docs: add DeerFlow agent runner documentation#165
Conversation
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances AstrBot's documentation by introducing detailed guides for integrating the DeerFlow Agent Runner. It ensures that users have clear instructions for deployment, configuration, and troubleshooting, while also updating existing sections to reflect the expanded list of supported agent runners. The changes are applied consistently across both English and Chinese versions of the documentation. Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey - 我在这里给出了一些整体反馈：
- 在
zh/providers/agent-runners.md中，DeerFlow 在介绍性句子里被提到，但没有添加到 Agent Runner 服务商的项目符号列表中；建议在列表中增加一个DeerFlow条目（与英文页面保持一致），这样用户就可以从中文的服务商列表中导航到新的 DeerFlow 指南。
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- In `zh/providers/agent-runners.md`, DeerFlow is mentioned in the introductory sentence but not added to the bullet list of Agent Runner providers; consider adding a `DeerFlow` entry (mirroring the English page) so users can navigate to the new DeerFlow guide from the Chinese provider list.帮我变得更有用！请在每条评论上点 👍 或 👎，我会根据你的反馈改进后续评审。
Original comment in English
Hey - I've left some high level feedback:
- In
zh/providers/agent-runners.md, DeerFlow is mentioned in the introductory sentence but not added to the bullet list of Agent Runner providers; consider adding aDeerFlowentry (mirroring the English page) so users can navigate to the new DeerFlow guide from the Chinese provider list.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- In `zh/providers/agent-runners.md`, DeerFlow is mentioned in the introductory sentence but not added to the bullet list of Agent Runner providers; consider adding a `DeerFlow` entry (mirroring the English page) so users can navigate to the new DeerFlow guide from the Chinese provider list.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces comprehensive support for DeerFlow as a new Agent Runner in AstrBot. The changes include adding new documentation pages in both English and Chinese (en/providers/agent-runners/deerflow.md and zh/providers/agent-runners/deerflow.md) that detail the setup, configuration options (such as API Base URL, API Key, Assistant ID, model override, thinking mode, plan mode, subagent settings, and recursion limit), and troubleshooting steps for integrating DeerFlow. Additionally, existing documentation files and navigation configurations (.vitepress/config.mjs, en/providers/agent-runners.md, en/use/agent-runner.md, en/what-is-astrbot.md, and their Chinese counterparts) have been updated to reflect DeerFlow's inclusion as a supported third-party Agent Runner. A minor formatting change was also made to the .gitignore file. Review comments highlight the need to clarify the description for "thinking mode" in the DeerFlow configuration documentation, both in English and Chinese, by explaining its function or effect, and suggest improving the readability and consistency of technical terms and default values in the Chinese documentation by wrapping them in backticks.
| - `Authorization Header`: Optional. Custom Authorization header value. This takes precedence over `DeerFlow API Key` | ||
| - `Assistant ID`: Maps to LangGraph `assistant_id`. Default: `lead_agent` | ||
| - `Model name override`: Optional. Overrides the default model configured in DeerFlow | ||
| - `Enable thinking mode`: Whether to enable DeerFlow thinking mode |
There was a problem hiding this comment.
The description for Enable thinking mode is a bit circular ("Whether to enable DeerFlow thinking mode"). Could you add a brief explanation of what "thinking mode" does in DeerFlow, or what effect enabling it has? This would help users understand when they should enable this option.
| - `Assistant ID`：对应 LangGraph 的 `assistant_id`，默认为 `lead_agent` | ||
| - `模型名称覆盖`：可选。覆盖 DeerFlow 默认模型 | ||
| - `启用思考模式`：是否启用 DeerFlow 的思考模式 | ||
| - `启用计划模式`：对应 DeerFlow 的 `is_plan_mode` | ||
| - `启用子智能体`：对应 DeerFlow 的 `subagent_enabled` | ||
| - `子智能体最大并发数`：对应 `max_concurrent_subagents`，仅在启用子智能体时生效，默认 `3` | ||
| - `递归深度上限`：对应 LangGraph 的 `recursion_limit`，默认 `1000` |
There was a problem hiding this comment.
为了提高可读性和一致性，建议将技术术语（如 API 属性和字符串默认值）用反引号包裹起来。此外，“默认”的用法也应保持一致。
| - `Assistant ID`：对应 LangGraph 的 `assistant_id`，默认为 `lead_agent` | |
| - `模型名称覆盖`：可选。覆盖 DeerFlow 默认模型 | |
| - `启用思考模式`：是否启用 DeerFlow 的思考模式 | |
| - `启用计划模式`：对应 DeerFlow 的 `is_plan_mode` | |
| - `启用子智能体`：对应 DeerFlow 的 `subagent_enabled` | |
| - `子智能体最大并发数`：对应 `max_concurrent_subagents`，仅在启用子智能体时生效，默认 `3` | |
| - `递归深度上限`：对应 LangGraph 的 `recursion_limit`，默认 `1000` | |
| - `Assistant ID`：对应 LangGraph 的 `assistant_id`，默认为 `lead_agent` | |
| - `模型名称覆盖`：可选。覆盖 DeerFlow 默认模型 | |
| - `启用思考模式`：是否启用 DeerFlow 的思考模式 | |
| - `启用计划模式`：对应 DeerFlow 的 `is_plan_mode` | |
| - `启用子智能体`：对应 DeerFlow 的 `subagent_enabled` | |
| - `子智能体最大并发数`：对应 `max_concurrent_subagents`，仅在启用子智能体时生效，默认为 `3` | |
| - `递归深度上限`：对应 LangGraph 的 `recursion_limit`，默认为 `1000` |
| - `Authorization Header`：可选。自定义 Authorization 请求头，优先级高于 `DeerFlow API Key` | ||
| - `Assistant ID`：对应 LangGraph 的 `assistant_id`，默认为 `lead_agent` | ||
| - `模型名称覆盖`：可选。覆盖 DeerFlow 默认模型 | ||
| - `启用思考模式`：是否启用 DeerFlow 的思考模式 |
There was a problem hiding this comment.
启用思考模式 的描述有些循环（“是否启用 DeerFlow 的思考模式”）。能否简要解释一下“思考模式”在 DeerFlow 中的作用，或者启用它会有什么效果？这将帮助用户理解何时应该启用此选项。
1 participant
Summary
Verification
Summary by Sourcery
在英文和中文指南及导航中，将 DeerFlow 记录为受支持的 Agent Runner 提供商。
文档：
Original summary in English
Summary by Sourcery
Document DeerFlow as a supported Agent Runner provider in both English and Chinese guides and navigation.
Documentation: