ Checkpoint: checkpoint_01HXRCP1                    │
│ Label: before pool config changes                  │
│ Files: 4 reverted                                  │
╰────────────────────────────────────────────────────╯

╭─ Changes Reverted ──────────────────────╮
│ File                      Action        │
│ ────────────────────────  ──────────    │
│ src/db/pool_config.py     restored      │
│ src/db/health_check.py    removed       │
│ src/db/__init__.py        restored      │
│ config/database.toml      restored      │
╰─────────────────────────────────────────╯

╭─ Impact ──────────────────────────────────╮
│ Child Plans Invalidated: 0                │
│ Sandbox: restored to checkpoint_01HXRCP1  │
│ Decisions After CP: 2 discarded           │
│ Tool Calls After CP: 3 undone             │
╰───────────────────────────────────────────╯

╭─ Post-Rollback State ──────────╮
│ Phase: execute                 │
│ State: queued (awaiting input) │
│ Checkpoints Remaining: 1       │
╰────────────────────────────────╯

✓ OK Rollback complete
#### Step 3: Correct and Re-Execute 

# Correct the decision that caused the issue
$ agents plan correct 01HXRCD3E4F5G6H7I8J9K0L1 \
    --mode revert \
    --guidance "The connection pool size change caused the outage. \
                Keep the pool at 20 connections maximum and add \
                connection health checks instead." --yes

╭─ Correction ──────────────────────────────────────────────╮
│ Mode: revert                                              │
│ Impact: 1 decision, 0 child plans, 2 artifacts            │
│ New Decision: 01HXRCCORR1A2B3C4D5                         │
│ Corrects: 01HXRCD3E4F5G6H7I8J9K0L1                        │
│ Attempt: 2                                                │
╰───────────────────────────────────────────────────────────╯

╭─ Affected Subtree ──────────────╮
│ Decisions Invalidated: 1        │
│ Child Plans Rolled Back: 0      │
│ Artifacts Archived: 2           │
│ Unaffected Decisions: 4         │
╰─────────────────────────────────╯

╭─ Sandbox Rollback ──────────────────╮
│ Checkpoint: checkpoint_01HXRCP1     │
│ Files Reverted: 2                   │
│ Status: restored                    │
╰─────────────────────────────────────╯

╭─ Recompute ───────────╮
│ Queued: 1 re-execute  │
│ ETA: 2m               │
╰───────────────────────╯

╭─ History ───────────────────────────────────────────────╮
│ - Original decision superseded                          │
│ - Prior artifacts archived for comparison               │
│ - agents plan diff --correction 01HXRCCORR1A2B3C4D5     │
╰─────────────────────────────────────────────────────────╯

✓ OK Correction applied — re-executing affected subtree


# The affected subtree is re-executed. Review the new changes.
$ agents plan diff --correction 01HXRCCORR1A2B3C4D5

╭─ Correction Diff ────────────────────────────────────╮
│ Correction: 01HXRCCORR1A2B3C4D5                      │
│ Original Decision: 01HXRCD3E4F5G6H7I8J9K0L1          │
│ Mode: revert                                         │
│ Files Changed: 3                                     │
│ New Insertions: 32                                   │
│ New Deletions: 4                                     │
╰──────────────────────────────────────────────────────╯

╭─ Comparison ─────────────────────────────────────────────────────────────╮
│ File                      Before (original)   After (corrected)          │
│ ────────────────────────  ──────────────────  ──────────────────────     │
│ src/db/pool_config.py     +14 -6 (pool=100)  +8 -2 (pool=20, checks)     │
│ src/db/health_check.py    +18 -0 (basic)     +24 -0 (robust checks)      │
│ config/database.toml      +2 -2 (pool=100)   (unchanged — pool=20)       │
╰──────────────────────────────────────────────────────────────────────────╯

╭─ Patch Preview (corrected vs original) ───────────────────────╮
│ --- a/src/db/pool_config.py (original)                        │
│ +++ b/src/db/pool_config.py (corrected)                       │
│ @@ -8,6 +8,10 @@                                              │
│ - POOL_SIZE = 100                                             │
│ - POOL_MAX_OVERFLOW = 50                                      │
│ + POOL_SIZE = 20                                              │
│ + POOL_MAX_OVERFLOW = 10                                      │
│ + POOL_PRE_PING = True                                        │
│ + POOL_HEALTH_CHECK_INTERVAL = 30                             │
│ --- a/src/db/health_check.py (original)                       │
│ +++ b/src/db/health_check.py (corrected)                      │
│ @@ -1,18 +1,24 @@                                             │
│ + # Added: connection validation, stale connection eviction,  │
│ + # periodic health probes, and circuit breaker pattern       │
│   ...                                                         │
╰───────────────────────────────────────────────────────────────╯

✓ OK Correction diff generated


# Re-apply with the fix
$ agents plan apply --yes 01HXRCF1G2H3I4J5K6L7M8N9O0

╭─ Apply Summary ──────────────────────────╮
│ Plan: 01HXRCF1G2H3I4J5K6L7M8N9O0         │
│ Artifacts: 3 files updated               │
│ Changes: 32 insertions, 4 deletions      │
│ Project: local/api-service               │
│ Applied At: 2026-02-11 09:02             │
╰──────────────────────────────────────────╯

╭─ Validation ───────────────────╮
│ Tests: passed (31/31)          │
│ Lint: passed (0 warnings)      │
│ Type Check: passed (0 errors)  │
│ Health Check: passed           │
│ Duration: 18.6s                │
╰────────────────────────────────╯

╭─ Sandbox Cleanup ─────────╮
│ Worktree: removed         │
│ Branch: merged to main    │
│ Checkpoint: archived      │
╰───────────────────────────╯

╭─ Plan Lifecycle ──────────────────────────╮
│ Phase: apply                              │
│ State: applied                            │
│ Total Duration: 00:32:02 (incl. rollback) │
│ Total Cost: $0.118                        │
│ Decisions Made: 7 (1 corrected)           │
│ Child Plans: 0                            │
╰───────────────────────────────────────────╯

╭─ Next Steps ──────╮
│ - Review git diff │
│ - Commit changes  │
╰───────────────────╯

✓ OK Changes applied
### Example 16: Devcontainer-Driven Development !!! adr "Related ADRs" [ADR-043: Devcontainer Integration](adr/ADR-043-devcontainer-integration.md) · [ADR-042: Resource Type Inheritance](adr/ADR-042-resource-type-inheritance.md) · [ADR-039: Container Resource Types](adr/ADR-039-container-resource-types.md) **Scenario:** A developer registers a git checkout that contains a `.devcontainer/` directory. The system auto-detects the devcontainer, creates it in `detected` state, then lazily builds and starts it when a plan executes. All tool invocations route to the container via execution environment routing. **What this example demonstrates:** - Devcontainer auto-discovery during `agents resource add` - Lazy activation (container not built until first plan execution) - Execution environment routing selecting the nearest-ancestor devcontainer (precedence level 3) - Tool invocations running inside the container - Apply phase writing changes back to host via bind mount **Step 1 — Register the git checkout (devcontainer auto-detected):** === "Rich" 

    $ agents resource add git-checkout local/webapp --path /home/user/projects/webapp

    ╭─ Resource ──────────────────────────────────────────╮
    │ Name: local/webapp                                  │
    │ ID: 01J0A1B2C3D4E5F6G7H8J9K0L1                      │
    │ Type: git-checkout                                  │
    │ Path: /home/user/projects/webapp                    │
    │ Branch: main                                        │
    ╰─────────────────────────────────────────────────────╯

    ╭─ Auto-discovered Children ─────────────────────────────────────────╮
    │ ID               Type                    Status                    │
    │ ───────────────  ──────────────────────  ─────────────────         │
    │ 01J0A1B2C3D5…   git                     created                    │
    │ 01J0A1B2C3D6…   devcontainer-instance   detected (not built)       │
    │ 01J0A1B2C3D7…   fs-directory            created                    │
    │   + 38 git-commit, 205 git-tree-entry, 12 fs-file                  │
    ╰────────────────────────────────────────────────────────────────────╯

    ⚠ Devcontainer detected at .devcontainer/devcontainer.json
      Container will be built lazily on first access.

    ✓ OK Resource registered (259 child resources discovered)
=== "Plain" ``` $ agents resource add git-checkout local/webapp --path /home/user/projects/webapp Resource Name: local/webapp ID: 01J0A1B2C3D4E5F6G7H8J9K0L1 Type: git-checkout Path: /home/user/projects/webapp Branch: main Auto-discovered Children ID Type Status --------------- ---------------------- ----------------- 01J0A1B2C3D5.. git created 01J0A1B2C3D6.. devcontainer-instance detected (not built) 01J0A1B2C3D7.. fs-directory created + 38 git-commit, 205 git-tree-entry, 12 fs-file [WARN] Devcontainer detected at .devcontainer/devcontainer.json Container will be built lazily on first access. [OK] Resource registered (259 child resources discovered) ``` **Step 2 — Create project and link the resource:** === "Rich" 

    $ agents project create local/webapp-project
    ✓ OK Project created: local/webapp-project

    $ agents project link-resource local/webapp-project local/webapp
    ✓ OK Resource local/webapp linked to project local/webapp-project
=== "Plain" ``` $ agents project create local/webapp-project [OK] Project created: local/webapp-project $ agents project link-resource local/webapp-project local/webapp [OK] Resource local/webapp linked to project local/webapp-project ``` **Step 3 — Start a plan (devcontainer lazily built):** === "Rich" 

    $ agents plan use local/add-dark-mode local/webapp-project \
      --arg feature=dark-mode --automation-profile supervised

    ╭─ Plan Created ──────────────────────────────────────╮
    │ Plan ID: 01J0B2C3D4E5F6G7H8J9K0L1M2                 │
    │ Phase: strategize                                   │
    │ Action: local/add-dark-mode                         │
    │ Project: local/webapp-project                       │
    │ Automation: supervised                              │
    ╰─────────────────────────────────────────────────────╯

    ✓ OK Plan created — strategize phase starting
=== "Plain" ``` $ agents plan use local/add-dark-mode local/webapp-project \ --arg feature=dark-mode --automation-profile supervised Plan Created Plan ID: 01J0B2C3D4E5F6G7H8J9K0L1M2 Phase: strategize Action: local/add-dark-mode Project: local/webapp-project Automation: supervised [OK] Plan created — strategize phase starting ``` **Step 4 — Execute the plan (devcontainer activation + tool routing):** === "Rich" 

    $ agents plan execute 01J0B2C3D4E5F6G7H8J9K0L1M2

    ⏳ Building devcontainer from .devcontainer/devcontainer.json …
      Image: mcr.microsoft.com/devcontainers/typescript-node:1-20
      Features: ghcr.io/devcontainers/features/git:1
      Running postCreateCommand: npm install
    ✓ Devcontainer ready (01J0A1B2C3D6…) in 42s

    ╭─ Execution Environment ───────────────────────────╮
    │ Resolved via: nearest-ancestor devcontainer       │
    │ Resource: 01J0A1B2C3D6… (devcontainer-instance)   │
    │ Workspace: /workspaces/webapp                     │
    │ Precedence: level 3 of 6                          │
    ╰───────────────────────────────────────────────────╯

    ▸ Decision 1/3: Create src/theme/dark-mode.ts
      → write_file() in container /workspaces/webapp/src/theme/dark-mode.ts
      ✓ Checkpoint cp-001

    ▸ Decision 2/3: Update src/App.tsx to import ThemeProvider
      → edit_file() in container /workspaces/webapp/src/App.tsx
      ✓ Checkpoint cp-002

    ▸ Decision 3/3: Run tests
      → run_command() in container npm test
      ✓ All 47 tests passed
      ✓ Checkpoint cp-003

    ╭─ Execution Complete ──────────────────╮
    │ Decisions: 3/3 succeeded              │
    │ Checkpoints: 3                        │
    │ Environment: devcontainer             │
    │ Duration: 1m 12s (incl. 42s build)    │
    ╰───────────────────────────────────────╯

    ✓ OK Execution complete — ready for apply
=== "Plain" ``` $ agents plan execute 01J0B2C3D4E5F6G7H8J9K0L1M2 [WAIT] Building devcontainer from .devcontainer/devcontainer.json … Image: mcr.microsoft.com/devcontainers/typescript-node:1-20 Features: ghcr.io/devcontainers/features/git:1 Running postCreateCommand: npm install [OK] Devcontainer ready (01J0A1B2C3D6…) in 42s Execution Environment Resolved via: nearest-ancestor devcontainer Resource: 01J0A1B2C3D6… (devcontainer-instance) Workspace: /workspaces/webapp Precedence: level 3 of 6 Decision 1/3: Create src/theme/dark-mode.ts -> write_file() in container /workspaces/webapp/src/theme/dark-mode.ts [OK] Checkpoint cp-001 Decision 2/3: Update src/App.tsx to import ThemeProvider -> edit_file() in container /workspaces/webapp/src/App.tsx [OK] Checkpoint cp-002 Decision 3/3: Run tests -> run_command() in container npm test [OK] All 47 tests passed [OK] Checkpoint cp-003 Execution Complete Decisions: 3/3 succeeded Checkpoints: 3 Environment: devcontainer Duration: 1m 12s (incl. 42s build) [OK] Execution complete — ready for apply ``` **Step 5 — Apply changes to host:** === "Rich" 

    $ agents plan apply --yes 01J0B2C3D4E5F6G7H8J9K0L1M2

    ╭─ Apply ──────────────────────────────────────────╮
    │ Files modified: 2                                │
    │   + src/theme/dark-mode.ts (new)                 │
    │   ~ src/App.tsx (modified)                       │
    │ Target: /home/user/projects/webapp (host)        │
    │ Via: bind mount sync from container workspace    │
    ╰──────────────────────────────────────────────────╯

    ✓ OK Changes applied to host filesystem
=== "Plain" ``` $ agents plan apply --yes 01J0B2C3D4E5F6G7H8J9K0L1M2 Apply Files modified: 2 + src/theme/dark-mode.ts (new) ~ src/App.tsx (modified) Target: /home/user/projects/webapp (host) Via: bind mount sync from container workspace [OK] Changes applied to host filesystem ``` ### Example 17: Explicit Container with Directory Mount !!! adr "Related ADRs" [ADR-043: Devcontainer Integration](adr/ADR-043-devcontainer-integration.md) · [ADR-039: Container Resource Types](adr/ADR-039-container-resource-types.md) **Scenario:** A team uses a custom container image (not a devcontainer) for development. The operator explicitly creates a `container-instance` resource with `--mount` to bind a local directory into the container, then sets it as the project's execution environment with `override` priority. **What this example demonstrates:** - Explicit container-instance creation via `agents resource add` with `--mount` flags - Both resource-reference and raw host-path mount styles - Project-level `execution_environment` with `priority: override` (precedence level 2) - Container started on first plan execution, no devcontainer.json needed **Step 1 — Register the code repository and container:** === "Rich" 

    $ agents resource add git-checkout local/api-repo --path /home/user/projects/api
    ✓ OK Resource registered: local/api-repo (127 children)

    $ agents resource add container-instance local/api-container \
      --mount local/api-repo:/workspace \
      --mount /home/user/.ssh:/home/dev/.ssh:ro

    ╭─ Resource ──────────────────────────────────────╮
    │ Name: local/api-container                       │
    │ ID: 01J0C3D4E5F6G7H8J9K0L1M2N3                  │
    │ Type: container-instance                        │
    │ State: created (not started)                    │
    ╰─────────────────────────────────────────────────╯

    ╭─ Mounts ──────────────────────────────────────────────────────────╮
    │ Source                    Container Path       Kind    Mode       │
    │ ────────────────────────  ──────────────────   ──────  ────       │
    │ local/api-repo            /workspace           res-ref rw         │
    │ /home/user/.ssh           /home/dev/.ssh       host    ro         │
    ╰───────────────────────────────────────────────────────────────────╯

    ✓ OK Container resource registered
=== "Plain" ``` $ agents resource add git-checkout local/api-repo --path /home/user/projects/api [OK] Resource registered: local/api-repo (127 children) $ agents resource add container-instance local/api-container \ --mount local/api-repo:/workspace \ --mount /home/user/.ssh:/home/dev/.ssh:ro Resource Name: local/api-container ID: 01J0C3D4E5F6G7H8J9K0L1M2N3 Type: container-instance State: created (not started) Mounts Source Container Path Kind Mode ------------------------ ------------------ ------ ---- local/api-repo /workspace res-ref rw /home/user/.ssh /home/dev/.ssh host ro [OK] Container resource registered ``` **Step 2 — Create project, link resources, set execution environment:** === "Rich" 

    $ agents project create local/api-project
    ✓ OK Project created

    $ agents project link-resource local/api-project local/api-repo
    ✓ OK Resource linked

    $ agents project link-resource local/api-project local/api-container
    ✓ OK Resource linked

    $ agents project context set \
      --execution-environment local/api-container \
      --execution-env-priority override \
      local/api-project

    ╭─ Context Policy Updated ──────────────────────────╮
    │ Execution Environment: local/api-container        │
    │ Priority: override (precedence level 2)           │
    │ Note: All tool invocations will route to this     │
    │       container, bypassing devcontainer detection │
    ╰───────────────────────────────────────────────────╯

    ✓ OK Context policy updated
=== "Plain" ``` $ agents project create local/api-project [OK] Project created $ agents project link-resource local/api-project local/api-repo [OK] Resource linked $ agents project link-resource local/api-project local/api-container [OK] Resource linked $ agents project context set \ --execution-environment local/api-container \ --execution-env-priority override \ local/api-project Context Policy Updated Execution Environment: local/api-container Priority: override (precedence level 2) Note: All tool invocations will route to this container, bypassing devcontainer detection [OK] Context policy updated ``` **Step 3 — Execute a plan (container started, tools routed):** === "Rich" 

    $ agents plan use local/fix-auth-bug local/api-project --automation-profile trusted

    ✓ OK Plan 01J0D4E5F6G7H8J9K0L1M2N3O4 created — strategize phase starting

    $ agents plan execute 01J0D4E5F6G7H8J9K0L1M2N3O4

    ⏳ Starting container local/api-container …
    ✓ Container ready in 3s

    ╭─ Execution Environment ───────────────────────────╮
    │ Resolved via: project override                    │
    │ Resource: local/api-container                     │
    │ Workspace: /workspace                             │
    │ Precedence: level 2 of 6                          │
    ╰───────────────────────────────────────────────────╯

    ▸ Decision 1/2: Fix token validation in src/auth/jwt.ts
      → edit_file() in container /workspace/src/auth/jwt.ts
      ✓ Checkpoint cp-001

    ▸ Decision 2/2: Run auth test suite
      → run_command() in container npm test -- --grep auth
      ✓ 12/12 tests passed
      ✓ Checkpoint cp-002

    ✓ OK Execution complete — ready for apply
=== "Plain" ``` $ agents plan use local/fix-auth-bug local/api-project --automation-profile trusted [OK] Plan 01J0D4E5F6G7H8J9K0L1M2N3O4 created — strategize phase starting $ agents plan execute 01J0D4E5F6G7H8J9K0L1M2N3O4 [WAIT] Starting container local/api-container … [OK] Container ready in 3s Execution Environment Resolved via: project override Resource: local/api-container Workspace: /workspace Precedence: level 2 of 6 Decision 1/2: Fix token validation in src/auth/jwt.ts -> edit_file() in container /workspace/src/auth/jwt.ts [OK] Checkpoint cp-001 Decision 2/2: Run auth test suite -> run_command() in container npm test -- --grep auth [OK] 12/12 tests passed [OK] Checkpoint cp-002 [OK] Execution complete — ready for apply ``` ### Example 18: Container with Remote Repo Clone !!! adr "Related ADRs" [ADR-043: Devcontainer Integration](adr/ADR-043-devcontainer-integration.md) · [ADR-039: Container Resource Types](adr/ADR-039-container-resource-types.md) **Scenario:** A CI/CD pipeline creates a container-instance that clones a remote repository on first start. There is no local checkout — the code lives entirely inside the container. This pattern is useful for cloud-based or ephemeral build environments where the operator has no local filesystem access to the repository. **What this example demonstrates:** - `--clone-into` flag on `agents resource add container-instance` - Remote repository cloned lazily on container first start - Plan-level execution environment with `fallback` priority (precedence level 4) - No local git-checkout or devcontainer involved **Step 1 — Create container resource with clone-into:** === "Rich" 

    $ agents resource add container-instance cloud/build-env \
      --clone-into https://github.com/acme/billing-api.git:/workspace

    ╭─ Resource ──────────────────────────────────────────╮
    │ Name: cloud/build-env                               │
    │ ID: 01J0E5F6G7H8J9K0L1M2N3O4P5                      │
    │ Type: container-instance                            │
    │ State: created (not started)                        │
    │ Clone: https://github.com/acme/billing-api.git      │
    │ Clone Target: /workspace                            │
    ╰─────────────────────────────────────────────────────╯

    ✓ OK Container resource registered (repo will be cloned on first start)
=== "Plain" ``` $ agents resource add container-instance cloud/build-env \ --clone-into https://github.com/acme/billing-api.git:/workspace Resource Name: cloud/build-env ID: 01J0E5F6G7H8J9K0L1M2N3O4P5 Type: container-instance State: created (not started) Clone: https://github.com/acme/billing-api.git Clone Target: /workspace [OK] Container resource registered (repo will be cloned on first start) ``` **Step 2 — Create project and link the container:** === "Rich" 

    $ agents project create cloud/billing-api
    ✓ OK Project created

    $ agents project link-resource cloud/billing-api cloud/build-env
    ✓ OK Resource linked
=== "Plain" ``` $ agents project create cloud/billing-api [OK] Project created $ agents project link-resource cloud/billing-api cloud/build-env [OK] Resource linked ``` **Step 3 — Execute plan with plan-level execution environment:** === "Rich" 

    $ agents plan use local/add-pagination cloud/billing-api \
      --execution-environment cloud/build-env \
      --execution-env-priority fallback \
      --automation-profile trusted

    ✓ OK Plan 01J0F6G7H8J9K0L1M2N3O4P5Q6 created

    $ agents plan execute 01J0F6G7H8J9K0L1M2N3O4P5Q6

    ⏳ Starting container cloud/build-env …
    ⏳ Cloning https://github.com/acme/billing-api.git into /workspace …
    ✓ Clone complete (1.2 GB, 47s)
    ✓ Container ready in 52s

    ╭─ Execution Environment ─────────────────────────────╮
    │ Resolved via: plan fallback                         │
    │ Resource: cloud/build-env                           │
    │ Workspace: /workspace                               │
    │ Precedence: level 4 of 6                            │
    │ Note: No devcontainer detected; using plan fallback │
    ╰─────────────────────────────────────────────────────╯

    ▸ Decision 1/4: Add cursor-based pagination to /workspace/src/api/invoices.ts
      → edit_file() in container
      ✓ Checkpoint cp-001

    ▸ Decision 2/4: Add pagination types to /workspace/src/types/pagination.ts
      → write_file() in container
      ✓ Checkpoint cp-002

    ▸ Decision 3/4: Update API tests
      → edit_file() in container
      ✓ Checkpoint cp-003

    ▸ Decision 4/4: Run test suite
      → run_command() in container npm test
      ✓ 89/89 tests passed
      ✓ Checkpoint cp-004

    ✓ OK Execution complete — ready for apply
=== "Plain" ``` $ agents plan use local/add-pagination cloud/billing-api \ --execution-environment cloud/build-env \ --execution-env-priority fallback \ --automation-profile trusted [OK] Plan 01J0F6G7H8J9K0L1M2N3O4P5Q6 created $ agents plan execute 01J0F6G7H8J9K0L1M2N3O4P5Q6 [WAIT] Starting container cloud/build-env … [WAIT] Cloning https://github.com/acme/billing-api.git into /workspace … [OK] Clone complete (1.2 GB, 47s) [OK] Container ready in 52s Execution Environment Resolved via: plan fallback Resource: cloud/build-env Workspace: /workspace Precedence: level 4 of 6 Note: No devcontainer detected; using plan fallback Decision 1/4: Add cursor-based pagination to /workspace/src/api/invoices.ts -> edit_file() in container [OK] Checkpoint cp-001 Decision 2/4: Add pagination types to /workspace/src/types/pagination.ts -> write_file() in container [OK] Checkpoint cp-002 Decision 3/4: Update API tests -> edit_file() in container [OK] Checkpoint cp-003 Decision 4/4: Run test suite -> run_command() in container npm test [OK] 89/89 tests passed [OK] Checkpoint cp-004 [OK] Execution complete — ready for apply ``` **Step 4 — Apply (changes committed inside container, pushed to remote):** === "Rich" 

    $ agents plan apply --yes 01J0F6G7H8J9K0L1M2N3O4P5Q6

    ╭─ Apply ──────────────────────────────────────────╮
    │ Files modified: 3                                │
    │   ~ src/api/invoices.ts (modified)               │
    │   + src/types/pagination.ts (new)                │
    │   ~ tests/api/invoices.test.ts (modified)        │
    │ Target: container /workspace                     │
    │ Apply mode: commit + push to origin/main         │
    ╰──────────────────────────────────────────────────╯

