mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
ecea593a51
The RAG knowledge base (indexed and queried by agents at runtime) described entire fictional MCP tool surfaces — roboco_task_*, roboco_journal_*, roboco_message_send, roboco_notify_send, roboco_agent_*, roboco_session_*, roboco_workspace_*, roboco_project_* — that don't exist, so agents searching the KB were handed invented tool names. Rewrite every affected doc (tools, roles, workflows, troubleshooting, and the stale architecture snippets) to the real surface: the gateway intent verbs (give_me_work, i_will_work_on, open_pr, i_am_done, claim_review, pass, fail, claim_doc_task, i_documented, triage, delegate, i_will_plan, unblock, complete, escalate_up, escalate_to_ceo, ...) and content tools (commit, note(scope=...), say, dm, evidence, notify*, open_session, channels). Also reconcile the access-control docs to code: CEO can cancel (Board/Auditor cannot); the management-channel membership and the Auditor's silent-but-present status now match communications.py.
RAG Knowledge Base Documentation
Optimized documentation for the RoboCo AI agent knowledge base. Each file is sized for effective RAG chunking.
Structure
docs/rag/
├── roles/ # Agent role responsibilities
├── workflows/ # Step-by-step task flows
├── standards/ # Coding, security, testing rules
├── architecture/ # System components
├── tools/ # MCP tools reference
└── troubleshooting/ # Common issues and fixes
Organization Principles
- One topic per file - Each file covers a single concept
- Chunk-friendly - Content fits in 512-1536 token chunks
- Self-contained - Each file provides complete context
- Actionable - Focus on what agents need to DO
For Agents
When searching the knowledge base:
- Use
roboco_kb_search()for semantic search - Use
roboco_rag_query()for AI-synthesized answers - Use
roboco_ask_mentor()for conversational help
See docs/rag/tools/kb-tools.md for the full KB tool reference.