Files
FabledScribe/tests
bvandeusenandClaude Opus 5.5 be62abf142
CI & Build / Plugin hooks (push) Successful in 17s
CI & Build / Python lint (push) Successful in 2s
CI & Build / TypeScript typecheck (push) Successful in 55s
CI & Build / integration (push) Successful in 1m25s
CI & Build / Python tests (push) Successful in 2m6s
CI & Build / Build & push image (push) Successful in 1m25s
perf(retrieval): one embedding per query per plugin request (milestone 456 step 1, #4903)
A single plugin request fans one query out to several ranked arms. The
operator message is searched by auto_inject, its reuse and lesson slots,
prompt_rule, the preference slot and rule_via_lesson, and each arm called
get_embedding on its own: up to six model calls for one vector.

- embeddings.query_embedding_memo(): a request-scoped ContextVar memo that
  get_embedding consults. Outside a scope the default is None, so every
  other caller is unchanged. A failed embedding is not remembered.
- memoized_query_embeddings decorates /retrieve, /tool-rules and
  /prior-art.
- get_embeddings (document chunks) is untouched.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05 07:55:06 -04:00
..