Learn lightweight conversational style signals from the latest user message. Pass only the message text — not secrets, private memories, or full conversation logs. Optionally include hints: things YOU (the host LLM) noticed that the built-in dictionary wouldn't catch, such as a self-invented sentence-final particle or a unique structural quirk.

Return a short style brief for the agent to use lightly. Call this at the start of a conversation or before drafting a friendly reply.

One-shot batched distillation: based on the user's recent ~10–20 messages, identify 3–7 signature expressions (catchphrases, sentence-final particles, structural quirks, etc.) and write them all at once. Treated as user-endorsed — each habit becomes active immediately if its content passes basic checks. Use sparingly: at conversation seed-time, or when the agent feels its style brief is too thin.

One-shot batched distillation of concrete collaboration preferences. Use for response structure, explanation style, workflow, and decision-making preferences — not personality labels.

List stored style habits and candidates from the local JSON store.

List stored collaboration and response-structure preferences from the local JSON store.

Return a concise review queue with suggested actions such as keep, pin, forget, or observe.

Return a concise review queue for stored collaboration preferences, with suggested actions such as keep, pin, forget, or observe.

Delete a style habit by id or exact text.

Delete a collaboration preference by id or exact text.

Pin or unpin a style habit so cleanup will not delete it.

Pin or unpin a collaboration preference so cleanup will not delete it.

Enable or disable style learning in the local JSON store.

Score whether the local style memory is usable, stable, fresh, and at risk of drift or over-imitation.

Show where the local JSON store lives and how many habits are stored.