feat: release export-to-docx v0.4.4 w/ formatting & font fixes

Major enhancements:
- Zero-config OpenWebUI Tool Bridge: automatically converts WebUI Functions to Copilot-compatible tools
- Dynamic MCP Discovery: seamlessly reads MCP servers from Admin Settings -> Connections
- High-performance async engine with optimized event-driven streaming
- Robust interoperability via dynamic Pydantic model generation
- Simplified token acquisition (web-based PAT only, removed CLI method)
- Updated configuration valves (renamed, removed legacy parameters)
- Comprehensive bilingual documentation sync

.agent/workflows/plugin-development.md

@@ -11,6 +11,7 @@ This workflow outlines the standard process for developing, documenting, and rel
 Reference: `.github/copilot-instructions.md`
 
 ### Bilingual Requirement
+
 Every plugin **MUST** have bilingual versions for both code and documentation:
 
 - **Code**:
@@ -21,6 +22,7 @@ Every plugin **MUST** have bilingual versions for both code and documentation:
   - Chinese: `plugins/{type}/{name}/README_CN.md`
 
 ### Code Structure
+
 - **Docstring**: Must include `title`, `author`, `version`, `description`, etc.
 - **Valves**: Use `pydantic` for configuration.
 - **Database**: Re-use `open_webui.internal.db` shared connection.
@@ -32,8 +34,9 @@ Every plugin **MUST** have bilingual versions for both code and documentation:
   - Use Chat Persistence API for database storage
   - Always update both `messages[]` and `history.messages`
 
-### Commit Messages
-- **Language**: **English ONLY**. Do not use Chinese in commit messages.
+### Commit Messages & Release Notes
+
+- **Language**: **English ONLY**. Do not use Chinese in commit messages or release notes.
 - **Format**: Conventional Commits (e.g., `feat:`, `fix:`, `docs:`).
 
 ## 2. Documentation Updates
@@ -41,10 +44,12 @@ Every plugin **MUST** have bilingual versions for both code and documentation:
 When adding or updating a plugin, you **MUST** update the following documentation files to maintain consistency:
 
 ### Plugin Directory
+
 - `README.md`: Update version, description, and usage. **Explicitly describe new features in a prominent position at the beginning.**
 - `README_CN.md`: Update version, description, and usage. **Explicitly describe new features in a prominent position at the beginning.**
 
 ### Global Documentation (`docs/`)
+
 - **Index Pages**:
   - `docs/plugins/{type}/index.md`: Add/Update list item with **correct version**.
   - `docs/plugins/{type}/index.zh.md`: Add/Update list item with **correct version**.
@@ -53,6 +58,7 @@ When adding or updating a plugin, you **MUST** update the following documentatio
   - `docs/plugins/{type}/{name}.zh.md`: Ensure content matches README_CN.
 
 ### Root README
+
 - `README.md`: Add to "Featured Plugins" if applicable.
 - `README_CN.md`: Add to "Featured Plugins" if applicable.
 
@@ -61,6 +67,7 @@ When adding or updating a plugin, you **MUST** update the following documentatio
 Reference: `.github/workflows/release.yml`
 
 ### Version Bumping
+
 - **Rule**: Version bump is required **ONLY when the user explicitly requests a release**. Regular code changes do NOT require version bumps.
 - **Format**: Semantic Versioning (e.g., `1.0.0` -> `1.0.1`).
 - **When to Bump**: Only update the version when:
@@ -78,13 +85,14 @@ Reference: `.github/workflows/release.yml`
   8. Docs Detail CN (`docs/.../{name}.zh.md`)
 
 ### Automated Release Process
-1.  **Trigger**: Push to `main` branch with changes in `plugins/**/*.py`.
-2.  **Detection**: `scripts/extract_plugin_versions.py` detects changed plugins and compares versions.
-3.  **Release**:
+
+1. **Trigger**: Push to `main` branch with changes in `plugins/**/*.py`.
+2. **Detection**: `scripts/extract_plugin_versions.py` detects changed plugins and compares versions.
+3. **Release**:
     - Generates release notes based on changes.
     - Creates a GitHub Release tag (e.g., `v2024.01.01-1`).
     - Uploads individual `.py` files of **changed plugins only** as assets.
-4.  **Market Publishing**:
+4. **Market Publishing**:
     - Workflow: `.github/workflows/publish_plugin.yml`
     - Trigger: Release published.
     - Action: Automatically updates the plugin code and metadata on OpenWebUI.com using `scripts/publish_plugin.py`.
@@ -95,6 +103,7 @@ Reference: `.github/workflows/release.yml`
       - Example: `https://github.com/Fu-Jie/awesome-openwebui/blob/main/plugins/filters/folder-memory/README.md`
 
 ### Pull Request Check
+
 - Workflow: `.github/workflows/plugin-version-check.yml`
 - Checks if plugin files are modified.
 - **Fails** if version number is not updated.
@@ -114,5 +123,3 @@ Before committing:
 ## 5. Git Operations (Agent Rules)
 
 Strictly follow the rules defined in `.github/copilot-instructions.md` → **Git Operations (Agent Rules)** section.
-
-

.github/copilot-instructions.md

@@ -42,11 +42,15 @@ plugins/actions/export_to_docx/
     - 格式: `**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** x.x.x | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)`
     - **注意**: Author 和 Project 为固定值，仅需更新 Version 版本号
 3.  **描述 (Description)**: 一句话功能介绍
-4.  **最新更新 (What's New)**: **必须**放在描述之后，显著展示最新版本的变更点 (仅展示最近 3 次更新)
+4.  **最新更新 (What's New)**: **必须**放在描述之后，仅展示**最近 1 次**更新
 5.  **核心特性 (Key Features)**: 使用 Emoji + 粗体标题 + 描述格式
 6.  **使用方法 (How to Use)**: 按步骤说明
 7.  **配置参数 (Configuration/Valves)**: 使用表格格式，包含参数名、默认值、描述
-8.  **其他 (Others)**: 支持的模板类型、语法示例、故障排除等
+8.  **支持 (Support)**: **必须**包含，放在配置参数之后、故障排除之前
+    - English: `If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.`
+    - 中文: `如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。`
+9.  **其他 (Others)**: 支持的模板类型、语法示例、故障排除等
+    - **Changelog**: 统一指向 GitHub 项目历史，不在 README 中列出具体变更
 
 ### 2. 插件目录结构 (Plugin Directory Structure)
 

README.md

@@ -10,28 +10,28 @@ A collection of enhancements, plugins, and prompts for [OpenWebUI](https://githu
 <!-- STATS_START -->
 ## 📊 Community Stats
 
-> 🕐 Auto-updated: 2026-01-28 01:12
+> 🕐 Auto-updated: 2026-02-07 17:12
 
 | 👤 Author | 👥 Followers | ⭐ Points | 🏆 Contributions |
 |:---:|:---:|:---:|:---:|
-| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **165** | **157** | **34** |
+| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **204** | **257** | **41** |
 
 | 📝 Posts | ⬇️ Downloads | 👁️ Views | 👍 Upvotes | 💾 Saves |
 |:---:|:---:|:---:|:---:|:---:|
-| **19** | **2501** | **29277** | **141** | **197** |
+| **20** | **3711** | **43662** | **220** | **256** |
 
 ### 🔥 Top 6 Popular Plugins
 
-> 🕐 Auto-updated: 2026-01-28 01:12
+> 🕐 Auto-updated: 2026-02-07 17:12
 
 | Rank | Plugin | Version | Downloads | Views | Updated |
 |:---:|------|:---:|:---:|:---:|:---:|
-| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 0.9.1 | 652 | 5828 | 2026-01-17 |
-| 🥈 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 1.4.9 | 434 | 3928 | 2026-01-25 |
-| 🥉 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 0.3.7 | 263 | 1082 | 2026-01-07 |
-| 4️⃣ | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 0.4.3 | 238 | 1916 | 2026-01-17 |
-| 5️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 1.2.2 | 236 | 2557 | 2026-01-21 |
-| 6️⃣ | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | 0.2.4 | 176 | 2769 | 2026-01-17 |
+| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 0.9.2 | 883 | 7810 | 2026-01-28 |
+| 🥈 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 1.5.0 | 635 | 5880 | 2026-01-30 |
+| 🥉 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 0.4.3 | 347 | 2686 | 2026-01-28 |
+| 4️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 1.2.2 | 330 | 3436 | 2026-01-28 |
+| 5️⃣ | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 0.3.7 | 327 | 1520 | 2026-01-29 |
+| 6️⃣ | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) | 1.2.4 | 294 | 4270 | 2026-01-29 |
 
 *See full stats in [Community Stats Report](./docs/community-stats.md)*
 <!-- STATS_END -->
@@ -73,6 +73,12 @@ Located in the `prompts/` directory, containing fine-tuned System Prompts:
 - **Coding**: Programming assistance prompts.
 - **Marketing**: Marketing and copywriting prompts.
 
+## 🛠️ Extensions
+
+Standalone frontend extensions to supercharge your Open WebUI:
+
+- **[Open WebUI Prompt Plus](https://github.com/Fu-Jie/open-webui-prompt-plus)**: An all-in-one prompt management suite featuring AI-powered prompt generation, spotlight-style quick search, and advanced category organization.
+
 ## 📖 Documentation
 
 Located in the `docs/en/` directory:

README_CN.md

@@ -7,28 +7,28 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
 <!-- STATS_START -->
 ## 📊 社区统计
 
-> 🕐 自动更新于 2026-01-28 01:12
+> 🕐 自动更新于 2026-02-07 17:12
 
 | 👤 作者 | 👥 粉丝 | ⭐ 积分 | 🏆 贡献 |
 |:---:|:---:|:---:|:---:|
-| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **165** | **157** | **34** |
+| [Fu-Jie](https://openwebui.com/u/Fu-Jie) | **204** | **257** | **41** |
 
 | 📝 发布 | ⬇️ 下载 | 👁️ 浏览 | 👍 点赞 | 💾 收藏 |
 |:---:|:---:|:---:|:---:|:---:|
-| **19** | **2501** | **29277** | **141** | **197** |
+| **20** | **3711** | **43662** | **220** | **256** |
 
 ### 🔥 热门插件 Top 6
 
-> 🕐 自动更新于 2026-01-28 01:12
+> 🕐 自动更新于 2026-02-07 17:12
 
 | 排名 | 插件 | 版本 | 下载 | 浏览 | 更新日期 |
 |:---:|------|:---:|:---:|:---:|:---:|
-| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 0.9.1 | 652 | 5828 | 2026-01-17 |
-| 🥈 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 1.4.9 | 434 | 3928 | 2026-01-25 |
-| 🥉 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 0.3.7 | 263 | 1082 | 2026-01-07 |
-| 4️⃣ | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 0.4.3 | 238 | 1916 | 2026-01-17 |
-| 5️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 1.2.2 | 236 | 2557 | 2026-01-21 |
-| 6️⃣ | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | 0.2.4 | 176 | 2769 | 2026-01-17 |
+| 🥇 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | 0.9.2 | 883 | 7810 | 2026-01-28 |
+| 🥈 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | 1.5.0 | 635 | 5880 | 2026-01-30 |
+| 🥉 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | 0.4.3 | 347 | 2686 | 2026-01-28 |
+| 4️⃣ | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | 1.2.2 | 330 | 3436 | 2026-01-28 |
+| 5️⃣ | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | 0.3.7 | 327 | 1520 | 2026-01-29 |
+| 6️⃣ | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) | 1.2.4 | 294 | 4270 | 2026-01-29 |
 
 *完整统计请查看 [社区统计报告](./docs/community-stats.zh.md)*
 <!-- STATS_END -->
@@ -76,6 +76,12 @@ OpenWebUI 增强功能集合。包含个人开发与收集的插件、提示词
 
 每个提示词都独立保存为 Markdown 文件，可直接在 OpenWebUI 中使用。
 
+## 🛠️ 扩展 (Extensions)
+
+Open WebUI 的前端增强扩展：
+
+- **[Open WebUI Prompt Plus](https://github.com/Fu-Jie/open-webui-prompt-plus)**: 一站式提示词管理套件，支持 AI 提示词生成、Spotlight 风格快速搜索及高级分类管理。
+
 ## 📖 开发文档
 
 位于 `docs/zh/` 目录：

docs/PLUGIN_README_TEMPLATE.md

@@ -10,9 +10,10 @@ The Chinese version (README_CN.md) MUST be translated based on this English vers
 
 ## What's New
 
-<!-- Keep the changelog for the last 3 versions here. Remove this section for the initial release. -->
+<!-- Keep only the latest update here. Remove this section for the initial release. -->
 
 ### v1.0.0
+
 - **Initial Release**: Released the first version of the plugin.
 - **[Feature Name]**: [Brief description of the feature].
 
@@ -36,9 +37,17 @@ The Chinese version (README_CN.md) MUST be translated based on this English vers
 | `VALVE_NAME` | `Default Value` | Description of what this setting does. |
 | `ANOTHER_VALVE` | `True` | Another setting description. |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## Troubleshooting ❓
 
 - **Plugin not working?**: Check if the filter/action is enabled in the model settings.
 - **Debug Logs**: Enable `SHOW_DEBUG_LOG` in Valves and check the browser console (F12) for detailed logs.
 - **Error Messages**: If you see an error, please copy the full error message and report it.
 - **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

docs/badges/downloads.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
   "label": "downloads",
-  "message": "2.5k",
+  "message": "3.7k",
   "color": "blue",
   "namedLogo": "openwebui"
 }

docs/badges/followers.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
   "label": "followers",
-  "message": "165",
+  "message": "204",
   "color": "blue"
 }

docs/badges/plugins.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
   "label": "plugins",
-  "message": "19",
+  "message": "20",
   "color": "green"
 }

docs/badges/points.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
   "label": "points",
-  "message": "157",
+  "message": "257",
   "color": "orange"
 }

docs/badges/upvotes.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
   "label": "upvotes",
-  "message": "141",
+  "message": "220",
   "color": "brightgreen"
 }

docs/community-stats.json

@@ -1,15 +1,15 @@
 {
-  "total_posts": 19,
-  "total_downloads": 2501,
-  "total_views": 29277,
-  "total_upvotes": 141,
+  "total_posts": 20,
+  "total_downloads": 3711,
+  "total_views": 43662,
+  "total_upvotes": 220,
   "total_downvotes": 2,
-  "total_saves": 197,
-  "total_comments": 38,
+  "total_saves": 256,
+  "total_comments": 47,
   "by_type": {
     "pipe": 1,
     "action": 14,
-    "unknown": 3,
+    "unknown": 4,
     "filter": 1
   },
   "posts": [
@@ -17,50 +17,34 @@
       "title": "Smart Mind Map",
       "slug": "turn_any_text_into_beautiful_mind_maps_3094c59a",
       "type": "action",
-      "version": "0.9.1",
+      "version": "0.9.2",
       "author": "Fu-Jie",
       "description": "Intelligently analyzes text content and generates interactive mind maps to help users structure and visualize knowledge.",
-      "downloads": 652,
-      "views": 5828,
-      "upvotes": 17,
-      "saves": 38,
-      "comments": 11,
+      "downloads": 883,
+      "views": 7810,
+      "upvotes": 22,
+      "saves": 48,
+      "comments": 13,
       "created_at": "2025-12-30",
-      "updated_at": "2026-01-17",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a"
     },
     {
       "title": "Smart Infographic",
       "slug": "smart_infographic_ad6f0c7f",
       "type": "action",
-      "version": "1.4.9",
+      "version": "1.5.0",
       "author": "Fu-Jie",
       "description": "AI-powered infographic generator based on AntV Infographic. Supports professional templates, auto-icon matching, and SVG/PNG downloads.",
-      "downloads": 434,
-      "views": 3928,
-      "upvotes": 18,
-      "saves": 28,
+      "downloads": 635,
+      "views": 5880,
+      "upvotes": 24,
+      "saves": 33,
       "comments": 10,
       "created_at": "2025-12-28",
-      "updated_at": "2026-01-25",
+      "updated_at": "2026-01-30",
       "url": "https://openwebui.com/posts/smart_infographic_ad6f0c7f"
     },
-    {
-      "title": "Export to Excel",
-      "slug": "export_mulit_table_to_excel_244b8f9d",
-      "type": "action",
-      "version": "0.3.7",
-      "author": "Fu-Jie",
-      "description": "Extracts tables from chat messages and exports them to Excel (.xlsx) files with smart formatting.",
-      "downloads": 263,
-      "views": 1082,
-      "upvotes": 4,
-      "saves": 6,
-      "comments": 0,
-      "created_at": "2025-05-30",
-      "updated_at": "2026-01-07",
-      "url": "https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d"
-    },
     {
       "title": "Export to Word (Enhanced)",
       "slug": "export_to_word_enhanced_formatting_fca6a315",
@@ -68,13 +52,13 @@
       "version": "0.4.3",
       "author": "Fu-Jie",
       "description": "Export current conversation from Markdown to Word (.docx) with Mermaid diagrams rendered client-side (Mermaid.js, SVG+PNG), LaTeX math, real hyperlinks, improved tables, syntax highlighting, and blockquote support.",
-      "downloads": 238,
-      "views": 1916,
-      "upvotes": 8,
-      "saves": 21,
-      "comments": 0,
+      "downloads": 347,
+      "views": 2686,
+      "upvotes": 14,
+      "saves": 26,
+      "comments": 2,
       "created_at": "2026-01-03",
-      "updated_at": "2026-01-17",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315"
     },
     {
@@ -84,30 +68,30 @@
       "version": "1.2.2",
       "author": "Fu-Jie",
       "description": "Reduces token consumption in long conversations while maintaining coherence through intelligent summarization and message compression.",
-      "downloads": 236,
-      "views": 2557,
-      "upvotes": 9,
-      "saves": 27,
+      "downloads": 330,
+      "views": 3436,
+      "upvotes": 14,
+      "saves": 33,
       "comments": 0,
       "created_at": "2025-11-08",
-      "updated_at": "2026-01-21",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/async_context_compression_b1655bc8"
     },
     {
-      "title": "Flash Card",
-      "slug": "flash_card_65a2ea8f",
+      "title": "Export to Excel",
+      "slug": "export_mulit_table_to_excel_244b8f9d",
       "type": "action",
-      "version": "0.2.4",
+      "version": "0.3.7",
       "author": "Fu-Jie",
-      "description": "Quickly generates beautiful flashcards from text, extracting key points and categories.",
-      "downloads": 176,
-      "views": 2769,
-      "upvotes": 11,
-      "saves": 13,
-      "comments": 2,
-      "created_at": "2025-12-30",
-      "updated_at": "2026-01-17",
-      "url": "https://openwebui.com/posts/flash_card_65a2ea8f"
+      "description": "Extracts tables from chat messages and exports them to Excel (.xlsx) files with smart formatting.",
+      "downloads": 327,
+      "views": 1520,
+      "upvotes": 7,
+      "saves": 6,
+      "comments": 0,
+      "created_at": "2025-05-30",
+      "updated_at": "2026-01-29",
+      "url": "https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d"
     },
     {
       "title": "Markdown Normalizer",
@@ -116,15 +100,47 @@
       "version": "1.2.4",
       "author": "Fu-Jie",
       "description": "A content normalizer filter that fixes common Markdown formatting issues in LLM outputs, such as broken code blocks, LaTeX formulas, and list formatting.",
-      "downloads": 160,
-      "views": 2884,
-      "upvotes": 10,
-      "saves": 22,
+      "downloads": 294,
+      "views": 4270,
+      "upvotes": 17,
+      "saves": 27,
       "comments": 5,
       "created_at": "2026-01-12",
-      "updated_at": "2026-01-19",
+      "updated_at": "2026-01-29",
       "url": "https://openwebui.com/posts/markdown_normalizer_baaa8732"
     },
+    {
+      "title": "Flash Card",
+      "slug": "flash_card_65a2ea8f",
+      "type": "action",
+      "version": "0.2.4",
+      "author": "Fu-Jie",
+      "description": "Quickly generates beautiful flashcards from text, extracting key points and categories.",
+      "downloads": 213,
+      "views": 3247,
+      "upvotes": 13,
+      "saves": 14,
+      "comments": 2,
+      "created_at": "2025-12-30",
+      "updated_at": "2026-01-28",
+      "url": "https://openwebui.com/posts/flash_card_65a2ea8f"
+    },
+    {
+      "title": "AI Task Instruction Generator",
+      "slug": "ai_task_instruction_generator_9bab8b37",
+      "type": "unknown",
+      "version": "",
+      "author": "",
+      "description": "",
+      "downloads": 153,
+      "views": 2234,
+      "upvotes": 8,
+      "saves": 3,
+      "comments": 0,
+      "created_at": "2026-01-28",
+      "updated_at": "2026-01-28",
+      "url": "https://openwebui.com/posts/ai_task_instruction_generator_9bab8b37"
+    },
     {
       "title": "Deep Dive",
       "slug": "deep_dive_c0b846e4",
@@ -132,10 +148,10 @@
       "version": "1.0.0",
       "author": "Fu-Jie",
       "description": "A comprehensive thinking lens that dives deep into any content - from context to logic, insights, and action paths.",
-      "downloads": 94,
-      "views": 863,
-      "upvotes": 4,
-      "saves": 8,
+      "downloads": 134,
+      "views": 1162,
+      "upvotes": 6,
+      "saves": 11,
       "comments": 0,
       "created_at": "2026-01-08",
       "updated_at": "2026-01-08",
@@ -148,29 +164,29 @@
       "version": "0.4.3",
       "author": "Fu-Jie",
       "description": "将对话导出为 Word (.docx)，支持 Mermaid 图表 (客户端渲染 SVG+PNG)、LaTeX 数学公式、真实超链接、增强表格格式、代码高亮和引用块。",
-      "downloads": 89,
-      "views": 1689,
-      "upvotes": 11,
-      "saves": 4,
+      "downloads": 119,
+      "views": 2111,
+      "upvotes": 13,
+      "saves": 6,
       "comments": 4,
       "created_at": "2026-01-04",
-      "updated_at": "2026-01-17",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0"
     },
     {
-      "title": "📊 智能信息图 (AntV Infographic)",
+      "title": "智能信息图",
       "slug": "智能信息图_e04a48ff",
       "type": "action",
-      "version": "1.4.9",
+      "version": "1.5.0",
       "author": "Fu-Jie",
       "description": "基于 AntV Infographic 的智能信息图生成插件。支持多种专业模板，自动图标匹配，并提供 SVG/PNG 下载功能。",
-      "downloads": 47,
-      "views": 799,
-      "upvotes": 6,
-      "saves": 0,
+      "downloads": 56,
+      "views": 1006,
+      "upvotes": 10,
+      "saves": 1,
       "comments": 0,
       "created_at": "2025-12-28",
-      "updated_at": "2026-01-17",
+      "updated_at": "2026-01-29",
       "url": "https://openwebui.com/posts/智能信息图_e04a48ff"
     },
     {
@@ -180,29 +196,45 @@
       "version": "0.1.0",
       "author": "Fu-Jie",
       "description": "Automatically extracts project rules from conversations and injects them into the folder's system prompt.",
-      "downloads": 28,
-      "views": 810,
-      "upvotes": 4,
-      "saves": 7,
+      "downloads": 56,
+      "views": 1209,
+      "upvotes": 6,
+      "saves": 8,
       "comments": 0,
       "created_at": "2026-01-20",
       "updated_at": "2026-01-20",
       "url": "https://openwebui.com/posts/folder_memory_auto_evolving_project_context_4a9875b2"
     },
+    {
+      "title": "GitHub Copilot Official SDK Pipe",
+      "slug": "github_copilot_official_sdk_pipe_ce96f7b4",
+      "type": "pipe",
+      "version": "0.3.0",
+      "author": "Fu-Jie",
+      "description": "Integrate GitHub Copilot SDK. Supports dynamic models, multi-turn conversation, streaming, multimodal input, infinite sessions, and frontend debug logging.",
+      "downloads": 52,
+      "views": 1882,
+      "upvotes": 12,
+      "saves": 6,
+      "comments": 1,
+      "created_at": "2026-01-26",
+      "updated_at": "2026-02-07",
+      "url": "https://openwebui.com/posts/github_copilot_official_sdk_pipe_ce96f7b4"
+    },
     {
       "title": "思维导图",
       "slug": "智能生成交互式思维导图帮助用户可视化知识_8d4b097b",
       "type": "action",
-      "version": "0.9.1",
+      "version": "0.9.2",
       "author": "Fu-Jie",
       "description": "智能分析文本内容,生成交互式思维导图,帮助用户结构化和可视化知识。",
-      "downloads": 27,
-      "views": 463,
-      "upvotes": 4,
-      "saves": 1,
+      "downloads": 37,
+      "views": 564,
+      "upvotes": 6,
+      "saves": 2,
       "comments": 0,
       "created_at": "2025-12-31",
-      "updated_at": "2026-01-17",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b"
     },
     {
@@ -212,13 +244,13 @@
       "version": "1.2.2",
       "author": "Fu-Jie",
       "description": "通过智能摘要和消息压缩，降低长对话的 token 消耗，同时保持对话连贯性。",
-      "downloads": 22,
-      "views": 511,
-      "upvotes": 5,
-      "saves": 2,
+      "downloads": 31,
+      "views": 628,
+      "upvotes": 7,
+      "saves": 4,
       "comments": 0,
       "created_at": "2025-11-08",
-      "updated_at": "2026-01-21",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/异步上下文压缩_5c0617cb"
     },
     {
@@ -228,13 +260,13 @@
       "version": "0.2.4",
       "author": "Fu-Jie",
       "description": "快速将文本提炼为精美的学习记忆卡片，支持核心要点提取与分类。",
-      "downloads": 19,
-      "views": 524,
-      "upvotes": 6,
+      "downloads": 27,
+      "views": 661,
+      "upvotes": 8,
       "saves": 1,
       "comments": 0,
       "created_at": "2025-12-30",
-      "updated_at": "2026-01-17",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/闪记卡生成插件_4a31eac3"
     },
     {
@@ -244,31 +276,15 @@
       "version": "1.0.0",
       "author": "Fu-Jie",
       "description": "全方位的思维透镜 —— 从背景全景到逻辑脉络，从深度洞察到行动路径。",
-      "downloads": 9,
-      "views": 316,
-      "upvotes": 3,
+      "downloads": 17,
+      "views": 400,
+      "upvotes": 5,
       "saves": 1,
       "comments": 0,
       "created_at": "2026-01-08",
       "updated_at": "2026-01-08",
       "url": "https://openwebui.com/posts/精读_99830b0f"
     },
-    {
-      "title": "GitHub Copilot Official SDK Pipe",
-      "slug": "github_copilot_official_sdk_pipe_ce96f7b4",
-      "type": "pipe",
-      "version": "0.2.3",
-      "author": "Fu-Jie",
-      "description": "Integrate GitHub Copilot SDK. Supports dynamic models, multi-turn conversation, streaming, multimodal input, infinite sessions, and frontend debug logging.",
-      "downloads": 7,
-      "views": 295,
-      "upvotes": 2,
-      "saves": 2,
-      "comments": 1,
-      "created_at": "2026-01-26",
-      "updated_at": "2026-01-26",
-      "url": "https://openwebui.com/posts/github_copilot_official_sdk_pipe_ce96f7b4"
-    },
     {
       "title": "🚀 Open WebUI Prompt Plus: AI-Powered Prompt Manager",
       "slug": "open_webui_prompt_plus_ai_powered_prompt_manager_s_15fa060e",
@@ -277,12 +293,12 @@
       "author": "",
       "description": "",
       "downloads": 0,
-      "views": 653,
-      "upvotes": 6,
-      "saves": 8,
-      "comments": 3,
+      "views": 1429,
+      "upvotes": 12,
+      "saves": 17,
+      "comments": 8,
       "created_at": "2026-01-25",
-      "updated_at": "2026-01-25",
+      "updated_at": "2026-01-28",
       "url": "https://openwebui.com/posts/open_webui_prompt_plus_ai_powered_prompt_manager_s_15fa060e"
     },
     {
@@ -293,8 +309,8 @@
       "author": "",
       "description": "",
       "downloads": 0,
-      "views": 99,
-      "upvotes": 1,
+      "views": 135,
+      "upvotes": 2,
       "saves": 0,
       "comments": 0,
       "created_at": "2026-01-14",
@@ -309,9 +325,9 @@
       "author": "",
       "description": "",
       "downloads": 0,
-      "views": 1291,
-      "upvotes": 12,
-      "saves": 8,
+      "views": 1392,
+      "upvotes": 14,
+      "saves": 9,
       "comments": 2,
       "created_at": "2026-01-10",
       "updated_at": "2026-01-10",
@@ -323,11 +339,11 @@
     "name": "Fu-Jie",
     "profile_url": "https://openwebui.com/u/Fu-Jie",
     "profile_image": "https://community.s3.openwebui.com/uploads/users/b15d1348-4347-42b4-b815-e053342d6cb0/profile_d9510745-4bd4-4f8f-a997-4a21847d9300.webp",
-    "followers": 165,
-    "following": 3,
-    "total_points": 157,
-    "post_points": 139,
-    "comment_points": 18,
-    "contributions": 34
+    "followers": 204,
+    "following": 4,
+    "total_points": 257,
+    "post_points": 218,
+    "comment_points": 39,
+    "contributions": 41
   }
 }

docs/community-stats.md

@@ -1,45 +1,46 @@
 # 📊 OpenWebUI Community Stats Report
 
-> 📅 Updated: 2026-01-28 01:12
+> 📅 Updated: 2026-02-07 17:12
 
 ## 📈 Overview
 
 | Metric | Value |
 |------|------|
-| 📝 Total Posts | 19 |
-| ⬇️ Total Downloads | 2501 |
-| 👁️ Total Views | 29277 |
-| 👍 Total Upvotes | 141 |
-| 💾 Total Saves | 197 |
-| 💬 Total Comments | 38 |
+| 📝 Total Posts | 20 |
+| ⬇️ Total Downloads | 3711 |
+| 👁️ Total Views | 43662 |
+| 👍 Total Upvotes | 220 |
+| 💾 Total Saves | 256 |
+| 💬 Total Comments | 47 |
 
 ## 📂 By Type
 
 - **pipe**: 1
 - **action**: 14
-- **unknown**: 3
+- **unknown**: 4
 - **filter**: 1
 
 ## 📋 Posts List
 
 | Rank | Title | Type | Version | Downloads | Views | Upvotes | Saves | Updated |
 |:---:|------|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.1 | 652 | 5828 | 17 | 38 | 2026-01-17 |
-| 2 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.4.9 | 434 | 3928 | 18 | 28 | 2026-01-25 |
-| 3 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 263 | 1082 | 4 | 6 | 2026-01-07 |
-| 4 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 238 | 1916 | 8 | 21 | 2026-01-17 |
-| 5 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | action | 1.2.2 | 236 | 2557 | 9 | 27 | 2026-01-21 |
-| 6 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 176 | 2769 | 11 | 13 | 2026-01-17 |
-| 7 | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) | action | 1.2.4 | 160 | 2884 | 10 | 22 | 2026-01-19 |
-| 8 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 94 | 863 | 4 | 8 | 2026-01-08 |
-| 9 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 89 | 1689 | 11 | 4 | 2026-01-17 |
-| 10 | [📊 智能信息图 (AntV Infographic)](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.4.9 | 47 | 799 | 6 | 0 | 2026-01-17 |
-| 11 | [📂 Folder Memory – Auto-Evolving Project Context](https://openwebui.com/posts/folder_memory_auto_evolving_project_context_4a9875b2) | filter | 0.1.0 | 28 | 810 | 4 | 7 | 2026-01-20 |
-| 12 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.1 | 27 | 463 | 4 | 1 | 2026-01-17 |
-| 13 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | action | 1.2.2 | 22 | 511 | 5 | 2 | 2026-01-21 |
-| 14 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 19 | 524 | 6 | 1 | 2026-01-17 |
-| 15 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 9 | 316 | 3 | 1 | 2026-01-08 |
-| 16 | [GitHub Copilot Official SDK Pipe](https://openwebui.com/posts/github_copilot_official_sdk_pipe_ce96f7b4) | pipe | 0.2.3 | 7 | 295 | 2 | 2 | 2026-01-26 |
-| 17 | [🚀 Open WebUI Prompt Plus: AI-Powered Prompt Manager](https://openwebui.com/posts/open_webui_prompt_plus_ai_powered_prompt_manager_s_15fa060e) | unknown |  | 0 | 653 | 6 | 8 | 2026-01-25 |
-| 18 | [Review of Claude Haiku 4.5](https://openwebui.com/posts/review_of_claude_haiku_45_41b0db39) | unknown |  | 0 | 99 | 1 | 0 | 2026-01-14 |
-| 19 | [ 🛠️ Debug Open WebUI Plugins in Your Browser](https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960) | unknown |  | 0 | 1291 | 12 | 8 | 2026-01-10 |
+| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.2 | 883 | 7810 | 22 | 48 | 2026-01-28 |
+| 2 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.5.0 | 635 | 5880 | 24 | 33 | 2026-01-30 |
+| 3 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 347 | 2686 | 14 | 26 | 2026-01-28 |
+| 4 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | action | 1.2.2 | 330 | 3436 | 14 | 33 | 2026-01-28 |
+| 5 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 327 | 1520 | 7 | 6 | 2026-01-29 |
+| 6 | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) | action | 1.2.4 | 294 | 4270 | 17 | 27 | 2026-01-29 |
+| 7 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 213 | 3247 | 13 | 14 | 2026-01-28 |
+| 8 | [AI Task Instruction Generator](https://openwebui.com/posts/ai_task_instruction_generator_9bab8b37) | unknown |  | 153 | 2234 | 8 | 3 | 2026-01-28 |
+| 9 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 134 | 1162 | 6 | 11 | 2026-01-08 |
+| 10 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 119 | 2111 | 13 | 6 | 2026-01-28 |
+| 11 | [智能信息图](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.5.0 | 56 | 1006 | 10 | 1 | 2026-01-29 |
+| 12 | [📂 Folder Memory – Auto-Evolving Project Context](https://openwebui.com/posts/folder_memory_auto_evolving_project_context_4a9875b2) | filter | 0.1.0 | 56 | 1209 | 6 | 8 | 2026-01-20 |
+| 13 | [GitHub Copilot Official SDK Pipe](https://openwebui.com/posts/github_copilot_official_sdk_pipe_ce96f7b4) | pipe | 0.3.0 | 52 | 1882 | 12 | 6 | 2026-02-07 |
+| 14 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.2 | 37 | 564 | 6 | 2 | 2026-01-28 |
+| 15 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | action | 1.2.2 | 31 | 628 | 7 | 4 | 2026-01-28 |
+| 16 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 27 | 661 | 8 | 1 | 2026-01-28 |
+| 17 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 17 | 400 | 5 | 1 | 2026-01-08 |
+| 18 | [🚀 Open WebUI Prompt Plus: AI-Powered Prompt Manager](https://openwebui.com/posts/open_webui_prompt_plus_ai_powered_prompt_manager_s_15fa060e) | unknown |  | 0 | 1429 | 12 | 17 | 2026-01-28 |
+| 19 | [Review of Claude Haiku 4.5](https://openwebui.com/posts/review_of_claude_haiku_45_41b0db39) | unknown |  | 0 | 135 | 2 | 0 | 2026-01-14 |
+| 20 | [ 🛠️ Debug Open WebUI Plugins in Your Browser](https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960) | unknown |  | 0 | 1392 | 14 | 9 | 2026-01-10 |

docs/community-stats.zh.md

@@ -1,45 +1,46 @@
 # 📊 OpenWebUI 社区统计报告
 
-> 📅 更新时间: 2026-01-28 01:12
+> 📅 更新时间: 2026-02-07 17:12
 
 ## 📈 总览
 
 | 指标 | 数值 |
 |------|------|
-| 📝 发布数量 | 19 |
-| ⬇️ 总下载量 | 2501 |
-| 👁️ 总浏览量 | 29277 |
-| 👍 总点赞数 | 141 |
-| 💾 总收藏数 | 197 |
-| 💬 总评论数 | 38 |
+| 📝 发布数量 | 20 |
+| ⬇️ 总下载量 | 3711 |
+| 👁️ 总浏览量 | 43662 |
+| 👍 总点赞数 | 220 |
+| 💾 总收藏数 | 256 |
+| 💬 总评论数 | 47 |
 
