teknium1 ce4e74b350 fix(kimi): send thinking xor reasoning_effort, never both ... The standalone Kimi/Moonshot profile (api.moonshot.ai/v1) sent both extra_body.thinking AND a top-level reasoning_effort. With no reasoning config it even defaulted to thinking:enabled + reasoning_effort:medium, pairing them on every default call. Moonshot treats these as mutually exclusive (cannot specify both 'thinking' and 'reasoning_effort'). Align with the kimi-k2 handling already shipped for the opencode-go relay: send effort when a recognized low|medium|high is requested, otherwise fall back to the extra_body.thinking toggle. Disabled sends thinking:disabled only. Never both. Reported by Cars29 (NOUS Discord). DeepSeek was deliberately left untouched: its native endpoint accepts both (verified by the live guardrail in test_deepseek_v4_thinking_live.py), so the report's DeepSeek claim does not hold there. Tests: tests/plugins/model_providers/test_kimi_profile.py pins the xor contract across all config shapes.		2026-06-07 01:24:29 -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	polish(minimax): address Copilot review comments on M3 default-aux fix	2026-06-04 05:53:35 -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