Record a canonical learning
record_learningSave reusable technical truths (API gotchas, invariants, constraints) under one topic per note. Reusing the topic replaces old content, preserving current knowledge for upcoming tickets.
Instructions
Record a durable, re-usable truth discovered while working — an API gotcha, an invariant, a constraint, a design decision confirmed in code (e.g. 'OCC fillets need edge ids re-resolved after every boolean'). One TOPIC = one canonical note (kb/learning-.md): calling again with the same topic REPLACES the body — latest confirmed truth wins, no appended contradictions; git keeps the history and the frontmatter accumulates ticket provenance. Use this for knowledge the NEXT ticket needs, not work narration (that's log_work) and not in-flight research (that's append_research). Learnings are indexed like any kb doc: they surface in search_kb, rag_search, and are auto-injected into matching work packets.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"project": "<project>",
"topic": "<topic>",
"content": "<content>"
},
"name": "record_learning"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Stable topic name — the canonical key. Re-use the SAME topic to update a truth (e.g. 'cad_fillet edge-id stability'). | |
| ticket | No | Ticket that produced/confirmed this learning; recorded as provenance. | |
| content | Yes | The current, complete truth on this topic in markdown. Replaces any previous body wholesale — write it to stand alone. | |
| project | Yes |