 ## 📂 按类型分类
 
 - **pipe**: 1
 - **action**: 14
-- **unknown**: 3
+- **unknown**: 4
 - **filter**: 1
 
 ## 📋 发布列表
 
 | 排名 | 标题 | 类型 | 版本 | 下载 | 浏览 | 点赞 | 收藏 | 更新日期 |
 |:---:|------|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
-| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.1 | 652 | 5828 | 17 | 38 | 2026-01-17 |
-| 2 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.4.9 | 434 | 3928 | 18 | 28 | 2026-01-25 |
-| 3 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 263 | 1082 | 4 | 6 | 2026-01-07 |
-| 4 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 238 | 1916 | 8 | 21 | 2026-01-17 |
-| 5 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | action | 1.2.2 | 236 | 2557 | 9 | 27 | 2026-01-21 |
-| 6 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 176 | 2769 | 11 | 13 | 2026-01-17 |
-| 7 | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) | action | 1.2.4 | 160 | 2884 | 10 | 22 | 2026-01-19 |
-| 8 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 94 | 863 | 4 | 8 | 2026-01-08 |
-| 9 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 89 | 1689 | 11 | 4 | 2026-01-17 |
-| 10 | [📊 智能信息图 (AntV Infographic)](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.4.9 | 47 | 799 | 6 | 0 | 2026-01-17 |
-| 11 | [📂 Folder Memory – Auto-Evolving Project Context](https://openwebui.com/posts/folder_memory_auto_evolving_project_context_4a9875b2) | filter | 0.1.0 | 28 | 810 | 4 | 7 | 2026-01-20 |
-| 12 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.1 | 27 | 463 | 4 | 1 | 2026-01-17 |
-| 13 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | action | 1.2.2 | 22 | 511 | 5 | 2 | 2026-01-21 |
-| 14 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 19 | 524 | 6 | 1 | 2026-01-17 |
-| 15 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 9 | 316 | 3 | 1 | 2026-01-08 |
-| 16 | [GitHub Copilot Official SDK Pipe](https://openwebui.com/posts/github_copilot_official_sdk_pipe_ce96f7b4) | pipe | 0.2.3 | 7 | 295 | 2 | 2 | 2026-01-26 |
-| 17 | [🚀 Open WebUI Prompt Plus: AI-Powered Prompt Manager](https://openwebui.com/posts/open_webui_prompt_plus_ai_powered_prompt_manager_s_15fa060e) | unknown |  | 0 | 653 | 6 | 8 | 2026-01-25 |
-| 18 | [Review of Claude Haiku 4.5](https://openwebui.com/posts/review_of_claude_haiku_45_41b0db39) | unknown |  | 0 | 99 | 1 | 0 | 2026-01-14 |
-| 19 | [ 🛠️ Debug Open WebUI Plugins in Your Browser](https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960) | unknown |  | 0 | 1291 | 12 | 8 | 2026-01-10 |
+| 1 | [Smart Mind Map](https://openwebui.com/posts/turn_any_text_into_beautiful_mind_maps_3094c59a) | action | 0.9.2 | 883 | 7810 | 22 | 48 | 2026-01-28 |
+| 2 | [Smart Infographic](https://openwebui.com/posts/smart_infographic_ad6f0c7f) | action | 1.5.0 | 635 | 5880 | 24 | 33 | 2026-01-30 |
+| 3 | [Export to Word (Enhanced)](https://openwebui.com/posts/export_to_word_enhanced_formatting_fca6a315) | action | 0.4.3 | 347 | 2686 | 14 | 26 | 2026-01-28 |
+| 4 | [Async Context Compression](https://openwebui.com/posts/async_context_compression_b1655bc8) | action | 1.2.2 | 330 | 3436 | 14 | 33 | 2026-01-28 |
+| 5 | [Export to Excel](https://openwebui.com/posts/export_mulit_table_to_excel_244b8f9d) | action | 0.3.7 | 327 | 1520 | 7 | 6 | 2026-01-29 |
+| 6 | [Markdown Normalizer](https://openwebui.com/posts/markdown_normalizer_baaa8732) | action | 1.2.4 | 294 | 4270 | 17 | 27 | 2026-01-29 |
+| 7 | [Flash Card](https://openwebui.com/posts/flash_card_65a2ea8f) | action | 0.2.4 | 213 | 3247 | 13 | 14 | 2026-01-28 |
+| 8 | [AI Task Instruction Generator](https://openwebui.com/posts/ai_task_instruction_generator_9bab8b37) | unknown |  | 153 | 2234 | 8 | 3 | 2026-01-28 |
+| 9 | [Deep Dive](https://openwebui.com/posts/deep_dive_c0b846e4) | action | 1.0.0 | 134 | 1162 | 6 | 11 | 2026-01-08 |
+| 10 | [导出为 Word (增强版)](https://openwebui.com/posts/导出为_word_支持公式流程图表格和代码块_8a6306c0) | action | 0.4.3 | 119 | 2111 | 13 | 6 | 2026-01-28 |
+| 11 | [智能信息图](https://openwebui.com/posts/智能信息图_e04a48ff) | action | 1.5.0 | 56 | 1006 | 10 | 1 | 2026-01-29 |
+| 12 | [📂 Folder Memory – Auto-Evolving Project Context](https://openwebui.com/posts/folder_memory_auto_evolving_project_context_4a9875b2) | filter | 0.1.0 | 56 | 1209 | 6 | 8 | 2026-01-20 |
+| 13 | [GitHub Copilot Official SDK Pipe](https://openwebui.com/posts/github_copilot_official_sdk_pipe_ce96f7b4) | pipe | 0.3.0 | 52 | 1882 | 12 | 6 | 2026-02-07 |
+| 14 | [思维导图](https://openwebui.com/posts/智能生成交互式思维导图帮助用户可视化知识_8d4b097b) | action | 0.9.2 | 37 | 564 | 6 | 2 | 2026-01-28 |
+| 15 | [异步上下文压缩](https://openwebui.com/posts/异步上下文压缩_5c0617cb) | action | 1.2.2 | 31 | 628 | 7 | 4 | 2026-01-28 |
+| 16 | [闪记卡 (Flash Card)](https://openwebui.com/posts/闪记卡生成插件_4a31eac3) | action | 0.2.4 | 27 | 661 | 8 | 1 | 2026-01-28 |
+| 17 | [精读](https://openwebui.com/posts/精读_99830b0f) | action | 1.0.0 | 17 | 400 | 5 | 1 | 2026-01-08 |
+| 18 | [🚀 Open WebUI Prompt Plus: AI-Powered Prompt Manager](https://openwebui.com/posts/open_webui_prompt_plus_ai_powered_prompt_manager_s_15fa060e) | unknown |  | 0 | 1429 | 12 | 17 | 2026-01-28 |
+| 19 | [Review of Claude Haiku 4.5](https://openwebui.com/posts/review_of_claude_haiku_45_41b0db39) | unknown |  | 0 | 135 | 2 | 0 | 2026-01-14 |
+| 20 | [ 🛠️ Debug Open WebUI Plugins in Your Browser](https://openwebui.com/posts/debug_open_webui_plugins_in_your_browser_81bf7960) | unknown |  | 0 | 1392 | 14 | 9 | 2026-01-10 |

docs/extensions/index.md

@@ -0,0 +1,22 @@
+---
+title: Extensions
+---
+
+# Extensions
+
+Standalone frontend extensions to supercharge your Open WebUI.
+
+---
+
+## 🚀 Open WebUI Prompt Plus
+
+**An all-in-one prompt management suite for power users.**
+
+[Open WebUI Prompt Plus](https://github.com/Fu-Jie/open-webui-prompt-plus) elevates your experience with:
+
+- **🤖 AI-Powered Prompt Generator**: Turn natural language into structured prompts.
+- **⚡ Quick Insert Panel**: Spotlight-style search (`Cmd/Ctrl + Shift + P`).
+- **📂 Advanced Management**: Dynamic categories, favorites, and usage stats.
+- **📝 Native Variable Support**: Visual form rendering for template variables.
+
+[:fontawesome-brands-github: View on GitHub](https://github.com/Fu-Jie/open-webui-prompt-plus){ .md-button .md-button--primary }

docs/extensions/index.zh.md

@@ -0,0 +1,22 @@
+---
+title: 扩展 (Extensions)
+---
+
+# 扩展 (Extensions)
+
+Open WebUI 的独立前端增强扩展。
+
+---
+
+## 🚀 Open WebUI Prompt Plus
+
+**专为高级用户打造的一站式提示词管理套件。**
+
+[Open WebUI Prompt Plus](https://github.com/Fu-Jie/open-webui-prompt-plus) 通过以下功能提升您的体验：
+
+- **🤖 AI 提示词生成器**: 将自然语言转化为结构化提示词。
+- **⚡ 快速插入面板**: Spotlight 风格的快速搜索 (`Cmd/Ctrl + Shift + P`)。
+- **📂 高级管理**: 动态分类、收藏夹及使用统计。
+- **📝 原生变量支持**: 模板变量的可视化表单渲染。
+
+[:fontawesome-brands-github: 查看 GitHub](https://github.com/Fu-Jie/open-webui-prompt-plus){ .md-button .md-button--primary }

docs/index.md

@@ -25,7 +25,7 @@ hide:
 
 <div class="grid cards" markdown>
 
--   :material-puzzle:{ .lg .middle } **Plugin Center**
+- :material-puzzle:{ .lg .middle } **Plugin Center**
 
     ---
 
@@ -33,7 +33,7 @@ hide:
 
     [:octicons-arrow-right-24: Explore Plugins](plugins/index.md)
 
--   :material-message-text:{ .lg .middle } **Prompt Library**
+- :material-message-text:{ .lg .middle } **Prompt Library**
 
     ---
 
@@ -41,7 +41,7 @@ hide:
 
     [:octicons-arrow-right-24: Browse Prompts](prompts/index.md)
 
--   :material-tools:{ .lg .middle } **Enhancements**
+- :material-tools:{ .lg .middle } **Enhancements**
 
     ---
 
@@ -49,7 +49,15 @@ hide:
 
     [:octicons-arrow-right-24: View Guides](enhancements/index.md)
 
--   :material-book-open-page-variant:{ .lg .middle } **Development**
+- :material-rocket-launch:{ .lg .middle } **Extensions**
+
+    ---
+
+    Standalone frontend extensions to supercharge your Open WebUI interface.
+
+    [:octicons-arrow-right-24: Browse Extensions](extensions/index.md)
+
+- :material-book-open-page-variant:{ .lg .middle } **Development**
 
     ---
 
@@ -65,7 +73,7 @@ hide:
 
 <div class="grid cards" markdown>
 
--   :material-brain:{ .lg .middle } **Smart Mind Map**
+- :material-brain:{ .lg .middle } **Smart Mind Map**
 
     ---
 
@@ -73,7 +81,7 @@ hide:
 
     [:octicons-arrow-right-24: Learn More](plugins/actions/smart-mind-map.md)
 
--   :material-card-text:{ .lg .middle } **Flash Card**
+- :material-card-text:{ .lg .middle } **Flash Card**
 
     ---
 
@@ -81,7 +89,7 @@ hide:
 
     [:octicons-arrow-right-24: Learn More](plugins/actions/flash-card.md)
 
--   :material-arrow-collapse-vertical:{ .lg .middle } **Async Context Compression**
+- :material-arrow-collapse-vertical:{ .lg .middle } **Async Context Compression**
 
     ---
 

docs/index.zh.md

@@ -25,7 +25,7 @@ hide:
 
 <div class="grid cards" markdown>
 
--   :material-puzzle:{ .lg .middle } **插件中心**
+- :material-puzzle:{ .lg .middle } **插件中心**
 
     ---
 
@@ -33,7 +33,7 @@ hide:
 
     [:octicons-arrow-right-24: 探索插件](plugins/index.md)
 
--   :material-message-text:{ .lg .middle } **提示词库**
+- :material-message-text:{ .lg .middle } **提示词库**
 
     ---
 
@@ -41,7 +41,7 @@ hide:
 
     [:octicons-arrow-right-24: 浏览提示词](prompts/index.md)
 
--   :material-tools:{ .lg .middle } **增强功能**
+- :material-tools:{ .lg .middle } **增强功能**
 
     ---
 
@@ -49,7 +49,15 @@ hide:
 
     [:octicons-arrow-right-24: 查看指南](enhancements/index.md)
 
--   :material-book-open-page-variant:{ .lg .middle } **开发指南**
+- :material-rocket-launch:{ .lg .middle } **扩展 (Extensions)**
+
+    ---
+
+    独立的 OpenWebUI 前端增强扩展，全面提升交互体验。
+
+    [:octicons-arrow-right-24: 浏览扩展](extensions/index.md)
+
+- :material-book-open-page-variant:{ .lg .middle } **开发指南**
 
     ---
 
@@ -65,7 +73,7 @@ hide:
 
 <div class="grid cards" markdown>
 
--   :material-brain:{ .lg .middle } **智能思维导图**
+- :material-brain:{ .lg .middle } **智能思维导图**
 
     ---
 
@@ -73,7 +81,7 @@ hide:
 
     [:octicons-arrow-right-24: 了解更多](plugins/actions/smart-mind-map.md)
 
--   :material-card-text:{ .lg .middle } **Flash Card（闪记卡）**
+- :material-card-text:{ .lg .middle } **Flash Card（闪记卡）**
 
     ---
 
@@ -81,7 +89,7 @@ hide:
 
     [:octicons-arrow-right-24: 了解更多](plugins/actions/flash-card.md)
 
--   :material-arrow-collapse-vertical:{ .lg .middle } **异步上下文压缩**
+- :material-arrow-collapse-vertical:{ .lg .middle } **异步上下文压缩**
 
     ---
 

docs/plugins/actions/export-to-word.md

@@ -1,7 +1,7 @@
 # Export to Word
 
 <span class="category-badge action">Action</span>
-<span class="version-badge">v0.4.3</span>
+<span class="version-badge">v0.4.4</span>
 
 Export conversation to Word (.docx) with **syntax highlighting**, **native math equations**, **Mermaid diagrams**, **citations**, and **enhanced table formatting**.
 
@@ -53,11 +53,17 @@ You can configure the following settings via the **Valves** button in the plugin
 | `MATH_ENABLE` | Enable LaTeX math block conversion. | `True` |
 | `MATH_INLINE_DOLLAR_ENABLE` | Enable inline `$ ... $` math conversion. | `True` |
 
-## 🔥 What's New in v0.4.3
+## 🔥 What's New in v0.4.4
+
+- 🧹 **Content Cleanup**: Enhanced stripping of `<details>` blocks (often used for tool calls/thinking process) to ensure a clean final document.
+- 📄 **Standard Document Formatting**: Applied professional document formatting standards for titles and headings (centered title, bold, optimized font sizes and spacing), including GB/T compliance for Chinese content.
+- 🔠 **Font Rendering Fix**: Fixed an issue where CJK characters would fallback to MS Gothic in Word; now correctly uses the configured Asian font (e.g., SimSun).
+- ⚙️ **Title Alignment**: Added `TITLE_ALIGNMENT` valve to configure document title alignment (left, center, right).
 
 ### User-Level Configuration (UserValves)
 
 Users can override the following settings in their personal settings:
+
 - `TITLE_SOURCE`
 - `UI_LANGUAGE`
 - `FONT_LATIN`, `FONT_ASIAN`, `FONT_CODE`
@@ -120,4 +126,4 @@ Users can override the following settings in their personal settings:
 ## Source Code
 
 [:fontawesome-brands-github: View on GitHub](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/actions/export_to_docx){ .md-button }
-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.4.4 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

docs/plugins/actions/export-to-word.zh.md

@@ -1,7 +1,7 @@
 # Export to Word（导出为 Word）
 
 <span class="category-badge action">Action</span>
-<span class="version-badge">v0.4.3</span>
+<span class="version-badge">v0.4.4</span>
 
 将当前对话导出为完美格式的 Word 文档，支持**代码语法高亮**、**原生数学公式**、**Mermaid 图表**、**引用资料**以及**增强表格**渲染。
 
@@ -53,9 +53,17 @@ Export to Word 插件会把聊天消息从 Markdown 转成精致的 Word 文档
 | `启用数学公式` | 启用 LaTeX 数学公式块转换。 | `True` |
 | `启用行内公式` | 启用行内 `$ ... $` 数学公式转换。 | `True` |
 
+## 🔥 v0.4.4 更新内容
+
+- 🧹 **内容清理加强**: 增强了对 `<details>` 块（通常包含工具调用或思考过程）的清理，确保最终文档整洁。
+- 📄 **文档格式标准化**: 采用了专业的文档排版标准（兼容中文 GB/T 规范），标题居中加粗，各级标题使用标准字号和间距。
+- 🔠 **字体渲染修复**: 修复了 CJK 字符在 Word 中回退到 MS Gothic 的问题；现在正确使用配置的中文字体（例如宋体）。
+- ⚙️ **标题对齐配置**: 新增 `标题对齐方式` Valve，支持配置文档标题的对齐方式（左对齐、居中、右对齐）。
+
 ### 用户级配置 (UserValves)
 
 用户可以在个人设置中覆盖以下配置：
+
 - `文档标题来源`
 - `界面语言`
 - `英文字体`, `中文字体`, `代码字体`
@@ -117,4 +125,5 @@ Export to Word 插件会把聊天消息从 Markdown 转成精致的 Word 文档
 
 ## 源码
 
-[:fontawes**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)/tree/main/plugins/actions/export_to_docx){ .md-button }
+[:fontawesome-brands-github: View on GitHub](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/actions/export_to_docx){ .md-button }
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.4.4 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

docs/plugins/actions/index.md

@@ -17,7 +17,7 @@ Actions are interactive plugins that:
 
 <div class="grid cards" markdown>
 
--   :material-brain:{ .lg .middle } **Smart Mind Map**
+- :material-brain:{ .lg .middle } **Smart Mind Map**
 
     ---
 
@@ -27,7 +27,7 @@ Actions are interactive plugins that:
 
     [:octicons-arrow-right-24: Documentation](smart-mind-map.md)
 
--   :material-chart-bar:{ .lg .middle } **Smart Infographic**
+- :material-chart-bar:{ .lg .middle } **Smart Infographic**
 
     ---
 
@@ -37,7 +37,7 @@ Actions are interactive plugins that:
 
     [:octicons-arrow-right-24: Documentation](smart-infographic.md)
 
--   :material-card-text:{ .lg .middle } **Flash Card**
+- :material-card-text:{ .lg .middle } **Flash Card**
 
     ---
 
@@ -47,7 +47,7 @@ Actions are interactive plugins that:
 
     [:octicons-arrow-right-24: Documentation](flash-card.md)
 
--   :material-file-excel:{ .lg .middle } **Export to Excel**
+- :material-file-excel:{ .lg .middle } **Export to Excel**
 
     ---
 
@@ -57,17 +57,17 @@ Actions are interactive plugins that:
 
     [:octicons-arrow-right-24: Documentation](export-to-excel.md)
 
--   :material-file-word-box:{ .lg .middle } **Export to Word (Enhanced Formatting)**
+- :material-file-word-box:{ .lg .middle } **Export to Word (Enhanced Formatting)**
 
     ---
 
     Export the current conversation to a formatted Word doc with **syntax highlighting**, **native math equations**, **Mermaid diagrams**, **citations**, and **enhanced table formatting**.
-    
-    **Version:** 0.4.2
+
+    **Version:** 0.4.4
 
     [:octicons-arrow-right-24: Documentation](export-to-word.md)
 
--   :material-brain:{ .lg .middle } **Deep Dive**
+- :material-brain:{ .lg .middle } **Deep Dive**
 
     ---
 
@@ -77,8 +77,6 @@ Actions are interactive plugins that:
 
     [:octicons-arrow-right-24: Documentation](deep-dive.md)
 
-
-
 </div>
 
 ---

docs/plugins/actions/index.zh.md

@@ -17,7 +17,7 @@ Actions 是交互式插件，能够：
 
 <div class="grid cards" markdown>
 
--   :material-brain:{ .lg .middle } **Smart Mind Map**
+- :material-brain:{ .lg .middle } **Smart Mind Map**
 
     ---
 
@@ -27,7 +27,7 @@ Actions 是交互式插件，能够：
 
     [:octicons-arrow-right-24: 查看文档](smart-mind-map.md)
 
--   :material-chart-bar:{ .lg .middle } **Smart Infographic**
+- :material-chart-bar:{ .lg .middle } **Smart Infographic**
 
     ---
 
@@ -37,7 +37,7 @@ Actions 是交互式插件，能够：
 
     [:octicons-arrow-right-24: 查看文档](smart-infographic.md)
 
--   :material-card-text:{ .lg .middle } **Flash Card（闪记卡）**
+- :material-card-text:{ .lg .middle } **Flash Card（闪记卡）**
 
     ---
 
@@ -47,7 +47,7 @@ Actions 是交互式插件，能够：
 
     [:octicons-arrow-right-24: 查看文档](flash-card.md)
 
--   :material-file-excel:{ .lg .middle } **Export to Excel**
+- :material-file-excel:{ .lg .middle } **Export to Excel**
 
     ---
 
@@ -57,17 +57,17 @@ Actions 是交互式插件，能够：
 
     [:octicons-arrow-right-24: 查看文档](export-to-excel.md)
 
--   :material-file-word-box:{ .lg .middle } **Word 导出 (格式增强)**
+- :material-file-word-box:{ .lg .middle } **Word 导出 (格式增强)**
 
     ---
 
     将当前对话导出为完美格式的 Word 文档，支持**代码语法高亮**、**原生数学公式**、**Mermaid 图表**、**引用资料**以及**增强表格**渲染。
 
-    **版本：** 0.4.2
+    **版本：** 0.4.4
 
     [:octicons-arrow-right-24: 查看文档](export-to-word.md)
 
--   :material-brain:{ .lg .middle } **精读 (Deep Dive)**
+- :material-brain:{ .lg .middle } **精读 (Deep Dive)**
 
     ---
 
@@ -77,8 +77,6 @@ Actions 是交互式插件，能够：
 
     [:octicons-arrow-right-24: 查看文档](deep-dive.zh.md)
 
-
-
 </div>
 
 ---

docs/plugins/actions/smart-mind-map.md

@@ -1,7 +1,7 @@
 # Smart Mind Map
 
 <span class="category-badge action">Action</span>
-<span class="version-badge">v0.9.1</span>
+<span class="version-badge">v0.9.2</span>
 
 Intelligently analyzes text content and generates interactive mind maps for better visualization and understanding.
 
@@ -17,7 +17,7 @@ The Smart Mind Map plugin transforms text content into beautiful, interactive mi
 - :material-gesture-swipe: **Rich Controls**: Zoom, reset view, expand level selector (All/2/3) and fullscreen
 - :material-palette: **Theme Aware**: Auto-detects OpenWebUI light/dark theme with manual toggle
 - :material-download: **One-Click Export**: Download high-res PNG, copy SVG, or copy Markdown source
-- :material-translate: **Multi-language**: Adapts output language to the user context
+- :material-translate: **Multi-language**: Matches output language to the input text
 
 ---
 

docs/plugins/actions/smart-mind-map.zh.md

@@ -1,7 +1,7 @@
 # Smart Mind Map（智能思维导图）
 
 <span class="category-badge action">Action</span>
-<span class="version-badge">v0.9.1</span>
+<span class="version-badge">v0.9.2</span>
 
 智能分析文本内容，生成交互式思维导图，帮助你更直观地理解信息结构。
 
@@ -17,7 +17,7 @@ Smart Mind Map 会将文本转换成漂亮的交互式思维导图。插件会
 - :material-gesture-swipe: **丰富控制**：缩放/重置、展开层级（全部/2/3 级）与全屏
 - :material-palette: **主题感知**：自动检测 OpenWebUI 亮/暗色主题并支持手动切换
 - :material-download: **一键导出**：下载高分辨率 PNG、复制 SVG 或 Markdown
-- :material-translate: **多语言**：根据用户语言自动输出
+- :material-translate: **多语言**：输出语言与输入文本一致
 
 ---
 

docs/plugins/index.md

@@ -48,7 +48,7 @@ OpenWebUI supports four types of plugins, each serving a different purpose:
 
 | Plugin | Type | Description | Version |
 |--------|------|-------------|---------|
-| [Smart Mind Map](actions/smart-mind-map.md) | Action | Generate interactive mind maps from text | 0.9.1 |
+| [Smart Mind Map](actions/smart-mind-map.md) | Action | Generate interactive mind maps from text | 0.9.2 |
 | [Smart Infographic](actions/smart-infographic.md) | Action | Transform text into professional infographics | 1.4.9 |
 | [Flash Card](actions/flash-card.md) | Action | Create beautiful learning flashcards | 0.2.4 |
 | [Export to Excel](actions/export-to-excel.md) | Action | Export chat history to Excel files | 0.3.7 |

docs/plugins/index.zh.md

@@ -48,7 +48,7 @@ OpenWebUI 支持四种类型的插件，每种都有不同的用途：
 
 | 插件 | 类型 | 描述 | 版本 |
 |--------|------|-------------|---------|
-| [Smart Mind Map（智能思维导图）](actions/smart-mind-map.md) | Action | 从文本生成交互式思维导图 | 0.9.1 |
+| [Smart Mind Map（智能思维导图）](actions/smart-mind-map.md) | Action | 从文本生成交互式思维导图 | 0.9.2 |
 | [Smart Infographic（智能信息图）](actions/smart-infographic.md) | Action | 将文本转成专业信息图 | 1.4.9 |
 | [Flash Card（闪记卡）](actions/flash-card.md) | Action | 生成精美学习卡片 | 0.2.4 |
 | [Export to Excel（导出到 Excel）](actions/export-to-excel.md) | Action | 导出聊天记录为 Excel | 0.3.7 |

docs/plugins/pipes/github-copilot-sdk.md

@@ -1,26 +1,28 @@
 # GitHub Copilot SDK Pipe for OpenWebUI
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.2.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.3.0 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
 This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/open-webui) that allows you to use GitHub Copilot models (such as `gpt-5`, `gpt-5-mini`, `claude-sonnet-4.5`) directly within OpenWebUI. It is built upon the official [GitHub Copilot SDK for Python](https://github.com/github/copilot-sdk), providing a native integration experience.
 
-## 🚀 What's New (v0.2.3)
+> [!IMPORTANT]
+> **Active GitHub Copilot Subscription Required**
+> This plugin requires a valid GitHub Copilot subscription (Individual, Business, or Enterprise). It will verify your subscription status during authentication.
 
-* **🧩 Per-user Overrides**: Added user-level overrides for `REASONING_EFFORT`, `CLI_PATH`, `DEBUG`, `SHOW_THINKING`, and `MODEL_ID`.
-* **🧠 Thinking Output Reliability**: Thinking visibility now respects the user setting and is correctly passed into streaming.
-* **📝 Formatting Enforcement**: Added automatic formatting hints to ensure outputs are well-structured (paragraphs, lists).
+## 🚀 What's New (v0.3.0) - The Power of "Unified Ecosystem"
 
-## ✨ Core Features
+* **🔌 Zero-Config Tool Bridge**: Automatically transforms your existing OpenWebUI Functions (Tools) into Copilot-compatible tools. **Copilot now has total access to your entire WebUI toolset!**
+* **🔗 Dynamic MCP Discovery**: Seamlessly connects to MCP servers defined in **Admin Settings -> Connections**. No configuration files required—it just works.
+* **⚡ High-Performance Async Engine**: Background CLI updates and optimized event-driven streaming ensure lightning-fast responses without UI lag.
+* **🛡️ Robust Interoperability**: Advanced sanitization and dynamic Pydantic model generation ensure smooth integration even with complex third-party tools.
 
-* **🚀 Official SDK Integration**: Built on the official SDK for stability and reliability.
-* **🛠️ Custom Tools Support**: Example tools included (random number). Easy to extend with your own tools.
-* **💬 Multi-turn Conversation**: Automatically concatenates history context so Copilot understands your previous messages.
-* **🌊 Streaming Output**: Supports typewriter effect for fast responses.
-* **🖼️ Multimodal Support**: Supports image uploads, automatically converting them to attachments for Copilot (requires model support).
-* **🛠️ Zero-config Installation**: Automatically detects and downloads the GitHub Copilot CLI, ready to use out of the box.
-* **🔑 Secure Authentication**: Supports Fine-grained Personal Access Tokens for minimized permissions.
-* **🐛 Debug Mode**: Built-in detailed log output (browser console) for easy troubleshooting.
-* **⚠️ Single Node Only**: Due to local session storage, this plugin currently supports single-node OpenWebUI deployment or multi-node with sticky sessions enabled.
+## ✨ Key Capabilities
+
+* **🌉 The Ultimate Bridge**: The first and only plugin that creates a seamless bridge between **OpenWebUI Tools** and **GitHub Copilot SDK**.
+* **🚀 Official & Native**: Built directly on the official Python SDK, providing the most stable and authentic Copilot experience.
+* **🌊 Advanced Streaming (Thought Process)**: Supports full model reasoning/thinking display with typewriter effects.
+* **🖼️ Intelligent Multimodal**: Full support for images and attachments, enabling Copilot to "see" your workspace.
+* **🛠️ Effortless Setup**: Automatic CLI detection, version enforcement, and dependency management.
+* **🔑 Dual-Layer Security**: Supports secure OAuth flow for Chat and standard PAT for extended MCP capabilities.
 
 ## 📦 Installation & Usage
 
@@ -38,13 +40,11 @@ Find "GitHub Copilot" in the function list and click the **⚙️ (Valves)** ico
 
 | Parameter | Description | Default |
 | :--- | :--- | :--- |
-| **GH_TOKEN** | **(Required)** Your GitHub Token. | - |
-| **MODEL_ID** | The model name to use. Recommended `gpt-5-mini` or `gpt-5`. | `gpt-5-mini` |
-| **CLI_PATH** | Path to the Copilot CLI. Will download automatically if not found. | `/usr/local/bin/copilot` |
+| **GH_TOKEN** | **(Required)** GitHub Access Token (PAT or OAuth Token). Access to Chat. | - |
 | **DEBUG** | Whether to enable debug logs (output to browser console). | `False` |
 | **LOG_LEVEL** | Copilot CLI log level: none, error, warning, info, debug, all. | `error` |
 | **SHOW_THINKING** | Show model reasoning/thinking process (requires streaming + model support). | `True` |
-| **SHOW_WORKSPACE_INFO** | Show session workspace path and summary in debug mode. | `True` |
+| **COPILOT_CLI_VERSION** | Specific Copilot CLI version to install/enforce. | `0.0.405` |
 | **EXCLUDE_KEYWORDS** | Exclude models containing these keywords (comma separated). | - |
 | **WORKSPACE_DIR** | Restricted workspace directory for file operations. | - |
 | **INFINITE_SESSION** | Enable Infinite Sessions (automatic context compaction). | `True` |
@@ -52,10 +52,10 @@ Find "GitHub Copilot" in the function list and click the **⚙️ (Valves)** ico
 | **BUFFER_THRESHOLD** | Buffer exhaustion threshold (0.0-1.0). | `0.95` |
 | **TIMEOUT** | Timeout for each stream chunk (seconds). | `300` |
 | **CUSTOM_ENV_VARS** | Custom environment variables (JSON format). | - |
-| **REASONING_EFFORT** | Reasoning effort level: low, medium, high. `xhigh` is supported for gpt-5.2-codex. | `medium` |
+| **REASONING_EFFORT** | Reasoning effort level: low, medium, high. `xhigh` is supported for some models. | `medium` |
 | **ENFORCE_FORMATTING** | Add formatting instructions to system prompt for better readability. | `True` |
-| **ENABLE_TOOLS** | Enable custom tools (example: random number). | `False` |
-| **AVAILABLE_TOOLS** | Available tools: 'all' or comma-separated list. | `all` |
+| **ENABLE_MCP_SERVER** | Enable Direct MCP Client connection (Recommended). | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | Enable OpenWebUI Tools (includes defined and server tools). | `True` |
 
 #### User Valves (per-user overrides)
 
@@ -63,37 +63,26 @@ These optional settings can be set per user (overrides global Valves):
 
 | Parameter | Description | Default |
 | :--- | :--- | :--- |
+| **GH_TOKEN** | Personal GitHub Token (overrides global setting). | - |
 | **REASONING_EFFORT** | Reasoning effort level (low/medium/high/xhigh). | - |
-| **CLI_PATH** | Custom path to Copilot CLI. | - |
 | **DEBUG** | Enable technical debug logs. | `False` |
-| **SHOW_THINKING** | Show model reasoning/thinking process (requires streaming + model support). | `True` |
-| **MODEL_ID** | Custom model ID. | - |
+| **SHOW_THINKING** | Show model reasoning/thinking process. | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | Enable OpenWebUI Tools (overrides global). | `True` |
+| **ENABLE_MCP_SERVER** | Enable MCP server loading (overrides global). | `True` |
+| **ENFORCE_FORMATTING** | Enforce formatting guidelines (overrides global). | `True` |
 
-### 3. Using Custom Tools (🆕 Optional)
+### 3. Get Token
 
-This pipe includes **1 example tool** to demonstrate tool calling:
+To use GitHub Copilot, you need a GitHub Personal Access Token (PAT) with appropriate permissions.
 
-* **🎲 generate_random_number**: Generate random integers
-
-**To enable:**
-
-1. Set `ENABLE_TOOLS: true` in Valves
-2. Try: "Give me a random number"
-
-**📚 For detailed usage and creating your own tools, see [plugins/pipes/github-copilot-sdk/TOOLS_USAGE.md](plugins/pipes/github-copilot-sdk/TOOLS_USAGE.md)**
-
-### 4. Get GH_TOKEN
-
-For security, it is recommended to use a **Fine-grained Personal Access Token**:
+**Steps to generate your token:**
 
 1. Visit [GitHub Token Settings](https://github.com/settings/tokens?type=beta).
-2. Click **Generate new token**.
-3. **Repository access**: Select **Public repositories** (Required to access Copilot permissions).
+2. Click **Generate new token (fine-grained)**.
+3. **Repository access**: Select **Public Repositories** (simplest) or **All repositories**.
 4. **Permissions**:
-
-* Click **Account permissions**.
-* Find **Copilot Requests** (It defaults to **Read-only**, no selection needed).
-
+    * If you chose **All repositories**, you must click **Account permissions**.
+    * Find **Copilot Requests**, and select **Access**.
 5. Generate and copy the Token.
 
 ## 📋 Dependencies
@@ -103,17 +92,12 @@ This Pipe will automatically attempt to install the following dependencies:
 * `github-copilot-sdk` (Python package)
 * `github-copilot-cli` (Binary file, installed via official script)
 
-## ⚠️ FAQ
+## Troubleshooting ❓
 
-* **Stuck on "Waiting..."**:
-  * Check if `GH_TOKEN` is correct and has `Copilot Requests` permission.
-* **Images not recognized**:
+* **Images and Multimodal Usage**:
   * Ensure `MODEL_ID` is a model that supports multimodal input.
 * **Thinking not shown**:
   * Ensure **streaming is enabled** and the selected model supports reasoning output.
-* **CLI Installation Failed**:
-  * Ensure the OpenWebUI container has internet access.
-  * You can manually download the CLI and specify `CLI_PATH` in Valves.
 
