请求与响应遵循 OpenAI-compatible 规范，支持流式（stream: true）与非流式两种模式。

响应示例

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "choices": [{ "index": 0, "message": { "role": "assistant", "content": "你好！" }, "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15 }
}