Check memory storage status
amber_get_store_task_statusCheck whether a stored memory task is pending, processing, completed, or errored before listing, searching, deleting, or retrying facts. Poll by task ID or idempotency key to confirm writes finished.
Instructions
Check the processing status of a memory store task. Call this before you list, search for or delete the facts you just stored, or when the user asks whether something was saved. Do NOT hold your reply to the user waiting for completed: an accepted store is already durable and finishes in the background, usually within a minute for a few facts. Not rate-limited. Read-only. Requires an active subscription.
Statuses, and these are the ONLY four: pending (accepted and queued, nothing written yet), processing (facts are being written; some are already stored), completed (every fact written), error (error says why). Poll until completed -- note the ed. The import tool's vocabulary (awaiting_upload, running, complete, failed) was published here by mistake until 2026-09-12; an agent waiting for complete waited for ever.
progress reads Stored N/M memories... while writing. Facts are embedded in one batch and then written one at a time, each write idempotent and retry-safe, so a QUEUE redelivery creates no duplicates. That is Amber retrying internally. A CLIENT retry is different: re-sending the same amber_store_memory call starts a NEW task and stores a second copy, so check this status before resending after a transport error.
Rows become listable and SEARCHABLE as they land, NOT only at completed: a partially written task already has some of its memories retrievable. Wait for completed before concluding a fact is absent.
Returns code: not_found if the task_id doesn't exist or has expired (tasks are pruned after 7 days).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "amber_get_store_task_status"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | No | UUID from `amber_store_memory`'s response. Poll this to know when memories are ready to search. Invalid IDs return `code: not_found`. Omit it only if you are passing `idempotency_key` instead. | |
| idempotency_key | No | ALTERNATIVE to `task_id`: the key you sent to `amber_store_memory`. Use this when you never received the response and so have no task_id -- which is the exact situation the key exists for. Without it the only way to resolve a key is to re-issue the whole store, which needs the payload you may no longer hold. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| error | Yes | Error message if status is error. Null otherwise. | |
| status | Yes | `pending` queued, `processing` writing, `completed` all facts stored, `error` stopped (see `error`). Rows become listable and searchable AS THEY LAND, not only at `completed` -- a task mid-write already has some of its memories retrievable. Wait for `completed` before concluding a fact is ABSENT, which is the reason to wait; do not assume nothing is stored until then. | |
| task_id | Yes | The task this report is about. | |
| progress | Yes | Human-readable progress, e.g. 'Stored 4/14 memories...'. The count increments as memories are written. Null when pending, when completed, AND during the early phase of processing before the first memory is written -- so a null here does NOT mean the task is stuck; poll again. | |
| fact_count | Yes | How many facts this task was created with. Once status is `completed`, memory_ids.length MUST equal this -- compare them. A shorter list means some facts did not resolve to a stored row, which is a real shortfall and not something to report as a successful save. | |
| memory_ids | Yes | Memory IDs created by this task. Null until completed. |