freemo/cleveragents-core
0
0
Fork 0
forked from cleveragents/cleveragents-core
Code Pull Requests Activity

Merge branch 'master' into feature/m1-e2e-sourcecode

Browse Source
This commit is contained in:
Brent Edwards
2026-02-25 06:07:09 +00:00
committed by Forgejo
parent 0397a00eb6 1282bc03b3
commit 5bf1908708
2 changed files with 148 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CONTRIBUTING.md
+9 -7
View File
@@ -615,13 +615,15 @@ Every issue must include:
during triaging.
Do **not** assign `MoSCoW/` labels — these are set exclusively by the project owner.
- **Milestone:** Every issue that has moved beyond `State/Unverified` must be assigned to a
milestone. Issues in `State/Unverified` may optionally have a milestone — it is not required
at creation time, but is typically assigned by a maintainer during triaging when the issue is
moved to `State/Verified`. Once an issue is in any active state (`State/Verified`,
`State/In Progress`, `State/Paused`, `State/In Review`, or `State/Completed`), a milestone
is mandatory. If no appropriate milestone exists, discuss with the project owner before
proceeding.
- **Milestone:** Every non-Epic, non-Legendary issue that has moved beyond `State/Unverified`
must be assigned to a milestone. `Type/Epic` and `Type/Legendary` issues are exempt from
this requirement because they typically span multiple milestones; a milestone may optionally
be assigned to them but is not required. Issues in `State/Unverified` may optionally have a
milestone — it is not required at creation time, but is typically assigned by a maintainer
during triaging when the issue is moved to `State/Verified`. Once a non-Epic, non-Legendary
issue is in any active state (`State/Verified`, `State/In Progress`, `State/Paused`,
`State/In Review`, or `State/Completed`), a milestone is mandatory. If no appropriate
milestone exists, discuss with the project owner before proceeding.
- **Branch/Tag (Ref):** Forgejo issues have a **branch/tag** field (the `Ref` field on the
issue form) that associates the issue with a specific branch or tag in the repository.
The rules for this field depend on the nature of the issue:
docs/timeline.md
+139 -112
View File
@@ -17,7 +17,7 @@ saturday are closed
sunday are closed
printscale weekly zoom 2
today is 2026-02-23
today is 2026-02-24
today is colored in #FF6666
<style>
@@ -379,13 +379,13 @@ legend right
----
**Milestone Scope**
|= Milestone |= Target |= Epics |= SP |= Key Deliverables |
| v3.0.0 | Feb 15 | 9 | 172 | Foundation, QA, domain models |
| v3.1.0 | Feb 22 | 4 | 208 | Plan lifecycle, projects, actor schema |
| v3.2.0 | Feb 26 | 2 | 104 | Sessions, actor runtime, tool exec |
| v3.3.0 | Mar 02 | 3 | 126 | Tool sources, security, providers |
| v3.4.0 | Mar 06 | 3 | 129 | Decisions, validation, CLI polish |
| v3.5.0 | Mar 10 | 2 | 151 | Corrections, ACMS v1, context |
| v3.6.0 | Mar 27 | 2 | 100 | Remote clients, safety, RDF |
| v3.0.0 | Feb 15 | 9 | 172 | Minimal local source-code workflow |
| v3.1.0 | Feb 22 | 4 | 208 | Actor graphs + tool sources |
| v3.2.0 | Feb 26 | 2 | 104 | Decisions + validations + invariants |
| v3.3.0 | Mar 02 | 3 | 126 | Corrections + subplans + checkpoints |
| v3.4.0 | Mar 06 | 3 | 129 | ACMS v1 + context scaling |
| v3.5.0 | Mar 10 | 2 | 151 | Autonomy hardening + server stubs |
| v3.6.0 | Mar 27 | 2 | 100 | Deferred work |
----
**Risk Register**
|= Epic |= Completion |= Risk |= Blocker |
@@ -401,7 +401,7 @@ legend right
| <back:LightSkyBlue> </back> | In Progress |
| <back:#E8E8E8> </back> | Not Started |
| <back:Gold> <> </back> | Milestone Target |
| <back:#FF6666> | </back> | Today (2026-02-23) |
| <back:#FF6666> | </back> | Today (2026-02-24) |
----
29 Epics | 9 Legendaries | 7 Milestones | 6 Developers
~1350 total story points | ~2700 estimated hours
@@ -428,7 +428,7 @@ saturday are closed
sunday are closed
printscale weekly zoom 2
today is 2026-02-23
today is 2026-02-24
today is colored in #FF6666
<style>
@@ -1933,7 +1933,7 @@ legend right
| <back:LightSkyBlue> </back> | Issue: In Progress |
| <back:#E8E8E8> </back> | Issue: Not Started |
| <back:Gold> <> </back> | Milestone Target |
| <back:#FF6666> | </back> | Today (2026-02-23) |
| <back:#FF6666> | </back> | Today (2026-02-24) |
----
213 Issues | 29 Epics | 9 Legendaries | 7 Milestones
~1350 total story points | ~2700 estimated hours
@@ -1948,13 +1948,13 @@ This section provides a high-level overview of the CleverAgents implementation r
### Current Status Summary
As of Day 16 (2026-02-24), the project has **~77 closed issues out of ~120 active rebaseline issues** (excluding pre-rebaseline and organizational issues). The foundational layers — domain models, persistence, YAML schemas, CLI commands, quality automation, and CI/CD — are substantially built out. Recent progress includes decision domain model and context snapshots (Hamza, PR #385 merged), resource registry with DAG metadata, resource handler runtime for git-checkout and fs-directory, and phase reversion state machine.