    ✓ OK Changes applied (committed as abc1234, pushed to origin/main)
=== "Plain" ``` $ agents plan apply --yes 01J0F6G7H8J9K0L1M2N3O4P5Q6 Apply Files modified: 3 ~ src/api/invoices.ts (modified) + src/types/pagination.ts (new) ~ tests/api/invoices.test.ts (modified) Target: container /workspace Apply mode: commit + push to origin/main [OK] Changes applied (committed as abc1234, pushed to origin/main) ``` ## Architecture This section provides the complete architectural blueprint for CleverAgents. It defines the system's structural composition, technology choices, layer boundaries, data flow, and operational characteristics. An implementor should be able to build the entire system from this section combined with the behavioral specification above. ### Architecture Overview !!! adr "Architecture Decision" The layered architecture, DDD boundaries, and deployment modes are defined in [ADR-001: Layered Architecture](adr/ADR-001-layered-architecture.md). CleverAgents is architected as a **layered, event-driven application** following Domain-Driven Design (DDD) principles with clean architecture boundaries. The system is organized into four primary layers — Presentation, Application, Domain, and Infrastructure — with strict dependency rules: outer layers depend on inner layers, never the reverse. Cross-cutting concerns (logging, configuration, security) are handled through dependency injection and aspect-oriented patterns. The architecture supports two deployment modes: 1. **Local Mode**: A single-process CLI application where all components run in the same Python process. The CLI is the primary entry point, the database is SQLite, and all resources are local. A2A flows over **stdio** (agent as subprocess). 2. **Server Mode**: A multi-user service where the CLI acts as a thin client communicating with a remote CleverAgents server via **A2A over HTTP** (JSON-RPC 2.0). The server hosts shared storage (PostgreSQL), namespace resolution, and remote plan execution (via LangGraph Platform RemoteGraph). Both modes share the same domain model and application layer. The infrastructure layer provides swappable implementations for each deployment target. All communication uses the **Agent-to-Agent Protocol (A2A)** standard — there is no REST API. #### High-Level Component Diagram ```kroki-plantuml @startuml skinparam componentStyle rectangle skinparam defaultFontSize 12 skinparam packageStyle frame skinparam packageFontSize 14 skinparam packageFontStyle bold skinparam componentFontSize 11 package "Presentation Layer" <> #E0F7FA { component [CLI\n(Typer)] as CLI component [TUI\n(Textual)] as TUI component [Web\n(Textual Web)] as Web component [IDE Plugin\n(Embedded TUI)] as IDE component [A2A Server\n(JSON-RPC 2.0 Endpoint)] as A2ASRV } interface "A2A\n(Agent-to-Agent Protocol)" as A2A #FFD54F note right of A2A : Local: A2A over stdio\nServer: A2A over HTTP\nJSON-RPC 2.0 wire format package "Application Layer" <> #E3F2FD { package "Service Facade" { component [PlanService] as PS component [ProjectService] as ProjS component [ActorService] as ActS component [ContextService] as CtxS component [ToolService] as ToolS component [SkillService] as SkillS component [ResourceSvc] as ResS } package "Workflow Engine" { component [PlanLifecycle] as PL component [SessionWorkflow] as SW component [CorrectionFlow] as CF component [MergeWorkflow] as MW } package "Event Bus" { component [StructuredLog] as SL component [EventEmitter] as EE component [MetricsCollector] as MC } component [DI Container\n(dependency-injector DeclarativeContainer)] as DI #D1C4E9 } package "Domain Layer" <> #F3E5F5 { package "Domain Models" { component [Plan / Decision / Project\nResource / Actor / Action\nTool / Skill / Session\nInvariant / AutomationProf\nCheckpoint / CorrectionAtmpt] as DM } package "Domain Services" { component [InvariantEnforcer\nAutonomyCtrl\nContextBuilder\nMergeResolver] as DS note bottom of DS : Repository Interfaces\n(Protocol classes) } package "Domain Events" { component [PlanCreated / PhaseChanged\nDecisionMade / ToolInvoked\nApplyCompleted / CorrectionReq] as DE } } package "Infrastructure Layer" <> #FFEBEE { package "Database" { component [SQLite / SQLAlchemy\nAlembic / UoW] as DB } package "Indexing" { component [Tantivy / FAISS\nNeo4j / Qdrant / RDFLib] as IDX } package "Sandbox" { component [GitWorktree / FsCopy\nTxnRollback / NoOp] as SBX } package "LLM / AI Runtime" { component [LangChain / LangGraph\nProviderRegistry\nRxPY Bridge / MCP SDK] as LLM } package "External Integrations" { component [MCP Servers\nAgent Skills Std\nREST/gRPC Clients] as EXT } package "LSP Runtime" { component [LSP Server Manager\nLSPToolAdapter\nLanguage Servers] as LSPR } package "File System / OS" { component [Watchdog / File I/O\nGit CLI / Subprocess\nOS Process / Signals] as FS } } CLI -[hidden]right-> TUI TUI -[hidden]right-> Web Web -[hidden]right-> IDE IDE -[hidden]right-> A2ASRV CLI -down-> A2A TUI -down-> A2A Web -down-> A2A IDE -down-> A2A A2ASRV -down-> A2A A2A -down-> PS A2A -down-> SW A2A -down-> EE PS -down-> DI DI -down-> DM DS -down-> DB DS -down-> IDX @enduml ``` #### Standards and Protocols in the Architecture !!! adr "Architecture Decision" The four protocol standards and their architectural roles are defined across [ADR-026: Agent-to-Agent Protocol (A2A)](adr/ADR-026-agent-client-protocol.md), [ADR-027: Language Server Protocol (LSP) Integration](adr/ADR-027-language-server-protocol.md), [ADR-028: Agent Skills Standard (AgentSkills.io)](adr/ADR-028-agent-skills-standard.md), and [ADR-029: Model Context Protocol (MCP) Adoption](adr/ADR-029-model-context-protocol.md). Each adopted standard maps to an explicit architectural boundary: * **A2A (Agent-to-Agent Protocol)** — the [A2A standard](https://a2a-protocol.org) (JSON-RPC 2.0) connects Presentation-layer clients (CLI, TUI, IDE) to the Application layer. Standard A2A operations handle agent messaging (`message/send`, `message/stream`), task lifecycle, and streaming updates. CleverAgents `_cleveragents/`-prefixed extension methods handle platform operations (plans, registries, context, sync). In local mode A2A flows over stdio; in server mode over HTTP. This keeps clients interchangeable and supports third-party client and agent development. * **LSP (Language Server Protocol)** — LSP servers are registered in the LSP Registry (Infrastructure layer) and bound to actor graph nodes to provide language intelligence. The `LSPToolAdapter` exposes LSP capabilities as tools (diagnostics, hover, go-to-definition, completions, references, rename) that actors call during reasoning, and the LSP Runtime automatically enriches actor context with diagnostic and type information. This gives actors the same semantic code understanding that human developers get from IDEs. See [LSP Integration](#lsp-integration). * **MCP (Model Context Protocol)** — external MCP servers reside in the Infrastructure layer. The MCPToolAdapter bridges them into first-class Tools in the Domain model with extended capability metadata. MCP tools are composed into skills and used as tool nodes in actor graphs, giving the system standardized tool discovery and invocation. * **Agent Skills ([https://AgentSkills.io](https://AgentSkills.io))** — Agent Skills are ingested into the Skill Registry and loaded by the actor runtime via progressive disclosure. Inside actor graphs they appear as tool nodes whose execution is instruction-driven — the agent follows multi-step procedures that may call MCP tools, built-ins, or other Agent Skills. This adds portable, reusable workflows that complement schema-driven MCP tools. #### A2A Integration Architecture !!! adr "Architecture Decision" The Agent-to-Agent Protocol is defined in [ADR-026: Agent-to-Agent Protocol (A2A)](adr/ADR-026-agent-client-protocol.md). The adoption of the A2A standard is defined in [ADR-047: A2A Standard Adoption](adr/ADR-047-acp-standard-adoption.md). See also [Core Concepts > Server > A2A](#agent-to-agent-protocol-a2a) for the behavioral specification. Of the four standards CleverAgents adopts, A2A has the deepest architectural integration. While MCP, Agent Skills, and LSP plug into the Infrastructure and Domain layers to provide capabilities to actors, **A2A defines the fundamental boundary between the Presentation and Application layers** — it is the protocol surface through which *every* client operation flows, in *every* deployment mode. This section provides the full architectural detail. ##### Why A2A Exists The architecture faces a structural tension: the system has multiple Presentation-layer surfaces (CLI, TUI, Web, IDE plugin) and multiple deployment modes (local, server). Without a shared contract: 1. Each client would implement its own calling convention into the Application layer. 2. Local and server modes would develop behavioral drift. 3. Third-party client development would be impractical. 4. Testing would require N x M test matrices (N clients x M modes). CleverAgents adopts the **Agent-to-Agent Protocol** standard ([a2a-protocol.org](https://a2a-protocol.org)), built on **JSON-RPC 2.0**, as the sole protocol for all client-server communication. The contract is the same whether the transport is stdio (local) or HTTP (server). This is the architectural guarantee that clients are interchangeable. ##### A2A in the Layer Diagram A2A sits at the boundary between the Presentation and Application layers. Every arrow from a Presentation-layer component to the Service Facade in the [High-Level Component Diagram](#high-level-component-diagram) represents an A2A method call: ```kroki-plantuml @startuml skinparam componentStyle rectangle skinparam defaultFontSize 11 package "Presentation Layer" #E0F7FA { component [CLI] as CLI component [TUI] as TUI component [Web] as Web component [IDE Plugin\n(Embedded TUI)] as IDE component [A2A Server Endpoint\n(JSON-RPC 2.0)] as A2ASRV } interface "A2A" as A2A_IF #FFD54F package "Application Layer" #E3F2FD { component [Service Facade\n(PlanService, ProjectService,\nActorService, ContextService,\nToolService, SkillService,\nResourceService)] as SF component [SessionWorkflow] as SW component [EventEmitter] as EE } CLI -down-> A2A_IF TUI -down-> A2A_IF Web -down-> A2A_IF IDE -down-> A2A_IF A2ASRV -down-> A2A_IF A2A_IF -down-> SF A2A_IF -down-> SW A2A_IF -down-> EE note right of A2A_IF **Local mode**: A2A over stdio **Server mode**: A2A over HTTP JSON-RPC 2.0 wire format end note @enduml ``` ##### Transport Modes The transport mechanism is the core architectural enabler that makes A2A work across deployment modes. The A2A Python SDK provides both transports: **Local Mode — A2A over stdio** ``` CLI ──stdio──→ Agent Subprocess ──→ A2aLocalFacade ──→ ServiceFacade.method() ──→ Domain / Infrastructure ``` The client spawns the agent as a subprocess. A2A JSON-RPC messages flow over stdin/stdout. Standard A2A operations (`message/send`, `message/stream`) drive the conversation. Extension methods (`_cleveragents/*`) are intercepted by `A2aLocalFacade` and routed to in-process Application-layer services. No network, no authentication — the agent runs with local user permissions. **Server Mode — A2A over HTTP** ``` CLI ──HTTP──→ CleverAgents A2A Server ──→ ServiceFacade.method() ──→ Domain / Infrastructure │ │ └── RemoteGraph.invoke() ──→ LangGraph Platform ────────┘ ``` The client connects to the CleverAgents server via the A2A SDK's HTTP transport. All methods — both standard A2A and `_cleveragents/` extensions — flow through the **single A2A JSON-RPC 2.0 endpoint**. The server delegates actor execution to LangGraph Platform via RemoteGraph. Authentication is required via HTTP auth schemes declared in the Agent Card. **External Agent Mode — Split Routing** ``` CLI ──HTTP──→ External A2A Server (standard A2A operations: message/send, message/stream, etc.) ──HTTP──→ CleverAgents Server (_cleveragents/* extension methods only) ``` When an agent is hosted on an external A2A-compatible server, the client routes standard A2A operations to that server and `_cleveragents/` extension methods to the CleverAgents server. This enables interoperability with any A2A-compliant agent. This transport architecture is enforced by: * **The same A2A test suite runs in both modes.** Contract tests validate that a given method with given parameters produces the same response shape over stdio and HTTP. * **No Presentation-layer module imports from Infrastructure.** Architecture tests (import-linter) verify this on every commit, preventing clients from bypassing A2A. * **The Service Facade is the sole entry point.** No Application-layer service is exposed directly to the Presentation layer. ##### Complete Method Routing Every A2A method routes to a specific Application-layer service method. The following tables are the authoritative mapping. **Standard A2A Operations → Service Mapping** | A2A Operation | Service Method | | :--------- | :------------- | | `initialize` | Capability negotiation — returns supported extensions, automation profiles, tool registries | | `authenticate` | Token validation against user/token store | | `session/new` | `SessionWorkflow.create()` | | `session/load` | `SessionWorkflow.resume()` | | `session/list` | `SessionWorkflow.list()` | | `session/prompt` | `SessionWorkflow.tell()` | | `session/cancel` | `PlanService.cancel()` (cancels in-progress plan execution) | | `session/set_mode` | `AutomationProfileService.switch()` | | `session/set_model` | `ProviderRegistry.switch_model()` | | `session/fork` | `SessionWorkflow.fork()` | | `session/resume` | `SessionWorkflow.resume()` | **Plan Extension Methods → Service Mapping** | A2A Extension Method | Service Method | | :------------------- | :------------- | | `_cleveragents/plan/use` | `PlanService.create_plan()` | | `_cleveragents/plan/execute` | `PlanLifecycle.execute()` | | `_cleveragents/plan/apply` | `PlanLifecycle.apply()` | | `_cleveragents/plan/cancel` | `PlanService.cancel()` | | `_cleveragents/plan/status` | `PlanService.get_status()` | | `_cleveragents/plan/tree` | `PlanService.get_tree()` | | `_cleveragents/plan/explain` | `PlanService.explain_decision()` | | `_cleveragents/plan/correct` | `CorrectionFlow.correct()` | | `_cleveragents/plan/diff` | `PlanService.get_diff()` | | `_cleveragents/plan/artifacts` | `PlanService.get_artifacts()` | | `_cleveragents/plan/prompt` | `PlanService.inject_guidance()` | | `_cleveragents/plan/rollback` | `PlanLifecycle.rollback()` | | `_cleveragents/plan/list` | `PlanService.list()` | **Registry Extension Methods → Service Mapping** (pattern applies to all entity types) | A2A Extension Method Pattern | Service Method Pattern | | :--------------------------- | :--------------------- | | `_cleveragents/registry/{entity}/list` | `{Entity}Service.list()` | | `_cleveragents/registry/{entity}/show` | `{Entity}Service.show()` | | `_cleveragents/registry/{entity}/add` | `{Entity}Service.add()` | | `_cleveragents/registry/{entity}/update` | `{Entity}Service.update()` | | `_cleveragents/registry/{entity}/remove` | `{Entity}Service.remove()` | Where `{entity}` is one of: `actor`, `skill`, `tool`, `validation`, `resource`, `resource_type`, `project`, `action`, `automation_profile`, `invariant`, `lsp`. **Context Extension Methods → Service Mapping** | A2A Extension Method | Service Method | | :------------------- | :------------- | | `_cleveragents/context/show` | `ContextService.show()` | | `_cleveragents/context/inspect` | `ContextService.inspect()` | | `_cleveragents/context/simulate` | `ContextService.simulate()` | | `_cleveragents/context/set` | `ContextService.set()` | **Sync, Namespace, and Health Extension Methods** | A2A Extension Method | Service Method | | :------------------- | :------------- | | `_cleveragents/sync/pull` | `SyncService.pull()` | | `_cleveragents/sync/push` | `SyncService.push()` | | `_cleveragents/sync/status` | `SyncService.status()` | | `_cleveragents/namespace/list` | `NamespaceService.list()` | | `_cleveragents/namespace/show` | `NamespaceService.show()` | | `_cleveragents/namespace/members` | `NamespaceService.members()` | | `_cleveragents/health/check` | Health check handler | | `_cleveragents/diagnostics/run` | Diagnostic runner | ##### Streaming Architecture A2A streaming uses **Server-Sent Events (SSE)** via `message/stream`. The server pushes `TaskStatusUpdateEvent` and `TaskArtifactUpdateEvent` to the client in real-time during long-running operations: **Event types and their CleverAgents mappings:** | Event Type | Emitted When | Payload | | :--------- | :----------- | :------ | | `TaskStatusUpdateEvent` | Agent produces response tokens, task state changes, automation profile switched | `status` (state + message with agent response Parts) | | `TaskArtifactUpdateEvent` | Tool execution results, plan artifacts generated | `artifact` (named artifact with Parts) | **Example streaming event:** ```json { "jsonrpc": "2.0", "method": "task/statusUpdate", "params": { "taskId": "task_01HXM8C2...", "status": { "state": "working" }, "message": { "role": "agent", "parts": [{ "kind": "text", "text": "Running git-diff on platform-repo..." }] } } } ``` **Causal Ordering Guarantee**: Events within a single session/plan lifecycle are delivered in causal order. A phase transition event always arrives after the preceding phase completion. In **local mode** (stdio), events flow as JSON-RPC messages over stdout. In **server mode** (HTTP), the A2A SDK manages the SSE streaming connection. Both modes deliver the same event types with the same payload shapes. ##### Authentication and Authorization Authentication follows the A2A standard Agent Card-based discovery: 1. **Agent Card discovery**: Client fetches the server's Agent Card (via `/.well-known/agent.json` or configured URL). The Agent Card declares supported capabilities, `_cleveragents` extensions, and authentication schemes. 2. **HTTP authentication**: Client authenticates using the scheme declared in the Agent Card (OAuth2, API key, Bearer token). Typically `Authorization: Bearer ` header on every request. 3. **All subsequent operations**: Authenticated. The `A2A-Version` header is sent on every request. **Local mode** (stdio): Authentication is bypassed entirely. The agent subprocess runs with the user's local permissions. **Server mode**: Every connection must discover the Agent Card and authenticate before any operation. Unauthenticated requests receive a JSON-RPC error: ```json { "jsonrpc": "2.0", "id": 1, "error": { "code": -32002, "message": "Authentication required" } } ``` **Authorization** is namespace-scoped: users can only access entities within namespaces they have been granted access to. The `local/` namespace is never accessible via server. ##### Error Taxonomy A2A uses JSON-RPC 2.0 integer error codes. Standard protocol errors use the reserved range; application-specific errors use `-32001` to `-32099`: | Error Code | Meaning | Domain Exception(s) | | :--------- | :------ | :------------------- | | `-32700` | Parse error (malformed JSON) | — | | `-32600` | Invalid request | — | | `-32601` | Method not found | `A2aOperationNotFoundError` | | `-32602` | Invalid params | `ValidationError` | | `-32603` | Internal error | Any unhandled `Exception` | | `-32001` | Entity not found | `ResourceNotFoundError` | | `-32002` | Authentication required | `AuthenticationError` | | `-32003` | Authorization forbidden | `AuthorizationError` | | `-32004` | Invalid state | `BusinessRuleViolation` | | `-32005` | Already exists | `DuplicateEntityError` | | `-32006` | Budget exceeded | `BudgetExceededError` | | `-32007` | Version mismatch | `A2aVersionMismatchError` | | `-32008` | Plan error | `PlanError` | All errors follow the JSON-RPC 2.0 error structure: `{ "code": , "message": , "data": }`. Clients should dispatch on `code` for precise error handling. ##### A2A Versioning - The JSON-RPC protocol version is always `"2.0"` (in the `jsonrpc` field) - A2A protocol version is declared in the Agent Card and sent via the `A2A-Version` HTTP header - CleverAgents extension version is declared in the Agent Card's extensions section under `_cleveragents.version` - Backward-compatible additions (new optional params, new extension methods) are permitted within a major version; breaking changes require a major version bump - Servers support the current extension version plus one prior minor version ##### A2A and the IDE Plugin The IDE plugin is an embedded TUI — essentially the same Textual-based interface used by the standalone TUI, but hosted inside an IDE environment. Like all Presentation-layer clients, it communicates with the backend exclusively through A2A. It does not access the Domain or Infrastructure layers directly — all plan operations, validation queries, and context lookups go through A2A. This means: * The IDE plugin works identically in local mode (A2A over stdio to a subprocess) and server mode (A2A over HTTP). * IDE features stay exactly aligned with CLI/TUI behavior (same A2A operations, same JSON-RPC 2.0 format). * The IDE plugin receives `TaskStatusUpdateEvent` / `TaskArtifactUpdateEvent` streaming events for real-time plan and session updates. * Extension methods (`_cleveragents/fs/*`, `_cleveragents/terminal/*`) allow the agent to interact with the IDE's workspace and integrated terminal. Note that the **Language Server Protocol (LSP)** in CleverAgents is unrelated to the IDE plugin. LSP serves an entirely different purpose: providing language intelligence to actors and agents in the Infrastructure layer. See [LSP Integration](#lsp-integration) and [ADR-027: Language Server Protocol (LSP) Integration](adr/ADR-027-language-server-protocol.md) for the full LSP architecture. #### Server and Client Architecture !!! adr "Architecture Decision" The server application architecture is defined in [ADR-048: Server Application Architecture](adr/ADR-048-server-application-architecture.md). The A2A standard adoption is defined in [ADR-047: A2A Standard Adoption](adr/ADR-047-acp-standard-adoption.md). This section defines the complete architecture of the CleverAgents server application and the client-side components that interact with it. The server is a **separate application** (distinct deployment unit) that shares the same Domain and Application layers as the client. ##### Server Application Structure The server follows the same four-layer architecture as the client (ADR-001), sharing two layers and providing its own implementations for the other two: | Layer | Client | Server | Shared? | | :---- | :----- | :----- | :------ | | **Domain** | Business rules, domain models, domain events | Same | Yes — identical package | | **Application** | Service facades, workflows, event bus | Same | Yes — identical package | | **Infrastructure** | SQLite, local sandbox, local file access, `A2aLocalFacade` | PostgreSQL, LangGraph Platform RemoteGraph, server-side sandbox, A2A SDK server | No | | **Presentation** | CLI (Typer), TUI (Textual), IDE plugin | A2A JSON-RPC 2.0 endpoint | No | The shared Domain and Application layers are consumed as a Python package dependency. This ensures zero behavioral drift between local and server modes. ```kroki-plantuml @startuml skinparam componentStyle rectangle skinparam defaultFontSize 11 package "Client Application" #E0F7FA { component [CLI / TUI / IDE Plugin] as ClientPres component [Application Layer\n(shared)] as ClientApp component [Domain Layer\n(shared)] as ClientDom component [Infrastructure\n(SQLite, local sandbox,\nA2aLocalFacade)] as ClientInfra } package "Server Application" #FFEBEE { component [A2A JSON-RPC 2.0\nEndpoint] as ServerPres component [Application Layer\n(shared)] as ServerApp component [Domain Layer\n(shared)] as ServerDom component [Infrastructure\n(PostgreSQL, RemoteGraph,\nA2A SDK server)] as ServerInfra } component [LangGraph\nPlatform] as LGP #FFF9C4 ClientPres -down-> ClientApp ClientApp -down-> ClientDom ClientDom -down-> ClientInfra ServerPres -down-> ServerApp ServerApp -down-> ServerDom ServerDom -down-> ServerInfra ServerInfra -right-> LGP : RemoteGraph ClientPres -right[hidden]-> ServerPres note bottom of ClientApp : Same Python package note bottom of ServerApp : Same Python package @enduml ``` ##### Server Presentation Layer The server's sole client-facing interface is an **A2A JSON-RPC 2.0 endpoint** implemented using the A2A Python SDK's server-side connection handler. There is no REST API, no GraphQL, no separate admin endpoint. The endpoint handles three categories of messages: 1. **Standard A2A operations** (`message/send`, `message/stream`): Routed to `SessionWorkflow` and actor execution (via LangGraph Platform RemoteGraph); Agent Card served at discovery endpoint 2. **Extension methods** (`_cleveragents/*`): Routed to Application-layer services (PlanService, RegistryServices, SyncService, NamespaceService, etc.) 3. **Multi-turn interactions to clients** (Task `input-required` state, `_cleveragents/fs/*`, `_cleveragents/terminal/*`): Forwarded from executing actors back to the connected client — enabling server-hosted agents to access client-local resources ##### Server Infrastructure: LangGraph Platform Actor graphs (StateGraphs defined in YAML) are **deployed to LangGraph Platform** as separate deployments. The server invokes them via **RemoteGraph**: ```kroki-mermaid sequenceDiagram participant C as Client participant S as A2A Server participant SW as SessionWorkflow participant RG as RemoteGraph participant LG as LangGraph Platform C->>S: message/send {"message": {"role": "user", "parts": [{"text": "Add pagination"}]}} S->>SW: tell("Add pagination") SW->>RG: invoke(strategy_actor, state) RG->>LG: Execute strategy actor graph LG-->>RG: Strategy result (plan entries) RG-->>SW: Plan with decisions SW-->>S: TaskStatusUpdateEvent (plan notification) S-->>C: TaskStatusUpdateEvent (streaming) SW->>RG: invoke(execution_actor, state) RG->>LG: Execute execution actor graph LG-->>RG: Execution result RG-->>SW: Completed execution SW-->>S: TaskArtifactUpdateEvent (tool_call results) S-->>C: TaskArtifactUpdateEvent (streaming) ``` Different actors for different plan phases (strategy, execution, estimation) each deploy as **separate RemoteGraphs**, enabling independent scaling without limiting plan capabilities. The `SessionWorkflow` orchestrates them the same way it orchestrates local actor graphs, but through the RemoteGraph interface. ##### Server Infrastructure: Persistence | Component | Technology | Notes | | :-------- | :--------- | :---- | | Database | PostgreSQL via SQLAlchemy | Same ORM as client (SQLite), different dialect | | Migrations | Alembic | Schema migrations for server-specific tables (users, tokens, namespace ACLs) | | Session store | PostgreSQL | Multi-user session persistence with namespace isolation | | Plan store | PostgreSQL | Plan lifecycle records, decision trees, artifacts | Server-specific tables (authentication, namespace ACLs, user management) are additive — they extend the shared schema without modifying it. ##### Server Security Architecture **Authentication**: Uses HTTP auth schemes declared in the server's Agent Card (OAuth2, API key, Bearer token). Tokens are validated against the server's user/token store. HTTP transport carries `Authorization: Bearer ` header on every request. **Authorization**: Namespace-scoped. Users can only access entities in namespaces they have been granted access to. The `local/` namespace is never accessible via server. **Transport security**: HTTPS required for all production deployments (TLS termination at Kubernetes ingress). ##### Client-Side Architecture The client uses an `A2aClient` that wraps the A2A Python SDK and routes method calls through a `TransportSelector`: ```python # Conceptual client architecture (not literal implementation) class TransportSelector: """Selects transport based on configuration.""" def get_transport(self) -> A2aTransport: if config.server_url: return A2aRemoteTransport(url=config.server_url, token=config.server_token) else: return A2aStdioTransport(agent_command=["cleveragents", "agent", "serve"]) class A2aClient: """Unified client for all A2A communication.""" def __init__(self, transport: A2aTransport): self.connection = A2AClient(transport) async def send_message(self, task_id: str, message: str) -> AsyncIterator[Event]: """Send a message and stream task events.""" return await self.connection.send_message(Message( role="user", parts=[TextPart(text=message)], ), task_id=task_id) async def plan_status(self, plan_id: str) -> dict: """Get plan status via extension method.""" return await self.connection.request("_cleveragents/plan/status", { "plan_id": plan_id, }) ``` **Evolution of existing source code:** | Current Component | Becomes | Notes | | :---------------- | :------ | :---- | | `A2aLocalFacade` | **Retained** | Handles `_cleveragents/` dispatch to in-process services; adapts A2A message/send to local workflows | | `A2aClient` | **Wraps** A2A SDK `A2AClient` | SDK provides production transport for both stdio and HTTP | | `A2aEvent` | **Mapped** to `TaskStatusUpdateEvent` / `TaskArtifactUpdateEvent` | Event types map to A2A streaming event types | | `A2aEventQueue` | **Retained** for local mode | Delivers events as in-process streaming events | ##### Local/Server Interchangeability The transport selector pattern ensures that application code is transport-agnostic. A CLI command works identically regardless of whether the backend is local or remote: ```python # CLI command — identical in local and server mode async def plan_status_command(plan_id: str): client = get_a2a_client() # TransportSelector picks stdio or HTTP result = await client.plan_status(plan_id) render_plan_status(result) ``` The only difference is where computation happens: | Aspect | Local Mode | Server Mode | | :----- | :--------- | :---------- | | Transport | A2A over stdio | A2A over HTTP | | Actor execution | In-process LangGraph | LangGraph Platform RemoteGraph | | Database | SQLite | PostgreSQL | | Authentication | Bypassed | HTTP auth (Agent Card scheme) + Bearer token | | File/terminal access | Direct | Via A2A multi-turn interactions (server → client) | | Namespace resolution | `local/` only | `local/` + server namespaces | ##### Server Deployment | Component | Technology | Notes | | :-------- | :--------- | :---- | | Container | Docker | Server packaged as container image | | Orchestration | Kubernetes | Production deployment target | | Configuration | Helm chart (`k8s/`) | Configurable replicas, resource limits, ingress | | Ingress | Kubernetes Ingress | TLS termination, routing to A2A endpoint | | Database | PostgreSQL (managed or self-hosted) | External to the application container | | LangGraph Platform | Managed or self-hosted | External service for graph execution | | Caching | Redis (optional) | Multi-instance session affinity, rate limiting | #### Architectural Principles 1. **Hexagonal Architecture (Ports and Adapters)**: The domain layer defines abstract repository interfaces (ports). The infrastructure layer provides concrete implementations (adapters). This allows swapping SQLite for PostgreSQL, FAISS for Qdrant, or local execution for remote server execution without touching domain logic. 2. **Command Query Responsibility Segregation (CQRS)**: Write operations (plan creation, decision recording, resource modification) flow through command handlers that enforce invariants and emit domain events. Read operations (plan status, decision tree visualization, context queries) use optimized read paths that may bypass the ORM for performance. 3. **Event-Driven Architecture**: All significant state changes emit domain events through a structured event bus. Events flow through RxPY reactive streams for real-time processing and through the structured logging pipeline for persistence. This enables decoupled observability, audit logging, and future webhook/notification systems. 4. **Dependency Injection**: All service dependencies are wired through a `DeclarativeContainer` (from the `dependency-injector` library). This eliminates hidden coupling, enables testing with mock implementations, and supports runtime reconfiguration (e.g., switching providers). 5. **Convention over Configuration**: Default behavior requires zero configuration. For entity registration commands, YAML configuration files are the complete definition (no CLI overrides). For runtime commands (e.g., `plan use`), CLI flags may override entity defaults. Environment variables can be interpolated into configuration files via `${ENV_VAR}` syntax. The resolution chain depends on context: entity registration uses config-file-only semantics, while runtime commands support per-invocation CLI overrides of entity defaults. #### Data Flow: Plan Lifecycle The following diagram traces data flow through the system during a complete plan lifecycle: ```kroki-mermaid sequenceDiagram participant U as User participant C as CLI participant A as Application participant D as Domain participant I as Infrastructure U->>C: plan use C->>A: PlanService.create_plan() A->>D: Plan(phase=strategize) D->>I: PlanRepository.save(plan) A->>D: InvariantEnforcer.reconcile() A->>D: AutonomyCtrl.should_proceed rect rgb(200, 230, 255) Note over A,D: Strategize Phase (if auto) A->>D: StrategyActor.invoke() D->>I: LangGraph StateGraph.invoke D->>I: ContextBuilder.build_hot_ctx() I-->>D: [FAISS/Tantivy results] D->>I: LLM Provider.generate() I-->>D: [LLM response] D-->>A: Decision[] D->>I: DecisionRepo.save_batch() end rect rgb(255, 230, 200) Note over A,D: Execute Phase A->>D: SandboxManager.create() D->>I: GitWorktree.create_worktree() A->>D: ExecutionActor.invoke(sandbox) D->>I: Tool calls via SkillRegistry D-->>A: ChangeSet end rect rgb(200, 255, 200) Note over A,D: Apply Phase A->>D: Validation.run_all() D->>I: Subprocess.run(commands) A->>D: SandboxManager.commit() D->>I: git merge end C-->>U: OK Applied ``` ### Technical Stack !!! adr "Architecture Decision" The technology selections, version constraints, and rationale are defined in [ADR-005: Technical Stack](adr/ADR-005-technical-stack.md). This section enumerates every technology choice in the CleverAgents stack, organized by functional area. Version constraints are minimum versions; newer compatible versions are acceptable. #### Core Runtime | Technology | Version | Role | Rationale | |---|---|---|---| | **Python** | >= 3.13 | Primary language | Type hint maturity, async/await, pattern matching, performance improvements in 3.13. The entire codebase is Python-only for consistency and LLM ecosystem alignment. | | **Hatchling** | >= 1.21.0 | PEP 517 build backend | Lightweight, standards-compliant build system. Produces wheels and sdists without complex configuration. | | **uv** | >= 0.8.0 | Package installer and resolver | 10-100x faster than pip. Used in CI, Docker builds, and Nox sessions for dependency installation. Drop-in replacement for pip with full PEP 723 support. | #### CLI and Presentation | Technology | Version | Role | Rationale | |---|---|---|---| | **Typer** | >= 0.9.0 | CLI framework | Built on Click with automatic help generation, type inference from Python type hints, and Rich integration for styled output. Supports nested command groups matching the `agents ` pattern. | | **Rich** | (transitive via Typer) | Terminal rendering | Provides Panel, Table, Tree, Syntax, Progress, Spinner, and Markdown rendering used by all output formats except `plain` and structured (`json`/`yaml`). | | **Textual** | (future) | TUI framework | Built by the Rich maintainers. Provides a reactive terminal UI framework that can be served as a web app via Textual Web, enabling the "single UI codebase" strategy for TUI, Web, and IDE plugin. | #### LLM and AI Runtime | Technology | Version | Role | Rationale | |---|---|---|---| | **LangChain** | >= 0.2.14 | LLM abstraction layer | Provider-agnostic interface for chat models, embeddings, output parsing, prompt templates, and tool calling. The `BaseLanguageModel` protocol enables swapping providers without changing application code. | | **LangGraph** | (transitive) | Stateful workflow orchestration | `StateGraph` with conditional edges, checkpointing (`MemorySaver`), and streaming execution. Used for the plan generation graph (`load_context -> analyze -> generate -> validate`) and auto-debug graph. | | **LangChain Provider Packages** | varies | LLM provider integrations | `langchain-openai` (>= 0.2.0), `langchain-google-genai` (>= 0.2.0), `langchain-anthropic`, `langchain-groq`, `langchain-together`, `langchain-cohere`. Each provides a `ChatModel` implementation. | | **LangChain Community** | >= 0.2.14 | Community integrations | FAISS vector store, FakeListLLM/FakeEmbeddings for testing. | | **RxPY** | >= 3.2.0 | Reactive stream processing | `Subject`, `BehaviorSubject`, `ReplaySubject`, and operators (`map`, `filter`, `flat_map`, `debounce`, `throttle`, `scan`) for real-time event routing between actors, stream-to-graph bridging, and backpressure management. | | **MCP SDK** | >= 1.4.0 | Model Context Protocol | Client SDK for communicating with MCP servers. Enables CleverAgents to discover and invoke tools exposed by any MCP-compliant server. | #### Data and Persistence | Technology | Version | Role | Rationale | |---|---|---|---| | **SQLite** | (system) | Primary database | Zero-configuration, file-based, ACID-compliant. Sufficient for local mode; supports WAL mode for concurrent reads during plan execution. For server mode, the infrastructure layer swaps in PostgreSQL via the same SQLAlchemy interface. | | **SQLAlchemy** | (transitive via Alembic) | ORM and database abstraction | Declarative model mapping, session management, Unit of Work pattern, and dialect abstraction enabling database portability. | | **Alembic** | >= 1.13.1 | Database migrations | Version-controlled schema migrations with upgrade/downgrade support. Migrations are auto-applied on first run and during `agents init`. | | **python-ulid** | >= 2.7.0 | ID generation | ULID generation for plans, decisions, resources, and correction attempts. ULIDs are lexicographically sortable by creation time, enabling efficient time-range queries without separate timestamp indexes. | #### Indexing and Code Intelligence | Technology | Version | Role | Rationale | |---|---|---|---| | **Tantivy** (via tantivy-py) | configurable | Full-text search | Rust-based search engine providing sub-millisecond full-text search across project resources. Used for keyword-based code search during context building. Alternative: SQLite FTS5 for zero-dependency installations. | | **FAISS** (faiss-cpu) | >= 1.7.4 | Vector similarity search | Facebook AI Similarity Search for semantic code search. Indexes embedding vectors generated from project files. Supports approximate nearest neighbor search for fast retrieval during context building. | | **Qdrant** | configurable | Vector search (alternative) | External vector database for production deployments requiring horizontal scaling, persistence, and filtering. Connected via `qdrant-client`. | | **Neo4j** | configurable | Knowledge graph | Graph database for structural code relationships (class hierarchies, call graphs, dependency trees). Enables queries like "find all callers of function X" during Strategize. Alternative: `rdflib` for in-process graph queries. | | **rdflib** | >= 7.1.4 | In-process graph store | Python RDF library for lightweight structural code analysis without external dependencies. Stores RDF triples representing code relationships. | | **OpenAI Embeddings** | configurable | Vector generation | Default embedding provider (`text-embedding-3-small`). Alternative providers: Anthropic, local sentence-transformers models via `index.embedding.provider` config. | #### Configuration and Validation | Technology | Version | Role | Rationale | |---|---|---|---| | **Pydantic** | >= 2.7.0 | Data validation and modeling | All domain models, configuration objects, and API schemas use Pydantic v2 for runtime validation, JSON Schema generation, and serialization. Provides type-safe data boundaries between layers. | | **Pydantic Settings** | >= 2.11.0 | Environment configuration | `BaseSettings` subclasses for environment variable loading with the `CLEVERAGENTS_` prefix, `.env` file support, and nested model resolution. Implements the four-tier configuration resolution chain. | | **Jinja2** | >= 3.1.0 | Template rendering | Used for actor system prompts, YAML configuration interpolation, and prompt template rendering. Supports `{{ context.* }}` variable expansion with sandboxed execution. | | **TOML** | (stdlib tomllib) | Configuration file format | Global configuration uses TOML for its native support of nested tables, which maps naturally to the dot-separated hierarchical key structure. Python 3.13 includes `tomllib` in stdlib. | | **YAML** | (via PyYAML) | Entity configuration format | All entity definitions (actors, skills, tools, actions, resource types, automation profiles) use YAML as the canonical human-authored format. JSON is accepted as valid YAML. | #### Testing | Technology | Version | Role | Rationale | |---|---|---|---| | **Behave** | >= 1.2.6 | BDD feature tests | Gherkin `.feature` files describe behavioral scenarios in natural language. Step implementations exercise the full application stack. Custom `behave-parallel` runner enables parallel execution via `ProcessPoolExecutor`. | | **Robot Framework** | >= 7.3.2 | Integration tests | Keyword-driven integration tests for end-to-end CLI workflows. `robotframework-pabot` enables parallel suite execution. | | **pytest** | >= 8.0.0 | Unit tests | Standard Python test framework for unit-level testing with fixtures, parametrization, and plugin support. | | **pytest-asyncio** | >= 0.23.0 | Async test support | Enables `async def test_*` functions for testing async LangGraph workflows and RxPY stream operations. | | **pytest-cov / coverage** | >= 7.11.0 | Coverage reporting | Target: 85% line coverage. HTML and XML reports generated by Nox sessions. Coverage gates enforce minimum thresholds in CI. | | **Hypothesis** | >= 6.136.6 | Property-based testing | Generates randomized test inputs for invariant verification, particularly useful for testing decision tree operations, merge strategies, and context tier boundaries. | | **ASV (Airspeed Velocity)** | >= 0.6.5 | Performance benchmarks | Tracks plan generation latency, CLI startup time, and indexing throughput across commits. Prevents performance regressions. | #### Code Quality | Technology | Version | Role | Rationale | |---|---|---|---| | **Ruff** | >= 0.1.0 | Linting and formatting | Single tool replacing Black, Flake8, isort, and pyupgrade. Rules: E, F, W, B, UP, I, SIM, RUF. Line length: 88. Double quotes. 4-space indent. | | **Pyright** | >= 1.1.350 | Static type checking | Strict mode type checking for the entire codebase. Catches type errors at development time rather than runtime. Configured via `pyrightconfig.json`. | #### Infrastructure and Deployment | Technology | Version | Role | Rationale | |---|---|---|---| | **Docker** | multi-stage | Containerization | Production image uses `python:3.13-slim` with multi-stage build. Non-root user (`appuser`, uid 1000). Entrypoint: `python -m cleveragents`. | | **Helm** | (chart) | Kubernetes deployment | Helm chart in `k8s/` directory for server mode deployment. Linted and template-tested in CI. | | **Nox** | >= 2025.4.22 | Task automation | Session-based task runner for lint, test, build, docs, benchmarks, and coverage. Uses `uv` as the virtual environment backend for fast session creation. | | **Forgejo CI** | (workflow) | Continuous integration | Self-hosted Forgejo instance with GitHub Actions-compatible workflow syntax. Pipeline: lint -> typecheck -> behave (matrix 3.11/3.12/3.13) -> build -> docker -> helm. | | **devcontainer CLI** | (optional) | Devcontainer management | Used for building and managing `devcontainer-instance` resources from `.devcontainer/devcontainer.json` configurations. Falls back to direct Docker/Podman CLI when not installed, with reduced feature support (e.g., devcontainer features may not be available). See [ADR-043](adr/ADR-043-devcontainer-integration.md). | #### Monitoring and Observability | Technology | Version | Role | Rationale | |---|---|---|---| | **structlog** | >= 24.4.0 | Structured logging | JSON-structured log output with context binding (plan_id, decision_id, actor_name, tool_name). Enables log aggregation, filtering, and correlation across complex plan hierarchies. | | **LangSmith** | (optional) | LLM observability | Optional integration for tracing LLM calls, token usage, latency, and cost. Configured via `CLEVERAGENTS_LANGSMITH_*` environment variables. Syncs to `LANGCHAIN_TRACING_V2`. | #### Additional Libraries | Technology | Version | Role | Rationale | |---|---|---|---| | **dependency-injector** | >= 4.41.0 | DI container | `DeclarativeContainer` with `Singleton`, `Factory`, and `Configuration` providers. Wires all services, repositories, and infrastructure components. | | **watchdog** | >= 4.0.0 | File system monitoring | Watches project resource directories for changes. Triggers automatic re-indexing when `index.auto-reindex` is enabled. | | **numpy** | >= 2.1.0 | Numerical computing | Vector operations for embedding similarity computation, confidence score aggregation, and distance calculations in the vector store layer. | | **uvicorn** | >= 0.30.1 | ASGI server | HTTP server for server mode A2A endpoint. Hosts the A2A JSON-RPC 2.0 server for remote plan execution, namespace resolution, and multi-user collaboration. | ### Dependency Injection !!! adr "Architecture Decision" The DI container design, wiring pattern, and testing strategy are defined in [ADR-003: Dependency Injection](adr/ADR-003-dependency-injection.md). All service dependencies in CleverAgents are wired through a **`DeclarativeContainer`** from the `dependency-injector` library (>= 4.41.0). This container is the single **composition root** for the entire application. No service instantiates its own dependencies — all are received through constructor injection managed by the container. #### Container Structure The DI container is a `DeclarativeContainer` subclass that declares all providers: - **`Singleton` providers** for long-lived services: database engine, repository implementations, event bus, index backends, provider registry. - **`Factory` providers** for per-request or per-operation objects: sandbox instances, plan execution contexts, LangGraph state graphs. - **`Configuration` provider** for loading and exposing the global TOML configuration and environment variables. #### Wiring Pattern The wiring pattern enforces the layered architecture (see Architecture Overview) by ensuring that dependencies always flow inward: 1. The **Domain Layer** defines repository interfaces as `Protocol` classes (e.g., `PlanRepository`, `DecisionRepository`, `ResourceRepository`). 2. The **Infrastructure Layer** provides concrete implementations (e.g., `SQLAlchemyPlanRepository`, `SQLAlchemyDecisionRepository`). 3. The **DI container** maps protocols to implementations using `Singleton` or `Factory` providers. 4. **Application Layer** services declare their dependencies as constructor parameters typed to the domain protocols. 5. The container **auto-wires** these dependencies at application startup. This pattern ensures that domain and application code never imports infrastructure modules directly. Swapping backends (e.g., SQLite → PostgreSQL, FAISS → Qdrant, local execution → remote server) requires only changing the container provider mapping — no application or domain code changes. #### Provider Types | Provider Type | Use Case | Example | |---|---|---| | `Singleton` | Shared stateful services | Database session factory, event bus, index backends | | `Factory` | Per-use transient objects | Sandbox instances, execution contexts | | `Configuration` | External configuration values | TOML config keys, environment variables | #### Testing Support In test configurations, the container is reconfigured to supply mock or fake implementations: - `FakeListLLM` / `FakeEmbeddings` from LangChain Community replace real LLM providers. - In-memory repositories replace SQLAlchemy-backed repositories. - No-op sandbox strategies replace git worktree or filesystem copy strategies. The container's `override()` context manager allows swapping providers for individual test cases without affecting the global configuration. #### Container Rules 1. **All cross-layer dependencies must flow through the DI container.** Direct instantiation of infrastructure components in application or domain code is prohibited. 2. **The container is initialized exactly once** at application startup (in the CLI entry point or server bootstrap). It must not be re-initialized during request handling. 3. **Domain Layer code must never import or reference the `dependency-injector` library.** Domain protocols are plain Python `Protocol` classes with no DI framework annotations. 4. **Every new service or repository must be registered in the container before use.** Unregistered dependencies cause explicit startup failures, not silent runtime errors. 5. **A startup self-test** verifies that all declared providers can be resolved without errors. This runs as part of the application bootstrap and in CI. ### Data Validation !!! adr "Architecture Decision" The data validation strategy, Pydantic usage, and schema generation approach are defined in [ADR-004: Data Validation](adr/ADR-004-data-validation.md). CleverAgents processes data from multiple untrusted or semi-trusted sources: user CLI input, YAML configuration files, LLM-generated tool call arguments, MCP server responses, environment variables, and database records. Every boundary crossing — between layers, between the system and external services, between the user and the application — is an opportunity for invalid data to enter the system and cause subtle downstream failures. All domain models, configuration objects, and API schemas use **Pydantic V2** (>= 2.7.0) for runtime data validation, JSON Schema generation, and serialization. **Pydantic Settings** (>= 2.11.0) extends this to environment variable loading. Pydantic serves as the **type-safe data boundary between all layers**. #### Domain Models Every domain entity — Plan, Decision, Action, Resource, Actor, Tool, Skill, Session, Invariant, AutomationProfile, Checkpoint, CorrectionAttempt — is a Pydantic model subclass. Domain entities that share the canonical configuration (`str_strip_whitespace`, `validate_assignment`, `arbitrary_types_allowed=False`, `populate_by_name`, `use_enum_values`) inherit from the shared `DomainBaseModel` base class (defined in `domain/models/base.py`) rather than directly from `pydantic.BaseModel`. Classes with genuinely different configuration requirements may still subclass `BaseModel` directly. Fields use Python type annotations with Pydantic field validators for business rule enforcement. #### Configuration Objects YAML entity configuration files (actors, skills, tools, actions, resource types, automation profiles, context views) are parsed into Pydantic models. Validation errors are reported with field paths and human-readable messages before any processing occurs. A partially valid configuration must never be applied — YAML files must validate completely before any side effects occur. #### Environment and Global Configuration `BaseSettings` subclasses from Pydantic Settings handle environment variable loading with the `CLEVERAGENTS_` prefix, `.env` file support, and nested model resolution. This implements the four-tier configuration resolution chain: CLI flag > environment variable > project-scoped config > global config file > built-in default. #### JSON Schema Generation Pydantic models automatically generate JSON Schema definitions, which are used for: - **Tool input/output schema definitions** consumed by LLM tool-calling protocols. - **Validation of LLM-generated tool call arguments** before execution. - **API request/response schema documentation.** JSON Schema generated from Pydantic models is the canonical schema for tool definitions. Manual schema definitions must not diverge from the model. #### Serialization Pydantic handles serialization to and from JSON, YAML (via dict intermediary), and database column types. Custom serializers are defined for domain-specific types (ULIDs, datetime formats, enum values). #### Data Validation Rules 1. **All data crossing a layer boundary must pass through a Pydantic model.** Raw dictionaries or untyped data structures must not propagate between layers. 2. **Strict mode** is used where appropriate to prevent implicit type coercion (e.g., strings silently becoming integers). 3. **Validation error messages** must include the field path and a human-readable explanation suitable for CLI display. 4. **Pyright in strict mode** verifies that Pydantic model field types are consistent across the codebase. 5. **Schema drift tests** verify that JSON Schema generated from Pydantic tool models matches the schemas expected by MCP and LangChain tool-calling protocols. ### ACMS (Advanced Context Management System) !!! adr "Architecture Decision" The ACMS architecture, UKO layer, CRP protocol, and context strategy framework are defined in [ADR-014: Context Management (ACMS)](adr/ADR-014-context-management-acms.md). This section provides the complete architectural design of the Advanced Context Management System (ACMS). For the conceptual overview, core data types, CRP skill definition, strategy protocol, and plan lifecycle integration, see **Core Concepts > Advanced Context Management System (ACMS)**. #### Architectural Overview ```kroki-plantuml @startuml skinparam componentStyle rectangle skinparam defaultFontSize 12 skinparam packageFontSize 13 skinparam packageFontStyle bold skinparam componentFontSize 11 package "Actor / Skill" as actor #E0F7FA { component [Issues ContextRequests\nvia Context Request Protocol] as CRP } package "Context Assembly Pipeline\n(10-component pluggable)" as pipeline #C8E6C9 { package "Phase 1: Strategy Orchestration" { component [StrategySelector] as SS component [BudgetAllocator] as BA component [StrategyExecutor] as SE } package "Phase 2: Fragment Fusion" { component [Deduplicator → DepthResolver\n→ Scorer → Packer → Orderer] as Fusion } package "Phase 3: Finalization" { component [PreambleGenerator\nSkeletonCompressor] as Final } } package "Strategies" as strats #E8EAF6 { component [ARCE\n(graph-aware)] as S1 component [Simple\n(keyword/embed)] as S2 component [Breadth/Depth\nNavigator] as S3 component [Custom\n(user-defined)] as S4 } package "Backend Abstraction Layer (BAL)" as bal #FFF9C4 { component [ScopedView\n(Text DB)] as TV component [ScopedView\n(Vector DB)] as VV component [ScopedView\n(Graph DB)] as GV } package "Physical Data Stores" as stores #E3F2FD { component [Tantivy /\nSQLite FTS] as TDB component [FAISS /\nQdrant / Weaviate] as VDB component [Blazegraph / Jena /\nNeo4j / Stardog\n(UKO triples)] as GDB } package "Resource Registry" as rr #F3E5F5 { component [Physical/virtual resources\nDAG links] as RR } CRP -down-> SS SS -down-> BA BA -down-> SE SE -down-> S1 SE -down-> S2 SE -down-> S3 SE -down-> S4 S1 -down-> TV S1 -down-> VV S1 -down-> GV S2 -down-> TV S2 -down-> VV S3 -down-> GV S4 -down-> TV SE -right[hidden]-> Fusion Fusion -right[hidden]-> Final TV -down-> TDB VV -down-> VDB GV -down-> GDB TDB -down-> RR VDB -down-> RR GDB -down-> RR @enduml ``` **Key Design Principles:** 1. **Strategy-agnostic framework**: The framework itself has no opinion about *how* context is assembled. That is the job of strategies. The framework provides the request protocol, the data plumbing, and the Context Assembly Pipeline. 2. **Dynamic budget**: The token budget for context assembly may change on every invocation. Strategies receive the current budget and must respect it. The pipeline's BudgetPacker enforces the budget as a hard ceiling. 3. **Hierarchical by default**: Every context assembly occurs within the context of a plan hierarchy. The system tracks parent context and provides progressive focusing primitives. 4. **Provenance everywhere**: Every piece of context delivered to an actor can be traced back to a specific resource, a specific location within that resource, a specific revision, and a specific UKO node. 5. **Pluggable Architecture**: Every component can be extended or replaced. 6. **Progressive Enhancement**: System works with basic text search, enhances with advanced features. 7. **Eager Indexing**: Indices are built immediately when resources are added and kept continuously up-to-date. 8. **Agent Awareness**: Agents understand available indices through skills. 9. **Real-time Synchronization**: Indices update immediately as code changes. #### Universal Knowledge Ontology (UKO) ##### Design Philosophy The UKO is designed around a single principle: **everything that an actor might want to know about a resource should be representable as a node in the knowledge graph, at any level of detail, with provenance back to the originating resource.** The ontology uses an inheritance hierarchy so that: - **Layer 0** defines universal concepts that apply to any information (code, docs, data, infra). DetailDepth is defined here as a non-negative integer with domain-agnostic semantics: depth 0 is the most minimal representation (just a name/identifier), and each increment reveals progressively more structure, content, and relationships. There is no fixed upper bound — the maximum meaningful depth depends on the domain. - **Layer 1** specializes for domain-specific concepts: general software (`uko-code:` — modules, callables, types), documents (`uko-doc:` — sections, paragraphs, citations), data schemas (`uko-data:` — tables, columns, constraints), and infrastructure (`uko-infra:` — services, endpoints, config). Each domain registers a DetailLevelMap that assigns named labels to specific integer depths (e.g., `uko-code:` maps `MODULE_LISTING` → 0, `SIGNATURES` → 4, `FULL_SOURCE` → 9). - **Layer 2** specializes for paradigm/format-specific concepts within a domain: object-oriented (`uko-oo:`), functional (`uko-func:`), procedural (`uko-proc:`) for code. Future extensions could add academic vs. technical for documents, or relational vs. graph for databases. Each paradigm extends its parent domain's DetailLevelMap, potentially inserting new named levels between existing ones (which shifts subsequent integer assignments). - **Layer 3** specializes for technology-specific concepts: Python (`uko-py:`), TypeScript (`uko-ts:`), Rust (`uko-rs:`), Java (`uko-java:`), and potentially Markdown, PostgreSQL, or others. Language/technology-specific DetailLevelMap extensions are added only when they provide meaningful additional semantics beyond the paradigm level. This layering means a strategy that operates at Layer 0 can work with *any* resource — code, documents, databases, infrastructure — while a strategy that operates at Layer 3 can provide language-specific or technology-specific intelligence. The `breadth-depth-navigator` strategy typically operates at Layers 0-1 (universal graph traversal), while `arce` leverages all layers. DetailDepth resolution follows the DetailLevelMap inheritance chain: when a named level is requested, the system looks up the name in the most specific map available for the target UKO node type (e.g., `uko-py:` first), then walks up to the parent map (`uko-oo:` → `uko-code:` → `uko:`) until a match is found. When a raw integer is specified, it is used directly. ##### Ontology Hierarchy The UKO defines five namespace prefixes: | Prefix | IRI | Purpose | |--------|-----|---------| | `uko:` | `https://cleveragents.ai/ontology/uko#` | Layer 0: Universal foundation | | `uko-code:` | `https://cleveragents.ai/ontology/uko/code#` | Layer 1: General software | | `uko-oo:` | `https://cleveragents.ai/ontology/uko/oo#` | Layer 2: Object-oriented paradigm | | `uko-func:` | `https://cleveragents.ai/ontology/uko/func#` | Layer 2: Functional paradigm | | `uko-proc:` | `https://cleveragents.ai/ontology/uko/proc#` | Layer 2: Procedural paradigm | | `uko-py:` | `https://cleveragents.ai/ontology/uko/py#` | Layer 3: Python-specific | | `uko-ts:` | `https://cleveragents.ai/ontology/uko/ts#` | Layer 3: TypeScript-specific | | `uko-rs:` | `https://cleveragents.ai/ontology/uko/rs#` | Layer 3: Rust-specific | | `uko-java:` | `https://cleveragents.ai/ontology/uko/java#` | Layer 3: Java-specific | | `uko-doc:` | `https://cleveragents.ai/ontology/uko/doc#` | Layer 1: Documents | | `uko-data:` | `https://cleveragents.ai/ontology/uko/data#` | Layer 1: Data schemas | | `uko-infra:` | `https://cleveragents.ai/ontology/uko/infra#` | Layer 1: Infrastructure | ###### Layer 0: Universal Foundation (`uko:`) Every UKO node, regardless of domain, is one of five base classes: 
@prefix uko: <https://cleveragents.ai/ontology/uko#> .
@prefix owl: <http://www.w3.org/2002/07/owl#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .

