错误信息: error_during_execution: Process failed after 0 turns 堆栈信息: AI_ProviderSpec...

2026年04月28日 11:55 processing

错误信息

错误名称: AI_ProviderSpecificError 错误信息: error_during_execution: Process failed after 0 turns 堆栈信息: AI_ProviderSpecificError: error_during_execution: Process failed after 0 turns at AiSdkToChunkAdapter.convertAndEmitChunk (file:///C:/Users/ZhangEnfan/AppData/Local/Programs/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-DmY8nbl4.js:349460:64) at AiSdkToChunkAdapter.readFullStream (file:///C:/Users/ZhangEnfan/AppData/Local/Programs/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-DmY8nbl4.js:349251:10) at async AiSdkToChunkAdapter.processStream (file:///C:/Users/ZhangEnfan/AppData/Local/Programs/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-DmY8nbl4.js:349213:31) at async fetchAndProcessAgentResponseImpl (file:///C:/Users/ZhangEnfan/AppData/Local/Programs/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-DmY8nbl4.js:168067:3) at async file:///C:/Users/ZhangEnfan/AppData/Local/Programs/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-DmY8nbl4.js:168254:5 at async file:///C:/Users/ZhangEnfan/AppData/Local/Programs/Cherry%20Studio/resources/app.asar/out/renderer/assets/store-DmY8nbl4.js:143162:21 错误原因: { "message": "error_during_execution: Process failed after 0 turns" }

AI 解决方案

##报错分析

1. 错误翻译

原文：error_during_execution: Process failed after 0 turns
译文：执行过程中出错：进程在0轮后失败

2.原因分析

根本原因：AI提供商的执行进程未进入有效交互轮次（0轮）即终止，导致流处理链路中断。

具体位置：Cherry Studio的AiSdkToChunkAdapter流转换链（convertAndEmitChunk→readFullStream→processStream），上下文为异步获取代理响应时的流读取失败。

3.解决方案

// 修复思路：添加重试机制+错误捕获（适配原异步流场景）
async function safeFetchAIResponse(url, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    try {
      const res = await fetch(url);
      if (!res.ok) throw new Error(`HTTP ${res.status}`);
      
      // 模拟原AiSdkToChunkAdapter的流处理（替换为实际逻辑）
      const reader = res.body.getReader();
      while (true) {
        const { done, value } = await reader.read();
        if (done) break;
        // 此处插入原convertAndEmitChunk的chunk处理逻辑
      }
      return; // 成功则退出
    } catch (err) {
      if (i === maxRetries - 1) throw err; // 最后一次重试失败抛出
      await new Promise(resolve => setTimeout(resolve, 1000 * 2 ** i)); // 指数退避
    }
  }
}

// 调用处替换原fetchAndProcessAgentResponseImpl的异步逻辑
try {
  await safeFetchAIResponse('your-ai-provider-endpoint');
} catch (finalErr) {
  console.error('AI响应最终失败:', finalErr);
}

4. 预防措施

最佳实践1：为AI调用添加超时控制（如AbortController设置10s超时）+指数退避重试（最多3次），应对瞬时故障。

最佳实践2：集成提供商健康检查（如定时ping状态端点），调用前验证服务可用性。

推荐工具：用axios（内置超时/重试配置）或p-retry（简化重试逻辑）替代原生fetch。

分析新问题查看更多