Add a belief grounded in an explicit user instruction or document independent of a queued incident. Provenance is required and persisted. Incident-derived conclusions must use record_experience and review_experience candidates; a standalone prior plus review feedback would count one incident twice.

Delete a belief and all its edges by ID. Returns {"deleted": true} if found, {"deleted": false} if not found.

Delete all beliefs tagged with a project name, along with their edges. Use this to forget project-specific knowledge when a project is complete.

Delete a pattern and all its edges by ID. Returns {"deleted": true} if found, {"deleted": false} if not found.

Add a new pattern to the graph.

Add a SUPPORTS edge from one belief to another.

Add a CAUSES edge from one belief to another (from_id causes to_id). Causal edges are what query_intervention traverses for counterfactual do(...) queries; unlike record_defeat this does NOT trigger propagation.

Add a DEFEATS edge and trigger defeat propagation cascade.

Add a bidirectional CONTRADICTS relationship between two beliefs.

Get a belief by ID.

List beliefs. If project is given, restricts to that project's beliefs plus untagged (global) beliefs; omit to list everything. Use limit and offset for bounded, oldest-first pages; without limit the legacy full array is returned.

List patterns. If project is given, restricts to that project's patterns plus untagged (global) patterns; omit to list everything.

Find all actively contradicting belief pairs. If project is given, restricts to pairs where both beliefs are visible in that project's scope (tagged with project or untagged).

Apply time decay to beliefs and return count of updated beliefs. If project is given, restricts the sweep to that project's beliefs plus untagged (global) beliefs.

Delete defeated beliefs whose grace period has elapsed (attenuated deletion — a defeated belief is deleted only once its probability has decayed below prob_threshold AND grace_hours have passed since it was last defeated, giving a wrong record_defeat call time to be caught and reversed first). Returns count of beliefs deleted. If project is given, restricts the sweep to that project's beliefs plus untagged (global) beliefs.

Hybrid retrieval: text match + graph-proximity expansion, ordered by probability. Set include_evidence=true to also return, per belief, the document passages that ground it (with weights). If project is given, restricts the candidate pool to that project's beliefs plus untagged (global) beliefs.

Ground a belief in a document passage: create a GROUNDS edge from a DocumentChunk to a Belief. Adds local positive evidence to the belief Beta state; GROUNDS never becomes a causal or belief-to-belief edge. Get chunk_id from query_document results.

Return the document passages grounding a belief (its GROUNDS edges), strongest first.

Run defeat propagation from a seed belief ID.

Counterfactual query P(downstream | do(target = value)). Severs the target's incoming edges and propagates along CAUSES edges only. READ-ONLY: returns projected probabilities for causal descendants; does NOT modify the graph. Use for 'if I change X, what downstream is affected?' — distinct from query_relevant (evidential association) and propagate_from (which mutates).

Parse a markdown file into heading-bounded chunks, embed each chunk, and index them for semantic search. Replaces existing chunks for the same path on reload. Requires [embeddings] in config.toml.

Semantic search over indexed document chunks. Embeds the query context and returns the most similar chunks ordered by cosine similarity. Requires [embeddings] in config.toml.

Remove all chunks and embeddings for a given document path. Returns {"cleared": N}. No-op if the path was never loaded.

Inspect the belief's incoming reasoning edges and a bounded page of active evidence-backed reviews. Follow experience_id with get_experience or experience_history for observations and past revisions. This explains provenance, not causal identification.

Record one observed action and outcome for incremental LLM review. Use a stable UUID for the same incident, expected_revision=0 to create, or the returned revision to correct it. Do not also insert a standalone conclusion from this same incident; review-owned candidates avoid that duplicate prior. Exact retries do not duplicate evidence. ToolResult/UserFeedback are caller-reported provenance, not server verification. A correction invalidates the old review and retracts its effects atomically.

Get the oldest new or changed experiences awaiting LLM review. Bounded incremental work: successful review removes that exact version; failed/stale submissions leave it pending. A judge may temporarily exclude deferred IDs; an empty filtered array does not prove the whole queue is empty. No claim or lease; concurrent reviewers use revision checks.

Apply one atomic, revision-checked review. Declare new belief/pattern candidates with stable keys; the response maps keys to server UUIDs. Candidate creation is not an observed successful use. Existing UUID-only reviews remain valid. Corrections retract owned evidence and links while retaining candidate identity and independent work.

Inspect current experience and revision tokens for safe correction or review.

Inspect immutable experience and review versions, including superseded judgments and their rationale.

Retrieve relevant beliefs and situation-matched procedures with outcome counts and Beta(1,1) success estimates. Agent reports and unknown outcomes do not count as measured success. Counts include current experience versions in this project only; retrieval is not successful use. Pattern matching is lexical; beliefs use existing hybrid retrieval.