 ## 📄 License
 

docs/plugins/pipes/github-copilot-sdk.zh.md

@@ -1,26 +1,28 @@
 # GitHub Copilot SDK 官方管道
 
-**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.2.3 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.3.0 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
 这是一个用于 [OpenWebUI](https://github.com/open-webui/open-webui) 的高级 Pipe 函数，允许你直接在 OpenWebUI 中使用 GitHub Copilot 模型（如 `gpt-5`, `gpt-5-mini`, `claude-sonnet-4.5`）。它基于官方 [GitHub Copilot SDK for Python](https://github.com/github/copilot-sdk) 构建，提供了原生级的集成体验。
 
-## 🚀 最新特性 (v0.2.3)
+> [!IMPORTANT]
+> **需 GitHub Copilot 订阅**
+> 本插件需要有效的 GitHub Copilot 订阅（个人版、商业版或企业版）。插件将在认证阶段验证您的订阅状态。
 
-* **🧩 用户级覆盖**：新增 `REASONING_EFFORT`、`CLI_PATH`、`DEBUG`、`SHOW_THINKING`、`MODEL_ID` 的用户级覆盖。
-* **🧠 思考输出可靠性**：思考显示会遵循用户设置，并正确传递到流式输出中。
-* **📝 格式化输出增强**：自动优化输出格式（段落、列表），并解决了在某些界面下显示过于紧凑的问题。
+## 🚀 最新特性 (v0.3.0) - “统一生态”的力量
 
-## ✨ 核心特性
+* **🔌 零配置工具桥接 (Unified Tool Bridge)**: 自动将您现有的 OpenWebUI Functions (工具) 转换为 Copilot 兼容工具。**Copilot 现在可以无缝调用您手头所有的 WebUI 工具！**
+* **🔗 动态 MCP 自动发现**: 直接联动 OpenWebUI **管理面板 -> 连接**。无需编写任何配置文件，即插即用，瞬间扩展 Copilot 能力边界。
+* **⚡ 高性能异步引擎**: 异步 CLI 更新检查与高度优化的事件驱动流式处理，确保对话毫秒级响应。
+* **🛡️ 卓越的兼容性**: 独创的动态 Pydantic 模型生成技术，确保复杂工具参数在 Copilot 端也能得到精准验证。
 
-* **🚀 官方 SDK 集成**：基于官方 SDK，稳定可靠。
-* **🛠️ 自定义工具支持**：内置示例工具（随机数）。易于扩展自定义工具。
-* **💬 多轮对话支持**：自动拼接历史上下文，Copilot 能理解你的前文。
-* **🌊 流式输出 (Streaming)**：支持打字机效果，响应迅速。
-* **🖼️ 多模态支持**：支持上传图片，自动转换为附件发送给 Copilot（需模型支持）。
-* **🛠️ 零配置安装**：自动检测并下载 GitHub Copilot CLI，开箱即用。
-* **🔑 安全认证**：支持 Fine-grained Personal Access Tokens，权限最小化。
-* **🐛 调试模式**：内置详细的日志输出（浏览器控制台），方便排查问题。
-* **⚠️ 仅支持单节点**：由于会话状态存储在本地，本插件目前仅支持 OpenWebUI 单节点部署，或开启了会话粘性 (Sticky Session) 的多节点集群。
+## ✨ 核心能力
+
+* **🌉 强大的生态桥接**: 首个且唯一完美打通 **OpenWebUI Tools** 与 **GitHub Copilot SDK** 的插件。
+* **🚀 官方原生产体验**: 基于官方 Python SDK 构建，提供最稳定、最纯正的 Copilot 交互体验。
+* **🌊 深度推理展示**: 完整支持模型思考过程 (Thinking Process) 的流式渲染。
+* **🖼️ 智能多模态**: 支持图像识别与附件上传，让 Copilot 拥有视觉能力。
+* **🛠️ 极简部署流程**: 自动检测环境、自动下载 CLI、自动管理依赖，全自动化开箱即用。
+* **🔑 安全认证体系**: 完美支持 OAuth 授权与 PAT 模式，兼顾便捷与安全性。
 
 ## 📦 安装与使用
 
@@ -38,24 +40,22 @@
 
 | 参数 | 说明 | 默认值 |
 | :--- | :--- | :--- |
-| **GH_TOKEN** | **(必填)** 你的 GitHub Token。 | - |
-| **MODEL_ID** | 使用的模型名称。推荐 `gpt-5-mini` 或 `gpt-5`。 | `gpt-5-mini` |
-| **CLI_PATH** | Copilot CLI 的路径。如果未找到会自动下载。 | `/usr/local/bin/copilot` |
+| **GH_TOKEN** | **(必填)** GitHub 访问令牌 (PAT 或 OAuth Token)。用于聊天。 | - |
 | **DEBUG** | 是否开启调试日志（输出到浏览器控制台）。 | `False` |
 | **LOG_LEVEL** | Copilot CLI 日志级别: none, error, warning, info, debug, all。 | `error` |
 | **SHOW_THINKING** | 是否显示模型推理/思考过程（需开启流式 + 模型支持）。 | `True` |
-| **SHOW_WORKSPACE_INFO** | 在调试模式下显示会话工作空间路径和摘要。 | `True` |
-| **EXCLUDE_KEYWORDS** | 排除包含这些关键词的模型 (逗号分隔)。 | - |
-| **WORKSPACE_DIR** | 文件操作的受限工作目录。 | - |
-| **INFINITE_SESSION** | 启用无限会话 (自动上下文压缩)。 | `True` |
+| **COPILOT_CLI_VERSION** | 指定安装/强制使用的 Copilot CLI 版本。 | `0.0.405` |
+| **EXCLUDE_KEYWORDS** | 排除包含这些关键词的模型（逗号分隔）。 | - |
+| **WORKSPACE_DIR** | 文件操作的受限工作区目录。 | - |
+| **INFINITE_SESSION** | 启用无限会话（自动上下文压缩）。 | `True` |
 | **COMPACTION_THRESHOLD** | 后台压缩阈值 (0.0-1.0)。 | `0.8` |
-| **BUFFER_THRESHOLD** | 缓冲耗尽阈值 (0.0-1.0)。 | `0.95` |
-| **TIMEOUT** | 流式数据块超时时间 (秒)。 | `300` |
+| **BUFFER_THRESHOLD** | 缓冲区耗尽阈值 (0.0-1.0)。 | `0.95` |
+| **TIMEOUT** | 每个流式分块超时（秒）。 | `300` |
 | **CUSTOM_ENV_VARS** | 自定义环境变量 (JSON 格式)。 | - |
-| **ENABLE_TOOLS** | 启用自定义工具 (示例：随机数)。 | `False` |
-| **AVAILABLE_TOOLS** | 可用工具: 'all' 或逗号分隔列表。 | `all` |
-| **REASONING_EFFORT** | 推理强度级别：low, medium, high。`gpt-5.2-codex`额外支持`xhigh`。 | `medium` |
-| **ENFORCE_FORMATTING** | 是否强制添加格式化指导，以提高输出可读性。 | `True` |
+| **REASONING_EFFORT** | 推理强度级别: low, medium, high. `xhigh` 仅部分模型支持。 | `medium` |
+| **ENFORCE_FORMATTING** | 在系统提示词中添加格式化指导。 | `True` |
+| **ENABLE_MCP_SERVER** | 启用直接 MCP 客户端连接 (建议)。 | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | 启用 OpenWebUI 工具 (包括自定义和服务器工具)。 | `True` |
 
 #### 用户 Valves（按用户覆盖）
 
@@ -63,38 +63,27 @@
 
 | 参数 | 说明 | 默认值 |
 | :--- | :--- | :--- |
+| **GH_TOKEN** | 个人 GitHub Token（覆盖全局设置）。 | - |
 | **REASONING_EFFORT** | 推理强度级别（low/medium/high/xhigh）。 | - |
-| **CLI_PATH** | 自定义 Copilot CLI 路径。 | - |
 | **DEBUG** | 是否启用技术调试日志。 | `False` |
-| **SHOW_THINKING** | 是否显示思考过程（需开启流式 + 模型支持）。 | `True` |
-| **MODEL_ID** | 自定义模型 ID。 | - |
+| **SHOW_THINKING** | 是否显示思考过程。 | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | 启用 OpenWebUI 工具（覆盖全局设置）。 | `True` |
+| **ENABLE_MCP_SERVER** | 启用动态 MCP 服务器加载（覆盖全局设置）。 | `True` |
+| **ENFORCE_FORMATTING** | 强制启用格式化指导（覆盖全局设置）。 | `True` |
 
-### 3. 使用自定义工具 (🆕 可选)
+### 3. 获取 Token
 
-本 Pipe 内置了 **1 个示例工具**来展示工具调用功能：
+要使用 GitHub Copilot，您需要一个具有适当权限的 GitHub 个人访问令牌 (PAT)。
 
-* **🎲 generate_random_number**：生成随机整数
+**获取步骤：**
 
-**启用方法：**
-
-1. 在 Valves 中设置 `ENABLE_TOOLS: true`
-2. 尝试问：“给我一个随机数”
-
-**📚 详细使用说明和创建自定义工具，请参阅 [plugins/pipes/github-copilot-sdk/TOOLS_USAGE.md](plugins/pipes/github-copilot-sdk/TOOLS_USAGE.md)**
-
-### 4. 获取 GH_TOKEN
-
-为了安全起见，推荐使用 **Fine-grained Personal Access Token**：
-
-1. 访问 [GitHub Token Settings](https://github.com/settings/tokens?type=beta)。
-2. 点击 **Generate new token**。
-3. **Repository access**: 选择 **Public repositories** (必须选择此项才能看到 Copilot 权限)。
+1. 访问 [GitHub 令牌设置](https://github.com/settings/tokens?type=beta)。
+2. 点击 **Generate new token (fine-grained)**。
+3. **Repository access**: 选择 **Public Repositories** (最简单) 或 **All repositories**。
 4. **Permissions**:
-
-* 点击 **Account permissions**。
-* 找到 **Copilot Requests** (默认即为 **Read-only**，无需手动修改)。
-
-5. 生成并复制 Token。
+    * 如果您选择了 **All repositories**，则必须点击 **Account permissions**。
+    * 找到 **Copilot Requests**，选择 **Access**。
+5. 生成并复制令牌。
 
 ## 📋 依赖说明
 
@@ -103,17 +92,12 @@
 * `github-copilot-sdk` (Python 包)
 * `github-copilot-cli` (二进制文件，通过官方脚本安装)
 
-## ⚠️ 常见问题
+## 故障排除 (Troubleshooting) ❓
 
-* **一直显示 "Waiting..."**：
-  * 检查 `GH_TOKEN` 是否正确且拥有 `Copilot Requests` 权限。
-* **图片无法识别**：
+* **图片及多模态使用说明**：
   * 确保 `MODEL_ID` 是支持多模态的模型。
 * **看不到思考过程**：
   * 确认已开启**流式输出**，且所选模型支持推理输出。
-* **CLI 安装失败**：
-  * 确保 OpenWebUI 容器有外网访问权限。
-  * 你可以手动下载 CLI 并挂载到容器中，然后在 Valves 中指定 `CLI_PATH`。
 
 ## 📄 许可证
 

docs/plugins/pipes/index.md

@@ -15,7 +15,7 @@ Pipes allow you to:
 
 ## Available Pipe Plugins
 
-- [GitHub Copilot SDK](github-copilot-sdk.md) (v0.1.1) - Official GitHub Copilot SDK integration. Supports dynamic models, multi-turn conversation, streaming, multimodal input, and infinite sessions.
+- [GitHub Copilot SDK](github-copilot-sdk.md) (v0.3.0) - Official GitHub Copilot SDK integration. Features **zero-config OpenWebUI Tool Bridge** and **dynamic MCP discovery**. Supports streaming, multimodal, and infinite sessions.
 
 ---
 

docs/plugins/pipes/index.zh.md

@@ -15,7 +15,7 @@ Pipes 可以用于：
 
 ## 可用的 Pipe 插件
 
-- [GitHub Copilot SDK](github-copilot-sdk.zh.md) (v0.1.1) - GitHub Copilot SDK 官方集成。支持动态模型、多轮对话、流式输出、图片输入及无限会话。
+- [GitHub Copilot SDK](github-copilot-sdk.zh.md) (v0.3.0) - GitHub Copilot SDK 官方集成。**零配置工具桥接**与**动态 MCP 发现**。支持流式输出、多模态及无限会话。
 
 ---
 

plugins/actions/deep-dive/README.md

@@ -39,6 +39,10 @@ A comprehensive thinking lens that dives deep into any content - from context to
 | **Clear Previous HTML (CLEAR_PREVIOUS_HTML)** | `True` | Whether to clear previous plugin results. |
 | **Message Count (MESSAGE_COUNT)** | `1` | Number of recent messages to analyze. |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## 🌗 Theme Support
 
 The plugin automatically detects and adapts to OpenWebUI's theme settings:
@@ -48,7 +52,7 @@ The plugin automatically detects and adapts to OpenWebUI's theme settings:
   2. Parent document `html/body` class or `data-theme` attribute
   3. System preference via `prefers-color-scheme: dark`
 
-- **Requirements**: For best results, enable **iframe Sandbox Allow Same Origin** in OpenWebUI: 
+- **Requirements**: For best results, enable **iframe Sandbox Allow Same Origin** in OpenWebUI:
   - Go to **Settings** → **Interface** → **Artifacts** → Check **iframe Sandbox Allow Same Origin**
 
 ## 🎨 Visual Preview
@@ -88,3 +92,7 @@ The plugin generates a structured thinking timeline:
 - **Debug Logs**: Enable `SHOW_STATUS` in Valves to see progress updates.
 - **Error Messages**: If you see an error, please copy the full error message and report it.
 - **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/deep-dive/README_CN.md

@@ -39,6 +39,10 @@
 | **清除旧 HTML (CLEAR_PREVIOUS_HTML)** | `True` | 是否清除之前的插件结果。 |
 | **消息数量 (MESSAGE_COUNT)** | `1` | 要分析的最近消息数量。 |
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
 ## 🌗 主题支持
 
 插件会自动检测并适配 OpenWebUI 的主题设置：
@@ -88,3 +92,7 @@
 - **调试日志**: 在 Valves 中启用 `SHOW_STATUS` 以查看进度更新。
 - **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
 - **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/export_to_docx/README.md

@@ -1,14 +1,15 @@
 # 📝 Export to Word (Enhanced)
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.4 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
 Export conversation to Word (.docx) with **syntax highlighting**, **native math equations**, **Mermaid diagrams**, **citations**, and **enhanced table formatting**.
 
-## 🔥 What's New in v0.4.3
+## 🔥 What's New in v0.4.4
 
-- ✨ **S3 Object Storage Support**: Direct access to images stored in S3/MinIO via boto3, bypassing API layer for faster exports.
-- 🔧 **Multi-level File Fallback**: 6-level fallback mechanism for file retrieval (DB → S3 → Local → URL → API → Attributes).
-- 🛡️ **Improved Error Handling**: Better logging and error messages for file retrieval failures.
+- 🧹 **Content Cleanup**: Enhanced stripping of `<details>` blocks (often used for tool calls/thinking process) to ensure a clean final document.
+- 📄 **Standard Document Formatting**: Applied professional document formatting standards for titles and headings (centered title, bold, optimized font sizes and spacing), including GB/T compliance for Chinese content.
+- 🔠 **Font Rendering Fix**: Fixed an issue where CJK characters would fallback to MS Gothic in Word; now correctly uses the configured Asian font (e.g., SimSun).
+- ⚙️ **Title Alignment**: Added `TITLE_ALIGNMENT` valve to configure document title alignment (left, center, right).
 
 ## ✨ Key Features
 
@@ -44,6 +45,10 @@ Export conversation to Word (.docx) with **syntax highlighting**, **native math
 | **Mermaid PNG Scale** | `3.0` | Resolution multiplier for Mermaid images |
 | **Math Enable** | `True` | Enable LaTeX math conversion |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## 🛠️ Supported Markdown Syntax
 
 | Syntax | Word Result |
@@ -71,25 +76,13 @@ Export conversation to Word (.docx) with **syntax highlighting**, **native math
 - `latex2mathml` - LaTeX to MathML conversion
 - `mathml2omml` - MathML to Office Math (OMML) conversion
 
-## 📝 Changelog
-
-### v0.4.3
-- **S3 Object Storage**: Direct S3/MinIO access via boto3 for faster image retrieval.
-- **6-Level Fallback**: Robust file retrieval: DB → S3 → Local → URL → API → Attributes.
-- **Better Logging**: Improved error messages for debugging file access issues.
-
-### v0.4.1
-- **Chinese Parameter Names**: Localized configuration names for Chinese version.
-
-### v0.4.0
-- **Multi-language Support**: UI language switching (English/Chinese).
-- **Font & Style Configuration**: Customizable fonts and table colors.
-- **Mermaid Enhancements**: Hybrid SVG+PNG rendering, background color config.
-- **Performance**: Real-time progress updates for large exports.
-
 ## Troubleshooting ❓
 
 - **Plugin not working?**: Check if the filter/action is enabled in the model settings.
 - **Debug Logs**: Check the browser console (F12) for detailed logs if available.
 - **Error Messages**: If you see an error, please copy the full error message and report it.
 - **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## 📝 Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/export_to_docx/README_CN.md

@@ -1,14 +1,15 @@
 # 📝 导出为 Word (增强版)
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.4 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
 将对话导出为 Word (.docx)，支持**代码语法高亮**、**原生数学公式**、**Mermaid 图表**、**引用参考**和**增强表格格式**。
 
-## 🔥 v0.4.3 更新内容
+## 🔥 v0.4.4 更新内容
 
-- ✨ **S3 对象存储支持**: 通过 boto3 直连 S3/MinIO，绕过 API 层，导出速度更快。
-- 🔧 **多级文件回退**: 6 级文件获取机制（数据库 → S3 → 本地 → URL → API → 属性）。
-- 🛡️ **错误处理优化**: 更完善的日志记录和错误提示，便于调试文件访问问题。
+- 🧹 **内容清理加强**: 增强了对 `<details>` 块（通常包含工具调用或思考过程）的清理，确保最终文档整洁。
+- 📄 **文档格式标准化**: 采用了专业的文档排版标准（兼容中文 GB/T 规范），标题居中加粗，各级标题使用标准字号和间距。
+- 🔠 **字体渲染修复**: 修复了 CJK 字符在 Word 中回退到 MS Gothic 的问题；现在正确使用配置的中文字体（例如宋体）。
+- ⚙️ **标题对齐配置**: 新增 `标题对齐方式` Valve，支持配置文档标题的对齐方式（左对齐、居中、右对齐）。
 
 ## ✨ 核心特性
 
@@ -44,6 +45,10 @@
 | **Mermaid_PNG缩放比例** | `3.0` | Mermaid 图片分辨率倍数 |
 | **启用数学公式** | `True` | 启用 LaTeX 公式转换 |
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
 ## 🛠️ 支持的 Markdown 语法
 
 | 语法 | Word 效果 |
@@ -71,25 +76,13 @@
 - `latex2mathml` - LaTeX 转 MathML
 - `mathml2omml` - MathML 转 Office Math (OMML)
 
-## 📝 更新日志
-
-### v0.4.3
-- **S3 对象存储**: 通过 boto3 直连 S3/MinIO，图片获取速度更快。
-- **6 级回退机制**: 稳健的文件获取：数据库 → S3 → 本地 → URL → API → 属性。
-- **日志优化**: 改进错误提示，便于调试文件访问问题。
-
-### v0.4.1
-- **中文参数名**: 配置项名称和描述全部汉化。
-
-### v0.4.0
-- **多语言支持**: 界面语言切换（中文/英文）。
-- **字体与样式配置**: 支持自定义中英文字体、代码字体以及表格颜色。
-- **Mermaid 增强**: 混合 SVG+PNG 渲染，支持背景色配置。
-- **性能优化**: 导出大型文档时提供实时进度反馈。
-
 ## 故障排除 (Troubleshooting) ❓
 
 - **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
 - **调试日志**: 请查看浏览器控制台 (F12) 获取详细日志（如果可用）。
 - **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
 - **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## 📝 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/export_to_docx/export_to_word.py

@@ -1,9 +1,9 @@
 """
-title: Export to Word (Enhanced)
+title: Export to Word Enhanced
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui
-version: 0.4.3
+version: 0.4.4
 openwebui_id: fca6a315-2a45-42cc-8c96-55cbc85f87f2
 icon_url: data:image/svg+xml;base64,PHN2ZwogIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIKICB3aWR0aD0iMjQiCiAgaGVpZ2h0PSIyNCIKICB2aWV3Qm94PSIwIDAgMjQgMjQiCiAgZmlsbD0ibm9uZSIKICBzdHJva2U9ImN1cnJlbnRDb2xvciIKICBzdHJva2Utd2lkdGg9IjIiCiAgc3Ryb2tlLWxpbmVjYXA9InJvdW5kIgogIHN0cm9rZS1saW5lam9pbj0icm91bmQiCj4KICA8cGF0aCBkPSJNNiAyMmEyIDIgMCAwIDEtMi0yVjRhMiAyIDAgMCAxIDItMmg4YTIuNCAyLjQgMCAwIDEgMS43MDQuNzA2bDMuNTg4IDMuNTg4QTIuNCAyLjQgMCAwIDEgMjAgOHYxMmEyIDIgMCAwIDEtMiAyeiIgLz4KICA8cGF0aCBkPSJNMTQgMnY1YTEgMSAwIDAgMCAxIDFoNSIgLz4KICA8cGF0aCBkPSJNMTAgOUg4IiAvPgogIDxwYXRoIGQ9Ik0xNiAxM0g4IiAvPgogIDxwYXRoIGQ9Ik0xNiAxN0g4IiAvPgo8L3N2Zz4K
 requirements: python-docx, Pygments, latex2mathml, mathml2omml
@@ -101,9 +101,8 @@ _TRANSPARENT_1PX_PNG = base64.b64decode(
 _ASVG_NS = "http://schemas.microsoft.com/office/drawing/2016/SVG/main"
 nsmap.setdefault("asvg", _ASVG_NS)
 
-_REASONING_DETAILS_RE = re.compile(
-    r"<details\b[^>]*\btype\s*=\s*(?:\"reasoning\"|'reasoning'|reasoning)[^>]*>.*?</details\s*>",
-    re.IGNORECASE | re.DOTALL,
+_ALL_DETAILS_RE = re.compile(
+    r"<details\b[^>]*>.*?</details\s*>", re.IGNORECASE | re.DOTALL
 )
 _THINK_RE = re.compile(r"<think\b[^>]*>.*?</think\s*>", re.IGNORECASE | re.DOTALL)
 _ANALYSIS_RE = re.compile(
@@ -178,6 +177,12 @@ class Action:
             description="Font for code blocks and inline code (e.g., 'Consolas', 'Courier New', 'Monaco')",
         )
 
+        # Title alignment
+        TITLE_ALIGNMENT: str = Field(
+            default="center",
+            description="Title alignment: 'left', 'center', or 'right'",
+        )
+
         # Table styling
         TABLE_HEADER_COLOR: str = Field(
             default="F2F2F2",
@@ -242,60 +247,60 @@ class Action:
         )
 
     class UserValves(BaseModel):
-        TITLE_SOURCE: str = Field(
-            default="chat_title",
+        TITLE_SOURCE: Optional[str] = Field(
+            default=None,
             description="Title Source: 'chat_title' (Chat Title), 'ai_generated' (AI Generated), 'markdown_title' (Markdown Title)",
         )
-        UI_LANGUAGE: str = Field(
-            default="en",
+        UI_LANGUAGE: Optional[str] = Field(
+            default=None,
             description="UI language for export messages. Options: 'en' (English), 'zh' (Chinese)",
         )
-        FONT_LATIN: str = Field(
-            default="Times New Roman",
+        FONT_LATIN: Optional[str] = Field(
+            default=None,
             description="Font for Latin characters (e.g., 'Times New Roman', 'Calibri', 'Arial')",
         )
-        FONT_ASIAN: str = Field(
-            default="SimSun",
+        FONT_ASIAN: Optional[str] = Field(
+            default=None,
             description="Font for Asian characters (e.g., 'SimSun', 'Microsoft YaHei', 'PingFang SC')",
         )
-        FONT_CODE: str = Field(
-            default="Consolas",
+        FONT_CODE: Optional[str] = Field(
+            default=None,
             description="Font for code blocks and inline code (e.g., 'Consolas', 'Courier New', 'Monaco')",
         )
-        TABLE_HEADER_COLOR: str = Field(
-            default="F2F2F2",
+        TABLE_HEADER_COLOR: Optional[str] = Field(
+            default=None,
             description="Table header background color (hex, without #)",
         )
-        TABLE_ZEBRA_COLOR: str = Field(
-            default="FBFBFB",
+        TABLE_ZEBRA_COLOR: Optional[str] = Field(
+            default=None,
             description="Table zebra stripe background color for alternate rows (hex, without #)",
         )
-        MERMAID_PNG_SCALE: float = Field(
-            default=3.0,
+        MERMAID_PNG_SCALE: Optional[float] = Field(
+            default=None,
             description="PNG render resolution multiplier (higher = clearer, larger file)",
         )
-        MERMAID_DISPLAY_SCALE: float = Field(
-            default=1.0,
+        MERMAID_DISPLAY_SCALE: Optional[float] = Field(
+            default=None,
             description="Diagram width relative to available page width (<=1 recommended)",
         )
-        MERMAID_OPTIMIZE_LAYOUT: bool = Field(
-            default=False,
+        MERMAID_OPTIMIZE_LAYOUT: Optional[bool] = Field(
+            default=None,
             description="Optimize Mermaid layout: convert LR to TD for graph/flowchart",
         )
-        MERMAID_BACKGROUND: str = Field(
-            default="",
+        MERMAID_BACKGROUND: Optional[str] = Field(
+            default=None,
             description="Mermaid background color. Empty = transparent (recommended for Word dark mode). Used only for optional PNG fill.",
         )
-        MERMAID_CAPTIONS_ENABLE: bool = Field(
-            default=True,
+        MERMAID_CAPTIONS_ENABLE: Optional[bool] = Field(
+            default=None,
             description="Add figure captions under Mermaid images/charts",
         )
-        MATH_ENABLE: bool = Field(
-            default=True,
+        MATH_ENABLE: Optional[bool] = Field(
+            default=None,
             description="Enable LaTeX math block conversion (\\\\[...\\\\] and $$...$$) into Word equations",
         )
-        MATH_INLINE_DOLLAR_ENABLE: bool = Field(
-            default=True,
+        MATH_INLINE_DOLLAR_ENABLE: Optional[bool] = Field(
+            default=None,
             description="Enable inline $...$ math conversion into Word equations (conservative parsing to reduce false positives)",
         )
 
@@ -449,13 +454,21 @@ class Action:
             user_id = __user__.get("id", "unknown_user")
 
         # Apply UserValves if present
-        if __user__ and "valves" in __user__:
-            # Update self.valves with user-specific values
-            # Note: This assumes per-request instantiation or that we are okay with modifying the singleton.
-            # Given the plugin architecture, we'll update it for this execution.
-            for key, value in __user__["valves"].model_dump().items():
-                if hasattr(self.valves, key):
-                    setattr(self.valves, key, value)
+        if __user__:
+            # Robustly parse UserValves whether it's a dict or Pydantic model
+            raw_valves = __user__.get("valves", {})
+            if isinstance(raw_valves, self.UserValves):
+                user_valves = raw_valves
+            elif isinstance(raw_valves, dict):
+                user_valves = self.UserValves(**raw_valves)
+            else:
+                user_valves = None
+
+            if user_valves:
+                for key, value in user_valves.model_dump(exclude_unset=True).items():
+                    # Only override if the value is not None (and explicitly set)
+                    if hasattr(self.valves, key) and value is not None:
+                        setattr(self.valves, key, value)
 
         # Get user language from Valves configuration
         self._user_lang = self._get_lang_key(self.valves.UI_LANGUAGE)
@@ -492,6 +505,37 @@ class Action:
             try:
                 message_content = last_assistant_message["content"]
                 if isinstance(message_content, str):
+                    if __event_emitter__ and self.valves.SHOW_DEBUG_LOG:
+                        debug_data = {}
+                        for name, regex in [
+                            ("Details Block", _ALL_DETAILS_RE),
+                            ("Think Block", _THINK_RE),
+                            ("Analysis Block", _ANALYSIS_RE),
+                        ]:
+                            matches = regex.findall(message_content)
+                            if matches:
+                                debug_data[name] = [
+                                    (m[:200] + "...") if len(m) > 200 else m
+                                    for m in matches
+                                ]
+                        if debug_data:
+                            await self._emit_debug_log(
+                                __event_emitter__,
+                                "Context Stripping Analysis",
+                                debug_data,
+                            )
+
+                        # Log font configuration
+                        await self._emit_debug_log(
+                            __event_emitter__,
+                            "Font Configuration",
+                            {
+                                "Latin Font": self.valves.FONT_LATIN,
+                                "Asian Font": self.valves.FONT_ASIAN,
+                                "Code Font": self.valves.FONT_CODE,
+                            },
+                        )
+
                     message_content = self._strip_reasoning_blocks(message_content)
 
                 if not message_content or not message_content.strip():
@@ -1107,30 +1151,7 @@ class Action:
         if not isinstance(name, str):
             return ""
 
-        def _is_emoji_codepoint(codepoint: int) -> bool:
-            # Common emoji ranges + flag regional indicators.
-            return (
-                0x1F000 <= codepoint <= 0x1FAFF
-                or 0x1F1E6 <= codepoint <= 0x1F1FF
-                or 0x2600 <= codepoint <= 0x26FF
-                or 0x2700 <= codepoint <= 0x27BF
-                or 0x2300 <= codepoint <= 0x23FF
-                or 0x2B00 <= codepoint <= 0x2BFF
-            )
-
-        def _is_emoji_modifier(codepoint: int) -> bool:
-            # VS15/VS16, ZWJ, keycap, skin tones, and tag characters used in some emoji sequences.
-            return (
-                codepoint in (0x200D, 0xFE0E, 0xFE0F, 0x20E3)
-                or 0x1F3FB <= codepoint <= 0x1F3FF
-                or 0xE0020 <= codepoint <= 0xE007F
-            )
-
-        without_emoji = "".join(
-            ch
-            for ch in name
-            if not (_is_emoji_codepoint(ord(ch)) or _is_emoji_modifier(ord(ch)))
-        )
+        without_emoji = self._remove_emojis(name)
         cleaned = re.sub(r'[\\/*?:"<>|]', "", without_emoji)
         cleaned = re.sub(r"\s+", " ", cleaned).strip().strip(".")
         return cleaned[:50].strip()
@@ -1498,7 +1519,10 @@ class Action:
 
             # If there is no h1 in content, prepend chat title as h1 when provided
             if top_heading and not has_h1:
-                self.add_heading(doc, top_heading, 1)
+                # Remove emojis from title for a professional look
+                clean_title = self._remove_emojis(top_heading)
+                # Use Title style (level 0) for the main document title
+                self.add_heading(doc, clean_title, 0)
 
             lines = markdown_text.split("\n")
             i = 0
@@ -1758,7 +1782,7 @@ class Action:
         cur = text
         for _ in range(10):
             prev = cur
-            cur = _REASONING_DETAILS_RE.sub("", cur)
+            cur = _ALL_DETAILS_RE.sub("", cur)
             cur = _THINK_RE.sub("", cur)
             cur = _ANALYSIS_RE.sub("", cur)
             if cur == prev:
@@ -2242,14 +2266,155 @@ class Action:
         font = style.font
         font.name = self.valves.FONT_LATIN
         font.size = Pt(11)
-        # Set Asian font
-        style._element.rPr.rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
+
+        # Ensure rPr element exists
+        rPr = style._element.get_or_add_rPr()
+        rFonts = rPr.get_or_add_rFonts()
+
+        # Set Latin and Asian fonts explicitly
+        rFonts.set(qn("w:ascii"), self.valves.FONT_LATIN)
+        rFonts.set(qn("w:hAnsi"), self.valves.FONT_LATIN)
+        rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
+
+        # Set language to zh-CN to prevent MS Gothic fallback (Japanese font)
+        # Even for English interface, we want to prioritize Chinese glyphs over Japanese for CJK
+        lang = rPr.find(qn("w:lang"))
+        if lang is None:
+            lang = OxmlElement("w:lang")
+            rPr.append(lang)
+        lang.set(qn("w:val"), "en-US")
+        lang.set(qn("w:eastAsia"), "zh-CN")
+
+        logger.info(
+            f"[Font Config] Latin: {self.valves.FONT_LATIN}, Asian: {self.valves.FONT_ASIAN}"
+        )
 
         # Set paragraph format
         paragraph_format = style.paragraph_format
         paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
         paragraph_format.space_after = Pt(6)
 
+        # Configure Title style (used for document title)
+        # Standard format: 22pt (二号), bold, centered, 24pt space after
+        if "Title" in doc.styles:
+            title_style = doc.styles["Title"]
+            title_font = title_style.font
+            title_font.name = self.valves.FONT_LATIN
+            title_font.size = Pt(22)  # 二号字体
+            title_font.bold = True
+            title_font.color.rgb = RGBColor(0, 0, 0)
+
+            # Set paragraph format: alignment based on configuration
+            title_pf = title_style.paragraph_format
+            alignment_map = {
+                "left": WD_ALIGN_PARAGRAPH.LEFT,
+                "center": WD_ALIGN_PARAGRAPH.CENTER,
+                "right": WD_ALIGN_PARAGRAPH.RIGHT,
+            }
+            title_pf.alignment = alignment_map.get(
+                self.valves.TITLE_ALIGNMENT.lower(), WD_ALIGN_PARAGRAPH.CENTER
+            )
+            title_pf.space_before = Pt(0)
+            title_pf.space_after = Pt(24)
+
+            t_rPr = title_style._element.get_or_add_rPr()
+            t_rFonts = t_rPr.get_or_add_rFonts()
+            t_rFonts.set(qn("w:ascii"), self.valves.FONT_LATIN)
+            t_rFonts.set(qn("w:hAnsi"), self.valves.FONT_LATIN)
+            t_rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
+
+            # Set language to zh-CN
+            t_lang = t_rPr.find(qn("w:lang"))
+            if t_lang is None:
+                t_lang = OxmlElement("w:lang")
+                t_rPr.append(t_lang)
+            t_lang.set(qn("w:val"), "en-US")
+            t_lang.set(qn("w:eastAsia"), "zh-CN")
+
+        # Standard heading sizes based on Chinese document standards:
+        # Heading 1: 16pt (三号), bold, space before 24pt, space after 12pt
+        # Heading 2: 15pt (小三), bold, space before 18pt, space after 6pt
+        # Heading 3: 14pt (四号), bold, space before 12pt, space after 6pt
+        # Heading 4-9: 12pt (小四), bold, gradually reduced spacing
+        heading_formats = {
+            1: {"size": 16, "space_before": 24, "space_after": 12},
+            2: {"size": 15, "space_before": 18, "space_after": 6},
+            3: {"size": 14, "space_before": 12, "space_after": 6},
+            4: {"size": 12, "space_before": 12, "space_after": 6},
+            5: {"size": 12, "space_before": 6, "space_after": 6},
+            6: {"size": 11, "space_before": 6, "space_after": 3},
+            7: {"size": 11, "space_before": 6, "space_after": 3},
+            8: {"size": 10.5, "space_before": 6, "space_after": 3},
+            9: {"size": 10.5, "space_before": 6, "space_after": 3},
+        }
+
+        # Apply font settings to Heading 1-9
+        for i in range(1, 10):
+            style_id = f"Heading {i}"
+            if style_id in doc.styles:
+                heading_style = doc.styles[style_id]
+                heading_font = heading_style.font
+                heading_font.name = self.valves.FONT_LATIN
+                heading_font.color.rgb = RGBColor(0, 0, 0)
+
+                # Apply standard formatting
+                fmt = heading_formats.get(
+                    i, {"size": 11, "space_before": 6, "space_after": 3}
+                )
+                heading_font.size = Pt(fmt["size"])
+                heading_font.bold = True
+
+                heading_pf = heading_style.paragraph_format
+                heading_pf.space_before = Pt(fmt["space_before"])
+                heading_pf.space_after = Pt(fmt["space_after"])
+
+                # Ensure rPr exists
+                h_rPr = heading_style._element.get_or_add_rPr()
+                h_rFonts = h_rPr.get_or_add_rFonts()
+
+                # Set fonts
+                h_rFonts.set(qn("w:ascii"), self.valves.FONT_LATIN)
+                h_rFonts.set(qn("w:hAnsi"), self.valves.FONT_LATIN)
+                h_rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
+
+                # Set language to zh-CN
+                h_lang = h_rPr.find(qn("w:lang"))
+                if h_lang is None:
+                    h_lang = OxmlElement("w:lang")
+                    h_rPr.append(h_lang)
+                h_lang.set(qn("w:val"), "en-US")
+                h_lang.set(qn("w:eastAsia"), "zh-CN")
+
+    def _remove_emojis(self, text: str) -> str:
+        """Remove emojis from text based on unicode ranges."""
+        if not isinstance(text, str):
+            return ""
+
+        def _is_emoji_codepoint(codepoint: int) -> bool:
+            # Common emoji ranges + flag regional indicators.
+            return (
+                0x1F000 <= codepoint <= 0x1FAFF
+                or 0x1F1E6 <= codepoint <= 0x1F1FF
+                or 0x2600 <= codepoint <= 0x26FF
+                or 0x2700 <= codepoint <= 0x27BF
+                or 0x2300 <= codepoint <= 0x23FF
+                or 0x2B00 <= codepoint <= 0x2BFF
+            )
+
+        def _is_emoji_modifier(codepoint: int) -> bool:
+            # VS15/VS16, ZWJ, keycap, skin tones, and tag characters used in some emoji sequences.
+            return (
+                codepoint in (0x200D, 0xFE0E, 0xFE0F, 0x20E3)
+                or 0x1F3FB <= codepoint <= 0x1F3FF
+                or 0xE0020 <= codepoint <= 0xE007F
+            )
+
+        return "".join(
+            ch
+            for ch in text
+            if not (_is_emoji_codepoint(ord(ch)) or _is_emoji_modifier(ord(ch)))
+        )
+
     def add_heading(self, doc: Document, text: str, level: int):
         """Add heading"""
         # Word heading levels start from 0, Markdown from 1
@@ -2285,6 +2450,12 @@ class Action:
         if strike:
             run.font.strike = True
 
