catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-03-01 15:03:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor(team): add fast-advance notification and knowledge transfer protocol

Browse Source 
- team-worker: add fast_advance message bus log after spawning successor,
  closing coordinator state blind spot during fast-advance
- team-worker: add Knowledge Transfer section with upstream loading,
  downstream publishing, and context_accumulator conventions
- role-spec-template: add Knowledge Transfer Protocol with Transfer
  Channels table and shared-memory.json namespaced write convention
- monitor.md (v2+v5): add fast-advance reconciliation step reading
  fast_advance messages, add State Sync section for coordinator wake
- lifecycle-v5 SKILL.md: update cadence diagram with fast_advance log
This commit is contained in:
catlog22
2026-02-28 22:53:56 +08:00
parent 67b2129f3c
commit e42597b1bc
4 changed files with 101 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.claude/skills/team-coordinate-v2/specs/role-spec-template.md
View File

@@ -134,3 +134,46 @@ Coordinator MAY reference these patterns when composing Phase 2-4 content for a
- Phase 2: Detect test framework + identify changed files from upstream
- Phase 3: Run test-fix cycle — iteration count and strategy determined by task
- Phase 4: Verify pass rate + coverage (Behavioral Traits) + update shared-memory
---
## Knowledge Transfer Protocol
How context flows between roles. Coordinator MUST reference this when composing Phase 2 of any role-spec.
### Transfer Channels
| Channel | Scope | Mechanism | When to Use |
|---------|-------|-----------|-------------|
| **Artifacts** | Producer -> Consumer | Write to `<session>/artifacts/<name>.md`, consumer reads in Phase 2 | Structured deliverables (reports, plans, specs) |
| **shared-memory.json** | Cross-role | Read-merge-write `<session>/shared-memory.json` | Key findings, decisions, metadata (small, structured data) |
| **Wisdom** | Cross-task | Append to `<session>/wisdom/{learnings,decisions,conventions,issues}.md` | Patterns, conventions, risks discovered during execution |
| **context_accumulator** | Intra-role (inner loop) | In-memory array, passed to each subsequent task in same-prefix loop | Prior task summaries within same role's inner loop |
| **Exploration cache** | Cross-role | `<session>/explorations/cache-index.json` + per-angle JSON | Codebase discovery results, prevents duplicate exploration |
### Phase 2 Context Loading (role-spec must specify)
Every generated role-spec Phase 2 MUST declare which upstream sources to load:
```
1. Extract session path from task description
2. Read upstream artifacts: <list which artifacts from which upstream role>
3. Read shared-memory.json for cross-role decisions
4. Load wisdom files for accumulated knowledge
5. For inner_loop roles: load context_accumulator from prior tasks
6. Check exploration cache before running new explorations
```
### shared-memory.json Usage Convention
- **Read-merge-write**: Read current content -> merge new keys -> write back (NOT overwrite)
- **Namespaced keys**: Each role writes under its own namespace: `{ "<role_name>": { ... } }`
- **Small data only**: Key findings, decision summaries, metadata. NOT full documents
- **Example**:
```json
{
"researcher": { "key_findings": [...], "scope": "..." },
"writer": { "documents_created": [...], "style_decisions": [...] },
"developer": { "files_changed": [...], "patterns_used": [...] }
}
```