632 Commits

Author	SHA1	Message	Date
HAL9000	d1ced790ca	docs: update CHANGELOG, CONTRIBUTORS, and fix DI snippet for module guides (#4848) ... - Add CHANGELOG.md [Unreleased] entry for the three new module guides - Add CONTRIBUTORS.md entry for HAL9000 authoring the module guides - Fix InvariantReconciliationActor DI container snippet in invariant-reconciliation.md: replace incorrect event_bus/audit_service params with the actual constructor params (invariant_service, decision_service) as defined in src/cleveragents/actor/reconciliation.py ISSUES CLOSED: #4848	2026-06-16 18:28:16 -04:00
HAL9000	44652c216a	docs: add sandbox, correction, and invariant module guides ... Document lifecycle details, security warnings, and CLI usage for the new module guides so implementors have a single reference. ISSUES CLOSED: #4848	2026-06-16 18:18:18 -04:00
HAL9000	4a68e02107	docs(spec): align checkpoint trigger names and config key path with implementation ... Fixes two spec-implementation discrepancies identified in issue #5009: 1. Checkpoint trigger names: rename on_tool_write → before_tool_execute and on_tool_write_complete → after_tool_execute to match the implementation in src/cleveragents/tool/runner.py and src/cleveragents/application/services/ config_service.py. The implementation names are more precise — they describe the execution phase rather than implying only write tools trigger them (though the implementation correctly gates them on write tools). 2. Config key path: correct the Configuration Reference table entry from sandbox.checkpoint.auto-create-on to core.checkpoints.auto-create-on, matching both the implementation (config_service.py line 482) and the inline spec at line 19449. Also update the default values in the table to use the corrected trigger names. Closes #5009	2026-06-15 13:14:25 -04:00
HAL9000	a7b6b3d0d4	docs(timeline): verify timeline status for 2026-04-16 Cycle 2 [AUTO-TIME-3]	2026-06-15 02:41:37 -04:00
HAL9000	9edee2d7d5	docs: fix inaccurate fast-path claim in CLI basics documentation ... The version, info, and diagnostics commands were incorrectly stated as being on the fast-path. Only --help and --version are eager exit options that skip subcommand module loading. ISSUES CLOSED: #7592	2026-06-14 23:57:38 -04:00
HAL9000	f38491e5a6	docs: add showcase example for CLI version/info/diagnostics basics ... Add a verified CLI showcase for the version, info, and diagnostics commands, register in examples.json and update CHANGELOG/CONTRIBUTORS. ISSUES CLOSED: #7592	2026-06-14 23:57:38 -04:00
HAL9000	f808abff86	chore(ci): fix pre-commit hook failures ... Fix JSON syntax errors in .devcontainer/devcontainer.json (removed invalid JS-style // comments) and .devcontainer/opencode.json (removed 90+ trailing commas). Apply auto-fixes for end-of-file and trailing whitespace issues across 100+ files. Fix SIM105 ruff violations in benchmarks/core_circuit_breaker_bench.py (use contextlib.suppress). Note: The security fix from issue #7478 (validate_path startswith bypass) was already delivered to master in commit e18ac5f2. This PR as currently structured is non-atomic (35 commits across 10+ issues) and needs significant restructure before merge. This commit only addresses the CI/pre-commit failures. ISSUES CLOSED: #7478	2026-06-14 09:51:14 -04:00
HAL9000	b6fe72e40f	chore(agents): fix bug-hunt-pool-supervisor tracking prefix AUTO-BUG-POOL to AUTO-BUG-SUP (complete fix)	2026-06-14 03:03:30 -04:00
HAL9000	ad88422efe	docs(spec): clarify layer boundary DI exception, ULID scope, TUI/ACMS gap-fill [AUTO-ARCH-1] ... Add targeted clarifications to docs/specification.md to fill identified gaps: 1. Layer boundary DI Container Exception (Cross-Milestone Architectural Invariants) 2. ULID Scope Clarification - domain vs internal identifiers 3. ACMS Pipeline Protocol Contracts with storage tiers and budget protocol 4. TUI Component Interfaces with verifiable checks Co-authored-by: CleverAgents Bot <bot@cleveragents.com> ISSUES CLOSED: #10451	2026-06-12 12:08:13 -04:00
