Recall — brief me on this graph
recallRead-onlyIdempotent
CALL THIS FIRST, before working in a graph — it is the briefing.
One composite read that answers what a cold agent actually needs: what
this graph holds (classes and counts), what landed recently, where the
graph contradicts itself, how much is waiting for a human's approval,
and the newest session checkpoint — where the last session stopped.
`memory` is the graph's slug from list_my_memories. `topic` additionally runs the
hybrid search and inlines the hits, so "brief me, and specifically about
pricing" is one call rather than two. `limit` bounds the recent list.
Read the `status` on everything it returns: 'unapproved' rows are
proposals a human has not accepted, and saying so is the difference
between reporting the team's record and inventing it — `review_queue`
counts how many are waiting, and a person clears them in the review UI. `conflicts` are
places the graph disagrees with itself — surface them, don't pick a side.
`value_conflicts` are one object's property carrying more than one value,
because two sources disagree (an IC memo's EBITDA against a QoE's): each
lists the values you may read with their status and sources, and
`waiting_for_review` counts values a person has not approved yet, which
you cannot see. Name both sides and say a value is still waiting; never
present one value as settled while its object has a value conflict.
Reach for something else when you already know what you are looking for:
semantic_search for a topic, get_object for one thing, list_objects for a
population.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| topic | No | ||
| memory | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||