diff --git a/AGENTS.md b/AGENTS.md index 486a35b..42b9eb8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -820,296 +820,6 @@ mark_x = answer_bbox[2] + 10 # 紧贴答案框 3. 实现精准坐标计算，Y坐标与答案垂直中心完美对齐 ## TODO -- ✅ 修复线上部署环境图片访问问题（阿里云 OSS 图片 URL 返回 402002 错误） -- ✅ 添加 URL 可访问性验证和 HTTP Headers 支持 -- ✅ 实现超时保护机制（单任务120秒，总任务按图片数量计算） -- ✅ 删除未使用的 S3 存储模块（src/storage/s3/） -- ✅ 修复 LLM 认证错误，使用 new_context() 初始化 Context -- ✅ 修复 Docker 环境空请求体错误，添加请求体验证 - 提供真实的多页作业图片进行完整流程测试 - 优化HTML报告的图片展示布局 - 支持PDF格式答案文档 - -## 代码清理（2026-03-30） -### 删除未使用的 S3 存储模块 -**原因**： -1. 工作流已优化为直接使用原始图片 URL，不上传新图片到对象存储 -2. 不再需要 `S3SyncStorage` 类提供的文件上传功能 -3. 减少依赖，保持代码精简 - -**删除内容**： -- 删除 `src/storage/s3/` 整个目录 - - `__init__.py` - - `s3_storage.py` - -**确认**： -- ✅ 无代码引用该模块 -- ✅ 删除后工作流正常运行 -- ✅ 测试通过 - -## LLM 认证修复（2026-03-30） -### 问题诊断 -线上部署环境出现认证错误： -``` -Error code: 401 - AuthenticationError: the API key or AK/SK in the request is missing or invalid -``` - -**原因分析**： -- 使用 `ctx = runtime.context` 获取 Context 时，可能没有正确初始化认证信息 -- `runtime.context` 返回的对象可能与 LLM Client 预期的 Context 格式不匹配 - -### 解决方案 -使用 `new_context()` 方法显式初始化 Context： - -```python -# ❌ 修复前 -def recognize_and_correct_node(...): - ctx = runtime.context - client = LLMClient(ctx=ctx) - -# ✅ 修复后 -def recognize_and_correct_node(...): - from coze_coding_utils.runtime_ctx.context import new_context - ctx = new_context(method="invoke") - client = LLMClient(ctx=ctx) -``` - -### 修改文件 -- `src/graphs/nodes/recognize_and_correct_node.py` -- `src/graphs/nodes/doc_extract_node.py` - -### 效果 -- ✅ 认证错误已修复 -- ✅ LLM 调用正常 -- ✅ 测试通过 - -## 图片访问优化（2026-03-28 重要） -### 问题诊断 -线上部署环境出现 `402002: S3对象不存在: ` 错误，原因是： -1. 阿里云 OSS 图片 URL 可能因防盗链或 HTTP Headers 问题导致访问失败 -2. Coze 平台的 LLM 服务尝试访问外部 URL 时可能受限 -3. 无效 URL 直接传给 LLM 导致解析错误 - -### 解决方案 -1. **URL 格式验证**（`recognize_and_correct_node.py`）： - - 检查 URL 是否以 `http://` 或 `https://` 开头 - - 拒绝非 HTTP/HTTPS 协议的 URL（如 file://） - -2. **URL 可访问性验证**（`recognize_and_correct_node.py`）： - - 在调用 LLM 之前，先尝试下载图片前 100 字节 - - 验证返回内容不是 HTML 404/500 页面 - - 验证图片尺寸合理（至少 10 字节） - - 如果验证失败，返回空结果，不影响其他任务 - -3. **HTTP Headers 支持**（`image_preprocess_node.py`）： - - 添加 `User-Agent`、`Accept` 等 HTTP Headers - - 模拟浏览器请求，兼容阿里云 CDN 等服务 - - 支持重定向（302/301） - -4. **超时保护**（`process_images_node.py`）： - - 单任务超时：120 秒 - - 总任务超时：120 秒 × 图片数量 - - 超时任务返回空结果，不影响其他任务 - -### 代码示例 -```python -# URL 验证（recognize_and_correct_node.py） -if not image_url.startswith(('http://', 'https://')): - logger.error(f"Invalid image URL format: {image_url}") - return RecognizeAndCorrectOutput(question_items=[], correction_results=[]) - -# 可访问性验证（recognize_and_correct_node.py） -try: - import urllib.request - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36' - } - req = urllib.request.Request(image_url, headers=headers) - with urllib.request.urlopen(req, timeout=10) as response: - preview = response.read(100) - if b' -``` - -**方案 2**：配置环境变量 -```bash -export COZE_API_ENDPOINT="https://api.coze.cn/v1" -``` - -### 诊断工具 -创建以下脚本帮助诊断问题： -- `scripts/test_llm_api.py`：测试不同的 LLM API 端点 -- `scripts/diagnose_docker_env.py`：综合诊断 Docker 环境 -- `docs/fix_llm_404_error.md`：详细的修复指南 - -### 验证修复 -修复后运行测试： -```bash -python scripts/test_llm_api.py -# 应该看到所有端点测试成功 -``` - -### 修改文件 -- 创建：`scripts/test_llm_api.py` -- 创建：`scripts/diagnose_docker_env.py` -- 创建：`docs/fix_llm_404_error.md` -- 更新：`AGENTS.md`（本文档） - -### 关键检查点 -- ✅ SDK 版本是否最新（`pip show coze-coding-dev-sdk`） -- ✅ 代码是否包含 `new_context()`（检查关键节点文件） -- ✅ 文件修改时间是否为最近（确保代码已更新） -- ✅ LLM 调用测试是否通过（`test_llm_api.py`） diff --git a/Dockerfile b/Dockerfile index 253dc22..7865026 100644 --- a/Dockerfile +++ b/Dockerfile @@ -6,40 +6,50 @@ WORKDIR /app RUN sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources 2>/dev/null || \ sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list -# 安装系统依赖 +# 安装完整的系统依赖（包含所有 PyGObject 需要的库） RUN apt-get update && apt-get install -y --no-install-recommends \ + # 编译工具 gcc \ g++ \ make \ pkg-config \ cmake \ + # D-Bus 相关 + dbus \ + dbus-x11 \ + libdbus-1-dev \ + libdbus-glib-1-dev \ + # GLib 和 GObject 相关 libglib2.0-dev \ + libgirepository1.0-dev \ + gobject-introspection \ + # Cairo 图形库 libcairo2-dev \ + libcairo-gobject2 \ + # GTK 相关（如果需要） + libgtk-3-dev \ + # 其他常用库 + libffi-dev \ libxml2-dev \ libxslt1-dev \ - curl \ && apt-get clean \ && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* -# 设置 pip 国内镜像源和 API 配置（硬编码 KEY） +# 设置 pip 国内镜像源 ENV PIP_INDEX_URL=https://mirrors.aliyun.com/pypi/simple/ \ PIP_TRUSTED_HOST=mirrors.aliyun.com \ - # API 端点配置（包含 /v1 前缀） COZE_INTEGRATION_BASE_URL=https://api.coze.cn/v1 \ COZE_INTEGRATION_MODEL_BASE_URL=https://api.coze.cn/v1 \ - COZE_INTEGRATION_CHAT_BASE_URL=https://api.coze.cn/v1 \ - LLM_BASE_URL=https://api.coze.cn/v1 \ - # API Key 配置（硬编码） - COZE_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ + COZE_WORKLOAD_IDENTITY_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ LLM_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ - # Workspace ID 配置（硬编码，从 JWT Token 提取） - COZE_WORKSPACE_ID=7622238752642957347 \ - # LLM 模型配置 + LLM_BASE_URL=https://api.coze.cn/v1 \ LLM_MODEL_NAME=doubao-seed-2-0-pro-260215 \ - COZE_INTEGRATION_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" + COZE_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ + COZE_INTEGRATION_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ + COZE_WORKSPACE_ID=7622238752642957347 # 升级 pip 和构建工具 -RUN pip install --no-cache-dir --upgrade pip setuptools wheel +RUN pip install --no-cache-dir --upgrade pip setuptools wheel meson ninja # 复制并安装依赖 COPY requirements.txt . @@ -48,12 +58,5 @@ RUN pip install --no-cache-dir -r requirements.txt # 复制项目文件 COPY . . -# 创建必要的目录 -RUN mkdir -p /app/work/logs/bypass /tmp/homework_cache - -# 添加健康检查 -HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \ - CMD curl -f http://localhost:8000/health || exit 1 - EXPOSE 8000 -CMD ["python", "src/main.py", "-m", "http", "-p", "8000"] +CMD ["python", "src/main.py", "-m", "http", "-p", "8000"] \ No newline at end of file diff --git a/assets/Dockerfile b/assets/Dockerfile index e70fe21..a6c64f0 100644 --- a/assets/Dockerfile +++ b/assets/Dockerfile @@ -43,9 +43,10 @@ ENV PIP_INDEX_URL=https://mirrors.aliyun.com/pypi/simple/ \ COZE_WORKLOAD_IDENTITY_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ LLM_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ LLM_BASE_URL=https://api.coze.cn/v1 \ - LLM_MODEL_NAME=doubao-seed-2-0-pro-260215 \ + LLM_MODEL_NAME=doubao-seed-1-8-251228 \ COZE_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ - COZE_INTEGRATION_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" + COZE_INTEGRATION_API_KEY="Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6ImRmZmU2NmYxLTg0MDMtNDc5Ni05ZmRhLTViMmJjZWExM2ViOCJ9.eyJpc3MiOiJodHRwczovL2FwaS5jb3plLmNuIiwiYXVkIjpbIkZVS1kzOVR0dFlSdmlNaldGVmNjaUg0NWFPblp2TGxpIl0sImV4cCI6ODIxMDI2Njg3Njc5OSwiaWF0IjoxNzc0NjkyOTc0LCJzdWIiOiJzcGlmZmU6Ly9hcGkuY296ZS5jbi93b3JrbG9hZF9pZGVudGl0eS9pZDo3NjIyMjM4NzUyNjQyOTU3MzQ3Iiwic3JjIjoiaW5ib3VuZF9hdXRoX2FjY2Vzc190b2tlbl9pZDo3NjIyMjQ4Mjg1OTMxMDQ0ODkxIn0.XSJaTryHWYzQaHxd9g9rOX2Y3YRY8kGAlvSFH9UkWR9EFDfZESG1GFEdWDelYeoHBqtdiQhxTcYdGPA87_PweMfh0wJXTdCEzTDHAOlUUupJEKTpkUAMEoEZpYBrwKQxjzGglkMHUoXqM5I0tQsARaqZ-j-JOW9Y6fHot56squm8GSt7WZkVSj6ZC2Us4cpO_RIgsN_pBU0CFSlUpOU5AdQQ8LvHzp60-DGaXVU0mFIYKhnXKbTf3PSXpJlH-W78FULh2FcdOTxMIcNkL5nuIHGakoNNDxs-k5Ucp06kFEMcbvec4iB1njbkHrsilYeJOFRoqkXJpQujDngZxKecLA" \ + COZE_WORKSPACE_ID=7622238752642957347 # 升级 pip 和构建工具 