# ── Base Classes ──────────────────────────────────────────────────
uko:InformationUnit a owl:Class ;
    rdfs:comment "The root of every UKO node. Anything that can appear in an actor's context." .

uko:Container a owl:Class ;
    rdfs:subClassOf uko:InformationUnit ;
    rdfs:comment "An information unit that contains other information units (file, module, class, section)." .

uko:Atom a owl:Class ;
    rdfs:subClassOf uko:InformationUnit ;
    rdfs:comment "A leaf-level information unit (function body, paragraph, config value)." .

uko:Annotation a owl:Class ;
    rdfs:subClassOf uko:InformationUnit ;
    rdfs:comment "Metadata attached to another information unit (comment, docstring, attribute)." .

uko:Boundary a owl:Class ;
    rdfs:subClassOf uko:InformationUnit ;
    rdfs:comment "An interface point between containers (export, API endpoint, public method signature)." .

# ── Core Relationships ────────────────────────────────────────────
uko:contains a owl:ObjectProperty ;
    rdfs:domain uko:Container ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Parent contains child (e.g., module contains class)." .

uko:references a owl:ObjectProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Weak reference (e.g., a function mentions a type in a docstring)." .

uko:dependsOn a owl:ObjectProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Strong dependency (e.g., import, inheritance, call)." .

# ── Content Properties ────────────────────────────────────────────
uko:hasRendering a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:string ;
    rdfs:comment "A rendered text representation of this node at a specific detail depth. Multiple renderings at different depths may exist for the same node. The depth is indicated by the associated uko:renderingDepth value." .

uko:renderingDepth a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:nonNegativeInteger ;
    rdfs:comment "The integer detail depth at which the associated uko:hasRendering was produced. Paired with uko:hasRendering via a blank node or reification." .

uko:hasFullContent a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:string ;
    rdfs:comment "Shorthand for the maximum-depth rendering of this node (complete, unabridged content). Equivalent to uko:hasRendering at the domain's maximum depth." .

# ── Provenance ────────────────────────────────────────────────────
uko:sourceResource a owl:ObjectProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:comment "The CleverAgents Resource (by ULID) this node was extracted from." .

uko:sourcePath a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:string ;
    rdfs:comment "Path within the resource (e.g., file path relative to the resource root)." .

uko:sourceRange a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:string ;
    rdfs:comment "Byte or line range within the source file (e.g., '42:1-87:0')." .

# ── Temporal ──────────────────────────────────────────────────────
uko:validFrom a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:dateTime .

uko:validUntil a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:dateTime .

uko:isCurrent a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:boolean .

uko:isRevisionOf a owl:ObjectProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Links a revised node to its predecessor." .
###### Layer 1: Domain Specializations Layer 1 specializes the universal Layer 0 foundation for four domains: general software (`uko-code:`), documents (`uko-doc:`), data schemas (`uko-data:`), and infrastructure (`uko-infra:`). Each domain defines its own classes, relationships, properties, and a DetailLevelMap mapping named levels to integer DetailDepth values. **General Software (`uko-code:`)**: 
@prefix uko-code: <https://cleveragents.ai/ontology/uko/code#> .

uko-code:Module a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A source code module (file, package, namespace)." .

uko-code:Callable a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "Any callable unit (function, method, procedure, lambda)." .

uko-code:TypeDefinition a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A type or schema definition (class, struct, interface, enum, typedef)." .

uko-code:TestCase a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A test case or test function." .

uko-code:Import a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "An import/include/require statement." .

uko-code:hasReturnType a owl:DatatypeProperty ;
    rdfs:domain uko-code:Callable ;
    rdfs:range xsd:string .

uko-code:hasParameters a owl:DatatypeProperty ;
    rdfs:domain uko-code:Callable ;
    rdfs:range xsd:string ;
    rdfs:comment "JSON-encoded parameter list." .

uko-code:testsCallable a owl:ObjectProperty ;
    rdfs:domain uko-code:TestCase ;
    rdfs:range uko-code:Callable ;
    rdfs:comment "Links a test case to the callable it tests." .
**Documents (`uko-doc:`)** — Layer 1: The document ontology represents structured and semi-structured documents (articles, technical papers, documentation, reports) as a hierarchy of containers and atoms. A key design principle is **semantic awareness**: when the system processes a document, it does not merely parse the structural hierarchy (sections, subsections, paragraphs) — it also analyzes the *content* of each text unit to infer implicit relationships. If a paragraph discusses a concept that is the subject of another section (even without an explicit hyperlink or mention by name), the RDF graph captures that relationship via `uko:references` or `uko-doc:discussesTopic` edges. This enables strategies to surface related content that a purely structural traversal would miss. 
@prefix uko-doc: <https://cleveragents.ai/ontology/uko/doc#> .

# ── Container Classes ──────────────────────────────────────────────
uko-doc:Document a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A complete document (article, report, manual, specification)." .

uko-doc:Part a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A top-level division of a document (e.g., Part I, Part II)." .

uko-doc:Chapter a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A chapter within a document or part." .

uko-doc:Section a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A numbered or titled section within a chapter." .

uko-doc:Subsection a owl:Class ;
    rdfs:subClassOf uko-doc:Section ;
    rdfs:comment "A subsection nested within a section (arbitrary depth)." .

# ── Atom Classes ───────────────────────────────────────────────────
uko-doc:Paragraph a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A paragraph of prose text." .

uko-doc:CodeBlock a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "An inline code listing or example within a document." .

uko-doc:Figure a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A figure, diagram, or image with an optional caption." .

uko-doc:Table a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A tabular data element within a document." .

uko-doc:BlockQuote a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A quoted passage from another source." .

uko-doc:ListBlock a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "An ordered or unordered list." .

# ── Annotation Classes ─────────────────────────────────────────────
uko-doc:Footnote a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "A footnote or endnote." .

uko-doc:Citation a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "A bibliographic citation or reference." .

uko-doc:Comment a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "An editorial comment or annotation (e.g., HTML comment, review note)." .

# ── Boundary Classes ───────────────────────────────────────────────
uko-doc:TableOfContents a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "The document's table of contents — an interface into the document's structure." .

uko-doc:Index a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "A back-of-book index or keyword index." .

uko-doc:Glossary a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "A glossary of terms defined in the document." .

# ── Document-Specific Relationships ────────────────────────────────
uko-doc:discussesTopic a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:references ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Semantic relationship: this unit discusses a topic that is the subject of another unit. Inferred by the document analyzer even when no explicit link exists." .

uko-doc:cites a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:references ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko-doc:Citation ;
    rdfs:comment "This unit cites a bibliographic reference." .

uko-doc:crossReferences a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:references ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Explicit cross-reference (e.g., 'see Section 3.2')." .

uko-doc:precedes a owl:ObjectProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range uko:InformationUnit ;
    rdfs:comment "Reading order: this unit comes before the target unit." .

# ── Document-Specific Properties ───────────────────────────────────
uko-doc:headingLevel a owl:DatatypeProperty ;
    rdfs:domain uko-doc:Section ;
    rdfs:range xsd:integer ;
    rdfs:comment "The nesting depth of this section (1 = top-level, 2 = subsection, etc.)." .

uko-doc:headingText a owl:DatatypeProperty ;
    rdfs:domain uko-doc:Section ;
    rdfs:range xsd:string ;
    rdfs:comment "The title/heading text of this section." .

uko-doc:wordCount a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:integer ;
    rdfs:comment "Word count of the text content in this unit." .

uko-doc:language a owl:DatatypeProperty ;
    rdfs:domain uko-doc:Document ;
    rdfs:range xsd:string ;
    rdfs:comment "Natural language of the document (e.g., 'en', 'fr')." .

uko-doc:topicKeywords a owl:DatatypeProperty ;
    rdfs:domain uko:InformationUnit ;
    rdfs:range xsd:string ;
    rdfs:comment "JSON-encoded list of topic keywords extracted from this unit." .
**Semantic Inference for Documents**: When the document analyzer processes a document, it performs semantic analysis beyond pure structural parsing: 1. **Topic extraction**: Each paragraph, section, and subsection is analyzed for key topics. These become `uko-doc:topicKeywords` properties. 2. **Implicit cross-references**: If Paragraph A in Section 2 discusses "authentication flow" and Section 5 is titled "Authentication Architecture", the analyzer creates a `uko-doc:discussesTopic` edge from Paragraph A to Section 5 — even though no explicit link exists in the source document. 3. **Citation resolution**: Bibliographic citations are linked to the paragraphs that cite them. 4. **Concept clustering**: Paragraphs discussing related concepts across different sections are linked via `uko:references`, enabling strategies to pull in contextually relevant content from distant parts of a document. This semantic awareness means that a `breadth-depth-navigator` strategy operating on a document resource can follow not just the structural containment hierarchy but also the semantic topic graph, surfacing related sections that an author would need to consider when modifying any part of the document. **Document DetailLevelMap Refinements** (per-type rendering at selected depths — see Core Data Types for the authoritative `uko-doc:` depth map): | Depth | Named Level | `uko-doc:Document` | `uko-doc:Section` | `uko-doc:Paragraph` | |-------|-------------|---------------------|--------------------|-----------------------| | 0 | `TITLE_ONLY` | Document title only | Heading text only | — (not individually listed) | | 1 | `TABLE_OF_CONTENTS_L1` | Title + top-level section headings | Heading + child section headings | First sentence only | | 4 | `TOC_WITH_SUMMARIES` | All headings + one-sentence abstract per section | Heading + paragraph count + topic keywords + abstract | First two sentences + topic keywords | | 8 | `STRUCTURAL_DETAIL` | Full TOC + figure/table captions + list item headers | Heading + first sentence of each paragraph + all captions | Full text with inline code and links preserved | | 10 | `FULL_CONTENT` | Complete document content | Complete section content including all children | Complete paragraph text with all formatting | **Data Schemas (`uko-data:`)** — Layer 1: The data schema ontology represents databases, data warehouses, and structured data stores. It models the schema structure (schemas, tables, columns, constraints) and captures query-time relationships (views referencing tables, foreign keys, stored procedures accessing tables). Like the document ontology, the system performs semantic analysis: when a stored procedure references columns from multiple tables, those dependency edges are created automatically. 
@prefix uko-data: <https://cleveragents.ai/ontology/uko/data#> .

# ── Container Classes ──────────────────────────────────────────────
uko-data:Database a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A database instance containing schemas." .

uko-data:Schema a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A database schema (namespace for tables, views, etc.)." .

uko-data:Table a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A database table containing columns." .

uko-data:View a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A database view (virtual table defined by a query)." .

# ── Atom Classes ───────────────────────────────────────────────────
uko-data:Column a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A column within a table or view." .

uko-data:StoredProcedure a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A stored procedure or function in the database." .

uko-data:Trigger a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A database trigger." .

uko-data:Migration a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A schema migration (DDL change script)." .

# ── Annotation Classes ─────────────────────────────────────────────
uko-data:Constraint a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "A column or table constraint (NOT NULL, UNIQUE, CHECK, etc.)." .

uko-data:Index a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "A database index on one or more columns." .

uko-data:ColumnComment a owl:Class ;
    rdfs:subClassOf uko:Annotation ;
    rdfs:comment "A COMMENT ON COLUMN annotation in the database." .

# ── Boundary Classes ───────────────────────────────────────────────
uko-data:ForeignKey a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "A foreign key constraint — an interface point between tables." .

uko-data:APIEndpoint a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "A database-level API endpoint (e.g., PostgREST, GraphQL)." .

# ── Data-Specific Relationships ────────────────────────────────────
uko-data:foreignKeyTo a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-data:Column ;
    rdfs:range uko-data:Column ;
    rdfs:comment "Foreign key relationship from this column to a column in another table." .

uko-data:viewReferences a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-data:View ;
    rdfs:range uko-data:Table ;
    rdfs:comment "This view's query references columns from the target table." .

uko-data:procedureAccesses a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-data:StoredProcedure ;
    rdfs:range uko-data:Table ;
    rdfs:comment "This stored procedure reads from or writes to the target table." .

uko-data:triggerFires a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-data:Trigger ;
    rdfs:range uko-data:Table ;
    rdfs:comment "This trigger fires on events on the target table." .

uko-data:migrationAlters a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-data:Migration ;
    rdfs:range uko-data:Table ;
    rdfs:comment "This migration modifies the schema of the target table." .

# ── Data-Specific Properties ──────────────────────────────────────
uko-data:dataType a owl:DatatypeProperty ;
    rdfs:domain uko-data:Column ;
    rdfs:range xsd:string ;
    rdfs:comment "SQL data type (e.g., 'VARCHAR(255)', 'INTEGER', 'JSONB')." .

uko-data:isNullable a owl:DatatypeProperty ;
    rdfs:domain uko-data:Column ;
    rdfs:range xsd:boolean .

uko-data:isPrimaryKey a owl:DatatypeProperty ;
    rdfs:domain uko-data:Column ;
    rdfs:range xsd:boolean .

uko-data:rowEstimate a owl:DatatypeProperty ;
    rdfs:domain uko-data:Table ;
    rdfs:range xsd:long ;
    rdfs:comment "Estimated row count from database statistics." .

uko-data:viewDefinition a owl:DatatypeProperty ;
    rdfs:domain uko-data:View ;
    rdfs:range xsd:string ;
    rdfs:comment "The SQL query that defines this view." .

uko-data:procedureBody a owl:DatatypeProperty ;
    rdfs:domain uko-data:StoredProcedure ;
    rdfs:range xsd:string ;
    rdfs:comment "The SQL/PL body of the stored procedure." .
**Database DetailLevelMap Refinements** (per-type rendering at selected depths — see Core Data Types for the authoritative `uko-data:` depth map): | Depth | Named Level | `uko-data:Database` | `uko-data:Table` | `uko-data:Column` | |-------|-------------|----------------------|-------------------|--------------------| | 0 | `SCHEMA_LISTING` | Schema names only | — (not individually listed) | — | | 1 | `TABLE_LISTING` | Schema names + table/view names | Table name only | — | | 3 | `TYPED_COLUMNS` | + column types + nullability | Column names + types + nullability | Name + type + nullable | | 5 | `RELATIONSHIPS` | + foreign key graph + row estimates | + primary key + foreign key targets + row estimate | + FK references + constraints | | 7 | `DDL` | Full CREATE TABLE DDL with constraints | Full CREATE TABLE DDL + index definitions | Full column DDL + all constraints | | 11 | `FULL_CATALOG` | Complete DDL + views + procedures + sample data | Full DDL + triggers + sample rows + statistics | Full DDL + value distribution + sample values | **Infrastructure (`uko-infra:`)** — Layer 1: 
@prefix uko-infra: <https://cleveragents.ai/ontology/uko/infra#> .

# ── Container Classes ──────────────────────────────────────────────
uko-infra:Service a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A deployable service or application." .

uko-infra:ConfigBlock a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A configuration block or section (e.g., a YAML map, TOML table)." .

uko-infra:DeploymentUnit a owl:Class ;
    rdfs:subClassOf uko:Container ;
    rdfs:comment "A deployment unit (e.g., Kubernetes Deployment, Docker Compose service)." .

# ── Atom Classes ───────────────────────────────────────────────────
uko-infra:ConfigKey a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "A configuration key-value pair." .

uko-infra:EnvironmentVariable a owl:Class ;
    rdfs:subClassOf uko:Atom ;
    rdfs:comment "An environment variable definition." .

# ── Boundary Classes ───────────────────────────────────────────────
uko-infra:Endpoint a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "A network endpoint (HTTP route, gRPC service, message queue)." .

uko-infra:Port a owl:Class ;
    rdfs:subClassOf uko:Boundary ;
    rdfs:comment "A network port binding." .

