mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00

Files

T

4fb0059556 fix: journals/learnings never reached the RAG corpus + git-readonly slug 404s (#339 )

* 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>

2026-07-08 16:03:00 +02:00

2.4 KiB

Raw Blame History

Knowledge Base Search

ALL agents have access to KB/RAG tools. These are automatically available.

Recommended: Ask Mentor

For most questions, use roboco_ask_mentor:

roboco_ask_mentor(question="How do I handle authentication?")

It searches ALL knowledge sources and supports follow-up questions.

Search Types

Tool	Purpose	Best For
`roboco_ask_mentor`	Conversational help	Most questions
`roboco_kb_search`	Semantic search	Browsing, exploration
`roboco_rag_query`	AI-synthesized answer	Quick answers

Semantic Search

roboco_kb_search(
    query="rate limiting redis implementation",
    top_k=5,                      # Results to return
    project="roboco-api",         # Optional project filter
    index_types=["code", "docs"]  # Filter by type
)

Returns similar content - not just keyword matches.

RAG Query (AI Answer)

roboco_rag_query(
    query="How does authentication work in this codebase?",
    top_k=5
)

Returns AI-synthesized answer with citations.

Good for:

"How does X work?"
"What pattern should I use?"
"What decisions were made about Y?"

Mentor (Conversational)

# First question
response = roboco_ask_mentor(
    question="How do I handle authentication?",
    domain="coding"
)

# Follow-up
roboco_ask_mentor(
    question="What about refresh tokens?",
    conversation_id=response["conversation_id"]
)

Index Types

Type	Content
`code`	Source files
`docs`	Documentation
`journals`	Agent journal entries
`errors`	Error patterns & fixes
`standards`	Coding rules
`decisions`	Architectural decisions
`reviews`	Code review patterns
`learnings`	Captured learnings

Before Starting a Task

Always search first:

roboco_kb_search(query="implementing rate limiter")
# Journal entries are part of the KB — filter to them with index_types:
roboco_kb_search(query="rate limit decisions", index_types=["journals", "decisions"])

This helps you:

Avoid repeating mistakes
Find proven patterns
Learn from others' experiences

Proactive Context

System auto-provides context when you claim:

roboco_get_proactive_context(task_id)
# Returns: similar_tasks, relevant_learnings, code_patterns,
#          applicable_standards, recent_decisions, known_issues

2.4 KiB Raw Blame History