Find Similar Career Points
kb_groom_entityCluster similar bullets on a career knowledge-base entity and propose a keeper via deterministic embedding scores, so you can review duplicates before combining or retiring points.
Instructions
Similar bullets on one Career KB entity, clustered, with a proposed keeper. Deterministic and zero LLM calls: the pinned local embedder scores every pair of the entity's active points (drafts included, retired and user_cannot_confirm excluded) and joins pairs at 0.80 cosine and above, minus pairs the user marked "Not the same" at /career. Proposes only; nothing is written. Each cluster carries score, keeper_id, members [{id, text, state, origin, provenance, usage_count, best_score}] and pairs. The keeper rule is approved over draft, then most recently updated, then longest text. compared_wording is false when the embedder could not run; clusters is then empty. Acting on a cluster is kb_combine_points (one claim in other words: the others become the keeper's wordings) or kb_retire_points (a similar but stale one).
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": {
"entity_id": "<entity_id>"
},
"name": "kb_groom_entity"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| entity_id | Yes |