litellm/tests/test_litellm/proxy/response_api_endpoints
ryan-crabbe-berri 49a8ce5e42 fix(responses): key a background response's managed row by the provider id
model_object_id is documented as "the id returned by the backend API
provider", and that is what batches and fine-tuning jobs store there. The
background responses create stored the advertised id in it instead, which
is encrypted with a fresh nonce on every call, so the row had no stable
handle on the generation it describes.

The cost poller now reads the provider id straight off the row. Rows
written before this still carry the advertised id there, and decrypting is
a no-op on an id that is already the provider's, so both shapes resolve
through the same call.

Claude-Session: https://claude.ai/code/session_01RHAjRxNhXTpKHeGMZ1nDKi
2026-09-15 00:37:54 +00:00
..
__init__.py [Fix] - Responses API - add /openai routes for responses API. (Azure OpenAI SDK Compatibility) (#15988) 2025-10-27 19:12:13 -07:00
test_endpoints.py fix(responses): key a background response's managed row by the provider id 2026-09-15 00:37:54 +00:00