# ── Infrastructure-Specific Relationships ──────────────────────────
uko-infra:connectsTo a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-infra:Service ;
    rdfs:range uko-infra:Service ;
    rdfs:comment "This service connects to or depends on the target service." .

uko-infra:exposes a owl:ObjectProperty ;
    rdfs:domain uko-infra:Service ;
    rdfs:range uko-infra:Endpoint ;
    rdfs:comment "This service exposes the target endpoint." .
###### Layer 2: Paradigm / Format Specializations Layer 2 refines Layer 1 domains with paradigm- or format-specific specializations. For code: OO, functional, and procedural paradigms. For documents: academic vs. technical. For databases: relational vs. graph. Each may extend the parent domain's DetailLevelMap with additional named levels. **Object-Oriented (`uko-oo:`)**: 
@prefix uko-oo: <https://cleveragents.ai/ontology/uko/oo#> .

uko-oo:Class a owl:Class ;
    rdfs:subClassOf uko-code:TypeDefinition, uko:Container ;
    rdfs:comment "An OO class that contains methods and attributes." .

uko-oo:Interface a owl:Class ;
    rdfs:subClassOf uko-code:TypeDefinition, uko:Boundary ;
    rdfs:comment "An interface or abstract base class." .

uko-oo:Method a owl:Class ;
    rdfs:subClassOf uko-code:Callable .

uko-oo:Attribute a owl:Class ;
    rdfs:subClassOf uko:Atom .

uko-oo:inheritsFrom a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-oo:Class ;
    rdfs:range uko-oo:Class .

uko-oo:implements a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-oo:Class ;
    rdfs:range uko-oo:Interface .
**Functional (`uko-func:`)**: 
@prefix uko-func: <https://cleveragents.ai/ontology/uko/func#> .

uko-func:PureFunction a owl:Class ;
    rdfs:subClassOf uko-code:Callable .

uko-func:TypeClass a owl:Class ;
    rdfs:subClassOf uko-code:TypeDefinition, uko:Boundary .

uko-func:Monad a owl:Class ;
    rdfs:subClassOf uko-code:TypeDefinition .
**Code DetailLevelMap Refinements by Paradigm and Language**: The authoritative DetailLevelMap definitions — with full integer depth assignments and named level descriptions for each domain — are specified in **Core Concepts > Advanced Context Management System (ACMS) > Core Data Types > DetailDepth and DetailLevelMap**. The tables below show how paradigm-specific (Layer 2) and language-specific (Layer 3) UKO node types map their content at selected depth levels from the parent domain's map. These are illustrative excerpts showing what content each node type contributes at key depths, not exhaustive depth-by-depth definitions. *General Software (`uko-code:`) — Layer 1 (per-type rendering at selected depths):* | Depth | Named Level | `uko-code:Module` | `uko-code:Callable` | `uko-code:TypeDefinition` | |-------|-------------|---------------------|----------------------|----------------------------| | 0 | `MODULE_LISTING` | Module name only | — (not individually listed) | — (not individually listed) | | 2 | `MEMBER_LISTING` | + names of top-level members | Function name (no signature) | Type name + kind (class/struct/enum) | | 4 | `SIGNATURES` | + all top-level signatures | Name + parameter types + return type | Name + field types + method signatures | | 6 | `STRUCTURAL_OUTLINE` | + control flow outline of callables | Signature + control flow outline (branches, loops) | Name + all field + method signatures + inheritance | | 9 | `FULL_SOURCE` | Complete module source | Complete function body | Complete type definition | *Object-Oriented (`uko-oo:`) — Layer 2 (per-type rendering at selected depths):* | Depth | Named Level | `uko-oo:Class` | `uko-oo:Method` | `uko-oo:Interface` | |-------|-------------|-----------------|------------------|--------------------| | 2 | `MEMBER_LISTING` | Class name + parent classes | Method name + visibility | Interface name | | 3 | `CLASS_HIERARCHY` (OO-inserted) | + inheritance chain + interface implementations | — | + method signatures | | 4 | `SIGNATURES` | + attribute types + method signatures | + params + return type + visibility | + all method signatures with param types | | 5 | `SIGNATURES_WITH_DOCS` | + class docstring + attribute descriptions | + docstring + side effect hints | + description + implementor count | | 9+ | `FULL_SOURCE` | Complete class definition | Complete method body | Complete interface definition | *Functional (`uko-func:`) — Layer 2 (per-type rendering at selected depths):* | Depth | Named Level | `uko-func:PureFunction` | `uko-func:TypeClass` | `uko-func:Monad` | |-------|-------------|--------------------------|----------------------|-------------------| | 2 | `MEMBER_LISTING` | Function name | Type class name | Monad name | | 4 | `SIGNATURES` | Name + type signature + purity annotation | Name + associated types | Name + bind/return types | | 6 | `STRUCTURAL_OUTLINE` | + pattern match structure + guard conditions | + all method signatures + laws | + bind/return implementations | | 9 | `FULL_SOURCE` | Complete function definition | Complete type class definition | Complete monad definition | *Procedural (`uko-proc:`) — Layer 2 (rendering at selected depths):* | Depth | Named Level | Procedural Specifics | |-------|-------------|---------------------| | 2 | `MEMBER_LISTING` | Function names + global variable names (no types) | | 4 | `SIGNATURES` | Function declarations + global variable types + header file exports | | 5 | `SIGNATURES_WITH_DOCS` | + function descriptions + global variable purposes + header summaries | | 6 | `STRUCTURAL_OUTLINE` | + function signatures with parameter names + struct definitions + macro signatures | | 9 | `FULL_SOURCE` | Complete source including all function bodies, macros, and inline assembly | ###### Layer 3: Technology-Specific Specializations Layer 3 extends Layer 2 (or Layer 1 directly) with technology-specific refinements — e.g., Python, TypeScript, Rust, Java for code; PostgreSQL, MongoDB for databases; Markdown, LaTeX for documents. Each may insert additional named DetailLevelMap levels into its parent's map. *Language-Specific (Layer 3) DetailLevelMap insertions — examples:* Each language extension may insert additional named levels into its parent paradigm's map, shifting subsequent depths upward to maintain consecutive integer numbering (see the fully expanded effective maps in Core Data Types). The table below summarizes the key additions: | Language | Inserted Levels | Additional Content at Those Depths | |----------|----------------|------------------------------------| | **Python** (`uko-py:`) | `DECORATED_SIGNATURES` (between SIGNATURES_WITH_DOCS and STRUCTURAL_OUTLINE), `TYPE_STUBS` (between KEY_LOGIC and NEAR_COMPLETE), `WITH_TESTS` (beyond FULL_SOURCE) | Decorator chains (`@property`, `@staticmethod`, custom), `.pyi` stub type annotations, associated test cases | | **TypeScript** (`uko-ts:`) | (extends at SIGNATURES level) | `export`/`default export` markers, `declare` ambient types, generic type parameters, mapped/conditional types | | **Rust** (`uko-rs:`) | (extends at SIGNATURES level) | Visibility modifiers (`pub`, `pub(crate)`), lifetime parameters, trait bounds, `unsafe` markers, `#[derive]` macros, `#[must_use]` annotations | | **Java** (`uko-java:`) | (extends at SIGNATURES level) | Package visibility, `final`/`abstract`/`sealed` modifiers, annotation lists (`@Override`, `@Deprecated`), checked exceptions | Not every language requires a Layer 3 extension. If a language's semantics are fully captured by the Layer 1 (`uko-code:`) and Layer 2 (paradigm) maps, no Layer 3 extension is needed. The system falls back to the nearest parent layer's DetailLevelMap. ##### The Universal View Guarantee Because every domain-specific class ultimately inherits from Layer 0 (`uko:InformationUnit`, `uko:Container`, etc.), any strategy or query written against Layer 0 automatically works across all domains — not just different programming languages, but across code, documents, databases, and infrastructure alike. For example: 
# "Find all containers that depend on this atom" — works for Python classes,
# TypeScript modules, Rust crates, SQL tables, document sections, or config blocks.
SELECT ?container WHERE {
    ?container a uko:Container .
    ?container uko:dependsOn <target_atom> .
}
Similarly, a DetailDepth request at Layer 0 is resolved by the most specific DetailLevelMap available in the inheritance chain. A request for depth 3 of a `uko:Container` will produce a member summary with one-line docstrings for a Python module (`MEMBER_SUMMARY`), a full table of contents for a document chapter (`FULL_TOC`), or typed column definitions for a database table (`TYPED_COLUMNS`) — all through the same universal integer-depth interface, with each domain mapping the integer to its domain-appropriate rendering. ##### Provenance Contract Every UKO node carries provenance back to the originating resource: 
uko-py:class/AuthManager
    uko:sourceResource  <resource-ulid-01HXM7...>
    uko:sourcePath      "src/auth/manager.py"
    uko:sourceRange     "15:1-87:0"
    uko:validFrom       "2026-01-15T10:30:00Z"
    uko:isCurrent       true
This allows the PreambleGenerator pipeline component to generate provenance summaries in the context preamble, and allows actors to trace any piece of context back to its exact source location. #### Temporal Data Model and Storage Tiers ##### Revision-Aware RDF Each UKO node carries temporal metadata. When code changes, existing nodes are **not deleted** — instead, their `validUntil` is set and `isCurrent` becomes `false`, and a new node is created with `isRevisionOf` pointing to the predecessor: 
# Before code change:
uko-py:class/AuthManager_v1
    uko:isCurrent true ;
    uko:validFrom "2026-01-10T00:00:00Z"^^xsd:dateTime .

# After code change:
uko-py:class/AuthManager_v1
    uko:isCurrent false ;
    uko:validFrom "2026-01-10T00:00:00Z"^^xsd:dateTime ;
    uko:validUntil "2026-01-15T10:30:00Z"^^xsd:dateTime .

uko-py:class/AuthManager_v2
    uko:isCurrent true ;
    uko:validFrom "2026-01-15T10:30:00Z"^^xsd:dateTime ;
    uko:isRevisionOf uko-py:class/AuthManager_v1 .
This temporal chain is what enables the `temporal-archaeology` strategy to find patterns like "this class was refactored 3 times in the last month" or "this function's signature changed after we updated the auth library." ##### Three Storage Tiers with Temporal Alignment | Tier | Content | Retention | Access Pattern | Temporal | |------|---------|-----------|---------------|----------| | **Hot** | Current UKO graph + recent embeddings + active text index | Until resource removed | Direct query via BAL | `isCurrent = true` only | | **Warm** | Recent decision contexts, plan context snapshots | `context.tiers.warm.retention-hours` (default: 24h) | Scoped query via plan hierarchy | Current + recently-expired nodes | | **Cold** | Archived decision contexts, historical UKO snapshots | `context.tiers.cold.retention-days` (default: 90d) | Full historical query | All temporal versions | #### Scoped Views and Plan Subgraph Projection ##### Resource Scope Resolution When a plan is created (via `agents plan use`), the system resolves its resource scope: 
class ResourceScopeResolver:
    """Determines which resources a plan can see."""

    def resolve(self, plan: Plan) -> ResourceScope:
        # 1. Get all projects this plan targets
        projects = plan.target_projects
        # 2. Collect all resources linked to those projects
        resources = set()
        for project in projects:
            resources.update(project.linked_resources)
        # 3. Expand to include child resources (DAG traversal)
        expanded = set()
        for resource in resources:
            expanded.add(resource)
            expanded.update(self.registry.get_descendants(resource))
        # 4. Apply context view filters (include/exclude)
        view = self._resolve_view(plan)
        filtered = self._apply_filters(expanded, view)
        return ResourceScope(resources=filtered, projects=projects)
##### UKO Subgraph Projection Given a resource scope, the system projects only the relevant UKO subgraph: 
class UKOSubgraphProjector:
    """Projects the UKO graph to only include nodes from scoped resources."""

    def project(self, scope: ResourceScope,
                graph_backend: GraphBackend) -> ProjectedGraph:
        # Only include UKO nodes whose sourceResource is in scope
        return graph_backend.subgraph_by_resources(
            resource_ulids=[r.ulid for r in scope.resources],
            include_temporal=scope.temporal_scope,
        )
##### Scoped Backend Views Each backend (text, vector, graph) is wrapped in a `ScopedView` that automatically filters queries to only return results from in-scope resources: 
class ScopedBackendView:
    """Wraps a backend to restrict queries to a resource scope."""

    def __init__(self, backend, scope: ResourceScope):
        self.backend = backend
        self.scope = scope
        self._resource_filter = {r.ulid for r in scope.resources}

    def search(self, query, **kwargs):
        # Inject the resource filter into the backend query
        results = self.backend.search(
            query,
            resource_filter=self._resource_filter,
            **kwargs,
        )
        return results
This is critical for multi-project isolation: a plan targeting `local/api-service` never sees resources from `local/frontend`, even if both projects share the same physical database indices. #### Backend Abstraction Layer (BAL) The BAL provides a uniform interface to heterogeneous data stores. Each backend type has a protocol: ##### Backend Protocols 
class TextBackend(Protocol):
    def search(self, query: str, *, resource_filter: set[str],
               limit: int = 20) -> list[TextResult]: ...
    def index(self, resource_ulid: str, content: str,
              metadata: dict) -> None: ...

class VectorBackend(Protocol):
    def search(self, embedding: list[float], *, resource_filter: set[str],
               limit: int = 20, threshold: float = 0.3) -> list[VectorResult]: ...
    def index(self, resource_ulid: str, chunks: list[EmbeddingChunk]) -> None: ...

class GraphBackend(Protocol):
    def query_sparql(self, sparql: str, *, resource_filter: set[str]) -> list[dict]: ...
    def add_triples(self, triples: list[Triple]) -> None: ...
    def subgraph_by_resources(self, resource_ulids: list[str],
                              include_temporal: TemporalScope) -> ProjectedGraph: ...
    def traverse(self, start_uri: str, max_hops: int,
                 edge_types: list[str], resource_filter: set[str]) -> SubGraph: ...
##### Unified Result Types 
@dataclass
class TextResult:
    resource_ulid: str
    path: str
    line_range: tuple[int, int]
    content: str
    score: float

@dataclass
class VectorResult:
    resource_ulid: str
    uko_node: str
    content: str
    similarity: float
    metadata: dict
#### Context Assembly Pipeline The context assembly pipeline is the central orchestrator of context assembly. It receives a `ContextRequest`, processes it through a chain of pluggable components, and produces a budget-respecting `AssembledContext`. Every stage of the pipeline is a replaceable plugin — each defined by a `Protocol` interface, shipped with a default implementation, and configurable at the global, project, or plan scope. ##### Pipeline Component Model The pipeline follows the **Pipes and Filters** architectural pattern, with each filter implemented as a **Strategy** (GoF) that can be swapped at runtime. Component resolution uses a **Chain of Responsibility** pattern: plan-level overrides take precedence over project-level, which take precedence over global defaults. 

Pipeline Component Resolution Order:

  plan scope  ──►  project scope  ──►  global scope  ──►  built-in default
  (most specific)                                          (least specific)
There are ten pluggable components, grouped into three pipeline phases: **Phase 1 — Strategy Orchestration** (selects and runs context strategies): | # | Component | Protocol | Responsibility | |---|-----------|----------|----------------| | 1 | **StrategySelector** | `StrategySelectorProtocol` | Decides which strategies to invoke and computes confidence scores | | 2 | **BudgetAllocator** | `BudgetAllocatorProtocol` | Distributes the token budget across selected strategies | | 3 | **StrategyExecutor** | `StrategyExecutorProtocol` | Controls how strategies are invoked (parallelism, timeouts, error handling) | **Phase 2 — Fragment Fusion** (merges strategy outputs into a coherent payload): | # | Component | Protocol | Responsibility | |---|-----------|----------|----------------| | 4 | **FragmentDeduplicator** | `FragmentDeduplicatorProtocol` | Removes duplicate fragments across strategy outputs | | 5 | **DetailDepthResolver** | `DetailDepthResolverProtocol` | Resolves conflicts when the same UKO node appears at different depths | | 6 | **FragmentScorer** | `FragmentScorerProtocol` | Computes composite relevance scores for ranking | | 7 | **BudgetPacker** | `BudgetPackerProtocol` | Fits scored fragments into the token budget | | 8 | **FragmentOrderer** | `FragmentOrdererProtocol` | Orders final fragments for coherence in the prompt | **Phase 3 — Context Finalization** (produces the final deliverable): | # | Component | Protocol | Responsibility | |---|-----------|----------|----------------| | 9 | **PreambleGenerator** | `PreambleGeneratorProtocol` | Generates the context preamble (provenance summary, structure map) | | 10 | **SkeletonCompressor** | `SkeletonCompressorProtocol` | Compresses parent context into a skeleton for child plan inheritance | ##### Component Protocol Definitions Each component is defined as a `@runtime_checkable` Protocol, enabling both structural subtyping (duck typing) and explicit isinstance checks. The protocols use **Generic** type parameters where applicable, and employ the **Template Method** pattern — each protocol defines the contract while default implementations provide the algorithm skeleton with overridable hook methods. 
# ── Phase 1: Strategy Orchestration ────────────────────────────────

@runtime_checkable
class StrategySelectorProtocol(Protocol):
    """Decides which strategies to invoke and with what confidence.
    Applies request preferences and backend availability filtering."""

    def select(
        self,
        strategies: Sequence[ContextStrategy],
        request: ContextRequest,
        backends: BackendSet,
    ) -> list[tuple[ContextStrategy, float]]:
        """Returns (strategy, confidence) pairs, sorted by priority.
        Confidence is 0.0-1.0. Strategies with 0.0 are excluded."""
        ...


@runtime_checkable
class BudgetAllocatorProtocol(Protocol):
    """Distributes the token budget across selected strategies.
    May use proportional, priority-weighted, or custom allocation schemes."""

    def allocate(
        self,
        candidates: list[tuple[ContextStrategy, float]],
        total_budget: int,
        request: ContextRequest,
    ) -> list[tuple[ContextStrategy, float, int]]:
        """Returns (strategy, confidence, allocated_tokens) triples.
        Sum of allocated_tokens must not exceed total_budget."""
        ...


@runtime_checkable
class StrategyExecutorProtocol(Protocol):
    """Controls how strategies are invoked — parallelism model,
    timeout handling, circuit breaking, and error recovery."""

    def execute(
        self,
        allocations: list[tuple[ContextStrategy, float, int]],
        request: ContextRequest,
        backends: BackendSet,
        plan_context: PlanContext,
    ) -> list[ContextFragment]:
        """Executes strategies and collects all fragments.
        Must handle strategy failures gracefully (log and continue)."""
        ...


# ── Phase 2: Fragment Fusion ────────────────────────────────────────

@runtime_checkable
class FragmentDeduplicatorProtocol(Protocol):
    """Removes duplicate fragments from the merged strategy output.
    Deduplication can be identity-based, content-hash-based, or semantic."""

    def deduplicate(
        self,
        fragments: list[ContextFragment],
    ) -> list[ContextFragment]:
        """Returns deduplicated fragments. When duplicates are found,
        the fragment with the highest relevance_score is retained."""
        ...


@runtime_checkable
class DetailDepthResolverProtocol(Protocol):
    """Resolves conflicts when the same UKO node appears at different
    detail depths across strategy outputs."""

    def resolve(
        self,
        fragments: list[ContextFragment],
        budget: int,
    ) -> list[ContextFragment]:
        """Returns fragments with depth conflicts resolved.
        Default: keep highest depth that fits within budget."""
        ...


@runtime_checkable
class FragmentScorerProtocol(Protocol):
    """Computes a composite score for each fragment, used for ranking
    during budget packing. Applies hierarchical weighting, strategy
    quality weighting, and recency bonuses."""

    def score(
        self,
        fragments: list[ContextFragment],
        plan_context: PlanContext,
    ) -> list[ScoredFragment]:
        """Returns fragments annotated with composite scores.
        ScoredFragment adds a `composite_score: float` field."""
        ...


@runtime_checkable
class BudgetPackerProtocol(Protocol):
    """Fits scored fragments into the token budget using a packing
    algorithm. Supports depth fallback — if a fragment doesn't fit
    at its current depth, it can be re-rendered at a lower depth."""

    def pack(
        self,
        scored_fragments: list[ScoredFragment],
        budget: int,
        detail_level_maps: DetailLevelMapRegistry,
    ) -> list[ContextFragment]:
        """Returns the subset of fragments that fit within budget,
        possibly re-rendered at lower depths. Ordered by score."""
        ...


@runtime_checkable
class FragmentOrdererProtocol(Protocol):
    """Orders the packed fragments for optimal coherence in the
    actor's context window. Ordering may be by relevance, by
    topological dependency, or by a hybrid coherence heuristic."""

    def order(
        self,
        fragments: list[ContextFragment],
    ) -> list[ContextFragment]:
        """Returns fragments in the final presentation order."""
        ...


# ── Phase 3: Context Finalization ──────────────────────────────────

@runtime_checkable
class PreambleGeneratorProtocol(Protocol):
    """Generates the preamble prepended to assembled context — a
    structured summary of what's included, why, and from where."""

    def generate(
        self,
        fragments: list[ContextFragment],
        strategies_used: list[str],
        budget_used: float,
        max_tokens: int,
    ) -> str | None:
        """Returns the preamble string, or None if preamble is disabled."""
        ...


@runtime_checkable
class SkeletonCompressorProtocol(Protocol):
    """Compresses a parent plan's assembled context into a compact
    skeleton representation for inheritance by child plans."""

    def compress(
        self,
        parent_context: AssembledContext,
        child_focus: list[str],
        skeleton_budget: int,
    ) -> AssembledContext:
        """Returns a compressed version of the parent context that
        fits within skeleton_budget tokens. Typically reduces all
        fragments to depth 0-1 (e.g., MODULE_LISTING / TITLE_ONLY)."""
        ...
##### Supporting Types 
@dataclass(frozen=True)
class ScoredFragment:
    """A ContextFragment annotated with a composite score by the FragmentScorer."""
    fragment: ContextFragment
    composite_score: float        # 0.0-1.0 composite ranking score
    score_components: dict[str, float]  # Breakdown: {"relevance": 0.9, "hierarchy": 0.8, ...}


@dataclass
class PipelineConfig:
    """Resolved configuration for the context assembly pipeline.
    Each field holds the concrete plugin instance to use for that stage.
    Resolved via the scope chain: plan > project > global > built-in."""

    strategy_selector: StrategySelectorProtocol
    budget_allocator: BudgetAllocatorProtocol
    strategy_executor: StrategyExecutorProtocol
    fragment_deduplicator: FragmentDeduplicatorProtocol
    detail_depth_resolver: DetailDepthResolverProtocol
    fragment_scorer: FragmentScorerProtocol
    budget_packer: BudgetPackerProtocol
    fragment_orderer: FragmentOrdererProtocol
    preamble_generator: PreambleGeneratorProtocol
    skeleton_compressor: SkeletonCompressorProtocol
##### Pipeline Orchestrator The `ContextAssemblyPipeline` is the top-level orchestrator that wires the ten components together. It implements the **Mediator** pattern — components do not communicate directly with each other; the pipeline mediates all data flow. The pipeline itself is stateless; all state is carried through the data flowing between stages. 
class ContextAssemblyPipeline:
    """Mediator that orchestrates the 10-stage context assembly pipeline.
    Each stage is a pluggable component resolved from the scope chain."""

    def __init__(self, config: PipelineConfig, strategies: Sequence[ContextStrategy]):
        self._config = config
        self._strategies = strategies

    def assemble(
        self,
        request: ContextRequest,
        backends: BackendSet,
        budget: int,
        plan_context: PlanContext,
        skeleton_ratio: float = 0.15,
        parent_fragments: tuple[ContextFragment, ...] | None = None,
    ) -> AssembledContext:
        # ── Phase 1: Strategy Orchestration ──────────────────────
        # 1. Select strategies
        candidates = self._config.strategy_selector.select(
            self._strategies, request, backends,
        )
        # 2. Allocate budget
        allocations = self._config.budget_allocator.allocate(
            candidates, budget, request,
        )
        # 3. Execute strategies
        raw_fragments = self._config.strategy_executor.execute(
            allocations, request, backends, plan_context,
        )

        # ── Phase 2: Fragment Fusion ──────────────────────────────
        # 4. Deduplicate
        deduped = self._config.fragment_deduplicator.deduplicate(raw_fragments)
        # 5. Resolve depth conflicts
        resolved = self._config.detail_depth_resolver.resolve(deduped, budget)
        # 6. Score fragments
        scored = self._config.fragment_scorer.score(resolved, plan_context)
        # 7. Pack into budget
        packed = self._config.budget_packer.pack(
            scored, budget, self._detail_level_maps,
        )
        # 8. Order for coherence
        ordered = self._config.fragment_orderer.order(packed)

        # ── Phase 3: Context Finalization ─────────────────────────
        # 9. Generate preamble
        strategies_used = [s.name for s, _, _ in allocations]
        preamble = self._config.preamble_generator.generate(
            ordered, strategies_used,
            budget_used=sum(f.token_count for f in ordered) / budget,
            max_tokens=self._preamble_max_tokens,
        )

        # 10. Compress parent context into skeleton for child plan inheritance
        skeleton_budget = int(budget * skeleton_ratio)
        skeleton_frags = ()
        if parent_fragments:
            skeleton_frags = self._config.skeleton_compressor.compress(
                parent_fragments, skeleton_budget,
            )

        return AssembledContext(
            fragments=ordered,
            total_tokens=sum(f.token_count for f in ordered),
            budget_used=sum(f.token_count for f in ordered) / budget,
            strategies_used=strategies_used,
            context_hash=self._compute_hash(ordered),
            preamble=preamble,
            provenance_map={f.uko_node: f.provenance for f in ordered},
            skeleton_fragments=skeleton_frags,
        )
##### Built-in Default Implementations Each component ships with a default implementation that provides the behavior described in the current specification. Custom implementations need only implement the relevant Protocol — they need not subclass the default. **Phase 1 defaults:** | Component | Default Class | Algorithm | |-----------|--------------|-----------| | StrategySelector | `ConfidenceWeightedSelector` | Calls `can_handle()` on all registered strategies; filters to confidence > 0; applies `ContextRequest.preferred_strategies` preferences; sorts by `confidence * quality_score` descending. Uses the **Observer** pattern to emit `StrategySelectionEvent` for diagnostics. | | BudgetAllocator | `ProportionalBudgetAllocator` | Allocates budget proportional to `confidence * quality_score`. Guarantees each strategy receives at least `min_useful_budget` tokens or is excluded. Implements **Flyweight** for allocation metadata reuse across re-assembly cycles. | | StrategyExecutor | `ParallelStrategyExecutor` | Runs strategies concurrently via `ThreadPoolExecutor`. Per-strategy timeout (default: 30s). Uses **Circuit Breaker** pattern: after 3 consecutive failures, a strategy is temporarily disabled for that plan. Failed strategies log warnings and are excluded from results. | **Phase 2 defaults:** | Component | Default Class | Algorithm | |-----------|--------------|-----------| | FragmentDeduplicator | `ContentHashDeduplicator` | Groups fragments by UKO node URI; within each group, hashes content to detect duplicates; retains the fragment with the highest `relevance_score`. Configurable via `context.fusion.dedup-strategy`: `content-hash` (default), `uko-identity` (URI only), or `semantic` (embedding cosine similarity > 0.95). Implements **Strategy** (GoF) pattern to swap dedup algorithms. | | DetailDepthResolver | `MaxDepthResolver` | When the same UKO node appears at multiple depths, retains the highest-depth rendering that fits within the remaining budget. Uses a **Specification** pattern: each fragment is tested against a budget specification, and the highest-depth satisfying fragment wins. | | FragmentScorer | `WeightedCompositeScorer` | Computes `composite = relevance_score * strategy_quality * hierarchy_weight * recency_bonus`. Hierarchy weight is derived from the fragment's distance to the plan's focus nodes. Recency bonus is 1.0 for current nodes, decaying for older revisions. Scoring weights are configurable. Uses **Decorator** pattern to compose scoring dimensions. | | BudgetPacker | `GreedyKnapsackPacker` | Sorts by composite score descending; greedily adds fragments until budget is exhausted. When a fragment doesn't fit at its current depth, attempts **depth fallback**: re-renders at progressively lower depths (e.g., depth 9 → 4 → 0) until it fits or is excluded. Implements **Iterator** pattern over the depth fallback sequence. | | FragmentOrderer | `RelevanceCoherenceOrderer` | Groups fragments by resource, then orders within each group by containment depth and source position. Groups are ordered by maximum composite score within the group. Configurable via `context.fusion.ordering`: `relevance` (strict score order), `topological` (dependency-aware), `relevance-coherence` (default hybrid). Implements **Template Method** with overridable `_group_key()` and `_intra_group_sort()` hooks. | **Phase 3 defaults:** | Component | Default Class | Algorithm | |-----------|--------------|-----------| | PreambleGenerator | `ProvenancePreambleGenerator` | Generates a structured preamble listing: included resources, strategies used, budget utilization, and a compact structure map. Respects `context.fusion.preamble-max-tokens` limit. Can be disabled via `context.fusion.preamble-enabled = false`. Uses **Builder** pattern to construct preamble sections. | | SkeletonCompressor | `DepthReductionCompressor` | Re-renders all parent context fragments at depth 0-1 (e.g., `MODULE_LISTING` for code, `TABLE_OF_CONTENTS_L1` for documents). Prioritizes fragments closer to the child's focus area. Fits within `skeleton_budget` tokens (derived from `skeleton_ratio`). Uses **Visitor** pattern to traverse and re-render fragments by domain type. | ##### Scope Resolution and Configuration Pipeline components are resolved through a three-level scope chain. Each scope can override any subset of the ten components; unspecified components inherit from the next broader scope. 
class PipelineConfigResolver:
    """Resolves the effective PipelineConfig for a given context assembly.
    Implements the Chain of Responsibility pattern across three scopes."""

    def resolve(
        self,
        plan: Plan | None,
        project: Project | None,
        global_config: GlobalConfig,
    ) -> PipelineConfig:
        # 1. Start with built-in defaults
        config = self._builtin_defaults()
        # 2. Apply global overrides from config.toml
        config = self._apply_scope(config, global_config.pipeline_overrides)
        # 3. Apply project-level overrides (if any)
        if project and project.pipeline_overrides:
            config = self._apply_scope(config, project.pipeline_overrides)
        # 4. Apply plan-level overrides (if any)
        if plan and plan.pipeline_overrides:
            config = self._apply_scope(config, plan.pipeline_overrides)
        return config

    def _apply_scope(self, base: PipelineConfig, overrides: dict) -> PipelineConfig:
        """Merges overrides into the base config using the Prototype pattern.
        Only non-None overrides replace the base component."""
        return PipelineConfig(**{
            field: overrides.get(field, getattr(base, field))
            for field in PipelineConfig.__dataclass_fields__
        })
Pipeline components are registered in TOML configuration: 
# ── Global config.toml ────────────────────────────────────────────
[context.pipeline]
# Override any pipeline component globally (values are "module:ClassName")
strategy-selector     = "builtin:ConfidenceWeightedSelector"   # default
budget-allocator      = "builtin:ProportionalBudgetAllocator"   # default
strategy-executor     = "builtin:ParallelStrategyExecutor"      # default
fragment-deduplicator = "builtin:ContentHashDeduplicator"       # default
detail-depth-resolver = "builtin:MaxDepthResolver"              # default
fragment-scorer       = "builtin:WeightedCompositeScorer"       # default
budget-packer         = "builtin:GreedyKnapsackPacker"          # default
fragment-orderer      = "builtin:RelevanceCoherenceOrderer"     # default
preamble-generator   = "builtin:ProvenancePreambleGenerator"   # default
skeleton-compressor  = "builtin:DepthReductionCompressor"      # default

# ── Per-component configuration ────────────────────────────────────
[context.pipeline.strategy-executor]
timeout-seconds = 30
max-workers = 4
circuit-breaker-threshold = 3

[context.pipeline.fragment-scorer]
relevance-weight = 0.4
hierarchy-weight = 0.3
quality-weight   = 0.2
recency-weight   = 0.1

[context.pipeline.budget-packer]
depth-fallback-steps = [9, 4, 2, 0]   # depths to try during fallback
min-fragment-tokens = 10              # fragments below this are excluded
Project-level and plan-level overrides use the same key structure, specified via the context view YAML or the `agents project context set` CLI: 
# ── Project-level context view YAML ────────────────────────────────
project: local/api-service
view: strategize
pipeline:
  fragment-scorer: "my_extensions.scorers:DomainAwareScorer"
  budget-packer: "my_extensions.packers:PriorityPreservingPacker"
##### Fallback Degradation Path The pipeline's `ConfidenceWeightedSelector` (default StrategySelector) implements automatic fallback: 1. Try `arce` (requires all backends) — if unavailable: 2. Try `breadth-depth-navigator` (requires graph) — if unavailable: 3. Try `semantic-embedding` (requires vector) — if unavailable: 4. Fall back to `simple-keyword` (requires only text search / ripgrep) This ensures the system always produces context, even when advanced backends are not configured. #### Initial Context Assembly Before the actor's first turn, the system assembles initial context: 
class InitialContextAssembler:
    """Produces the starting context for an actor invocation."""

    def assemble(self, plan: Plan, actor: Actor,
                 token_budget: int) -> AssembledContext:
        # 1. Resolve resource scope
        scope = self.scope_resolver.resolve(plan)
        # 2. Get inherited context from parent plan (if any)
        inherited = self._get_inherited_context(plan)
        # 3. Create scoped backend views
        backends = self.bal.create_scoped_views(scope)
        # 4. Build the initial context request from plan metadata
        initial_request = self._build_initial_request(plan, actor, inherited)
        # 5. Run through the Context Assembly Pipeline
        result = self.pipeline.assemble(
            request=initial_request,
            backends=backends,
            budget=token_budget,
            plan_context=PlanContext(
                plan=plan,
                parent_context=inherited,
                depth_in_tree=plan.depth_in_tree,
            ),
        )
        return result
#### Context Inheritance Mechanism 
class PlanContextInheritance:
    """Manages how child plans inherit and refine parent context.
    Uses the pipeline's SkeletonCompressor component to produce
    compact parent context for child plan inheritance."""

    def compute_child_context(self, parent_plan, child_plan, parent_context):
        # 1. Determine the child's focus from the parent's decisions
        child_focus = self._extract_child_focus(parent_plan, child_plan)
        # 2. Compute depth/breadth adjustments
        depth_delta = child_plan.depth_in_tree - parent_plan.depth_in_tree
        child_detail = self._increase_detail(self._avg_detail(parent_context), depth_delta)
        child_breadth = max(1, parent_context.avg_breadth - depth_delta)
        # 3. Compute skeleton budget from the child's token budget
        skeleton_budget = int(child_plan.token_budget * self.config.skeleton_ratio)
        # 4. Use the pipeline's SkeletonCompressor to build the parent skeleton
        skeleton = self.pipeline.skeleton_compressor.compress(
            parent_context=parent_context,
            child_focus=child_focus,
            skeleton_budget=skeleton_budget,
        )
        # 5. Build the inherited context request with parent skeleton
        return ContextRequest(
            focus=child_focus,
            breadth=child_breadth,
            depth=child_detail,
            depth_gradient=True,
            metadata={
                "parent_context_hash": parent_context.context_hash,
                "parent_skeleton": skeleton,
                "inherited_decisions": self._relevant_parent_decisions(parent_plan, child_focus),
            },
        )
##### Skeleton Context Propagation The **skeleton** is a compact, low-depth representation (depth 0-1) of the parent's context window that is passed to every child. This ensures children always have the "big picture" available, even though they focus on a narrow area. The skeleton typically consumes 5-15% of the child's token budget. 

