mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
4fb0059556
* fix(rag): per-index chunk floors — journals and learnings were never indexed The global 200-char garbage floor (sized for code/doc chunks) discarded every templated journal note and most distilled org-memory lessons, silently: ingest returned success with zero chunks, so agent journals and learnings were never retrievable via RAG. IndexConfig now carries a per-type min_chunk_length (journals 40, learnings 80, others unchanged). * fix(mcp): git-readonly tools default project_slug from the container env Agents 404ed /api/git/status with 'Project not found: roboco' — the tools made the LLM supply the slug and six doc examples taught a slug that matches no registered project. The tools now fall back to the ROBOCO_PROJECT_SLUG the orchestrator already injects, and the stale examples are corrected. * feat(rag): startup backfill re-ingests zero-chunk journals and learnings Before the per-index chunk-floor fix, ingest() returned success with chunk_count=0 for undersized content: every historical journal entry and distilled learning below the (then-global) 200-char floor was durably recorded in journal_entries but silently never got a chunks_journals / chunks_learnings row, and no exception meant the existing dead-letter (rag_index_failures) never saw it either. Extends the startup reconcile (roboco/api/app.py _reconcile_rag_indexes) with a new pass: backfill_unindexed_journals (roboco/services/ rag_index_failures.py) queries journal_entries for rows missing from each vector table and re-ingests them through the same live code paths (_reindex_journal_entry / record_learning). Journals and learnings are backfilled independently since a LEARNING entry can clear the (lower) JOURNALS floor while still failing the (higher) LEARNINGS floor — a learning's doc_source is a content hash, not the entry id, so presence there is checked by hashing each candidate the same way LearningsIndexPlugin.record_learning does and batch-querying chunks_learnings for those exact sources. Bounded to 200 rows per pass per boot (converges over restarts on a larger backlog) and best-effort per row (one failure never aborts the pass). Rows still under the current floor are excluded by a length filter in the SELECT so they are never retried forever, and private entries are excluded from the JOURNALS pass exactly like the live indexing path. * test(rag): scope backfill assertions to their own rows --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
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.