如题，同一个模型1.1.4版本可以正常使用。
请求命令与参数如下（把其他请求参数去掉，只保留role user也是一样）：
curl -X POST http://localhost:8080/v1/chat/completions \
-H "Authorization: Bearer API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen3.5-Plus",
"messages": [
{"role": "system", "content": "You are a helpful assistant, give correct and true answer to user."},
{"role": "user", "content": "你是什么模型？"}
],
"stream": false,
"stream_options": {
"include_usage": true
},
"enable_thinking": true,
"max_tokens": 1024,
"temperature": 0.1,
"top_p": 0.2
}'1.1.4版的日志：
# 请求
{"model":"Qwen3.5-Plus","messages":[{"role":"system","content":"You are a helpful assistant, give correct and true answer to user."},{"role":"user","content":"你是什么模型？"}],"stream":false,"stream_options":{"include_usage":true},"enable_thinking":true,"max_tokens":1024,"temperature":0.1,"top_p":0.2}
# 响应
{"id":"a2***1-**-**-**-*********","model":"qwen3.5-plus","object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"我是 Qwen3.5，是阿里巴巴集团旗下的通义实验室自主研发的超大规模语言模型。我能够回答问题、创作文字（如写故事、写公文、写邮件、写剧本、逻辑推理、编程等），还能表达观点、玩游戏等。如果你有任何具体问题或需要帮助，欢迎随时告诉我！","reasoning_content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1,"total_tokens":2},"created":1776308749}
1.2.0版的日志：
# 请求
{"model":"Qwen3.5-Plus","messages":[{"role":"system","content":"You are a helpful assistant, give correct and true answer to user."},{"role":"user","content":"你是什么模型？"}],"stream":false,"stream_options":{"include_usage":true},"enable_thinking":true,"max_tokens":1024,"temperature":0.1,"top_p":0.2}
# 响应
{"id":"","model":"Qwen3.5-Plus","object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"","reasoning_content":""},"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1,"total_tokens":2},"created":1776308693}
其它信息
- 系统：ubuntu 20.04
- 软件：Chat2API-1.1.4-amd64.deb、Chat2API-1.2.0-amd64.deb
如题，同一个模型1.1.4版本可以正常使用。
请求命令与参数如下（把其他请求参数去掉，只保留role user也是一样）：
1.1.4版的日志：
1.2.0版的日志：
其它信息