Parent's hot context (32K tokens):
  ┌─ Module: src/auth/          [depth 3/MEMBER_SUMMARY: 2K tokens]
  ├─ Module: src/core/          [depth 3/MEMBER_SUMMARY: 2K tokens]
  ├─ Module: src/api/           [depth 3/MEMBER_SUMMARY: 2K tokens]
  ├─ Module: src/services/      [depth 3/MEMBER_SUMMARY: 2K tokens]
  └─ ... 12 more modules        [depth 3/MEMBER_SUMMARY: 24K tokens]

Child's hot context (32K tokens):
  ┌─ [SKELETON from parent]     [depth 0/MODULE_LISTING: 3K tokens]
  │   Module: src/auth/         [just name + member names]
  │   Module: src/core/         [just name + member names]
  │   Module: src/api/          [just name + member names]
  │   ... etc.
  ├─ [CHILD FOCUS AREA]         [depth 9/FULL_SOURCE: 25K tokens]
  │   Class: AuthManager        [depth 9: all methods with bodies]
  │   Class: TokenValidator     [depth 9: referenced by AuthManager]
  │   Class: User               [depth 4/SIGNATURES: used as parameter type]
  └─ [INHERITED DECISIONS]      [4K tokens]
      Decision: "Use async patterns for all auth operations"
      Decision: "Maintain backward compat with sync callers"
#### Dynamic Context Window Adaptation The context window size may change between invocations. Different LLM providers, different models, different configurations, and even dynamic adjustments during a session can alter the available budget. The ACMS handles this seamlessly. ##### Budget Computation 
class ContextBudgetCalculator:
    """Computes the effective context budget for each assembly cycle."""

    def compute(self, actor: Actor, plan: Plan,
                conversation_history_tokens: int) -> int:
        # 1. Get the actor's hard context window limit
        model_limit = actor.model_config.context_window_tokens
        # 2. Reserve space for system prompt, history, tools, response
        reserved = (self._count_tokens(actor.system_prompt) +
                    conversation_history_tokens +
                    self._estimate_tool_tokens(actor.skills) +
                    actor.model_config.max_output_tokens)
        # 3. Apply the soft cap from context view policy
        soft_cap = self._resolve_view(plan).hot_max_tokens or float('inf')
        # 4. Calculate available budget
        effective_budget = max(0, min(model_limit - reserved, soft_cap))
        return effective_budget
##### Adaptive Behavior When the budget changes between context assembly cycles: 1. **Budget increase**: The pipeline re-runs strategy orchestration (Phase 1) with the expanded budget. The BudgetAllocator distributes the larger budget across strategies, and the BudgetPacker may promote fragments previously rendered at a low depth (e.g., depth 0) to a higher depth (e.g., depth 4 or 9). 2. **Budget decrease**: The pipeline's BudgetPacker re-applies the knapsack with the new budget, potentially reducing fragment depths via its depth fallback mechanism or dropping low-relevance items as ranked by the FragmentScorer. 3. **Strategies are stateless**: Each assembly cycle is independent. The pipeline runs all 10 components from scratch, and strategies receive the current budget and must respect it. ##### Progressive Refinement Within a Session As an actor makes tool calls during a session, the conversation grows and the available budget shrinks. The ACMS handles this through a **context refresh cycle** that triggers re-assembly when the budget changes by more than 30% (configurable via `context.budget.refresh_threshold`). #### Built-in Strategy Catalogue The ACMS ships with several built-in strategies. The ARCE pipeline is one of them, not the only one. ##### Strategy: `simple-keyword` Basic keyword/regex text search. Works with any backend, any resource type. No graph or vector required. This is the universal fallback. Quality score: 0.3. ##### Strategy: `semantic-embedding` Vector similarity search. Finds semantically related content even without exact keyword matches. Requires a vector backend. Quality score: 0.6. ##### Strategy: `breadth-depth-navigator` The graph-aware strategy that uses the depth/breadth projection system. Works with the UKO graph to provide structurally-aware context at any detail depth. Supports focus items, hop traversal, and detail depth gradients. This is the primary strategy for code-aware context. Quality score: 0.85. ##### Strategy: `arce` (Analyze, Retrieve, Contextualize, Execute) The sophisticated multi-modal pipeline. Combines text, vector, and graph search with intent analysis and actor-type-aware patterns. This is the "kitchen sink" strategy that produces the highest quality results but requires all backends. Quality score: 0.95. Actor-type-specific graph traversal patterns: - **Strategy actors**: Broader, shallower traversal. Emphasis on module boundaries and dependency structures. Prioritizes `uko:Container` and `uko:Boundary` nodes. - **Execution actors**: Narrower, deeper traversal. Emphasis on implementation details, function bodies, and test coverage. Prioritizes `uko:Atom` nodes. - **Estimation actors**: Focus on size metrics, complexity indicators, and historical data. Prioritizes temporal data. ##### Strategy: `temporal-archaeology` Searches the cold tier for historical patterns. Useful for understanding "what changed last time we touched this area" or "what decisions were made about this module in the past." Requires graph + cold tier access. Quality score: 0.5. ##### Strategy: `plan-decision-context` Retrieves context from parent and ancestor plan decisions. This is how child plans "remember" what their parent decided and why. Operates on the warm/cold tiers. Quality score: 0.7. #### ACMS Extensibility The ACMS-specific extension points (analyzers, backends, UKO vocabularies, strategies, and pipeline components) are documented in the **Extensibility** section below. See **Extensibility > ACMS Extensions** for the full details. #### UKO Runtime Services The UKO runtime is operationalized through three service classes: - **`UKOQueryInterface`** — Typed interface for ACMS context strategies to query UKO classification data. Provides `classify_resource(uri)` returning a `ClassificationResult` with `layer` (0–3), `primary_type`, `source_resource_id`, and `relationships`. Strategies use this to discover which ontology layer a resource belongs to and what relationships it has. - **`UKOInferenceEngine`** — Semantic analysis service that infers implicit relationships from UKO triples produced by domain analyzers. Infers three relationship types: `uko:implicitSiblingOf` (co-occurrence), `uko:implicitContains` (URI prefix containment), and `uko:implicitDependsOn` (URI reference in object values). Inferred triples are stored with confidence `0.7` to distinguish them from deterministic extractions. - **`UKOGraphPersistence`** — Serializes and restores UKO graph state via JSON or in-memory backends. Used for graph persistence across sessions and for test isolation. The `UKOIndexer.index_graph()` method runs inference via `UKOInferenceEngine` and populates `uko:layer` triples for all four ontology layers during indexing. #### Real-time Index Synchronization The system maintains index freshness through immediate, proactive updates. The `UKOIndexer` produces UKO triples from resources using pluggable analyzers, and simultaneously indexes into text and vector backends: 
class UKOIndexer:
    """Produces UKO triples from resources using pluggable analyzers."""

    def index_resource(self, resource: Resource):
        # 1. Determine the best analyzer for this resource
        analyzer = self.analyzers.get_for_resource(resource)
        # 2. Produce UKO triples using the most specific vocabulary
        triples = analyzer.analyze(resource)
        # 3. Add provenance
        for triple in triples:
            self._add_provenance(triple, resource)
        # 4. Store in graph backend
        self.graph_backend.add_triples(triples)
        # 5. Also index into text and vector backends
        self.text_indexer.index(resource, triples)
        self.vector_indexer.index(resource, triples)
##### Index Lifecycle | Stage | Trigger | Action | Result | |-------|---------|--------|--------| | Resource added | `agents resource add` / `agents project link-resource` | Immediate full indexing | All indices ready for instant search | | Code changed | File modification detected | Immediate incremental update | Indices reflect latest state | | Resource removed | `agents resource remove` / `agents project unlink-resource` | Immediate cleanup | Stale data removed, UKO nodes marked historical | | Maintenance | Scheduled | Full reindex, consistency check | Indices verified and optimized | ##### Fallback to Traditional Search When advanced features are unavailable, the system gracefully degrades. The pipeline's `ConfidenceWeightedSelector` (default StrategySelector component) automatically routes to simpler strategies: 1. Try `arce` (requires all backends) -> if unavailable: 2. Try `breadth-depth-navigator` (requires graph) -> if unavailable: 3. Try `semantic-embedding` (requires vector) -> if unavailable: 4. Fall back to `simple-keyword` (requires only text search / ripgrep) #### ACMS Performance Characteristics ##### Assembly Latency | Operation | Target Latency | Notes | |-----------|---------------|-------| | Resource scope resolution | < 10ms | In-memory set operations | | Scoped backend view creation | < 5ms | Filter injection | | Strategy `can_handle` check (all) | < 20ms | Simple capability checks | | `simple-keyword` assembly | < 100ms | Text search | | `semantic-embedding` assembly | < 200ms | Vector search | | `breadth-depth-navigator` assembly | < 500ms | Graph traversal + materialization | | `arce` assembly | < 1s | Multi-modal search + ranking | | `temporal-archaeology` assembly | < 2s | Cold tier queries | | Fragment fusion pipeline (phases 2-3) | < 100ms | Dedup + depth resolution + scoring + knapsack + ordering + preamble | | **Total initial assembly** | **< 2s** | Parallel strategy execution | | **Incremental refresh** | **< 500ms** | Re-compression only | ##### Indexing and Query Performance | Metric | Performance | |--------|------------| | Text indexing speed | 10,000 files/minute | | Vector indexing speed | 1,000 files/minute (with GPU) | | Graph indexing speed | 5,000 files/minute | | Text search query | < 100ms for 1M files | | Vector search query | < 200ms for 10M embeddings | | Graph traversal query | < 500ms for 3-hop queries | ##### Scalability Guarantees - **100K+ file projects**: The scoping mechanism ensures strategies never see the full dataset. Scoped views filter at the backend level. - **Deep plan hierarchies (10+ levels)**: Skeleton compression ensures parent context overhead stays bounded (10% per level, multiplicatively compressed). - **Concurrent plans**: Each plan gets independent ScopedBackendViews. No cross-plan interference. - **Dynamic budgets**: The knapsack algorithm is O(n) in the number of fragments. Re-compression is O(1) per fragment. - **Maximum scale tested**: 10M files, 1B+ triples, 100M+ embeddings. ##### Progressive Enhancement Path Organizations can adopt ACMS features progressively. At each stage, existing resources are reindexed to take advantage of new capabilities: | Stage | Features | Requirements | Benefit | |-------|----------|-------------|---------| | Basic | Text search, file watching | ripgrep, sqlite | Instant exact-match search | | Semantic | Vector embeddings, similarity search | Embedding model, vector DB | Instant semantic similarity search | | Structural | UKO graph, relationship queries | Graph database, language analyzers | Instant relationship queries | | Intelligent | ML-driven ranking, automated analysis | GPU, training data | Instant intelligent suggestions | | Custom | Domain-specific ontologies, custom analyzers | Domain expertise | Instant domain-aware intelligence | **Summary of Timing**: - **Indexing**: Eager (happens immediately when resources are added/changed) - **Searching**: Instant (because indices are pre-computed and ready) - **Sandboxing**: Lazy (only when execution needs to modify a resource) - **Context Assembly**: Real-time (but fast because it queries ready indices) This design ensures agents never wait for index building during execution, providing a responsive and predictable experience even on massive codebases. ### Storage and Persistence !!! adr "Architecture Decision" The hybrid storage model, database strategy, and migration approach are defined in [ADR-019: Storage and Persistence](adr/ADR-019-storage-and-persistence.md). This section defines the complete storage strategy for every persistent concept in CleverAgents, specifying the storage backend, data format, lifecycle management, and migration strategy for each entity type. #### Storage Architecture Overview CleverAgents uses a **hybrid storage model** combining a relational database for structured data, the filesystem for configuration files and artifacts, and specialized indexes for search operations. The storage layer is accessed exclusively through repository interfaces defined in the domain layer, ensuring that storage backends can be swapped without affecting application logic. ```kroki-plantuml @startuml skinparam componentStyle rectangle skinparam defaultFontSize 12 skinparam packageFontSize 13 skinparam packageFontStyle bold package "Storage Architecture" as SA { package "Relational Database" as RDB #E3F2FD { component [Plans\nDecisions\nProjects\nResources\nSessions\nActors (db)\nInvariants\nChanges\nCheckpoint Metadata\nCorrection Attempts\nAudit Log] as Tables } package "Filesystem" as FS #C8E6C9 { component [Config YAML Files] as Cfg component [Sandbox Worktree Files] as Sbx component [Artifact Storage] as Art } package "Search Indexes" as IDX #F3E5F5 { component [Text (Tantivy)] as TI component [Vector (FAISS)] as VI component [Graph (Neo4j)] as GI component [Checkpoint Store\n(filesystem)] as CS } } @enduml ``` #### Entity Storage Map The following table specifies where each CleverAgents concept is persisted, in both local and server modes: | Entity | Local Storage | Server Storage | Format | Identifier | |---|---|---|---|---| | **Plans** | SQLite `plans` table | Server PostgreSQL | Relational rows | ULID (`plan_id`) | | **Decisions** | SQLite `decisions` table | Server PostgreSQL | Relational rows + JSON `context_snapshot` | ULID (`decision_id`) | | **Projects** | SQLite `projects` table | Server PostgreSQL (for non-`local/` namespaces) | Relational rows | Namespaced name | | **Resources** | SQLite `resources` table + `resource_links` table | Server PostgreSQL | Relational rows + DAG edges | ULID (`resource_id`) | | **Resource Types** | SQLite `resource_types` table + YAML config files | Server PostgreSQL + synced YAML | Relational rows | Namespaced name (built-ins unnamespaced) | | **Actions** | SQLite `actions` table + YAML config files | Server PostgreSQL + synced YAML | Relational rows | Namespaced name | | **Actors** | SQLite `actors` table + YAML config files | Server PostgreSQL + synced YAML | Relational rows + file reference | Namespaced name | | **Skills** | SQLite `skills` table + YAML config files | Server PostgreSQL + synced YAML | Relational rows + file reference | Namespaced name | | **Tools** | SQLite `tools` table + YAML config files | Server PostgreSQL + synced YAML | Relational rows + file reference | Namespaced name | | **Sessions** | SQLite `sessions` table + `session_messages` table | Server PostgreSQL | Relational rows | ULID (`session_id`) | | **Invariants** | SQLite `invariants` table | Server PostgreSQL | Relational rows | Auto-generated ID | | **Automation Profiles** | SQLite `automation_profiles` table + YAML config files | Server PostgreSQL + synced YAML | Relational rows | Namespaced name (built-ins unnamespaced) | | **Changes / ChangeSets** | SQLite `changes` table | Server PostgreSQL | Relational rows | ULID per change | | **Checkpoints** | Filesystem (`/checkpoints//`) + SQLite `checkpoint_metadata` table | Server object storage + PostgreSQL metadata | Git refs or filesystem snapshots + metadata rows | ULID (`checkpoint_id`) | | **Correction Attempts** | SQLite `correction_attempts` table + archived artifacts on filesystem | Server PostgreSQL + object storage | Relational rows + file archives | ULID (`correction_attempt_id`) | | **Artifacts** | Filesystem (`/artifacts//`) | Server object storage (S3-compatible) | Raw files (code, documents, images, etc.) | Filesystem path relative to plan | | **Context Indexes (Text)** | Filesystem (`/index/text/`) | Server-managed index cluster | Tantivy index files or SQLite FTS5 | Index directory per project | | **Context Indexes (Vector)** | Filesystem (`/index/vector/`) | Server-managed FAISS/Qdrant cluster | FAISS index files or Qdrant collections | Index directory per project | | **Context Indexes (Graph)** | Neo4j database or rdflib files | Server-managed Neo4j instance | Graph triples | Graph database per project | | **Configuration** | TOML file (`/config.toml`) | N/A (server has own config) | TOML | Single file | | **Logs** | Filesystem (`/logs/`) | Server-managed log aggregation | Structured JSON (structlog) | Rotated log files | | **Audit Logs** | SQLite `audit_log` table | Server PostgreSQL | Relational rows | Auto-incrementing ID | #### Database Schema Design The relational database follows a normalized design with foreign key constraints enforcing referential integrity. The schema is version-controlled through Alembic migrations. **Key design decisions:** 1. **ULID primary keys**: All time-series entities (plans, decisions, checkpoints, correction attempts) use ULID primary keys. This provides natural time-ordering without separate timestamp indexes, collision-free generation without coordination, and URL-safe string representation. 2. **JSON columns for semi-structured data**: Fields like `context_snapshot`, `alternatives_considered`, `artifacts_produced`, and `resource_bindings` are stored as JSON text columns. This avoids over-normalization for data that is always read and written as a unit, while still being queryable via SQLite's `json_extract()` or PostgreSQL's `jsonb` operators. 3. **Soft delete pattern**: Entities that support archival (actions, actors, skills) use a `state` column with values like `available`, `archived`. No rows are physically deleted except during explicit `agents init` reset or retention policy enforcement. 4. **Optimistic concurrency control**: The `updated_at` timestamp column on mutable entities serves as a version check. Update operations include `WHERE updated_at = ` to detect concurrent modifications. On conflict, the operation fails with an explicit error rather than silently overwriting. 6. **PlanResult Domain Model — `result_success` column** (migration `m9_003_plan_result_success_column`): The legacy `plans` table includes a dedicated `result_success BOOLEAN NULLABLE` column that explicitly records the success status of the result (apply) phase. `PlanRepository._to_domain` derives `PlanResult.success` from this column rather than from `error_message is None`. The `error_message` column is shared between the build phase and the result phase; using it to infer result success would incorrectly mark plans as failed when a build-phase error was recorded but the apply phase later succeeded. When `result_success` is `NULL` (pre-migration records), the repository falls back to the legacy `error_message is None` heuristic for backward compatibility. 5. **Datetime handling contract**: All timestamps stored in the database are UTC ISO 8601 strings (format: `YYYY-MM-DDTHH:MM:SS.ffffff`). All Python datetime comparisons involving stored timestamps MUST parse the stored string back to a timezone-aware `datetime` object before comparing — **never** compare ISO timestamp strings lexicographically. String comparison is incorrect because different timezone offset formats (`+00:00` vs `Z` vs `+05:30`) produce strings that are not lexicographically comparable even when representing the same moment. The canonical pattern is: ```python from datetime import datetime, UTC def parse_utc_ts(ts_str: str) -> datetime: """Parse a stored ISO timestamp string to a UTC-aware datetime.""" dt = datetime.fromisoformat(str(ts_str)) return dt if dt.tzinfo is not None else dt.replace(tzinfo=UTC) # Correct: compare datetime objects if parse_utc_ts(stored_expires_at) >= datetime.now(UTC): ... # Wrong: string comparison (do not do this) # if stored_expires_at >= datetime.now(UTC).isoformat(): # BUG ``` For database-level comparisons (e.g., `DELETE WHERE expires_at < ?`), pass the ISO string produced by `datetime.now(UTC).isoformat()` only when the database column was also written using the same Python UTC isoformat — ensuring consistent format. Prefer Python-side datetime parsing over relying on lexicographic string ordering. **Core tables (SQLite DDL):** 
-- Plans table: the fundamental unit of orchestration
CREATE TABLE plans (
    plan_id TEXT PRIMARY KEY,                    -- ULID
    parent_plan_id TEXT REFERENCES plans(plan_id),
    root_plan_id TEXT NOT NULL REFERENCES plans(plan_id),
    action_name TEXT NOT NULL,                    -- namespaced action name
    phase TEXT NOT NULL DEFAULT 'strategize',     -- action|strategize|execute|apply
    state TEXT NOT NULL DEFAULT 'queued',         -- queued|processing|errored|complete|cancelled
    attempt INTEGER NOT NULL DEFAULT 1,
    automation_profile_name TEXT NOT NULL,
    effective_profile_snapshot TEXT NOT NULL,      -- JSON: frozen profile at creation
    arguments TEXT,                                -- JSON: action arguments
    project_names TEXT NOT NULL,                   -- JSON array of project names
    strategy_actor_name TEXT,
    execution_actor_name TEXT,
    estimation_actor_name TEXT,
    invariant_actor_name TEXT,
    created_by TEXT,                               -- session ID or user identity
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now')),
    updated_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now')),
    completed_at TEXT,
    error_message TEXT,
    error_traceback TEXT,
    cost_estimate_usd REAL,
    cost_actual_usd REAL,
    token_count_input INTEGER DEFAULT 0,
    token_count_output INTEGER DEFAULT 0
);

CREATE INDEX idx_plans_parent ON plans(parent_plan_id);
CREATE INDEX idx_plans_root ON plans(root_plan_id);
CREATE INDEX idx_plans_phase_state ON plans(phase, state);
CREATE INDEX idx_plans_action ON plans(action_name);
CREATE INDEX idx_plans_created ON plans(created_at);

-- Decisions table: the decision tree
CREATE TABLE decisions (
    decision_id TEXT PRIMARY KEY,                 -- ULID
    plan_id TEXT NOT NULL REFERENCES plans(plan_id),
    parent_decision_id TEXT REFERENCES decisions(decision_id),
    decision_type TEXT NOT NULL,                   -- prompt_definition|invariant_enforced|
                                                   -- strategy_choice|subplan_spawn|
                                                   -- subplan_parallel_spawn|implementation_choice
    question TEXT NOT NULL,
    chosen_option TEXT NOT NULL,
    alternatives_considered TEXT,                  -- JSON array of alternative options
    confidence_score REAL,                         -- 0.0-1.0
    rationale TEXT,
    context_snapshot TEXT NOT NULL,                -- JSON: hot_context_hash, relevant_resources,
                                                   --       actor_state_ref
    downstream_plan_ids TEXT,                      -- JSON array of child plan ULIDs
    artifacts_produced TEXT,                       -- JSON array of artifact references
    is_correction BOOLEAN DEFAULT FALSE,
    corrects_decision_id TEXT REFERENCES decisions(decision_id),
    superseded_by TEXT REFERENCES decisions(decision_id),
    sequence_number INTEGER NOT NULL,              -- ordering within this plan
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now'))
);

CREATE INDEX idx_decisions_plan ON decisions(plan_id);
CREATE INDEX idx_decisions_parent ON decisions(parent_decision_id);
CREATE INDEX idx_decisions_type ON decisions(decision_type);
CREATE INDEX idx_decisions_superseded ON decisions(superseded_by) WHERE superseded_by IS NOT NULL;

-- Resources table: the resource registry
CREATE TABLE resources (
    resource_id TEXT PRIMARY KEY,                  -- ULID
    name TEXT,                                     -- namespaced name (NULL for auto-discovered children)
    resource_type_name TEXT NOT NULL,              -- namespaced type name
    classification TEXT NOT NULL,                  -- physical|virtual
    description TEXT,
    properties TEXT,                               -- JSON: type-specific properties
    location TEXT,                                 -- physical resources only
    content_hash TEXT,                             -- for equivalence tracking
    sandbox_strategy TEXT,                         -- override per resource
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now')),
    updated_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now'))
);

CREATE UNIQUE INDEX idx_resources_name ON resources(name) WHERE name IS NOT NULL;
CREATE INDEX idx_resources_type ON resources(resource_type_name);
CREATE INDEX idx_resources_classification ON resources(classification);

-- Resource DAG: parent/child relationships
CREATE TABLE resource_links (
    parent_id TEXT NOT NULL REFERENCES resources(resource_id),
    child_id TEXT NOT NULL REFERENCES resources(resource_id),
    link_type TEXT DEFAULT 'contains',            -- contains|references|derived_from
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now')),
    PRIMARY KEY (parent_id, child_id)
);

CREATE INDEX idx_resource_links_child ON resource_links(child_id);

-- Project-resource linkage
CREATE TABLE project_resources (
    project_name TEXT NOT NULL,
    resource_id TEXT NOT NULL REFERENCES resources(resource_id),
    read_only BOOLEAN DEFAULT FALSE,
    linked_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now')),
    PRIMARY KEY (project_name, resource_id)
);

-- Checkpoint metadata (actual data on filesystem)
CREATE TABLE checkpoint_metadata (
    checkpoint_id TEXT PRIMARY KEY,               -- ULID
    plan_id TEXT NOT NULL REFERENCES plans(plan_id),
    decision_id TEXT REFERENCES decisions(decision_id),
    checkpoint_type TEXT NOT NULL,                 -- pre_write|post_step|manual
    resource_id TEXT REFERENCES resources(resource_id),
    filesystem_path TEXT NOT NULL,                 -- relative path within checkpoint dir
    size_bytes INTEGER,
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now'))
);

CREATE INDEX idx_checkpoints_plan ON checkpoint_metadata(plan_id);

-- Correction attempts
CREATE TABLE correction_attempts (
    correction_attempt_id TEXT PRIMARY KEY,        -- ULID
    plan_id TEXT NOT NULL REFERENCES plans(plan_id),
    original_decision_id TEXT NOT NULL REFERENCES decisions(decision_id),
    new_decision_id TEXT REFERENCES decisions(decision_id),
    mode TEXT NOT NULL,                            -- revert|append
    guidance TEXT NOT NULL,
    archived_artifacts_path TEXT,                  -- filesystem path to archived originals
    state TEXT NOT NULL DEFAULT 'pending',         -- pending|executing|complete|failed
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now')),
    completed_at TEXT
);

CREATE INDEX idx_corrections_plan ON correction_attempts(plan_id);

-- Audit log for apply operations
CREATE TABLE audit_log (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    event_type TEXT NOT NULL,                      -- plan_applied|plan_cancelled|resource_modified|
                                                   -- correction_applied|config_changed
    plan_id TEXT,
    project_name TEXT,
    actor_name TEXT,
    user_identity TEXT,
    details TEXT NOT NULL,                         -- JSON: event-specific details
    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%f', 'now'))
);

CREATE INDEX idx_audit_event ON audit_log(event_type);
CREATE INDEX idx_audit_plan ON audit_log(plan_id) WHERE plan_id IS NOT NULL;
CREATE INDEX idx_audit_created ON audit_log(created_at);
#### Filesystem Layout The data directory follows a deterministic layout. All paths are relative to `core.data-dir` (default: `~/.cleveragents`): 

~/.cleveragents/
├── config.toml                    # Global configuration
├── cleveragents.db                # SQLite database (WAL mode)
├── cleveragents.db-wal            # WAL file (auto-managed by SQLite)
├── cleveragents.db-shm            # Shared memory file (auto-managed)
├── logs/
│   ├── cleveragents.log           # Current log file (structured JSON)
│   ├── cleveragents.log.1         # Rotated log files
│   └── ...
├── cache/
│   ├── models/                    # Cached model artifacts
│   ├── tools/                     # Cached tool downloads
│   └── templates/                 # Compiled Jinja2 templates
├── backups/
│   ├── 2026-02-08T12-30-00/       # Timestamped backup snapshots
│   └── ...
├── checkpoints/
│   ├── 01HXR1C1D2E3F4G5H6I7.../  # Per-plan checkpoint directories
│   │   ├── chk_01HXR1E1.tar.gz   # Compressed checkpoint snapshots
│   │   └── ...
│   └── ...
├── artifacts/
│   ├── 01HXR1C1D2E3F4G5H6I7.../  # Per-plan artifact directories
│   │   ├── src/routes/health.py   # Generated/modified artifacts
│   │   └── ...
│   └── ...
├── index/
│   ├── text/
│   │   ├── local_api-service/     # Per-project Tantivy indexes
│   │   └── ...
│   ├── vector/
│   │   ├── local_api-service/     # Per-project FAISS indexes
│   │   └── ...
│   └── graph/
│       └── ...                     # rdflib stores or Neo4j connection info
├── sessions/
│   └── ...                         # Session state files (if needed beyond DB)
└── contexts/
    └── ...                         # Exported/cached context snapshots
#### Data Lifecycle and Retention | Data Type | Retention Policy | Cleanup Trigger | |---|---|---| | Plans (active) | Indefinite until the plan reaches `applied` or `cancelled` state | Manual deletion | | Plans (terminal) | Governed by `core.backup.retention-days` for archives | Automatic cleanup daemon | | Decisions | Retained as long as parent plan exists | Cascade delete with plan | | Checkpoints | `sandbox.checkpoint.max-per-plan` per plan; oldest pruned first (keeping first + most recent) | After apply or on retention limit | | Correction archives | `core.backup.retention-days` after plan reaches `applied` state | Automatic cleanup daemon | | Logs | `core.log.retention-days` | Daily rotation + age-based cleanup | | Backups | `core.backup.retention-days` | Age-based cleanup | | Cache | No automatic retention; manual cleanup via `agents diagnostics --cleanup` | User-initiated | | Search indexes | Rebuilt on resource add/remove; no explicit retention | Re-index on change | | Audit logs | Indefinite (critical for compliance) | Manual archival only | #### Migration Strategy Database schema changes are managed through Alembic migrations with the following rules: 1. **Forward-only in production**: Downgrade scripts are provided but only used in development. Production deployments only move forward. 2. **Auto-apply on startup**: When `CLEVERAGENTS_AUTO_APPLY_MIGRATIONS` is set (default in development), migrations run automatically on first database access. In production, migrations are triggered by `agents init` or explicit upgrade commands. 3. **Backward compatibility window**: Each migration maintains backward compatibility with the previous schema version for at least one minor release cycle, allowing rolling upgrades in server mode. 4. **Data migration separation**: Schema DDL changes and data transformations are kept in separate migration steps to enable rollback of data changes independently. ### Observability !!! adr "Architecture Decision" The observability strategy, structured logging, metrics, and distributed tracing are defined in [ADR-025: Observability and Logging](adr/ADR-025-observability-and-logging.md). CleverAgents implements a comprehensive observability strategy across three pillars — logging, metrics, and tracing — designed to provide full visibility into plan execution, actor behavior, tool invocations, and resource access. Every significant operation in the system is observable, enabling debugging of complex multi-plan hierarchies and performance optimization. #### Structured Logging All logging uses **structlog** with JSON output format. Every log entry includes contextual fields that enable correlation across plan hierarchies: 
import structlog

logger = structlog.get_logger()

# Every log entry automatically includes bound context
logger = logger.bind(
    plan_id="01HXR1C1D2E3F4G5H6I7J8K9L0",
    phase="execute",
    actor_name="anthropic/claude-3.5-sonnet",
    session_id="01HXM2A6K1P2E9Q9D4GQ7J4S7Z",
)

