fix(response): strip internal reasoning placeholder from all reasoning fields (#9790)

Browse Source

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

...

This commit is contained in:

adevwithpurpose

2026-08-11 16:25:35 +05:00

committed by GitHub

parent ce9b1e4641

commit 258fde411a

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

Diff Content Not Available