+        # Explicitly set East Asian font to prevent MS Gothic fallback
+        # Word may not inherit w:eastAsia from style, causing Japanese font fallback for CJK
+        rPr = run._element.get_or_add_rPr()
+        rFonts = rPr.get_or_add_rFonts()
+        rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
+
     def _add_inline_code(self, paragraph, s: str):
         if s == "":
             return
@@ -2684,7 +2855,11 @@ class Action:
     ):
         u = self._normalize_url(url)
         if not u:
-            paragraph.add_run(display_text or text)
+            run = paragraph.add_run(display_text or text)
+            # Set East Asian font to prevent MS Gothic fallback
+            rPr = run._element.get_or_add_rPr()
+            rFonts = rPr.get_or_add_rFonts()
+            rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
             return
 
         part = getattr(paragraph, "part", None)
@@ -2693,6 +2868,10 @@ class Action:
             run = paragraph.add_run(display_text or text)
             run.font.color.rgb = RGBColor(0, 0, 255)
             run.font.underline = True
+            # Set East Asian font to prevent MS Gothic fallback
+            rPr = run._element.get_or_add_rPr()
+            rFonts = rPr.get_or_add_rFonts()
+            rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
             return
 
         r_id = part.relate_to(u, RT.HYPERLINK, is_external=True)
@@ -2706,6 +2885,11 @@ class Action:
         rStyle.set(qn("w:val"), "Hyperlink")
         rPr.append(rStyle)
 
+        # Set East Asian font to prevent MS Gothic fallback
+        rFonts = OxmlElement("w:rFonts")
+        rFonts.set(qn("w:eastAsia"), self.valves.FONT_ASIAN)
+        rPr.append(rFonts)
+
         color = OxmlElement("w:color")
         color.set(qn("w:val"), "0000FF")
         rPr.append(color)

plugins/actions/export_to_docx/export_to_word_cn.py

@@ -1,9 +1,9 @@
 """
-title: 导出为 Word (增强版)
+title: 导出为Word增强版
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui
-version: 0.4.3
+version: 0.4.4
 openwebui_id: 8a6306c0-d005-4e46-aaae-8db3532c9ed5
 icon_url: data:image/svg+xml;base64,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
 requirements: python-docx, Pygments, latex2mathml, mathml2omml
@@ -101,9 +101,8 @@ _TRANSPARENT_1PX_PNG = base64.b64decode(
 _ASVG_NS = "http://schemas.microsoft.com/office/drawing/2016/SVG/main"
 nsmap.setdefault("asvg", _ASVG_NS)
 
-_REASONING_DETAILS_RE = re.compile(
-    r"<details\b[^>]*\btype\s*=\s*(?:\"reasoning\"|'reasoning'|reasoning)[^>]*>.*?</details\s*>",
-    re.IGNORECASE | re.DOTALL,
+_ALL_DETAILS_RE = re.compile(
+    r"<details\b[^>]*>.*?</details\s*>", re.IGNORECASE | re.DOTALL
 )
 _THINK_RE = re.compile(r"<think\b[^>]*>.*?</think\s*>", re.IGNORECASE | re.DOTALL)
 _ANALYSIS_RE = re.compile(
@@ -178,6 +177,12 @@ class Action:
             description="Font for code blocks and inline code (e.g., 'Consolas', 'Courier New', 'Monaco')",
         )
 
+        # Title alignment
+        标题对齐方式: str = Field(
+            default="center",
+            description="标题对齐方式: 'left' (左对齐), 'center' (居中), 或 'right' (右对齐)",
+        )
+
         # Table styling
         表头背景色: str = Field(
             default="F2F2F2",
@@ -242,60 +247,60 @@ class Action:
         )
 
     class UserValves(BaseModel):
-        文档标题来源: str = Field(
-            default="chat_title",
+        文档标题来源: Optional[str] = Field(
+            default=None,
             description="Title Source: 'chat_title' (Chat Title), 'ai_generated' (AI Generated), 'markdown_title' (Markdown Title)",
         )
-        界面语言: str = Field(
-            default="zh",
+        界面语言: Optional[str] = Field(
+            default=None,
             description="UI language for export messages. Options: 'en' (English), 'zh' (Chinese)",
         )
-        英文字体: str = Field(
-            default="Calibri",
+        英文字体: Optional[str] = Field(
+            default=None,
             description="Font for Latin characters (e.g., 'Times New Roman', '', 'Arial')",
         )
-        中文字体: str = Field(
-            default="SimSun",
+        中文字体: Optional[str] = Field(
+            default=None,
             description="Font for Asian characters (e.g., 'SimSun', 'Microsoft YaHei', 'PingFang SC')",
         )
-        代码字体: str = Field(
-            default="Consolas",
+        代码字体: Optional[str] = Field(
+            default=None,
             description="Font for code blocks and inline code (e.g., 'Consolas', 'Courier New', 'Monaco')",
         )
-        表头背景色: str = Field(
-            default="F2F2F2",
+        表头背景色: Optional[str] = Field(
+            default=None,
             description="Table header background color (hex, without #)",
         )
-        表格隔行背景色: str = Field(
-            default="FBFBFB",
+        表格隔行背景色: Optional[str] = Field(
+            default=None,
             description="Table zebra stripe background color for alternate rows (hex, without #)",
         )
-        Mermaid_PNG缩放比例: float = Field(
-            default=3.0,
+        Mermaid_PNG缩放比例: Optional[float] = Field(
+            default=None,
             description="PNG render resolution multiplier (higher = clearer, larger file)",
         )
-        Mermaid显示比例: float = Field(
-            default=1.0,
+        Mermaid显示比例: Optional[float] = Field(
+            default=None,
             description="Diagram width relative to available page width (<=1 recommended)",
         )
-        Mermaid布局优化: bool = Field(
-            default=False,
+        Mermaid布局优化: Optional[bool] = Field(
+            default=None,
             description="Optimize Mermaid layout: convert LR to TD for graph/flowchart",
         )
-        Mermaid背景色: str = Field(
-            default="",
+        Mermaid背景色: Optional[str] = Field(
+            default=None,
             description="Mermaid background color. Empty = transparent (recommended for Word dark mode). Used only for optional PNG fill.",
         )
-        启用Mermaid图注: bool = Field(
-            default=True,
+        启用Mermaid图注: Optional[bool] = Field(
+            default=None,
             description="Add figure captions under Mermaid images/charts",
         )
-        启用数学公式: bool = Field(
-            default=True,
+        启用数学公式: Optional[bool] = Field(
+            default=None,
             description="Enable LaTeX math block conversion (\\\\[...\\\\] and $$...$$) into Word equations",
         )
-        启用行内公式: bool = Field(
-            default=True,
+        启用行内公式: Optional[bool] = Field(
+            default=None,
             description="Enable inline $...$ math conversion into Word equations (conservative parsing to reduce false positives)",
         )
 
@@ -449,11 +454,21 @@ class Action:
             user_id = __user__.get("id", "unknown_user")
 
         # Apply UserValves if present
-        if __user__ and "valves" in __user__:
-            # Update self.valves with user-specific values
-            for key, value in __user__["valves"].model_dump().items():
-                if hasattr(self.valves, key):
-                    setattr(self.valves, key, value)
+        if __user__:
+            # Robustly parse UserValves whether it's a dict or Pydantic model
+            raw_valves = __user__.get("valves", {})
+            if isinstance(raw_valves, self.UserValves):
+                user_valves = raw_valves
+            elif isinstance(raw_valves, dict):
+                user_valves = self.UserValves(**raw_valves)
+            else:
+                user_valves = None
+
+            if user_valves:
+                for key, value in user_valves.model_dump(exclude_unset=True).items():
+                    # Only override if the value is not None (and explicitly set)
+                    if hasattr(self.valves, key) and value is not None:
+                        setattr(self.valves, key, value)
 
         # Get user language from Valves configuration
         self._user_lang = self._get_lang_key(self.valves.界面语言)
@@ -490,6 +505,37 @@ class Action:
             try:
                 message_content = last_assistant_message["content"]
                 if isinstance(message_content, str):
+                    if __event_emitter__ and self.valves.SHOW_DEBUG_LOG:
+                        debug_data = {}
+                        for name, regex in [
+                            ("Details Block (详情块)", _ALL_DETAILS_RE),
+                            ("Think Block (思考块)", _THINK_RE),
+                            ("Analysis Block (分析块)", _ANALYSIS_RE),
+                        ]:
+                            matches = regex.findall(message_content)
+                            if matches:
+                                debug_data[name] = [
+                                    (m[:200] + "...") if len(m) > 200 else m
+                                    for m in matches
+                                ]
+                        if debug_data:
+                            await self._emit_debug_log(
+                                __event_emitter__,
+                                "上下文内容清理分析 (Context Stripping Analysis)",
+                                debug_data,
+                            )
+
+                        # Log font configuration
+                        await self._emit_debug_log(
+                            __event_emitter__,
+                            "字体配置 (Font Configuration)",
+                            {
+                                "英文字体 (Latin Font)": self.valves.英文字体,
+                                "中文字体 (Asian Font)": self.valves.中文字体,
+                                "代码字体 (Code Font)": self.valves.代码字体,
+                            },
+                        )
+
                     message_content = self._strip_reasoning_blocks(message_content)
 
                 if not message_content or not message_content.strip():
@@ -1101,34 +1147,11 @@ class Action:
         return title.strip() if isinstance(title, str) else ""
 
     def clean_filename(self, name: str) -> str:
-        """Clean illegal characters from filename and strip emoji."""
+        """清理文件名中的非法字符并移除 Emoji"""
         if not isinstance(name, str):
             return ""
 
-        def _is_emoji_codepoint(codepoint: int) -> bool:
-            # Common emoji ranges + flag regional indicators.
-            return (
-                0x1F000 <= codepoint <= 0x1FAFF
-                or 0x1F1E6 <= codepoint <= 0x1F1FF
-                or 0x2600 <= codepoint <= 0x26FF
-                or 0x2700 <= codepoint <= 0x27BF
-                or 0x2300 <= codepoint <= 0x23FF
-                or 0x2B00 <= codepoint <= 0x2BFF
-            )
-
-        def _is_emoji_modifier(codepoint: int) -> bool:
-            # VS15/VS16, ZWJ, keycap, skin tones, and tag characters used in some emoji sequences.
-            return (
-                codepoint in (0x200D, 0xFE0E, 0xFE0F, 0x20E3)
-                or 0x1F3FB <= codepoint <= 0x1F3FF
-                or 0xE0020 <= codepoint <= 0xE007F
-            )
-
-        without_emoji = "".join(
-            ch
-            for ch in name
-            if not (_is_emoji_codepoint(ord(ch)) or _is_emoji_modifier(ord(ch)))
-        )
+        without_emoji = self._remove_emojis(name)
         cleaned = re.sub(r'[\\/*?:"<>|]', "", without_emoji)
         cleaned = re.sub(r"\s+", " ", cleaned).strip().strip(".")
         return cleaned[:50].strip()
@@ -1496,7 +1519,10 @@ class Action:
 
             # If there is no h1 in content, prepend chat title as h1 when provided
             if top_heading and not has_h1:
-                self.add_heading(doc, top_heading, 1)
+                # Remove emojis from title for a professional look
+                clean_title = self._remove_emojis(top_heading)
+                # Use Title style (level 0) for the main document title
+                self.add_heading(doc, clean_title, 0)
 
             lines = markdown_text.split("\n")
             i = 0
@@ -1756,7 +1782,7 @@ class Action:
         cur = text
         for _ in range(10):
             prev = cur
-            cur = _REASONING_DETAILS_RE.sub("", cur)
+            cur = _ALL_DETAILS_RE.sub("", cur)
             cur = _THINK_RE.sub("", cur)
             cur = _ANALYSIS_RE.sub("", cur)
             if cur == prev:
@@ -2240,14 +2266,154 @@ class Action:
         font = style.font
         font.name = self.valves.英文字体
         font.size = Pt(11)
-        # Set Asian font
-        style._element.rPr.rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
+
+        # Ensure rPr element exists
+        rPr = style._element.get_or_add_rPr()
+        rFonts = rPr.get_or_add_rFonts()
+
+        # Set Latin and Asian fonts explicitly
+        rFonts.set(qn("w:ascii"), self.valves.英文字体)
+        rFonts.set(qn("w:hAnsi"), self.valves.英文字体)
+        rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
+
+        # Set language to zh-CN to prevent MS Gothic fallback (Japanese font)
+        lang = rPr.find(qn("w:lang"))
+        if lang is None:
+            lang = OxmlElement("w:lang")
+            rPr.append(lang)
+        lang.set(qn("w:val"), "en-US")
+        lang.set(qn("w:eastAsia"), "zh-CN")
+
+        logger.info(
+            f"[Font Config] Latin: {self.valves.英文字体}, Asian: {self.valves.中文字体}"
+        )
 
         # Set paragraph format
         paragraph_format = style.paragraph_format
         paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
         paragraph_format.space_after = Pt(6)
 
+        # 配置 Title 样式 (用于文档标题)
+        # 标准格式: 22pt (二号), 加粗, 居中, 段后 24pt
+        if "Title" in doc.styles:
+            title_style = doc.styles["Title"]
+            title_font = title_style.font
+            title_font.name = self.valves.英文字体
+            title_font.size = Pt(22)  # 二号字体
+            title_font.bold = True
+            title_font.color.rgb = RGBColor(0, 0, 0)
+
+            # 段落格式: 根据配置设置对齐方式和间距
+            title_pf = title_style.paragraph_format
+            alignment_map = {
+                "left": WD_ALIGN_PARAGRAPH.LEFT,
+                "center": WD_ALIGN_PARAGRAPH.CENTER,
+                "right": WD_ALIGN_PARAGRAPH.RIGHT,
+            }
+            title_pf.alignment = alignment_map.get(
+                self.valves.标题对齐方式.lower(), WD_ALIGN_PARAGRAPH.CENTER
+            )
+            title_pf.space_before = Pt(0)
+            title_pf.space_after = Pt(24)
+
+            t_rPr = title_style._element.get_or_add_rPr()
+            t_rFonts = t_rPr.get_or_add_rFonts()
+            t_rFonts.set(qn("w:ascii"), self.valves.英文字体)
+            t_rFonts.set(qn("w:hAnsi"), self.valves.英文字体)
+            t_rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
+
+            # Set language for Title
+            t_lang = t_rPr.find(qn("w:lang"))
+            if t_lang is None:
+                t_lang = OxmlElement("w:lang")
+                t_rPr.append(t_lang)
+            t_lang.set(qn("w:val"), "en-US")
+            t_lang.set(qn("w:eastAsia"), "zh-CN")
+
+        # 标准标题字号 (基于中文文档规范):
+        # Heading 1: 16pt (三号), 加粗, 段前 24pt, 段后 12pt
+        # Heading 2: 15pt (小三), 加粗, 段前 18pt, 段后 6pt
+        # Heading 3: 14pt (四号), 加粗, 段前 12pt, 段后 6pt
+        # Heading 4-9: 12pt (小四), 加粗, 逐级减小间距
+        heading_formats = {
+            1: {"size": 16, "space_before": 24, "space_after": 12},
+            2: {"size": 15, "space_before": 18, "space_after": 6},
+            3: {"size": 14, "space_before": 12, "space_after": 6},
+            4: {"size": 12, "space_before": 12, "space_after": 6},
+            5: {"size": 12, "space_before": 6, "space_after": 6},
+            6: {"size": 11, "space_before": 6, "space_after": 3},
+            7: {"size": 11, "space_before": 6, "space_after": 3},
+            8: {"size": 10.5, "space_before": 6, "space_after": 3},
+            9: {"size": 10.5, "space_before": 6, "space_after": 3},
+        }
+
+        # Apply font settings to Heading 1-9
+        for i in range(1, 10):
+            style_id = f"Heading {i}"
+            if style_id in doc.styles:
+                heading_style = doc.styles[style_id]
+                heading_font = heading_style.font
+                heading_font.name = self.valves.英文字体
+                heading_font.color.rgb = RGBColor(0, 0, 0)
+
+                # 应用标准格式
+                fmt = heading_formats.get(
+                    i, {"size": 11, "space_before": 6, "space_after": 3}
+                )
+                heading_font.size = Pt(fmt["size"])
+                heading_font.bold = True
+
+                heading_pf = heading_style.paragraph_format
+                heading_pf.space_before = Pt(fmt["space_before"])
+                heading_pf.space_after = Pt(fmt["space_after"])
+
+                # Ensure rPr exists
+                h_rPr = heading_style._element.get_or_add_rPr()
+                h_rFonts = h_rPr.get_or_add_rFonts()
+
+                # Set fonts
+                h_rFonts.set(qn("w:ascii"), self.valves.英文字体)
+                h_rFonts.set(qn("w:hAnsi"), self.valves.英文字体)
+                h_rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
+
+                # Set language for Heading
+                h_lang = h_rPr.find(qn("w:lang"))
+                if h_lang is None:
+                    h_lang = OxmlElement("w:lang")
+                    h_rPr.append(h_lang)
+                h_lang.set(qn("w:val"), "en-US")
+                h_lang.set(qn("w:eastAsia"), "zh-CN")
+
+    def _remove_emojis(self, text: str) -> str:
+        """从文本中移除 Emoji (基于 Unicode 范围)"""
+        if not isinstance(text, str):
+            return ""
+
+        def _is_emoji_codepoint(codepoint: int) -> bool:
+            # Common emoji ranges + flag regional indicators.
+            return (
+                0x1F000 <= codepoint <= 0x1FAFF
+                or 0x1F1E6 <= codepoint <= 0x1F1FF
+                or 0x2600 <= codepoint <= 0x26FF
+                or 0x2700 <= codepoint <= 0x27BF
+                or 0x2300 <= codepoint <= 0x23FF
+                or 0x2B00 <= codepoint <= 0x2BFF
+            )
+
+        def _is_emoji_modifier(codepoint: int) -> bool:
+            # VS15/VS16, ZWJ, keycap, skin tones, and tag characters used in some emoji sequences.
+            return (
+                codepoint in (0x200D, 0xFE0E, 0xFE0F, 0x20E3)
+                or 0x1F3FB <= codepoint <= 0x1F3FF
+                or 0xE0020 <= codepoint <= 0xE007F
+            )
+
+        return "".join(
+            ch
+            for ch in text
+            if not (_is_emoji_codepoint(ord(ch)) or _is_emoji_modifier(ord(ch)))
+        )
+
     def add_heading(self, doc: Document, text: str, level: int):
         """Add heading"""
         # Word heading levels start from 0, Markdown from 1
@@ -2283,6 +2449,12 @@ class Action:
         if strike:
             run.font.strike = True
 
+        # Explicitly set East Asian font to prevent MS Gothic fallback
+        # Word may not inherit w:eastAsia from style, causing Japanese font fallback for CJK
+        rPr = run._element.get_or_add_rPr()
+        rFonts = rPr.get_or_add_rFonts()
+        rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
+
     def _add_inline_code(self, paragraph, s: str):
         if s == "":
             return
@@ -2678,7 +2850,11 @@ class Action:
     ):
         u = self._normalize_url(url)
         if not u:
-            paragraph.add_run(display_text or text)
+            run = paragraph.add_run(display_text or text)
+            # Set East Asian font to prevent MS Gothic fallback
+            rPr = run._element.get_or_add_rPr()
+            rFonts = rPr.get_or_add_rFonts()
+            rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
             return
 
         part = getattr(paragraph, "part", None)
@@ -2687,6 +2863,10 @@ class Action:
             run = paragraph.add_run(display_text or text)
             run.font.color.rgb = RGBColor(0, 0, 255)
             run.font.underline = True
+            # Set East Asian font to prevent MS Gothic fallback
+            rPr = run._element.get_or_add_rPr()
+            rFonts = rPr.get_or_add_rFonts()
+            rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
             return
 
         r_id = part.relate_to(u, RT.HYPERLINK, is_external=True)
@@ -2700,6 +2880,11 @@ class Action:
         rStyle.set(qn("w:val"), "Hyperlink")
         rPr.append(rStyle)
 
+        # Set East Asian font to prevent MS Gothic fallback
+        rFonts = OxmlElement("w:rFonts")
+        rFonts.set(qn("w:eastAsia"), self.valves.中文字体)
+        rPr.append(rFonts)
+
         color = OxmlElement("w:color")
         color.set(qn("w:val"), "0000FF")
         rPr.append(color)

plugins/actions/export_to_excel/README.md

@@ -1,4 +1,59 @@
-# Export to Excel
+# 📊 Export to Excel
+
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.3.6 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
+
+Export chat history to an Excel (.xlsx) file directly from the chat interface.
+
+## 🔥 What's New in v0.3.6
+
+- **OpenWebUI-Style Theme**: Modern dark header (#1f2937) with light gray zebra striping for better readability.
+- **Zebra Striping**: Alternating row colors (#ffffff / #f3f4f6) for improved visual scanning.
+- **Smart Data Type Conversion**: Automatically converts columns to numeric or datetime types with fallback to string.
+- **Full Cell Bold/Italic**: Supports full cell Markdown bold (`**text**`) and italic (`*text*`) formatting in Excel.
+- **Partial Markdown Cleanup**: Removes partial Markdown formatting symbols for cleaner Excel output.
+- **Export Scope**: Added `EXPORT_SCOPE` to choose between the last message or all messages.
+- **Smart Sheet Naming**: Names sheets based on Markdown headers, AI titles, or message index.
+- **Multiple Tables Support**: Improved handling of multiple tables across messages.
+- **Smart Filename Generation**: Supports filenames based on chat title, AI summary, or Markdown headers.
+- **Configuration Options**: Added `TITLE_SOURCE` to control filename strategy.
+- **AI Title Generation**: Added `MODEL_ID` to use AI for filename generation with progress notifications.
+
+## ✨ Core Features
+
+- 🚀 **One-Click Export**: Adds an “Export to Excel” action button to the chat.
+- 🧠 **Automatic Header Extraction**: Intelligently identifies table headers from chat content.
+- 📊 **Multi-Table Support**: Handles multiple tables within a single chat session.
+
+## 🚀 How to Use
+
+1. **Install**: Search for “Export to Excel” in the Open WebUI Community and install.
+2. **Trigger**: In any chat, click the “Export to Excel” action button.
+3. **Download**: The .xlsx file will be automatically downloaded.
+
+## ⚙️ Configuration (Valves)
+
+| Parameter | Default | Description |
+| :--- | :--- | :--- |
+| `TITLE_SOURCE` | `chat_title` | Filename source: `chat_title`, `ai_generated`, or `markdown_title`. |
+| `EXPORT_SCOPE` | `last_message` | Export scope: `last_message` or `all_messages`. |
+| `MODEL_ID` | `""` | Model ID for AI title generation. Empty uses current chat model. |
+| `SHOW_STATUS` | `True` | Show operation status updates. |
+| `SHOW_DEBUG_LOG` | `False` | Print debug logs in the browser console (F12). |
+
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
+## Troubleshooting ❓
+
+- **Plugin not working?**: Check if the filter/action is enabled in the model settings.
+- **Debug Logs**: Enable `SHOW_STATUS` and check the browser console (F12) if needed.
+- **Error Messages**: If you see an error, please copy the full error message and report it.
+- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)# Export to Excel
 
 This plugin allows you to export your chat history to an Excel (.xlsx) file directly from the chat interface.
 

plugins/actions/export_to_excel/README_CN.md

@@ -1,4 +1,59 @@
-# 导出为 Excel
+# 📊 导出为 Excel
+
+**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.3.6 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
+
+将对话历史直接导出为 Excel (.xlsx) 文件。
+
+## 🔥 最新更新 v0.3.6
+
+- **OpenWebUI 风格主题**：现代深灰表头（#1f2937）与浅灰斑马纹，提升可读性。
+- **斑马纹效果**：隔行变色（#ffffff / #f3f4f6），方便视觉扫描。
+- **智能数据类型转换**：自动将列转换为数字或日期类型，无法转换时保持字符串。
+- **全单元格粗体/斜体**：支持全单元格 Markdown 粗体与斜体格式。
+- **部分 Markdown 清理**：移除部分 Markdown 格式符号，输出更整洁。
+- **导出范围**：新增 `EXPORT_SCOPE`，可选择导出最后一条或所有消息。
+- **智能 Sheet 命名**：按 Markdown 标题、AI 标题或消息索引命名。
+- **多表格支持**：优化了多表格处理能力。
+- **智能文件名生成**：支持对话标题 / AI 总结 / Markdown 标题命名。
+- **配置选项**：新增 `TITLE_SOURCE` 控制文件名策略。
+- **AI 标题生成**：新增 `MODEL_ID`，支持 AI 标题生成与进度提示。
+
+## ✨ 核心特性
+
+- 🚀 **一键导出**：在聊天界面添加“导出为 Excel”按钮。
+- 🧠 **自动表头提取**：智能识别聊天内容中的表格标题。
+- 📊 **多表支持**：支持单次对话中的多个表格。
+
+## 🚀 使用方法
+
+1. **安装**：在 Open WebUI 社区搜索“导出为 Excel”并安装。
+2. **触发**：在任意对话中，点击“导出为 Excel”动作按钮。
+3. **下载**：.xlsx 文件将自动下载到你的设备。
+
+## ⚙️ 配置参数 (Valves)
+
+| 参数 | 默认值 | 描述 |
+| :--- | :--- | :--- |
+| `TITLE_SOURCE` | `chat_title` | 文件名来源：`chat_title`、`ai_generated`、`markdown_title`。 |
+| `EXPORT_SCOPE` | `last_message` | 导出范围：`last_message` 或 `all_messages`。 |
+| `MODEL_ID` | `""` | AI 标题生成的模型 ID。为空则使用当前对话模型。 |
+| `SHOW_STATUS` | `True` | 是否显示操作状态更新。 |
+| `SHOW_DEBUG_LOG` | `False` | 是否在浏览器控制台输出调试日志 (F12)。 |
+
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
+## 故障排除 (Troubleshooting) ❓
+
+- **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
+- **调试日志**: 如需排查，启用 `SHOW_STATUS` 并查看浏览器控制台 (F12)。
+- **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
+- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)# 导出为 Excel
 
 此插件允许你直接从聊天界面将对话历史导出为 Excel (.xlsx) 文件。
 

plugins/actions/flash-card/README.md

@@ -4,13 +4,10 @@ Generate polished learning flashcards from any text—title, summary, key points
 
 **Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.2.4 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
-## Preview 📸
-
-![Flash Card Example](flash_card.png)
-
 ## What's New
 
 ### v0.2.4
+
 - **Clean Output**: Removed debug messages from output.
 
 ## Key Features 🔑
@@ -39,9 +36,21 @@ Generate polished learning flashcards from any text—title, summary, key points
 | CLEAR_PREVIOUS_HTML | Whether to clear previous card HTML (otherwise append/merge) | false   |
 | MESSAGE_COUNT       | Use the latest N messages to build the card                  | 1       |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## Troubleshooting ❓
 
 - **Plugin not working?**: Check if the filter/action is enabled in the model settings.
 - **Debug Logs**: Enable `SHOW_STATUS` in Valves to see progress updates.
 - **Error Messages**: If you see an error, please copy the full error message and report it.
 - **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## Preview 📸
+
+![Flash Card Example](flash_card.png)
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/flash-card/README_CN.md

@@ -4,22 +4,17 @@
 
 **作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.2.4 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
-## 预览 📸
+## 🔥 最新更新 v0.2.4
 
-![闪记卡示例](flash_card_cn.png)
-
-## 更新日志
-
-### v0.2.4
-- **输出优化**: 移除输出中的调试信息。
+* **输出优化**: 移除输出中的调试信息。
 
 ## 核心特性 🔑
 
-- **一键生成**：输入任意文本，直接产出结构化卡片。
-- **要点聚合**：自动提取 3-5 个记忆要点与 2-4 个标签。
-- **多语言支持**：可设定目标语言（默认中文）。
-- **渐进合并**：多次调用会将新卡片合并到同一 HTML 容器中；如需重置可启用清空选项。
-- **状态提示**：实时推送“生成中/完成/错误”等状态与通知。
+* **一键生成**：输入任意文本，直接产出结构化卡片。
+* **要点聚合**：自动提取 3-5 个记忆要点与 2-4 个标签。
+* **多语言支持**：可设定目标语言（默认中文）。
+* **渐进合并**：多次调用会将新卡片合并到同一 HTML 容器中；如需重置可启用清空选项。
+* **状态提示**：实时推送“生成中/完成/错误”等状态与通知。
 
 ## 使用方法 🛠️
 
@@ -39,9 +34,21 @@
 | CLEAR_PREVIOUS_HTML | 是否清空旧的卡片 HTML（否则合并追加） | false  |
 | MESSAGE_COUNT       | 取最近 N 条消息生成卡片               | 1      |
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
 ## 故障排除 (Troubleshooting) ❓
 
-- **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
-- **调试日志**: 在 Valves 中启用 `SHOW_STATUS` 以查看进度更新。
-- **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
-- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+* **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
+* **调试日志**: 在 Valves 中启用 `SHOW_STATUS` 以查看进度更新。
+* **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
+* **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## 预览 📸
+
+![闪记卡示例](flash_card_cn.png)
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/infographic/README.md

@@ -1,4 +1,4 @@
-# 📊 Smart Infographic (AntV)
+# Smart Infographic
 
 **Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.5.0 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
@@ -10,19 +10,6 @@ An Open WebUI plugin powered by the AntV Infographic engine. It transforms long
 - 🗣️ **Context-Aware Generation**: Generated infographics now strictly follow the language of your input content (e.g., input Japanese -> output Japanese infographic).
 - 🐛 **Bug Fixes**: Fixed issues with language synchronization between the UI and generated content.
 
-### Previous: v1.4.9
-
-- 🎨 **70+ Official Templates**: Integrated comprehensive AntV infographic template library.
-- 🖼️ **Iconify & unDraw Support**: Richer visuals with official icons and illustrations.
-- 📏 **Visual Optimization**: Improved text wrapping, adaptive sizing, and layout refinement.
-- ✨ **PNG Upload**: Infographics now upload as PNG format for better Word export compatibility.
-- 🔧 **Canvas Conversion**: Uses browser canvas for high-quality SVG to PNG conversion (2x scale).
-
-### Previous: v1.4.0
-
-- ✨ **Default Mode Change**: Default output mode is now `image` (static image) for better compatibility.
-- 📱 **Responsive Sizing**: Images now auto-adapt to the chat container width.
-
 ## ✨ Key Features
 
 - 🚀 **AI-Powered Transformation**: Automatically analyzes text logic, extracts key points, and generates structured charts.
@@ -52,6 +39,10 @@ You can adjust the following parameters in the plugin settings to optimize the g
 | **Message Count (MESSAGE_COUNT)** | `1` | Number of recent messages to use for analysis. Increase this for more context. |
 | **Output Mode (OUTPUT_MODE)** | `image` | `image` for static image embedding (default, better compatibility), `html` for interactive chart. |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## 🛠️ Supported Template Types
 
 | Category | Template Name | Use Case |
@@ -69,6 +60,10 @@ You can adjust the following parameters in the plugin settings to optimize the g
 - **Error Messages**: If you see an error, please copy the full error message and report it.
 - **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
 
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
+
 ## 📝 Syntax Example (For Advanced Users)
 
 You can also input this syntax directly for AI to render:

plugins/actions/infographic/README_CN.md

@@ -1,28 +1,15 @@
-# 📊 智能信息图 (AntV Infographic)
+# 智能信息图
 
 **作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.5.0 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
 基于 AntV Infographic 引擎的 Open WebUI 插件，能够将长文本内容一键转换为专业、美观的信息图表。
 
-## 🔥 v1.5.0 更新日志
+## 🔥 最新更新 v1.5.0
 
 - 🌐 **智能语言检测**：自动从浏览器准确识别当前界面语言设置。
 - 🗣️ **上下文感知生成**：生成的信息图内容现在严格跟随用户输入内容的语言（例如：输入日语 -> 生成日语信息图）。
 - 🐛 **问题修复**：修复了界面语言与生成内容语言不同步的问题。
 
-### 此前: v1.4.9
-
-- 🎨 **70+ 官方模板**：全面集成 AntV 官方信息图模板库。
-- 🖼️ **图标与插图支持**：支持 Iconify 图标库与 unDraw 插图库，视觉效果更丰富。
-- 📏 **视觉优化**：改进文本换行逻辑，优化自适应尺寸，提升卡片布局精细度。
-- ✨ **PNG 上传**：信息图现在以 PNG 格式上传，与 Word 导出完美兼容。
-- 🔧 **Canvas 转换**：使用浏览器 Canvas 高质量转换 SVG 为 PNG（2倍缩放）。
-
-### 此前: v1.4.0
-
-- ✨ **默认模式变更**：默认输出模式调整为 `image`（静态图片）。
-- 📱 **响应式尺寸**：图片模式下自动适应聊天容器宽度。
-
 ## ✨ 核心特性
 
 - 🚀 **智能转换**：自动分析文本核心逻辑，提取关键点并生成结构化图表。
@@ -52,6 +39,10 @@
 | **上下文消息数 (MESSAGE_COUNT)** | `1` | 用于分析的最近消息条数。增加此值可让 AI 参考更多对话背景。 |
 | **输出模式 (OUTPUT_MODE)** | `image` | `image` 为静态图片嵌入（默认，兼容性好），`html` 为交互式图表。 |
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
 ## 🛠️ 支持的模板类型
 
 | 分类 | 模板名称 | 适用场景 |
@@ -69,6 +60,10 @@
 - **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
 - **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
 
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
+
 ## 📝 语法示例 (高级用户)
 
 你也可以直接输入以下语法让 AI 渲染：

plugins/actions/infographic/infographic.py

@@ -1,5 +1,5 @@
 """
-title: 📊 Smart Infographic (AntV)
+title: Smart Infographic
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui

plugins/actions/infographic/infographic_cn.py

@@ -1,5 +1,5 @@
 """
-title: 📊 智能信息图 (AntV Infographic)
+title: 智能信息图
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui

plugins/actions/smart-mind-map/README.md

@@ -2,17 +2,14 @@
 
 Smart Mind Map is a powerful OpenWebUI action plugin that intelligently analyzes long-form text content and automatically generates interactive mind maps, helping users structure and visualize knowledge.
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.9.1 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.9.2 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
-## What's New in v0.9.1
+## What's New in v0.9.2
 
-**New Feature: Image Output Mode**
+**Language Rule Alignment**
 
-- **Static Image Support**: Added `OUTPUT_MODE` configuration parameter.
-  - `html` (default): Interactive HTML mind map.
-  - `image`: Static SVG image embedded directly in Markdown (**No HTML code output**, cleaner chat history).
-- **Efficient Storage**: Image mode uploads SVG to `/api/v1/files`, avoiding huge base64 strings in chat history.
-- **Smart Features**: Auto-responsive width and automatic theme detection (light/dark) for generated images.
+- **Input Language First**: Mind map output now strictly matches the input text language.
+- **Consistent Behavior**: Matches the infographic language rule for predictable multilingual output.
 