As of Day 16 (2026-02-24), the project has **~144 closed issues out of ~259 assigned issues** across all milestones (72% overall completion rate). The foundational layers — domain models, persistence, YAML schemas, CLI commands, quality automation, and CI/CD — are substantially built out. Today's progress includes the **actor compiler** (Jeff, #158 merged — YAML to LangGraph StateGraph compilation), **agent skills discovery** (Jeff, #161 merged), **actor CLI alignment** (Jeff, #288 merged), **CLI plan/action extensions** (Jeff, #325 merged), and a **database parallelism fix** (Brent, #418 merged).
The primary blocker for M1 completion remains the **sandbox merge/apply pipeline with validation gating** and the **E2E source-code smoke test suite**. The actor runtime, tool-calling, and execute pipeline are now partially functional. The M2 blocker is the **actor compiler** (YAML -> LangGraph StateGraph) and **MCP adapter** runtime.
The primary blocker for M1 completion remains the **sandbox merge/apply pipeline** (#155, Luis — active branch) and the **E2E source-code smoke test suite** (#156, Brent). The M2 blockers are the **MCP adapter** (#159, Aditya — in review) and remaining **actor YAML extensions** (#157, Aditya — active branch). The actor compiler (#158) — previously the M2 critical-path blocker — was merged today.
!!! warning "Schedule Risk: 7-9 Days Behind"
The project is running **7-9 days behind** the original aggressive schedule. M1 (target Feb 15) is overdue by 9 days; M2 (target Feb 22) is overdue by 2 days. The team needs to focus aggressively on M1 completion items before moving to M2 work. Any `MoSCoW/Could Have` items in M1-M2 should be deferred to avoid further slippage.
The project is running **7-9 days behind** the original aggressive schedule. M1 (target Feb 15) is overdue by 9 days; M2 (target Feb 22) is overdue by 2 days. A major workload rebalancing from Luis (33 remaining issues, lowest velocity) to Jeff (highest velocity, capacity available) is being executed to close the gap. Any `MoSCoW/Could Have` items in M1-M2 should be deferred to avoid further slippage.
### Parallel Workstreams
@@ -1962,14 +1962,14 @@ Development is organized into six concurrent workstreams plus continuous quality
| Track | Focus Area | Status |
| :---- | :--------- | :----- |
| **A** — Plan Lifecycle | Action/plan domain models, persistence, CLI alignment, execute/apply wiring | Core models and persistence done; execute/apply pipeline in progress |
| **A** — Plan Lifecycle | Action/plan domain models, persistence, CLI alignment, execute/apply wiring | Core models and persistence done; CLI extensions merged today (#325). Execute/apply pipeline in progress. Config service (#352) deferred to M5. |
| **B** — Projects & Resources | Resource registry, project model, resource types, sandbox strategies, CLI | **Substantially complete.** Registry, models, CLI, handler runtime (git-checkout + fs-directory), DAG metadata all done. Auto-discovery remaining. |
| **C** — Actors, Tools, Skills | Actor YAML schema/loader/compiler, tool registry/runtime, skill framework, MCP adapter, validation runner | Schemas, loaders, tool runtime, file/git/search tools done. MCP adapter in progress (Aditya). Actor compiler and validation runner remaining. |
| **D** — Decisions & Apply | Decision tree model, change tracking, diff review, apply pipeline, correction engine | Decision domain model and context snapshots done (PR #385). Decision persistence in progress (Hamza). Correction engine models done. Apply pipeline partially done. |
| **C** — Actors, Tools, Skills | Actor YAML schema/loader/compiler, tool registry/runtime, skill framework, MCP adapter, validation runner | **Actor compiler DONE** (#158 merged today). Agent skills discovery DONE (#161 merged today). Actor CLI aligned (#288 merged today). MCP adapter in review (Aditya PR #382). Agent skills loader in review (Aditya PR #416). Validation runner remaining. |
| **D** — Decisions & Apply | Decision tree model, change tracking, diff review, apply pipeline, correction engine | Decision domain model and context snapshots done. **Decision persistence in review** (Hamza PR #131). Correction engine models done. Apply pipeline partially done; sandbox merge (#155) active. |
| **E** — Subplans | Subplan domain model, orchestration, parallel execution, three-way merge | Domain model done; orchestrator and merge logic remaining |
| **F** — ACMS & Context | UKO ontology, CRP protocol, context strategies, assembly pipeline, hot/warm/cold tiers | Not yet started; scheduled for later milestones |
| **Q** — Quality & CI | Pre-commit hooks, Forgejo CI/CD, coverage enforcement (97%), security scanning | Complete and ahead of schedule |