HAL9000	c1a29a331b	docs: add showcase example for resource and skill management ... Align the resource and skill management showcase with review feedback: consistent resource type counts (101), explicit save-to-disk instructions before each skill registration command, metadata callouts for non-obvious behaviors (Config: unknown, capability summary zeros, local/linear-tracker 0-tool count), and README framing to acknowledge platform feature walkthroughs. Remove obsolete tdd_issue tags from coverage threshold Robot tests now that the noxfile enforces COVERAGE_THRESHOLD = 97. Harden the Skip If No LLM Keys E2E helper with per-key regex validation and log-level suppression to prevent credential leakage in CI logs. Restore the Resolve LLM Actor keyword that was inadvertently removed from common_e2e.resource. Update CHANGELOG.md and CONTRIBUTORS.md per project requirements. ISSUES CLOSED: #4470	2026-06-06 22:55:02 -04:00
HAL9000	34f658a32a	docs(showcase): showcase CLI version/info/diagnostics commands ... Created comprehensive showcase documentation for CLI version, info, and diagnostics commands Documented fast-path vs regular command behavior Included verified outputs and machine-readable JSON/YAML examples Registered the showcase entry in docs/showcase/examples.json Added BDD tests for the showcase documentation Closes #7592	2026-06-06 06:28:09 -04:00
HAL9000	c0ca274691	fix(showcase): add "agents actor run" to commands list in examples.json ... The BDD test step_commands_include checks for exact list membership. "agents actor run" was missing from the commands list, causing the "Showcase commands list is not empty" scenario to fail with: AssertionError: Command 'agents actor run' not found in commands list	2026-06-06 04:58:21 -04:00
Repository Isolator	1551c6e41d	docs(showcase): add REPL and actor run CLI showcase ... - Register REPL and actor run showcase in examples.json - Add BDD tests for showcase documentation structure - Verify markdown file exists and is properly formatted - Validate JSON metadata for showcase entry - Test documented commands and content sections Closes #7552	2026-06-06 04:58:20 -04:00
HAL9000	8be7f59931	feat(providers): implement OpenRouter provider support in ProviderRegistry ... Added handling for ProviderType.OPENROUTER in _create_provider_llm in src/cleveragents/providers/registry.py to resolve ValueError: Unsupported provider type when using OpenRouter via create_llm. Created features/openrouter_provider_registry.feature with 11 scenarios validating OpenRouter provider behavior in ProviderRegistry. Created features/steps/openrouter_provider_registry_steps.py with step definitions for the new feature file. Created docs/reference/providers.md with comprehensive documentation including the OpenRouter configuration guide. ISSUES CLOSED: #8907	2026-06-06 04:37:11 -04:00
HAL9000	0b8b971e7f	docs: document actor removal impact handling and --unsafe flag ... - Added comprehensive documentation about actor removal impact handling, outlining potential effects on dependencies, data integrity, and service continuity. Includes a clear, step-by-step checklist for evaluating impact prior to removal and guidance on planning mitigations. - Documented the --unsafe flag and when it's required, with explicit warnings, usage criteria, and recommended safeguards, rollback steps, and testing considerations. - Added non-zero impact scenarios and best practices for safe removal, including concrete examples of edge cases, guidance on graceful shutdown, data migration considerations, and rollback planning to minimize disruption. - Updated the actor management workflow showcase with new guidance, aligning demonstrations and diagrams with the updated removal process and decision points. Closes #7540	2026-06-06 03:52:55 -04:00
HAL9000	a5218c143c	docs: add DI unification implementation plan for issue #8867	2026-06-06 01:15:58 -04:00
