Merge branch 'main' into feat/opt_benefit_1

# Conflicts:
#	.gitignore
#	backend/infra/platestwrite/latest_write_tracker.go

Author: xueyizheng

.github/PULL_REQUEST_TEMPLATE.md

@@ -15,30 +15,27 @@ test: Adding missing tests or correcting existing tests
 chore: Changes to the build process or auxiliary tools and libraries such as documentation generation
 -->
 
-#### Check the PR title.
+#### Check the PR title
 <!--
 The description of the title will be attached in Release Notes,
 so please describe it from user-oriented, what this PR does / why we need it.
 Please check your PR title with the below requirements:
 -->
-- [ ] This PR title match the format: \[\<type\>\]\[\<scope\>\]: \<description\>. For example: \[fix\]\[backend\] flaky fix
+- [ ] This PR title match the format: \[\<type\>\]\[\<scope\>\] \<description\>. For example: \[fix\]\[backend\] flaky fix
 - [ ] The description of this PR title is user-oriented and clear enough for others to understand.
 - [ ] Add documentation if the current PR requires user awareness at the usage level.
 - [ ] This PR is written in English. PRs not in English will not be reviewed.
 
+#### (Optional) Translate the PR title into Chinese
 
-#### (Optional) Translate the PR title into Chinese.
-
-
-#### (Optional) More detailed description for this PR(en: English/zh: Chinese).
+#### (Optional) More detailed description for this PR(en: English/zh: Chinese)
 <!--
 Provide more detailed info for review(e.g., it's recommended to provide perf data if this is a perf type PR).
 -->
 en:
 zh(optional):
 
-
-#### (Optional) Which issue(s) this PR fixes:
+#### (Optional) Which issue(s) this PR fixes
 <!--
 Automatically closes linked issue when PR is merged.
 Eg: `Fixes #<issue number>`, or `Fixes (paste link of issue)`.

.github/workflows/ai-cr-required.yaml

@@ -28,7 +28,7 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           echo "PR number: $PR_NUMBER"
-          COMMENTS=$(gh api -H "Accept: application/vnd.github+json" /repos/${{ github.repository }}/pulls/${PR_NUMBER}/comments --jq '.[].user.login')
+          COMMENTS=$(gh api -H "Accept: application/vnd.github+json" /repos/${{ github.repository }}/pulls/${PR_NUMBER}/reviews --jq '.[].user.login')
           echo "Comment authors: $COMMENTS"
           echo "$COMMENTS" | grep -q "^CozeLoop$"
           if [ $? -ne 0 ]; then

.gitignore

@@ -51,6 +51,11 @@ release/deployment/helm-chart/umbrella/Chart.lock
 
 **/kitex_remote_config.json
 .coda/
+.claude/
+.coco/
+CLAUDE.md
+AGENTS.md
 backend/script/errorx/.env
 .cursor/
-AGENTS.md
+.specify/
+specs/

.vscode/settings.json

@@ -169,13 +169,13 @@
   "[svg]": {
     "editor.defaultFormatter": "jock.svg"
   },
-  "svg.preview.background": "white",
   "[xml]": {
     "editor.defaultFormatter": "mblode.pretty-formatter"
   },
   "[sql]": {
     "editor.defaultFormatter": "adpyke.vscode-sql-formatter"
   },
+  "svg.preview.background": "white",
   "git.openRepositoryInParentFolders": "always",
   "references.preferredLocation": "view"
 }

CODE_OF_CONDUCT.md

@@ -69,10 +69,9 @@ members of the project's leadership.
 ## Attribution
 
 This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+available at <https://www.contributor-covenant.org/version/1/4/code-of-conduct.html>
 
 [homepage]: https://www.contributor-covenant.org
 
 For answers to common questions about this code of conduct, see
-https://www.contributor-covenant.org/faq
-
+<https://www.contributor-covenant.org/faq>

CONTRIBUTING.md

@@ -28,6 +28,7 @@ You could go to [README](./README.md) to find more information.
 <summary>Detailed Submission Process (Click to expand)</summary>
 