# Example: tool invocation logging
logger.info(
    "tool_invoked",
    tool_name="local/write-file",
    skill_name="local/file-ops",
    resource_id="01HXR1A1B2C3D4E5F6G7H8J9K0",
    resource_type="git-checkout",
    input_schema_hash="sha256:a1b2c3...",
    duration_ms=142,
    writes=True,
    checkpoint_created=True,
)
**Log levels and their semantics:** | Level | Usage | Examples | |---|---|---| | `DEBUG` | Internal state transitions, context building details, LLM prompt construction | "Building hot context: 12 files, 8,420 tokens", "Decision confidence computed: 0.87" | | `INFO` | Significant lifecycle events, phase transitions, tool completions | "Plan entered execute phase", "Tool write-file completed in 142ms", "Validation passed: pytest" | | `WARNING` | Degraded operations, approaching limits, non-fatal issues | "Budget at 82% ($4.10/$5.00)", "Checkpoint pruned: exceeded max-per-plan", "Provider fallback: openai -> anthropic" | | `ERROR` | Operation failures, invariant violations, unrecoverable tool errors | "Validation failed: pytest exited 1", "Invariant violated: API compatibility", "LLM provider error: rate limited" | **Log correlation**: Every log entry within a plan execution context includes `plan_id`, `root_plan_id`, `parent_plan_id`, `phase`, `state`, and `attempt`. This enables tracing a single decision through the entire plan hierarchy using standard log querying tools (e.g., `jq '.plan_id == "01HXR1C1..."'`). #### Event System CleverAgents emits domain events for every significant state change. Events flow through two channels: 1. **RxPY Reactive Stream**: Real-time event stream for in-process subscribers (TUI updates, progress bars, streaming output). Uses `Subject` for fan-out distribution. 2. **Persistent Event Log**: All events are written to the `audit_log` table for post-hoc analysis and compliance. **Event taxonomy:** 
from enum import Enum
from pydantic import BaseModel
from datetime import datetime

class EventType(StrEnum):
    # Plan lifecycle events
    PLAN_CREATED = "plan.created"
    PLAN_PHASE_CHANGED = "plan.phase_changed"
    PLAN_STATE_CHANGED = "plan.state_changed"
    PLAN_APPLIED = "plan.applied"
    PLAN_CANCELLED = "plan.cancelled"
    PLAN_ERRORED = "plan.errored"
    PLAN_ESTIMATION_COMPLETE = "plan.estimation_complete"  # emitted after Strategize when estimation_actor is set

    # Decision events
    DECISION_CREATED = "decision.created"
    DECISION_APPROVED = "decision.approved"
    DECISION_CORRECTED = "decision.corrected"
    DECISION_SUPERSEDED = "decision.superseded"

    # Invariant events
    INVARIANT_RECONCILED = "invariant.reconciled"
    INVARIANT_VIOLATED = "invariant.violated"
    INVARIANT_ENFORCED = "invariant.enforced"

    # Actor events
    ACTOR_INVOKED = "actor.invoked"
    ACTOR_COMPLETED = "actor.completed"
    ACTOR_ERRORED = "actor.errored"
    ACTOR_ESCALATED = "actor.escalated"       # confidence below threshold

    # Tool events
    TOOL_INVOKED = "tool.invoked"
    TOOL_COMPLETED = "tool.completed"
    TOOL_ERRORED = "tool.errored"
    TOOL_RETRIED = "tool.retried"

    # Resource events
    RESOURCE_ACCESSED = "resource.accessed"
    RESOURCE_MODIFIED = "resource.modified"
    RESOURCE_INDEXED = "resource.indexed"

    # Correction events
    CORRECTION_APPLIED = "correction.applied"

    # Configuration events
    CONFIG_CHANGED = "config.changed"

    # Entity lifecycle events
    ENTITY_DELETED = "entity.deleted"

    # Authentication events (server-mode only)
    AUTH_SUCCESS = "auth.success"
    AUTH_FAILURE = "auth.failure"

    # Sandbox events
    SANDBOX_CREATED = "sandbox.created"
    SANDBOX_COMMITTED = "sandbox.committed"
    SANDBOX_ROLLED_BACK = "sandbox.rolled_back"
    CHECKPOINT_CREATED = "checkpoint.created"
    CHECKPOINT_RESTORED = "checkpoint.restored"

    # Context events
    CONTEXT_BUILT = "context.built"
    CONTEXT_QUERY_EXECUTED = "context.query_executed"

    # Context tier lifecycle events
    TIER_PROMOTED = "tier.promoted"
    TIER_DEMOTED = "tier.demoted"
    TIER_EVICTED = "tier.evicted"

    # Validation events
    VALIDATION_STARTED = "validation.started"
    VALIDATION_PASSED = "validation.passed"
    VALIDATION_FAILED = "validation.failed"
    VALIDATION_FIX_ATTEMPTED = "validation.fix_attempted"
    VALIDATION_FIX_SUCCEEDED = "validation.fix_succeeded"
    VALIDATION_FIX_EXHAUSTED = "validation.fix_exhausted"

    # Session events
    SESSION_CREATED = "session.created"
    SESSION_MESSAGE_SENT = "session.message_sent"

    # Cost events
    BUDGET_WARNING = "budget.warning"
    BUDGET_EXCEEDED = "budget.exceeded"


class DomainEvent(BaseModel):
    """Base event model emitted by all domain operations."""
    event_type: EventType
    timestamp: datetime                          # UTC; defaults to now(UTC)
    correlation_id: str                           # ULID linking related events in one request chain
    plan_id: str | None = None
    root_plan_id: str | None = None
    session_id: str | None = None
    actor_name: str | None = None
    project_name: str | None = None
    user_identity: str | None = None           # Authenticated user; None in local (unauthenticated) mode
    details: dict                                  # Event-type-specific payload
**Event emission pattern**: Domain services emit events through an injected `EventBus` interface. The infrastructure layer provides two implementations: 
from typing import Protocol
import rx
from rx.subject import Subject

class EventBus(Protocol):
    def emit(self, event: DomainEvent) -> None: ...
    def subscribe(self, event_type: EventType, handler: Callable) -> None: ...

class ReactiveEventBus:
    """In-process event bus using RxPY for real-time distribution."""
    def __init__(self):
        self._subject = Subject()
        self._subscriptions: dict[EventType, list[Callable]] = {}

    def emit(self, event: DomainEvent) -> None:
        # Push to reactive stream for real-time subscribers
        self._subject.on_next(event)
        # Persist to audit log
        self._persist_audit(event)
        # Dispatch to type-specific handlers
        for handler in self._subscriptions.get(event.event_type, []):
            handler(event)

    def subscribe(self, event_type: EventType, handler: Callable) -> None:
        self._subscriptions.setdefault(event_type, []).append(handler)

    @property
    def stream(self) -> rx.Observable:
        """Raw observable stream for advanced RxPY operators."""
        return self._subject
#### LLM Call Tracing Every LLM invocation is traced with full context for debugging and cost tracking: 
# Trace record for each LLM call
class LLMTrace(BaseModel):
    trace_id: str                     # ULID
    plan_id: str
    decision_id: str | None
    actor_name: str
    provider: str                     # openai, anthropic, google, etc.
    model: str                        # gpt-4o, claude-3.5-sonnet, etc.
    prompt_tokens: int
    completion_tokens: int
    total_tokens: int
    cost_usd: float
    latency_ms: int
    temperature: float
    tool_calls: list[str]             # tool names invoked by the LLM
    context_hash: str                 # hash of the context window contents
    context_refs: list[str]           # resource IDs referenced in context
    streaming: bool
    retry_count: int
    error: str | None
    timestamp: datetime
**LangSmith integration**: When `CLEVERAGENTS_LANGSMITH_ENABLED` is `true`, all LLM traces are additionally forwarded to LangSmith for visualization, comparison, and cost analysis. The integration maps CleverAgents plan IDs to LangSmith run tags, enabling filtering by plan hierarchy in the LangSmith UI. #### Metrics Collection CleverAgents collects operational metrics for performance monitoring and capacity planning. Metrics are emitted as structured log entries (for local mode) and optionally exported to Prometheus (for server mode): | Metric | Type | Description | |---|---|---| | `plan.duration_seconds` | Histogram | Total wall-clock time per plan, labeled by phase | | `plan.cost_usd` | Counter | Cumulative API cost per plan | | `plan.decisions_count` | Counter | Number of decisions per plan | | `plan.child_plans_count` | Counter | Number of child plans spawned | | `actor.invocation_duration_ms` | Histogram | Per-actor invocation latency | | `actor.token_usage` | Counter | Token counts by provider and model | | `tool.invocation_duration_ms` | Histogram | Per-tool invocation latency | | `tool.error_rate` | Counter | Tool invocation failures by tool name | | `context.build_duration_ms` | Histogram | Context building time by tier (hot/warm/cold) | | `context.tokens_used` | Gauge | Current token usage in hot context | | `index.query_duration_ms` | Histogram | Index query latency by backend (text/vector/graph) | | `sandbox.operation_duration_ms` | Histogram | Sandbox create/commit/rollback time | | `validation.duration_seconds` | Histogram | Per-validation tool invocation execution time | | `validation.pass_rate` | Counter | Validation pass/fail counts (from `passed` field in return JSON) | #### Diagnostic Dashboard The `agents diagnostics` command provides a real-time health check combining all observability data: 1. **System health**: Config file readability, database accessibility, disk space, provider API key validation. 2. **Index health**: Text index status, vector index dimensionality and count, graph store connectivity. 3. **Active plan overview**: Running plans, queued plans, resource utilization. 4. **Cost summary**: Current session cost, budget utilization, provider-level breakdown. 5. **Performance summary**: Average plan duration, tool call latency percentiles, context build times. ### Security Model !!! adr "Architecture Decision" Sandbox isolation is covered in [ADR-015: Sandbox and Checkpoint](adr/ADR-015-sandbox-and-checkpoint.md). The server-mode security model is defined in [ADR-023: Server Mode](adr/ADR-023-server-mode.md). CleverAgents implements a defense-in-depth security model addressing five concerns: sandbox isolation, access control, prompt injection mitigation, secret management, and audit logging. The security model differs between local mode (single-user, trusted environment) and server mode (multi-user, potentially untrusted environment). #### Sandbox Isolation The sandbox is the primary safety mechanism preventing untested changes from reaching production resources. Every plan's Execute phase runs within an isolated sandbox unless explicitly disabled by the automation profile (`require_sandbox: false`). **Sandbox strategies and their security properties:** | Strategy | Isolation Level | Resource Type | Mechanism | Rollback | |---|---|---|---|---| | `git_worktree` | Process-level filesystem isolation | Git repositories | Creates a separate git worktree on a plan-specific branch. Changes are confined to the worktree directory. Merge back to main requires explicit apply. | `git checkout -- .` or worktree deletion | | `copy_on_write` | Process-level filesystem isolation | Filesystems with native CoW support (e.g., BTRFS, ZFS) | Leverages the filesystem's native copy-on-write capability to create a lightweight snapshot. The filesystem preserves original blocks when edits occur, requiring no explicit copy. Only available on CoW-capable filesystems. | Restore from snapshot | | `filesystem_copy` | Process-level filesystem isolation | All writable filesystems | Creates an explicit full copy of the resource directory (using `cp` or equivalent). Works on any writable filesystem regardless of CoW support, at the cost of duplicating data upfront. Original files are never modified during execution. | Delete the copy directory | | `overlay` | Process-level filesystem isolation | Filesystems supporting overlay mounts | Uses an overlay filesystem (e.g., OverlayFS) to layer changes on top of the original. Writes go to the upper layer; the lower layer remains untouched. | Remove the overlay mount | | `transaction_rollback` | Database transaction isolation | Databases | Opens a database transaction with `SERIALIZABLE` isolation level. All changes are staged within the transaction. Commit on apply; rollback on cancel/error. | `ROLLBACK` | | `none` | No isolation | Any | Changes are applied directly. Requires `require_sandbox: false` in the automation profile. Only appropriate when external safety mechanisms exist. | No automatic rollback | **Sandbox security invariants:** 1. **No cross-sandbox access**: Each plan's sandbox is isolated. Plan A cannot read or write Plan B's sandbox contents. The sandbox path is derived deterministically from the plan ULID, preventing path traversal. 2. **Read-only source guarantee during Execute**: The original project resources are never modified during Execute. All tool write operations target the sandbox copy. 3. **Atomic apply**: The Apply phase is an atomic operation — either all sandbox changes are committed to the real resources, or none are. For git-based resources, this uses git merge. For database resources, this uses transaction commit. 4. **Sandbox cleanup**: Sandbox directories are cleaned up according to `sandbox.cleanup` policy. Sensitive data (API responses, LLM outputs) is purged from the sandbox on cleanup. **Path containment implementation contract:** All path containment checks (verifying that a resolved path is inside a sandbox root) MUST use `Path.is_relative_to(root)` (Python 3.9+) or equivalent path-semantic comparison — **never** string prefix comparison (`str(path).startswith(str(root))`). String prefix comparison is incorrect: a sandbox root of `/tmp/sandbox` would incorrectly pass `/tmp/sandboxmalicious/file.txt` because the string starts with `/tmp/sandbox`. The canonical implementation is: ```python def validate_path(path_str: str, sandbox_root: str | None = None) -> Path: root = Path(sandbox_root).resolve() if sandbox_root else Path.cwd().resolve() target = (root / path_str).resolve() if not (target == root or target.is_relative_to(root)): raise ValueError(f"Path traversal detected: '{path_str}' escapes sandbox root '{root}'") return target ``` This invariant applies to all built-in tools, MCP tool adapters, and any infrastructure code that validates file paths against sandbox boundaries. #### Prompt Injection Mitigation In server mode, where user-provided content may flow into LLM prompts, CleverAgents implements several mitigations: 1. **Input sanitization**: User-provided text in action arguments, invariant text, and session prompts is sanitized before inclusion in LLM prompts. HTML entities, control characters, and known injection patterns are escaped or rejected. 2. **Prompt boundary markers**: System prompts and user content are separated by clear boundary markers that the LLM is instructed to recognize. The system prompt explicitly states that content between `[USER_CONTENT_START]` and `[USER_CONTENT_END]` markers is user-provided and should not be treated as system instructions. 3. **Output validation**: LLM outputs that are used as tool invocations are validated against the tool's JSON Schema before execution. This prevents the LLM from being tricked into invoking tools with malicious parameters. 4. **Tool capability restrictions**: Tools declare their capabilities (`read_only`, `writes`, `checkpointable`, `side_effects`). The execution engine enforces these declarations — a tool declared as `read_only` cannot invoke write operations even if the LLM requests it. 5. **Unsafe tool gating**: Tools marked as `unsafe` (e.g., arbitrary shell execution, network access) are blocked unless the automation profile explicitly sets `allow_unsafe_tools: true`. In server mode, only administrators can create automation profiles that allow unsafe tools. #### Secret Management Secrets (API keys, database credentials, authentication tokens) are managed through a layered approach: 1. **Environment variables (preferred)**: Provider API keys (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.) and the server token (`CLEVERAGENTS_SERVER_TOKEN`) are read from environment variables. This is the recommended approach for both local and CI environments. 2. **Configuration file (fallback)**: API keys can be stored in `config.toml` under the `provider.*` section. The config file should have restrictive permissions (`chmod 600`). The `agents diagnostics` command warns if config file permissions are too permissive. 3. **Secret masking in logs**: All log output and CLI display automatically masks values that match known secret patterns (keys starting with `sk-`, `sk-ant-`, `tok_`, etc.). Masked values are replaced with `***REDACTED***`. The masking is applied at the structlog processor level, ensuring no secret leaks through any log path. 4. **Secret masking in LLM context**: Before constructing LLM prompts, the context builder scans for patterns matching known secret formats and replaces them with `[REDACTED]`. This prevents accidental exposure of secrets in LLM training data (for providers that use customer data for training, which CleverAgents discourages). 5. **Server mode credential isolation**: In server mode, each user's API keys are stored encrypted in the server database using AES-256-GCM with a per-user key derived from the server's master secret. Keys are decrypted only at the moment of LLM invocation and are never transmitted to the client CLI. #### Exception Handling and Error Classification All exceptions surfacing through the CLI are processed by the `cleveragents.core.error_handling` module, which provides three guarantees: **classification**, **redaction**, and **safe wrapping**. **Error classification**: Every exception is mapped to an HTTP-like numeric error code via the exception class hierarchy. The mapping uses the exception's MRO (Method Resolution Order) to find the most specific match: | Range | Category | Examples | |---|---|---| | 400-range | Client / input errors | `ValidationError` → 422, `ResourceNotFoundError` → 404, `AuthenticationError` → 401, `RateLimitError` → 429 | | 500-range | Server / infrastructure errors | `DatabaseError` → 522, `NetworkError` → 524, `ProviderError` → 520, `ConfigurationError` → 525 | Unknown exceptions (not inheriting from `CleverAgentsError`) default to code 500 (`INTERNAL`). **Secret redaction in error output**: Both the exception **message** and its **details** dict are redacted before display. Redaction delegates to `cleveragents.shared.redaction` (the single redaction implementation shared with structlog processors and CLI output). This ensures: - Key names matching sensitive substrings (`api_key`, `password`, `secret`, `token`, `credential`, `auth`, etc.) have values fully replaced with `***REDACTED***`. - String values are scanned for known secret patterns (OpenAI keys, Anthropic keys, JWT tokens, GitHub PATs, GitLab PATs, Bearer tokens). - Nested dicts and lists are recursively redacted. - Error details always enforce redaction (`show_secrets=False`) regardless of the global `show_secrets` flag. **Safe wrapping of unexpected exceptions**: The `wrap_unexpected` function converts bare `Exception` instances into `CleverAgentsError` with a generic, user-safe message (`"An unexpected error occurred"`). Internal stack details are captured in the error's `details` dict for diagnostics but are not shown to the user. If the exception is already a `CleverAgentsError`, it is returned unchanged with optional context merged into a copy of its details. **CLI integration**: The top-level error handlers in `cli/main.py` use `classify_error` for `CleverAgentsError` exceptions and `wrap_unexpected` + `classify_error` for bare exceptions. CLI output includes the error code and category name for consistent, machine-parseable error reporting: ``` Error [422] VALIDATION_FAILED: name is required Error [500] INTERNAL: An unexpected error occurred ``` See `docs/reference/error_handling.md` for the complete API reference and exception hierarchy. #### Audit Logging All security-relevant operations are recorded in the `audit_log` table with the following events: | Event Type | Trigger | Details Captured | |---|---|---| | `plan_applied` | `agents plan apply` | Plan ID, project names, files changed, lines added/removed, resources modified, apply duration, user identity | | `plan_cancelled` | `agents plan cancel` | Plan ID, reason, project names, cancelled phase, cancelled processing state, last completed step, subplan count, sandbox refs, changeset ID, resources pending cleanup | | `resource_modified` | Tool write operations during Execute | Resource ID, modification type, sandbox path, tool name | | `correction_applied` | `agents plan correct` | Correction attempt ID, original decision ID, mode, guidance | | `config_changed` | `agents config set` | Key, old value (masked if secret), new value (masked if secret), user identity | | `entity_deleted` | `agents delete/remove` | Entity type, entity name, cascade effects | | `session_created` | `agents session create` | Session ID, actor name, user identity | | `auth_success` | Server mode login | User identity, IP address, token prefix | | `auth_failure` | Server mode failed login | Attempted identity, IP address, failure reason | **Audit log retention**: Audit logs are never automatically deleted. In server mode, audit logs can be exported for compliance archival using server administration commands. In local mode, audit logs are preserved in the SQLite database indefinitely and are included in backup snapshots. ### Extensibility !!! adr "Architecture Decision" The extensibility model and plugin architecture are grounded in the layered design defined in [ADR-001: Layered Architecture](adr/ADR-001-layered-architecture.md) and the configuration system in [ADR-024: Configuration System](adr/ADR-024-configuration-system.md). CleverAgents is designed as an extensible platform where every major subsystem supports custom implementations. The extensibility model follows the **Open/Closed Principle** — the system is open for extension through well-defined interfaces, but closed for modification of core behavior. #### Plugin Architecture Overview ```kroki-plantuml @startuml skinparam componentStyle rectangle skinparam defaultFontSize 12 skinparam packageFontSize 13 skinparam packageFontStyle bold skinparam componentFontSize 11 package "Extension Points" as EP { package "User-Facing Extensions" as UFE #C8E6C9 { component [Custom Tools\n(YAML/Python)] as CT component [Custom Skills\n(YAML)] as CS component [Custom Actors\n(YAML/Graph)] as CA } package "Integration Extensions" as IE #E3F2FD { component [MCP Servers\n(stdio/SSE)] as MCP component [Agent Skills\nStandard] as ASS component [Custom LLM\nProviders] as CLP } package "Core Registries" as CR #F3E5F5 { component [Tool Registry\nSkill Registry\nActor Registry\nProvider Registry] as REG } package "Infrastructure Extensions" as INF #FFF9C4 { component [Custom Resource\nTypes (YAML)] as CRT component [Custom Sandbox\nStrategies (Python)] as CSS component [Custom Index\nBackends] as CIB } package "ACMS Pipeline Extensions" as ACMS #E8EAF6 { component [Custom UKO\nAnalyzers / Vocabularies] as UKO component [Custom Context\nStrategies] as CCS component [Custom Pipeline\nComponents (10 slots)] as CPC } CT -down-> REG CS -down-> REG CA -down-> REG MCP -down-> REG ASS -down-> REG CLP -down-> REG REG -down-> CRT REG -down-> CSS REG -down-> CIB REG -down-> UKO REG -down-> CCS REG -down-> CPC } @enduml ``` #### Tool Extensibility Tools are the atomic unit of execution and the primary extension point. There are five ways to add tools: 1. **Custom Python tools**: Define a tool with inline Python code in a YAML configuration file. The code runs in a sandboxed execution context with access to the plan context, resource bindings, and checkpoint API. 
# File: tools/my-custom-tool.yaml
   tool:
     name: local/analyze-complexity
     description: "Compute cyclomatic complexity for Python files"
     source: custom

     input_schema:
       type: object
       properties:
         file_path: { type: string }
       required: [file_path]

     output_schema:
       type: object
       properties:
         complexity: { type: integer }
         functions: { type: array }

     capability:
       writes: false
       checkpointable: false

     resource_slots:
       - name: source
         type: git-checkout
         binding: contextual

     code: |
       import ast
       content = ctx.resources["source"].read(params["file_path"])
       tree = ast.parse(content)
       # ... complexity analysis ...
       return {"complexity": total, "functions": results}
2. **MCP server tools**: Any MCP-compliant server can expose tools to CleverAgents. Skills reference MCP servers by their transport configuration: 
# File: skills/kubernetes-ops.yaml
   skill:
     name: local/kubernetes-ops
     description: "Kubernetes cluster management tools"
     mcp_servers:
       - transport: stdio
         command: npx
         args: ["-y", "@anthropic/mcp-kubernetes"]
3. **Agent Skills Standard tools**: Tools organized in standard folder structures are auto-discovered and registered: 
skill:
     name: local/project-tools
     agent_skills_dirs:
       - ./agent-skills/
4. **Built-in tools**: Core file operations (`read_file`, `write_file`, `edit_file`, `delete_file`, `move_file`, `list_files`, `search_files`), plan operations (`create-subplan`), and system operations are provided as built-in tools grouped into built-in skills. 5. **Anonymous inline tools**: Tools can be defined inline within actor graph nodes or skill definitions for one-off operations that don't need global registration. **Tool lifecycle hooks**: Every tool follows a four-phase lifecycle — `discover` (find available capabilities), `activate` (prepare for use, acquire connections), `execute` (perform the operation), `deactivate` (release resources). The tool registry manages these lifecycle transitions. #### Skill Extensibility Skills compose tools into capability collections. Skills support: - **Tool aggregation**: Reference named tools from the Tool Registry - **Inline anonymous tools**: Define tools directly in the skill YAML - **Skill inclusion**: Include other skills by reference (composability) - **MCP server aggregation**: Expose tools from one or more MCP servers - **Agent Skills Standard**: Expose tools from Agent Skills Standard directories #### Actor Extensibility Actors can be extended through: 1. **YAML-defined agents**: Single LLM actors with custom system prompts, temperature settings, tool bindings, and capability constraints. 2. **YAML-defined graphs**: LangGraph topologies with multiple actors and tool nodes connected by edges, conditional routing, and parallel execution groups. 3. **Provider extension**: New LLM providers can be added by implementing the `AIProviderInterface` protocol and registering with the `ProviderRegistry`. The registry uses auto-discovery to detect installed `langchain-*` packages. 
from typing import Protocol

class AIProviderInterface(Protocol):
    """Protocol for LLM provider implementations."""

    @property
    def provider_name(self) -> str: ...

    @property
    def capabilities(self) -> ProviderCapabilities: ...

    def create_chat_model(
        self,
        model: str,
        temperature: float = 0.7,
        **kwargs,
    ) -> BaseChatModel: ...

    def create_embedding_model(
        self,
        model: str,
        **kwargs,
    ) -> BaseEmbeddings: ...
#### Custom Resource Types New resource types extend CleverAgents to manage any kind of resource: 
# File: resource-types/docker-registry.yaml
resource_type:
  name: local/docker-registry
  description: "Docker container registry"
  classification: physical
  user_addable: true

  cli_args:
    - name: registry_url
      type: string
      required: true
    - name: repository
      type: string
      required: true
    - name: tag
      type: string
      default: "latest"

  sandbox_strategy: none    # Docker images are immutable
  handler: docker_registry_handler

  child_types:
    - type: local/docker-image
      relationship: contains
      auto_discover: true

  auto_discovery:
    enabled: true
    strategy: list_tags
#### Custom Index Backends The indexing layer is abstracted behind three interfaces (text, vector, graph). Custom implementations can be registered for each: 
class TextIndexBackend(Protocol):
    """Interface for full-text search backends."""
    def index_document(self, project: str, doc_id: str, content: str, metadata: dict) -> None: ...
    def search(self, project: str, query: str, limit: int) -> list[SearchResult]: ...
    def remove_document(self, project: str, doc_id: str) -> None: ...
    def rebuild_index(self, project: str) -> None: ...

class VectorIndexBackend(Protocol):
    """Interface for vector similarity search backends."""
    def index_embedding(self, project: str, doc_id: str, embedding: list[float], metadata: dict) -> None: ...
    def search_similar(self, project: str, query_embedding: list[float], limit: int, min_relevance: float) -> list[VectorResult]: ...
    def remove_embedding(self, project: str, doc_id: str) -> None: ...

class GraphIndexBackend(Protocol):
    """Interface for knowledge graph backends."""
    def add_triple(self, project: str, subject: str, predicate: str, obj: str) -> None: ...
    def query(self, project: str, sparql: str) -> list[dict]: ...
    def remove_triples(self, project: str, subject: str | None, predicate: str | None, obj: str | None) -> None: ...
New backends are registered via configuration: 
# config.toml
[index.text]
backend = "custom"
custom_module = "my_extensions.elasticsearch_backend"
custom_class = "ElasticsearchTextIndex"

[index.text.custom_options]
hosts = ["http://localhost:9200"]
index_prefix = "cleveragents"
#### Custom Sandbox Strategies The sandbox layer supports custom isolation strategies for specialized resource types: 
class SandboxStrategy(Protocol):
    """Interface for sandbox isolation strategies."""
    def create(self, plan_id: str, resource: Resource) -> SandboxRef: ...
    def read(self, ref: SandboxRef, path: str) -> bytes: ...
    def write(self, ref: SandboxRef, path: str, content: bytes) -> Change: ...
    def diff(self, ref: SandboxRef) -> DiffView: ...
    def commit(self, ref: SandboxRef) -> None: ...
    def rollback(self, ref: SandboxRef) -> None: ...
    def checkpoint(self, ref: SandboxRef, checkpoint_id: str) -> None: ...
    def restore_checkpoint(self, ref: SandboxRef, checkpoint_id: str) -> None: ...
    def cleanup(self, ref: SandboxRef) -> None: ...
Custom strategies are mapped to resource types via the resource type configuration's `sandbox_strategy` field, or globally via `sandbox.strategy` config. #### Plugin Security Contract The plugin loading system enforces a security boundary: module imports are restricted to a configurable prefix allowlist to prevent arbitrary code execution from untrusted configuration. However, **protocol validation must never instantiate the plugin class** to perform type checking. Instantiation during validation runs `__init__` side effects (network connections, file I/O, subprocess spawning) before the plugin is approved for use. **Protocol compliance MUST be checked structurally** using `issubclass()` for `@runtime_checkable` protocols, or by inspecting declared methods — never by creating a live instance: ```python # Correct: structural check only — no instantiation @staticmethod def validate_protocol(klass: type[Any], protocol: type[Any]) -> bool: try: return issubclass(klass, protocol) except TypeError: return False # Wrong: instantiates the class, running __init__ side effects (do not do this) # instance = klass() # BUG: arbitrary code execution during validation # return isinstance(instance, protocol) ``` This contract applies to all plugin loaders in the Infrastructure layer (provider plugins, custom tool plugins, custom index backend plugins, custom sandbox strategy plugins, and ACMS extension plugins). #### ACMS Extensions The ACMS provides five categories of extension points: UKO analyzers, index backends, context strategies, UKO vocabularies, and Context Assembly Pipeline components. ##### Domain and Language-Specific Analyzers Analyzers are pluggable components that parse resources and produce UKO triples. They are organized by domain (code, documents, data, infrastructure) and then by specific technology within each domain: 
PluginSystem:
  analyzers:
    # --- Source Code Analyzers (Layer 1: uko-code + Layer 2/3) ---
    python:
      class: "PythonAnalyzer"
      features: [AST parsing, Type inference via mypy, Import resolution, Docstring extraction]
    typescript:
      class: "TypeScriptAnalyzer"
      features: [TSC-based parsing, Type extraction, Module resolution, JSDoc parsing]
    rust:
      class: "RustAnalyzer"
      features: [rust-analyzer integration, Lifetime analysis, Trait resolution, Macro expansion]
    custom_dsl:
      class: "CustomDSLAnalyzer"
      config:
        grammar: "path/to/grammar.peg"
        semantic_rules: "path/to/rules.yaml"

    # --- Document Analyzers (Layer 1: uko-doc) ---
    markdown:
      class: "MarkdownAnalyzer"
      features: [Heading hierarchy, Link extraction, Code block detection, Topic inference, Cross-reference resolution]
    restructuredtext:
      class: "ReStructuredTextAnalyzer"
      features: [Directive parsing, Role resolution, Cross-reference resolution, Index extraction]
    html:
      class: "HTMLDocumentAnalyzer"
      features: [Semantic HTML parsing, Heading extraction, Link graph, Readability scoring]

    # --- Data Schema Analyzers (Layer 1: uko-data) ---
    postgresql:
      class: "PostgreSQLAnalyzer"
      features: [Schema introspection, DDL extraction, Foreign key graph, View dependency analysis, Stored procedure parsing, Statistics collection]
    mysql:
      class: "MySQLAnalyzer"
      features: [Schema introspection, DDL extraction, Foreign key graph, Trigger parsing]
    sqlite:
      class: "SQLiteAnalyzer"
      features: [Schema introspection, DDL extraction, Virtual table detection]

    # --- Infrastructure Analyzers (Layer 1: uko-infra) ---
    docker_compose:
      class: "DockerComposeAnalyzer"
      features: [Service graph, Port mapping, Volume resolution, Environment variable extraction]
    kubernetes:
      class: "KubernetesAnalyzer"
      features: [Resource parsing, Service dependency graph, ConfigMap/Secret references, Ingress routing]
##### Index Backend Providers 
  backends:
    graph:
      - { name: "blazegraph", class: "BlazegraphBackend", features: ["SPARQL", "reasoning"] }
      - { name: "neo4j", class: "Neo4jBackend", features: ["Cypher", "APOC", "GDS"] }
    vector:
      - { name: "faiss", class: "FaissBackend", features: ["GPU acceleration", "HNSW"] }
      - { name: "qdrant", class: "QdrantBackend", features: ["filtering", "payloads"] }
  embedders:
    - { name: "openai", class: "OpenAIEmbedder", models: ["text-embedding-3-large"] }
    - { name: "local", class: "LocalEmbedder", models: ["all-MiniLM-L6-v2"] }
##### Adding a New UKO Vocabulary (e.g., for Terraform) 
@prefix uko-tf: <https://cleveragents.ai/ontology/uko/infra/terraform#> .

uko-tf:TerraformModule a owl:Class ;
    rdfs:subClassOf uko-infra:ConfigBlock, uko:Container .
uko-tf:Resource a owl:Class ;
    rdfs:subClassOf uko:Container .
uko-tf:Variable a owl:Class ;
    rdfs:subClassOf uko-infra:ConfigKey .
uko-tf:Output a owl:Class ;
    rdfs:subClassOf uko:Boundary .
uko-tf:provisionsOn a owl:ObjectProperty ;
    rdfs:subPropertyOf uko:dependsOn ;
    rdfs:domain uko-tf:Resource ;
    rdfs:range uko-infra:Service .
##### Adding a New Context Strategy 
class MyDomainStrategy:
    name = "my-namespace/domain-strategy"
    capabilities = StrategyCapabilities(
        uses_graph=True, uses_text=True,
        uko_levels=["uko:", "uko-tf:"],
        resource_types=["*"],
        supports_depth_breadth=True,
        quality_score=0.8,
    )

    def can_handle(self, request, backends):
        if any("terraform" in f for f in request.focus):
            return 0.9
        return 0.0

    def assemble(self, request, backends, budget, plan_context):
        # Custom logic...
        ...
Register via config: 
[context.strategies.custom]
"my-namespace/domain-strategy" = "my_package.strategies.MyDomainStrategy"
##### Replacing Pipeline Components Any of the 10 Context Assembly Pipeline components can be replaced by implementing the corresponding Protocol and registering the implementation. Components can be overridden at three scopes (plan > project > global), with more specific scopes taking precedence. 
class MyCustomScorer:
    """A domain-aware fragment scorer that boosts infrastructure fragments
    when the plan focuses on deployment tasks."""

