Check whether this problem (or a similar one) has been solved before. Call BEFORE investigating. Returns ranked hits with fix, avoid-list and confidence. Exact error text in signals enables deterministic matching; semantic + lexical search catches near matches. Read-only.

Store what happened after solving (or failing to solve) a non-trivial problem. Duplicates are merged automatically: the response says whether the record was created, merged into an existing one, or linked to one with a different fix. Keep it terse and never include secrets.

Feedback loop. After applying a fix from recall, report whether it worked. Updates the record's confidence, which drives future ranking. If it failed, pass a short note and it is added to the record's avoid-list.

Patch fields of an existing record (better fix, extra avoid items, corrected context). Only supplied fields change.

Permanently remove a record that is wrong or obsolete.

Deterministic clustering of episodes that look like the same underlying lesson. For each cluster, write ONE record with kind='rule' that generalises them. Read-only; nothing is changed by this call.

Counts, success rate, duplicates prevented, embedding status, most common context tags.

Portability. mode='export' writes every record as JSONL (to path if given, else returned inline). mode='import' reads JSONL from path or jsonl and merges it idempotently: newer wins on id clash, duplicates are merged. Paths are .jsonl files inside the transfer directory (relative names are resolved there). Embeddings are not transferred; they are recomputed by whichever model the destination uses.