 1. Create a feature branch from the `main` branch:
+
    ```bash
    git checkout main
    git pull
@@ -37,18 +38,21 @@ You could go to [README](./README.md) to find more information.
 2. Develop and commit on the feature branch
 
 3. Ensure the code passes all tests:
+
    ```bash
-   cd ./backend && go test -gcflags="all=-N -l" ./... 
+   cd ./backend && go test -gcflags="all=-N -l" ./...
    ```
 
 4. Push the branch to the remote repository:
+
    ```bash
    git push origin feat/your-feature-name
    ```
 
 5. Create a Pull Request to the `main` branch
 
 6. After code review is passed, merge into the `main` branch
+
 </details>
 
 ```mermaid
@@ -79,6 +83,7 @@ Follow the [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/
 ```
 
 Types include:
+
 * `feat`: New feature
 * `fix`: Bug fix
 * `docs`: Documentation changes
@@ -89,6 +94,7 @@ Types include:
 * `chore`: Changes to the build process or auxiliary tools
 
 Example:
+
 ```
 feat(api): add user authentication interface
 
@@ -133,6 +139,7 @@ Closes #123
 * It is better to Use mockgen to generate mock struct instead of using patch
 
 Run unit tests:
+
 ```bash
 cd ./backend && go test  -gcflags="all=-N -l" ./...
 ```
@@ -146,6 +153,7 @@ cd ./backend && go test  -gcflags="all=-N -l" ./...
 * Use [GoDoc](https://blog.golang.org/godoc) format for writing comments
 
 Example:
+
 ```go
 // UserService provides operations related to users.
 type UserService struct {

README.cn.md

@@ -10,45 +10,54 @@
 <p>
   <img alt="License" src="https://img.shields.io/badge/license-apache2.0-blue.svg">
   <img alt="Go Version" src="https://img.shields.io/badge/go-%3E%3D%201.24.0-blue">
+  <a href="https://deepwiki.com/coze-dev/coze-loop"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 </p>
 
 [English](README.md) | 中文
 
 </div>
 
 ## 什么是 Coze Loop
-[Coze Loop ](https://www.coze.cn/loop) 是一个面向开发者，专注于 AI Agent 开发与运维的平台级解决方案。 它可以解决 AI Agent 开发过程中面临的各种挑战，提供从开发、调试、评估、到监控的全生命周期管理能力。
+
+[Coze Loop](https://www.coze.cn/loop) 是一个面向开发者，专注于 AI Agent 开发与运维的平台级解决方案。 它可以解决 AI Agent 开发过程中面临的各种挑战，提供从开发、调试、评估、到监控的全生命周期管理能力。
 Coze Loop 在商业化版本的基础上，推出开源版免费对开发者开放核心基础功能模块，以开源模式共享核心技术框架，开发者可根据业务需求定制与扩展，便于社区共建、分享交流，助力开发者零门槛参与 AI Agent 的探索与实践。
+
 ## Coze Loop 能做什么？
+
 Coze Loop 通过提供全生命周期的管理能力，帮助开发者更高效地开发和运维 AI Agent。无论是提示词工程、AI Agent 评测，还是上线后的监控与调优，Coze Loop 都提供了强大的工具和智能化的支持，极大地简化了 AI Agent 的开发流程，提升了 AI Agent 的运行效果和稳定性。
 
 * **Prompt 开发**：Coze Loop 的 Prompt 开发模块为开发者提供了从编写、调试、优化到版本管理的全流程支持，通过可视化 Playground 实现 Prompt 的实时交互测试，让开发者能够直观比较不同大语言模型的输出效果。
 * **评测**：Coze Loop 评测模块为开发者提供系统化的评测能力，能够对 Prompt 和扣子智能体的输出效果进行多维度自动化检测，例如准确性、简洁性和合规性等。
 * **观测**：Coze Loop 为开发者提供了全链路执行过程的可视化观测能力，完整记录从用户输入到 AI 输出的每个处理环节，包括 Prompt 解析、模型调用和工具执行等关键节点，并自动捕获中间结果和异常状态。
 
 ## 功能清单
+
 | **功能** | **功能点** |
 | --- | --- |
-| Prompt 调试 | * Playground 调试、对比 <br> * Prompt 版本管理 |
-| 评测 | * 管理评测集 <br> * 管理评估器 <br> * 管理实验 |
-| 观测 | * SDK 上报 Trace <br> * Trace 数据观测 |
+| Prompt 调试 | *Playground 调试、对比 <br>* Prompt 版本管理 |
+| 评测 | *管理评测集 <br>* 管理评估器 <br> * 管理实验 |
+| 观测 | *SDK 上报 Trace <br>* Trace 数据观测 |
 | 模型 | 支持接入 OpenAI、火山方舟等模型 |
+
 ## 快速开始
+>
 > 参考[快速开始](https://github.com/coze-dev/coze-loop/wiki/2.-%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B)，详细了解如何安装部署 Coze Loop 最新版本。
 
 ### 部署方式1：Docker 部署 (Docker Compose)
+>
 > 请提前安装并启动 Docker Engine。
 
 操作步骤：
 
 1. 获取源码。
    执行以下命令，获取 Coze Loop 最新版本的源码。
+
    ```Bash
    # 克隆代码
    git clone https://github.com/coze-dev/coze-loop.git
-   
+
    # 进入coze-loop目录下
-   cd coze-loop 
+   cd coze-loop
    ```
 
 2. 配置模型。
@@ -59,10 +68,11 @@ Coze Loop 通过提供全生命周期的管理能力，帮助开发者更高效
       * model：火山方舟模型接入点的 Endpoint ID。中国境内用户参考参考[火山方舟文档](https://www.volcengine.com/docs/82379/1099522)；非中国境内的用户可参考[BytePlus ModelArk 文档](https://docs.byteplus.com/en/docs/ModelArk/1099522?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source)。
 3. 启动服务。
    执行以下命令，使用 Docker Compose 快速部署 Coze Loop 开源版。
+
    ```Bash
-   # 启动服务，默认为开发模式 
+   # 启动服务，默认为开发模式
    # 在 coze-loop/目录下执行
-   make compose-up 
+   make compose-up
    ```
 
 4. 通过浏览器访问 Coze Loop 开源版 `http://localhost:8082`。
@@ -75,6 +85,7 @@ Coze Loop 通过提供全生命周期的管理能力，帮助开发者更高效
 操作步骤：
 
 1. 执行以下命令获取 Helm Chart 包。
+
    ```Bash
    helm pull oci://docker.io/cozedev/coze-loop --version 1.0.0-helm
    tar -zxvf coze-loop-1.0.0-helm.tgz && cd coze-loop && rm -f ../coze-loop-1.0.0-helm.tgz
@@ -88,6 +99,7 @@ Coze Loop 通过提供全生命周期的管理能力，帮助开发者更高效
    Ingress 用于暴露服务到外部，需根据集群实际情况配置项目目录下的`templates/ingress.yaml` 文件，自行修改 ingressClassName 等参数，配置 class、instance、host、ip 分配等要素。
 4. 部署并启动服务。
    执行以下命令，使用 Helm 快速部署 Coze Loop 开源版。
+
    ```Bash
    # 在 coze-loop/目录下执行
    make helm-up
@@ -119,21 +131,31 @@ Coze Loop 通过提供全生命周期的管理能力，帮助开发者更高效
 * [故障排查](https://github.com/coze-dev/coze-loop/wiki/7.-%E6%95%85%E9%9A%9C%E6%8E%92%E6%9F%A5)：了解如何查看容器状态、系统日志。
 
 ## License
+
 本项目采用 Apache 2.0 许可证。详情请参阅 [LICENSE](LICENSE) 文件。
+
 ## 社区贡献
+
 我们欢迎社区贡献，贡献指南参见 [CONTRIBUTING](CONTRIBUTING.md) 和 [Code of conduct](CODE_OF_CONDUCT.md)，期待您的贡献！
+
 ## 安全与隐私
+
 如果你在该项目中发现潜在的安全问题，或你认为可能发现了安全问题，请通过我们的[安全中心](https://security.bytedance.com/src) 或[漏洞报告邮箱](sec@bytedance.com)通知字节跳动安全团队。
 请**不要**创建公开的 GitHub Issue。
+
 ## 加入社区
+
 我们致力于构建一个开放、友好的开发者社区，欢迎所有对 AI Agent 开发感兴趣的开发者加入我们！
+
 ### 问题反馈与功能建议
+
 为了更高效地跟踪和解决问题，保证信息透明和便于协同，我们推荐通过以下方式参与：
 
 * **GitHub Issues**：[提交 Bug 报告或功能请求](https://github.com/coze-dev/coze-loop/issues)
 * **Pull Requests**：[贡献代码或文档改进](https://github.com/coze-dev/coze-loop/pulls)
 
 ### 技术交流与讨论
+
 加入我们的技术交流群，与其他开发者分享经验、获取项目最新动态：
 
 * 飞书群聊：飞书移动端扫描以下二维码，加入Coze Loop 技术交流群。
@@ -144,6 +166,7 @@ Coze Loop 通过提供全生命周期的管理能力，帮助开发者更高效
 * Telegram 群组：[Coze](https://t.me/+pP9CkPnomDA0Mjgx)
 
 ## 致谢
+
 感谢所有为 Coze Loop 项目做出贡献的开发者和社区成员。特别感谢：
 
 * [Eino](https://github.com/cloudwego/eino) 框架团队提供的 LLM 集成支持

README.md

@@ -9,6 +9,7 @@
 <p>
   <img alt="License" src="https://img.shields.io/badge/license-apache2.0-blue.svg">
   <img alt="Go Version" src="https://img.shields.io/badge/go-%3E%3D%201.24.0-blue">
+  <a href="https://deepwiki.com/coze-dev/coze-loop"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 </p>
 
 English | [中文](README.cn.md)
@@ -22,35 +23,41 @@ English | [中文](README.cn.md)
