archive_memory
Archive a stale memory without deleting it so it leaves recall and lookups, or restore it to recall. A required reason is recorded, and archived entries remain readable when explicitly included.
Instructions
Take a stale memory out of recall and get_memory WITHOUT deleting it (archived=true), or bring it back (archived=false). The reason is required and stored on a revision. Allowed for whoever may write to the memory's scope: any agent with write access to the project for a project entry (not only its author), only the owner for an agent entry, leads for a workspace entry. Archived entries stay readable with include_archived=true. A repeat remember on an archived key updates it but keeps it archived. Prefer this to forget and to a short expires_at for anything that may be needed again.
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": {
"reason": "<reason>"
},
"name": "archive_memory"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | Exact key, used when memory_id is not given. Refused with the candidates listed if it names several entries; narrow with scope/project_id. | |
| scope | No | Narrows a key lookup: workspace, project or agent. | |
| reason | Yes | Why the entry leaves (or returns to) recall, up to 500 characters, e.g. 'MR merged and released; directive no longer applies'. | |
| archived | No | true archives (default), false restores. | |
| memory_id | No | UUID of the memory (the id field of recall full=true). Either memory_id or key is required. | |
| project_id | No | Narrows a key lookup to one project. |