HAL9000	7f47ec85da	docs(milestones): split oversized milestone pages into sub-pages (PR #9957) ... Refactor Milestones documentation to address PR #9957 reviewer feedback: - Split v3.0.0.md (506 lines) into 3 sub-pages under milestones/v3.0.0/: - index.md — Overview, goals, feature table, architecture notes (87 lines) - cli-reference.md — Full CLI command reference (142 lines) - deep-dive.md — Sandbox, persistence, domain model internals (95 lines) - Split v3.1.0.md (682 lines) into 5 sub-pages under milestones/v3.1.0/: - index.md — Overview, goals, feature table, architecture notes (69 lines) - actor-yaml.md — Actor YAML format + Compiler/LangGraph integration (131 lines) - integration.md — MCP Adapter + Tool Router provider normalization (91 lines) - skills.md — Skill Registry + Validation Runner gates (127 lines) - quickstart.md — Common workflows and reference guide (66 lines) - Update mkdocs.yml navigation to reflect the new sub-page structure - Total: from 2 files at 506/682 lines to 9 files all under 150 lines ISSUES CLOSED: #9957	2026-06-04 01:49:54 -04:00
HAL9000	980fcabc48	docs: document ACP to A2A module rename and symbol standardization [AUTO-DOCS-8]	2026-06-03 22:51:33 -04:00
HAL9000	35bf1d6962	[AUTO-TIME-1] Update timeline: schedule adherence 2026-04-17	2026-06-03 22:29:32 -04:00
HAL9000	8170dabb4f	docs(timeline): [AUTO-TIME-2] update schedule adherence 2026-04-18 with changelog and contributor entries ... - Add Schedule Adherence tables for 2026-04-18 (M3-M10) - Add Daily Snapshot section with milestone risk assessments - Fix missing newline at end of timeline table content - Update CHANGELOG.md under [Unreleased] with entry for timeline snapshot - Update CONTRIBUTORS.md with HAL 9000 contribution entry - Proper newline termination before new markdown table sections ISSUES CLOSED: #10288 Epic reference: Tracking issue #8519 (AUTO-TIME supervisor) Automated by CleverAgents Bot Supervisor: Timeline Update | Agent: timeline-update-pool-supervisor	2026-06-03 22:07:47 -04:00
CleverAgents Bot	5ca87cd5af	docs(v3.6.0-v3.7.0): add comprehensive feature documentation and guides ... - Add v3.6.0 features guide covering advanced context management, enhanced security profiles, improved observability, performance optimizations, and API enhancements - Add v3.7.0 features guide covering TUI redesign, Agent-to-Agent Communication (A2A), enhanced automation execution, advanced skill management, and improved developer experience - Add comprehensive v3.7.0 TUI guide with detailed navigation, management interfaces, keyboard shortcuts, and advanced features - Add v3.7.0 A2A protocol specification covering message format, transport layers, authentication, error handling, and multi-agent orchestration - Add v3.6.0-v3.7.0 release notes with upgrade paths, deprecation timeline, and migration guides - Include practical examples and best practices for all major features - Ensure all documentation is properly formatted with table of contents and cross-references This documentation audit and update provides comprehensive coverage of v3.6.0 and v3.7.0 features with examples, ensuring users can effectively utilize new capabilities.	2026-06-03 21:06:30 -04:00
HAL9000	0aacec7845	fix(cli): address PR #6626 review blockers for context set output ... - Fix ruff import ordering in project_context_cli_steps.py (yaml moved to third-party section) - Remove unused noqa: F401 suppression in rendering/__init__.py - Add *args, **kwargs to _test_format_output stub in coverage boost steps (fixes TypeError) - Extract context-set step definitions into dedicated module (project_context_set_steps.py) to bring project_context_cli_steps.py under 500-line limit (469 -> 316 lines) - Revert spec changes for context show/inspect/simulate message format (bare strings) to keep PR focused on issue #6319 (context set only),	2026-06-03 17:30:22 -04:00
HAL9000	388fc458c5	fix(cli): fix project context set JSON/YAML output structure (#6319) ... Implemented spec-compliant JSON, YAML, plain, and rich outputs for `agents project context set`. Added BDD coverage verifying the new output structure across formats.\n\nISSUES CLOSED: #6319	2026-06-03 17:30:22 -04:00
HAL9000	46fff75c1a	docs: add v3.2.0 and v3.3.0 feature documentation [AUTO-DOCS-2]	2026-06-03 15:56:46 -04:00