| **T** — Testing | Behave unit tests, Robot integration tests, ASV benchmarks, end-to-end smoke suites | Ongoing; currently carried by quality specialist and feature owners |
| **F** — ACMS & Context | UKO ontology, CRP protocol, context strategies, assembly pipeline, hot/warm/cold tiers | Not yet started; scheduled for M5-M6 milestones |
| **Q** — Quality & CI | Pre-commit hooks, Forgejo CI/CD, coverage enforcement (97%), security scanning | Complete. Database parallelism fix merged today (#418). |
| **T** — Testing | Behave unit tests, Robot integration tests, ASV benchmarks, end-to-end smoke suites | Ongoing; CLI extension tests in review (Brent PR #420). E2E milestone suites (#402-#407) pending. Rui returns Feb 27. |
### What Has Been Completed
@@ -1981,21 +1981,22 @@ The following major areas are fully or substantially implemented:
- **CLI commands**: Action (create/list/show/archive), Plan (use/execute/apply/status/list/cancel/diff/artifacts), Skill (add/remove/list/show/tools), Session (create/list/show/delete/tell/export/import), Actor (run/add/remove/list/show with context management), Tool, LSP, Resource, Validation, Config, Invariant, Automation-Profile, Audit, and Cleanup command groups — all with multi-format output support (rich/json/yaml/plain/table/color).
- **Tool runtime**: Tool registry with thread-safe operations, tool runner with four-stage lifecycle (discover/activate/execute/deactivate), built-in file tools (read/write/edit/delete/list/search), git tools (status/diff/log/blame), tool call router for multi-provider format normalization (OpenAI/Anthropic/LangChain), and path traversal prevention.
- **Sandbox infrastructure**: Sandbox protocol with status transitions, NoSandbox implementation for non-sandboxable resources, git_worktree and copy-on-write sandbox strategies, sandbox factory, thread-safe sandbox manager with plan-scoped tracking, and three merge strategies (git, sequential, JSON deep-merge).
- **Actor system**: Actor loader with thread-safe discovery, SHA-256 content-hash caching, namespace normalization, duplicate detection, and tool reference resolution. Actor registry with CRUD operations and built-in generation. Jinja2 YAML template engine with sandboxed rendering.
- **Actor system**: Actor loader with thread-safe discovery, SHA-256 content-hash caching, namespace normalization, duplicate detection, and tool reference resolution. Actor registry with CRUD operations and built-in generation. Jinja2 YAML template engine with sandboxed rendering. **Actor compiler** translating GRAPH-type YAML definitions into LangGraph NodeConfig/Edge structures with subgraph resolution, cycle detection, entry/exit validation, and LSP binding metadata (#158 merged 2026-02-24). Actor CLI commands aligned to YAML-first configs with --format support (#288 merged 2026-02-24).
- **Resource system**: Resource registry with DAG metadata, handler runtime for git-checkout and fs-directory resource types, resource type schema loader, project-resource linking.
- **Decision system**: Decision domain model with 12 decision types, context snapshot capture, influence DAG support, and `with_superseded_by()` helper for frozen model mutation.
- **Automation levels**: Manual, review-before-apply, and full-automation modes with plan-level overrides, settings resolution, pause/resume, and auto-progression. 8 built-in automation profiles with guard logic.
- **Correction engine**: Correction model with revert/append modes, BFS impact analysis, dry-run reporting.
- **Phase reversion**: State machine for constrained apply -> back to strategize transitions.
- **Security hardening**: All `eval()`/`exec()` calls replaced with named operation registries, config security scanner detecting 15 disallowed patterns, AST-based code validation, Jinja2 sandboxed environments, secrets masking and validation.
- **Quality automation**: Pre-commit hooks (12 hooks across 5 categories), Forgejo CI/CD pipeline with 10 nox-routed jobs, nightly quality monitoring, ADR compliance checking, 97% test coverage enforcement, and comprehensive security scanning (Bandit + Semgrep + Vulture).
- **Agent skills discovery**: Filesystem scanning for Agent Skills Standard folders (SKILL.md with YAML front-matter), registering discovered skills as tools in ToolRegistry with configurable conflict handling (skip/error/replace), refresh hooks, and CLI integration (#161 merged 2026-02-24).
- **CLI extensions**: Plan use command extended with --automation-profile, --invariant (repeatable), --strategy-actor/--execution-actor/--estimation-actor/--invariant-actor flags. Plan status/list and action show commands extended with profile, invariant, and actor override rendering across all output formats (#325 merged 2026-02-24).
