Report === --- User-Friendly Information --- Message: 自定义模型 deepseek-flash-guan ...
错误信息
=== Error Report ===
--- User-Friendly Information ---
Message: 自定义模型 deepseek-flash-guan 错误，请切换模型或重试。
--- Technical Details ---
Error Code: 0
Request ID: 47adf31b3a524f82b9267bf9d9ebc134/84897462-9179-4415-a5a5-a7379e97e573
Trace ID: 47adf31b3a524f82b9267bf9d9ebc134
Timestamp: 2026/09/15 16:49:45 (UTC+8)
Server Detail: {"code":-32603,"message":"Internal error","data":{"message":"The `reasoning_content` in the thinking mode must be passed back to the API.","type":"invalid_request_error","param":"","code":0,"details":"400 The `reasoning_content` in the thinking mode must be passed back to the API. (acc6f9b2be6f44d99933674b1fe65e4d/84897462-9179-4415-a5a5-a7379e97e573)","statusCode":400,"category":"internal"}}
App Version: 5.5.6
User ID: 22d12551-3250-426f-919a-69a58a2d8707
AI 解决方案
🔍 错误翻译
原文：The `reasoning_content` in the thinking mode must be passed back to the API.
译文：思考模式中的 `reasoning_content` 必须回传给 API。
🎯 原因分析
该错误是在使用
deepseek-flash-guan 自定义模型时，API 要求客户端在请求中必须包含 reasoning_content 字段（通常用于思维链模式），但此字段缺失或未正确传递。💡 解决方案
请确保在请求中添加
reasoning_content 参数，或调整为该模型支持的模式：# 方案一：明确指定包含推理内容的请求结构
payload = {
"model": "deepseek-flash-guan",
"messages": [...],
# 添加思考模式所需字段
"enable_thinking": True,
"reasoning_content": "<你的推理内容占位符>"
}
# 方案二：若不需要思维链，切换为非思考模式（根据模型支持情况）
payload = {
"model": "deepseek-flash-guan",
"messages": [...],
"enable_thinking": False
}