CleverAgents Bot	70517398a6	[AUTO-TIME-1] Day 105 timeline update — 2026-04-15 ... Update schedule adherence and milestone progress: - v3.2.0: 26% complete (933 open) - v3.3.0: 36% complete (212 open) - v3.4.0: 37% complete (158 closed / 427 total) - v3.5.0: 18% complete (1,107 open) - v3.6.0: 33% complete (329 open) - v3.7.0: 42% complete (603 open) - v3.8.0: 29% complete (364 open) - v3.9.0: 41% complete (35 open) Automated by CleverAgents Bot	2026-06-03 11:55:34 -04:00
HAL9000	b31d52fe0e	docs(spec): clarify Anonymous Tool enforcement rules in glossary ... Expands the Anonymous Tool glossary entry to explicitly document: - Anonymous tools are never passed to ToolRegistry.register() - Name field is required but context-local (no namespace prefix) - Attempting global registration raises ToolError - Namespacing requirement applies only to registered tools Closes #8799. [AUTO-ARCH-14]	2026-06-03 00:24:21 -04:00
HAL9000	7ba1e5737f	docs(spec): document context_tier_hydrator module in ACMS architecture section ... Adds Context Tier Hydration subsection to the ACMS Architecture section of the specification, documenting the context_tier_hydrator module's public interface (hydrate_tiers_for_plan, hydrate_tiers_from_project), file listing strategy (git ls-files for git-checkout resources, os.walk fallback), budget limits (256 KB per file, 10 MB total per project), and fragment structure (TieredFragment with ContextTier.HOT placement, metadata keys path/detail_depth/relevance_score). Also updates CHANGELOG.md under [Unreleased] > Documentation and adds contribution entry to CONTRIBUTORS.md. ISSUES CLOSED: #6175	2026-06-02 23:07:34 -04:00
HAL9000	5e89f1016c	refactor(subplans): Centralize subplan errors per v3.3.0 spec (#8725) ... Move SubplanSpawnError from local subplan_service definition to centralized cleveragents.core.exceptions alongside four new spec-defined error types: SubplanExecutionError, MaxParallelExceededError, and SubplanDepthLimitError. Per the v3.3.0 specification (AUTO-ARCH-6), all subplan-related errors are defined in exceptions.py with proper inheritance hierarchy under DomainError/ PlanError/BusinessRuleViolation. The old local SpawnValidationError class has been replaced with SubplanSpawnError(PlanError) with a simplified constructor API (message string instead of validation_errors list). Updates: - exceptions.py: Added 4 subplan error classes + __all__ entries - subplan_service.py: Remove local SpawnValidationError, import SubplanSpawnError from exceptions - services/__init__.py: Update TYPE_CHECKING stub and _LAZY_IMPORTS for new location - vulture_whitelist.py: Replace old entry with new error class names - docs/reference/subplan_service.md: Update to reference SubplanSpawnError (v3.3.0) - features/*.feature + steps: Update test references from SpawnValidationError to SubplanSpawnError	2026-06-02 19:50:41 -04:00
HAL9000	bc6677b3cd	feat(subplans): Subplan System Specification and Invariant Enforcement v3.3.0 (#8725) ... Add comprehensive Subplan System specification defining module boundaries, data models (Subplan, SubplanResult, SubplanTree), PostgreSQL schema with indexes, the 8-step spawning algorithm, concurrency control via per-plan semaphores, and error handling. Implement invariant loading and enforcement in Strategize phase: - Add InvariantViolationError exception class - Add load_active_invariants() and check_invariants() methods to InvariantService - Add _is_violation heuristic for action/invariant matching - Add BDD tests with @load_invariants, @check_invariants, etc. tags ISSUES CLOSED: #8725	2026-06-02 19:50:41 -04:00
HAL9000	8ebd922e77	docs(specification): add deleted_at field to agents project delete JSON/YAML output ... Updated docs/specification.md to document the correct JSON/YAML output structure for the project delete command, replacing the legacy deletion_summary object with the deleted, success, and deleted_at fields that match the actual implementation introduced in PR #6639. Added BDD feature file and step definitions to validate the output format. ISSUES CLOSED: #7872	2026-06-02 04:09:01 -04:00
