sseToJsonHandler.js unconditionally deleted reasoning_content from all non-streaming responses (added for Firecrawl SDK compatibility). This breaks thinking models (Qwen3.5, Claude extended thinking, etc.) where the model may use all tokens for reasoning, leaving content empty. When reasoning_content is stripped in that case, the response appears completely empty to the client. Fix: only strip reasoning_content when the response also has non-empty content, so that reasoning output is preserved when it is the only useful output. Co-authored-by: Agent Zero <agent@agent-zero.local> |
||
|---|---|---|
| .. | ||
| chatCore | ||
| chatCore.js | ||
| embeddingsCore.js | ||
| responsesHandler.js | ||
| ttsCore.js | ||