optimize_stage
Stage memory curation suggestions for human review in the dashboard, skipping invalid ones and reporting errors before application.
Instructions
Stage a batch of curation suggestions for human review in the dashboard.
Step 2 of the "optimize my memories" workflow. NOT applied here: the user reviews and applies or rejects each one in the admin dashboard, which backs up before the first apply and can undo any of them.
Invalid suggestions are skipped and reported in errors, as many as fit
one page, with errors_total counting them all when some are left out;
the rest are staged. Returns {run_id, staged, errors}.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | one short summary of the pass, at most 250 characters; a longer one raises and stages nothing. What a single suggestion needs said belongs in its own `rationale` and `verified`, which are not capped. | |
| suggestions | Yes | each one {"kind", "target_uid", "payload", "rationale", "verified"}. Kinds: compact/reword {"new_content"}, retag {"tags"}, retitle {"title"}, redomain {"domain"}, crosslist {"also": [...]} (replaces the whole set), set_confidence {"confidence"}, review {"review_after"} (a date or a span like '180d'; '' clears it), archive {"reason"}, link {"from_uid","to_uid","relation_type"}, merge {"keep_uid","drop_uid"}, distill {"source_uids","new_type","new_content", "title"}, unleak {"field": "content|tags|source_ref"} (the repair is computed at staging). link/merge derive target_uid from the payload and distill creates its target -- omit it for those. Destructive kinds (archive, set_confidence=contradicted, merge, distill) require a non-empty `verified` describing the live-facts check behind them. |