 ## Key Features 🔑
 
@@ -41,6 +38,10 @@ Smart Mind Map is a powerful OpenWebUI action plugin that intelligently analyzes
 | `MESSAGE_COUNT` | `1` | Number of recent messages to use for generation (1-5). |
 | `OUTPUT_MODE` | `html` | Output mode: `html` (interactive) or `image` (static). |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## Troubleshooting ❓
 
 - **Plugin not working?**: Check if the action is enabled in the chat settings.
@@ -62,3 +63,7 @@ Smart Mind Map is a powerful OpenWebUI action plugin that intelligently analyzes
 1. **Text Preparation**: Provide text with clear structure and distinct hierarchies.
 2. **Model Selection**: Use fast models like `gemini-2.5-flash` for daily use.
 3. **Export Quality**: Use PNG for presentations and SVG for further editing.
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/smart-mind-map/README_CN.md

@@ -2,17 +2,14 @@
 
 思维导图是一个强大的 OpenWebUI 动作插件，能够智能分析长篇文本内容，自动生成交互式思维导图，帮助用户结构化和可视化知识。
 
-**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.9.1 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.9.2 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
-## v0.9.1 更新亮点
+## v0.9.2 更新亮点
 
-**新功能：图片输出模式**
+**语言规则对齐**
 
-- **静态图片支持**：新增 `OUTPUT_MODE` 配置参数。
-  - `html`（默认）：交互式 HTML 思维导图。
-  - `image`：静态 SVG 图片直接嵌入 Markdown（**不输出 HTML 代码**，聊天记录更简洁）。
-- **高效存储**：图片模式将 SVG 上传至 `/api/v1/files`，避免聊天记录中出现超长 Base64 字符串。
-- **智能特性**：生成的图片支持自动响应式宽度和自动主题检测（亮色/暗色）。
+- **输入语言优先**：导图输出严格与输入文本语言一致。
+- **一致性提升**：与信息图语言规则保持一致，多语言输出更可预期。
 
 ## 核心特性 🔑
 
@@ -41,6 +38,10 @@
 | `MESSAGE_COUNT` | `1` | 用于生成思维导图的最近消息数量（1-5）。 |
 | `OUTPUT_MODE` | `html` | 输出模式：`html`（交互式）或 `image`（静态图片）。 |
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
 ## 故障排除 (Troubleshooting) ❓
 
 - **插件无法启动**：检查 OpenWebUI 日志，确认插件已正确上传并启用。
@@ -62,3 +63,7 @@
 1. **文本准备**：提供结构清晰、层次分明的文本内容。
 2. **模型选择**：日常使用推荐 `gemini-2.5-flash` 等快速模型。
 3. **导出质量**：PNG 适合演示分享，SVG 适合进一步矢量编辑。
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/actions/smart-mind-map/smart_mind_map.py

@@ -4,7 +4,7 @@ author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.9.1
+version: 0.9.2
 openwebui_id: 3094c59a-b4dd-4e0c-9449-15e2dd547dc4
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPjxyZWN0IHg9IjE2IiB5PSIxNiIgd2lkdGg9IjYiIGhlaWdodD0iNiIgcng9IjEiLz48cmVjdCB4PSIyIiB5PSIxNiIgd2lkdGg9IjYiIGhlaWdodD0iNiIgcng9IjEiLz48cmVjdCB4PSI5IiB5PSIyIiB3aWR0aD0iNiIgaGVpZ2h0PSI2IiByeD0iMSIvPjxwYXRoIGQ9Ik01IDE2di0zYTEgMSAwIDAgMSAxLTFoMTJhMSAxIDAgMCAxIDEgMXYzIi8+PHBhdGggZD0iTTEyIDEyVjgiLz48L3N2Zz4=
 description: Intelligently analyzes text content and generates interactive mind maps to help users structure and visualize knowledge.
@@ -33,7 +33,8 @@ SYSTEM_PROMPT_MINDMAP_ASSISTANT = """
 You are a professional mind map generation assistant, capable of efficiently analyzing long-form text provided by users and structuring its core themes, key concepts, branches, and sub-branches into standard Markdown list syntax for rendering by Markmap.js.
 
 Please strictly follow these guidelines:
--   **Language**: All output must be in the language specified by the user.
+-   **Language**: All output must be in the exact same language as the input text (the text you are analyzing).
+-   **Format Consistency**: Even if this system prompt is in English, if the user input is in Chinese, the mind map content must be in Chinese. If input is Japanese, output Japanese.
 -   **Format**: Your output must strictly be in Markdown list format, wrapped with ```markdown and ```.
     -   Use `#` to define the central theme (root node).
     -   Use `-` with two-space indentation to represent branches and sub-branches.
@@ -811,7 +812,11 @@ class Action:
             "Sunday": "Sunday",
         }
 
-    def _get_user_context(self, __user__: Optional[Dict[str, Any]]) -> Dict[str, str]:
+    async def _get_user_context(
+        self,
+        __user__: Optional[Dict[str, Any]],
+        __event_call__: Optional[Callable[[Any], Awaitable[None]]] = None,
+    ) -> Dict[str, str]:
         """Extract basic user context with safe fallbacks."""
         if isinstance(__user__, (list, tuple)):
             user_data = __user__[0] if __user__ else {}
@@ -820,10 +825,32 @@ class Action:
         else:
             user_data = {}
 
+        user_id = user_data.get("id", "unknown_user")
+        user_name = user_data.get("name", "User")
+        user_language = user_data.get("language", "en-US")
+
+        if __event_call__:
+            try:
+                js_code = """
+                    return (
+                        localStorage.getItem('locale') || 
+                        localStorage.getItem('language') || 
+                        navigator.language || 
+                        'en-US'
+                    );
+                """
+                frontend_lang = await __event_call__(
+                    {"type": "execute", "data": {"code": js_code}}
+                )
+                if frontend_lang and isinstance(frontend_lang, str):
+                    user_language = frontend_lang
+            except Exception as e:
+                logger.warning(f"Failed to retrieve frontend language: {e}")
+
         return {
-            "user_id": user_data.get("id", "unknown_user"),
-            "user_name": user_data.get("name", "User"),
-            "user_language": user_data.get("language", "en-US"),
+            "user_id": user_id,
+            "user_name": user_name,
+            "user_language": user_language,
         }
 
     def _get_chat_context(
@@ -1369,8 +1396,8 @@ class Action:
         __metadata__: Optional[dict] = None,
         __request__: Optional[Request] = None,
     ) -> Optional[dict]:
-        logger.info("Action: Smart Mind Map (v0.9.1) started")
-        user_ctx = self._get_user_context(__user__)
+        logger.info("Action: Smart Mind Map (v0.9.2) started")
+        user_ctx = await self._get_user_context(__user__, __event_call__)
         user_language = user_ctx["user_language"]
         user_name = user_ctx["user_name"]
         user_id = user_ctx["user_id"]

plugins/actions/smart-mind-map/smart_mind_map_cn.py

@@ -3,7 +3,7 @@ title: 思维导图
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui
-version: 0.9.1
+version: 0.9.2
 openwebui_id: 8d4b097b-219b-4dd2-b509-05fbe6388335
 icon_url: data:image/svg+xml;base64,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
 description: 智能分析文本内容,生成交互式思维导图,帮助用户结构化和可视化知识。
@@ -32,7 +32,8 @@ SYSTEM_PROMPT_MINDMAP_ASSISTANT = """
 你是一个专业的思维导图生成助手,能够高效地分析用户提供的长篇文本,并将其核心主题、关键概念、分支和子分支结构化为标准的Markdown列表语法,以便Markmap.js进行渲染。
 
 请严格遵循以下指导原则:
--   **语言**: 所有输出必须使用用户指定的语言。
+-   **语言**: 所有输出必须与输入文本(正在分析的文本)保持完全一致的语言。
+-   **格式一致性**: 即使系统提示词是中文,只要用户输入是英文,导图内容必须是英文;若输入为日文,则输出日文。
 -   **格式**: 你的输出必须严格为Markdown列表格式,并用```markdown 和 ``` 包裹。
     -   使用 `#` 定义中心主题(根节点)。
     -   使用 `-` 和两个空格的缩进表示分支和子分支。
@@ -809,7 +810,11 @@ class Action:
             "Sunday": "星期日",
         }
 
-    def _get_user_context(self, __user__: Optional[Dict[str, Any]]) -> Dict[str, str]:
+    async def _get_user_context(
+        self,
+        __user__: Optional[Dict[str, Any]],
+        __event_call__: Optional[Callable[[Any], Awaitable[None]]] = None,
+    ) -> Dict[str, str]:
         """Extract basic user context with safe fallbacks."""
         if isinstance(__user__, (list, tuple)):
             user_data = __user__[0] if __user__ else {}
@@ -818,10 +823,32 @@ class Action:
         else:
             user_data = {}
 
+        user_id = user_data.get("id", "unknown_user")
+        user_name = user_data.get("name", "User")
+        user_language = user_data.get("language", "en-US")
+
+        if __event_call__:
+            try:
+                js_code = """
+                    return (
+                        localStorage.getItem('locale') || 
+                        localStorage.getItem('language') || 
+                        navigator.language || 
+                        'en-US'
+                    );
+                """
+                frontend_lang = await __event_call__(
+                    {"type": "execute", "data": {"code": js_code}}
+                )
+                if frontend_lang and isinstance(frontend_lang, str):
+                    user_language = frontend_lang
+            except Exception as e:
+                logger.warning(f"Failed to retrieve frontend language: {e}")
+
         return {
-            "user_id": user_data.get("id", "unknown_user"),
-            "user_name": user_data.get("name", "用户"),
-            "user_language": user_data.get("language", "zh-CN"),
+            "user_id": user_id,
+            "user_name": user_name,
+            "user_language": user_language,
         }
 
     def _get_chat_context(
@@ -1348,8 +1375,8 @@ class Action:
         __metadata__: Optional[dict] = None,
         __request__: Optional[Request] = None,
     ) -> Optional[dict]:
-        logger.info("Action: 思维导图 (v0.9.1) started")
-        user_ctx = self._get_user_context(__user__)
+        logger.info("Action: 思维导图 (v0.9.2) started")
+        user_ctx = await self._get_user_context(__user__, __event_call__)
         user_language = user_ctx["user_language"]
         user_name = user_ctx["user_name"]
         user_id = user_ctx["user_id"]

plugins/debug/common_tools/update_readmes_to_market.py

@@ -0,0 +1,359 @@
+#!/usr/bin/env python3
+"""
+======================================================================
+Staged README Synchronizer to OpenWebUI Community
+暂存 README 文件同步到 OpenWebUI 社区工具
+======================================================================
+
+PURPOSE / 用途:
+--------------
+This script synchronizes staged README.md/README_CN.md files to their
+corresponding OpenWebUI Community posts automatically. It's designed for
+batch updating documentation content without modifying plugin versions
+or media attachments.
+
+本脚本自动将暂存的 README.md/README_CN.md 文件同步到对应的 OpenWebUI
+社区帖子。专为批量更新文档内容设计，不修改插件版本或媒体附件。
+
+USAGE / 使用方法:
+----------------
+1. Set up environment:
+   配置环境：
+
+   Create a .env file in the repository root with:
+   在仓库根目录创建 .env 文件，包含：
+
+   OPENWEBUI_API_KEY=your_api_key_here
+
+2. Stage README files to sync:
+   暂存需要同步的 README 文件：
+
+   git add plugins/actions/my_plugin/README.md
+   git add plugins/actions/my_plugin/README_CN.md
+
+3. Run the script:
+   运行脚本：
+
+   python plugins/debug/common_tools/update_readmes_to_market.py
+
+WORKFLOW / 工作流程:
+-------------------
+1. Load OPENWEBUI_API_KEY from .env file
+   从 .env 文件加载 OPENWEBUI_API_KEY
+
+2. Get list of staged README.md/README_CN.md files via git
+   通过 git 获取暂存的 README.md/README_CN.md 文件列表
+
+3. For each staged README:
+   对于每个暂存的 README：
+
+   a. Locate the corresponding plugin .py file
+      定位对应的插件 .py 文件
+
+   b. Extract openwebui_id/post_id from plugin frontmatter
+      从插件前置信息中提取 openwebui_id/post_id
+
+   c. Fetch existing post data from OpenWebUI Community API
+      从 OpenWebUI 社区 API 获取现有帖子数据
+
+   d. Update post content with new README content
+      用新的 README 内容更新帖子内容
+
+   e. Push changes via API (preserves version & media)
+      通过 API 推送更改（保留版本和媒体）
+
+REQUIREMENTS / 依赖要求:
+-----------------------
+- python-dotenv: For loading .env configuration
+                 用于加载 .env 配置文件
+- Git repository: Must be run from a git-tracked workspace
+                  必须在 git 跟踪的工作区中运行
+
+KEY FEATURES / 关键特性:
+-----------------------
+✅ Only updates content field (不仅更新内容字段)
+✅ Skips files without openwebui_id (跳过没有 openwebui_id 的文件)
+✅ Automatically matches CN/EN plugin files (自动匹配中英文插件文件)
+✅ Supports staged plugin source code updates (支持暂存插件源码更新)
+✅ Safe: Won't modify version or media fields (安全：不会修改版本或媒体字段)
+
+NOTES / 注意事项:
+---------------
+- This is a DEBUG/DEVELOPMENT tool, not for production workflows
+  这是一个调试/开发工具，不用于生产工作流
+
+- Always verify changes in OpenWebUI Community after sync
+  同步后务必在 OpenWebUI 社区中验证更改
+
+- Requires valid API key with update permissions
+  需要具有更新权限的有效 API 密钥
+
+AUTHOR / 作者:
+-------------
+Fu-Jie
+GitHub: https://github.com/Fu-Jie/awesome-openwebui
+
+======================================================================
+"""
+
+from __future__ import annotations
+
+import importlib.util
+import os
+import re
+import sys
+import subprocess
+from pathlib import Path
+from typing import Dict, Optional, List
+
+
+def _load_dotenv(repo_root: Path) -> None:
+    try:
+        from dotenv import load_dotenv  # type: ignore
+    except Exception as exc:  # pragma: no cover
+        print("Missing dependency: python-dotenv. Please install it and retry.")
+        raise SystemExit(1) from exc
+
+    env_path = repo_root / ".env"
+    load_dotenv(env_path)
+
+
+def _get_repo_root() -> Path:
+    return Path(__file__).resolve().parents[3]
+
+
+def _get_staged_readmes(repo_root: Path) -> List[Path]:
+    try:
+        output = subprocess.check_output(
+            [
+                "git",
+                "-C",
+                str(repo_root),
+                "diff",
+                "--cached",
+                "--name-only",
+                "--",
+                "*.md",
+            ],
+            text=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        print(f"Failed to read staged files: {exc}")
+        return []
+
+    paths = []
+    for line in output.splitlines():
+        line = line.strip()
+        if not line:
+            continue
+        if line.endswith("README.md") or line.endswith("README_CN.md"):
+            paths.append(repo_root / line)
+    return paths
+
+
+def _get_staged_plugin_files(repo_root: Path) -> List[Path]:
+    try:
+        output = subprocess.check_output(
+            [
+                "git",
+                "-C",
+                str(repo_root),
+                "diff",
+                "--cached",
+                "--name-only",
+                "--",
+                "*.py",
+            ],
+            text=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        print(f"Failed to read staged files: {exc}")
+        return []
+
+    paths = []
+    for line in output.splitlines():
+        line = line.strip()
+        if not line:
+            continue
+        if "/plugins/" not in line:
+            continue
+        if line.endswith("__init__.py") or os.path.basename(line).startswith("test_"):
+            continue
+        paths.append(repo_root / line)
+    return paths
+
+
+def _parse_frontmatter(content: str) -> Dict[str, str]:
+    match = re.search(r'^\s*"""\n(.*?)\n"""', content, re.DOTALL)
+    if not match:
+        match = re.search(r'"""\n(.*?)\n"""', content, re.DOTALL)
+        if not match:
+            return {}
+
+    frontmatter = match.group(1)
+    meta: Dict[str, str] = {}
+    for line in frontmatter.split("\n"):
+        if ":" in line:
+            key, value = line.split(":", 1)
+            meta[key.strip()] = value.strip()
+    return meta
+
+
+def _find_plugin_file(readme_path: Path) -> Optional[Path]:
+    plugin_dir = readme_path.parent
+    is_cn = readme_path.name.lower().endswith("readme_cn.md")
+
+    py_files = [
+        p
+        for p in plugin_dir.glob("*.py")
+        if p.name != "__init__.py" and not p.name.startswith("test_")
+    ]
+    if not py_files:
+        return None
+
+    cn_files = [p for p in py_files if p.stem.endswith("_cn")]
+    en_files = [p for p in py_files if not p.stem.endswith("_cn")]
+
+    candidates = cn_files + en_files if is_cn else en_files + cn_files
+
+    # Prefer files that contain openwebui_id/post_id in frontmatter
+    for candidate in candidates:
+        post_id = _get_post_id(candidate)
+        if post_id:
+            return candidate
+
+    return candidates[0] if candidates else None
+
+
+def _get_post_id(plugin_file: Path) -> Optional[str]:
+    try:
+        content = plugin_file.read_text(encoding="utf-8")
+    except Exception:
+        return None
+
+    meta = _parse_frontmatter(content)
+    return meta.get("openwebui_id") or meta.get("post_id")
+
+
+def _get_plugin_metadata(plugin_file: Path) -> Dict[str, str]:
+    try:
+        content = plugin_file.read_text(encoding="utf-8")
+    except Exception:
+        return {}
+    return _parse_frontmatter(content)
+
+
+def _find_readme_for_plugin(plugin_file: Path) -> Optional[str]:
+    plugin_dir = plugin_file.parent
+    is_cn = plugin_file.stem.endswith("_cn")
+    readme_candidates = ["README_CN.md", "README.md"] if is_cn else ["README.md", "README_CN.md"]
+    for name in readme_candidates:
+        readme_path = plugin_dir / name
+        if readme_path.exists():
+            return readme_path.read_text(encoding="utf-8")
+    return None
+
+
+def main() -> int:
+    repo_root = _get_repo_root()
+    _load_dotenv(repo_root)
+
+    api_key = os.environ.get("OPENWEBUI_API_KEY")
+    if not api_key:
+        print("OPENWEBUI_API_KEY is not set in environment.")
+        return 1
+
+    client_module_path = repo_root / "scripts" / "openwebui_community_client.py"
+    spec = importlib.util.spec_from_file_location(
+        "openwebui_community_client", client_module_path
+    )
+    if not spec or not spec.loader:
+        print("Failed to load openwebui_community_client module.")
+        return 1
+
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    client = module.get_client(api_key)
+
+    staged_plugins = _get_staged_plugin_files(repo_root)
+    staged_readmes = _get_staged_readmes(repo_root)
+    if not staged_plugins and not staged_readmes:
+        print("No staged README or plugin files found.")
+        return 0
+
+    updated_post_ids: set[str] = set()
+
+    for plugin_file in staged_plugins:
+        if not plugin_file.exists():
+            print(f"Skipped (missing): {plugin_file}")
+            continue
+
+        post_id = _get_post_id(plugin_file)
+        if not post_id:
+            print(f"Skipped (no openwebui_id): {plugin_file}")
+            continue
+
+        try:
+            post_data = client.get_post(post_id)
+            if not post_data:
+                print(f"Skipped (post not found): {plugin_file}")
+                continue
+
+            source_code = plugin_file.read_text(encoding="utf-8")
+            metadata = _get_plugin_metadata(plugin_file)
+            readme_content = _find_readme_for_plugin(plugin_file)
+
+            ok = client.update_plugin(
+                post_id=post_id,
+                source_code=source_code,
+                readme_content=readme_content or metadata.get("description", ""),
+                metadata=metadata,
+                media_urls=None,
+            )
+            if ok:
+                updated_post_ids.add(post_id)
+                print(f"Updated plugin -> {plugin_file} (post_id: {post_id})")
+        except Exception as exc:
+            print(f"Failed: {plugin_file} ({exc})")
+
+    for readme_path in staged_readmes:
+        if not readme_path.exists():
+            print(f"Skipped (missing): {readme_path}")
+            continue
+
+        plugin_file = _find_plugin_file(readme_path)
+        if not plugin_file:
+            print(f"Skipped (no plugin file): {readme_path}")
+            continue
+
+        post_id = _get_post_id(plugin_file)
+        if not post_id:
+            print(f"Skipped (no openwebui_id): {readme_path}")
+            continue
+
+        try:
+            if post_id in updated_post_ids:
+                print(f"Skipped (already updated via plugin): {readme_path}")
+                continue
+
+            post_data = client.get_post(post_id)
+            if not post_data:
+                print(f"Skipped (post not found): {readme_path}")
+                continue
+
+            readme_content = readme_path.read_text(encoding="utf-8")
+
+            # Update README content only, keep other fields unchanged.
+            post_data["content"] = readme_content
+
+            ok = client.update_post(post_id, post_data)
+            if ok:
+                print(f"Updated README -> {readme_path} (post_id: {post_id})")
+        except Exception as exc:
+            print(f"Failed: {readme_path} ({exc})")
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

plugins/debug/copilot_sdk_research/GUIDE_ERRATA.md

@@ -0,0 +1,98 @@
+# 开发指南勘误与更新
+
+## 权限控制章节修正（第 2.2 节）
+
+### ⚠️ 关键勘误
+
+在实际测试中发现，Shell 权限请求使用的是 **`fullCommandText`** 字段，而非文档中提到的 `command` 字段。
+
+### 需要修改的代码行
+
+**第 89 行（错误）：**
+
+```python
+command = request.get("command", "")
+```
+
+**应改为（正确）：**
+
+```python
+command = request.get("fullCommandText", "") or request.get("command", "")
+```
+
+### 完整的正确实现
+
+```python
+async def on_user_permission_request(request, context):
+    """
+    统一权限审批网关
+    """
+    kind = request.get("kind")  # shell, write, mcp, read, url
+    # ✅ 正确：使用 fullCommandText（shell）或 command（其他）
+    command = request.get("fullCommandText", "") or request.get("command", "")
+
+    # 1. 超级模式：全部允许
+    if self.valves.PERMISSIONS_ALLOW_ALL:
+        return {"kind": "approved"}
+
+    # 2. 默认安全：始终允许 "读" 和 "Web浏览"
+    if kind in ["read", "url"]:
+        return {"kind": "approved"}
+
+    # 3. 细粒度控制
+    if kind == "shell":
+        if self.valves.PERMISSIONS_ALLOW_SHELL:
+            return {"kind": "approved"}
+        
+        pattern = self.valves.PERMISSIONS_SHELL_ALLOW_PATTERN
+        if pattern and command:
+            try:
+                if re.match(pattern, command):
+                    return {"kind": "approved"}
+            except re.error:
+                print(f"[Config Error] Invalid Regex: {pattern}")
+
+    if kind == "write" and self.valves.PERMISSIONS_ALLOW_WRITE:
+        return {"kind": "approved"}
+        
+    if kind == "mcp" and self.valves.PERMISSIONS_ALLOW_MCP:
+        return {"kind": "approved"}
+
+    # 4. 默认拒绝
+    print(f"[Permission Denied] Blocked: {kind} {command}")
+    return {
+        "kind": "denied-by-rules", 
+        "rules": [{"kind": "check-openwebui-valves"}]
+    }
+```
+
+### Shell 权限请求的完整结构
+
+```json
+{
+  "kind": "shell",
+  "toolCallId": "call_xxx",
+  "fullCommandText": "ls -la",                    // ← 关键字段
+  "intention": "List all files and directories",
+  "commands": [
+    {
+      "identifier": "ls -la",
+      "readOnly": false
+    }
+  ],
+  "possiblePaths": [],
+  "possibleUrls": [],
+  "hasWriteFileRedirection": false,
+  "canOfferSessionApproval": false
+}
+```
+
+## 测试验证
+
+已通过完整测试套件验证（8/8 通过），详见 [PERMISSION_TEST_REPORT.md](./PERMISSION_TEST_REPORT.md)。
+
+---
+
+**更新日期**: 2026-01-30  
+**验证状态**: ✅ 已测试  
+**影响范围**: 2.2 权限与确认章节

plugins/debug/copilot_sdk_research/PERMISSION_TEST_REPORT.md

@@ -0,0 +1,173 @@
+# GitHub Copilot SDK 权限控制测试报告
+
+## 测试日期
+
+2026-01-30
+
+## 测试环境
+
+- **Model**: gpt-4.1
+- **Python**: 3.12
+- **Copilot SDK**: Latest
+
+## 关键发现
+
+### 1. Shell 权限请求结构
+
+Shell 类型的权限请求使用 **`fullCommandText`** 字段，而非 `command` 字段。
+
+**完整请求示例：**
+
+```json
+{
+  "kind": "shell",
+  "toolCallId": "call_JKLi7tz3uSDQWE3LgzCpvSVy",
+  "fullCommandText": "ls -la",
+  "intention": "List all files and directories with details in the current directory",
+  "commands": [
+    {
+      "identifier": "ls -la",
+      "readOnly": false
+    }
+  ],
+  "possiblePaths": [],
+  "possibleUrls": [],
+  "hasWriteFileRedirection": false,
+  "canOfferSessionApproval": false
+}
+```
+
+### 2. 正则匹配模式验证
+
+正则白名单模式已验证有效，必须使用 `fullCommandText` 字段：
+
+```python
+command = request.get("fullCommandText", "") or request.get("command", "")
+pattern = self.valves.PERMISSIONS_SHELL_ALLOW_PATTERN
+if pattern and command:
+    if re.match(pattern, command):
+        return {"kind": "approved"}
+```
+
+## 测试结果
+
+### 完整测试套件（8/8 通过 ✅）
+
+| # | 测试用例 | 配置 | 提示词 | 预期 | 结果 | 状态 |
+|---|---------|------|--------|------|------|------|
+| 1 | Default Deny Shell | 默认 | 请执行: ls -la | ❌ Denied | ❌ Denied | ✅ |
+| 2 | Allow All | allow_all=True | 请执行: ls -la | ✅ Approved | ✅ Approved | ✅ |
+| 3 | Allow Shell | allow_shell=True | 请执行: pwd | ✅ Approved | ✅ Approved | ✅ |
+| 4 | Regex Match: ^ls | pattern='^ls' | 请执行: ls -la | ✅ Approved | ✅ Approved | ✅ |
+| 5 | Regex No Match | pattern='^ls' | 请执行: pwd | ❌ Denied | ❌ Denied | ✅ |
+| 6 | Regex Complex | pattern='^(ls\|pwd\|echo)' | 请执行: pwd | ✅ Approved | ✅ Approved | ✅ |
+| 7 | Regex No Match: git | pattern='^(ls\|pwd\|echo)' | 请执行: git status | ❌ Denied | ❌ Denied | ✅ |
+| 8 | Read Permission | 默认 | Read: README.md | ✅ Approved | ✅ Approved | ✅ |
+
+**总体通过率: 100%** 🎉
+
+## 推荐配置示例
+
+### 1. 安全模式（推荐生产环境）
+
+```python
+PERMISSIONS_ALLOW_ALL: bool = False
+PERMISSIONS_ALLOW_SHELL: bool = False
+PERMISSIONS_SHELL_ALLOW_PATTERN: str = "^(ls|pwd|echo|cat).*"
+PERMISSIONS_ALLOW_WRITE: bool = False
+PERMISSIONS_ALLOW_MCP: bool = True
+```
+
+### 2. 开发模式
+
+```python
+PERMISSIONS_ALLOW_ALL: bool = False
+PERMISSIONS_ALLOW_SHELL: bool = False
+PERMISSIONS_SHELL_ALLOW_PATTERN: str = "^(ls|pwd|echo|cat|grep|git status|npm test).*"
+PERMISSIONS_ALLOW_WRITE: bool = False
+PERMISSIONS_ALLOW_MCP: bool = True
+```
+
+### 3. 完全信任模式（仅限受控环境）
+
+```python
+PERMISSIONS_ALLOW_ALL: bool = True
+```
+
+## 实现建议
+
+### 正确的权限处理代码
+
+```python
+import re
+from typing import Any, Dict
+
+async def on_user_permission_request(request: Dict[str, Any], context: Dict[str, str]):
+    """
+    统一权限审批网关
+    """
+    kind = request.get("kind")
+    # 关键：使用 fullCommandText 而非 command
+    command = request.get("fullCommandText", "") or request.get("command", "")
+
+    # 1. 超级模式
+    if self.valves.PERMISSIONS_ALLOW_ALL:
+        return {"kind": "approved"}
+
+    # 2. 默认安全（read、url）
+    if kind in ["read", "url"]:
+        return {"kind": "approved"}
+
+    # 3. Shell 细粒度控制
+    if kind == "shell":
+        if self.valves.PERMISSIONS_ALLOW_SHELL:
+            return {"kind": "approved"}
+        
+        pattern = self.valves.PERMISSIONS_SHELL_ALLOW_PATTERN
+        if pattern and command:
+            try:
+                if re.match(pattern, command):
+                    return {"kind": "approved"}
+            except re.error as e:
+                logger.error(f"Invalid regex: {pattern} - {e}")
+
+    # 4. Write 权限
+    if kind == "write" and self.valves.PERMISSIONS_ALLOW_WRITE:
+        return {"kind": "approved"}
+        
+    # 5. MCP 权限
+    if kind == "mcp" and self.valves.PERMISSIONS_ALLOW_MCP:
+        return {"kind": "approved"}
+
+    # 6. 默认拒绝
+    logger.warning(f"Permission Denied: {kind} {command}")
+    return {
+        "kind": "denied-by-rules", 
+        "rules": [{"kind": "security-policy"}]
+    }
+```
+
+## 常见正则模式示例
+
+| 用途 | 正则表达式 | 说明 |
+|------|-----------|------|
+| 只读命令 | `^(ls|pwd|cat|echo|grep).*` | 允许常见只读命令 |
+| Git 只读 | `^git (status\|log\|diff\|show).*` | 允许 Git 只读操作 |
+| npm/yarn 测试 | `^(npm\|yarn) (test\|run).*` | 允许测试脚本 |
+| 完全 shell | `.*` | ⚠️ 危险：允许所有命令 |
+
+## 测试脚本位置
+
+- 基础测试: [test_shell_permission_pattern.py](./test_shell_permission_pattern.py)
+- 完整测试套件: [test_permission_comprehensive.py](./test_permission_comprehensive.py)
+
+## 结论
+
+✅ **GitHub Copilot SDK 的权限控制机制完全有效**
+✅ **正则白名单模式已验证可用**  
+⚠️ **必须使用 `fullCommandText` 字段获取命令内容**
+
+---
+
+**测试执行者**: GitHub Copilot  
+**审核状态**: ✅ 已验证

