Files
roboco/docs/rag/tools/kb-tools.md
T
879afc14a4 Board Program LEARN context, ruff 0.16, and verb-rejection observability (#700)
* fix(board): LEARN decisions name the item, not its per-cycle index

A cycle's reject reasons are rendered into the NEXT cycle's exploration
prompt, but the ref recorded alongside each reason was the item's stored
id (item-0/item-1) — a per-cycle index that means something different
every cycle and appears nowhere the explorer can resolve. The reason
survived the loop; what it was about did not.

Record the item's title instead, via a shared learn_ref() helper (falls
back to the id when title-less, and reads target_task_title for Scales,
whose items name the live task they mutate).

* chore(lint): satisfy ruff 0.16 — keyword-only signatures and markdown formatting

The dev toolchain resolved ruff 0.16.0, which stabilises PLR0917 (too many
positional arguments) and formats python code blocks inside markdown. Both
fired repo-wide and neither had anything to do with the code they flagged.

- 36 signatures gain a `*` so their tail arguments are keyword-only, and
  the 104 call sites that passed them positionally are converted. mypy was
  the safety net for the static ones; the full suite caught nine more that
  only bind at runtime (the MCP tool functions, whose real callers already
  pass named JSON arguments).
- 28 markdown files reformatted by 0.16's code-block formatter.
- One RUF036 (`None` mid-union) autofixed in the GitLab provider.

* fix(gateway): log the reason when a verb rejects

A rejected envelope rides an HTTP 200, its body is never logged, and there
is no trace table — so in the access log a verb an agent could not satisfy
looks identical to one that worked. On 2026-07-25 four Board Programs
(Periscope, Sentinel, Scales, Barfly) each POSTed their propose verb three
or four times, persisted nothing, and left their exploration tasks PENDING;
the reason was unrecoverable afterwards, from the logs or from the agents'
own transcripts.

Log error/message/remediate/missing plus the calling agent at
envelope_to_response — the one chokepoint every v1 flow and do route
returns through. Success envelopes stay silent.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-26 15:07:28 +02:00

164 lines
3.6 KiB
Markdown

# Knowledge Base Tools
## Search and Query
| Tool | Purpose |
|------|---------|
| `roboco_kb_search` | Semantic search |
| `roboco_rag_query` | AI-synthesized answer |
| `roboco_ask_mentor` | Conversational help |
| `roboco_kb_stats` | Index statistics |
## Semantic Search
```python
roboco_kb_search(
query="rate limiting redis",
top_k=5,
project="roboco-api",
index_types=["code", "docs"],
)
```
## AI-Generated Answers
```python
roboco_rag_query(query="How does authentication work?", top_k=5)
```
## Mentor (Conversational)
```python
response = roboco_ask_mentor(question="How do I handle auth?", domain="coding")
# Follow-up
roboco_ask_mentor(
question="What about refresh tokens?", conversation_id=response["conversation_id"]
)
```
## Documentation Writing (Documenter, Cell PM)
```python
# Write/update documentation (auto-dedup via RAG)
roboco_docs_write(
{
"task_id": "task-uuid",
"filename": "api-endpoints.md",
"doc_type": "api", # api, qa, guide, readme, changelog, architecture, design
"title": "API Endpoints",
"content": "# API Endpoints\n\n...",
}
)
# List docs for a task
roboco_docs_list(task_id="task-uuid")
# Read a doc
roboco_docs_read(path="backend/api/endpoints.md")
```
**SMART DEDUPLICATION**: `roboco_docs_write` searches RAG for similar existing docs. If high-similarity match found, updates instead of creating duplicate.
## Bulk Indexing
```python
# Index code (PM, Developer)
roboco_kb_index_code(sources=["src/**/*.py"], project="roboco-api")
# Index docs (PM, Documenter) - for bulk/explicit indexing
# Note: roboco_docs_write() auto-indexes when writing
roboco_kb_index_docs(sources=["docs/**/*.md"], project="roboco-api")
```
## Error Tracking
```python
# Search for similar errors
roboco_search_error(error_message="Redis connection timed out", context="startup")
# Record solution
roboco_record_error_solution(
error_message="Redis connection timed out",
solution="Added retry with backoff",
worked=True,
)
```
## Decision Tracking
```python
# Check for similar decisions
roboco_check_decision(topic="session storage")
# Record decision
roboco_record_decision(
params={topic: "Session storage", decision: "Use Redis", rationale: "Sub-ms reads"}
)
```
## Standards & Validation
### Get Standards
```python
roboco_get_standards(domain="coding", language="python")
```
**Domains:** `coding`, `security`, `workflow`, `architecture`
### Validate Action (LLM-Based)
Uses LLM to check code/context against organizational standards.
```python
result = roboco_validate_action(
action_type="create_endpoint",
context="""
def create_user(email, password):
user = User(email=email, password=password)
db.add(user)
return user
""",
)
```
**Returns:**
```json
{
"allowed": false,
"violations": [
{
"rule_id": "SEC-001",
"rule_title": "Password Hashing",
"message": "Password stored in plaintext",
"severity": "error",
"suggestion": "Hash password with bcrypt before storage"
}
],
"warnings": [...],
"relevant_standards": [...]
}
```
**How it works:**
1. Searches KB for relevant standards based on `action_type`
2. Sends standards + context to LLM for analysis
3. Returns structured violations with fix suggestions
4. Falls back to heuristic matching if LLM unavailable
**Action types:** `create_endpoint`, `add_dependency`, `database_migration`, `auth_change`, `file_upload`, `external_api`
### Code Review
```python
roboco_review_code(
code="def handle(...):",
file_path="src/api/auth.py",
change_type="modify", # add, modify, delete
)
```
**Returns:** Score (0-100), comments by severity, approval status