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

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

4.9 KiB

Raw Blame History

View Raw