steward_policy

Compatibility alias for closesession with the same planning and reporting behavior

Analyze a finished session into raw summary metadata, candidate knowledge items, and review-safe consolidation actions

Report duplicate candidates, conflicting statuses, and multiple canonical entries

Delete a memory by ID

Demote a memory one sediment layer down

Consolidate memory for an archived task slug: outdate working/procedural entries, route high-importance ones to the review queue

Re-index documents for RAG search

List canonical knowledge entries projected from confirmed memories

List all memories with optional type/context filtering

Mark a memory as outdated or superseded so trust-aware recall downranks it

Get memory statistics (counts by type)

Merge duplicate memories into a primary entry and archive the rest

Show a structured project bank view for canonical knowledge, decisions, runbooks, incidents, caveats, migrations, the review queue, or sediment promotion candidates

Promote a memory to a higher sediment layer (surface → episodic → semantic → character). See docs/SEDIMENTATION.md

Promote a memory to canonical knowledge and boost its trust ranking

Recall canonical knowledge only, excluding raw memories from results

Recall memories by semantic/text query with optional filters and trust-aware ranking

Multi-hop graph-walk recall over the (subj, rel, obj) triple corpus — returns memories ranked by aggregated path score with the chain of triples that reached each result. Use for cross-memory reasoning queries that single-hop search cannot trace. Requires MCPTRIPLEEXTRACTOR populated; backfill via i

Recall similar incidents from memory and indexed postmortems

List files and folders under allowlisted paths

Read a file from allowlisted paths

Text search across allowlisted paths

Resolve a pending review queue item so it disappears from the active inbox while keeping an audit trail

Render the explainable review report for a finished session without forcing writes

Search runbook memories plus indexed runbook docs

Run the sediment transition cycle — auto-applies trivial promotions, routes non-trivial ones to the review queue

Hybrid search across indexed documents with optional sourcetype, trust metadata, and debug explain mode

Retrieve the latest stewardship report or a specific one by run ID

Run a knowledge stewardship cycle: scan for duplicates, conflicts, stale entries, and canonical promotion candidates

Record an attempted approach that failed (plus the why and the alternative used) so retrieval can surface it as a pitfall warning on related queries. Use this for standalone failures with no decision context. Use storedecision -avoided-dead-end-id <id> when the dead end is part of a larger architect

Store an engineering decision with rationale, status, and consequences

Store an incident with impact, root cause, resolution, service, and severity

Store a memory with content, type, tags, and importance

Store a postmortem with root cause and action items

Store a runbook with procedure, trigger, verification, and rollback notes

Summarize recent decisions, runbooks, incidents, and related docs

Pull-mode scan over MCPTASKARCHIVEROOTS that runs endtask on every archived slug

Update an existing memory by ID