Kirill Turanskiy 2ea95266e3 fix: clamp reasoning_effort to valid OpenAI-format values ...

CPA-internal thinking levels like 'xhigh' and 'minimal' are not accepted
by OpenAI-format providers (MiniMax, etc.). The OpenAI applier now maps
non-standard levels to the nearest valid reasoning_effort value before
writing to the request body:

  xhigh   → high
  minimal → low
  auto    → medium

2ea95266e3 · 2026-02-18 03:36:42 +03:00

History

..

provider

fix: clamp reasoning_effort to valid OpenAI-format values

2026-02-18 03:36:42 +03:00

apply.go

Add Kimi (Moonshot AI) provider support

2026-02-05 19:24:46 -05:00

convert.go

fix(thinking): map reasoning_effort to thinkingConfig

2026-01-15 13:06:40 +08:00

errors.go

refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation

2026-01-18 10:30:15 +08:00

strip.go

refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation

2026-01-18 10:30:15 +08:00

suffix.go

fix(thinking): map reasoning_effort to thinkingConfig

2026-01-15 13:06:40 +08:00

text.go

fix(thinking): map reasoning_effort to thinkingConfig

2026-01-15 13:06:40 +08:00

types.go

refactor(thinking): refine configuration logging

2026-01-15 13:06:41 +08:00

validate.go

fix(thinking): update ValidateConfig to include fromSuffix parameter and adjust budget validation logic

2026-01-18 16:37:14 +08:00