backlog_recall
Recall past knowledge and episodes captured across sessions using free-text queries, with stubs or full memory bodies, filtered by tags, layers, and context.
Instructions
Recall memories — knowledge and episodes captured across sessions. Returns STUBS (title + one-line digest + provenance) by default; expand interesting ones with backlog_get(MEMO-id), or pass full:true for bodies. Weigh a stub's trust BEFORE hydrating: age_days (on the knowledge's own timeline), uses/idle_days (recall demand), supersedes (this is a correction), derived (consolidator inference), kind (current/historical/plan/preference/timeless). Old + never-used = treat as hypothesis, not truth. Distinct from backlog_search (live entities). Use to answer "how do we deploy?", "have I hit this before?", "what did I finish about X?". Memories point back to source entities via entity_id.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| full | No | Return full memory bodies instead of stubs. Prefer stubs + backlog_get for the ones you need. | |
| home | No | Select the document home for this read. "all" queries global plus the explicitly supplied/bridged project root; it never scans prior projects. | |
| tags | No | Filter by memory tags (any-match). e.g. ["artifact"] or ["task"]. | |
| limit | No | Max results. Default: 10. | |
| query | Yes | Free-text query (keyword or phrase). | |
| layers | No | Restrict to specific memory layers. Default: all persisted layers (episodic + semantic + procedural). | |
| context | No | Optional scope — usually a parent_id like "FLDR-0001". Filters to memories captured with that entity as their context. | |
| project_root | No | Project root for this call. Overrides the bridge project root and selects the project home. | |
| token_budget | No | Approximate token budget — results are greedily packed to fit. |