backlog_consolidation_candidates
Identify clusters of episodic memories ready for consolidation into durable knowledge, returning bundles to process into narratives.
Instructions
List clusters of episodic memories that are ripe for consolidation into durable knowledge. Consolidator workflow: (1) call this and take ripe bundles; (2) per bundle, read members (backlog_get on MEMO- ids for depth), then write ONE narrative memory via backlog_remember({ layer: "semantic"|"procedural", derived: true, entity_refs: [member MEMO- ids + key source entities], context }) — a self-contained story, not fragments; (3) retire the members via backlog_forget({ ids }) so they stop appearing here while staying auditable; (4) track your progress with a backlog_remember state_key like "consolidation.watermark.".
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| min_count | No | Minimum bundle size to be ripe. Default: 3. | |
| min_age_days | No | Minimum age (days) of the oldest member. Default: 7. | |
| min_demand | No | Recall-demand threshold — bundles recalled this often (30d) are ripe regardless of age. Default: 3. | |
| context | No | Restrict to one context (e.g. "FLDR-0001"). | |
| limit | No | Max bundles, ripe first. Default: 10. | |
| max_digests | No | Max digest lines per bundle. Default: 10. |