HAL9000	f7ce8f0093	fix: update pr-review-pool-supervisor tracking prefix from AUTO-REV-POOL to AUTO-REV-SUP ... - Updated pr-review-pool-supervisor.md tracking prefix from AUTO-REV-POOL to AUTO-REV-SUP - Updated automation-tracking.md table and search query to use AUTO-REV-SUP - Updated agent-system-specification.md all references from AUTO-REV-POOL to AUTO-REV-SUP - Aligns documentation with actual production tracking prefix ISSUES CLOSED: #7891	2026-06-02 00:58:16 -04:00
HAL9000	518c40be21	docs: document 2026-04-06 to 2026-04-08 improvements ... - add changelog entries summarizing watchdog supervision and documentation updates\n- add ci-log-fetcher module guide detailing interface contract and usage\n- refresh system-watchdog doc with CI-blocker escalation and struggling PR detection\n- normalize coverage threshold robot test by dropping temporary tdd_expected_fail tags\n\nISSUES CLOSED: #7987	2026-05-31 09:38:17 -04:00
freemo	1fd4918be8	docs(spec): clarify TUI session export formats and persona schema fields ... Accept implementation extensions as spec updates based on UAT findings: 1. `/session:export` now officially supports three formats: - `json` (default, canonical, importable) - `md` (Markdown transcript, lossy) - `txt` (plain-text transcript, lossy) Updated ADR-046 command table and spec Conversation Export section. 2. Persona data model now includes two optional display fields: - `icon`: emoji or single character for tab labels and lists - `greeting`: message shown when persona is activated Updated ADR-045 data model YAML example and Decision section. These changes accept positive implementation extensions discovered by UAT testing (issues #4871, #4858) rather than reverting them. Refs: #4940	2026-05-31 08:35:06 -04:00
HAL9000	bc64074036	docs: add tool and validation management showcase ... - document the CLI workflow for registering tools, wrapping validations, and querying registry metadata - index the new example in docs/showcase/examples.json - re-enable coverage threshold regression checks by removing obsolete tdd_expected_fail tags ISSUES CLOSED: #4565 Refs: #4305 Refs: #4227	2026-05-30 17:21:55 -04:00
HAL9000	fc0366d05a	fix(docs): correct SDK link from a2aprojects to a2aproject ... The SDK URL was incorrectly changed to a2aprojects/a2a-python (404 broken link). Revert to the correct a2aproject/a2a-python which is the official A2A Python SDK org. Fixes blocker from PR review.	2026-05-30 09:33:19 -04:00
freemo	9b64297eff	docs(a2a): fix SSE streaming event example method name ... Corrects the Example Streaming Event in docs/reference/a2a.md to use the correct JSON-RPC 2.0 notification method name `task/statusUpdate` instead of the incorrect `message/stream`. `message/stream` is the client→server REQUEST method that initiates streaming. The actual SSE data payloads are JSON-RPC 2.0 notifications (no `id` field) with method names `task/statusUpdate` or `task/artifactUpdate`, as implemented in SseEventFormatter. Closes #2519	2026-05-30 09:33:19 -04:00
CoreRasurae	3e13411fcf	fix(actors): distinguish namespace/name from provider/model in actor name parsing ... When action YAML references actors using namespace/name format (e.g. `strategy_actor: local/my-strategist`), `_parse_actor_name()` incorrectly treated the namespace prefix as a provider name, causing `ValueError: Unknown provider type: local`. Changes: - `_is_known_provider()`: New utility function (strategy_resolution.py) that checks whether a slash-separated first segment matches a known `ProviderType` value (openai, anthropic, etc.). Consolidated into a single implementation; llm_actors.py now imports from strategy_resolution.py. - `_parse_actor_name()`: When the first segment IS a known provider, preserves existing behaviour (provider/model). When it is NOT a known provider, treats the input as namespace/name and returns the full name as the model identifier with the default provider. Callers SHOULD pre-resolve namespace/name references via the actor registry before calling this function. Both implementations (strategy_resolution.py and llm_actors.py) updated; ProviderType