Files
9router/tests/unit
Anantachoke 7c2b1fe3e1 fix(translator): drop replayed reasoning fields for Groq/Mistral/Cerebras (#4220)
Strict OpenAI-compatible validators reject unknown assistant-message
fields: Groq 400 ("property 'reasoning_content' is unsupported"),
Mistral 422 ("extra_forbidden"), Cerebras 400 ("wrong_api_format").

Clients driving reasoning models (Hermes Agent, and anything following
the DeepSeek/Kimi convention) echo the previous turn's reasoning_content
on every assistant message, so from the second turn on every request to
these providers fails and a fallback combo silently skips them.

Add a dropMessageFields rule to paramSupport.js that strips
reasoning_content / reasoning / reasoning_details from assistant turns
for groq, mistral, and cerebras.
2026-09-21 20:02:21 +07:00
..
2026-06-15 18:18:04 +07:00
2026-06-15 18:18:04 +07:00
2026-05-09 22:48:07 +07:00
2026-06-15 18:18:04 +07:00
2026-06-15 18:18:04 +07:00
2026-06-15 18:18:04 +07:00
2026-04-22 15:36:51 +07:00