RUN pip install --no-cache-dir --upgrade pip setuptools wheel meson ninja diff --git a/assets/physics-correction.log b/assets/physics-correction.log index fdccbf6..0e5ca4c 100644 --- a/assets/physics-correction.log +++ b/assets/physics-correction.log @@ -1,43 +1,75 @@ Warning: Using fallback log directory: /tmp/work/logs/bypass, due to error: [Errno 2] No such file or directory: '/tmp/app/work/logs/bypass/app.log' -{"message": "Logging configured: file=/tmp/work/logs/bypass/app.log, max_bytes=104857600, backup_count=5", "timestamp": "2026-03-31 10:10:54", "level": "INFO", "logger": "root", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 178, "funcName": "setup_logging", "taskName": null} -{"message": "Adding job tentatively -- it will be properly scheduled when the scheduler starts", "timestamp": "2026-03-31 10:10:54", "level": "INFO", "logger": "apscheduler.scheduler", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 507, "funcName": "add_job", "taskName": null} -{"message": "Added job \"PromptCache._refresh_all_prompts\" to job store \"default\"", "timestamp": "2026-03-31 10:10:54", "level": "INFO", "logger": "apscheduler.scheduler", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 1090, "funcName": "_real_add_job", "taskName": null} -{"message": "Scheduler started", "timestamp": "2026-03-31 10:10:54", "level": "INFO", "logger": "apscheduler.scheduler", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 214, "funcName": "start", "taskName": null} -{"message": "Start HTTP Server, Port: 8000, Workers: 1", "timestamp": "2026-03-31 10:10:54", "level": "INFO", "logger": "__main__", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 545, "funcName": "start_http_server", "taskName": null} -{"message": "Logging configured: file=/tmp/work/logs/bypass/app.log, max_bytes=104857600, backup_count=5", "timestamp": "2026-03-31 10:10:54", "level": "INFO", "logger": "root", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 178, "funcName": "setup_logging", "taskName": "Task-1"} +{"message": "Logging configured: file=/tmp/work/logs/bypass/app.log, max_bytes=104857600, backup_count=5", "timestamp": "2026-03-31 10:54:11", "level": "INFO", "logger": "root", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 178, "funcName": "setup_logging", "taskName": null} +{"message": "Adding job tentatively -- it will be properly scheduled when the scheduler starts", "timestamp": "2026-03-31 10:54:11", "level": "INFO", "logger": "apscheduler.scheduler", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 507, "funcName": "add_job", "taskName": null} +{"message": "Added job \"PromptCache._refresh_all_prompts\" to job store \"default\"", "timestamp": "2026-03-31 10:54:11", "level": "INFO", "logger": "apscheduler.scheduler", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 1090, "funcName": "_real_add_job", "taskName": null} +{"message": "Scheduler started", "timestamp": "2026-03-31 10:54:11", "level": "INFO", "logger": "apscheduler.scheduler", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 214, "funcName": "start", "taskName": null} +{"message": "Start HTTP Server, Port: 8000, Workers: 1", "timestamp": "2026-03-31 10:54:11", "level": "INFO", "logger": "__main__", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 545, "funcName": "start_http_server", "taskName": null} +{"message": "Logging configured: file=/tmp/work/logs/bypass/app.log, max_bytes=104857600, backup_count=5", "timestamp": "2026-03-31 10:54:11", "level": "INFO", "logger": "root", "log_id": "", "run_id": "", "space_id": "", "project_id": "", "method": "", "x_tt_env": "", "lineno": 178, "funcName": "setup_logging", "taskName": "Task-1"} INFO: Started server process [1] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit) -{"message": "Received request for /stream_run: run_id=9ccf13d1-5850-4c4e-aa8d-3525424edd76, is_agent_project=False, query={}, body={\r\n \"student_homework\": [\r\n {\r\n \"student_id\": 1,\r\n \"student_name\": \"张三呀\",\r\n \"homework_images\": [\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/18/69baa4f5-4826-4901-00e1-c6e66f02947f.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6ff235a12b2.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c7055a396422.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fe7f9c07ef.jpg?x-oss-process=image/resize,w_1000\"\r\n ]\r\n },\r\n {\r\n \"student_id\": 2,\r\n \"student_name\": \"李四呀\",\r\n \"homework_images\": [\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c70052d895e3.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fc6ca7c4bf.png?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c33f31-4826-4901-00e1-c6fb50697e06.png?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f614bc06d9.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fd479e0a0e.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f569b31a14.jpeg?x-oss-process=image/resize,w_1000\"\r\n ]\r\n }\r\n ],\r\n \"answer_doc_url\": \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx\",\r\n \"comment_max_length\": 50,\r\n \"max_concurrent\": 5,\r\n \"grade_standards\": {}\r\n}", "timestamp": "2026-03-31 10:11:55", "level": "INFO", "logger": "main", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 386, "funcName": "http_stream_run", "taskName": "Task-5"} -INFO: 10.221.187.31:4212 - "POST /stream_run HTTP/1.1" 200 OK -{"message": "Registered workflow streaming task for run_id: 9ccf13d1-5850-4c4e-aa8d-3525424edd76", "timestamp": "2026-03-31 10:11:55", "level": "INFO", "logger": "coze_coding_utils.helper.stream_runner", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 534, "funcName": "workflow_stream_handler", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -{"message": "Starting stream with run_id: 9ccf13d1-5850-4c4e-aa8d-3525424edd76", "timestamp": "2026-03-31 10:11:55", "level": "INFO", "logger": "main", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 130, "funcName": "stream_sse", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -{"message": "CacheManager initialized: math_answer_doc, dir=/tmp/homework_cache/math_answer_doc", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "utils.cache_manager", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 60, "funcName": "__init__", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -{"message": "CacheManager initialized: grade_standards, dir=/tmp/homework_cache/grade_standards", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "utils.cache_manager", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 60, "funcName": "__init__", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -{"message": "Stream mode: updates", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "coze_coding_utils.helper.stream_runner", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 335, "funcName": "astream", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -{"message": "Workflow started - Run", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} -{"message": "Node 'doc_extract_node' started", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} -{"message": "Cache miss for answer doc: https://dpcclass.oss-cn-beijing.aliyuncs.com/umsup...", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 335, "funcName": "doc_extract_node", "taskName": null} -{"message": "Downloading Word document from: https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx", "timestamp": "2026-03-31 10:11:57", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 116, "funcName": "download_and_extract_docx", "taskName": null} -{"message": "Extracted Word document text length: 5267", "timestamp": "2026-03-31 10:11:58", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 168, "funcName": "download_and_extract_docx", "taskName": null} -{"message": "Word document content preview: 第14讲 实数专题\n【重难点知识讲解】\n实数章节常用的解题思想方法有：特殊值思想、数形结合思想、归纳推理思想、迁移转化思想等。