 Based on the commercial version, Coze Loop introduces an open-source edition that offers developers free access to core foundational feature modules. By sharing its core technology framework in an open-source model, developers can customize and extend according to business needs, facilitating community co-construction, sharing, and exchange, helping developers participate in AI agent exploration and practice with zero barriers.
 
 ## What can Coze Loop do?
+
 Coze Loop helps developers develop and operate AI Agent more efficiently by providing full lifecycle management capabilities. Whether it is prompt engineering, AI Agent evaluation, or monitoring and optimization after deployment, Coze Loop provides powerful tools and intelligent support, greatly simplifying the development process of AI Agents and enhancing their operational performance and stability.
 
 * **Prompt development**: The Prompt development module of Coze Loop provides developers with end-to-end support for writing, debugging, optimizing, and version management. Through a visual Playground, it enables real-time interactive testing of prompts, allowing developers to intuitively compare the output of different LLMs.
 * **Evaluation**: The Coze Loop evaluation module provides developers with systematic evaluation capabilities, enabling automated multi-dimensional testing of prompts and Coze agents' output, such as accuracy, conciseness, compliance, and more.
 * **Observability**: Coze Loop provides developers with observability for the entire execution process, fully recording every stage from user input to AI output, including key stages such as prompt parsing, model invocation, and tool execution, and automatically capturing intermediate results and exceptions.
 
 ## Feature list
+
 | **Feature** | **Functional points** |
 | --- | --- |
-| Prompt debugging | * Playground debugging and comparison <br> * Prompt version management |
-| Evaluation | * Manage evaluation sets <br> Management evaluator <br> * Manage experiments |
+| Prompt debugging | *Playground debugging and comparison <br>* Prompt version management |
+| Evaluation | *Manage evaluation sets <br> Management evaluator <br>* Manage experiments |
 | Observation | SDK trace reporting <br> * Trace data observation |
 | Model | Support integration with OpenAI, Volcengine Ark, and other models |
+
 ## Quick Start
+>
 > Refer to [Quick Start](https://github.com/coze-dev/coze-loop/wiki/2.-Quickstart) to learn in detail how to install and deploy the latest version of Coze Loop.
 
 ### Deployment method 1: Docker deployment (Docker Compose)
+>
 > Please install and start Docker Engine before you start.
 
 Procedure:
 
 1. Clone the source code.
    Run the following command to obtain the latest version of the Coze Loop source code.
+
    ```Bash
    # Clone the code
    git clone https://github.com/coze-dev/coze-loop.git
-   
+
    # Enter the coze-loop directory
-   cd coze-loop 
+   cd coze-loop
    ```
 
