memory_record_use
Record whether a retrieved memory was ignored, contradicted, or corrected to adjust its future relevance and flag unresolved contradictions.
Instructions
Override the auto-applied outcome. Default behavior: every memory_search hit settles as applied at turn end (excerpts when the reply used it, auto=true otherwise). The common case handles itself — only call this tool when the model needs to record one of the three actionable outcomes below.
Outcome | When | What it does |
| retrieved but off-topic | annotates later hits; under |
| stored fact disagreed AND not yet fixed | raises the unresolved-contradiction flag until a later memory_update or memory_verify clears it; demotes 2x under the same flag |
| drifted and you fixed it inline (memory_update and/or memory_verify already called) | audit-only; does NOT raise the flag, never demotes |
applied is also accepted explicitly (rarely needed — auto handles it; call only to force-commit early).
Parameters:
memory_ids: list (1+).outcome: see table above.note(optional, ≤800 chars): free-form context.claim_excerpts(optional): list parallel tomemory_ids(same length,Noneslots OK) carrying the load-bearing phrase that shaped the response. ≤500 chars per excerpt. PassNonefor 'no specific claim' — empty strings are rejected (they're ambiguous: missing claim vs. zero-length claim). Especially useful oncontradicted/correctedso the audit log records WHICH claim was wrong, not just that the memory drifted. Surfaces back inrecent_negative_outcomeson later search hits.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| outcome | Yes | ||
| memory_ids | Yes | ||
| claim_excerpts | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||