plugins/debug/copilot_sdk_research/copilot_pipe_enhancement_guide.md

@@ -0,0 +1,238 @@
+# OpenWebUI GitHub Copilot Pipe Enhancement Guide
+
+基于 Copilot SDK 源码级研究的深度技术总结，旨在指导 OpenWebUI Pipe 的功能增强开发。
+
+## 1. 认证机制 (Authentication)
+
+官方支持通过环境变量传递 Token。在 Pipe 中，只要确保 `GH_TOKEN` 或 `GITHUB_TOKEN` 存在于环境变量中，Copilot CLI 即可自动识别，无需在 `CopilotClient` 构造函数中重复注入。
+
+### 核心实现
+
+Pipe 应确保将 Token（来自 Valve 或 Env）正确设置到当前进程的环境变量中。
+
+```python
+import os
+from copilot import CopilotClient
+
+# 1. 设置环境变量 (如果从 Valve 获取)
+if self.valves.GH_TOKEN:
+    os.environ["GH_TOKEN"] = self.valves.GH_TOKEN
+
+# 2. 初始化客户端
+# CopilotClient 启动的 CLI 子进程会自动继承当前环境中的 GH_TOKEN
+client = CopilotClient({
+    # "cli_path": ...,
+    # 注意：无需在此处重复传入 github_token，CLI 会自动读取环境变量
+})
+
+# 3. 启动前检查 (建议)
+# status = await client.get_auth_status()
+# if not status.isAuthenticated: ...
+```
+
+## 2. 权限与确认 (Permissions & Tools) - 核心控制点
+
+这是用户最关心的部分：如何知道有哪些工具，以及如何控制它们的执行。
+
+### 2.1 内置工具 (Built-in Tools)
+
+Copilot CLI 内部管理了一组标准工具，**Python SDK 目前没有直接的 API (`client.list_tools()`) 来列出这些工具**。
+
+但是，根据 SDK 的 `PermissionRequest` 类型定义 (`copilot/types.py`)，我们可以反推其能力类别：
+
+* **`shell`**: 执行终端命令 (对应 `run_terminal_command` 等)
+* **`filesystem`** (对应 `read/write`): 文件读写 (对应 `read_file`, `edit_file`, `delete_file` 等)
+* **`url`**: 网络访问 (对应 `fetch_url` 等)
+* **`mcp`**: 连接的 MCP 服务器工具
+
+> **提示**: `available_tools` 参数可以用来“隐藏”工具，让 Agent 根本不知道它有一把锤子。而 `on_permission_request` 是用来拦截 Agent 挥舞锤子的动作。通常我们建议**能力全开 (不设置 available_tools 限制)**，而在**权限层 (on_permission_request) 做拦截**。
+
+### 2.2 实现“全部允许”与“按需允许”
+
+建议在 Valves 中增加权限控制字段，并在 `on_permission_request` 中实现逻辑。
+
+```python
+import re
+
+class Valves(BaseModel):
+    # ... 其他 Valve ...
+    # 权限控制开关
+    PERMISSIONS_ALLOW_ALL: bool = Field(default=False, description="DANGER: Auto-approve ALL actions (shell, write, etc).")
+    PERMISSIONS_ALLOW_SHELL: bool = Field(default=False, description="Auto-approve shell commands.")
+    PERMISSIONS_SHELL_ALLOW_PATTERN: str = Field(default="", description="Regex for approved shell commands (e.g., '^ls|^grep').")
+    PERMISSIONS_ALLOW_WRITE: bool = Field(default=False, description="Auto-approve file write/edit/delete.")
+    PERMISSIONS_ALLOW_MCP: bool = Field(default=True, description="Auto-approve MCP tool execution.")
+
+# 权限处理 Hook 实现
+async def on_user_permission_request(request, context):
+    """
+    统一权限审批网关
+    request keys: kind, toolCallId, ... (shell requests have 'command')
+    """
+    kind = request.get("kind") # shell, write, mcp, read, url
+
+    # 1. 超级模式：全部允许
+    if self.valves.PERMISSIONS_ALLOW_ALL:
+        return {"kind": "approved"}
+
+    # 2. 默认安全：始终允许 "读" 和 "Web浏览" (根据需求调整)
+    if kind in ["read", "url"]:
+        return {"kind": "approved"}
+
+    # 3. 细粒度控制
+    if kind == "shell":
+        # 3.1 完全允许 Shell
+        if self.valves.PERMISSIONS_ALLOW_SHELL:
+            return {"kind": "approved"}
+        
+        # 3.2 基于正则允许特定命令
+        command = request.get("command", "")
+        pattern = self.valves.PERMISSIONS_SHELL_ALLOW_PATTERN
+        if pattern and command:
+            try:
+                if re.match(pattern, command):
+                    return {"kind": "approved"}
+            except re.error:
+                print(f"[Config Error] Invalid Regex: {pattern}")
+
+    if kind == "write" and self.valves.PERMISSIONS_ALLOW_WRITE:
+        return {"kind": "approved"}
+        
+    if kind == "mcp" and self.valves.PERMISSIONS_ALLOW_MCP:
+        return {"kind": "approved"}
+
+    # 4. 默认拒绝
+    print(f"[Permission Denied] Blocked request for: {kind} {request.get('command', '')}")
+    return {
+        "kind": "denied-by-rules", 
+        "rules": [{"kind": "check-openwebui-valves"}]
+    }
+
+# 注册 Hook
+session = await client.create_session({
+    # ... 
+    "on_permission_request": on_user_permission_request
+})
+```
+
+## 3. Agent 与 MCP 集成 (Agents & MCP)
+
+SDK 中的 Agent 和 MCP 并非独立文件，而是会话配置 (`SessionConfig`) 的一部分。Pipe 可以通过 Valves 动态构建这些配置。
+
+### 关键映射关系
+
+| SDK 概念 | OpenWebUI 对应 | 实现位置 | 关键参数 |
+| :--- | :--- | :--- | :--- |
+| **Custom Agent** | 自定义模型 / Persona | `create_session(custom_agents=[...])` | `name`, `prompt`, `tools` (仅名称) |
+| **Agent Tools** | Valve 开关 / 预置工具 | `create_session(tools=[func1, func2])` | 必须先在 `tools` 注册函数，Agent 才能引用 |
+| **MCP Server** | Valve 配置 (JSON) | `create_session(mcp_servers={...})` | `command`, `args`, `env` (本地) |
+
+### 代码范式：动态构建 Agent
+
+```python
+async def create_agent_session(client, user_prompt, model_name):
+    # 1. 定义工具 (必须是函数引用)
+    # 假设已从 OpenWebUI Tools 转换或内置
+    available_tools = [tool_web_search, tool_run_script] 
+    
+    # 2. 构建 Agent Manifest (针对当前请求的虚拟 Agent)
+    agent_manifest = {
+        "name": "openwebui_agent",
+        "description": "Dynamic agent from OpenWebUI",
+        "prompt": "You are a helpful assistant...", # 这里注入 System Prompt
+        "tools": ["web_search", "run_script"],    # 引用上方工具的 name
+        "mcp_servers": {
+            # 可以在这里为特定 Agent 绑定 MCP
+        }
+    }
+
+    # 3. 创建会话
+    session = await client.create_session({
+        "model": "gpt-4", # 底层模型
+        "custom_agents": [agent_manifest],
+        "tools": available_tools,          # 注册实际代码
+        "available_tools": ["web_search"], # 白名单控制当前可用工具
+        # ... 权限配置
+    })
+```
+
+## 4. MCP 服务器配置 (Native MCP Support)
+
+Pipe 可以直接支持标准 MCP 协议（Stdio）。不需要额外的 MCP 客户端代理，SDK 原生支持。
+
+### Valve 配置结构建议
+
+建议在 Pipe 的 Valves 中增加一个 `MCP_CONFIG` 字段（JSON 字符串），解析后直接传给 SDK。
+
+```python
+# Valve 输入示例 (JSON)
+# {
+#   "brave_search": {
+#     "type": "local",
+#     "command": "npx",
+#     "args": ["-y", "@modelcontextprotocol/server-brave-search"],
+#     "env": {"BRAVE_API_KEY": "..."}
+#   }
+# }
+
+# 代码实现
+mcp_config = json.loads(self.valves.MCP_CONFIG)
+session = await client.create_session({
+    # ...
+    "mcp_servers": mcp_config,
+    # 注意：必须配合权限自动审批，否则 MCP 工具无法调用
+    "on_permission_request": auto_approve_policy 
+})
+```
+
+## 5. 会话管理：持久化 vs 重放 (Persistence)
+
+OpenWebUI 是无状态的，但 Copilot SDK 是有状态的（保留上下文窗口优化）。
+
+### 最佳实践：以 `chat_id` 为锚点
+
+利用 OpenWebUI 提供的 `chat_id` 来决定是 `resume` 还是 `start`。
+
+1. **Map**: 维护 `Dict[chat_id, session_id]` (内存或数据库)。
+2. **Flow**:
+    * 请求进来 -> 检查 `chat_id` 是否有对应的 `session_id`。
+    * **有**: 尝试 `client.resume_session(session_id)`。
+        * *注意*：Resume 时必须重新传入 `tools`, `hooks`, `on_permission_request`，因为这些 Python 对象不会被序列化保存。
+    * **无/失败**: 调用 `client.create_session()`，并将新 `session_id` 存入 Map。
+3. **Fallback**: 如果 Resume 失败（例如后端重启 SDK 进程丢失），回退到 Create 新会话，并可选地将 OpenWebUI 传来的 `messages` 历史以 System Message 或历史插入的方式“重放”进去（虽然 SDK 不直接支持 insert history，但可以通过连续的 `send` 模拟，但这很慢）。
+    * *简易方案*：Resume 失败就作为新对话开始，只带入 System Prompt。
+
+## 6. 高级 Hook：提示词增强
+
+利用 `on_user_prompt_submitted` 钩子，可以在不修改用户可见内容的情况下，向 Copilot 注入隐式上下文（例如当前文件内容、Pipe 的元指令）。
+
+```python
+async def inject_context_hook(input_data, ctx):
+    user_prompt = input_data["prompt"]
+    
+    # 比如：检测到用户在问代码，自动附加上下文
+    additional_context = "Current Language: Python. Framework: OpenWebUI."
+    
+    return {
+        "modifiedPrompt": user_prompt, # 可以在这里改写提示词
+        "additionalContext": additional_context # 注入隐藏上下文
+    }
+
+session = await client.create_session({
+    # ...
+    "hooks": {
+        "on_user_prompt_submitted": inject_context_hook
+    }
+})
+```
+
+---
+
+**总结开发清单：**
+
+1. [ ] **Env Auth**: 读取环境变量 -> `CopilotClient`。
+2. [ ] **Permission Valve**: 实现 `PERMISSIONS_ALLOW_ALL/SHELL` 等 Valves。
+3. [ ] **Auto-Approve Hook**: 实现 `on_permission_request` 逻辑。
+4. [ ] **MCP Valve**: 添加 JSON Valve -> `session.mcp_servers`。
+5. [ ] **Session Map**: 实现 `chat_id` <-> `session_id` 的简单的内存映射。
+6. [ ] **Resume Logic**: 优先 `resume_session`，并记得并在 resume 时重传 Hook 和 Tools。

plugins/debug/copilot_sdk_research/copilot_sdk_guide.py

@@ -0,0 +1,620 @@
+#!/usr/bin/env python3
+import argparse
+import asyncio
+import datetime as dt
+import json
+import logging
+import os
+import sys
+import textwrap
+from typing import Iterable, List, Optional
+
+from copilot import CopilotClient
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+)
+logger = logging.getLogger("copilot_sdk_guide")
+
+DEFAULT_CONTEXT_URLS = [
+    "https://raw.githubusercontent.com/github/copilot-sdk/main/README.md",
+    "https://raw.githubusercontent.com/github/copilot-sdk/main/python/README.md",
+    "https://raw.githubusercontent.com/github/copilot-sdk/main/docs/getting-started.md",
+    "https://raw.githubusercontent.com/github/copilot-cli/main/README.md",
+    "https://raw.githubusercontent.com/github/copilot-cli/main/changelog.md",
+    "https://docs.github.com/en/copilot/concepts/agents/about-copilot-cli",
+    "https://docs.github.com/en/copilot/concepts/agents/about-agent-skills",
+    "https://raw.githubusercontent.com/github/awesome-copilot/main/README.md",
+    "https://raw.githubusercontent.com/github/awesome-copilot/main/skills/copilot-sdk/SKILL.md",
+    "https://raw.githubusercontent.com/github/awesome-copilot/main/instructions/agent-skills.instructions.md",
+]
+
+AWESOME_COPILOT_REPO = "github/awesome-copilot"
+AWESOME_COPILOT_BRANCH = "main"
+AWESOME_COPILOT_DOC_DIRS = ["docs/", "instructions/"]
+
+TOPICS = [
+    "MCP Server Integration: JSON-RPC config and SDK hooks",
+    "Agent Manifests: Defining capabilities and permissions programmatically",
+    "Headless Auth: Device Code Flow and credential persistence",
+    "Session Replay vs Resume: Handling stateless frontend history",
+    "Advanced Session Hooks: Intercepting and modifying user prompts",
+    "Workspace Virtualization: Handling CWD for remote/virtual files",
+    "Error Recovery: Handling session disconnects and re-auth",
+    "Confirmation Events: programmatic handling of 'confirmation_required'",
+    "Skills: Conflict resolution and precedence defaults",
+    "Debugging: Tracing JSON-RPC traffic in the SDK",
+    "Billing & Policies: How seat management affects SDK features",
+]
+
+QUESTION_TEMPLATES = [
+    "Give a concise overview of {topic}.",
+    "Provide best practices and common pitfalls for {topic}.",
+    "Show a minimal example snippet for {topic}.",
+    "List recommended configuration defaults for {topic}.",
+    "How does {topic} relate to building a custom Agent?",
+]
+
+CLI_FOCUS_QUESTIONS = [
+    "How to configure MCP servers in ~/.copilot/config.json for SDK usage?",
+    "What CLI environment variables force 'Agent' mode vs 'Generic' mode?",
+    "Explain the 'confirmation' flow in CLI and how it maps to SDK events.",
+    "Does the CLI support 'dry-run' permission checks for tools?",
+    "What are the undocumented requirements for 'workspace' context updates?",
+    "How does the CLI handle 'device code' re-authentication automatically?",
+]
+
+
+def build_questions(max_questions: int) -> List[str]:
+    questions: List[str] = []
+
+    for topic in TOPICS:
+        for template in QUESTION_TEMPLATES:
+            questions.append(template.format(topic=topic))
+
+    questions.extend(CLI_FOCUS_QUESTIONS)
+
+    # De-duplicate while preserving order
+    seen = set()
+    uniq: List[str] = []
+    for q in questions:
+        if q in seen:
+            continue
+        seen.add(q)
+        uniq.append(q)
+
+    return uniq[:max_questions]
+
+
+def build_deep_dive_prompts() -> List[str]:
+    return [
+        "Provide a python code example for configuring `CopilotClient` to connect to a local MCP server (e.g. Brave Search) via `CopilotClient` config.",
+        "Explain how to programmatically handle `tool.confirmation_required` events in a non-interactive stream using `session.on()`.",
+        "Show how to implement a 'Device Flow' login helper using SDK primitives (if available) or raw HTTP showing how to persist credentials.",
+        "Compare the pros and cons of 'Session Replay' (fast-forwarding history) vs 'Session Resume' (stateful ID) for a stateless web backend like OpenWebUI.",
+        "Detail the exact protocol for 'Virtual Workspace': how to implement a file system provider that feeds content to Copilot without physical files.",
+        "Create an 'Agent Manifest' example: how to define an Agent capable of specific high-privileged tools via SDK.",
+        "List all 'hidden' `SessionConfig` parameters relevant to Agent behavior and personality.",
+    ]
+
+
+def load_questions(path: str) -> List[str]:
+    if path.lower().endswith(".json"):
+        with open(path, "r", encoding="utf-8") as f:
+            data = json.load(f)
+        if isinstance(data, list):
+            return [str(x).strip() for x in data if str(x).strip()]
+        raise ValueError("JSON must be an array of strings")
+
+    with open(path, "r", encoding="utf-8") as f:
+        lines = [line.strip() for line in f.readlines()]
+    return [line for line in lines if line]
+
+
+def fetch_url(url: str, headers: Optional[dict] = None) -> str:
+    import urllib.request
+    import time
+
+    retries = 3
+    if headers is None:
+        headers = {}
+
+    req = urllib.request.Request(url, headers=headers)
+
+    for i in range(retries):
+        try:
+            with urllib.request.urlopen(req, timeout=20) as response:
+                return response.read().decode("utf-8", errors="replace")
+        except Exception as exc:
+            if i == retries - 1:
+                logger.warning(
+                    "Failed to fetch %s after %d attempts: %s", url, retries, exc
+                )
+                return ""
+            time.sleep(1 * (i + 1))
+    return ""
+
+
+def list_repo_markdown_urls(
+    repo: str,
+    branch: str,
+    dir_prefixes: List[str],
+) -> List[str]:
+    api_url = f"https://api.github.com/repos/{repo}/git/trees/{branch}?recursive=1"
+    headers = {}
+    if os.environ.get("GITHUB_TOKEN"):
+        headers["Authorization"] = f"token {os.environ.get('GITHUB_TOKEN')}"
+
+    try:
+        content = fetch_url(api_url, headers=headers)
+        if not content:
+            return []
+        data = json.loads(content)
+    except Exception as exc:
+        logger.warning("Failed to list repo tree: %s", exc)
+        return []
+
+    tree = data.get("tree", []) if isinstance(data, dict) else []
+    urls: List[str] = []
+    for item in tree:
+        if not isinstance(item, dict):
+            continue
+        path = item.get("path", "")
+        if not path or not path.endswith(".md"):
+            continue
+        if any(path.startswith(prefix) for prefix in dir_prefixes):
+            raw = f"https://raw.githubusercontent.com/{repo}/{branch}/{path}"
+            urls.append(raw)
+    return urls
+
+
+def read_local_sdk_source(max_chars: int = 300000) -> str:
+    """
+    Locates the installed 'copilot' package and reads its source code.
+    This ensures analysis is based on the actual installed version, not just docs.
+    """
+    try:
+        import copilot
+    except ImportError:
+        logger.error("Could not import 'copilot' SDK. Is it installed?")
+        return ""
+
+    package_dir = os.path.dirname(copilot.__file__)
+    logger.info(f"Reading SDK source from: {package_dir}")
+
+    source_chunks = []
+    total_chars = 0
+
+    # Prioritize key files that define core logic
+    priority_files = ["client.py", "session.py", "types.py", "events.py", "__init__.py"]
+
+    # First pass: Recursively find all .py files
+    all_py_files = []
+    for root, dirs, files in os.walk(package_dir):
+        if "__pycache__" in root:
+            continue
+        for file in files:
+            if file.endswith(".py"):
+                all_py_files.append(os.path.join(root, file))
+
+    # Sort files: priority files first, then alphabetical
+    def sort_key(path):
+        fname = os.path.basename(path)
+        if fname in priority_files:
+            return (0, priority_files.index(fname))
+        return (1, path)
+
+    all_py_files.sort(key=sort_key)
+
+    for path in all_py_files:
+        rel_path = os.path.relpath(path, os.path.dirname(package_dir))
+        try:
+            with open(path, "r", encoding="utf-8") as f:
+                content = f.read()
+
+            # Add file delimiter for the model
+            header = f"\n\n# ==================================================\n# SOURCE CODE FILE: {rel_path}\n# ==================================================\n"
+            chunk = header + content
+
+            if total_chars + len(chunk) > max_chars:
+                remaining = max_chars - total_chars
+                if remaining > len(header) + 100:
+                    source_chunks.append(
+                        chunk[:remaining] + "\n# [TRUNCATED DUE TO LENGTH LIMIT]"
+                    )
+                logger.warning(f"Context limit reached. Stopping at {rel_path}")
+                break
+
+            source_chunks.append(chunk)
+            total_chars += len(chunk)
+            logger.info(f"Loaded source file: {rel_path} ({len(content)} chars)")
+
+        except Exception as e:
+            logger.warning(f"Failed to read source file {path}: {e}")
+
+    return "".join(source_chunks)
+
+
+def build_context(urls: Iterable[str], max_chars: int) -> str:
+    chunks: List[str] = []
+    remaining = max_chars
+
+    for url in urls:
+        if remaining <= 0:
+            break
+        try:
+            content = fetch_url(url)
+            header = f"[Source: {url}]\n"
+            if len(header) >= remaining:
+                break
+            remaining -= len(header)
+
+            if len(content) > remaining:
+                content = content[:remaining] + "\n[TRUNCATED]\n"
+                remaining = 0
+            else:
+                remaining -= len(content)
+
+            chunks.append(header + content)
+            logger.info("Fetched context: %s", url)
+        except Exception as exc:
+            logger.warning("Failed to fetch %s: %s", url, exc)
+
+    return "\n\n".join(chunks)
+
+
+def write_jsonl(path: str, item: dict) -> None:
+    with open(path, "a", encoding="utf-8") as f:
+        f.write(json.dumps(item, ensure_ascii=False) + "\n")
+
+
+def write_markdown_header(path: str, title: str, meta: dict) -> None:
+    with open(path, "w", encoding="utf-8") as f:
+        f.write(f"# {title}\n\n")
+        for k, v in meta.items():
+            f.write(f"- **{k}**: {v}\n")
+        f.write("\n---\n\n")
+
+
+def append_markdown_qa(path: str, question: str, answer: str) -> None:
+    with open(path, "a", encoding="utf-8") as f:
+        f.write(f"## Q: {question}\n\n")
+        f.write(f"{answer}\n\n")
+
+
+def clamp_questions(questions: List[str], max_questions: int) -> List[str]:
+    return questions[: max(1, min(max_questions, 400))]
+
+
+def print_progress_bar(
+    iteration,
+    total,
+    prefix="",
+    suffix="",
+    decimals=1,
+    length=50,
+    fill="█",
+    printEnd="\r",
+):
+    """
+    Call in a loop to create terminal progress bar
+    """
+    percent = ("{0:." + str(decimals) + "f}").format(100 * (iteration / float(total)))
+    filledLength = int(length * iteration // total)
+    bar = fill * filledLength + "-" * (length - filledLength)
+    # Clear line extension to handle shrinking suffixes
+    print(f"\r{prefix} |{bar}| {percent}% {suffix}\033[K", end=printEnd)
+    # Print New Line on Complete
+    if iteration == total:
+        print()
+
+
+async def run_session(
+    model: str,
+    questions: List[str],
+    output_dir: str,
+    context: str,
+    session_id: Optional[str],
+    delay: float,
+    output_lang: str,
+    enable_infinite_sessions: bool,
+    timeout: int,
+) -> None:
+    client = CopilotClient()
+    await client.start()
+
+    session_config = {"model": model}
+    if session_id:
+        session_config["session_id"] = session_id
+    if enable_infinite_sessions:
+        session_config["infinite_sessions"] = {
+            "enabled": True,
+            "background_compaction_threshold": 0.8,
+            "buffer_exhaustion_threshold": 0.95,
+        }
+
+    session = await client.create_session(session_config)
+
+    timestamp = dt.datetime.now().strftime("%Y%m%d_%H%M%S")
+    jsonl_path = os.path.join(output_dir, f"copilot_sdk_guide_{timestamp}.jsonl")
+    md_path = os.path.join(output_dir, f"copilot_sdk_guide_{timestamp}.md")
+
+    write_markdown_header(
+        md_path,
+        "GitHub Copilot SDK & CLI 研究报告",
+        {
+            "model": model,
+            "questions": len(questions),
+            "timestamp": timestamp,
+            "language": output_lang,
+        },
+    )
+
+    lang_instruction = "Chinese" if "zh" in output_lang.lower() else "English"
+
+    system_prompt = textwrap.dedent(
+        f"""
+        You are an expert assistant. Focus on GitHub Copilot SDK and GitHub Copilot CLI.
+        
+        CRITICAL INSTRUCTION: SOURCE CODE FIRST.
+        You have been provided with the ACTUAL PYTHON SOURCE CODE of the `copilot` SDK in the context.
+        When answering questions:
+        1. FIRST, analyze the provided source code (look for class definitions, type hints, methods).
+        2. THEN, refer to documentation if source code is ambiguous.
+        3. Do NOT hallucinate methods that do not exist in the source code.
+        4. If a feature (like MCP) is not explicitly in the code, explain how to implement it using the available primitives (low-level hooks/events).
+
+        Provide accurate, concise answers in {lang_instruction}. When relevant, include command names,
+        configuration keys, and pitfalls. Use bullet points where useful.
+
+        Output requirements:
+        - Write in {lang_instruction}.
+        - Provide practical code snippets (Python/TypeScript/CLI) when helpful.
+        - Include a short "建议/落地" section for integration into a pipe.
+        - If citing facts from provided context, briefly mention the source URL.
+        """
+    ).strip()
+
+    if context:
+        system_prompt += "\n\nAdditional context:\n" + context
+
+    await session.send_and_wait({"prompt": system_prompt}, timeout=timeout)
+
+    total_q = len(questions)
+    print_progress_bar(0, total_q, prefix="Progress:", suffix="Starting...", length=30)
+
+    for idx, question in enumerate(questions, start=1):
+        # Update progress bar (Asking...)
+        q_short = (question[:40] + "...") if len(question) > 40 else question.ljust(43)
+        print_progress_bar(
+            idx - 1, total_q, prefix="Progress:", suffix=f"Asking: {q_short}", length=30
+        )
+
+        # Log to file/debug only
+        logger.debug("[%s/%s] Asking: %s", idx, total_q, question)
+
+        answer = ""
+        max_retries = 3
+        for attempt in range(max_retries):
+            try:
+                response = await session.send_and_wait(
+                    {"prompt": question}, timeout=timeout
+                )
+                answer = response.data.content if response and response.data else ""
+                break
+            except Exception as e:
+                logger.error(
+                    f"Error asking question (Attempt {attempt+1}/{max_retries}): {e}"
+                )
+                if attempt < max_retries - 1:
+                    await asyncio.sleep(2)
+                else:
+                    answer = f"Error retrieving answer: {e}"
+
+        write_jsonl(
+            jsonl_path,
+            {
+                "index": idx,
+                "question": question,
+                "answer": answer,
+                "model": model,
+            },
+        )
+        append_markdown_qa(md_path, question, answer)
+
+        # Update progress bar (Done...)
+        print_progress_bar(
+            idx, total_q, prefix="Progress:", suffix=f"Done: {q_short}", length=30
+        )
+
+        if delay > 0:
+            await asyncio.sleep(delay)
+
+    await session.destroy()
+    await client.stop()
+
+    logger.info("Saved output to %s and %s", jsonl_path, md_path)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Ask up to 100 Copilot SDK questions via GitHub Copilot SDK",
+    )
+    parser.add_argument("--model", default="gpt-5.2-codex", help="Model to use")
+    parser.add_argument(
+        "--max-questions",
+        type=int,
+        default=100,
+        help="Max number of questions (1-400)",
+    )
+    parser.add_argument(
+        "--questions-file",
+        default="",
+        help="Path to .txt or .json list of questions",
+    )
+    parser.add_argument(
+        "--context-url",
+        action="append",
+        default=[],
+        help="Additional context URL (repeatable)",
+    )
+    parser.add_argument(
+        "--no-default-context",
+        action="store_true",
+        help="Disable default Copilot SDK context URLs",
+    )
+    parser.add_argument(
+        "--include-awesome-copilot-docs",
+        action="store_true",
+        help="Include all markdown files from awesome-copilot/docs",
+    )
+    parser.add_argument(
+        "--include-awesome-copilot-instructions",
+        action="store_true",
+        help="Include all markdown files from awesome-copilot/instructions",
+    )
+    parser.add_argument(
+        "--no-sdk-source",
+        action="store_true",
+        help="Do NOT read local SDK source code (default: reads source)",
+    )
+    parser.add_argument(
+        "--session-id",
+        default="",
+        help="Optional custom session ID",
+    )
+    parser.add_argument(
+        "--output-dir",
+        default="",
+        help="Directory to save outputs",
+    )
+    parser.add_argument(
+        "--delay",
+        type=float,
+        default=0.5,
+        help="Delay between questions (seconds)",
+    )
+    parser.add_argument(
+        "--max-context-chars",
+        type=int,
+        default=400000,
+        help="Max characters of aggregated context (default: 400000)",
+    )
+    parser.add_argument(
+        "--disable-infinite-sessions",
+        action="store_true",
+        help="Disable infinite sessions (default: enabled)",
+    )
+    parser.add_argument(
+        "--output-lang",
+        default="zh-CN",
+        help="Output language (default: zh-CN)",
+    )
+    parser.add_argument(
+        "--deep-dive",
+        action="store_true",
+        help="Append deep-dive prompts for more detailed research",
+    )
+    parser.add_argument(
+        "--timeout",
+        type=int,
+        default=3600,
+        help="Session request timeout in seconds (default: 3600)",
+    )
+    return parser.parse_args()
+
+
+def main() -> None:
+    args = parse_args()
+
+    if args.questions_file:
+        questions = load_questions(args.questions_file)
+    else:
+        # Generate enough questions to cover everything
+        questions = build_questions(9999)
+
+    if args.deep_dive:
+        # Prepend deep dive questions to ensure they are prioritized
+        questions = build_deep_dive_prompts() + questions
+
+    questions = clamp_questions(questions, args.max_questions)
+    if not questions:
+        logger.error("No questions to ask")
+        sys.exit(1)
+
+    context_urls = [] if args.no_default_context else list(DEFAULT_CONTEXT_URLS)
+
+    if args.include_awesome_copilot_docs:
+        context_urls.extend(
+            list_repo_markdown_urls(
+                AWESOME_COPILOT_REPO,
+                AWESOME_COPILOT_BRANCH,
+                ["docs/"],
+            )
+        )
+
+    if args.include_awesome_copilot_instructions:
+        context_urls.extend(
+            list_repo_markdown_urls(
+                AWESOME_COPILOT_REPO,
+                AWESOME_COPILOT_BRANCH,
+                ["instructions/"],
+            )
+        )
+
+    context_urls.extend(args.context_url or [])
+
+    # 1. Read local source code first (Priority: High)
+    # We allocate up to max_context_chars to source code initially.
+    # The actual usage will likely be less for a typical SDK.
+    source_context = ""
+    source_chars_count = 0
+    if not args.no_sdk_source:
+        source_context = read_local_sdk_source(args.max_context_chars)
+        source_chars_count = len(source_context)
+        logger.info(f"Source context usage: {source_chars_count} chars")
+
+    # 2. Calculate remaining budget for Web Docs (Priority: Secondary)
+    # We ensure we don't exceed the global limit.
+    remaining_chars = max(10000, args.max_context_chars - source_chars_count)
+    logger.info(f"Remaining budget for web docs: {remaining_chars} chars")
+
+    # 3. Fetch remote docs
+    web_context = build_context(context_urls, remaining_chars)
+
+    combined_context = ""
+    # Assemble context in order of authority (Source > Docs)
+    if source_context:
+        combined_context += (
+            "# PRIMARY SOURCE: LOCAL SDK CODE (AUTHORITATIVE)\n"
+            + source_context
+            + "\n\n"
+        )
+    if web_context:
+        combined_context += (
+            "# SECONDARY SOURCE: WEB DOCUMENTATION & AWESOME-COPILOT\n" + web_context
+        )
+
+    output_dir = args.output_dir or os.path.join(
+        os.getcwd(), "plugins", "debug", "copilot_sdk_research", "outputs"
+    )
+    os.makedirs(output_dir, exist_ok=True)
+
+    asyncio.run(
+        run_session(
+            model=args.model,
+            questions=questions,
+            output_dir=output_dir,
+            context=combined_context,
+            session_id=args.session_id or None,
+            delay=args.delay,
+            output_lang=args.output_lang,
+            enable_infinite_sessions=not args.disable_infinite_sessions,
+            timeout=args.timeout,
+        )
+    )
+
+
+if __name__ == "__main__":
+    main()

plugins/debug/copilot_sdk_research/dummy_test_file.txt

@@ -0,0 +1,2 @@
+This is a dummy test file for verifying permission controls.
+You can delete this file safely.

plugins/debug/copilot_sdk_research/inspect_permissions.py

@@ -0,0 +1,26 @@
+import inspect
+import json
+
+try:
+    import copilot
+    from copilot import types
+
+    print(f"Copilot location: {copilot.__file__}")
+
+    print("\n=== Inspecting PermissionRequest types ===")
+    # Look for definition of PermissionRequest or similar
+
+    # In the absence of direct access to the CLI output structure documentation,
+    # we can check if there are type hints or typed dicts in copilot.types
+
+    for name, obj in inspect.getmembers(types):
+        if "Permission" in name or "Request" in name:
+            print(f"\nType: {name}")
+            try:
+                if hasattr(obj, "__annotations__"):
+                    print(obj.__annotations__)
+            except:
+                pass
+
+except ImportError:
+    print("copilot module not installed")

plugins/debug/copilot_sdk_research/outputs/copilot_sdk_guide_20260130_114642.jsonl