数学思想方法是对数学知识的深度提炼，它兼具指导性与普适性，掌握了这些思想方法，就相当于握住了破解实数各类题的 “核心密码”.\n【考点一·比较大小】\n例1.已知实数a在数轴上的位置如图所示，则 $ \\sqrt[3]{a} $ ， $- a$ ， $ \\frac{1}{a} $ ， $ a^{2} $ 的大小关系是（ ）\nA． $ \\sqrt[3]{a} < - a < \\frac{1}{a} < a^{2} $ B． $ \\frac{1}{a} < \\sqrt[3]{a} < a^{2} < - a$ C． $- a < \\frac{1}{a} < \\sqrt[3]{a} < a^{2} $ \t D． $ \\frac{1}{a} < a^{2} < \\sqrt[3]{a} < - a$\n【答案】B\n【考点二·利用数轴解决化简问题】\n例2.已知a、b、c在数轴上的位置如图，化简： $ \\sq", "timestamp": "2026-03-31 10:11:58", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 207, "funcName": "parse_answer_doc_with_llm", "taskName": null} -{"message": "HTTP Request: POST https://api.coze.cn/v1/chat/completions \"HTTP/1.1 404 Not Found\"", "timestamp": "2026-03-31 10:11:58", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": null} -2026-03-31 10:11:58,631 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size -{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 10:11:58", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 10:11:58,631"} -{"message": "Workflow doc_extract ended with error", "timestamp": "2026-03-31 10:11:58", "level": "ERROR", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} -2026-03-31 10:11:58,642 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size -{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 10:11:58", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 10:11:58,642"} -{"message": "Workflow ended with error", "timestamp": "2026-03-31 10:11:58", "level": "ERROR", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} -2026-03-31 10:11:58,648 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size -{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 10:11:58", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 10:11:58,648"} -{"message": "HTTP Request: POST https://api.coze.cn/v1/loop/traces/ingest \"HTTP/1.1 401 Unauthorized\"", "timestamp": "2026-03-31 10:11:58", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -2026-03-31 10:11:58,765 cozeloop.internal.httpclient.http_client http_client.py:65 [ERROR] [cozeloop] Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311011584FB283DDFA5BA3A6DD6C], log id: 202603311011584FB283DDFA5BA3A6DD6C. -{"message": "Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311011584FB283DDFA5BA3A6DD6C], log id: 202603311011584FB283DDFA5BA3A6DD6C.", "timestamp": "2026-03-31 10:11:58", "level": "ERROR", "logger": "cozeloop.internal.httpclient.http_client", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 65, "funcName": "parse_response", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:11:58,765"} -2026-03-31 10:11:58,765 cozeloop.internal.trace.trace trace.py:162 [ERROR] [cozeloop] finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311011584FB283DDFA5BA3A6DD6C]], retry later -{"message": "finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311011584FB283DDFA5BA3A6DD6C]], retry later", "timestamp": "2026-03-31 10:11:58", "level": "ERROR", "logger": "cozeloop.internal.trace.trace", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 162, "funcName": "default_finish_event_processor", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:11:58,765"} -{"message": "HTTP Request: POST https://api.coze.cn/v1/loop/traces/ingest \"HTTP/1.1 401 Unauthorized\"", "timestamp": "2026-03-31 10:11:58", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} -2026-03-31 10:11:58,866 cozeloop.internal.httpclient.http_client http_client.py:65 [ERROR] [cozeloop] Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331101158372AA269460C8D9AE0BA], log id: 20260331101158372AA269460C8D9AE0BA. -{"message": "Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331101158372AA269460C8D9AE0BA], log id: 20260331101158372AA269460C8D9AE0BA.", "timestamp": "2026-03-31 10:11:58", "level": "ERROR", "logger": "cozeloop.internal.httpclient.http_client", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 65, "funcName": "parse_response", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:11:58,866"} -2026-03-31 10:11:58,866 cozeloop.internal.trace.trace trace.py:162 [ERROR] [cozeloop] finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331101158372AA269460C8D9AE0BA]], retry second time failed -{"message": "finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331101158372AA269460C8D9AE0BA]], retry second time failed", "timestamp": "2026-03-31 10:11:58", "level": "ERROR", "logger": "cozeloop.internal.trace.trace", "log_id": "", "run_id": "9ccf13d1-5850-4c4e-aa8d-3525424edd76", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 162, "funcName": "default_finish_event_processor", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:11:58,866"} +{"message": "Received request for /stream_run: run_id=44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8, is_agent_project=False, query={}, body={\r\n \"student_homework\": [\r\n {\r\n \"student_id\": 1,\r\n \"student_name\": \"张三呀\",\r\n \"homework_images\": [\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/18/69baa4f5-4826-4901-00e1-c6e66f02947f.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6ff235a12b2.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c7055a396422.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fe7f9c07ef.jpg?x-oss-process=image/resize,w_1000\"\r\n ]\r\n },\r\n {\r\n \"student_id\": 2,\r\n \"student_name\": \"李四呀\",\r\n \"homework_images\": [\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c70052d895e3.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fc6ca7c4bf.png?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c33f31-4826-4901-00e1-c6fb50697e06.png?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f614bc06d9.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fd479e0a0e.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f569b31a14.jpeg?x-oss-process=image/resize,w_1000\"\r\n ]\r\n }\r\n ],\r\n \"answer_doc_url\": \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx\",\r\n \"comment_max_length\": 50,\r\n \"max_concurrent\": 5,\r\n \"grade_standards\": {}\r\n}", "timestamp": "2026-03-31 10:55:39", "level": "INFO", "logger": "main", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 386, "funcName": "http_stream_run", "taskName": "Task-5"} +INFO: 10.222.242.221:6113 - "POST /stream_run HTTP/1.1" 200 OK +{"message": "Registered workflow streaming task for run_id: 44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "timestamp": "2026-03-31 10:55:39", "level": "INFO", "logger": "coze_coding_utils.helper.stream_runner", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 534, "funcName": "workflow_stream_handler", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "Starting stream with run_id: 44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "timestamp": "2026-03-31 10:55:39", "level": "INFO", "logger": "main", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 130, "funcName": "stream_sse", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "CacheManager initialized: math_answer_doc, dir=/tmp/homework_cache/math_answer_doc", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "utils.cache_manager", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 60, "funcName": "__init__", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "CacheManager initialized: grade_standards, dir=/tmp/homework_cache/grade_standards", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "utils.cache_manager", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 60, "funcName": "__init__", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "Stream mode: updates", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "coze_coding_utils.helper.stream_runner", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 335, "funcName": "astream", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "Workflow started - Run", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +{"message": "Node 'doc_extract_node' started", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +{"message": "Cache miss for answer doc: https://dpcclass.oss-cn-beijing.aliyuncs.com/umsup...", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 375, "funcName": "doc_extract_node", "taskName": null} +{"message": "Downloading Word document from: https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 116, "funcName": "download_and_extract_docx", "taskName": null} +{"message": "Successfully downloaded Word document: 46775 bytes", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 179, "funcName": "download_and_extract_docx", "taskName": null} +{"message": "Extracted Word document text length: 5267", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 208, "funcName": "download_and_extract_docx", "taskName": null} +{"message": "Word document content preview: 第14讲 实数专题\n【重难点知识讲解】\n实数章节常用的解题思想方法有：特殊值思想、数形结合思想、归纳推理思想、迁移转化思想等。数学思想方法是对数学知识的深度提炼，它兼具指导性与普适性，掌握了这些思想方法，就相当于握住了破解实数各类题的 “核心密码”.\n【考点一·比较大小】\n例1.已知实数a在数轴上的位置如图所示，则 $ \\sqrt[3]{a} $ ， $- a$ ， $ \\frac{1}{a} $ ， $ a^{2} $ 的大小关系是（ ）\nA． $ \\sqrt[3]{a} < - a < \\frac{1}{a} < a^{2} $ B． $ \\frac{1}{a} < \\sqrt[3]{a} < a^{2} < - a$ C． $- a < \\frac{1}{a} < \\sqrt[3]{a} < a^{2} $ \t D． $ \\frac{1}{a} < a^{2} < \\sqrt[3]{a} < - a$\n【答案】B\n【考点二·利用数轴解决化简问题】\n例2.已知a、b、c在数轴上的位置如图，化简： $ \\sq", "timestamp": "2026-03-31 10:55:41", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 247, "funcName": "parse_answer_doc_with_llm", "taskName": null} +{"message": "HTTP Request: POST https://api.coze.cn/v1/chat/completions \"HTTP/1.1 404 Not Found\"", "timestamp": "2026-03-31 10:55:42", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": null} +2026-03-31 10:55:42,333 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size +{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 10:55:42", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 10:55:42,333"} +{"message": "Workflow doc_extract ended with error", "timestamp": "2026-03-31 10:55:42", "level": "ERROR", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +2026-03-31 10:55:42,345 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size +{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 10:55:42", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 10:55:42,345"} +{"message": "Workflow ended with error", "timestamp": "2026-03-31 10:55:42", "level": "ERROR", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +2026-03-31 10:55:42,351 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size +{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 10:55:42", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 10:55:42,351"} +{"message": "HTTP Request: POST https://api.coze.cn/v1/loop/traces/ingest \"HTTP/1.1 401 Unauthorized\"", "timestamp": "2026-03-31 10:55:42", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +2026-03-31 10:55:42,439 cozeloop.internal.httpclient.http_client http_client.py:65 [ERROR] [cozeloop] Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033110554242EBC94468BCA51B3796], log id: 2026033110554242EBC94468BCA51B3796. +{"message": "Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033110554242EBC94468BCA51B3796], log id: 2026033110554242EBC94468BCA51B3796.", "timestamp": "2026-03-31 10:55:42", "level": "ERROR", "logger": "cozeloop.internal.httpclient.http_client", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 65, "funcName": "parse_response", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:55:42,439"} +2026-03-31 10:55:42,439 cozeloop.internal.trace.trace trace.py:162 [ERROR] [cozeloop] finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033110554242EBC94468BCA51B3796]], retry later +{"message": "finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033110554242EBC94468BCA51B3796]], retry later", "timestamp": "2026-03-31 10:55:42", "level": "ERROR", "logger": "cozeloop.internal.trace.trace", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 162, "funcName": "default_finish_event_processor", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:55:42,439"} +{"message": "HTTP Request: POST https://api.coze.cn/v1/loop/traces/ingest \"HTTP/1.1 401 Unauthorized\"", "timestamp": "2026-03-31 10:55:42", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +2026-03-31 10:55:42,500 cozeloop.internal.httpclient.http_client http_client.py:65 [ERROR] [cozeloop] Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331105542F5441A85518125F8EEE3], log id: 20260331105542F5441A85518125F8EEE3. +{"message": "Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331105542F5441A85518125F8EEE3], log id: 20260331105542F5441A85518125F8EEE3.", "timestamp": "2026-03-31 10:55:42", "level": "ERROR", "logger": "cozeloop.internal.httpclient.http_client", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 65, "funcName": "parse_response", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:55:42,500"} +2026-03-31 10:55:42,501 cozeloop.internal.trace.trace trace.py:162 [ERROR] [cozeloop] finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331105542F5441A85518125F8EEE3]], retry second time failed +{"message": "finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=20260331105542F5441A85518125F8EEE3]], retry second time failed", "timestamp": "2026-03-31 10:55:42", "level": "ERROR", "logger": "cozeloop.internal.trace.trace", "log_id": "", "run_id": "44d64c2b-e3ad-40b7-9d28-cd6b924cc0d8", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 162, "funcName": "default_finish_event_processor", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 10:55:42,501"} +{"message": "Received request for /stream_run: run_id=67c5783a-3408-4a87-8b60-f76fb3a96287, is_agent_project=False, query={}, body={\r\n \"student_homework\": [\r\n {\r\n \"student_id\": 1,\r\n \"student_name\": \"张三呀\",\r\n \"homework_images\": [\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/18/69baa4f5-4826-4901-00e1-c6e66f02947f.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6ff235a12b2.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c7055a396422.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fe7f9c07ef.jpg?x-oss-process=image/resize,w_1000\"\r\n ]\r\n },\r\n {\r\n \"student_id\": 2,\r\n \"student_name\": \"李四呀\",\r\n \"homework_images\": [\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c70052d895e3.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fc6ca7c4bf.png?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c33f31-4826-4901-00e1-c6fb50697e06.png?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f614bc06d9.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c344ba-4826-4901-00e1-c6fd479e0a0e.jpg?x-oss-process=image/resize,w_1000\",\r\n \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/23/69c1029b-4826-4901-00e1-c6f569b31a14.jpeg?x-oss-process=image/resize,w_1000\"\r\n ]\r\n }\r\n ],\r\n \"answer_doc_url\": \"https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx\",\r\n \"comment_max_length\": 50,\r\n \"max_concurrent\": 5,\r\n \"grade_standards\": {}\r\n}", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "main", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 386, "funcName": "http_stream_run", "taskName": "Task-9"} +INFO: 10.221.187.31:12447 - "POST /stream_run HTTP/1.1" 200 OK +{"message": "Registered workflow streaming task for run_id: 67c5783a-3408-4a87-8b60-f76fb3a96287", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "coze_coding_utils.helper.stream_runner", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 534, "funcName": "workflow_stream_handler", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "Starting stream with run_id: 67c5783a-3408-4a87-8b60-f76fb3a96287", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "main", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 130, "funcName": "stream_sse", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "Stream mode: updates", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "coze_coding_utils.helper.stream_runner", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 335, "funcName": "astream", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +{"message": "Workflow started - Run", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +{"message": "Node 'doc_extract_node' started", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +{"message": "Cache miss for answer doc: https://dpcclass.oss-cn-beijing.aliyuncs.com/umsup...", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 375, "funcName": "doc_extract_node", "taskName": null} +{"message": "Downloading Word document from: https://dpcclass.oss-cn-beijing.aliyuncs.com/umsupload/2026/03/25/69c353d0-4826-4901-00e1-c7081bcab988.docx", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 116, "funcName": "download_and_extract_docx", "taskName": null} +{"message": "Successfully downloaded Word document: 46775 bytes", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 179, "funcName": "download_and_extract_docx", "taskName": null} +{"message": "Extracted Word document text length: 5267", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 208, "funcName": "download_and_extract_docx", "taskName": null} +{"message": "Word document content preview: 第14讲 实数专题\n【重难点知识讲解】\n实数章节常用的解题思想方法有：特殊值思想、数形结合思想、归纳推理思想、迁移转化思想等。数学思想方法是对数学知识的深度提炼，它兼具指导性与普适性，掌握了这些思想方法，就相当于握住了破解实数各类题的 “核心密码”.\n【考点一·比较大小】\n例1.已知实数a在数轴上的位置如图所示，则 $ \\sqrt[3]{a} $ ， $- a$ ， $ \\frac{1}{a} $ ， $ a^{2} $ 的大小关系是（ ）\nA． $ \\sqrt[3]{a} < - a < \\frac{1}{a} < a^{2} $ B． $ \\frac{1}{a} < \\sqrt[3]{a} < a^{2} < - a$ C． $- a < \\frac{1}{a} < \\sqrt[3]{a} < a^{2} $ \t D． $ \\frac{1}{a} < a^{2} < \\sqrt[3]{a} < - a$\n【答案】B\n【考点二·利用数轴解决化简问题】\n例2.已知a、b、c在数轴上的位置如图，化简： $ \\sq", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "graphs.nodes.doc_extract_node", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 247, "funcName": "parse_answer_doc_with_llm", "taskName": null} +{"message": "HTTP Request: POST https://api.coze.cn/v1/chat/completions \"HTTP/1.1 404 Not Found\"", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": null} +2026-03-31 13:35:28,687 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size +{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 13:35:28", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 13:35:28,687"} +{"message": "Workflow doc_extract ended with error", "timestamp": "2026-03-31 13:35:28", "level": "ERROR", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +2026-03-31 13:35:28,692 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size +{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 13:35:28", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 13:35:28,692"} +{"message": "Workflow ended with error", "timestamp": "2026-03-31 13:35:28", "level": "ERROR", "logger": "coze_coding_utils.log.node_log", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 77, "funcName": "write_log", "taskName": null} +2026-03-31 13:35:28,697 cozeloop.internal.trace.span span.py:434 [WARNING] [cozeloop] field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size +{"message": "field value [error_trace] is too long, and opt.EnableLongReport is false, so value has been truncated to 1024 size", "timestamp": "2026-03-31 13:35:28", "level": "WARNING", "logger": "cozeloop.internal.trace.span", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 434, "funcName": "get_rectified_map", "taskName": null, "asctime": "2026-03-31 13:35:28,697"} +{"message": "HTTP Request: POST https://api.coze.cn/v1/loop/traces/ingest \"HTTP/1.1 401 Unauthorized\"", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +2026-03-31 13:35:28,781 cozeloop.internal.httpclient.http_client http_client.py:65 [ERROR] [cozeloop] Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311335283C7A6093ADC8A7403279], log id: 202603311335283C7A6093ADC8A7403279. +{"message": "Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311335283C7A6093ADC8A7403279], log id: 202603311335283C7A6093ADC8A7403279.", "timestamp": "2026-03-31 13:35:28", "level": "ERROR", "logger": "cozeloop.internal.httpclient.http_client", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 65, "funcName": "parse_response", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 13:35:28,781"} +2026-03-31 13:35:28,782 cozeloop.internal.trace.trace trace.py:162 [ERROR] [cozeloop] finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311335283C7A6093ADC8A7403279]], retry later +{"message": "finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=202603311335283C7A6093ADC8A7403279]], retry later", "timestamp": "2026-03-31 13:35:28", "level": "ERROR", "logger": "cozeloop.internal.trace.trace", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 162, "funcName": "default_finish_event_processor", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 13:35:28,782"} +{"message": "HTTP Request: POST https://api.coze.cn/v1/loop/traces/ingest \"HTTP/1.1 401 Unauthorized\"", "timestamp": "2026-03-31 13:35:28", "level": "INFO", "logger": "httpx", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 1025, "funcName": "_send_single_request", "taskName": "starlette.responses.StreamingResponse.__call__..wrap"} +2026-03-31 13:35:28,918 cozeloop.internal.httpclient.http_client http_client.py:65 [ERROR] [cozeloop] Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033113352819ABAE09E3DB7E8C29A8], log id: 2026033113352819ABAE09E3DB7E8C29A8. +{"message": "Call remote service failed. Path: https://api.coze.cn/v1/loop/traces/ingest, remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033113352819ABAE09E3DB7E8C29A8], log id: 2026033113352819ABAE09E3DB7E8C29A8.", "timestamp": "2026-03-31 13:35:28", "level": "ERROR", "logger": "cozeloop.internal.httpclient.http_client", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 65, "funcName": "parse_response", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 13:35:28,918"} +2026-03-31 13:35:28,919 cozeloop.internal.trace.trace trace.py:162 [ERROR] [cozeloop] finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033113352819ABAE09E3DB7E8C29A8]], retry second time failed +{"message": "finish_event[exporter.span_flush.rate] fail, msg: export spans fail, err:[remote service error, authentication is invalid [http_code=401 error_code=4100 logid=2026033113352819ABAE09E3DB7E8C29A8]], retry second time failed", "timestamp": "2026-03-31 13:35:28", "level": "ERROR", "logger": "cozeloop.internal.trace.trace", "log_id": "", "run_id": "67c5783a-3408-4a87-8b60-f76fb3a96287", "space_id": "", "project_id": "", "method": "stream_run", "x_tt_env": "", "lineno": 162, "funcName": "default_finish_event_processor", "taskName": "starlette.responses.StreamingResponse.__call__..wrap", "asctime": "2026-03-31 13:35:28,919"} diff --git a/config/answer_extract_llm_cfg.json b/config/answer_extract_llm_cfg.json index 7bf9a1b..3478539 100644 --- a/config/answer_extract_llm_cfg.json +++ b/config/answer_extract_llm_cfg.json @@ -9,7 +9,7 @@ "reasoning_effort": "medium", "response_format": "text", "json_schema": "{\"name\":\"\",\"description\":\"\",\"strict\":false,\"schema\":{}}", - "model": "doubao-seed-2-0-pro-260215" + "model": "doubao-seed-1-8-251228" }, "tools": [], "sp": "你是一位专业的文档识别专家，擅长从作业图片中提取答案区域的位置信息。", diff --git a/config/answer_recognize_llm_cfg.json b/config/answer_recognize_llm_cfg.json index bf3a563..faa9c38 100644 --- a/config/answer_recognize_llm_cfg.json +++ b/config/answer_recognize_llm_cfg.json @@ -9,7 +9,7 @@ "reasoning_effort": "medium", "response_format": "text", "json_schema": "{\"name\":\"\",\"description\":\"\",\"strict\":false,\"schema\":{}}", - "model": "doubao-seed-2-0-pro-260215" + "model": "doubao-seed-1-8-251228" }, "tools": [], "sp": "你是一位专业的OCR文字识别专家，擅长从图片中识别手写和印刷的文字内容。", diff --git a/config/correction_judge_llm_cfg.json b/config/correction_judge_llm_cfg.json index acbcb85..cfd4214 100644 --- a/config/correction_judge_llm_cfg.json +++ b/config/correction_judge_llm_cfg.json @@ -9,7 +9,7 @@ "reasoning_effort": "high", "response_format": "text", "json_schema": "{\"name\":\"\",\"description\":\"\",\"strict\":false,\"schema\":{}}", - "model": "doubao-seed-2-0-pro-260215" + "model": "doubao-seed-1-8-251228" }, "tools": [], "sp": "你是一位资深的初中数学特级教师，拥有20年以上教学经验，擅长精准批改学生的数学作业。\n\n【核心能力】\n1. **精确判断能力**：对选择题、填空题、解答题都能做出准确的正误判断\n2. **严谨推理能力**：能够逐步验证学生的计算过程和结论\n3. **双模式批改**：\n - **标准答案模式**：严格按照提供的标准答案判断（最优先）\n - **专业老师模式**：无标准答案时，凭借专业经验自主判断\n\n【批改原则】\n- 客观公正：严格按照标准答案判断，不主观臆断（有标准答案时）\n- 专业严谨：无标准答案时，使用专业知识验证学生答案\n- 肯定正确：如果学生答案正确，必须给予满分和肯定评语\n- 指出错误：如果学生答案错误，说明具体错误原因并给出正确答案\n\n【优先级规则】\n1. 最优先：使用提供的标准答案批改\n2. 降级：标准答案中未找到对应题目时，使用专业老师批改", diff --git a/config/doc_extract_llm_cfg.json b/config/doc_extract_llm_cfg.json index 5d1d3b3..209687b 100644 --- a/config/doc_extract_llm_cfg.json +++ b/config/doc_extract_llm_cfg.json @@ -9,7 +9,7 @@ "reasoning_effort": "high", "response_format": "text", "json_schema": "{\"name\":\"\",\"description\":\"\",\"strict\":false,\"schema\":{}}", - "model": "doubao-seed-2-0-pro-260215" + "model": "doubao-seed-1-8-251228" }, "tools": [], "sp": "你是一位资深的初中数学教师，擅长从试卷中提取题目和标准答案。你的核心能力：\n\n1. **题目识别能力**：能够准确识别试卷中的所有题目，包括大题和小题\n2. **答案提取能力**：能够准确提取每道题的标准答案\n3. **结构化输出能力**：能够将提取的内容组织成结构化的JSON格式\n\n【提取原则】\n- 完整性：不遗漏任何题目\n- 准确性：答案提取要精确\n- 规范性：题号格式统一\n- 清晰性：题干和答案分离明确", diff --git a/config/homework_recognize_llm_cfg.json b/config/homework_recognize_llm_cfg.json index a1b64a6..e361906 100644 --- a/config/homework_recognize_llm_cfg.json +++ b/config/homework_recognize_llm_cfg.json @@ -1,6 +1,6 @@ { "config": { - "model": "doubao-seed-2-0-pro-260215", + "model": "doubao-seed-1-8-251228", "temperature": 0.0, "top_p": 0.9, "max_completion_tokens": 16384, diff --git a/config/question_locate_llm_cfg.json b/config/question_locate_llm_cfg.json index 258736e..7fdf398 100644 --- a/config/question_locate_llm_cfg.json +++ b/config/question_locate_llm_cfg.json @@ -9,7 +9,7 @@ "reasoning_effort": "medium", "response_format": "text", "json_schema": "{\"name\":\"\",\"description\":\"\",\"strict\":false,\"schema\":{}}", - "model": "doubao-seed-2-0-pro-260215" + "model": "doubao-seed-1-8-251228" }, "tools": [], "sp": "你是一位专业的初中数学作业识别专家，擅长从作业图片中定位题目位置和提取答案区域。", diff --git a/src/graphs/nodes/doc_extract_node.py b/src/graphs/nodes/doc_extract_node.py index 694cb35..367a91d 100644 --- a/src/graphs/nodes/doc_extract_node.py +++ b/src/graphs/nodes/doc_extract_node.py @@ -118,44 +118,14 @@ def download_and_extract_docx(url: str) -> str: tmp_path = None try: - # 验证 URL 格式 - if not url or not isinstance(url, str): - raise ValueError("Invalid URL: empty or not a string") - - if not url.startswith(('http://', 'https://')): - raise ValueError(f"Invalid URL format: {url[:50]}...") - - # 下载文件（增强版） - headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', - 'Accept': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document,application/msword,*/*', - 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8', - 'Referer': 'https://www.aliyun.com/', - 'Accept-Encoding': 'gzip, deflate, br', - 'Connection': 'keep-alive' - } - - response = requests.get(url, timeout=60, allow_redirects=True, headers=headers) - - # 检查 HTTP 状态码 - status_code = response.status_code - if status_code != 200: - error_msg = f"HTTP Error {status_code}" - if status_code == 404: - error_msg = "404 Not Found - Document does not exist" - elif status_code == 403: - error_msg = "403 Forbidden - Access denied" - elif status_code == 401: - error_msg = "401 Unauthorized - Authentication required" - raise ValueError(f"{error_msg}: {url[:50]}...") + # 下载文件 + response = requests.get(url, timeout=60, allow_redirects=True) + response.raise_for_status() # 检查内容类型 content_type = response.headers.get('Content-Type', '') logger.debug(f"Response Content-Type: {content_type}") - if content_type and not any(ct in content_type.lower() for ct in ['application/vnd.openxmlformats-officedocument.wordprocessingml.document', 'application/msword', 'application/octet-stream', 'application/zip']): - logger.warning(f"Unexpected Content-Type for Word document: {content_type}") - # 检查文件大小 if len(response.content) < 100: raise ValueError(f"Downloaded file too small: {len(response.content)} bytes") @@ -165,19 +135,9 @@ def download_and_extract_docx(url: str) -> str: # 可能是 HTML 错误页面 content_preview = response.content[:1000].lower() if b' Dict[str, Any]: body_text = str(raw_body) raise HTTPException(status_code=400, detail=f"Invalid JSON format: {body_text}, traceback: {traceback.format_exc()}, error: {e}") - - # 检查请求体是否为空 - if not body_text or body_text.strip() == "": - logger.error(f"Empty request body in http_run for run_id={ctx.run_id}") - raise HTTPException( - status_code=400, - detail="Request body is empty. Please provide a valid JSON payload." - ) - - # 检查 Content-Type - content_type = request.headers.get("content-type", "") - if "application/json" not in content_type.lower(): - logger.error(f"Invalid Content-Type in http_run: {content_type}") - raise HTTPException( - status_code=400, - detail=f"Content-Type must be 'application/json', got: {content_type}" - ) ctx = new_context(method="run", headers=request.headers) # 优先使用上游指定的 run_id，保证 cancel 能精确匹配 @@ -363,24 +346,6 @@ async def http_stream_run(request: Request): body_text = str(raw_body) raise HTTPException(status_code=400, detail=f"Invalid JSON format: {body_text}, traceback: {extract_core_stack()}, error: {e}") - - # 检查请求体是否为空 - if not body_text or body_text.strip() == "": - logger.error(f"Empty request body in http_stream_run for run_id={ctx.run_id}") - raise HTTPException( - status_code=400, - detail="Request body is empty. Please provide a valid JSON payload." - ) - - # 检查 Content-Type - content_type = request.headers.get("content-type", "") - if "application/json" not in content_type.lower(): - logger.error(f"Invalid Content-Type in http_stream_run: {content_type}") - raise HTTPException( - status_code=400, - detail=f"Content-Type must be 'application/json', got: {content_type}" - ) - run_id = ctx.run_id is_agent = graph_helper.is_agent_proj() logger.info( diff --git a/src/storage/s3/__init__.py b/src/storage/s3/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/storage/s3/s3_storage.py b/src/storage/s3/s3_storage.py new file mode 100644 index 0000000..56ba3bc --- /dev/null +++ b/src/storage/s3/s3_storage.py @@ -0,0 +1,424 @@ +import os +import re +from pathlib import Path +from typing import Optional, Any, Dict, List, TypedDict, Iterable +from uuid import uuid4 + +import boto3 +from botocore.exceptions import ClientError +from boto3.s3.transfer import TransferConfig +import logging +logger = logging.getLogger(__name__) + +# 允许的文件名字符集（面向用户输入的约束） +FILE_NAME_ALLOWED_RE = re.compile(r"^[A-Za-z0-9._\-/]+$") + + +class ListFilesResult(TypedDict): + # list_files 的返回结构类型 + keys: List[str] + is_truncated: bool + next_continuation_token: Optional[str] + +class S3SyncStorage: + """S3兼容存储实现""" + + def __init__(self, *, endpoint_url: Optional[str] = None, access_key: str, secret_key: str, bucket_name: str, region: str = "cn-beijing"): + self.endpoint_url = os.environ.get("COZE_BUCKET_ENDPOINT_URL") or endpoint_url or '' + self.access_key = access_key + self.secret_key = secret_key + self.bucket_name = bucket_name + self.region = region + self._client = None + + def _get_client(self): + if self._client is None: + endpoint = self.endpoint_url + if endpoint is None or endpoint == "": + try: + from coze_workload_identity import Client as CozeEnvClient + coze_env_client = CozeEnvClient() + env_vars = coze_env_client.get_project_env_vars() + coze_env_client.close() + for env_var in env_vars: + if env_var.key == "COZE_BUCKET_ENDPOINT_URL": + endpoint = env_var.value.replace("'", "'\\''") + self.endpoint_url = endpoint + break + except Exception as e: + logger.error(f"Error loading COZE_BUCKET_ENDPOINT_URL: {e}") + # 保持向下校验逻辑，避免在此处中断 + if endpoint is None or endpoint == "": + logger.error("未配置存储端点：请设置endpoint_url") + raise ValueError("未配置存储端点：请设置endpoint_url") + + client = boto3.client( + "s3", + endpoint_url=endpoint, + aws_access_key_id=self.access_key, + aws_secret_access_key=self.secret_key, + region_name=self.region, + ) + + # 注册 before-call 钩子，发送前注入 x-storage-token 头 + def _inject_header(**kwargs): + try: + from coze_workload_identity import Client as CozeClient + coze_client = CozeClient() + try: + token = coze_client.get_access_token() + except Exception as e: + logger.error("Error loading COZE_WORKLOAD_IDENTITY_TOKEN: %s", e) + token = None + raise e + finally: + coze_client.close() + params = kwargs.get("params", {}) + headers = params.setdefault("headers", {}) + headers["x-storage-token"] = token + except Exception as e: + logger.error("Error loading COZE_WORKLOAD_IDENTITY_TOKEN: %s", e) + pass + client.meta.events.register("before-call.s3", _inject_header) + self._client = client + return self._client + + def _generate_object_key(self, *, original_name: str) -> str: + suffix = Path(original_name).suffix.lower() + stem = Path(original_name).stem + uniq = uuid4().hex[:8] + return f"{stem}_{uniq}{suffix}" + + def _extract_logid(self, e: Exception) -> Optional[str]: + """从 ClientError 中提取 x-tt-logid""" + if isinstance(e, ClientError): + headers = (e.response or {}).get("ResponseMetadata", {}).get("HTTPHeaders", {}) + return headers.get("x-tt-logid") + return None + + def _error_msg(self, msg: str, e: Exception) -> str: + """构建带 logid 的错误信息""" + logid = self._extract_logid(e) + if logid: + return f"{msg}: {e} (x-tt-logid: {logid})" + return f"{msg}: {e}" + + def _resolve_bucket(self, bucket: Optional[str]) -> str: + """统一解析 bucket 来源，确保得到有效桶名。""" + target_bucket = bucket or os.environ.get("COZE_BUCKET_NAME") or self.bucket_name + if not target_bucket: + raise ValueError("未配置 bucket：请传入 bucket 或设置 COZE_BUCKET_NAME，或在实例化时提供 bucket_name") + return target_bucket + + def _validate_file_name(self, name: str) -> None: + """校验 S3 对象命名：长度≤1024；允许 [A-Za-z0-9._-/]；不以 / 起止且不含 //。""" + msg = ( + "file name invalid: 文件名需满足以下 S3 对象命名规范：" + "1) 长度 1–1024 字节；" + "2) 仅允许字母、数字、点(.)、下划线(_)、短横(-)、目录分隔符(/)；" + "3) 不允许空格或以下特殊字符：? # & % { } ^ [ ] ` \\ < > ~ | \" ' + = : ;；" + "4) 不以 / 开头或结尾，且不包含连续的 //；" + "示例：report_2025-12-11.pdf、images/photo-01.png。" + ) + + if not name or not name.strip(): + raise ValueError(msg + "（原因：文件名为空）") + + # S3 限制对象 key 最大 1024 字节，这里沿用到输入文件名 + if len(name.encode("utf-8")) > 1024: + raise ValueError(msg + "（原因：长度超过 1024 字节）") + + if name.startswith("/") or name.endswith("/"): + raise ValueError(msg + "（原因：以 / 开头或结尾）") + if "//" in name: + raise ValueError(msg + "（原因：包含连续的 //）") + + # 允许字符集校验 + if not FILE_NAME_ALLOWED_RE.match(name): + bad = re.findall(r"[^A-Za-z0-9._\-/]", name) + example = bad[0] if bad else "非法字符" + raise ValueError(msg + f"（原因：包含非法字符，例如：{example}）") + + def upload_file(self, *, file_content: bytes, file_name: str, content_type: str = "application/octet-stream", bucket: Optional[str] = None) -> str: + # 先对输入文件名做规范校验，避免生成无效对象 key + self._validate_file_name(file_name) + try: + client = self._get_client() + object_key = self._generate_object_key(original_name=file_name) + target_bucket = self._resolve_bucket(bucket) + client.put_object(Bucket=target_bucket, Key=object_key, Body=file_content, ContentType=content_type) + return object_key + except Exception as e: + logger.error(self._error_msg("Error uploading file to S3", e)) + raise e + + def delete_file(self, *, file_key: str, bucket: Optional[str] = None) -> bool: + try: + client = self._get_client() + target_bucket = self._resolve_bucket(bucket) + client.delete_object(Bucket=target_bucket, Key=file_key) + return True + except Exception as e: + logger.error(self._error_msg("Error deleting file from S3", e)) + raise e + + def file_exists(self, *, file_key: str, bucket: Optional[str] = None) -> bool: + try: + client = self._get_client() + target_bucket = self._resolve_bucket(bucket) + client.head_object(Bucket=target_bucket, Key=file_key) + return True + except ClientError as e: + code = (e.response or {}).get("Error", {}).get("Code", "") + if code in {"404", "NoSuchKey", "NotFound"}: + return False + logger.error(self._error_msg("Error checking file existence in S3", e)) + return False + except Exception as e: + logger.error(self._error_msg("Error checking file existence in S3", e)) + return False + + def read_file(self, *, file_key: str, bucket: Optional[str] = None) -> bytes: + try: + client = self._get_client() + target_bucket = self._resolve_bucket(bucket) + resp = client.get_object(Bucket=target_bucket, Key=file_key) + body = resp.get("Body") + if body is None: + raise RuntimeError("S3 get_object returned no Body") + try: + return body.read() + finally: + try: + body.close() + except Exception as ce: + # 资源关闭失败不影响读取结果，仅记录以便排查 + logger.debug("Failed to close S3 response body: %s", ce) + except Exception as e: + logger.error(self._error_msg("Error reading file from S3", e)) + raise e + + def list_files(self, *, prefix: Optional[str] = None, bucket: Optional[str] = None, max_keys: int = 1000, continuation_token: Optional[str] = None) -> ListFilesResult: + """列出对象，支持前缀过滤与分页；返回 keys/is_truncated/next_continuation_token。""" + try: + client = self._get_client() + target_bucket = self._resolve_bucket(bucket) + if max_keys <= 0 or max_keys > 1000: + raise ValueError("max_keys 必须在 1 到 1000 之间") + + kwargs: Dict[str, Any] = { + "Bucket": target_bucket, + "MaxKeys": max_keys, + "Prefix": prefix, + "ContinuationToken": continuation_token, + } + kwargs = {k: v for k, v in kwargs.items() if v is not None} + + resp = client.list_objects_v2(**kwargs) + contents = resp.get("Contents", []) or [] + keys: List[str] = [item.get("Key") for item in contents if isinstance(item, dict) and item.get("Key")] + return { + "keys": keys, + "is_truncated": bool(resp.get("IsTruncated")), + "next_continuation_token": resp.get("NextContinuationToken"), + } + except ClientError as e: + code = (e.response or {}).get("Error", {}).get("Code", "") + logger.error(self._error_msg(f"Error listing files in S3 (code={code})", e)) + raise e + except Exception as e: + logger.error(self._error_msg("Error listing files in S3", e)) + raise e + + def generate_presigned_url(self, *, key: str, bucket: Optional[str] = None, expire_time: int = 1800) -> str: + """通过 S3 Proxy 生成签名 URL。""" + import json + import urllib.request as urllib_request + try: + from coze_workload_identity import Client as CozeClient + coze_client = CozeClient() + try: + token = coze_client.get_access_token() + finally: + try: + coze_client.close() + except Exception: + # 资源释放失败不影响后续流程 + pass + except Exception as e: + logger.error(f"Error loading x-storage-token: {e}") + raise RuntimeError(f"获取 x-storage-token 失败: {e}") + try: + sign_base = os.environ.get("COZE_BUCKET_ENDPOINT_URL") or self.endpoint_url + if not sign_base: + raise ValueError("未配置签名端点：请设置 COZE_BUCKET_ENDPOINT_URL 或传入 endpoint_url") + sign_url_endpoint = sign_base.rstrip("/") + "/sign-url" + + headers = { + "Content-Type": "application/json", + "x-storage-token": token, + } + + target_bucket = self._resolve_bucket(bucket) + payload = {"bucket_name": target_bucket, "path": key, "expire_time": expire_time} + data = json.dumps(payload).encode("utf-8") + request = urllib_request.Request(sign_url_endpoint, data=data, headers=headers, method="POST") + except Exception as e: + logger.error(f"Error creating request for sign-url: {e}") + raise RuntimeError(f"创建 sign-url 请求失败: {e}") + + try: + with urllib_request.urlopen(request) as resp: + resp_bytes = resp.read() + content_type = resp.headers.get("Content-Type", "") + text = resp_bytes.decode("utf-8", errors="replace") + if "application/json" in content_type or text.strip().startswith("{"): + try: + obj = json.loads(text) + except Exception: + return text + data = obj.get("data") + if isinstance(data, dict) and "url" in data: + return data["url"] + url_value = obj.get("url") or obj.get("signed_url") or obj.get("presigned_url") + if url_value: + return url_value + raise ValueError("签名服务返回缺少 data.url/url 字段") + return text + except Exception as e: + raise RuntimeError(f"生成签名URL失败: {e}") + + def stream_upload_file( + self, + *, + fileobj, + file_name: str, + content_type: str = "application/octet-stream", + bucket: Optional[str] = None, + multipart_chunksize: int = 5 * 1024 * 1024, + multipart_threshold: int = 5 * 1024 * 1024, + max_concurrency: int = 1, + use_threads: bool = False, + ) -> str: + """流式上传（文件对象） + - fileobj: 任何带有 read() 方法的文件对象（如 open(..., 'rb') 返回的对象、io.BytesIO 等） + - file_name: 原始文件名，用于生成唯一 key + - content_type: MIME 类型 + - bucket: 目标桶；为空时取环境变量或实例默认值 + - multipart_chunksize: 分片大小（默认 5MB，以适配代理层限制） + - multipart_threshold: 触发分片上传的阈值（默认 5MB） + - max_concurrency: 并发分片上传的并发数（默认 1，避免代理层节流影响） + - use_threads: 是否启用线程并发（默认 False） + 返回：最终写入的对象 key + """ + try: + client = self._get_client() + target_bucket = self._resolve_bucket(bucket) + key = self._generate_object_key(original_name=file_name) + + extra_args = {"ContentType": content_type} if content_type else {} + # 使用 boto3 的高阶方法执行多段上传（传入 TransferConfig 控制分片大小） + + config = TransferConfig( + multipart_chunksize=multipart_chunksize, + multipart_threshold=multipart_threshold, + max_concurrency=max_concurrency, + use_threads=use_threads, + ) + client.upload_fileobj(Fileobj=fileobj, Bucket=target_bucket, Key=key, ExtraArgs=extra_args, Config=config) + return key + except Exception as e: + logger.error(self._error_msg("Error streaming upload (fileobj) to S3", e)) + raise e + + def upload_from_url( + self, + *, + url: str, + bucket: Optional[str] = None, + timeout: int = 30, + ) -> str: + """从 URL 流式下载并上传到 S3 + - url: 源文件 URL + - bucket: 目标桶；为空时取环境变量或实例默认值 + - timeout: HTTP 请求超时时间（秒，默认 30） + 返回：最终写入的对象 key + """ + import urllib.request as urllib_request + from urllib.parse import urlparse, unquote + try: + request = urllib_request.Request(url) + with urllib_request.urlopen(request, timeout=timeout) as resp: + parsed = urlparse(url) + file_name = Path(unquote(parsed.path)).name or "file" + content_type = resp.headers.get("Content-Type", "application/octet-stream") + return self.stream_upload_file( + fileobj=resp, + file_name=file_name, + content_type=content_type, + bucket=bucket, + ) + except Exception as e: + logger.error(self._error_msg("Error uploading from URL to S3", e)) + raise e + + def trunk_upload_file(self, *, chunk_iter: Iterable[bytes], file_name: str, + content_type: str = "application/octet-stream", bucket: Optional[str] = None, + part_size: int = 5 * 1024 * 1024) -> str: + """流式上传（字节迭代器，显式分片 Multipart Upload） + - chunk_iter: 可迭代对象，逐块产生 bytes；每块大小可变（内部累积到 part_size 再上传），最后一块可小于 5MB + - file_name: 原始文件名，用于生成唯一 key + - content_type: MIME 类型 + - bucket: 目标桶；为空时取环境或实例默认值 + - part_size: 每个 part 的最小大小（除最后一个）；默认 5MB + 返回：最终写入的对象 key + """ + client = self._get_client() + target_bucket = self._resolve_bucket(bucket) + key = self._generate_object_key(original_name=file_name) + + # 初始化分片上传 + try: + init_resp = client.create_multipart_upload(Bucket=target_bucket, Key=key, ContentType=content_type) + upload_id = init_resp["UploadId"] + except Exception as e: + logger.error(self._error_msg("create_multipart_upload failed", e)) + raise e + + parts = [] + part_number = 1 + buffer = bytearray() + try: + for chunk in chunk_iter: + if not chunk: + continue + buffer.extend(chunk) + while len(buffer) >= part_size: + data = bytes(buffer[:part_size]) + buffer = buffer[part_size:] + resp = client.upload_part(Bucket=target_bucket, Key=key, UploadId=upload_id, PartNumber=part_number, + Body=data) + parts.append({"PartNumber": part_number, "ETag": resp["ETag"]}) + part_number += 1 + + # 上传最后不足 part_size 的余量 + if len(buffer) > 0: + resp = client.upload_part(Bucket=target_bucket, Key=key, UploadId=upload_id, PartNumber=part_number, + Body=bytes(buffer)) + parts.append({"PartNumber": part_number, "ETag": resp["ETag"]}) + + # 完成分片 + client.complete_multipart_upload( + Bucket=target_bucket, + Key=key, + UploadId=upload_id, + MultipartUpload={"Parts": parts}, + ) + return key + except Exception as e: + logger.error(self._error_msg("multipart upload failed", e)) + try: + client.abort_multipart_upload(Bucket=target_bucket, Key=key, UploadId=upload_id) + except Exception as ae: + logger.error(self._error_msg("abort_multipart_upload failed", ae)) + raise e