Files
OmniRoute/open-sse
safeer cde81fb69c fix(response): strip internal reasoning placeholder from all reasoning fields
copyOpenAICompatibleReasoningFields only stripped the sentinel
(NON_ANTHROPIC_THINKING_PLACEHOLDER = "(prior reasoning summary
unavailable)") from reasoning_content and reasoning. Non-standard
reasoning fields (reasoning_text, thinking, thought) and
reasoning_details items passed through raw, leaking the internal
replay sentinel to clients on providers that use those fields
(e.g. Venice), where the model echo surfaces as a bogus thought block
and can degrade into empty turns.

Strip the sentinel from every forwarded reasoning field, including
per-item text/content inside reasoning_details; drop items/fields that
strip to nothing while preserving non-text details such as
reasoning.encrypted.

Fixes #9765
Refs #8081, #9606
2026-08-09 01:34:52 -03:00
..
2026-05-26 23:51:47 -03:00
2026-07-07 13:14:06 -03:00