@@ -0,0 +1,68 @@
+{"index": 1, "question": "Provide a python code example for configuring `CopilotClient` to connect to a local MCP server (e.g. Brave Search) via `CopilotClient` config.", "answer": "SDK 源码显示 MCP 服务器通过 `create_session`/`resume_session` 的 `mcp_servers` 配置传入并映射为 `mcpServers`，不是 CopilotClient 构造参数（源：本地源码 copilot/types.py / copilot/client.py）。下面是本地 stdio MCP（以 Brave Search 为例，命令/密钥请替换）的 Python 示例。  \n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"mcp_servers\": {\n            \"brave_search\": {\n                \"type\": \"local\",  # 或 \"stdio\"\n                \"command\": \"/path/to/brave-search-mcp\",  # 替换为你的 MCP server 启动命令\n                \"args\": [],\n                \"env\": {\"BRAVE_API_KEY\": \"YOUR_KEY\"},\n                \"tools\": [\"*\"],\n                \"timeout\": 30000,  # 毫秒\n            }\n        },\n    })\n\n    await session.send_and_wait({\"prompt\": \"用 Brave Search 查询 OpenAI 最新公告\"})\n    await client.stop()\n\nasyncio.run(main())\n```\n\n要点/坑：\n- `tools`: `[\"*\"]` 表示全量，`[]` 表示不启用\n- `timeout`: 毫秒\n- `command/args/env`: 按你的 MCP server 实际启动方式替换\n\n建议/落地：\n- pipe 内复用同一 session，结束时统一 `client.stop()`", "model": "gpt-5.2-codex"}
+{"index": 2, "question": "Explain how to programmatically handle `tool.confirmation_required` events in a non-interactive stream using `session.on()`.", "answer": "SDK 源码未定义 `tool.confirmation_required` 事件，权限确认由 JSON‑RPC `permission.request` 触发并交给 `on_permission_request` 回调处理，`session.on()` 只能订阅 `tool.user_requested`/`tool.execution_start` 等事件做记录关联（来源：本地源码 copilot/client.py、copilot/session.py、copilot/types.py）。  \n在非交互流里必须提供 `on_permission_request` 自动审批/拒绝，否则默认拒绝且回调异常也会被拒绝。\n\n要点/坑  \n- 配置键: `on_permission_request`（SessionConfig）  \n- 权限类型: `shell` / `write` / `mcp` / `read` / `url`  \n- 回调异常或缺失 -> `denied-no-approval-rule-and-could-not-request-from-user`\n\n```python\nimport asyncio\nfrom copilot import CopilotClient\nfrom copilot.generated.session_events import SessionEventType\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    def on_event(ev):\n        if ev.type == SessionEventType.TOOL_USER_REQUESTED:\n            print(f\"tool requested: {ev.data.tool_name} {ev.data.tool_call_id}\")\n        elif ev.type == SessionEventType.TOOL_EXECUTION_START:\n            print(f\"tool start: {ev.data.tool_name}\")\n\n    async def on_permission_request(req, ctx):\n        kind = req.get(\"kind\")\n        if kind in (\"read\", \"mcp\"):\n            return {\"kind\": \"approved\"}\n        return {\"kind\": \"denied-by-rules\", \"rules\": [{\"kind\": \"deny-non-read\"}]}\n\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"on_permission_request\": on_permission_request,\n    })\n    session.on(on_event)\n\n    await session.send_and_wait({\"prompt\": \"请调用需要权限的工具\"})\n    await client.stop()\n\nasyncio.run(main())\n```\n\n建议/落地  \n- pipe 启动时注册审批策略 + `session.on` 记录 `tool_call_id` 做审计", "model": "gpt-5.2-codex"}
+{"index": 3, "question": "Show how to implement a 'Device Flow' login helper using SDK primitives (if available) or raw HTTP showing how to persist credentials.", "answer": "SDK 本身没有 device‑flow 登录 API；可用鉴权原语只有 CopilotClient 的 `github_token`/`use_logged_in_user` 与 `get_auth_status`（源：本地源码 copilot/client.py、copilot/types.py）。  \n下面用 GitHub OAuth Device Flow 原始 HTTP 获取 token、持久化本地并注入 `github_token`（端点说明：https://docs.github.com/en/apps/oauth-apps/building-oauth-apps/authorizing-oauth-apps#device-flow）。\n\n```python\nimport asyncio\nimport json\nimport os\nimport time\nimport urllib.parse\nimport urllib.request\nfrom pathlib import Path\n\nfrom copilot import CopilotClient\n\nCLIENT_ID = \"YOUR_OAUTH_APP_CLIENT_ID\"\nSCOPE = \"read:user\"  # 按你的 OAuth App 需求调整\nTOKEN_PATH = Path.home() / \".config\" / \"myapp\" / \"copilot_token.json\"\n\ndef http_post(url, data):\n    body = urllib.parse.urlencode(data).encode()\n    req = urllib.request.Request(url, data=body, headers={\"Accept\": \"application/json\"})\n    with urllib.request.urlopen(req) as resp:\n        return json.loads(resp.read().decode())\n\ndef load_token():\n    if TOKEN_PATH.exists():\n        return json.loads(TOKEN_PATH.read_text()).get(\"access_token\")\n    return None\n\ndef save_token(token):\n    TOKEN_PATH.parent.mkdir(parents=True, exist_ok=True)\n    TOKEN_PATH.write_text(json.dumps(token))\n    os.chmod(TOKEN_PATH, 0o600)\n\ndef device_flow():\n    code = http_post(\n        \"https://github.com/login/device/code\",\n        {\"client_id\": CLIENT_ID, \"scope\": SCOPE},\n    )\n    print(f\"Open {code['verification_uri']} and enter {code['user_code']}\")\n    interval = int(code.get(\"interval\", 5))\n\n    while True:\n        token = http_post(\n            \"https://github.com/login/oauth/access_token\",\n            {\n                \"client_id\": CLIENT_ID,\n                \"device_code\": code[\"device_code\"],\n                \"grant_type\": \"urn:ietf:params:oauth:grant-type:device_code\",\n            },\n        )\n        if \"access_token\" in token:\n            return token\n        if token.get(\"error\") == \"slow_down\":\n            interval += 5\n        elif token.get(\"error\") not in (\"authorization_pending\",):\n            raise RuntimeError(token)\n        time.sleep(interval)\n\nasync def main():\n    access_token = load_token()\n    if not access_token:\n        token = device_flow()\n        save_token(token)\n        access_token = token[\"access_token\"]\n\n    client = CopilotClient({\"github_token\": access_token})\n    await client.start()\n    # ... create_session / send ...\n    await client.stop()\n\nif __name__ == \"__main__\":\n    asyncio.run(main())\n```\n\n要点/坑  \n- `cli_url` 与 `github_token` 互斥  \n- SDK 不保存凭据 需自行持久化  \n- 轮询需处理 `authorization_pending` / `slow_down`\n\n建议/落地  \n- pipe 启动时读取 token 文件 不存在则走 device flow  \n- 用 `github_token` 注入 保持非交互运行", "model": "gpt-5.2-codex"}
+{"index": 4, "question": "Compare the pros and cons of 'Session Replay' (fast-forwarding history) vs 'Session Resume' (stateful ID) for a stateless web backend like OpenWebUI.", "answer": "对无状态后端(OpenWebUI)而言，SDK 只支持通过 `resume_session(session_id)` 的状态续接；所谓“Session Replay”需要你自行重放历史 prompt（来源：本地 SDK 源码 copilot/client.py、copilot/session.py）。  \n对比要点（短语）：  \n- Replay：无状态/易扩展；缺点是耗时耗 tokens、易截断/丢工具状态、可能重复副作用  \n- Resume：省 tokens、保留工具/compaction/`workspace_path` 状态；缺点是需持久化 session_id、依赖会话存活/跨实例一致性。  \n建议/落地：优先持久化 chat_id→session_id 并 resume_session，失效时回退为重放最近 N 轮并重建工具上下文。", "model": "gpt-5.2-codex"}
+{"index": 5, "question": "Detail the exact protocol for 'Virtual Workspace': how to implement a file system provider that feeds content to Copilot without physical files.", "answer": "SDK 源码里没有“Virtual Workspace”协议或文件系统 provider 接口；会话只识别真实路径（`SessionConfig.working_directory`、`MessageOptions.attachments`）。要在无物理文件情况下供给内容，只能用自定义工具或 MCP 服务器把“读写文件”变成 tool 调用（来源：本地 SDK 源码 copilot/types.py / copilot/client.py）。\n\n可用原语（源码）\n- `SessionConfig.tools` / `available_tools`：自定义工具与白名单\n- `MessageOptions.attachments`：仅支持真实路径文件/目录\n\n方案 A：自定义工具实现 VFS（推荐）\n```python\nimport asyncio\nfrom pydantic import BaseModel, Field\nfrom copilot import CopilotClient, define_tool\n\nVFS = {\"README.md\": \"# Virtual README\\n内容来自内存\\n\"}\n\nclass VfsReadParams(BaseModel):\n    path: str = Field(description=\"virtual path\")\n\n@define_tool(name=\"vfs_read\", description=\"Read a virtual file\")\ndef vfs_read(params: VfsReadParams) -> str:\n    return VFS.get(params.path, \"\")\n\n@define_tool(name=\"vfs_list\", description=\"List virtual files\")\ndef vfs_list() -> list[str]:\n    return sorted(VFS.keys())\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"tools\": [vfs_read, vfs_list],\n        \"available_tools\": [\"vfs_read\", \"vfs_list\"],\n        \"system_message\": {\"content\": \"Use vfs_* tools for all file access.\"},\n    })\n    await session.send_and_wait({\"prompt\": \"打开 README.md\"})\n    await client.stop()\n\nasyncio.run(main())\n```\n\n方案 B：MCP 服务器（本地 stdio，VFS 由你实现）\n```python\nsession = await client.create_session({\n    \"model\": \"gpt-5\",\n    \"mcp_servers\": {\n        \"vfs\": {\n            \"type\": \"local\",\n            \"command\": \"python\",\n            \"args\": [\"-m\", \"my_vfs_mcp_server\"],\n            \"tools\": [\"*\"],\n        }\n    },\n})\n```\n\n注意/坑  \n- `available_tools` 只保留你的 VFS 工具以强制使用  \n- 内置文件工具只读真实文件；要兼容只能落地临时文件  \n- 大文件需分块返回，避免上下文爆炸  \n\n建议/落地  \n- pipe 内维护 VFS 存储（DB/Redis/内存）  \n- 启动 session 时注入 `system_message` + `available_tools` 强制 VFS 入口", "model": "gpt-5.2-codex"}
+{"index": 6, "question": "Create an 'Agent Manifest' example: how to define an Agent capable of specific high-privileged tools via SDK.", "answer": "SDK 没有独立“Agent Manifest”文件格式，等价于 `create_session` 的 `custom_agents`（CustomAgentConfig），并用 `tools`/`available_tools` 约束高权限工具，权限由 `on_permission_request` 处理（来源：本地 SDK 源码 copilot/types.py、copilot/client.py）。  \n示例如下（manifest 为 Python dict，可序列化为 JSON 配置）。\n\n```python\nimport asyncio\nfrom pydantic import BaseModel, Field\nfrom copilot import CopilotClient, define_tool\n\nclass AdminShellParams(BaseModel):\n    cmd: str = Field(description=\"approved shell command\")\n\n@define_tool(name=\"admin_shell\", description=\"Run an approved shell command\")\ndef admin_shell(params: AdminShellParams) -> str:\n    # TODO: 执行受控命令（白名单/沙箱）\n    return f\"approved: {params.cmd}\"\n\nclass AdminWriteParams(BaseModel):\n    path: str = Field(description=\"target path\")\n    content: str = Field(description=\"content\")\n\n@define_tool(name=\"admin_write\", description=\"Write to privileged store\")\ndef admin_write(params: AdminWriteParams) -> str:\n    # TODO: 受控写入\n    return \"ok\"\n\nasync def on_permission_request(req, _ctx):\n    if req.get(\"kind\") in (\"shell\", \"write\"):\n        return {\"kind\": \"approved\"}\n    return {\"kind\": \"denied-by-rules\", \"rules\": [{\"kind\": \"deny\"}]}\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    agent_manifest = {\n        \"name\": \"ops-admin\",\n        \"display_name\": \"Ops Admin\",\n        \"description\": \"Privileged ops agent\",\n        \"prompt\": \"Use only admin_* tools for privileged ops.\",\n        \"tools\": [\"admin_shell\", \"admin_write\"],\n        \"infer\": True,\n    }\n\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"tools\": [admin_shell, admin_write],\n        \"custom_agents\": [agent_manifest],\n        \"available_tools\": [\"admin_shell\", \"admin_write\"],\n        \"on_permission_request\": on_permission_request,\n    })\n\n    await session.send_and_wait({\"prompt\": \"使用 ops-admin 执行受控操作\"})\n    await client.stop()\n\nasyncio.run(main())\n```\n\n要点/坑  \n- session.tools 未注册 -> agent.tools 不可用  \n- custom_agents.tools 仅写名称  \n- 非交互缺少 on_permission_request -> 默认拒绝  \n- SDK 无显式 agent 选择参数 -> 需在 prompt 指定  \n\n建议/落地  \n- pipe 启动时加载 manifest 注入 custom_agents + available_tools + on_permission_request", "model": "gpt-5.2-codex"}
+{"index": 7, "question": "List all 'hidden' `SessionConfig` parameters relevant to Agent behavior and personality.", "answer": "基于本地 SDK 源码 `copilot/types.py` 的 SessionConfig，影响 Agent 行为/人格的相关参数如下（来源：本地 SDK 源码）。  \n- `system_message`: `append`/`replace`；`replace` 会移除 SDK guardrails（风险）  \n- `custom_agents`: `prompt`/`description`/`display_name`/`tools`/`mcp_servers`/`infer`；`tools` 仅名称且必须在 `tools` 注册  \n- `tools` / `available_tools` / `excluded_tools`: 能力与行为边界；`available_tools` 优先于 `excluded_tools`  \n- `hooks`: `on_user_prompt_submitted`/`on_pre_tool_use`/`on_post_tool_use`/`on_session_start`/`on_session_end`/`on_error_occurred`，可改写 prompt/工具参数/结果  \n- `on_permission_request`: 非交互审批策略；缺失或异常 => 拒绝  \n- `on_user_input_request`: 启用/处理 `ask_user`  \n- `mcp_servers`: 注入外部工具集  \n- `skill_directories` / `disabled_skills`: 技能启用/禁用  \n- `model` / `provider`: 模型与 BYOK 影响输出风格与能力  \n- `working_directory`: 上下文范围  \n- `infinite_sessions`: compaction 阈值影响记忆保留  \n- `config_dir`: CLI 配置/状态目录，行为取决于 CLI 侧配置  \n\n建议/落地：在 pipe 启动时固定 `system_message` + `available_tools/excluded_tools` + `hooks`，并持久化 session_id 以便 `resume_session`。", "model": "gpt-5.2-codex"}
+{"index": 8, "question": "Give a concise overview of MCP Server Integration: JSON-RPC config and SDK hooks.", "answer": "SDK 中 MCP 通过 create_session/resume_session 的 mcp_servers 传入（映射到 JSON‑RPC 的 mcpServers），支持 local/stdio 与 http/sse，两类配置字段分别为 type/command/args/env/cwd/timeout/tools 或 type/url/headers/timeout/tools（来源：本地 SDK 源码）。  \nSDK hooks 使用 hooks(on_pre_tool_use/on_post_tool_use/on_user_prompt_submitted/on_session_start/on_session_end/on_error_occurred) 进行拦截与附加上下文，权限需 on_permission_request 对 kind='mcp' 明确批准，且 session.on 可审计 tool.execution_* 事件中的 mcp_server_name/mcp_tool_name。  \n示例见下，建议/落地：pipe 中启用 on_permission_request、限制 tools 白名单并记录 MCP 事件。\n\n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def on_permission_request(req, _):\n    return {\"kind\": \"approved\"} if req.get(\"kind\") == \"mcp\" else {\n        \"kind\": \"denied-by-rules\",\n        \"rules\": [{\"kind\": \"deny\"}],\n    }\n\nasync def on_pre_tool_use(input, _):\n    if input.get(\"toolName\", \"\").startswith(\"mcp.\"):\n        return {\"additionalContext\": \"MCP tool call observed\"}\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"mcp_servers\": {\n            \"brave\": {\n                \"type\": \"local\",\n                \"command\": \"/path/to/brave-mcp\",\n                \"args\": [],\n                \"env\": {\"BRAVE_API_KEY\": \"YOUR_KEY\"},\n                \"tools\": [\"*\"],\n                \"timeout\": 30000,\n            }\n        },\n        \"hooks\": {\"on_pre_tool_use\": on_pre_tool_use},\n        \"on_permission_request\": on_permission_request,\n    })\n\n    await session.send_and_wait({\"prompt\": \"用 Brave Search 查询 Copilot SDK 新闻\"})\n    await client.stop()\n\nasyncio.run(main())\n```", "model": "gpt-5.2-codex"}
+{"index": 9, "question": "Provide best practices and common pitfalls for MCP Server Integration: JSON-RPC config and SDK hooks.", "answer": "基于本地 SDK 源码，MCP 配置通过 `create_session`/`resume_session` 的 `mcp_servers` 进入 JSON‑RPC `mcpServers`，并通过 `on_permission_request` 与 `hooks` 控制工具审批与行为（来源：本地 SDK 源码）  \n- 最佳实践：local/stdio 用 `type/command/args/env/cwd/timeout/tools`；remote http/sse 用 `type/url/headers/timeout/tools`；`tools` 尽量白名单、必要时 `[\"*\"]`；`timeout` 毫秒；`hooks.on_pre_tool_use` 做改参/拒绝，`session.on` 记录 `tool.execution_*` 与 `mcp_server_name`/`mcp_tool_name`  \n- 常见坑：把 MCP 配置放在 CopilotClient；缺少 `on_permission_request`（kind=\"mcp\"）导致默认拒绝；`tools: []` 等于禁用全部；设置 `available_tools` 却未包含 MCP 工具名导致被过滤  \n\n建议/落地：pipe 中固定审批策略 + 统一 MCP 配置模板 + 审计日志", "model": "gpt-5.2-codex"}
+{"index": 10, "question": "Show a minimal example snippet for MCP Server Integration: JSON-RPC config and SDK hooks.", "answer": "基于本地 SDK 源码，MCP 通过 `mcp_servers` 传入并用 `hooks` 处理工具调用（来源：本地 SDK 源码）。最小示例：  \n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"mcp_servers\": {\n            \"brave\": {\n                \"type\": \"local\",\n                \"command\": \"/path/to/brave-mcp\",\n                \"args\": [],\n                \"env\": {\"BRAVE_API_KEY\": \"YOUR_KEY\"},\n                \"tools\": [\"*\"],\n            }\n        },\n        \"hooks\": {\n            \"on_pre_tool_use\": lambda input, _: {\"additionalContext\": \"MCP tool call\"},\n        },\n        \"on_permission_request\": lambda req, _: {\"kind\": \"approved\"},\n    })\n\n    await session.send_and_wait({\"prompt\": \"用 Brave Search 搜索 Copilot SDK\"})\n    await client.stop()\n\nasyncio.run(main())\n```\n\n建议/落地：固定 `on_permission_request`（kind=\"mcp\"）并限制 `tools` 白名单。", "model": "gpt-5.2-codex"}
+{"index": 11, "question": "List recommended configuration defaults for MCP Server Integration: JSON-RPC config and SDK hooks.", "answer": "推荐默认值（MCP JSON‑RPC 配置，来源：本地 SDK 源码）：local/stdio 服务器用 `type=\"local\"/\"stdio\"`（远程用 `http`/`sse`）、`tools` 白名单（无则 `\"*\"`）、`timeout=30000` 毫秒、`env` 仅放密钥、`cwd` 指向受控目录。  \nHooks 默认：`on_pre_tool_use` 追加上下文并可设 `permissionDecision`（ask/allow）、必要时改参，`on_post_tool_use` 记录结果，`on_error_occurred` 设置 retry/skip。  \n建议/落地：非交互场景配置 `on_permission_request` 仅放行 `kind=\"mcp\"`，否则拒绝；工具名不确定时先不设 `available_tools`，避免误过滤。", "model": "gpt-5.2-codex"}
+{"index": 12, "question": "How does MCP Server Integration: JSON-RPC config and SDK hooks relate to building a custom Agent?", "answer": "SDK 源码中，自定义 Agent 通过 `SessionConfig.custom_agents` 定义，`CustomAgentConfig` 支持 `mcp_servers`，因此“Agent 绑定 MCP”就是在 agent config 里声明 `mcp_servers`，底层在 `create_session` 时转成 JSON‑RPC 的 `mcpServers`（来源：本地 SDK 源码 copilot/types.py、copilot/client.py）。  \nHooks 是会话级拦截器（`on_pre_tool_use`/`on_post_tool_use` 等），对 MCP 工具同样生效；权限确认需 `on_permission_request` 审批 `kind=\"mcp\"`。  \n建议/落地：pipe 中为目标 Agent 绑定 MCP + 审批钩子，示例：  \n```python\nsession = await client.create_session({\n    \"model\": \"gpt-5\",\n    \"custom_agents\": [{\n        \"name\": \"search\",\n        \"prompt\": \"Use MCP for search.\",\n        \"mcp_servers\": {\n            \"brave\": {\n                \"type\": \"local\",\n                \"command\": \"/path/to/brave-mcp\",\n                \"args\": [],\n                \"env\": {\"BRAVE_API_KEY\": \"YOUR_KEY\"},\n                \"tools\": [\"*\"],\n            }\n        },\n    }],\n    \"hooks\": {\"on_pre_tool_use\": lambda i, _: {\"additionalContext\": \"mcp\"}},\n    \"on_permission_request\": lambda r, _: {\"kind\": \"approved\"},\n})\n```", "model": "gpt-5.2-codex"}
+{"index": 13, "question": "Give a concise overview of Agent Manifests: Defining capabilities and permissions programmatically.", "answer": "SDK 没有独立的 Agent Manifest 文件，等价做法是用 `SessionConfig.custom_agents` 描述 agent，并用 `tools`/`available_tools`/`excluded_tools` 限定能力。  \n权限通过 `on_permission_request` 与 `hooks`（如 `on_pre_tool_use`）在会话级控制，且 `custom_agents.tools` 只能写工具名并需在 `SessionConfig.tools` 注册。  \n建议/落地：pipe 启动时加载 manifest→注入 `custom_agents` + `available_tools` + `on_permission_request` 固化权限边界。", "model": "gpt-5.2-codex"}
+{"index": 14, "question": "Provide best practices and common pitfalls for Agent Manifests: Defining capabilities and permissions programmatically.", "answer": "SDK 没有独立 Manifest 文件，等价于 `SessionConfig.custom_agents` + `tools/available_tools/excluded_tools` + `on_permission_request` + `hooks` 来定义能力与权限（来源：本地 SDK 源码）。  \n最佳实践：`custom_agents.tools` 只写已在 `SessionConfig.tools` 注册的名称，配合 `available_tools` 白名单与 `on_permission_request` 精准放行，必要时用 `hooks.on_pre_tool_use` 做参数校验/审计，`system_message` 选 append 以保留 guardrails。  \n常见坑：工具未注册或名称不一致、缺少 `on_permission_request` 导致默认拒绝、误用 `system_message` replace 去掉安全限制、期待 agent 自动被选中或跨实例不持久 `session_id`；建议/落地：pipe 启动时加载 manifest→注入 `custom_agents/available_tools/on_permission_request` 并持久化 `session_id`。", "model": "gpt-5.2-codex"}
+{"index": 15, "question": "Show a minimal example snippet for Agent Manifests: Defining capabilities and permissions programmatically.", "answer": "最小示例（本地 SDK 源码：`custom_agents` + `tools` + `available_tools` + `on_permission_request`）：  \n```python\nimport asyncio\nfrom pydantic import BaseModel, Field\nfrom copilot import CopilotClient, define_tool\n\nclass PingParams(BaseModel):\n    text: str = Field(description=\"text to echo\")\n\n@define_tool(name=\"priv_ping\", description=\"Privileged echo\")\ndef priv_ping(params: PingParams) -> str:\n    return f\"ok: {params.text}\"\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    agent_manifest = {\n        \"name\": \"priv-agent\",\n        \"prompt\": \"Only use priv_ping for actions.\",\n        \"tools\": [\"priv_ping\"],\n        \"infer\": True,\n    }\n\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"tools\": [priv_ping],\n        \"custom_agents\": [agent_manifest],\n        \"available_tools\": [\"priv_ping\"],\n        \"on_permission_request\": lambda req, _: {\"kind\": \"approved\"},\n    })\n\n    await session.send_and_wait({\"prompt\": \"调用 priv_ping\"})\n    await client.stop()\n\nasyncio.run(main())\n```\n\n建议/落地：保持工具名一致并白名单化，非交互务必提供 `on_permission_request`。", "model": "gpt-5.2-codex"}
+{"index": 16, "question": "List recommended configuration defaults for Agent Manifests: Defining capabilities and permissions programmatically.", "answer": "基于本地 SDK 源码（copilot/types.py / copilot/client.py），推荐默认值如下：  \n- custom_agents：name 必填、prompt 必填、tools 仅名称、infer=True，display_name/description 可选  \n- available_tools=白名单、excluded_tools=空、system_message=append  \n- on_permission_request：除明确允许的 kind 其余拒绝；hooks.on_pre_tool_use 做审计/参数校验（其余 hooks 按需）  \n建议/落地：pipe 启动时加载 manifest→注册 tools + available_tools + on_permission_request，并持久化 session_id。", "model": "gpt-5.2-codex"}
+{"index": 17, "question": "How does Agent Manifests: Defining capabilities and permissions programmatically relate to building a custom Agent?", "answer": "“Agent Manifest”在 SDK 里就是 `SessionConfig.custom_agents` 的配置对象，用它定义自定义 Agent 的 `name/prompt/tools/mcp_servers/infer`，并在同一 session 里用 `tools` 注册实际工具、用 `available_tools/excluded_tools` 限定能力（来源：本地 SDK 源码）。  \n权限不在 manifest 内，而是由会话级 `on_permission_request` 和 hooks（如 `on_pre_tool_use`）统一控制，且对所有 Agent 生效。  \n建议/落地：pipe 启动时把 manifest 转成 `custom_agents` 并同步注册工具 + 白名单，再配置 `on_permission_request` 作为权限策略。", "model": "gpt-5.2-codex"}
+{"index": 18, "question": "Give a concise overview of Headless Auth: Device Code Flow and credential persistence.", "answer": "SDK 仅提供 `CopilotClient` 的 `github_token/use_logged_in_user` 与 `get_auth_status()`，没有内置 device‑flow API（源码：copilot/client.py、copilot/types.py）。  \nHeadless Device Flow 需走 GitHub OAuth Device Flow HTTP 端点获取 token（https://docs.github.com/en/apps/oauth-apps/building-oauth-apps/authorizing-oauth-apps#device-flow），将 token 持久化（权限 600）并通过 `CopilotClient({\"github_token\": token})` 注入，且与 `cli_url` 互斥。  \n建议/落地：启动时读 token 文件，不存在则执行 device flow 并保存，再启动客户端。\n\n```python\ntoken = load_token() or device_flow()  # 调用 device code + access_token 端点\nsave_token(token)  # chmod 600\nclient = CopilotClient({\"github_token\": token[\"access_token\"]})\nawait client.start()\n```", "model": "gpt-5.2-codex"}
+{"index": 19, "question": "Provide best practices and common pitfalls for Headless Auth: Device Code Flow and credential persistence.", "answer": "SDK 不内置 device flow，只能用 GitHub OAuth Device Flow HTTP 换取 token 并通过 CopilotClient({github_token}) 注入，且与 cli_url 互斥（源码：copilot/client.py、copilot/types.py）。  \n最佳实践/坑：- token 文件 chmod 600 或 OS keychain；- 记录到期与刷新策略，启动时用 get_auth_status 验证；- 轮询需处理 authorization_pending/slow_down；- 未持久化、use_logged_in_user 与 github_token 同时使用或与 cli_url 混用会失败（端点说明：https://docs.github.com/en/apps/oauth-apps/building-oauth-apps/authorizing-oauth-apps#device-flow）。  \n建议/落地：pipe 启动时读 token 文件，不存在则走 device flow 并保存，失败时回退重新授权。", "model": "gpt-5.2-codex"}
+{"index": 20, "question": "Show a minimal example snippet for Headless Auth: Device Code Flow and credential persistence.", "answer": "最小示例：用 GitHub Device Flow（端点说明见 https://docs.github.com/en/apps/oauth-apps/building-oauth-apps/authorizing-oauth-apps#device-flow）拿 token，持久化后注入 CopilotClient({github_token}).  \n```python\nimport asyncio\nimport json\nimport os\nimport time\nimport urllib.parse\nimport urllib.request\nfrom pathlib import Path\nfrom copilot import CopilotClient\n\nCLIENT_ID = \"YOUR_OAUTH_APP_CLIENT_ID\"\nTOKEN_PATH = Path.home() / \".config\" / \"myapp\" / \"copilot_token.json\"\n\ndef post(url, data):\n    body = urllib.parse.urlencode(data).encode()\n    req = urllib.request.Request(url, data=body, headers={\"Accept\": \"application/json\"})\n    with urllib.request.urlopen(req) as resp:\n        return json.loads(resp.read().decode())\n\ndef device_flow():\n    code = post(\"https://github.com/login/device/code\", {\"client_id\": CLIENT_ID, \"scope\": \"read:user\"})\n    print(f\"Open {code['verification_uri']} and enter {code['user_code']}\")\n    interval = int(code.get(\"interval\", 5))\n    while True:\n        tok = post(\n            \"https://github.com/login/oauth/access_token\",\n            {\n                \"client_id\": CLIENT_ID,\n                \"device_code\": code[\"device_code\"],\n                \"grant_type\": \"urn:ietf:params:oauth:grant-type:device_code\",\n            },\n        )\n        if \"access_token\" in tok:\n            return tok\n        if tok.get(\"error\") == \"slow_down\":\n            interval += 5\n        elif tok.get(\"error\") != \"authorization_pending\":\n            raise RuntimeError(tok)\n        time.sleep(interval)\n\ndef load_token():\n    return json.loads(TOKEN_PATH.read_text()).get(\"access_token\") if TOKEN_PATH.exists() else None\n\ndef save_token(tok):\n    TOKEN_PATH.parent.mkdir(parents=True, exist_ok=True)\n    TOKEN_PATH.write_text(json.dumps(tok))\n    os.chmod(TOKEN_PATH, 0o600)\n\nasync def main():\n    access_token = load_token()\n    if not access_token:\n        tok = device_flow()\n        save_token(tok)\n        access_token = tok[\"access_token\"]\n\n    client = CopilotClient({\"github_token\": access_token})\n    await client.start()\n    # ... create_session / send ...\n    await client.stop()\n\nasyncio.run(main())\n```\n\n建议/落地  \n- 启动先读 token 文件；缺失再 device flow  \n- token 文件权限 600  \n- 失效则重新授权", "model": "gpt-5.2-codex"}
+{"index": 21, "question": "List recommended configuration defaults for Headless Auth: Device Code Flow and credential persistence.", "answer": "基于本地 SDK 源码（`github_token` 与 `cli_url` 互斥）与 GitHub Device Flow 文档（https://docs.github.com/en/apps/oauth-apps/building-oauth-apps/authorizing-oauth-apps#device-flow），推荐默认值：  \n- Token 持久化：`~/.config/<app>/copilot_token.json` 或系统密钥链，文件权限 600  \n- Client 选项：仅 `github_token`，`use_logged_in_user` 留空/False，禁用 `cli_url`  \n- 轮询：使用 device code 返回的 `interval`（缺省 5s），处理 `authorization_pending`/`slow_down`  \n- 启动校验：`get_auth_status()` 失败即重新授权  \n\n建议/落地：启动先读 token 文件 → 无则 device flow → 保存 → `client.start()`", "model": "gpt-5.2-codex"}
+{"index": 22, "question": "How does Headless Auth: Device Code Flow and credential persistence relate to building a custom Agent?", "answer": "Headless Auth 只负责拿到并持久化 `github_token`，让 `CopilotClient` 能在无交互环境启动会话并加载 `custom_agents`；因此它是自定义 Agent 能稳定运行的前置条件，而不是 Agent 定义本身（来源：本地 SDK 源码）。  \n建议/落地：在无状态后端启动时读取 token 文件（不存在就走 device flow）→ `CopilotClient({\"github_token\": token})` → `create_session(custom_agents=...)`。", "model": "gpt-5.2-codex"}
+{"index": 23, "question": "Give a concise overview of Session Replay vs Resume: Handling stateless frontend history.", "answer": "基于本地 SDK 源码（copilot/client.py、copilot/session.py），Resume 是 `resume_session(session_id)` 保留会话状态，Replay 只能由应用重放历史 prompt。优缺点：Resume 省 tokens/保工具与 compaction 状态但依赖持久化 session_id；Replay 无状态易扩展但成本高且易丢副作用控制。建议/落地：无状态前端请保存 session_id 并优先 Resume，失效时回放最近 N 轮。", "model": "gpt-5.2-codex"}
+{"index": 24, "question": "Provide best practices and common pitfalls for Session Replay vs Resume: Handling stateless frontend history.", "answer": "最佳实践：在无状态前端每次请求携带 session_id 并优先 `resume_session`，同时恢复 tools/hooks/on_permission_request/system_message 以保持行为一致（来源：本地 SDK 源码）。  \n常见坑：Replay 会重复执行工具且耗 tokens；Resume 未重新注册工具或权限处理器会出现 tool not supported/默认拒绝；会话失效未回退。  \n建议/落地：持久化 chat_id→session_id，resume 失败时仅回放最近 N 轮并禁用/幂等化有副作用的工具。", "model": "gpt-5.2-codex"}
+{"index": 25, "question": "Show a minimal example snippet for Session Replay vs Resume: Handling stateless frontend history.", "answer": "来源：本地 SDK 源码（copilot/client.py, copilot/session.py），最小示例如下（优先 Resume，失败则 Replay）。  \n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def handle_request(session_id: str | None, history: list[str], latest: str):\n    client = CopilotClient()\n    await client.start()\n\n    try:\n        # Resume: 复用会话状态\n        if not session_id:\n            raise RuntimeError(\"no session_id\")\n        session = await client.resume_session(session_id)\n    except Exception:\n        # Replay: 逐条重放历史\n        session = await client.create_session({\"model\": \"gpt-5\"})\n        session_id = session.session_id\n        for prompt in history:\n            await session.send_and_wait({\"prompt\": prompt})\n\n    response = await session.send_and_wait({\"prompt\": latest})\n    await client.stop()\n    return response.data.content, session_id\n\n# asyncio.run(handle_request(session_id, history, latest_prompt))\n```\n建议/落地：持久化 session_id，resume 失败时仅回放最近 N 轮。", "model": "gpt-5.2-codex"}
+{"index": 26, "question": "List recommended configuration defaults for Session Replay vs Resume: Handling stateless frontend history.", "answer": "基于本地 SDK 源码，推荐默认配置如下（Resume / Replay）：  \n- Resume：持久化 session_id；`resume_session({...})` 传回 tools、hooks、on_permission_request、working_directory、streaming、provider、mcp_servers、custom_agents、skill_directories、disabled_skills；`disable_resume` 保持默认 False  \n- Replay：`create_session({...})` 传回 model、system_message、tools、available_tools/excluded_tools、hooks、on_permission_request、working_directory、provider、mcp_servers、custom_agents、infinite_sessions(默认启用)；仅回放最近 N 轮；默认拒绝 write/shell 或用只读白名单", "model": "gpt-5.2-codex"}
+{"index": 27, "question": "How does Session Replay vs Resume: Handling stateless frontend history relate to building a custom Agent?", "answer": "Resume 会保留 session_id 关联的 custom_agents/工具状态，Replay 需要每次 create_session 时重新注入 custom_agents + tools，否则 persona/能力会丢失（来源：本地 SDK 源码）。对于无状态前端，Resume 更可靠且省 token，但要持久化 session_id 并在 resume 时重新注册 tools/hooks；Replay 则需回放历史并保证相同 custom_agents 配置。建议/落地：pipe 优先 resume_session，失败再 replay 最近 N 轮并重建 custom_agents/tools/权限策略。", "model": "gpt-5.2-codex"}
+{"index": 28, "question": "Give a concise overview of Advanced Session Hooks: Intercepting and modifying user prompts.", "answer": "拦截/修改用户提示要用 `SessionHooks.on_user_prompt_submitted`（不是 `session.on` 事件订阅），`input.prompt` 可改为 `output.modifiedPrompt` 并附加 `additionalContext`/`suppressOutput`，且需在 `create_session`/`resume_session` 传入 `hooks` 才会触发 `hooks.invoke`（来源：本地 SDK 源码 copilot/types.py、copilot/session.py、copilot/client.py）。  \n```python\nfrom copilot import CopilotClient\n\nasync def on_user_prompt_submitted(input, _ctx):\n    return {\"modifiedPrompt\": input[\"prompt\"].strip(), \"additionalContext\": \"normalize whitespace\"}\n\nsession = await client.create_session({\n    \"model\": \"gpt-5\",\n    \"hooks\": {\"on_user_prompt_submitted\": on_user_prompt_submitted},\n})\n```\n建议/落地：在 pipe 入口统一做 prompt 清洗/拼接上下文，并记录修改前后用于审计。", "model": "gpt-5.2-codex"}
+{"index": 29, "question": "Provide best practices and common pitfalls for Advanced Session Hooks: Intercepting and modifying user prompts.", "answer": "最佳实践：在 create_session/resume_session 传入 hooks.on_user_prompt_submitted，返回 {modifiedPrompt, additionalContext, suppressOutput}，修改保持幂等、最小化、可审计（来源：本地 SDK 源码 copilot/types.py、copilot/client.py、copilot/session.py）。  \n常见坑：忘记传 hooks 或 resume 时未重新传、handler 抛异常会被吞并返回 None、返回非 dict 或过度改写提示导致无效/偏航。  \n建议/落地：在 pipe 入口统一注册该 hook 并记录修改前后，保持 system_message 为 append。", "model": "gpt-5.2-codex"}
+{"index": 30, "question": "Show a minimal example snippet for Advanced Session Hooks: Intercepting and modifying user prompts.", "answer": "最小示例（来源：本地 SDK 源码）：  \n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def on_user_prompt_submitted(hook_input, _ctx):\n    return {\n        \"modifiedPrompt\": hook_input[\"prompt\"].strip(),\n        \"additionalContext\": \"normalized\",\n    }\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n    session = await client.create_session({\n        \"model\": \"gpt-5\",\n        \"hooks\": {\"on_user_prompt_submitted\": on_user_prompt_submitted},\n    })\n    await session.send_and_wait({\"prompt\": \"  hello  \"})\n    await client.stop()\n\nasyncio.run(main())\n```\n建议/落地：在 pipe 入口统一注册该 hook，并记录修改前后以便审计。", "model": "gpt-5.2-codex"}
+{"index": 31, "question": "List recommended configuration defaults for Advanced Session Hooks: Intercepting and modifying user prompts.", "answer": "- 推荐默认值（来源：本地 SDK 源码 copilot/types.py）：`hooks={\"on_user_prompt_submitted\": handler}`，handler 默认返回 `{\"modifiedPrompt\": input[\"prompt\"], \"additionalContext\": \"\", \"suppressOutput\": False}` 或 `None`（不改写）。  \n- `create_session`/`resume_session` 都要传同一 hooks；`system_message` 保持 append 以保留 guardrails。  \n- 建议/落地：pipe 入口统一注册该 hook 并记录原/改提示用于审计。", "model": "gpt-5.2-codex"}
+{"index": 32, "question": "How does Advanced Session Hooks: Intercepting and modifying user prompts relate to building a custom Agent?", "answer": "Hooks 是会话级拦截器，对所有自定义 Agent 都生效；因此它是定义 Agent 行为边界和输入规范化的“外层控制”，而不是 Agent Manifest 本身（来源：本地 SDK 源码 copilot/types.py、copilot/session.py）。  \n在自定义 Agent 场景下，`on_user_prompt_submitted` 可统一清洗/增强用户指令，再由 custom_agents 的 prompt 决定具体风格。  \n建议/落地：pipe 启动时同时注入 custom_agents + hooks，确保 resume 时同样注册 hooks。", "model": "gpt-5.2-codex"}
+{"index": 33, "question": "Give a concise overview of Workspace Virtualization: Handling CWD for remote/virtual files.", "answer": "SDK 只有 `SessionConfig.working_directory` 来约束 CWD，`attachments` 也要求真实路径，没有“虚拟工作区/FS provider”协议（来源：本地 SDK 源码 copilot/types.py、copilot/client.py）。要处理远程/虚拟文件，需用自定义工具或 MCP 服务器实现 VFS 读写，或把内容落地到 working_directory 下的临时文件再交给模型。建议/落地：pipe 固定 working_directory 映射到会话工作区，统一走 vfs_* 工具/MCP，且在 on_permission_request 限制 write/shell。", "model": "gpt-5.2-codex"}
+{"index": 34, "question": "Provide best practices and common pitfalls for Workspace Virtualization: Handling CWD for remote/virtual files.", "answer": "SDK 没有虚拟工作区/FS provider，仅支持 `SessionConfig.working_directory` 与真实路径 `attachments`（来源：本地 SDK 源码），因此远程/虚拟文件需落地或用自定义工具/MCP 提供内容。  \n最佳实践：固定 working_directory 到可控目录/会话 workspace，VFS 工具分块返回，配合 `available_tools`/`on_permission_request` 限权；常见坑：直接传虚拟路径/URL、working_directory 不存在、resume 未重注册工具/权限、一次性返回过大内容导致上下文截断。  \n建议/落地：pipe 入口做 remote→临时文件或 vfs_* 映射，并持久化路径索引。", "model": "gpt-5.2-codex"}
+{"index": 35, "question": "Show a minimal example snippet for Workspace Virtualization: Handling CWD for remote/virtual files.", "answer": "SDK 仅提供 `SessionConfig.working_directory` 与真实路径附件，没有虚拟 FS/provider（来源：本地 SDK 源码 copilot/types.py）。最小做法是把远程内容落地到 CWD 下再作为附件传入：  \n```python\nimport asyncio\nimport pathlib\nfrom copilot import CopilotClient\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    workdir = \"/tmp/owui\"\n    pathlib.Path(workdir).mkdir(parents=True, exist_ok=True)\n    remote_content = \"...\"\n    path = f\"{workdir}/remote.txt\"\n    pathlib.Path(path).write_text(remote_content)\n\n    session = await client.create_session({\"model\": \"gpt-5\", \"working_directory\": workdir})\n    await session.send_and_wait({\n        \"prompt\": \"Summarize remote.txt\",\n        \"attachments\": [{\"type\": \"file\", \"path\": path}],\n    })\n    await client.stop()\n\nasyncio.run(main())\n```\n建议/落地：pipe 入口固定 working_directory，落地临时文件后立即处理，并用 `on_permission_request` 限制 write/shell。", "model": "gpt-5.2-codex"}
+{"index": 36, "question": "List recommended configuration defaults for Workspace Virtualization: Handling CWD for remote/virtual files.", "answer": "推荐默认值（来源：本地 SDK 源码 copilot/types.py）：  \n- `working_directory`: 指向可控的会话目录（如 session.workspace_path 或 /tmp/<app>/<session_id>）  \n- `available_tools`: 只允许 vfs_* 或只读工具，避免任意 shell/write  \n- `on_permission_request`: 默认拒绝 write/shell，仅放行 read/mcp  \n- `attachments`: 仅真实路径文件；远程内容先落地  \n\n建议/落地：pipe 入口统一映射 remote→临时文件或 VFS 工具，并持久化映射表。", "model": "gpt-5.2-codex"}
+{"index": 37, "question": "How does Workspace Virtualization: Handling CWD for remote/virtual files relate to building a custom Agent?", "answer": "SDK 没有虚拟文件系统协议，custom agent 只能依赖 `working_directory` 和真实路径附件，因此处理远程/虚拟文件需通过自定义工具/MCP 并在 agent prompt/available_tools 中强制使用（来源：本地 SDK 源码 copilot/types.py、copilot/client.py）。  \n这使“工作区虚拟化”成为 agent 能力与权限设计的一部分，需要 `available_tools`/`on_permission_request`/hooks 来限定访问范围。  \n建议/落地：pipe 中固定 working_directory 到会话目录，注入 vfs_* 工具白名单并在 prompt 明确使用 VFS。", "model": "gpt-5.2-codex"}
+{"index": 38, "question": "Give a concise overview of Error Recovery: Handling session disconnects and re-auth.", "answer": "本地 SDK 源码中没有显式“重连”API，断线通常表现为请求异常或 `SessionEventType.SESSION_ERROR`，需要 `stop()/force_stop()` 后重新 `start()` 并 `resume_session`（失败则 replay）（来源：本地 SDK 源码）。  \n认证可用 `get_auth_status()` 检测，未认证时重新创建 `CopilotClient({\"github_token\": token})`；若 `cli_url` 连接外部服务器则认证由外部处理（来源：本地 SDK 源码）。\n\n```python\nimport asyncio\nfrom copilot import CopilotClient\nfrom copilot.generated.session_events import SessionEventType\n\nasync def safe_send(session_id, prompt, token):\n    client = CopilotClient({\"github_token\": token})\n    await client.start()\n    try:\n        session = await (client.resume_session(session_id) if session_id else client.create_session({\"model\": \"gpt-5\"}))\n        session.on(lambda ev: ev.type == SessionEventType.SESSION_ERROR and print(ev.data.message))\n        resp = await session.send_and_wait({\"prompt\": prompt})\n        return resp, session.session_id\n    except Exception:\n        await client.stop()\n        client = CopilotClient({\"github_token\": token})\n        await client.start()\n        session = await client.create_session({\"model\": \"gpt-5\"})\n        resp = await session.send_and_wait({\"prompt\": prompt})\n        return resp, session.session_id\n    finally:\n        await client.stop()\n```\n\n建议/落地：持久化 session_id 与 token，优先 resume，失败再回放最近 N 轮。", "model": "gpt-5.2-codex"}
+{"index": 39, "question": "Provide best practices and common pitfalls for Error Recovery: Handling session disconnects and re-auth.", "answer": "最佳实践（基于本地 SDK 源码）：监听 `SESSION_ERROR`/捕获请求异常后 `stop()/force_stop()`→重新 `start()`→`resume_session`（失败再 replay），启动时用 `get_auth_status()` 校验并在失效时重建 `CopilotClient({\"github_token\": ...})`，同时在 resume 时重新注册 tools/hooks/权限处理器。  \n常见坑：把 `cli_url` 与 `github_token` 混用、忘记重注册工具导致 `tool not supported`、缺少 `on_permission_request` 导致默认拒绝、以及不回退到 replay 造成会话中断。  \n建议/落地：无状态后端持久化 `session_id+token`、实现幂等的重试/回放策略并记录错误上下文用于告警。", "model": "gpt-5.2-codex"}
+{"index": 40, "question": "Show a minimal example snippet for Error Recovery: Handling session disconnects and re-auth.", "answer": "最小示例（本地 SDK 源码：copilot/client.py、copilot/session.py）：  \n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def send_with_recovery(session_id, prompt, token):\n    client = CopilotClient({\"github_token\": token})\n    await client.start()\n    try:\n        session = await (client.resume_session(session_id) if session_id else client.create_session({\"model\": \"gpt-5\"}))\n        resp = await session.send_and_wait({\"prompt\": prompt})\n        return resp.data.content, session.session_id\n    except Exception:\n        await client.stop()\n        client = CopilotClient({\"github_token\": token})\n        await client.start()\n        session = await client.create_session({\"model\": \"gpt-5\"})\n        resp = await session.send_and_wait({\"prompt\": prompt})\n        return resp.data.content, session.session_id\n    finally:\n        await client.stop()\n```\n建议/落地：持久化 token+session_id，resume 失败再重建并回放必要历史。", "model": "gpt-5.2-codex"}
+{"index": 41, "question": "List recommended configuration defaults for Error Recovery: Handling session disconnects and re-auth.", "answer": "推荐默认值（字段来源：本地 SDK 源码）：CopilotClientOptions—auto_start=True、log_level='info'、use_stdio=True（非 cli_url）、github_token=持久化 token；SessionConfig/ResumeSessionConfig—hooks.on_error_occurred=handler、on_permission_request=非交互审批、working_directory 固定、mcp_servers/custom_agents/streaming 与首次一致、可固定 config_dir 并持久化 session_id。  \n常见坑：cli_url 与 github_token 互斥、resume 时未重传 tools/hooks 导致 tool not supported 或默认拒绝。  \n建议/落地：pipe 保存 token+session_id，断线后先 resume_session，失败再回放最近 N 轮。", "model": "gpt-5.2-codex"}
+{"index": 42, "question": "How does Error Recovery: Handling session disconnects and re-auth relate to building a custom Agent?", "answer": "错误恢复与自定义 Agent 强相关：Agent 定义与工具/权限处理器都是 session 级配置，断线或重认证后必须重建客户端并重新注入 `custom_agents`、`tools`、`hooks`、`on_permission_request`，否则能力/人格会丢失（来源：本地 SDK 源码）。  \n建议/落地：持久化 session_id+token，重连优先 `resume_session` 并重新注册上述配置，失败再回放最近 N 轮。", "model": "gpt-5.2-codex"}
+{"index": 43, "question": "Give a concise overview of Confirmation Events: programmatic handling of 'confirmation_required'.", "answer": "SDK 源码里没有独立的 `confirmation_required` 事件；权限确认是 JSON‑RPC `permission.request`，通过 `SessionConfig.on_permission_request` 回调处理（缺失或异常会默认拒绝）。  \n`session.on()` 只能用于审计/关联工具事件（如 `tool.user_requested`、`tool.execution_start`），不能替代确认逻辑。", "model": "gpt-5.2-codex"}
+{"index": 44, "question": "Provide best practices and common pitfalls for Confirmation Events: programmatic handling of 'confirmation_required'.", "answer": "SDK 源码未定义 `confirmation_required` 事件，确认流程必须用 `SessionConfig.on_permission_request` 处理，缺失或异常会默认拒绝（来源：本地 SDK 源码）。  \n最佳实践/坑：  \n- ✅ 对 `kind` 建立白名单策略（如仅允许 `read/mcp`），记录决策并用 `session.on` 仅做审计关联 `tool.user_requested`  \n- ✅ `resume_session` 时重新注册 `on_permission_request`/hooks  \n- ❌ 误以为 `session.on()` 可完成确认、返回非规范 dict 或抛异常导致全部拒绝", "model": "gpt-5.2-codex"}
+{"index": 45, "question": "Show a minimal example snippet for Confirmation Events: programmatic handling of 'confirmation_required'.", "answer": "SDK 里没有 `confirmation_required` 事件，需用 `SessionConfig.on_permission_request` 处理权限确认。  \n最小示例：  \n```python\nfrom copilot import CopilotClient\n\nclient = CopilotClient()\nawait client.start()\n\nsession = await client.create_session({\n    \"model\": \"gpt-5\",\n    \"on_permission_request\": lambda req, _: {\"kind\": \"approved\"},\n})\n```\n建议/落地：在 pipe 中统一注册 on_permission_request，并在 resume_session 时重复注册。", "model": "gpt-5.2-codex"}
+{"index": 46, "question": "List recommended configuration defaults for Confirmation Events: programmatic handling of 'confirmation_required'.", "answer": "推荐默认值（SDK 无 confirmation_required 事件，改用 on_permission_request，来源：本地 SDK 源码）：- 对 kind 建白名单（常见只放行 read/mcp）- 未命中默认返回 denied-by-rules 并给 rules - resume_session 时重注册 on_permission_request/hooks。  \n建议/落地：pipe 启动即注入 on_permission_request 并记录审批日志。", "model": "gpt-5.2-codex"}
+{"index": 47, "question": "How does Confirmation Events: programmatic handling of 'confirmation_required' relate to building a custom Agent?", "answer": "SDK 没有 `confirmation_required` 事件，权限确认由 `create_session`/`resume_session` 的 `on_permission_request` 处理，且对同一 session 的所有 custom agent 生效（来源：本地 SDK 源码）。  \n建议/落地：在 pipe 启动时注入 `on_permission_request` 白名单策略并在 resume 时重注册，以约束高权限工具。", "model": "gpt-5.2-codex"}
+{"index": 48, "question": "Give a concise overview of Skills: Conflict resolution and precedence defaults.", "answer": "在本地 SDK 源码中，Skills 只通过 SessionConfig 的 `skill_directories` 与 `disabled_skills` 暴露，未定义冲突解析/优先级规则，因此行为取决于 CLI 运行时实现（来源：本地 SDK 源码 copilot/types.py）。  \n为可控性，建议确保技能名唯一、仅配置单一目录或由你自行按顺序拼接目录，并用 `disabled_skills` 明确屏蔽同名/不应启用的技能。  \n建议/落地：在无状态后端每次 `create_session`/`resume_session` 时显式传入同一份 `skill_directories` 与 `disabled_skills`，避免因默认加载顺序差异导致行为漂移。", "model": "gpt-5.2-codex"}
+{"index": 49, "question": "Provide best practices and common pitfalls for Skills: Conflict resolution and precedence defaults.", "answer": "SDK 源码仅暴露 SessionConfig/ResumeSessionConfig 的 `skill_directories` 和 `disabled_skills`，未定义冲突解析或优先级，行为由 CLI 侧决定（来源：本地 SDK 源码 copilot/types.py）。  \n最佳实践：技能名全局唯一、只配置单一目录或显式排序，并用 `disabled_skills` 禁用冲突项；常见坑是依赖默认加载顺序或 resume 未重传这两个字段导致行为漂移。  \n建议/落地：在 pipe 启动与 resume 时统一注入同一份 `skill_directories`/`disabled_skills` 并记录变更。", "model": "gpt-5.2-codex"}
+{"index": 50, "question": "Show a minimal example snippet for Skills: Conflict resolution and precedence defaults.", "answer": "SDK 里技能只通过 `skill_directories` 与 `disabled_skills` 配置，冲突/优先级未在源码定义，需自行避免同名。  \n最小示例：  \n```python\nsession = await client.create_session({\n    \"model\": \"gpt-5\",\n    \"skill_directories\": [\"/opt/skills\"],\n    \"disabled_skills\": [\"legacy_skill\"],\n})\n```  \n建议：技能名唯一并在 `resume_session` 时重传这两项。", "model": "gpt-5.2-codex"}
+{"index": 51, "question": "List recommended configuration defaults for Skills: Conflict resolution and precedence defaults.", "answer": "推荐默认值（基于 SDK 仅暴露 `skill_directories`/`disabled_skills`）：  \n- `skill_directories`: 明确设置为单一目录（或你自己控制顺序的列表），不要依赖 CLI 默认搜索顺序  \n- `disabled_skills`: 默认空列表；如存在同名/旧技能则显式禁用  \n- Resume/Replay：始终复用同一份配置以避免“隐式优先级”漂移", "model": "gpt-5.2-codex"}
+{"index": 52, "question": "How does Skills: Conflict resolution and precedence defaults relate to building a custom Agent?", "answer": "Skills 是会话级配置（`skill_directories`/`disabled_skills`），会影响所有自定义 Agent 的可用能力与提示行为；SDK 不定义冲突优先级，因此需要你在构建自定义 Agent 时确保技能命名唯一并显式禁用冲突项（来源：本地 SDK 源码）。  \n建议/落地：为 custom agent 固定同一份 skills 配置，并在 resume 时重复传入，避免行为漂移。", "model": "gpt-5.2-codex"}
+{"index": 53, "question": "Give a concise overview of Debugging: Tracing JSON-RPC traffic in the SDK.", "answer": "本地 SDK 源码里 JsonRpcClient 没有内置 JSON‑RPC trace，只能通过 `CopilotClient({\"log_level\":\"debug\"})` 打开 CLI 侧日志（非原始包）（来源：本地 SDK 源码）。  \n要抓实际 JSON‑RPC 流量，可 monkey‑patch `JsonRpcClient._send_message`/`_read_message` 或包装 stdio 进行 tee，最小示例如下。  \n建议/落地：在 pipe 中开启 patch 并对日志做脱敏与采样。  \n```python\nfrom copilot.jsonrpc import JsonRpcClient\n\norig_send = JsonRpcClient._send_message\nasync def _send(self, message):\n    print(\">>\", message)\n    return await orig_send(self, message)\nJsonRpcClient._send_message = _send\n\norig_read = JsonRpcClient._read_message\ndef _read(self):\n    msg = orig_read(self)\n    if msg:\n        print(\"<<\", msg)\n    return msg\nJsonRpcClient._read_message = _read\n```", "model": "gpt-5.2-codex"}
+{"index": 54, "question": "Provide best practices and common pitfalls for Debugging: Tracing JSON-RPC traffic in the SDK.", "answer": "源码里 JsonRpcClient 没有内置 trace，只能用 `CopilotClient({\"log_level\":\"debug\"})` 查看 CLI 侧日志或 monkey‑patch `JsonRpcClient._send_message/_read_message` 做 tee（来源：本地 SDK 源码）。  \n最佳实践：仅在调试启用、对 github_token/API key/内容脱敏、采样/限流、只读不改消息并注意线程安全；常见坑：记录完整 prompt/工具参数导致泄露，或同步打印阻塞 IO 造成超时/断连。", "model": "gpt-5.2-codex"}
+{"index": 55, "question": "Show a minimal example snippet for Debugging: Tracing JSON-RPC traffic in the SDK.", "answer": "最小示例（monkey‑patch `JsonRpcClient` 打印收发）：  \n```python\nfrom copilot.jsonrpc import JsonRpcClient\n\norig_send = JsonRpcClient._send_message\nasync def _send(self, msg):\n    print(\">>\", msg)\n    return await orig_send(self, msg)\nJsonRpcClient._send_message = _send\n\norig_read = JsonRpcClient._read_message\ndef _read(self):\n    msg = orig_read(self)\n    if msg:\n        print(\"<<\", msg)\n    return msg\nJsonRpcClient._read_message = _read\n```\n建议：仅在调试启用并脱敏日志。", "model": "gpt-5.2-codex"}
+{"index": 56, "question": "List recommended configuration defaults for Debugging: Tracing JSON-RPC traffic in the SDK.", "answer": "推荐默认值（基于 SDK 源码）：- 生产环境关闭 trace；- 调试时 `CopilotClient({\"log_level\":\"debug\"})`；- 如需 JSON‑RPC 报文，采用临时 monkey‑patch 并启用脱敏/采样；- 不修改消息内容，避免线程阻塞。  \n建议/落地：pipe 中通过环境变量开关调试与采样率。", "model": "gpt-5.2-codex"}
+{"index": 57, "question": "How does Debugging: Tracing JSON-RPC traffic in the SDK relate to building a custom Agent?", "answer": "JSON‑RPC trace 能看到 custom_agents 在 `session.create/session.resume` 的实际 payload，以及后续 `tool.call`/`permission.request`/`hooks.invoke` 是否按预期触发，从而验证自定义 Agent 的能力与权限边界（来源：本地 SDK 源码）。  \n建议/落地：仅在开发环境开启并脱敏日志；用它核对 customAgents/tools/权限决策与 MCP 配置。", "model": "gpt-5.2-codex"}
+{"index": 58, "question": "Give a concise overview of Billing & Policies: How seat management affects SDK features.", "answer": "- 访问与政策：SDK 依赖 Copilot CLI，需有效 Copilot 订阅且组织/企业未禁用 CLI，否则无法使用（源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md，https://raw.githubusercontent.com/github/copilot-cli/main/README.md）  \n- 计费与认证：每次 prompt 计入 Copilot premium requests 配额，PAT 需 Copilot Requests 权限（源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md，https://raw.githubusercontent.com/github/copilot-cli/main/README.md）\n\n建议/落地：启动先 `get_auth_status()`，失败时提示分配席位/启用 CLI 或更新 token", "model": "gpt-5.2-codex"}
+{"index": 59, "question": "Provide best practices and common pitfalls for Billing & Policies: How seat management affects SDK features.", "answer": "最佳实践：确认用户/组织席位允许 Copilot CLI/SDK 使用，启动前用 `get_auth_status()` 预检，使用 PAT 时确保具备 Copilot Requests 权限（源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md，https://raw.githubusercontent.com/github/copilot-cli/main/README.md）。  \n常见坑：未分配席位或组织/企业策略禁用 CLI 导致 SDK 失效、PAT 权限不足或 premium requests 用尽引发认证/配额错误（源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md，https://raw.githubusercontent.com/github/copilot-cli/main/README.md）。  \n建议/落地：在 pipe 启动时做席位与鉴权检测并给出明确提示/自助链接，记录每次请求计费与配额告警阈值以便限流。", "model": "gpt-5.2-codex"}
+{"index": 60, "question": "Show a minimal example snippet for Billing & Policies: How seat management affects SDK features.", "answer": "基于 SDK README，最小示例是在启动时用 `get_auth_status()` 检查是否已分配席位/可用认证（源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md）。  \n```python\nimport asyncio\nfrom copilot import CopilotClient\n\nasync def main():\n    client = CopilotClient()\n    await client.start()\n\n    auth = await client.get_auth_status()\n    if not auth.isAuthenticated:\n        raise RuntimeError(\"Copilot 未认证/未分配席位，请先登录或分配权限\")\n\n    # ...正常创建 session...\n    await client.stop()\n\nasyncio.run(main())\n```\n建议/落地：pipe 启动先做该检查，失败时提示分配席位或更新 PAT 权限。", "model": "gpt-5.2-codex"}
+{"index": 61, "question": "List recommended configuration defaults for Billing & Policies: How seat management affects SDK features.", "answer": "推荐默认值：CopilotClient 用 `use_logged_in_user=True`、`auto_start=True`、`log_level=\"info\"`；如用 PAT 则用 `github_token` 注入并确保具备 Copilot Requests 权限，且启动前 `get_auth_status()` 失败即按席位/策略限制处理（来源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md ，https://raw.githubusercontent.com/github/copilot-cli/main/README.md）。  \n建议/落地：pipe 启动先做 auth 预检并给出续订/分配席位提示，避免会话中途才触发权限或配额错误。", "model": "gpt-5.2-codex"}
+{"index": 62, "question": "How does Billing & Policies: How seat management affects SDK features relate to building a custom Agent?", "answer": "席位与组织策略决定 Copilot CLI/SDK 是否可用，因此自定义 Agent 只是同一会话上的配置，前提仍是有有效订阅与允许的策略，否则 Agent 无法运行（源：https://raw.githubusercontent.com/github/copilot-sdk/main/README.md ，https://raw.githubusercontent.com/github/copilot-cli/main/README.md）。  \n建议/落地：在创建自定义 Agent 前先 `get_auth_status()` 预检并对配额/政策限制做降级提示。", "model": "gpt-5.2-codex"}
+{"index": 63, "question": "How to configure MCP servers in ~/.copilot/config.json for SDK usage?", "answer": "我在 CLI 文档里未看到 `~/.copilot/config.json` 的 MCP 配置结构；CLI 仅提供 `/mcp add|edit|delete|show` 命令管理配置（来源：Copilot CLI 文档）。  \n因此建议用 CLI 写入配置，并在 SDK 中用 `config_dir` 指向该配置目录；或直接在 SDK 的 `create_session(mcp_servers=...)` 传入。  \n如果你确认存在 `~/.copilot/config.json` 的具体 schema，请提供示例或路径，我可按你的文件格式给出精确配置。", "model": "gpt-5.2-codex"}
+{"index": 64, "question": "What CLI environment variables force 'Agent' mode vs 'Generic' mode?", "answer": "CLI 文档未提到任何“通过环境变量强制 Agent 模式/Generic 模式”的开关（源：Copilot CLI 文档）。  \n已知与模式相关的是命令/参数，例如 `--agent` 选择自定义 agent，或交互内 `/agent` 切换；但不是环境变量。  \n如果你指的是内部实验开关，请提供具体变量名或版本线索，我可继续追索。", "model": "gpt-5.2-codex"}
+{"index": 65, "question": "Explain the 'confirmation' flow in CLI and how it maps to SDK events.", "answer": "- CLI：工具权限弹窗确认，可用 `/allow-all` 或 `/yolo` 自动批准。（源: https://raw.githubusercontent.com/github/copilot-cli/main/README.md）  \n- SDK：对应 JSON‑RPC `permission.request`→`on_permission_request` 返回 `approved/denied-*`，`session.on()` 只用于审计 tool.execution_*，无独立 confirmation 事件。（源: 本地 SDK 源码 copilot/client.py、copilot/session.py、copilot/types.py）\n\n示例：\n```python\nfrom copilot import CopilotClient\nfrom copilot.generated.session_events import SessionEventType\n\nclient = CopilotClient()\nawait client.start()\nsession = await client.create_session({\n    \"model\": \"gpt-5\",\n    \"on_permission_request\": lambda req, _: {\"kind\": \"approved\"},\n})\nsession.on(lambda ev: ev.type == SessionEventType.TOOL_EXECUTION_START and print(ev.data.tool_name))\n```\n\n建议/落地：非交互模式实现 `on_permission_request` 并记录 `tool.execution_*` 事件。", "model": "gpt-5.2-codex"}
+{"index": 66, "question": "Does the CLI support 'dry-run' permission checks for tools?", "answer": "CLI 文档未提到“dry-run”权限检查，只有正常确认与 `/allow-all`、`/yolo` 自动批准（源：https://raw.githubusercontent.com/github/copilot-cli/main/README.md）。SDK 侧仅有 `permission.request`→`on_permission_request` 与 `hooks.on_pre_tool_use` 的拦截/拒绝（本地 SDK 源码），不提供不执行的试运行；建议/落地：pipe 中用 `on_permission_request` 记录/拒绝高风险工具并在 hooks 做审计。", "model": "gpt-5.2-codex"}
+{"index": 67, "question": "What are the undocumented requirements for 'workspace' context updates?", "answer": "CLI 文档与本地 SDK 源码都未提到“workspace context updates”的未公开要求；SDK 只暴露 `working_directory` 与 `session.workspace_path`，以及 `attachments` 真实路径（来源：本地 SDK 源码）。  \n如果你指的是 CLI 的“工作区/会话文件”更新规则，请提供具体页面或日志片段，我可以进一步定位。", "model": "gpt-5.2-codex"}
+{"index": 68, "question": "How does the CLI handle 'device code' re-authentication automatically?", "answer": "CLI 文档未说明“自动 device code 重新认证”的具体机制；只提到未登录时使用 `/login`，PAT 可通过 `GH_TOKEN/GITHUB_TOKEN` 提供（源：Copilot CLI 文档）。因此无法确认是否有自动 re-auth 或缓存刷新策略。  \n若需无交互场景，请使用 SDK 的 `github_token` 注入并自行实现 device flow 轮询与持久化。", "model": "gpt-5.2-codex"}