    def score(self, fragments: list[ContextFragment],
              plan_context: PlanContext) -> list[ScoredFragment]:
        scored = []
        is_deploy = "deploy" in plan_context.plan.description.lower()
        for f in fragments:
            base_score = f.relevance_score * 0.4 + f.hierarchy_weight * 0.3
            if is_deploy and "uko-infra:" in f.uko_uri:
                base_score *= 1.5  # Boost infrastructure fragments
            scored.append(ScoredFragment(**vars(f), composite_score=base_score))
        return sorted(scored, key=lambda s: s.composite_score, reverse=True)
Register via TOML config (global scope): 
[context.pipeline]
fragment-scorer = "my_extensions.scorers:MyCustomScorer"
Or via project-level context view YAML: 
project: local/api-service
view: strategize
pipeline:
  fragment-scorer: "my_extensions.scorers:MyCustomScorer"
The following table shows which Protocol each pipeline slot implements and what the default implementation provides: | Pipeline Slot | Protocol | Default Implementation | Design Pattern | |---|---|---|---| | `strategy-selector` | `StrategySelectorProtocol` | `ConfidenceWeightedSelector` | Strategy | | `budget-allocator` | `BudgetAllocatorProtocol` | `ProportionalBudgetAllocator` | Strategy | | `strategy-executor` | `StrategyExecutorProtocol` | `ParallelStrategyExecutor` | Circuit Breaker | | `fragment-deduplicator` | `FragmentDeduplicatorProtocol` | `ContentHashDeduplicator` | Strategy | | `detail-depth-resolver` | `DetailDepthResolverProtocol` | `MaxDepthResolver` | Specification | | `fragment-scorer` | `FragmentScorerProtocol` | `WeightedCompositeScorer` | Decorator | | `budget-packer` | `BudgetPackerProtocol` | `GreedyKnapsackPacker` | Iterator | | `fragment-orderer` | `FragmentOrdererProtocol` | `RelevanceCoherenceOrderer` | Template Method | | `preamble-generator` | `PreambleGeneratorProtocol` | `ProvenancePreambleGenerator` | Builder | | `skeleton-compressor` | `SkeletonCompressorProtocol` | `DepthReductionCompressor` | Visitor | #### Extension Points Summary | Extension Point | Registration Mechanism | Configuration Format | Discovery | |---|---|---|---| | **Custom Tools** | `agents tool add --config ` | YAML | Manual registration | | **MCP Server Tools** | Referenced in skill YAML `mcp_servers` section | YAML | Auto-discovered from MCP server | | **Agent Skills Standard** | Referenced in skill YAML `agent_skills_dirs` section | Folder structure | Auto-discovered from directory | | **Custom Skills** | `agents skill add --config ` | YAML | Manual registration | | **Custom Actors** | `agents actor add --config ` | YAML | Manual registration | | **Custom Resource Types** | `agents resource type add --config ` | YAML | Manual registration | | **Custom LLM Providers** | Python package installation + ProviderRegistry auto-discovery | Python module | Auto-discovered via `langchain-*` package naming | | **Custom Index Backends** | `config.toml` `index.*.custom_module` | TOML + Python module | Configuration-driven | | **Custom Sandbox Strategies** | Resource type `sandbox_strategy` field | YAML + Python module | Configuration-driven | | **Custom Automation Profiles** | `agents automation-profile add --config ` | YAML | Manual registration | | **Custom Invariant Actors** | Standard actor registration + assignment via `--invariant-actor` | YAML | Manual assignment | | **Custom UKO Analyzers** | `config.toml` `context.uko.analyzers.custom.*` | TOML + Python module | Configuration-driven | | **Custom UKO Vocabularies** | Turtle/RDF files + analyzer registration | RDF/Turtle + TOML | Configuration-driven | | **Custom Context Strategies** | `config.toml` `context.strategies.custom.*` | TOML + Python module | Configuration-driven | | **Pipeline: StrategySelector** | `config.toml` `context.pipeline.strategy-selector` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain: plan > project > global > built-in) | | **Pipeline: BudgetAllocator** | `config.toml` `context.pipeline.budget-allocator` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: StrategyExecutor** | `config.toml` `context.pipeline.strategy-executor` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: FragmentDeduplicator** | `config.toml` `context.pipeline.fragment-deduplicator` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: DetailDepthResolver** | `config.toml` `context.pipeline.detail-depth-resolver` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: FragmentScorer** | `config.toml` `context.pipeline.fragment-scorer` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: BudgetPacker** | `config.toml` `context.pipeline.budget-packer` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: FragmentOrderer** | `config.toml` `context.pipeline.fragment-orderer` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: PreambleGenerator** | `config.toml` `context.pipeline.preamble-generator` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | | **Pipeline: SkeletonCompressor** | `config.toml` `context.pipeline.skeleton-compressor` or project/plan YAML | TOML/YAML + Python module | Configuration-driven (scope chain) | ## Milestone Plan This section defines the ordered milestone plan for CleverAgents v3.x, mapping architectural features to verifiable deliverables. Each milestone builds on the previous and is independently testable. Milestones v3.0.0 and v3.1.0 are **complete**. This plan covers v3.2.0 through v3.8.0 — the production-ready target including server mode. !!! note "Milestone Status (as of 2026-04-11)" - **v3.0.0** ✅ CLOSED — Minimal Local Source-Code Workflow - **v3.1.0** ✅ CLOSED — Actor Compiler + Full LLM Integration - **v3.2.0** 🔄 IN PROGRESS — Decisions + Validations + Invariants (571 open / 257 closed) - **v3.3.0** 🔄 IN PROGRESS — Corrections + Subplans + Checkpoints (122 open / 108 closed) - **v3.4.0** 🔄 IN PROGRESS — ACMS v1 + Context Scaling (200 open / 137 closed) - **v3.5.0** 🔄 IN PROGRESS — Autonomy Hardening (971 open / 201 closed) - **v3.6.0** 🔄 IN PROGRESS — Advanced Concepts & Deferred Features (282 open / 150 closed) - **v3.7.0** 🔄 IN PROGRESS — TUI Implementation (526 open / 427 closed) - **v3.8.0** 🔄 IN PROGRESS — Server Implementation (352 open / 132 closed) --- ### v3.2.0 — Decisions + Validations + Invariants **Goal**: Decisions are recorded during Strategize and Execute phases and persisted to the database. Users can view the decision tree, inspect individual decisions, manage invariants, and correct decisions with selective subtree recomputation. **Spec Coverage**: [Decision Tree and Correction](#decision-tree-and-correction), [Invariant System](#invariant-system), [Validation Abstraction](#validation-abstraction) #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | Decision recording during Strategize with full context snapshots | §Decision Tree — Recording Protocol | `agents plan tree ` renders non-empty tree after strategize | | 2 | Decision recording during Execute phase | §Decision Tree — Execute Phase | Execute-phase decisions appear in `plan tree` output | | 3 | `agents plan tree` renders the decision tree with correct hierarchy | §CLI Commands — plan tree | Command exits 0, shows tree structure with decision IDs | | 4 | `agents plan explain ` shows decision details including alternatives | §CLI Commands — plan explain | Output includes `alternatives`, `confidence_score`, `rationale` fields | | 5 | `agents invariant add` creates invariants; `agents invariant list` displays them | §CLI Commands — invariant | Round-trip: add then list shows the invariant | | 6 | Invariants enforced during Strategize phase | §Invariant System — Enforcement | `invariant_enforced` decision type appears in tree when invariant applies | | 7 | `agents plan correct --mode=revert` re-executes from targeted decision point | §Correction Model — Revert Mode | Correction creates new attempt, affected subtree recomputed | | 8 | `agents plan correct --mode=append` adds guidance without recomputing | §Correction Model — Append Mode | Append correction recorded; no subtree recomputation triggered | | 9 | `agents plan correct --dry-run` shows warnings, recompute time, and hint | §Correction Model — Dry Run | Output includes `warnings`, `estimated_recompute_time_seconds`, and "remove --dry-run" hint | | 10 | `plan.attempt` incremented on each correction | §Correction Safety Guarantees | `plan show` displays `Attempt: N` where N > 1 after correction | | 11 | Validation runner executes required and informational validations | §Validation Abstraction | `agents validation attach` + plan execute triggers validation; required failure blocks apply | | 12 | Output validation is flexible — structural checks, not exact character matching | §Testing Strategy | Tests use structural assertions, not string equality | | 13 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **Decision persistence**: All decisions use ULID identifiers; stored in `v3_decisions` table with `context_snapshot` JSONB column. - **Correction atomicity**: `CorrectionService.execute_revert()` MUST increment `plan.attempt` via `PlanLifecycleService` before recomputing the subtree. - **Dry-run purity**: `generate_dry_run_report()` MUST be used for `--dry-run` (not `analyze_impact()`); it preserves correction status at PENDING. - **Invariant precedence**: plan > action > project > global; `non_overridable` global invariants always win. - **Validation read-only**: Validations are always `writes=False`, `checkpointable=False`. #### Definition of Done - All 13 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.2.0 milestone - `agents plan tree`, `plan explain`, `plan correct`, `invariant add/list` all functional end-to-end --- ### v3.3.0 — Corrections + Subplans + Checkpoints **Goal**: Plans can spawn child plans (subplans) during execution. Subplans execute in parallel with configurable concurrency limits. Results are merged back using three-way merge strategies. Checkpointing enables rollback to previous plan states. **Spec Coverage**: [Subplan Architecture](#subplan-architecture), [Checkpoint and Rollback](#checkpoint-and-rollback), [Merge Strategies](#merge-strategies), [Correction Model](#correction-model) #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | Plans spawn child subplans during Execute via `subplan_spawn` decision type | §Subplan Architecture | `plan tree` shows `subplan_spawn` decisions with child plan IDs | | 2 | Sequential subplan execution functional | §Subplan Execution — Sequential | Child plan completes before parent resumes | | 3 | Parallel subplan execution with `max_parallel` limit | §Subplan Execution — Parallel | Multiple child plans execute concurrently up to `max_parallel` | | 4 | Parent plan tracks all subplan statuses | §Subplan Status Tracking | `plan show ` lists child plan statuses | | 5 | Three-way merge combines non-conflicting changes | §Merge Strategies — Three-Way | Non-conflicting file edits from two subplans both appear in merged result | | 6 | Merge conflicts surfaced to user for resolution | §Merge Strategies — Conflict Resolution | Conflicting changes produce `CONFLICT` markers; user prompted | | 7 | Checkpoint creation during Execute | §Checkpoint System | `plan show` lists checkpoints; each has a ULID and timestamp | | 8 | `agents plan rollback --checkpoint ` restores plan state | §CLI Commands — plan rollback | Plan state reverts to checkpoint; subsequent apply uses checkpoint state | | 9 | Correction flow functional (`plan correct --mode revert` and `--mode append`) | §Correction Model | Both modes functional end-to-end (builds on v3.2.0) | | 10 | Correction rejects decisions whose subtree includes applied child plans | §Correction Safety Guarantees | Attempting to correct such a decision returns error with explanation | | 11 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **Subplan identity**: Child plans use ULID identifiers only (no namespaced name); referenced by plan ID in all operations. - **Sandbox isolation**: Each subplan operates in its own sandbox; parent sandbox merges results via `MergeWorkflow`. - **Checkpoint granularity**: Checkpoints capture the full plan state including decision tree, sandbox state hash, and resource versions. - **Parallel limit enforcement**: `max_parallel` is enforced by the `PlanLifecycleService`; excess subplans queue until a slot opens. - **Merge strategy selection**: Strategy selected per resource type; `git-checkout` uses git three-way merge; `fs-mount` uses file-level merge. #### Definition of Done - All 11 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.3.0 milestone - Subplan spawning, parallel execution, checkpoint/rollback, and merge all functional end-to-end --- ### v3.4.0 — ACMS v1 + Context Scaling **Goal**: The Advanced Context Management System v1 is operational. Projects with 10,000+ files can be indexed and queried. The context assembly pipeline produces scoped, budget-constrained context views for actors. Hot/warm/cold storage tiers manage context lifecycle. **Spec Coverage**: [ACMS Architecture](#acms-advanced-context-management-system), [Context Assembly Pipeline](#context-assembly-pipeline), [UKO Ontology](#uko-universal-knowledge-ontology), [Hot/Warm/Cold Tiers](#context-storage-tiers) #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | Context policies configurable with view-specific settings (strategize/execute/apply/default) | §Context Policy Configuration | `agents project context set --view strategize` persists and is retrievable | | 2 | Budget enforcement: `max_file_size` and `max_total_size` constraints respected | §Context Budget Enforcement | Files exceeding `max_file_size` excluded; total context ≤ `max_total_size` | | 3 | `agents project context show` displays current context policy | §CLI Commands — project context show | Command exits 0, shows all configured parameters | | 4 | `agents project context inspect` runs context assembly and shows result | §CLI Commands — project context inspect | Returns assembled context fragments with UKO URIs | | 5 | `agents project context simulate` shows budget simulation without executing | §CLI Commands — project context simulate | Returns token budget breakdown without modifying state | | 6 | Context assembly pipeline produces scoped context output for actors | §Context Assembly Pipeline | Plan execution uses ACMS context; actor receives assembled fragments | | 7 | Hot/warm/cold tier management functional | §Context Storage Tiers | Hot tier bounded by `hot_max_tokens`; overflow moves to warm tier | | 8 | Projects with 10,000+ files index without timeout | §ACMS Scalability | Indexing a 10k-file project completes within 5 minutes | | 9 | UKO ontology indexing for Python and common resource types | §UKO — Technology-Specific Layer | Python files indexed with `uko-py:` URIs; relationships inferred | | 10 | Pluggable context strategies execute in parallel | §Context Strategy Execution | Multiple strategies run concurrently; results fused by `FragmentFusionCoordinator` | | 11 | Skeleton compression for child plan context inheritance | §Skeleton Compressor | Child plans receive compressed parent context via `skeleton_ratio` budget | | 12 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **Pipeline composability**: All 10 Context Assembly Pipeline slots are overridable at plan > project > global scope. - **UKO URI stability**: UKO URIs are stable identifiers; changing a file's content does not change its URI. - **Strategy parallelism**: `ParallelStrategyExecutor` runs strategies concurrently with circuit-breaker protection per strategy. - **Budget packing**: `GreedyKnapsackPacker` fills context up to token budget; fragments ordered by `RelevanceCoherenceOrderer`. - **Tier eviction**: Hot tier evicts to warm on overflow; warm evicts to cold on age threshold; cold is persistent storage. #### Definition of Done - All 12 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.4.0 milestone - ACMS pipeline functional end-to-end; 10k-file project indexes and queries successfully --- ### v3.5.0 — Autonomy Hardening **Goal**: The system can autonomously execute a large-scale task using hierarchical plan decomposition with 4+ levels of subplans, decision correction with selective subtree recomputation, parallel execution scaling to 10+ concurrent subplans, and validation-gated apply. **Spec Coverage**: [Automation Profiles](#automation-profiles), [Safety Profiles](#safety-profiles), [A2A Facade](#agent-to-agent-protocol-a2a), [Guard Enforcement](#guard-enforcement), [Event Queue](#event-queue) #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | A2A facade session and plan lifecycle operations functional via CLI | §A2A Local Facade | `agents session create` and `agents plan use` route through A2A facade | | 2 | Event queue publish/subscribe operational | §Event Queue | Plan lifecycle events published; subscribers receive events | | 3 | Guard enforcement: denylist, budget caps, tool call limits | §Guard Enforcement | Plan exceeding `max_cost_per_plan` is blocked; denylist tools rejected | | 4 | Automation profile resolution precedence correct (plan > action > global) | §Automation Profiles — Precedence | Plan-level profile overrides action-level; action overrides global | | 5 | Safety profile enforcement: `require_sandbox`, `require_checkpoints`, `allow_unsafe_tools` | §Safety Profiles | Plans with `require_sandbox=true` fail if sandbox unavailable | | 6 | Hierarchical decomposition creates 4+ levels of subplans | §Subplan Architecture — Hierarchy | `plan tree` shows 4+ nesting levels for complex tasks | | 7 | Parallel execution scales to 10+ concurrent subplans | §Subplan Execution — Parallel | 10 subplans execute concurrently without deadlock or resource starvation | | 8 | Decision correction recomputes only affected subtree | §Correction Model — Selective Recomputation | Unaffected decisions preserved; only downstream decisions recomputed | | 9 | Validation-gated apply: required validations must pass before apply | §Validation Abstraction — Apply Gating | Apply blocked when required validation fails; informational validation does not block | | 10 | A realistic porting task completes autonomously | §Autonomy Acceptance | End-to-end task (e.g., port a Python module) completes without human intervention | | 11 | `agents automation-profile add/list/show` functional | §CLI Commands — automation-profile | Round-trip: add profile, list shows it, show displays details | | 12 | `agents plan guard` shows active guards for a plan | §CLI Commands — plan guard | Command shows denylist, budget caps, tool limits | | 13 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **A2A facade**: In local mode, `A2aLocalFacade` resolves all A2A operations in-process; no subprocess spawning for local operations. - **Guard evaluation order**: Denylist checked first (fast reject), then budget caps, then tool call limits. - **Autonomy threshold**: `0.0` = always automatic; `1.0` = always manual; eight built-in profiles from `manual` to `full-auto`. - **Subtree recomputation**: Only decisions with `depends_on` edges to the corrected decision are recomputed; others preserved. - **Validation gating**: `required` validations block apply; `informational` validations log but do not block. #### Definition of Done - All 13 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.5.0 milestone - Full autonomy acceptance flow with 4+ subplan levels completes successfully --- ### v3.6.0 — Advanced Concepts & Deferred Features **Goal**: Advanced concepts not needed for basic MVP. Extends beyond core MVP but does not require TUI (v3.7.0) or Server (v3.8.0). Includes advanced context strategies, additional LLM backends, additional resource types, A2A module rename, container tool execution, pluggable scope chain extensions, cost/session budgets, and E2E workflow specification tests. **Spec Coverage**: [LSP Integration](#lsp-integration), [Resource Type Inheritance](#resource-type-inheritance), [Devcontainer Integration](#devcontainer-integration), [Container Resource Types](#container-resource-types), [Advanced Context Strategies](#advanced-context-strategies), [Provider Registry](#provider-registry) #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | ACP → A2A module rename and symbol standardization complete | §A2A Protocol — Module Structure | No `acp` references in public API; all imports use `a2a` namespace | | 2 | LSP Registry: `agents lsp add/list/show/remove` functional | §LSP Integration — Registry | Round-trip: add LSP server, list shows it, show displays capabilities | | 3 | LSP server bound to actor graph node via YAML configuration | §LSP Integration — Actor Binding | Actor with `lsp_bindings` activates LSP server on startup | | 4 | LSP capabilities exposed as tools via `LSPToolAdapter` | §LSP Integration — Tool Adapter | `agents actor run` with LSP-bound actor can invoke `lsp/diagnostics` tool | | 5 | LSP diagnostics injected into ACMS hot context automatically | §LSP Integration — Context Enrichment | Plan execution with LSP-bound actor includes diagnostic fragments in context | | 6 | Resource type inheritance: `inherits` field functional | §Resource Type Inheritance | Subtype resource inherits parent type's tools and sandbox strategy | | 7 | Polymorphic tool matching: tools bound to parent type work with subtypes | §Resource Type Inheritance — Polymorphism | Tool registered for `container-instance` works with `devcontainer-instance` | | 8 | Devcontainer auto-discovery from `.devcontainer/devcontainer.json` | §Devcontainer Integration | `agents resource add git-checkout ` auto-discovers devcontainer | | 9 | Devcontainer lazy activation: container built only when first needed | §Devcontainer Integration — Lazy Activation | Container not started until plan execution requires it | | 10 | Container tool execution: tools run inside devcontainer | §Container Resource Types — Execution | Tool invocation with `execution_environment` set runs in container | | 11 | Additional LLM provider backends registered via `ProviderRegistry` | §Provider Registry | `agents actor add` with non-OpenAI/Anthropic provider works | | 12 | Cloud resource types stubbed with `NotImplementedError` for future implementation | §Cloud Resource Types | `agents resource add cloud-*` validates config but raises `NotImplementedError` for sandbox | | 13 | Pluggable scope chain resolution extensions | §Scope Chain Resolution | Custom scope resolver registered and invoked during name resolution | | 14 | Cost and session budget enforcement | §Safety Profiles — Budget Caps | Plan exceeding `max_cost_per_plan` or `max_total_cost` is blocked | | 15 | E2E workflow specification tests covering all major user workflows | §Testing Strategy — E2E | Robot Framework E2E tests cover: plan lifecycle, correction, subplans, ACMS, invariants | | 16 | Code review tool examples in `examples/` directory | §Workflow Examples | `examples/code-review/` contains working action YAML and actor YAML | | 17 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **ACP deprecation**: The `acp` module is deprecated; all new code uses `a2a`. The `acp` module may remain as a compatibility shim but must not be used in new implementations. - **LSP server lifecycle**: LSP servers start when actor activates and stop when actor deactivates; managed by `LSPRuntime`. - **Resource type inheritance depth**: Maximum chain depth of 5 levels; circular inheritance rejected at registration time. - **Devcontainer resource type**: `devcontainer-instance` inherits from `container-instance`; uses lazy activation pattern. - **Cloud resource stubs**: Cloud SDK integration is planned for v3.8.0+; stubs validate configuration but raise `NotImplementedError` for sandbox provisioning. #### Definition of Done - All 17 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.6.0 milestone - LSP integration, resource type inheritance, devcontainer, and container execution all functional end-to-end --- ### v3.7.0 — TUI Implementation **Goal**: Implement the comprehensive Text User Interface (TUI) and all TUI-dependent features using Textual ≥ 1.0. **Spec Coverage**: [TUI Architecture](#tui), [Persona System](#persona-system), [Reference and Command System](#reference-and-command-system), [TUI Materializer](#tui-materializer) **Key ADRs**: [ADR-044](adr/ADR-044-tui-architecture-and-framework.md), [ADR-045](adr/ADR-045-tui-persona-system.md), [ADR-046](adr/ADR-046-tui-reference-and-command-system.md) #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | `agents tui` launches Textual-based MainScreen | §TUI — MainScreen | Command launches TUI; MainScreen renders without errors | | 2 | 3 sidebar states: hidden / visible / fullscreen | §TUI — Sidebar States | Keyboard shortcuts cycle through all 3 sidebar states | | 3 | Persona system: YAML-based actor + args + scope + presets | §Persona System | `agents persona add --config persona.yaml` creates persona; persona selectable in TUI | | 4 | Reference input system (`@` mode for resources/files) | §Reference and Command System — @ Mode | Typing `@` in input shows resource completion popup | | 5 | Command input system (`/` mode for commands) | §Reference and Command System — / Mode | Typing `/` in input shows command completion popup | | 6 | Shell execution mode (`!` mode) | §Reference and Command System — ! Mode | Typing `!` in input executes shell command; output shown in TUI | | 7 | `TuiMaterializer` A2A integration layer functional | §TUI Materializer | TUI operations route through A2A facade; same operations as CLI | | 8 | Session persistence in SQLite at `~/.local/state/cleveragents/tui.db` | §TUI — Session Persistence | TUI state persists across restarts; previous sessions resumable | | 9 | Dracula theme applied | §TUI — Theme | TUI renders with Dracula color scheme | | 10 | Block cursor navigation | §TUI — Navigation | Block cursor moves through interactive elements | | 11 | Notification system for async events | §TUI — Notifications | Plan phase changes trigger toast notifications | | 12 | Multi-session tabs with independent A2A bindings | §TUI — Multi-Session | Multiple tabs open simultaneously; each has independent session | | 13 | Settings screen functional | §TUI — Settings Screen | Settings screen opens; configuration changes persist | | 14 | Session management screen functional | §TUI — Session Management Screen | Session list shows all sessions; sessions can be created/deleted | | 15 | Content pruning for long conversations | §TUI — Content Pruning | Long conversations pruned to fit display; older messages summarized | | 16 | Safety behaviors: confirmation dialogs for destructive operations | §TUI — Safety Behaviors | Destructive operations (delete, apply) show confirmation dialog | | 17 | Loading states for async operations | §TUI — Loading States | Spinner shown during plan execution; progress updates streamed | | 18 | `agents tui web` launches Textual Web mode | §TUI — Web Mode | Web mode accessible via browser at configured port | | 19 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **Textual version**: Textual ≥ 1.0 required; no compatibility with pre-1.0 API. - **TUI/CLI parity**: All operations available in CLI must be available in TUI via `TuiMaterializer`; no TUI-exclusive features. - **A2A routing**: TUI operations route through `A2aLocalFacade` in local mode; same A2A operations as CLI. - **Session database**: TUI session state stored in `~/.local/state/cleveragents/tui.db` (SQLite); separate from main `~/.local/share/cleveragents/data.db`. - **Persona scope**: Personas are scoped to TUI only; they are not visible to CLI or server mode. #### Definition of Done - All 19 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.7.0 milestone - Full TUI functional end-to-end: launch, persona, reference/command input, multi-session, settings, session management --- ### v3.8.0 — Server Implementation **Goal**: Implement the CleverAgents server and all server-dependent capabilities using the A2A (Agent-to-Agent) protocol standard. The server enables multi-device collaboration, shared namespaces, team RBAC, and cloud-hosted actor execution via LangGraph Platform. **Spec Coverage**: [Server and Client Architecture](#server-and-client-architecture), [A2A Protocol](#agent-to-agent-protocol-a2a), [Authentication and Authorization](#authentication-and-authorization) **Key ADRs**: [ADR-047](adr/ADR-047-acp-standard-adoption.md), [ADR-048](adr/ADR-048-server-application-architecture.md) !!! note "Sequencing" v3.8.0 has no deadline. Development effort should focus on M1–M6 (v3.2.0–v3.7.0) first. v3.8.0 work may proceed in parallel but is not on the critical path for local-mode production readiness. #### Deliverables | # | Deliverable | Spec Reference | Verifiable Check | |---|-------------|----------------|-----------------| | 1 | A2A JSON-RPC 2.0 wire format: standard operations (`message/send`, `message/stream`, task lifecycle) | §Server and Client Architecture — Server Presentation Layer | `curl` to A2A endpoint returns valid JSON-RPC 2.0 response | | 2 | `_cleveragents/` extension method routing: plan lifecycle, registry CRUD, entity sync, namespace management | §Server and Client Architecture — Extension Methods | `_cleveragents/plan/use` creates a plan via server | | 3 | A2A stdio transport (local mode — agent as subprocess) | §A2A Protocol — Local Mode | `agents plan use` routes through A2A stdio transport in local mode | | 4 | A2A HTTP transport (server mode — single JSON-RPC endpoint) | §A2A Protocol — Server Mode | CLI connects to remote server via HTTP; all operations functional | | 5 | LangGraph Platform RemoteGraph integration for server-side actor execution | §Server Infrastructure — LangGraph Platform | Strategy and execution actors run on LangGraph Platform via RemoteGraph | | 6 | Server application structure: FastAPI + A2A SDK server | §Server Application Structure | Server starts, serves Agent Card at discovery endpoint | | 7 | API token authentication: `Authorization: Bearer ` header | §Authentication and Authorization — API Tokens | Requests without valid token return 401; valid token accepted | | 8 | Team RBAC: namespace-scoped read/write/admin permissions | §Authentication and Authorization — Team RBAC | User without write permission cannot create plans in restricted namespace | | 9 | Entity sync via `_cleveragents/sync/*` extension methods | §Entity Sync | `_cleveragents/sync/pull` fetches server entities to local registry | | 10 | Multi-device experience: shared namespaces accessible from any device | §Multi-Device Experience | Plan created on device A visible from device B via shared namespace | | 11 | Shared namespaces: team members access same actors, actions, projects | §Shared Namespaces | Actor in shared namespace usable by all team members | | 12 | PostgreSQL backend for server persistence | §Server Infrastructure — Persistence | Server stores plans, decisions, and registry data in PostgreSQL | | 13 | Server deployment: Docker container with `docker compose up` | §Server Deployment — Docker | `docker compose up` starts server; health check endpoint returns 200 | | 14 | Server deployment: Kubernetes Helm chart | §Server Deployment — Kubernetes | `helm install cleveragents ./charts/cleveragents` deploys to cluster | | 15 | `agents server add` registers a remote server in local config | §CLI Commands — server | Round-trip: add server, list shows it, CLI connects to it | | 16 | `agents server status` shows server health and version | §CLI Commands — server status | Command exits 0, shows server version and uptime | | 17 | Multi-turn interactions forwarded to client: `_cleveragents/fs/*`, `_cleveragents/terminal/*` | §Server Presentation Layer — Multi-Turn | Server-hosted actor can read client-local files via forwarded fs operations | | 18 | Test coverage ≥ 97% | §Quality Gates | `nox -s coverage_report` passes | #### Key Architectural Constraints - **A2A exclusivity**: The server exposes **only** an A2A JSON-RPC 2.0 endpoint. No REST API, no GraphQL, no admin endpoint. - **Shared domain/application layers**: Server and client share identical Domain and Application layer packages. Zero behavioral drift between local and server modes. - **LangGraph Platform**: Actor graphs are deployed to LangGraph Platform as separate deployments; server invokes them via RemoteGraph. The server does NOT run actor graphs in-process. - **PostgreSQL schema**: Server uses the same schema as the SQLite client database, with PostgreSQL-specific extensions for multi-tenancy (namespace isolation, team membership). - **Authentication boundary**: All A2A requests require a valid API token. Tokens are scoped to a namespace; team RBAC controls per-namespace permissions. - **Extension method routing**: `_cleveragents/` methods are routed to Application-layer services. Standard A2A operations (`message/send`, etc.) are routed to `SessionWorkflow` and actor execution. - **Multi-turn forwarding**: When a server-hosted actor needs client-local resources (files, terminal), it sends a `_cleveragents/fs/*` or `_cleveragents/terminal/*` request back to the connected client via the A2A task `input-required` mechanism. #### Definition of Done - All 18 deliverables verified by automated tests - `nox` passes with coverage ≥ 97% - No open P0/P1 bugs in v3.8.0 milestone - Server starts, accepts A2A connections, executes plans via LangGraph Platform, and persists to PostgreSQL - CLI connects to remote server; all plan lifecycle operations functional in server mode --- ### Cross-Milestone Quality Gates These quality gates apply to **every milestone** and must pass before a milestone is considered complete: | Gate | Requirement | Command | |------|-------------|---------| | **Unit Tests** | All BDD Behave scenarios pass | `nox -s unit_tests` | | **Integration Tests** | All Robot Framework tests pass | `nox -s integration_tests` | | **Type Checking** | Zero Pyright errors (strict mode) | `nox -s typecheck` | | **Linting** | Zero Ruff violations | `nox -s lint` | | **Coverage** | ≥ 97% line coverage | `nox -s coverage_report` | | **Security Scan** | No high/critical Bandit findings | `nox -s security_scan` | | **Performance** | No ASV benchmark regressions > 10% | `nox -s benchmarks` | | **Documentation** | All public APIs documented | `nox -s docs` | ### Cross-Milestone Architectural Invariants These architectural invariants must be maintained across all milestones: 1. **Spec-first**: No feature is implemented without spec coverage. If implementation discovers a better approach, the spec is updated first via PR. 2. **Layer boundaries**: Presentation → Application → Domain → Infrastructure. No reverse dependencies. 3. **Type safety**: Full Pyright strict compliance. No `# type: ignore` suppressions. 4. **Fail-fast**: All argument validation at entry points. No silent failures. 5. **ULID identifiers**: Plans, decisions, resources, correction attempts, and validation attachments use ULIDs. Projects, actions, skills, and tools use namespaced names. 6. **Namespace format**: `[[server:]namespace/]name`. `local/` reserved for local-only items. 7. **A2A exclusivity**: All client-server communication uses A2A. No REST API. 8. **BDD tests**: All unit-level tests expressed as Behave/Gherkin scenarios. No xUnit-style tests. 