feat: workflow enforcement, RAG upgrade, and permission fixes

Task Management:
  - Add cancellation safeguards: require valid reason category (duplicate,
    obsolete, blocked_permanently, reassigned, scope_change, stakeholder_request)
  - Protect active work from arbitrary cancellation - must pause/block first
  - Auto-notify PM when task is blocked with ACTION REQUIRED message
  - PM task scan now shows blocked tasks needing their attention

  Permissions:
  - Add VIEW_STATS to Developer, QA, Documenter, Head Marketing KB permissions
  - Aligns code with docs/workflows/PERMISSIONS.md specification

  RAG/Embeddings:
  - Upgrade embedding model from all-MiniLM-L6-v2 to nomic-embed-text-v1.5
  - 768 dimensions with 8K token context (vs 512 tokens)
  - Add per-index chunk sizes: docs=1536, journals=1024, others=512
  - Switch to fixed chunking (semantic chunking loads separate MiniLM model)
  - Add einops dependency required by nomic model
This commit is contained in:
Renn F
2025-12-29 00:30:18 +01:00
parent fc55068f2b
commit 5315e9c72d
33 changed files with 1288 additions and 843 deletions
+14
View File
@@ -154,6 +154,20 @@ roboco_journal_search("qa patterns") # Your past reviews
See [KNOWLEDGE_BASE.md](./KNOWLEDGE_BASE.md) for full documentation.
## Agent-to-Agent (A2A) Tools
QA can collaborate directly with other agents:
```python
roboco_agent_discover(role, team, skill) # Find agents who can help
roboco_agent_request(target_agent, skill, message) # Request work
roboco_agent_request_status(a2a_task_id) # Check request progress
```
**When to use A2A:**
- Need dev clarification? → `roboco_agent_request("be-dev-1", "code_review", "Can you explain...")`
- Need security review? → `roboco_agent_discover(skill="security_audit")`
## Key Rules
1. **Only claim awaiting_qa** - Can't claim pending tasks