import moved to top level. - `PlanLifecycleService.resolve_actor_provider_model()`: New method that resolves a namespaced actor name (e.g. local/my-strategist) to provider/model format by looking up the actor record and extracting its provider and model fields. - `LifecycleService` Protocol (strategy_resolution.py): Added `resolve_actor_provider_model` to the protocol, eliminating the need for `# type: ignore[union-attr]` at call sites. - `PlanLifecycleProtocol` (llm_actors.py): Added `resolve_actor_provider_model` to the protocol. - Caller pre-resolution: StrategyActor, LLMStrategizeActor, LLMExecuteActor, SessionWorkflow._resolve_llm(), and CLI session commands now pre-resolve actor names through the lifecycle service or via injected actor_resolver callables before calling `_parse_actor_name()`, ensuring namespace/name references are correctly mapped to their underlying LLM providers. - `_build_actor_resolver()` (cli/commands/session.py) and `_build_actor_resolver_for_session_workflow()` (a2a/facade.py): Moved `_is_known_provider` imports to top level; removed redundant `except (NotFoundError, Exception)`; added warning logging for outer exception handlers. - `make_mock_lifecycle()` (mock_strategy_llm.py) and `_make_mock_lifecycle()` (llm_actors_coverage_steps.py): Added `resolve_actor_provider_model` to mock lifecycle services for test compatibility. - Added `@tdd_issue @tdd_issue_11254` tags to all new BDD scenarios related to namespace/name disambiguation in llm_actors_coverage, strategy_actor_llm, and plan_lifecycle_service_coverage_boost_r4 feature files. - Updated docs/CHANGELOG.md with the fix entry. ISSUES CLOSED: #11254	2026-05-22 20:42:25 +01:00
CoreRasurae	8548644819	fix(cli): wire SubplanExecutionService in _get_plan_executor() to enable child plan execution ... Wire subplan_service from the DI container into _get_plan_executor() so PlanExecutor can spawn child plans during the Execute phase. When SubplanService is available but SubplanExecutionService is not explicitly injected, _execute_subplans() now lazily creates a SubplanExecutionService on-the-fly using the parent plan's subplan_config and the new _execute_child_plan callback. - _get_plan_executor(): retrieve subplan_service from container, pass to PlanExecutor constructor - _execute_subplans(): lazily build SubplanExecutionService when only SubplanService is wired (Forgejo #10268) - _execute_child_plan(): new PlanExecutor method that runs a child plan's strategize + execute phases, registered as executor_fn callback ISSUES CLOSED: #10268	2026-05-19 19:28:35 +01:00
HAL9000	2cba7d41bc	chore(agents): fix bug-hunt-pool-supervisor tracking prefix AUTO-BUG-POOL to AUTO-BUG-SUP (complete fix) ... Replace all remaining AUTO-BUG-POOL references with correct AUTO-BUG-SUP in agent-system-specification.md, automation-tracking.md documentation and agent-system-specification.md spec document, replaced with correct `AUTO-BUG-SUP` prefix used by the bug-hunt-pool-supervisor agent (#7875). ISSUES CLOSED: #7875	2026-05-09 00:05:17 +00:00
HAL9000	57881a075b	docs(spec): update specification — validation gate blocks on empty validation summary	2026-05-08 19:14:24 +00:00
HAL9000	a130d63357	docs(timeline): update schedule adherence Day 101 (2026-04-12) (#7858)	2026-05-08 10:21:23 +00:00
HAL9000	3d7afb4378	fix(resource): wire discover_devcontainers() into git-checkout and fs-directory handlers ... GitCheckoutHandler.discover_children() and FsDirectoryHandler.discover_children() now call discover_devcontainers() after scanning for fs-directory children. Any .devcontainer/devcontainer.json or root-level .devcontainer.json found at the resource location is registered as a devcontainer-instance child resource with provisioning_state: discovered. Named configurations are also discovered and carry the configuration name in the config_name property. This wires the previously-isolated discover_devcontainers() function into the production code path, enabling the spec's zero-configuration devcontainer experience. ISSUES CLOSED: #4740	2026-05-07 23:49:20 +00:00
