错误信息: 所有令牌分组 default 下对于模型 gemini-3-pro-preview 均无可用渠道,请更换分组尝试 (request id: 2026...

2026年04月01日 09:46 processing

错误信息

错误名称: AI_APICallError 错误信息: 所有令牌分组 default 下对于模型 gemini-3-pro-preview 均无可用渠道,请更换分组尝试 (request id: 20260401094532580573280AGmpZCe3) 堆栈信息: AI_APICallError: 所有令牌分组 default 下对于模型 gemini-3-pro-preview 均无可用渠道,请更换分组尝试 (request id: 20260401094532580573280AGmpZCe3) at file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/dist-CUjkTMRK.js:2082:11 at async postToApi (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/dist-CUjkTMRK.js:1977:24) at async OpenAICompatibleChatLanguageModel.doStream (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/dist-DYjHuC4A.js:451:48) at async wrapStream (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:55023:32) at async fn (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:53889:17) at async file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:50243:19 at async _retryWithExponentialBackoff (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:50406:10) at async streamStep (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:53858:109) at async fn (file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:54164:5) at async file:///C:/Program%20Files/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-CsnpwSxn.js:50243:19 错误原因: "[undefined]" 状态码: 503 请求路径: https://www.dmxapi.cn/v1/chat/completions 请求体: { "model": "gemini-3-pro-preview", "user": "[undefined]", "max_tokens": "[undefined]", "temperature": "[undefined]", "top_p": "[undefined]", "frequency_penalty": "[undefined]", "presence_penalty": "[undefined]", "response_format": "[undefined]", "stop": "[undefined]", "seed": "[undefined]", "serviceTier": "[undefined]", "reasoning_effort": "[undefined]", "verbosity": "[undefined]", "messages": [ { "role": "user", "content": "Gluten hydrolysates lower starch digestibility via protein network and amylase binding.这句字数超了,压缩到85字符内" }, { "role": "user", "content": "Gluten hydrolysates lower starch digestibility via protein network and amylase binding.这句字数超了,压缩到85字符内" }, { "role": "user", "content": "Gluten hydrolysates lower starch digestibility via protein network and amylase binding.这句字数超了,压缩到85字符内" }, { "role": "assistant", "content": "Here are precise options under **85 characters** (including spaces):\n\n1. Original compression: \n**\"Gluten hydrolysates lower starch digestibility via protein network & amylase binding.\"** \n*(82 characters)*\n\n2. Further streamlined: \n**\"Gluten hydrolysates reduce starch digestion via inhibitory network & binding.\"** \n*(74 characters - uses \"digestion\" & broadens mechanisms)*\n\n3. Alternate focus: \n**\"Gluten hydrolysates inhibit starch digestibility through amylase binding/network.\"** \n*(80 characters - emphasizes inhibition)*\n\n### Key edits:\n- Replaced ***\"lower\"*** → ***\"reduce\"*** (saves space)\n- Changed ***\"digestibility\"*** → ***\"digestion\"*** (shorter)\n- Simplified ***\"protein network and amylase binding\"*** → ***\"inhibitory network & binding\"*** or ***\"amylase binding/network\"***\n\nAll versions retain the core mechanisms while staying within 85 characters. Use option **1 (82 chars)** for maximal accuracy.", "reasoning_content": "Hmm, the user keeps repeating the same request about compressing a scientific sentence. They've sent identical queries four times - looks like either a technical glitch or they're really anxious to get this right. \n\nOkay, focusing on the task: \"Gluten hydrolysates lower starch digestibility via protein network and amylase binding\" needs to be under 85 characters. The original is already quite tight at 103 characters with spaces. \n\nFirst stab would be cutting \"via\" to slash 3 chars instantly. \"Network\" could become \"net\" but loses precision... Wait, the core mechanisms are protein structures and enzyme binding. Maybe \"inhibitory network\" covers both? \n\n*counts on fingers* \"Hydrolysates reduce starch digest. via inhibitory network/binding\" - oh that fits! But the slash might confuse. Alternatively \"through protein binding effects\" is vague but saves space. \n\nUser is probably a researcher on tight abstract limits. They'd value accuracy over brevity. The third version keeps \"amylase\" explicitly - crucial for biochem readers. 84 characters with \"amylase binding\" preserved feels like the winner. \n\n*double-checks count* Yep, \"Gluten hydrolysates lower starch digestibility through amylase inhibition/network\" leaves out \"protein\" but implies it via context. Compromise achieved.\n", "tool_calls": "[undefined]" }, { "role": "user", "content": "在吗?" } ], "tools": "[undefined]", "tool_choice": "[undefined]", "stream": true, "stream_options": { "include_usage": true } } 响应首部: { "content-length": "209", "content-type": "application/json; charset=utf-8", "date": "Wed, 01 Apr 2026 01:45:32 GMT", "document-policy": "include-js-call-stacks-in-crash-reports", "server": "nginx", "x-rixapi-request-id": "20260401094532580573280AGmpZCe3" } 响应内容: { "error": { "code": "", "message": "所有令牌分组 default 下对于模型 gemini-3-pro-preview 均无可用渠道,请更换分组尝试 (request id: 20260401094532580573280AGmpZCe3)", "type": "rix_api_error" } } 数据: { "error": { "message": "所有令牌分组 default 下对于模型 gemini-3-pro-preview 均无可用渠道,请更换分组尝试 (request id: 20260401094532580573280AGmpZCe3)", "type": "rix_api_error", "code": "" } }

AI 解决方案

报错分析报告

1.错误翻译


原文:所有令牌分组 default 下对于模型 gemini-3-pro-preview 均无可用渠道,请更换分组尝试
译文:在默认令牌分组下,模型 gemini-3-pro-preview 没有任何可用的访问渠道,请尝试更换分组。

2. 原因分析


  • 根本原因:默认令牌分组(default)未配置模型gemini-3-pro-preview的可用访问渠道。

  • 发生位置:调用gemini-3-pro-preview模型的API时(堆栈中OpenAICompatibleChatLanguageModel.doStream方法),触发渠道可用性校验失败。
  • 3. 解决方案


    修改配置以使用有该模型可用渠道的分组(需替换为实际存在的分组名,如custom-group):
    // 修复后的配置示例(以JavaScript为例)
    const apiConfig = {
      group: "custom-group", // 替换default为有gemini-3-pro-preview权限的分组
      model: "gemini-3-pro-preview",
      // 其他参数保持不变
    };
    

    或直接通过请求参数指定分组(若API支持):
    # 示例:curl请求中添加分组参数
    curl -X POST https://www.dmxapi.cn/v1/chat/completions \
      -H "Content-Type: application/json" \
      -d '{"group":"custom-group","model":"gemini-3-pro-preview",...}'
    

    4. 预防措施


  • 最佳实践1:调用前通过DMXAPI的「模型列表接口」校验目标模型在当前分组的可用性(避免硬编码分组)。

  • 最佳实践2:配置文件中使用环境变量管理分组名称(如DMX_GROUP=custom-group),便于快速切换。

  • 推荐工具:使用Postman或Apifox的「环境管理」功能,预存不同分组的配置模板;或通过DMXAPI控制台的「分组详情页」查看可用模型。