Teknium 49e743985a fix: route minimax m3 reasoning controls through profile ... Follow up PR #46609's api.minimax.io reasoning report by moving the behavior out of the broad run_agent host gate and into the MiniMax provider profile. Only MiniMax-M3 on the documented OpenAI-compatible /v1 route gets reasoning_split/thinking/reasoning_effort; Anthropic-format MiniMax and non-M3 models keep their existing wire shapes. Co-authored-by: goku94123 <gooku94123@gmail.com>		2026-06-15 07:08:43 -07:00
..
test_deepseek_profile.py	fix(deepseek): set default_aux_model on profile so aux warning stops firing	2026-05-16 22:54:22 -07:00
test_kimi_profile.py	fix(kimi): send thinking xor reasoning_effort, never both	2026-06-07 01:24:29 -07:00
test_minimax_profile.py	fix: route minimax m3 reasoning controls through profile	2026-06-15 07:08:43 -07:00
test_opencode_go_profile.py	fix(opencode-go): gate thinking when reasoning_effort set to avoid HTTP 400	2026-06-07 01:24:29 -07:00