- **Quality automation**: Pre-commit hooks (12 hooks across 5 categories), Forgejo CI/CD pipeline with 10 nox-routed jobs, nightly quality monitoring, ADR compliance checking, 97% test coverage enforcement, comprehensive security scanning (Bandit + Semgrep + Vulture), and per-scenario temp database isolation for parallel Behave execution (#418 merged 2026-02-24).
### What Remains To Be Done
The majority of the specification's domain models, services, CLI commands, and infrastructure modules are now implemented. The following areas still require completion or have only partial implementations:
- **Actor compiler**: A standalone compiler module that transforms actor YAML configurations into runnable LangGraph StateGraph instances (graph node wiring, conditional routing, subgraph invocation). The actor loader, registry, and schema infrastructure exist; the compilation step from YAML to executable graph is the remaining gap. **This is the M2 critical-path blocker.**
- **MCP runtime adapter**: Live connection to MCP servers for external tool discovery and invocation at runtime. Aditya has active work on `develop-aditya-2` branch. Schema and domain models exist; the runtime bridge is pending.
- **MCP runtime adapter**: Live connection to MCP servers for external tool discovery and invocation at runtime. Aditya has active work on `develop-aditya-2` branch with PR #382 in review. Schema and domain models exist; the runtime bridge is pending. **This is the remaining M2 critical-path blocker** (actor compiler was merged 2026-02-24).
- **Decision persistence**: Hamza has active work on `feature/m4-decision-persistence`. The domain model and context snapshots are now merged; the database persistence layer (tables, repositories, CRUD) is next.
- **Decision recording service**: Wire decision recording into the strategize/execute phases so decisions are automatically captured during plan execution.
- **Validation runner pipeline**: A dedicated module for executing required and informational validations attached to resources, with pass/fail gating on the apply phase.
@@ -2025,77 +2026,95 @@ The following areas are substantially implemented and are no longer blocking:
### Milestone Roadmap
#### Milestone 1: Minimal Plan Execution (Target: Feb 15, ETA: ~Feb 25)
#### Milestone 1: Minimal Local Source-Code Workflow (Target: Feb 15, ETA: ~Feb 27)
**Goal**: A minimally usable local-mode flow where a user can register an action from YAML, link a git repository resource to a project, and run a plan end-to-end (`plan use` -> `plan execute` -> `plan diff` -> `plan apply`) with a sandboxed workspace and tool-based change capture.
**Current status**: ~86% of M1 tasks complete (7 open out of ~157 total M1 issues). Resource handler runtime (git-checkout, fs-directory) now done. Actor runtime and tool-calling partially operational.
**Current status**: ~96% of M1 tasks complete (6 open out of ~153 total M1 issues). Resource handler runtime (git-checkout, fs-directory) done. Actor runtime and tool-calling partially operational. Database parallelism fix merged today.
**Key remaining work**:
- Sandbox merge/apply pipeline with conflict resolution and validation gating hooks (#155)
- E2E source-code plan lifecycle smoke test suite (#156)
- FakeListLLM default removal and provider cost controls (#323, #324)
- Docs reorganization completion (#408, #409)
- Sandbox merge/apply pipeline with conflict resolution and validation gating hooks (#155, Luis — active branch)
- E2E source-code plan lifecycle smoke test suite (#156, Brent)
- M1 success criteria verification (#402, Brent)
- FakeListLLM default removal and provider cost controls (#323, #324 — reassigned to Jeff)
#### Milestone 2: Actor Compiler + Full LLM Integration (~Day 20)
#### Milestone 2: Actor Compiler + Full LLM Integration (Target: Feb 22, ETA: ~Mar 1)
**Goal**: Actor YAML files compile into live LangGraph graphs. Custom actors (strategy, execution, estimation) are fully operational. The tool router normalizes calls across providers, the validation runner enforces resource-attached validations, and the MCP adapter connects to external tool servers.
**Current status**: ~63% of M2 tasks complete (17 closed out of ~48 total M2 issues). Actor compiler (#158) merged today. MCP adapter (#159) in review (PR #382). Agent skills loader (#160) in review (PR #416). Actor YAML hierarchy (#157) active.
**Key remaining work**:
- Actor compiler (YAML -> LangGraph StateGraph)
- MCP adapter runtime and Agent Skills loader
- Validation runner with required/informational mode enforcement
- Full multi-provider tool routing (OpenAI, Anthropic, Google, OpenRouter)
- MCP adapter runtime (#159, Aditya — PR #382 in review)
- Agent skills loader (#160, Aditya — PR #416 in review)
- Actor YAML hierarchy extensions (#157, Aditya — active branch)
- Changeset persistence and diff review (#163, #303 — Jeff after reassignment, #303 deferred to M3)
- Validation runner with required/informational mode enforcement (#175, #176 — Jeff after reassignment)
- M2 E2E actor integration suite (#403, Brent)
#### Milestone 3: Decision Tree + Correction (~Day 26)
#### Milestone 3: Decisions + Validations + Invariants (Target: Feb 26, ETA: ~Mar 5)
**Goal**: Decisions are recorded during Strategize and Execute phases and persisted to the database. Users can view the decision tree (`plan tree`), inspect individual decisions (`plan explain`), manage invariants (`invariant add/list/remove`), and correct decisions (`plan correct --mode revert|append`) with selective subtree recomputation.
