7610f28f42
Gemini CLI requests with small max_tokens spend the whole output budget on thoughts after reasoning_effort maps to thinkingConfig, returning blank content or finish=length. Raise maxOutputTokens floors per thinking level/ budget (clamped to caps.maxOutput). Also emit toolConfig functionCallingConfig.mode=VALIDATED for Gemini CLI tool requests to avoid MALFORMED_FUNCTION_CALL. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| chunk.js | ||
| finishReason.js | ||
| image.js | ||
| json.js | ||
| message.js | ||
| modality.js | ||
| paramSupport.js | ||
| prefetch.js | ||
| reasoning.js | ||
| thinking.js | ||
| thinkingUnified.js | ||
| toolCall.js | ||
| usage.js | ||