hkfires d20b71deb9 fix(thinking): normalize effort mapping ...

Route OpenAI reasoning effort through ThinkingEffortToBudget for Claude
translators, preserve "minimal" when translating OpenAI Responses, and
treat blank/unknown efforts as no-ops for Gemini thinking configs.

Also map budget -1 to "auto" and expand cross-protocol thinking tests.

2025-12-15 09:16:15 +08:00

..

claude_openai_request.go

fix(thinking): normalize effort mapping

2025-12-15 09:16:15 +08:00

claude_openai_response.go

rebuild branch

2025-09-25 10:32:48 +08:00

init.go

rebuild branch

2025-09-25 10:32:48 +08:00