Back to Omniroute

10139 Thinking Output Cap Provider Scope

changelog.d/fixes/10139-thinking-output-cap-provider-scope.md

3.8.49378 B
Original Source
  • fix(translator): resolve the Claude thinking output cap with the routed provider so a provider-scoped-only max_output_tokens override is no longer invisible to fitThinkingToMaxTokens(), which previously let the synthesized max_tokens (caller room + thinking budget) go out unbounded and 400 upstream (#10139)