 2. Configure a model.
@@ -61,10 +68,11 @@ Procedure:
       * model: The Endpoint ID of the Volcengine Ark model access point. Users within China can refer to [the Volcengine Ark documentation](https://www.volcengine.com/docs/82379/1099522); users outside China can refer to [the BytePlus ModelArk documentation](https://docs.byteplus.com/en/docs/ModelArk/1099522?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).
 3. Start the service.
    Run the following commands to quickly deploy the open-source version of Coze Loop using Docker Compose.
+
    ```Bash
    # Start the service (default: development mode)
    # Run in the coze-loop/ directory
-   make compose-up 
+   make compose-up
    ```
 
 4. Access the Coze Loop open-source version through your browser `http://localhost:8082`.
@@ -77,6 +85,7 @@ Procedure:
 Procedure:
 
 1. Run the following command to obtain the Helm Chart package.
+
    ```Bash
    helm pull oci://docker.io/cozedev/coze-loop --version 1.0.0-helm
    tar -zxvf coze-loop-1.0.0-helm.tgz && cd coze-loop && rm -f ../coze-loop-1.0.0-helm.tgz
@@ -90,6 +99,7 @@ Procedure:
    Ingress is used to expose services to external networks. You need to configure the `templates/ingress.yaml` file in the project directory according to the actual cluster situation, manually modify parameters such as ingressClassName, and configure elements such as class, instance, host, and IP allocation.
 4. Deploy and start the service.
    Execute the following commands to quickly deploy the open-source version of Coze Loop using Helm.
+
    ```Bash
    # Run in the coze-loop/ directory
    make helm-up
@@ -139,11 +149,14 @@ Please **do not** create public GitHub Issues.
 We are committed to building an open and friendly developer community. All developers interested in AI Agent development are welcome to join us!
 
 ### Issue Reports & Feature Requests
+
 To efficiently track and resolve issues while ensuring transparency and collaboration, we recommend participating through:
-- **GitHub Issues**: [Submit bug reports or feature requests](https://github.com/coze-dev/coze-loop/issues)
-- **Pull Requests**: [Contribute code or documentation improvements](https://github.com/coze-dev/coze-loop/pulls)
+
+* **GitHub Issues**: [Submit bug reports or feature requests](https://github.com/coze-dev/coze-loop/issues)
+* **Pull Requests**: [Contribute code or documentation improvements](https://github.com/coze-dev/coze-loop/pulls)
 
 ### Technical Discussion & Communication
+
 Join our technical discussion groups to share experiences with other developers and stay updated with the latest project developments:
 
 * Lark Group Chat: Scan the QR code below on the Lark mobile app to join the Coze Loop technical discussion group.
@@ -155,9 +168,9 @@ Join our technical discussion groups to share experiences with other developers
 * Telegram Group: [Coze](https://t.me/+pP9CkPnomDA0Mjgx)
 
 ## Acknowledgments
+
 Thanks to all developers and community members who contributed to the Coze Loop project Special thanks:
 
 * LLM integration support provided by the [Eino](https://github.com/cloudwego/eino) framework team
 * High-performance frameworks developed by the [CloudWeGo](https://www.cloudwego.io) team
 * All users who participated in testing and feedback
-