**Key remaining work**:
- Decision domain model and persistence
- Decision recording during strategize/execute phases
- Invariant enforcement and reconciliation
- Correction engine (revert and append modes)
- Plan tree and explain CLI commands
#### Milestone 4: Subplans + Parallel Execution (~Day 30)
**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. This milestone is the threshold for handling **large, complex codebases** — the system can decompose a large task into independent subtasks, execute them concurrently, and merge the results.
**Current status**: ~33% of M3 tasks complete (5 closed out of ~15 total M3 issues). Decision domain model and context snapshots merged. Decision persistence (#171) in review (PR #131, Hamza).
**Key remaining work**:
- Subplan orchestrator and scheduler
- Parallel execution with max_parallel limits and fail-fast behavior
- Three-way merge of subplan changesets with conflict detection
- Phase reversion (constrained apply -> back to strategize)
- Parent plan status aggregation across subplan tree
- Decision persistence service wiring (#171, Hamza — PR #131 in review)
- Decision recording during strategize/execute phases (#172, Hamza)
- Plan tree and explain CLI commands (#174, Hamza)
- Diff review artifacts (#303, Luis — active branch, deferred from M2 to M3)
- Invariant enforcement and reconciliation (#319-#322, Hamza after reassignment)
- Validation runner and gating (#175, #176, Jeff after reassignment)
#### Milestone 5: ACMS + Large-Project Context (~Day 34)
#### Milestone 4: Corrections + Subplans + Checkpoints (Target: Mar 2, ETA: ~Mar 8)
**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. Correction engine supports revert and append modes. Checkpointing enables rollback to previous plan states.
**Current status**: ~59% of M4 tasks complete (13 closed out of ~22 total M4 issues). Phase reversion landed. Subplan domain model done.
**Key remaining work**:
- Correction engine — revert mode (#178, Jeff after reassignment)
- Correction engine — append mode (#186, Jeff after reassignment)
- Subplan orchestrator and scheduler (#201, Jeff after reassignment)
- Parallel execution with max_parallel and fail-fast (#259, Jeff after reassignment)
- Three-way merge of subplan changesets (#312, Jeff after reassignment)
- Checkpoint persistence and rollback (#313, Jeff after reassignment)
- CLI extension tests (PR #420, Brent — in review)
- M4 E2E correction + subplan suite (#405, Brent)
#### Milestone 5: ACMS v1 + Context Scaling (Target: Mar 6, ETA: ~Mar 11)
**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.
**Key remaining work**:
- UKO ontology with RDF-based resource representation
- CRP protocol for actor context requests
- Context strategies (keyword, semantic, graph, temporal)
- Ten-component context assembly pipeline
- Hot/warm/cold tiered storage with skeleton compression
#### Milestone 6: Large-Scale Autonomous Execution (~Day 38)
**Goal**: The system can autonomously execute a large-scale task (e.g., porting a substantial codebase) 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. This is the target for demonstrating production-level autonomous capability in local mode.
**Current status**: ~21% of M5 tasks complete (4 closed out of ~19 total M5 issues). UKO/RDF groundwork started (Hamza). Config service foundations exist.
**Key remaining work**:
- Hierarchical decomposition (recursive subplan planning)
- Autonomous estimation (cost/risk/time) before execution
- Performance tuning for large-project context assembly
- End-to-end porting run with validation gates
- Comprehensive integration test suite
- UKO ontology with RDF-based resource representation (#338, #342, #343, Jeff after reassignment)
- CRP protocol for actor context requests (#199, Jeff after reassignment)
- Context strategies — keyword, semantic, graph, temporal (#208, #209, Jeff after reassignment)
- Ten-component context assembly pipeline (Hamza)
- Hot/warm/cold tiered storage with skeleton compression (Hamza)
- M5 E2E ACMS integration suite (#406, Brent)
#### Milestone 6: Autonomy Hardening + Server Stubs (Target: Mar 10, ETA: ~Mar 13)
**Goal**: The system can autonomously execute a large-scale task (e.g., porting a substantial codebase) 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. Client-side server stubs are in place for future connectivity.
**Current status**: ~26% of M6 tasks complete (5 closed out of ~19 total M6 issues). Foundation work from M3-M5 will accelerate M6.
