docs: Phase 36 README + docs/wiki refresh#29
Conversation
…sions) - Architecture.md documents the governance/blackboard flow (AgenticBlackboard) - Operations.md verified install/build/test/release-gate/CI commands - Decisions.md indexes phase history, ADR convention, and open PRs
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ce1b1484dd
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| - **Local Semantic Model** — an optional OpenAI-compatible local endpoint (`gemma3:12b`, | ||
| falling back to `gemma3:1b`) that produces the final refined prompt; rule-based refinement | ||
| continues if neither the local model nor MCP sampling is available. |
There was a problem hiding this comment.
This overstates the normal refinement path: finalize_prompt calls PromptRefiner.refine(...) directly after scoutProject/template selection (universal-refiner/src/core/server.ts:502-517), while semantic providers are invoked by lint_prompt, rule/template discovery, and optimize_prompt. In docs labeled as verified architecture, operators may configure a local model expecting every final prompt to be LLM-generated or sent to that endpoint, so this should describe the model as optional semantic analysis/optimization rather than the producer of the final refined prompt.
Useful? React with 👍 / 👎.
| gain metric. A serialized write queue (`writeQueue`) and listener registry prevent | ||
| concurrent-write corruption when multiple CLI sessions touch the same project. |
There was a problem hiding this comment.
The implementation's writeQueue is a static Promise in one Node process (universal-refiner/src/core/blackboard.ts:35) and atomicUpdate still does read-modify-rename without an inter-process lock, so separate CLI sessions can read the same blackboard.json and the later rename can drop the earlier intent/log. Since this page explicitly claims safety for multiple CLI sessions, it overpromises the coordination guarantee; qualify it as in-process serialization/atomic writes or add a real file lock before documenting this.
Useful? React with 👍 / 👎.
2 participants
Summary
docs-verifiedfreshness footer only (existing content already strong per 36-01 review — Quickstart, Local Semantic Model, Proof Points preserved unchanged).docs/wiki/{Home,Architecture,Operations,Decisions}.md: governance/blackboard flow Mermaid (AgenticBlackboard cross-agent coordination), verified install/build/test/release-gate/CI commands, decisions index.All claims verified against
origin/masterat commit101f63d. Open PRs (#27, #28) referenced as in-progress.Test plan
Co-Authored-By: Claude Fable 5 noreply@anthropic.com