[Bug]: from_openai_message misses vLLM-served Qwen3 reasoning field (uses ‘reasoning’ instead of ‘reasoning_content’)
![[Bug]: from_openai_message misses vLLM-served Qwen3 reasoning field (uses 'reasoning' instead of 'reasoning_content')](https://www.chat-gpts.plus/wp-content/uploads/2026/06/21582-8f2b1a6d-768x403.jpg)
用户使用 LlamaIndex 的 OpenAI 兼容 LLM 客户端( llama-index-llms-openai )连接 vLLM 服务器(>=0.20.x),服务模型为 Qwen3/Qwen3.5/Qwen3.6 系列(如 Qwen/Qwen3.6-35B-A3B,并启用 --reason
![[Bug]: GLM-5 tool calls in stream mode get error tool name](https://www.chat-gpts.plus/wp-content/uploads/2026/06/39757-790e149e-768x403.jpg)
![[Bug]:Existing document id collision with another knowledge base](https://www.chat-gpts.plus/wp-content/uploads/2026/06/14360-83480988-768x403.jpg)

![[Bug]: obj serialization mismatch](https://www.chat-gpts.plus/wp-content/uploads/2026/06/21611-5b2ecf70-768x403.jpg)


![[Local LLM] 有支持 6000 Ada 使用 deepseek v4 flash 推理 的框架吗](https://www.chat-gpts.plus/wp-content/uploads/2026/06/ai_cover_4-741-768x403.jpg)
![[Question]: ApiError(503, 'search_phase_execution_exception', None)](https://www.chat-gpts.plus/wp-content/uploads/2026/06/14830-05bd00c6-768x403.jpg)