**Key remaining work**:
- Hierarchical decomposition — recursive subplan planning (#335, #336, Jeff after reassignment)
- Autonomous estimation — cost/risk/time (#337, Jeff after reassignment)
- Performance tuning for large-project context assembly (#340, Jeff after reassignment)
- Server connectivity client stubs (#323, #324, Jeff after reassignment)
- End-to-end porting run with validation gates (all)
- M6 E2E autonomy integration suite (#407, Brent)
### Beyond Day 38: Extended Roadmap
@@ -2123,7 +2142,7 @@ Final refinements to achieve the complete specification:
The project is currently running approximately **7-9 days behind** the original aggressive schedule. The primary causes are: (1) the scope of v2-to-v3 architectural transition was larger than anticipated, requiring significant model realignment and test rewriting; (2) CI/CD pipeline stabilization consumed more effort than planned due to container resource constraints and cross-environment compatibility issues; and (3) the execute/apply pipeline — the critical vertical slice — was deferred in favor of breadth-first foundation work.
The gap is expected to **narrow** in later milestones because the foundational infrastructure (persistence, CLI patterns, quality gates, domain models) is now solid and reusable. Each subsequent milestone builds on proven patterns rather than establishing new ones.
The gap is expected to **narrow** in later milestones because: (a) foundational infrastructure (persistence, CLI patterns, quality gates, domain models) is now solid and reusable; (b) aggressive workload redistribution on Day 16 moved 25 issues from slower developers (Luis, Hamza) to Jeff (highest velocity), reducing bottleneck risk; and (c) each subsequent milestone builds on proven patterns rather than establishing new ones. Actor compiler merging today unblocks actor-dependent work across M2-M4.
!!! note "Server Mode"
@@ -2135,13 +2154,13 @@ The gap is expected to **narrow** in later milestones because the foundational i
| Developer | Role | Primary Focus Areas | Notes |
|-----------|------|---------------------|-------|
| **Jeff** (freemo) | CTO/Lead Architect | Critical path items, architectural decisions, complex integrations | Fastest, most expert developer - handles blocking issues |
| **Luis** (CoreRasurae) | Senior Python Architect | Domain models, persistence, algorithms, state machines | Good architecture but can be pedantic - needs clear requirements |
| **Aditya** (aditya) | Domain Expert (Agents/LLMs) | Actor YAML configs, hierarchical actors, skill execution | Understands topic best but code may need cleanup |
| **Hamza** (hamza.khyari) | Python/RDF Expert | Resources, sandbox, database, general Python | Well-rounded, no agent experience - assign infrastructure |
| **Rui** (hurui200320) | Fast Developer | Testing (Behave/Robot), simpler implementations (post-2026-02-27) | New to Python; unavailable 2026-02-13 to 2026-02-27 |
| **Brent** (brent.edwards) | Quality Specialist | Code review, linting, type checking, E2E tests, documentation | Slow but detail-oriented - low contention independent work |
| **Mike** (mngrif) / **Brian** (brian) | Sysadmins | Deployment, infrastructure setup, CI/CD | Minimal coding tasks |
| **Jeff** (freemo) | CTO/Lead Architect | Critical path items, M3-M6 feature work (validation, corrections, subplans, ACMS, server stubs) | Fastest developer — absorbed 25 issues from Luis/Hamza to unblock schedule |
| **Luis** (CoreRasurae) | Senior Python Architect | Apply pipeline (#155), diff review (#303) — active branches only | Workload reduced from 41 to ~4 open issues; 22 reassigned out. Focus on completing active branches |
| **Aditya** (aditya) | Domain Expert (Agents/LLMs) | MCP adapter (#159), agent skills (#160), actor YAML hierarchy (#157) | 3 PRs in flight; highest domain expertise for actor system |
| **Hamza** (hamza.khyari) | Python/RDF Expert | Decision persistence (#171), decision recording (#172), invariant enforcement (#319-#322) | Picks up 4 invariant issues from Luis; decision track is critical path for M3 |
| **Rui** (rui.vieira) | Fast Developer | Testing (Behave/Robot), simpler implementations | Returns 2026-02-27; will take M3+ integration test suites |
| **Brent** (brent.edwards) | Quality Specialist | E2E milestone suites (#402-#407), CLI extension tests (PR #420), coverage enforcement | Detail-oriented — owns all milestone verification testing |
| **Mike** (mngrif) / **Brian** (brian) | Sysadmins | Deployment, infrastructure setup, CI/CD, ASV runner (PR #388) | Minimal coding tasks |
## Weekly Development Schedules
@@ -2214,11 +2233,13 @@ The gap is expected to **narrow** in later milestones because the foundational i
| Risk | Mitigation | Owner |
|------|------------|-------|
| Git worktree complexity | Use B4.sandbox git_worktree with pre-commit verification and isolation tests | Jeff |
| Multi-file generation reliability | Validate C9.execute/C9.apply flows with diff review artifacts and Robot E2E | Luis + Brent (Rui after 2026-02-27) |
| Decision tree correction bugs | Jeff reviews D4 correction + checkpointing; add revert/append Behave coverage | Jeff |
| Large codebase performance | Profile CTX1/CTX2 indexing + hot/warm/cold tiers; enforce bounded memory tests | Luis + Hamza |
| Server connectivity stubs stability | Keep client-only stubs isolated; gate with feature flags and contract tests | Jeff + Luis |
| Apply pipeline completion (#155) | Luis has active branch; Jeff available to pair if blocked beyond Feb 26 | Luis (Jeff backup) |
| MCP adapter + agent skills merge | Aditya has 2 PRs in review (#382, #416); expedite review cycle | Aditya + Jeff (reviewer) |
| Decision system critical path | Hamza's PR #131 blocks M3; invariant issues (#319-#322) now assigned to Hamza | Hamza + Jeff (reviewer) |
| Jeff overload post-redistribution | 25 new issues absorbed; mitigate via parallel execution + prioritization of Must-Have items first | Jeff |
| Large codebase performance | Profile ACMS indexing + hot/warm/cold tiers; enforce bounded memory tests | Jeff + Hamza |
| Rui ramp-up after return | Pre-assign Behave/Robot test suites for M3+; pair with Brent first day back | Rui + Brent |
| Server connectivity stubs stability | Keep client-only stubs isolated; gate with feature flags and contract tests | Jeff |
## Schedule Adherence History
@@ -2872,17 +2893,23 @@ Note: Story point allocation was not recorded at this time.
**Summary**
Status: Behind ~7-9d
Deadline risk: HIGH
Deadline risk: HIGH
Overall completion: 72.3% (134/221 milestone issues closed, excluding Epics/Legendaries)
**Notes**
- **Today's merges**: Actor compiler #158 (Jeff), agent skills discovery #161 (Jeff), actor CLI alignment #288 (Jeff), CLI plan/action extensions #325 (Jeff), database parallelism fix #418 (Brent)
- Decision domain model + context snapshots merged (Hamza PR #385)
- resource registry + DAG metadata + handler runtime merged
- phase reversion landed
- MCP adapter in progress (Aditya)
- decision persistence in progress (Hamza)
- docs reorganization in progress (Jeff)
- 17 stale pre-rebaseline issues closed during tracker cleanup.
- Resource registry + DAG metadata + handler runtime merged
- Phase reversion landed
- MCP adapter in review (Aditya, PR #382)
- Agent skills loader in review (Aditya, PR #416)
- Decision persistence in review (Hamza, PR #131)
- CLI extension tests in review (Brent, PR #420)
- Apply pipeline active (Luis, branch `feature/m1-apply-pipeline`)
- 29 issues being redistributed: 18 Luis→Jeff, 4 Luis→Hamza, 7 Hamza→Jeff (no active branches on any)
- Issues #402-#407 (E2E milestone verification suites) moved from Unverified to Verified
- #303 (diff review artifacts) deferred from v3.1.0 to v3.2.0.
#### Milestone forecast
@@ -2913,13 +2940,13 @@ Deadline risk: HIGH
| Name | Days Ahead/Behind | Availability | Risk | Focus |
|------|-------------------|--------------|------|-------|
| Jeff | -2d behind | available | HIGH | M1 completion (sandbox apply), actor compiler (#158), docs (#408) |
| Luis | -3d behind | available | HIGH | validation pipeline (#175, #176), changeset persistence (#163), sandbox merge (#155) |
| Hamza | -1d behind | available | MED-HIGH | decision persistence (#171), decision recording (#172), plan explain CLI (#174) |
| Aditya | +1d ahead | available | MEDIUM | MCP adapter (#159), agent skills (#160), actor YAML extensions (#157) |
| Brent | on track | available | MEDIUM | E2E suites (#156, #169, #402-#407), DB parallelism fix (#410) |
| Rui | N/A (unavailable until Feb 27) | returning 2026-02-27 | MEDIUM | Behave/Robot tests after return |
| Mike/Brian | N/A | standby | LOW | ASV runner fix (#388) |
| Jeff | +1d ahead (5 merges today; 58/92 issues closed = 63% after absorbing 25 new issues) | available | HIGH | Picks up 25 reassigned issues from Luis/Hamza across M2-M6+. Immediate: M3 validation (#173, #176, #178), M4 corrections (#186), M5 ACMS (#338, #342, #343) |
| Luis | -5d behind (8/19 issues closed = 42% post-redistribution) | available | HIGH | **Reduced to active branches only**: apply pipeline (#155, active branch), diff review (#303, active branch, deferred to M3). 18 issues reassigned to Jeff, 4 to Hamza |
| Hamza | -1d behind (6/22 issues closed = 27%; +4 invariant issues absorbed) | available | MED-HIGH | Decision persistence (#171, PR in review), decision recording (#172), plan explain CLI (#174). Picks up 4 invariant issues (#319-#322) from Luis |
| Aditya | +1d ahead (20/26 issues closed = 77%) | available | MEDIUM | MCP adapter (#159, PR #382 in review), agent skills (#160, PR #416 in review), actor YAML hierarchy (#157, active branch) |
