Changhyun Min 0031c5c371 refactor(agent): treat unknown Solar models as reasoning-capable ... Invert the reasoning-support check from an allow-list (solar-pro, solar-open) to a deny-list of the known non-reasoning families (solar-mini, syn-pro). Newly released Solar models now get reasoning_effort by default instead of having it silently dropped. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-07-15 00:09:24 +05:30
..
test_custom_profile.py	fix(custom-provider): emit reasoning_effort at the live profile path	2026-07-04 14:19:44 +05:30
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_fireworks_profile.py	fix(providers): align Fireworks integration with project policy	2026-07-11 05:43:35 -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_ollama_cloud_profile.py	feat(reasoning): add max and ultra effort levels (#62650)	2026-07-12 00:26:49 -07:00
test_opencode_go_profile.py	feat(providers): GLM-5.2 native reasoning_effort controls (#58884)	2026-07-05 13:48:01 -07:00
test_upstage_profile.py	refactor(agent): treat unknown Solar models as reasoning-capable	2026-07-15 00:09:24 +05:30
test_zai_profile.py	feat(providers): GLM-5.2 native reasoning_effort controls (#58884)	2026-07-05 13:48:01 -07:00