Forget

The user wants to remove data from agentmemory: $ARGUMENTS

Quick start

memory_smart_search { "query": "old api key in config", "targetLayer": "memory", "limit": 20 }

Show the matches, get a yes, then:

memory_governance_delete { "memoryIds": "abc12345,def67890", "reason": "user privacy request" }

Expected output:

Found 2 matching memories. Confirmed. Deleted 2 memories.

Why

This is destructive and irreversible. Show exactly what will be deleted and get an explicit yes before calling delete. Delete by memory ID, never a bare session.

Workflow

1. Search with memory_smart_search, the user's text as query, targetLayer: "memory", limit: 20, and the requested project/agent scope. These are selected relevance matches, not an exhaustive inventory.
2. Show what matched: memory ids, titles, and scope. Redact secret values. Ask for explicit confirmation. Do not proceed on silence or a vague "sure, whatever".
3. On confirmation, call memory_governance_delete with memoryIds as a comma-separated string and optional reason (default plugin skill request).
4. Observation or whole-session erasure is not supported by this operation. Explain that limit before proceeding; never label selected memory deletion as a complete session wipe. Do not pass observation IDs or a sessionId.
5. Lessons are separate: delete one with memory_lesson_delete and its lessonId; memory_governance_delete does not touch lessons.
6. Check deleted, notFound, and failed in the response. Report actual deletions and unresolved IDs separately. Recheck the selected IDs before retrying a failed request; an interrupted response may hide a completed write.

Anti-patterns

WRONG: search returns matches, you immediately call memory_governance_delete without showing them or waiting for a yes.

RIGHT: list the matches, ask "Delete these 2? (yes/no)", and only delete after an explicit yes.

Checklist