| Brent | on track (17/32 issues closed = 53%) | available | MEDIUM | CLI extension tests (PR #420), E2E milestone suites (#156, #402-#407), coverage enforcement |
| Rui | N/A (returns Feb 27) | returning 2026-02-27 | MEDIUM | Behave/Robot test suites after return |
| Mike/Brian | N/A | standby | LOW | ASV runner fix (#388, PR in review) |
#### Task inventory
@@ -2928,14 +2955,14 @@ Note: Each cell is **completed/total issues** for that milestone/owner per Forge
| Milestone | Jeff | Aditya | Luis | Hamza | Brent | Rui | Unassigned | Total |
|-----------|------|--------|------|-------|-------|-----|------------|-------|
| M1 | 25/25 | 12/12 | 1/4 | 4/4 | 8/10 | 0/0 | 26/26 | 76/81 |
| M2 | 15/19 | 8/13 | 4/9 | 1/1 | 2/5 | 0/0 | 0/1 | 30/48 |
| M3 | 4/4 | 0/0 | 0/4 | 1/4 | 0/3 | 0/0 | 0/0 | 5/15 |
| M4 | 6/6 | 0/0 | 3/9 | 0/1 | 3/5 | 0/0 | 1/1 | 13/22 |
| M5 | 1/6 | 0/1 | 0/1 | 0/6 | 1/3 | 0/0 | 2/2 | 4/19 |
| M6 | 2/5 | 0/0 | 0/7 | 0/2 | 3/5 | 0/0 | 0/0 | 5/19 |
| M6+ | 0/1 | 0/0 | 0/7 | 0/7 | 0/1 | 1/1 | 0/0 | 1/17 |
| **Total** | **53/66** | **20/26** | **8/41** | **6/25** | **17/32** | **1/1** | **29/30** | **134/221** |
| M1 | 25/27 | 12/12 | 1/2 | 4/4 | 8/10 | 0/0 | 26/26 | 76/81 |
| M2 | 20/24 | 8/13 | 4/4 | 1/1 | 2/5 | 0/0 | 0/0 | 35/47 |
| M3 | 4/7 | 0/0 | 0/2 | 1/4 | 0/3 | 0/0 | 0/0 | 5/16 |
| M4 | 6/8 | 0/0 | 3/4 | 0/4 | 3/5 | 0/0 | 1/1 | 13/22 |
| M5 | 1/8 | 0/1 | 0/0 | 0/5 | 1/3 | 0/0 | 2/2 | 4/19 |
| M6 | 2/10 | 0/0 | 0/4 | 0/0 | 3/5 | 0/0 | 0/0 | 5/19 |
| M6+ | 0/8 | 0/0 | 0/3 | 0/4 | 0/1 | 0/0 | 1/1 | 1/17 |
| **Total** | **58/92** | **20/26** | **8/19** | **6/22** | **17/32** | **0/0** | **30/30** | **139/221** |
#### Story point allocation
@@ -2944,11 +2971,11 @@ Note: Each cell is **completed/total story points** for that milestone/owner per
| Milestone | Jeff | Aditya | Luis | Hamza | Brent | Rui | Unassigned | Total |
|-----------|------|--------|------|-------|-------|-----|------------|-------|
| M1 | 172/172 | 128/128 | 8/32 | 19/19 | 65/71 | - | 95/95 | 487/517 |
| M2 | 113/142 | 49/86 | 29/66 | 5/5 | 10/21 | - | - | 206/320 |
| M3 | 37/37 | - | 0/34 | 5/23 | 0/11 | - | - | 42/105 |
| M4 | 34/34 | - | 29/74 | 0/5 | 18/24 | - | 1/1 | 82/138 |
| M5 | 5/45 | 0/8 | 0/8 | 0/45 | 8/14 | - | 4/4 | 17/124 |
| M6 | 13/42 | - | 0/68 | 0/21 | 24/30 | - | - | 37/161 |
| M6+ | 0/8 | - | 0/56 | 0/53 | 0/5 | 8/8 | - | 8/130 |
| **Total** | **374/480** | **177/222** | **66/338** | **29/171** | **125/176** | **8/8** | **100/100** | **879/1495** |
| M1 | 172/188 | 128/128 | 8/16 | 19/19 | 65/71 | - | 95/95 | 487/517 |
| M2 | 142/171 | 49/86 | 29/29 | 5/5 | 10/21 | - | - | 235/312 |
| M3 | 37/58 | - | 0/21 | 5/23 | 0/11 | - | - | 42/113 |
| M4 | 34/47 | - | 29/34 | 0/32 | 18/24 | - | 1/1 | 82/138 |
| M5 | 5/61 | 0/8 | - | 0/37 | 8/14 | - | 4/4 | 17/124 |
| M6 | 13/92 | - | 0/39 | - | 24/30 | - | - | 37/161 |
| M6+ | 0/64 | - | 0/24 | 0/29 | 0/5 | - | 8/8 | 8/130 |
| **Total** | **403/681** | **177/222** | **66/163** | **29/145** | **125/176** | **0/0** | **108/108** | **908/1495** |