HAL9000	2778bde95a	fix(repositories): derive PlanResult.success from result_success column instead of error_message ... ISSUES CLOSED: #7501	2026-05-07 14:22:57 +00:00
HAL9000	f2d1f4efe7	docs: fix quickstart plan/apply command signatures ... Update docs/quickstart.md to use correct CLI command signatures: - Replace 'cleveragents plan --project' with 'cleveragents plan use <action> --project' - Replace 'cleveragents apply --project' with 'cleveragents plan list' + 'cleveragents plan apply <plan-id>' Addresses reviewer non-blocking suggestion to verify CLI commands match actual signatures before merging.	2026-05-06 04:29:40 +00:00
HAL9000	54fef4768c	docs: add quick start guide (PR #9245) ... Add docs/quickstart.md with end-to-end quick start guide covering prerequisites, installation, project creation, resource registration, plan/apply workflow, and troubleshooting. Update mkdocs.yml navigation to include Quick Start page and rename ADR-028 title to Skill/Tool Abstraction Definition. Update CHANGELOG.md with quick start guide entry. Closes #9245	2026-05-06 04:29:40 +00:00
HAL9000	8384f53e28	test(cli): cover actor remove format regression (#6491) ... Add Robot regression coverage for `actor remove --format json`, document the flag in the CLI synopsis, and record the fix in the changelog.\n\nISSUES CLOSED: #6491	2026-05-06 01:07:15 +00:00
hurui200320	85c579b51f	fix(cli): display full session IDs in session list output ... Remove the [:8] truncation from session IDs in the Rich table row, Most Recent summary, and Oldest summary fields of list_sessions() and _session_list_dict(). Session IDs are 26-character ULIDs and must be usable directly for copy-paste into session tell, session show, and other session commands. The structured output (JSON/YAML) already used full IDs in the sessions[*].id field, but the summary panel leaked the truncation into those formats as well. Added Behave scenarios: - Rich table displays full 26-character ULIDs (scoped to table region) - Summary panel shows full ULIDs for unnamed sessions (scoped to panel) - Summary panel shows session names for named sessions - Full ULID from list output works with session tell (round-trip, uses parsed ULID, not hardcoded constant) Review Cycle 2 fixes: - docs/specification.md: Updated YAML output example to full ULIDs - docs/showcase/*.md: Updated all example output blocks to full ULIDs - docs/reference/session_cli.md: Replaced placeholder with full ULID - features/session_cli.feature: Consecutive When steps -> And - features/steps/session_cli_steps.py: Summary panel asserts both IDs, 8-char negative guard in table output, ULID capture scoped to table region with fixture verification, named-session absence check for second session - CHANGELOG.md: Added [Unreleased] entry for the behavioral change ISSUES CLOSED: #10970	2026-05-05 10:56:18 +00:00
hurui200320	7164b04019	refactor(providers): unify provider factory behind single source of truth ... Extract _get_api_key() and _create_provider_instance() as a single internal factory that handles all provider types, including MOCK. Both create_llm() and create_ai_provider() now delegate to _create_provider_instance(), eliminating the duplicated if/elif provider-switching chains and the divergence between the two code paths. Adding a new provider now requires touching exactly one place. Key changes: - New _get_api_key(provider_type) consolidates API key lookup and validation that was previously duplicated across create_llm(), _create_provider_llm(), and every branch of create_ai_provider(). - New _create_provider_instance() is the unified raw-LLM factory, replacing _create_provider_llm() and the specialised adapter constructors in create_ai_provider(). MOCK is now handled here via FakeListLLM. - create_ai_provider() wraps all providers uniformly in LangChainChatProvider instead of using specialised adapters (OpenAIChatProvider, AnthropicChatProvider, GoogleChatProvider, OpenRouterChatProvider) for the four primary providers. - create_llm() drops its own API key validation block; validation now happens inside _create_provider_instance() via _get_api_key(). - All BDD scenarios updated: _create_provider_llm references become _create_provider_instance, and provider-type assertions on create_ai_provider results are updated to LangChainChatProvider. Review fixes (Cycle 2): - Add _coerce_env_bool() for consistent boolean env-var coercion in CLEVERAGENTS_ALLOW_MOCK_PROVIDER checks. - Introduce _ApiKeyMissing sentinel to distinguish 'not provided' from None in provider configuration. - Set MOCK supports_streaming=False in DEFAULT_CAPABILITIES to align with FakeListLLM semantics. - Make MOCK is_configured conditional on CLEVERAGENTS_ALLOW_MOCK_PROVIDER. - Use FakeListLLM(responses=['mock response'] * 10) to prevent IndexError in multi-step workflows. - Strip max_retries from kwargs before passing to LangChain constructors. - Extract _resolve_provider_type() helper shared by create_llm() and create_ai_provider() to reduce duplication and improve readability. - Ensure __api_key_sentinel flows through factory_kwargs even when api_key is None, avoiding double _get_api_key() calls. - Add CHANGELOG env-var documentation and providers.md env-var table. - Resolve template DB lock issues by persisting in-memory SQLite via VACUUM INTO instead of direct file creation on tmpfs. ISSUES CLOSED: #10949	2026-05-05 06:16:46 +00:00
HAL9000	988a169831	docs: add InvariantReconciliationActor API docs, devcontainer discovery module guide, and mkdocs nav ... - docs/api/actor.md: Add InvariantReconciliationActor section documenting the built-in reconciliation actor introduced in v3.8.0, including the reconciliation algorithm, ReconciliationResult/ConflictRecord/ScopeInvariants data classes, standalone reconcile_invariants() function, DI registration, and failure behaviour. - docs/modules/devcontainer-discovery.md: New module guide for the devcontainer auto-discovery system (v3.8.0 fix #2615), covering DevcontainerDiscoveryResult, discover_devcontainers(), is_trigger_type(), monorepo named-config support, and gotchas. - mkdocs.yml: Add 'Devcontainer Auto-Discovery' to the Modules nav section, alongside shell-safety, uko-provenance, invariant-reconciliation, context-hydration, and git-worktree-sandbox module docs. - robot/coverage_threshold.robot: Add tdd_issue and tdd_issue_4305 tags to the Noxfile Contains Coverage Threshold Constant test case. ISSUES CLOSED: #4485	2026-05-05 06:15:57 +00:00
CoreRasurae	cc24d8c8ac	fix(cli): remove legacy plan commands from help output ... Completely removed all legacy plan commands from the CLI: - Removed tell, build, new, current, cd, continue CLI commands - Removed programmatic wrapper functions (tell_command, build_command, etc.) - Removed legacy deprecation message - Updated help text to indicate V3 Plan Lifecycle exclusively - Removed stale references to tell/build in help output and command validation Removes the legacy 'tell' and 'build' CLI shortcuts from main.py: - Removed echo lines advertising tell/build commands - Removed tell/build from valid_cmds list - Removed tell/build from _LIGHTWEIGHT_COMMANDS frozenset - These dead entries were preventing helpful error messages Test infrastructure improvements: - Event bus exception test: Patch the module-level logger during emit() so that structlog.testing.capture_logs() can capture the logs. Without patching, the module-level logger created at import time is not captured by the context manager. - Session create/list commands: Suppress cleveragents.mcp logger to CRITICAL level during JSON/YAML output formatting to prevent health check warnings with ANSI codes from being written to stdout before JSON output, which breaks JSON parsing. - Extended plan_cli_coverage_boost with scenarios for estimation_result, invariants, execution_environment, validation_summary, and checkpoint coverage in _plan_spec_dict Documentation: - Created docs/Legacy_to_V3_Guide.md with comprehensive migration instructions - Updated CONTRIBUTING.md to document removal of legacy workflow - Updated CHANGELOG.md to reference issue #4181 instead of PR #10800 ISSUES CLOSED: #4181	2026-05-05 02:01:49 +00:00