Retrieve relevant long-term memories for the current task. Call this at the START of any task before doing work. Returns ranked memories (facts, decisions, open tasks/questions) within a token budget, plus a count of open items. query should be a few keywords describing the task.

Persist ONE distilled memory after completing a work block. type is one of: fact, decision, task, question, note. content must be 1-2 sentences, self-contained, in past/declarative form (a distillation — never a raw transcript). entity is a short slug for what it concerns (e.g. 'auth', 'db-choice'). If a live memory already exists for the same type+entity, this returns a CONFLICT without writing — then either supersede(old_id,...) to update it, ask the user which stands, or retry with force=true to keep both.

Replace an outdated memory with an updated one. The old memory is kept in the chain for history (never deleted). Use this when a decision or fact has changed.

List open tasks and questions (optionally filter by type: 'task' or 'question'). Call when planning what to do next.

Mark a task/question as 'done' or 'dropped' (or reopen with 'open').

Show the full supersession chain for a memory — how a fact/decision evolved over time. Useful for 'why did we think X before?' questions.

Counts of total/live memories and open items. Cheap health check. Also reports token-usage metrics: recall_count, avg_tokens_per_recall, total_tokens_served (lifetime tokens returned by recall), live_corpus_tokens (estimated tokens across all live memories), and savings_ratio (live_corpus_tokens / avg_tokens_per_recall — roughly how many recalls it would take to read the whole corpus instead of a budgeted slice; null if no recalls have happened yet).