ReMe/tests
BeiMu-new bc47906f79 fix(embedding): stop quota failures and transient item errors from multiplying
Review follow-up on the two P2 findings in #579:

* quota exhaustion no longer falls into the per-item split. The store now gives
  up explicitly when the provider reports insufficient_quota, including after
  the opt-in quota retries are spent, because no single item is to blame and
  splitting only multiplied the rejected requests (3 items -> 4 requests).
* the per-item fallback goes back through `_call_with_retry`, so a 429,
  connection error or timeout on an isolated item keeps the existing backoff
  and retry policy instead of silently dropping that item's vector. A one-item
  request still cannot split again.

Regression tests cover both findings: a quota failure stays a single request
with the default policy and with exhausted quota retries, and a transient
failure on one item of a split batch still ends with every healthy sibling
embedded.

python -m pytest tests/unit/test_local_embedding_store.py tests/unit/test_file_store_consistency.py -q
-> 83 passed, 41 skipped
2026-10-16 21:10:38 +08:00
..
fixtures/config fix(ci): support AgentScope 2.0.6 initialization (#457) 2026-08-19 11:33:52 +08:00
integration feat(integrations): add automatic memory plugins for Claude Code and Codex (#575) 2026-10-12 20:12:47 +08:00
unit fix(embedding): stop quota failures and transient item errors from multiplying 2026-10-16 21:10:38 +08:00