9. **File size limit**: No source file exceeds 500 lines. Split into modules if approaching limit. 10. **Atomic commits**: One logical change per commit. No mixed concerns. ## ACMS v1 — Advanced Context Management System (Milestone v3.4.0) ### Overview The **Advanced Context Management System (ACMS) v1** is the context intelligence layer of CleverAgents. It provides a principled, scalable mechanism for indexing project knowledge, assembling budget-constrained context views, and delivering scoped context payloads to actors for LLM calls. ACMS v1 is the primary deliverable of milestone **v3.4.0 — ACMS v1 + Context Scaling**. ACMS is built on two foundational subsystems: - **UKO (Unified Knowledge Ontology)** — a layered RDF/Turtle ontology that indexes project files, symbols, relationships, and semantic concepts into a queryable knowledge graph. - **CRP (Context Request Protocol)** — a structured protocol through which actors declare what information they need, at what level of detail, and with what scope, triggering a context assembly cycle in the ACMS pipeline. Together, UKO and CRP power a **10-component context assembly pipeline** that transforms raw retrieval results into a budget-constrained, coherently ordered context window for each actor. **Design goals for ACMS v1:** - Support projects with 10,000+ files without timeout or memory exhaustion. - Respect hard token budget ceilings derived from the actor's model context window. - Enable multiple complementary retrieval strategies (keyword, semantic, graph, LLM-driven). - Provide tiered context lifecycle management (hot/warm/cold) with per-actor visibility. - Expose a clean CLI interface for context inspection, simulation, and policy management. --- ### Architecture #### UKO — Unified Knowledge Ontology UKO is the indexing layer. It transforms project resources into a queryable hierarchy of knowledge nodes, each with multiple detail depths enabling progressive disclosure. **Layer structure:** | Layer | Prefix(es) | IRI Namespace | Purpose | |-------|------------|---------------|---------| | 0 | `uko:` | `https://cleveragents.ai/ontology/uko#` | Universal foundation — base information unit types and core relationships | | 1 | `uko-code:`, `uko-doc:`, `uko-data:`, `uko-infra:` | `https://cleveragents.ai/ontology/uko/code#` etc. | General software — modules, callables, types, tests, imports | | 2 | `uko-oo:`, `uko-func:`, `uko-proc:` | `https://cleveragents.ai/ontology/uko/oo#` etc. | Paradigm-specific — OO classes, interfaces, methods, attributes | | 3 | `uko-py:`, `uko-ts:`, `uko-rs:`, `uko-java:` | `https://cleveragents.ai/ontology/uko/py#` etc. | Technology-specific — DetailLevelMap insertions | **Layer 0 root types:** - `InformationUnit` — root of every UKO node; anything that can appear in an actor's context. - `Container` — an information unit that contains other units (file, module, class, section). - `Atom` — a leaf-level information unit (function body, paragraph, config value). - `Annotation` — metadata attached to another unit (comment, docstring, attribute). - `Boundary` — an interface point between containers (export, API endpoint, public method signature). **Core relationship properties:** - `contains` — parent contains child. - `references` — weak reference (e.g. a function mentions a type in a docstring). - `dependsOn` — strong dependency (import, inheritance, call). **Detail depths** enable progressive disclosure: | Depth | Question Answered | What Gets Included | |-------|-------------------|--------------------| | 0 | *What exists?* | Name/identifier only | | 1 | *How is it organized?* | Names of immediate children | | 2 | *What are the key relationships?* | Children + dependency/reference edges | | 3 | *What is each thing's purpose?* | + Short descriptions/summaries | | 4 | *What is the structural shape?* | + Type info, size/count metadata | | 5-8 | *How does it work?* | Progressively more content | | 9 | *Everything.* | Complete content — nothing omitted | When context budget is tight, fragments are downgraded to shallower depths rather than omitted entirely (depth fallback). **Provenance properties** on every UKO node: - `sourceResource` — the CleverAgents Resource (by ULID) this node was extracted from. - `sourcePath` — file path within the resource. - `sourceRange` — byte or line range within the source file (e.g. `42:1-87:0`). **Temporal properties** support versioned knowledge: - `validFrom`, `validUntil`, `isCurrent`, `isRevisionOf`. #### CRP — Context Request Protocol CRP is the structured vocabulary through which actors declare context needs. Each `ContextRequest` triggers a context assembly cycle in the ACMS pipeline. **ContextRequest fields:** | Field | Type | Default | Description | |-------|------|---------|-------------| | `query` | `str \| None` | `None` | Natural language query | | `entities` | `list[str]` | `[]` | Named entities to focus on | | `uko_types` | `list[str]` | `[]` | UKO types to filter | | `focus` | `list[str]` | `[]` | URIs or identifiers to focus on | | `breadth` | `int` | `2` | Dependency hops outward (>= 0) | | `depth` | `int \| str` | `3` | Detail depth — integer or named level | | `depth_gradient` | `bool` | `True` | Items closer to focus get more detail | | `temporal` | `TemporalScope` | `CURRENT` | Temporal scope for retrieval | | `max_tokens` | `int \| None` | `None` | Maximum token budget (>= 0) | | `preferred_strategies` | `list[str]` | `[]` | Preferred context strategies | | `required_backends` | `list[str]` | `[]` | Required data backends | | `priority` | `float` | `0.5` | 0.0 = background, 1.0 = critical | | `purpose` | `str` | `""` | Why this context is needed | **DetailLevelMap** maps named detail levels to integer depths for a UKO domain. Inheritance allows child maps to include all entries from their parent map and insert additional levels. Built-in named levels (universal Layer 0): | Name | Depth | |------|-------| | `MODULE_LISTING` | 0 | | `SIGNATURES` | 4 | | `FULL_SOURCE` | 9 | #### Context Pipeline The ACMS pipeline transforms a `ContextRequest` into an `AssembledContext` through five high-level stages: 1. **Indexing** — Project files are indexed into the UKO ontology by `RepoIndexingService`. Language-specific analyzers extract structural elements (functions, classes, modules, types) into UKO nodes with multiple detail depths. The index is persisted in SQLite and refreshed incrementally on file changes. 2. **Assembly** — A `ContextRequest` triggers the 10-component assembly pipeline. Strategies run in parallel; their results are fused, deduplicated, scored, and packed. 3. **Scoping** — Context is filtered by the project's `ProjectContextPolicy`. Each plan phase (`default` -> `strategize` -> `execute` -> `apply`) may override the policy view, controlling which resources and file paths are visible. 4. **Budget Enforcement** — `ContextBudgetEnforcer` applies `max_file_size` and `max_total_size` constraints. The token budget is a hard ceiling: ``` budget = model_context_window - response_reserve (4096) - tool_definitions - skeleton_allocation ``` Budget refresh is triggered when available budget changes by more than `context.budget.refresh-threshold` (default: 0.30). 5. **Delivery** — The assembled `AssembledContext` (or `ContextPayload`) is delivered to the actor for its LLM call. Child plans inherit a compressed skeleton of their parent's context (default: 15% of child's budget via `SkeletonCompressor`). #### Storage Tiers ACMS v1 manages context fragments across three storage tiers: | Tier | Backend | Latency | Capacity | Actor Visibility | |------|---------|---------|----------|-----------------| | **Hot** | In-memory cache | Low | Token-budget (`max_tokens_hot`, default: 8,000) | All roles | | **Warm** | SQLite (fast disk) | Medium | Decision-count (`max_decisions_warm`, default: 500) | Strategist, Executor | | **Cold** | File archive (compressed) | High | Decision-count (`max_decisions_cold`, default: 5,000) | Strategist only | **Actor roles and tier visibility:** | Role | Sees | |------|------| | `strategist` | hot + warm + cold | | `executor` | hot + warm | | `reviewer` | hot only | **Tier operations:** - `promote(fragment_id)` — cold->warm or warm->hot. - `demote(fragment_id)` — hot->warm or warm->cold (with optional summarisation). - `evict_lru(tier, count)` — evict least-recently-used fragments from a tier. > **v1 Note:** In v1, tier labels on `ContextFragment` are sort-priority labels used for > ranking during assembly (`hot > warm > cold`). Full storage-tier semantics with retention > policies, promotion/demotion, and eviction are implemented in `ContextTierService`. --- ### Module Definitions ACMS v1 follows the project's layered architecture (Domain -> Application -> Infrastructure -> Presentation). #### Domain Layer Domain models are pure Pydantic v2 frozen dataclasses with ULID identifiers and UTC datetimes. No infrastructure dependencies. | Class | Module | Description | |-------|--------|-------------| | `ContextFragment` | `cleveragents.domain.models.core.context_fragment` | Atomic unit of context with UKO node, content, depth, token count, relevance, provenance, and tier | | `FragmentProvenance` | `cleveragents.domain.models.core.context_fragment` | Links a fragment back to its originating resource and location | | `ContextBudget` | `cleveragents.domain.models.core.context_fragment` | Token budget with max and reserved tokens | | `ContextPayload` | `cleveragents.domain.models.core.context_fragment` | Assembled payload with fragments, token count, budget usage, context hash, and provenance map | | `ContextView` | `cleveragents.domain.models.core.context_policy` | Per-phase view controlling resource/path filters and size limits | | `ProjectContextPolicy` | `cleveragents.domain.models.core.context_policy` | Per-project policy with phase-based view inheritance | | `ContextRequest` | `cleveragents.domain.models.acms.crp` | Structured context request issued by an actor via CRP | | `DetailLevelMap` | `cleveragents.domain.models.acms.crp` | Maps named detail levels to integer depths for a UKO domain | | `AssembledContext` | `cleveragents.domain.models.acms.crp` | Fused, budget-respecting context payload delivered to an actor | | `TieredFragment` | `cleveragents.domain.models.acms.context_tiers` | Extends `ContextFragment` with tier placement and access tracking metadata | | `TierBudget` | `cleveragents.domain.models.acms.context_tiers` | Controls capacity per tier | | `ActorContextView` | `cleveragents.domain.models.acms.context_tiers` | Per-actor filtered view configuration with role-based default tiers | | `TierMetrics` | `cleveragents.domain.models.acms.context_tiers` | Hit/miss counters and population counts per tier | | `FileRecord` | `cleveragents.domain.models.acms.context_indexing` | Per-file metadata stored during indexing | | `IndexMetadata` | `cleveragents.domain.models.acms.context_indexing` | Summary record for a repository index | | `RepoIndex` | `cleveragents.domain.models.acms.context_indexing` | Composite object returned by index and refresh operations | #### Application Layer Application services orchestrate domain models and delegate to infrastructure adapters. They are registered as singletons in the DI container. | Class | Module | Description | |-------|--------|-------------| | `ACMSPipeline` | `cleveragents.application.services.acms_service` | Orchestrates the 10-component context assembly pipeline | | `ContextTierService` | `cleveragents.application.services.context_tiers` | Manages fragment lifecycle across hot/warm/cold tiers with LRU eviction | | `RepoIndexingService` | `cleveragents.application.services.context_indexing` | Scans repository resources and builds persistent file-level indexes | | `ContextBudgetEnforcer` | `cleveragents.application.services.acms_service` | Enforces `max_file_size` and `max_total_size` constraints on assembled context | | `ContextStrategyRegistry` | `cleveragents.application.services.context_strategies` | Manages pluggable retrieval strategies; validates capabilities and handles fallback degradation | | `UKOLoader` | `cleveragents.application.services.uko_loader` | Parses `docs/ontology/uko.ttl` into an in-memory ontology graph; resolves inheritance chains | #### Infrastructure Layer Infrastructure adapters implement persistence and external integrations. | Class | Module | Description | |-------|--------|-------------| | `UKOStore` | `cleveragents.infrastructure.acms.uko_store` | RDF storage adapter for UKO ontology nodes; supports query and index operations | | `ContextTierManager` | `cleveragents.infrastructure.acms.context_tier_manager` | Manages hot (in-memory), warm (SQLite), and cold (file) storage backends | | `ContextPersistenceAdapter` | `cleveragents.infrastructure.acms.context_persistence` | SQLAlchemy-backed persistence for `repo_indexes` and `indexed_files` tables | | `TextBackend` | `cleveragents.infrastructure.acms.backends` | Full-text search via Tantivy or SQLite FTS5 | | `VectorBackend` | `cleveragents.infrastructure.acms.backends` | Vector similarity search via FAISS or Qdrant | | `GraphBackend` | `cleveragents.infrastructure.acms.backends` | Graph traversal over UKO structural relationships | | `TemporalBackend` | `cleveragents.infrastructure.acms.backends` | Temporal/cold-tier data access for historical context | #### Presentation Layer CLI commands expose ACMS functionality to users. | Class | Module | Description | |-------|--------|-------------| | `ContextCLI` | `cleveragents.presentation.cli.context` | `agents context list/add/show/clear` commands | | `ProjectContextCLI` | `cleveragents.presentation.cli.project_context` | `agents project context set/show/inspect/simulate` commands | --- ### Data Models #### ContextFragment The atomic unit of context returned by strategies and consumed by the assembly pipeline. | Field | Type | Default | Description | |-------|------|---------|-------------| | `fragment_id` | `str` | auto ULID | Stable unique identifier | | `uko_node` | `str` | required | UKO URI of the source node | | `content` | `str` | required | Rendered text content (max 1,000,000 chars) | | `detail_depth` | `int` | `0` | Resolved depth: 0 (MODULE_LISTING) through 9 (FULL_SOURCE) | | `token_count` | `int` | required | Actual token count of content (>= 0) | | `relevance_score` | `float` | `0.5` | Score from 0.0 to 1.0 | | `provenance` | `FragmentProvenance` | required | Provenance trace | | `tier` | `str` | `"warm"` | Priority tier: `"hot"`, `"warm"`, `"cold"` | | `metadata` | `dict[str, str]` | `{}` | Arbitrary key-value metadata (max 64 entries) | | `created_at` | `datetime` | auto UTC | Creation timestamp | #### ContextBudget | Field | Type | Default | Description | |-------|------|---------|-------------| | `max_tokens` | `int` | `4096` | Maximum total tokens (>= 1) | | `reserved_tokens` | `int` | `512` | Tokens reserved for system prompt (>= 0, < `max_tokens`) | | `available_tokens` | `int` | computed | `max_tokens - reserved_tokens` | #### ProjectContextPolicy Controls what context is available during each ACMS phase via view inheritance: ``` default -> strategize -> execute -> apply ``` Each phase resolves to the first explicitly-set `ContextView` walking up the chain. **ContextView fields:** | Field | Type | Default | Description | |-------|------|---------|-------------| | `include_resources` | `list[str]` | `[]` | Resource names/patterns to include (empty = all) | | `exclude_resources` | `list[str]` | `[]` | Resource names/patterns to exclude | | `include_paths` | `list[str]` | `[]` | File path globs to include (empty = all) | | `exclude_paths` | `list[str]` | `[]` | File path globs to exclude | | `max_file_size` | `int \| None` | `None` | Max file size in bytes (None = no limit) | | `max_total_size` | `int \| None` | `None` | Max total context size in bytes (None = no limit) | Exclusions always take precedence over inclusions. #### AssembledContext / ContextPayload The fused, budget-respecting context payload delivered to an actor. | Field | Type | Description | |-------|------|-------------| | `payload_id` | `str` | ULID identifier | | `plan_id` | `str` | Plan this payload was assembled for | | `fragments` | `tuple[ContextFragment, ...]` | Ordered context fragments | | `total_tokens` | `int` | Sum of fragment `token_count` values | | `budget` | `ContextBudget` | Budget used for assembly | | `budget_used` | `float` | Fraction of budget consumed (0.0-1.0) | | `strategies_used` | `tuple[str, ...]` | Strategy names that contributed | | `context_hash` | `str` | SHA-256 hash of assembled content | | `preamble` | `str \| None` | Optional structure summary (max 200 tokens) | | `provenance_map` | `dict[str, Any]` | Fragment ID -> provenance mapping | | `assembled_at` | `datetime` | UTC timestamp | **Properties:** - `is_within_budget` — `True` if total tokens do not exceed available budget. - `remaining_tokens` — Tokens still available in the budget. #### IndexMetadata | Field | Type | Description | |-------|------|-------------| | `index_id` | `str` | ULID identifier for this index snapshot | | `resource_id` | `str` | ULID of the linked resource | | `indexed_at` | `datetime` | When indexing completed (UTC) | | `file_count` | `int` | Total files in the index | | `token_estimate` | `int` | Sum of all file token counts | | `primary_language` | `str` | Most common language by token count | | `status` | `IndexStatus` | `pending`, `indexing`, `ready`, `stale`, `error` | | `error_message` | `str \| None` | Error details when `status == error` | --- ### Key Interfaces #### ContextAssemblyService (ACMSPipeline) ```python class ACMSPipeline: def assemble( self, plan_id: str, fragments: Sequence[ContextFragment], budget: ContextBudget, strategy: str = "relevance", ) -> ContextPayload: ... def register_strategy(self, name: str, strategy: ContextStrategy) -> None: ... ``` The pipeline applies a named strategy to rank and filter fragments, then runs all 10 pipeline components to produce the final `ContextPayload`. #### ContextBudgetEnforcer ```python class ContextBudgetEnforcer: def enforce( self, view: ContextView, policy: ContextPolicy, ) -> ContextView: ... ``` Applies `max_file_size` and `max_total_size` constraints from the policy to the assembled view, excluding or summarising fragments that exceed limits. #### UKOStore ```python class UKOStore: def query( self, ontology: UKOOntology, query: str, ) -> list[ContextFragment]: ... def index( self, project: Project, ) -> UKOOntology: ... ``` RDF storage adapter for UKO ontology nodes. Supports SPARQL-like queries and full project indexing. #### ContextTierService ```python class ContextTierService: def store(self, fragment: TieredFragment) -> None: ... def get(self, fragment_id: str) -> TieredFragment | None: ... def promote(self, fragment_id: str) -> None: ... # cold->warm or warm->hot def demote(self, fragment_id: str) -> None: ... # hot->warm or warm->cold def evict_lru(self, tier: ContextTier, count: int) -> int: ... def get_for_actor( self, role: ActorRole, project_names: list[str], ) -> list[TieredFragment]: ... def get_scoped_view(self, project_names: list[str]) -> ScopedBackendView: ... def get_metrics(self) -> TierMetrics: ... ``` #### RepoIndexingService ```python class RepoIndexingService: def index_resource( self, resource_id: str, root_path: str | Path, *, include_globs: tuple[str, ...] = (), exclude_globs: tuple[str, ...] = (), max_file_size: int | None = None, max_total_size: int | None = None, ) -> RepoIndex: ... def refresh_index(self, resource_id: str, root_path: str | Path, **kwargs) -> RepoIndex: ... def get_index(self, resource_id: str) -> RepoIndex | None: ... def get_index_status(self, resource_id: str) -> IndexMetadata | None: ... def remove_index(self, resource_id: str) -> bool: ... def cleanup_stale_indexing(self) -> int: ... ``` --- ### 10-Component Pipeline Architecture The ACMS pipeline runs three phases, each containing specific components. All 10 components have explicit Protocol definitions and injectable Default implementations. **Phase 1 — Strategy Orchestration:** | # | Component | Responsibility | |---|-----------|---------------| | 1 | `StrategySelector` | Decides which strategies to invoke and with what confidence. Polls `can_handle()` on each registered strategy. | | 2 | `BudgetAllocator` | Distributes the token budget across selected strategies proportionally. | | 3 | `StrategyExecutor` | Runs strategies in parallel with timeouts (default: 30s), circuit breakers (threshold: 3 failures), and configurable max workers (default: 4). | **Phase 2 — Fragment Fusion:** | # | Component | Responsibility | |---|-----------|---------------| | 4 | `FragmentDeduplicator` | Removes duplicate fragments via content-hash, UKO-identity, or semantic similarity. | | 5 | `DetailDepthResolver` | Resolves conflicts when the same UKO node appears at different detail depths (keeps the most appropriate depth for the budget). | | 6 | `FragmentScorer` | Computes composite relevance scores using weighted factors: relevance (0.4), hierarchy position (0.3), strategy quality (0.2), recency (0.1). | | 7 | `BudgetPacker` | Fits scored fragments into the token budget using a greedy knapsack algorithm with depth fallback (steps: `[9, 4, 2, 0]`). Minimum fragment size: 10 tokens. | | 8 | `FragmentOrderer` | Orders packed fragments for optimal coherence in the context window. | **Phase 3 — Context Finalization:** | # | Component | Responsibility | |---|-----------|---------------| | 9 | `PreambleGenerator` | Generates provenance summaries prepended to assembled context (max tokens: 200). | | 10 | `SkeletonCompressor` | Compresses parent plan context into skeleton form for child plan inheritance (budget ratio: `context.budget.skeleton-ratio`, default: 0.15). | Each component is pluggable via `context.pipeline.*` configuration keys specifying `"module:ClassName"`. All 10 components must execute for every context assembly; components may produce empty output but must not be skipped. **v1 defaults:** Phase 1 uses single-strategy selection, full-budget allocation, and synchronous execution. Phase 2 components are pass-through stubs. Phase 3 components are no-op (no preamble, identity compression). Production implementations are planned for future milestones. --- ### Context Strategies Strategies implement the `ContextStrategy` protocol and are registered in the `ContextStrategyRegistry`. **Built-in strategies:** | Strategy | Quality | Backends | Description | |----------|---------|----------|-------------| | `simple-keyword` | 0.3 | Text | Full-text search via Tantivy or SQLite FTS5 | | `semantic-embedding` | 0.6 | Vector | Vector similarity search via FAISS or Qdrant | | `breadth-depth-navigator` | 0.85 | Graph | Graph traversal from focus nodes, expanding by `request.breadth` hops | | `arce` | 0.95 | All | Multi-modal: text (40%) + vector (40%) + graph (20%); results merged and deduplicated | | `temporal-archaeology` | 0.5 | Graph + Cold | Two-phase: cold-tier historical nodes + graph traversal | | `plan-decision-context` | 0.7 | Warm/Cold | Walks parent/ancestor plan hierarchy, retrieving decision records | Default enabled: `["simple-keyword", "semantic-embedding", "breadth-depth-navigator"]` **Fallback degradation path** (when backends are unavailable): ``` arce -> breadth-depth-navigator -> semantic-embedding -> simple-keyword ``` **StrategyCapabilities fields:** | Field | Type | Default | Description | |-------|------|---------|-------------| | `uses_text` | `bool` | `False` | Requires TextBackend | | `uses_vector` | `bool` | `False` | Requires VectorBackend | | `uses_graph` | `bool` | `False` | Requires GraphBackend | | `uses_temporal` | `bool` | `False` | Requires temporal/cold-tier data | | `quality_score` | `float` | `0.5` | Intrinsic quality score (0.0-1.0) | | `supports_depth_breadth` | `bool` | `False` | Supports depth/breadth projection | | `supports_plan_hierarchy` | `bool` | `False` | Supports plan hierarchy traversal | --- ### CLI Commands #### `agents context` — Context Entry Management | Command | Description | |---------|-------------| | `agents context list` | List context entries for the current project | | `agents context add` | Add a context entry | | `agents context show ` | Show details of a specific context entry | | `agents context clear` | Clear all context entries for the current project | #### `agents project context` — Project Context Policy and ACMS Management | Command | Description | |---------|-------------| | `agents project context set PROJECT [OPTIONS]` | Persist a context policy view and ACMS pipeline configuration for a project | | `agents project context show PROJECT [OPTIONS]` | Display the context policy and ACMS pipeline configuration | | `agents project context inspect PROJECT [OPTIONS]` | Inspect the effective context state (tier metrics, fragment distribution, actor visibility) | | `agents project context simulate PROJECT [OPTIONS]` | Run a dry-run context window assembly | **`agents project context set` key options:** | Option | Default | Description | |--------|---------|-------------| | `--view` | `default` | Phase view: default, strategize, execute, apply | | `--include-resource` | — | Resource pattern to include (repeatable) | | `--exclude-resource` | — | Resource pattern to exclude (repeatable) | | `--include-path` | — | File path glob to include (repeatable) | | `--exclude-path` | — | File path glob to exclude (repeatable) | | `--max-file-size` | `None` | Max file size in bytes | | `--max-total-size` | `None` | Max total context size in bytes | | `--hot-max-tokens` | `8000` | Max tokens for the hot tier context window | | `--warm-max-decisions` | `500` | Max decisions for the warm tier | | `--cold-max-decisions` | `5000` | Max decisions for the cold tier | | `--strategy` | — | Preferred context strategy (repeatable) | | `--default-breadth` | `2` | Default breadth for context retrieval | | `--default-depth` | `3` | Default depth (integer or named level) | | `--skeleton-ratio` | `0.2` | Skeleton compression ratio (0.0-1.0) | | `--temporal-scope` | `current` | Temporal scope: current, recent, or all | | `--auto-refresh/--no-auto-refresh` | `True` | Auto-refresh context on resource changes | --- ### Integration Points #### Plan Lifecycle Integration Context assembly is triggered at each plan phase transition (see ADR-006). The ACMS pipeline runs before the actor's LLM call for each phase: 1. `strategize` — full context assembly with `breadth-depth-navigator` + `semantic-embedding`. 2. `execute` — focused context assembly scoped to the current task. 3. `apply` — minimal context assembly; primarily hot-tier fragments. Child plans inherit a compressed skeleton of their parent's context via `SkeletonCompressor`. #### Resource System Integration When a resource is linked to a project via `agents project link-resource`, the `RepoIndexingService` is triggered to index the resource's filesystem tree. The index is stored in SQLite and refreshed incrementally on file changes (see ADR-008). #### Actor and Agent Integration Actors consume assembled context via the `builtin/context` skill, which provides three tools: | Tool | Description | |------|-------------| | `request_context` | Request specific context during reasoning | | `query_history` | Query historical context about past decisions | | `get_context_budget` | Check remaining context token budget | #### Configuration System Integration ACMS behaviour is controlled via `config.toml` under the `[context]` namespace (see ADR-024). **Key configuration keys:** | Key | Default | Description | |-----|---------|-------------| | `context.hot.max-tokens` | `16000` | Hot tier token budget | | `context.warm.max-decisions` | `100` | Warm tier max decisions | | `context.warm.retention-hours` | `24` | Warm tier retention period | | `context.cold.max-decisions` | `500` | Cold tier max decisions | | `context.cold.retention-days` | `90` | Cold tier retention period | | `context.strategies.enabled` | `["simple-keyword", "semantic-embedding", "breadth-depth-navigator"]` | Enabled strategies | | `context.strategies.arce.max-rounds` | `3` | ARCE max refinement rounds | | `context.strategies.breadth-depth-navigator.max-hops` | `4` | Max graph traversal hops | | `context.query.min-relevance` | `0.3` | Minimum relevance score threshold | | `context.file.max-size` | `1048576` | Max file size in bytes (1 MB) | | `context.file.max-total-size` | `52428800` | Max total file size (50 MB) | | `context.budget.refresh-threshold` | `0.30` | Budget change threshold for refresh | | `context.budget.min-useful-budget` | `500` | Minimum useful budget (tokens) | | `context.budget.skeleton-ratio` | `0.15` | Skeleton compression ratio | | `context.pipeline.*` | — | Pluggable pipeline component overrides (`"module:ClassName"`) | #### DI Container Integration All ACMS services are registered as singletons in the DI container: ```python from cleveragents.application.container import get_container container = get_container() acms_pipeline = container.acms_pipeline() tier_service = container.context_tier_service() indexing_service = container.repo_indexing_service() ``` --- ### Database Schema ACMS v1 adds two tables to the SQLite database: #### `repo_indexes` | Column | Type | Constraints | |--------|------|-------------| | `index_id` | `String(26)` | PK | | `resource_id` | `String(26)` | NOT NULL, UNIQUE, INDEXED | | `indexed_at` | `String(40)` | NOT NULL (ISO-8601 UTC) | | `file_count` | `Integer` | NOT NULL, DEFAULT 0 | | `token_estimate` | `Integer` | NOT NULL, DEFAULT 0 | | `primary_language` | `String(50)` | NOT NULL, DEFAULT "unknown" | | `status` | `String(20)` | NOT NULL, CHECK IN (`pending`, `indexing`, `ready`, `stale`, `error`) | | `error_message` | `Text` | NULLABLE | | `created_at` | `String(40)` | NOT NULL (ISO-8601 UTC) | #### `indexed_files` | Column | Type | Constraints | |--------|------|-------------| | `index_id` | `String(26)` | PK (composite), FK -> `repo_indexes.index_id` ON DELETE CASCADE | | `path` | `String(1024)` | PK (composite) | | `content_hash` | `String(64)` | NOT NULL | | `token_count` | `Integer` | NOT NULL, DEFAULT 0 | | `size_bytes` | `Integer` | NOT NULL, DEFAULT 0 | | `language` | `String(50)` | NOT NULL, DEFAULT "unknown" | | `last_modified` | `String(40)` | NOT NULL | --- ### v1 Known Limitations The following are accepted deviations from the full specification in v1, with a planned path to spec conformance in future milestones: | Area | v1 Behaviour | Spec Target | Planned | |------|-------------|-------------|---------| | Pipeline components | All 10 Protocol + Default classes defined; defaults are pass-through stubs | Production implementations (parallel execution, dedup, scoring, compression) | Future milestone | | `ContextStrategy` signatures | `can_handle(request: dict)`, `assemble(fragments, budget)` | `can_handle(request: ContextRequest, backends: BackendSet)`, `assemble(request, backends, budget, plan_context)` | M6 strategy registry | | `StrategyCapabilities` fields | `supports_semantic_search`, `supports_graph_navigation`, `max_fragments` | `uses_text`, `uses_vector`, `uses_graph`, `uses_temporal`, `quality_score` | M6 strategy registry | | Tiers | Sort-priority labels for ranking | Storage tiers with retention policies, promotion/demotion | `ContextTierService` future milestone | | `SemanticEmbeddingStrategy` | Character-frequency embedding approximation | Real embedding model integration | Future milestone | | `DetailDepthResolver.resolve()` | Missing `budget` parameter | `resolve(fragments, budget)` | Future milestone | | `FragmentScorer.score()` | Missing `plan_context` param; returns `Sequence[ContextFragment]` | Returns `list[ScoredFragment]` with `plan_context` | Future milestone | | `PreambleGenerator.generate()` | Missing `strategies_used`, `budget_used`, `max_tokens` params | Full parameter set per spec | Future milestone | | `provenance_map` keying | Keyed by `fragment_id` (ULID) | Spec keys by `uko_node` (UKO URI) | Under review | --- ### Acceptance Criteria The following criteria must be satisfied for ACMS v1 to be considered complete for milestone v3.4.0: **Indexing:** - `RepoIndexingService.index_resource()` successfully indexes a repository with 10,000+ files without timeout (target: < 60 seconds on standard hardware). - Incremental `refresh_index()` only re-processes changed files (verified by content hash comparison). - Language detection correctly identifies all supported languages. - Index status transitions correctly through `pending -> indexing -> ready`. - `cleanup_stale_indexing()` removes orphan `INDEXING` rows on startup. **Assembly:** - `ACMSPipeline.assemble()` produces a `ContextPayload` that never exceeds the declared token budget (`is_within_budget == True`). - All three built-in strategies (`relevance`, `recency`, `tiered`) produce correctly ordered fragment sequences. - The pipeline runs all 10 components for every assembly call. - Depth fallback correctly downgrades fragments to shallower depths when budget is tight. - `ContextBudgetEnforcer` correctly applies `max_file_size` and `max_total_size` limits. **Tiers:** - `ContextTierService.store()` correctly places fragments in the specified tier. - `promote()` and `demote()` correctly move fragments between tiers. - `evict_lru()` removes the correct number of least-recently-used fragments. - Actor role visibility is correctly enforced (reviewer sees hot only; executor sees hot + warm; strategist sees all). - Project scoping correctly isolates fragments by `project_name`. **Policy:** - `ProjectContextPolicy.resolve_view()` correctly walks the inheritance chain. - Empty policy correctly includes all resources and paths. - Exclusions take precedence over inclusions. - `max_file_size` and `max_total_size` validation rejects zero or negative values. **CLI:** - `agents context list/add/show/clear` commands function correctly. - `agents project context set` persists policy views and ACMS pipeline configuration. - `agents project context show` displays resolved views and ACMS config. - `agents project context inspect` displays tier metrics, fragment distribution, and actor visibility. - `agents project context simulate` produces a dry-run `AssembledContext` using the project's ACMS configuration. **UKO:** - `UKOLoader` correctly parses `docs/ontology/uko.ttl` and resolves inheritance chains (including multi-parent `rdfs:subClassOf`). - All four layers (0-3) are correctly identified by prefix. - `resolve_inheritance()` returns the correct BFS-ordered chain for `uko-oo:Class`. **Testing:** - Budget constraint tests verify assembled context never exceeds declared token budget. - Each of the 10 pipeline components has unit tests for edge cases (empty input, budget exhaustion, duplicate fragments). - Each retrieval strategy has integration tests verifying correctly structured results. - Depth fallback tests verify fragments are downgraded to shallower depths when budget is insufficient. - Configuration tests verify custom pipeline components and strategy registrations are loaded and invoked correctly. - Performance benchmark: index 10,000 files in < 60 seconds; assemble context in < 5 seconds. --- *Section added by [AUTO-ARCH-20] — Cycle 27 — Milestone v3.4.0 — ACMS v1 + Context Scaling*