openclaw 调用本地昇腾mindie的qwen3-32b异常：
第一种配置异常：HTTP 422: "Check open ai req parameter error"
"local": {
"baseUrl": "http://127.0.0.1:8001/v1",
"apiKey": "sk-local",
"api": "openai-completions",
"models": [
{
"id": "local_model",
"name": "local_model",
"reasoning": false,
"input": ["text"],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 4096
}
]
}
第二种异常：只改变了api的类型 "api": "openai-responses"
404 status code (no body)
- 错误日志：
vllm_openai_infer.cpp:1166 Check input Text failed
查了半天依然无法解决，官方是否有类似的解决案例可供参考，或者有根治的解决方案呢。
点赞
收藏
回复
分享
举报
已解决
openclaw 调用本地昇腾mindie的qwen3-32b异常：
第一种配置异常：HTTP 422: "Check open ai req parameter error"
"local": {
"baseUrl": "http://127.0.0.1:8001/v1",
"apiKey": "sk-local",
"api": "openai-completions",
"models": [
{
"id": "local_model",
"name": "local_model",
"reasoning": false,
"input": ["text"],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 32768,
"maxTokens": 4096
}
]
}
第二种异常：只改变了api的类型 "api": "openai-responses"
404 status code (no body)
vllm_openai_infer.cpp:1166 Check input Text failed查了半天依然无法解决，官方是否有类似的解决案例可供参考，或者有根治的解决方案呢。