plugins/debug/copilot_sdk_research/test_multi_rule_permission.py

@@ -0,0 +1,186 @@
+"""
+Test multi-rule permission control pattern (VSCode-style)
+Tests ordered rule matching like VSCode's chat.tools.terminal.autoApprove
+SAFE VERSION: Uses harmless commands (echo/ls) only. No rm, no git.
+"""
+
+import argparse
+import asyncio
+import json
+import logging
+import re
+from typing import Any, Dict, List, Tuple
+
+from copilot import CopilotClient
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+logger = logging.getLogger(__name__)
+
+
+def build_multi_rule_handler(rules_json: str):
+    """
+    Build permission handler with ordered rules (VSCode-style)
+    """
+    try:
+        rules = json.loads(rules_json) if rules_json else {}
+    except json.JSONDecodeError as e:
+        logger.error("Invalid rules JSON: %s", e)
+        rules = {}
+
+    async def on_permission_request(request: Dict[str, Any], context: Dict[str, str]):
+        kind = request.get("kind")
+        command = request.get("fullCommandText", "") or request.get("command", "")
+
+        # Always approve read and url
+        if kind in ("read", "url"):
+            return {"kind": "approved"}
+
+        # For shell commands, apply ordered rules
+        if kind == "shell" and command:
+            for pattern, approved in rules.items():
+                try:
+                    if re.match(pattern, command):
+                        if approved:
+                            logger.info(
+                                "✅ Approved (rule match): pattern=%r command=%r",
+                                pattern,
+                                command,
+                            )
+                            return {"kind": "approved"}
+                        else:
+                            logger.warning(
+                                "❌ Denied (rule match): pattern=%r command=%r",
+                                pattern,
+                                command,
+                            )
+                            return {
+                                "kind": "denied-by-rules",
+                                "rules": [
+                                    {"kind": "multi-rule-deny", "pattern": pattern}
+                                ],
+                            }
+                except re.error as exc:
+                    logger.error("Invalid pattern %r: %s", pattern, exc)
+                    continue
+
+        # Default deny for shell without matching rule
+        logger.warning("❌ Denied (no matching rule): command=%r", command)
+        return {"kind": "denied-by-rules", "rules": [{"kind": "no-rule-match"}]}
+
+    return on_permission_request
+
+
+async def run_test(model: str, rules_json: str, prompt: str) -> Tuple[bool, str]:
+    """Run a single test and return (approved, response)"""
+    try:
+        client = CopilotClient()
+        await client.start()
+
+        session = await client.create_session(
+            {
+                "model": model,
+                "on_permission_request": build_multi_rule_handler(rules_json),
+            }
+        )
+
+        # Set a short timeout
+        try:
+            response = await asyncio.wait_for(
+                session.send_and_wait({"prompt": prompt}), timeout=15.0
+            )
+        except asyncio.TimeoutError:
+            logger.error("Test Timed Out")
+            return (False, "Timeout")
+        finally:
+            await client.stop()
+
+        content = response.data.content
+        # Heuristics to detect denial in response
+        denied_keywords = [
+            "不允许",
+            "无法",
+            "对不起",
+            "Sorry",
+            "can't",
+            "cannot",
+            "not have permission",
+            "denied",
+        ]
+        is_denied = any(kw in content for kw in denied_keywords)
+
+        return (not is_denied, content)
+    except Exception as e:
+        logger.error("Test failed: %s", e)
+        return (False, str(e))
+
+
+async def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--model", default="gpt-4.1", help="Model ID")
+    args = parser.parse_args()
+
+    # LOGIC TEST RULES
+    # 1. Deny "echo secret" explicitly (Specific Deny)
+    # 2. Allow "echo" anything else (General Allow)
+    # 3. Allow "ls" (General Allow)
+    # 4. Deny everything else (Default Deny)
+    logic_test_rules = {
+        "^echo\\s+secret": False,  # Higher priority: Deny specific echo
+        "^echo": True,  # Lower priority: Allow general echo
+        "^ls": True,  # Allow ls
+        ".*": False,  # Deny everything else (e.g. whoami)
+    }
+
+    rules_json = json.dumps(logic_test_rules)
+
+    test_cases = [
+        # 1. Matches Rule 2 (^echo) -> Should be Approved
+        ("Allowed: Normal Echo", "请执行: echo 'hello world'", True),
+        # 2. Matches Rule 3 (^ls) -> Should be Approved
+        ("Allowed: LS", "请执行: ls -la", True),
+        # 3. Matches Rule 1 (^echo\s+secret) -> Should be DENIED
+        # This proves the ORDER matters. If it matched Rule 2 first, it would be allowed.
+        ("Denied: Restricted Echo", "请执行: echo secret data", False),
+        # 4. Matches Rule 4 (.*) -> Should be DENIED
+        ("Denied: Unknown Command", "请执行: whoami", False),
+    ]
+
+    logger.info("=" * 80)
+    logger.info("Safe Multi-Rule Logic Test (Proving Precedence)")
+    logger.info("Rules: %s", json.dumps(logic_test_rules, indent=2))
+    logger.info("=" * 80)
+
+    results = []
+    for i, (name, prompt, expected) in enumerate(test_cases, 1):
+        logger.info("\n[Test %d/%d] %s", i, len(test_cases), name)
+        logger.info("  Prompt: %s", prompt)
+
+        approved, response = await run_test(args.model, rules_json, prompt)
+        passed = approved == expected
+
+        status = "✅ PASS" if passed else "❌ FAIL"
+        results.append((name, passed))
+
+        logger.info(
+            "  Expected: %s, Got: %s - %s",
+            "Approved" if expected else "Denied",
+            "Approved" if approved else "Denied",
+            status,
+        )
+        logger.info("  Response: %s", response[:100].replace("\n", " "))
+
+    # Summary
+    logger.info("\n" + "=" * 80)
+    logger.info("Test Summary")
+    logger.info("=" * 80)
+    passed_count = sum(1 for _, passed in results if passed)
+    for name, passed in results:
+        logger.info("%s %s", "✅" if passed else "❌", name)
+    logger.info("Total: %d/%d tests passed", passed_count, len(results))
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

plugins/debug/copilot_sdk_research/test_permission_comprehensive.py

@@ -0,0 +1,202 @@
+"""
+Comprehensive Permission Control Test Suite
+Tests all permission control scenarios for GitHub Copilot SDK
+"""
+
+import argparse
+import asyncio
+import logging
+import re
+from typing import Any, Dict, List, Tuple
+
+from copilot import CopilotClient
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+logger = logging.getLogger(__name__)
+
+
+def build_permission_handler(allow_all: bool, allow_shell: bool, pattern: str):
+    async def on_permission_request(request: Dict[str, Any], context: Dict[str, str]):
+        kind = request.get("kind")
+        # Shell requests use 'fullCommandText' not 'command'
+        command = request.get("fullCommandText", "") or request.get("command", "")
+
+        if allow_all:
+            logger.info("✅ Approved (allow-all): kind=%s command=%r", kind, command)
+            return {"kind": "approved"}
+
+        if kind in ("read", "url"):
+            logger.info("✅ Approved (safe): kind=%s", kind)
+            return {"kind": "approved"}
+
+        if kind == "shell":
+            if allow_shell:
+                logger.info("✅ Approved (allow-shell): command=%r", command)
+                return {"kind": "approved"}
+
+            if pattern and command:
+                try:
+                    if re.match(pattern, command):
+                        logger.info(
+                            "✅ Approved (regex match): pattern=%r command=%r",
+                            pattern,
+                            command,
+                        )
+                        return {"kind": "approved"}
+                except re.error as exc:
+                    logger.error("Invalid regex pattern: %s (%s)", pattern, exc)
+
+        logger.warning("❌ Denied: kind=%s command=%r", kind, command)
+        return {"kind": "denied-by-rules", "rules": [{"kind": "test-suite"}]}
+
+    return on_permission_request
+
+
+async def run_test(
+    model: str, allow_all: bool, allow_shell: bool, pattern: str, prompt: str
+) -> Tuple[bool, str]:
+    """Run a single test and return (success, response)"""
+    try:
+        client = CopilotClient()
+        await client.start()
+
+        session = await client.create_session(
+            {
+                "model": model,
+                "on_permission_request": build_permission_handler(
+                    allow_all=allow_all,
+                    allow_shell=allow_shell,
+                    pattern=pattern,
+                ),
+            }
+        )
+
+        response = await session.send_and_wait({"prompt": prompt})
+        await client.stop()
+
+        content = response.data.content
+        # Check if response indicates success or denial
+        denied_keywords = [
+            "不允许",
+            "无法",
+            "对不起",
+            "Sorry",
+            "can't",
+            "cannot",
+            "not have permission",
+        ]
+        is_denied = any(kw in content for kw in denied_keywords)
+
+        return (not is_denied, content)
+    except Exception as e:
+        logger.error("Test failed with exception: %s", e)
+        return (False, str(e))
+
+
+async def main():
+    parser = argparse.ArgumentParser(
+        description="Comprehensive permission control test suite."
+    )
+    parser.add_argument("--model", default="gpt-4.1", help="Model ID for testing.")
+
+    args = parser.parse_args()
+
+    # Test cases: (name, allow_all, allow_shell, pattern, prompt, expected_approved)
+    test_cases = [
+        ("Default Deny Shell", False, False, "", "请执行: ls -la", False),
+        ("Allow All", True, False, "", "请执行: ls -la", True),
+        ("Allow Shell", False, True, "", "请执行: pwd", True),
+        ("Regex Match: ^ls", False, False, "^ls", "请执行: ls -la", True),
+        ("Regex No Match: ^ls vs pwd", False, False, "^ls", "请执行: pwd", False),
+        (
+            "Regex Complex: ^(ls|pwd|echo)",
+            False,
+            False,
+            "^(ls|pwd|echo)",
+            "请执行: pwd",
+            True,
+        ),
+        (
+            "Regex Complex No Match: git",
+            False,
+            False,
+            "^(ls|pwd|echo)",
+            "请执行: git status",
+            False,
+        ),
+        (
+            "Read Permission (Always Allow)",
+            False,
+            False,
+            "",
+            "Read the file: README.md",
+            True,
+        ),
+    ]
+
+    results = []
+    logger.info("=" * 80)
+    logger.info("Starting Comprehensive Permission Control Test Suite")
+    logger.info("Model: %s", args.model)
+    logger.info("=" * 80)
+
+    for i, (name, allow_all, allow_shell, pattern, prompt, expected) in enumerate(
+        test_cases, 1
+    ):
+        logger.info("\n[Test %d/%d] %s", i, len(test_cases), name)
+        logger.info(
+            "  Config: allow_all=%s, allow_shell=%s, pattern=%r",
+            allow_all,
+            allow_shell,
+            pattern,
+        )
+        logger.info("  Prompt: %s", prompt)
+
+        approved, response = await run_test(
+            args.model, allow_all, allow_shell, pattern, prompt
+        )
+        passed = approved == expected
+
+        status = "✅ PASS" if passed else "❌ FAIL"
+        results.append((name, passed))
+
+        logger.info(
+            "  Expected: %s, Got: %s - %s",
+            "Approved" if expected else "Denied",
+            "Approved" if approved else "Denied",
+            status,
+        )
+        logger.info(
+            "  Response: %s",
+            response[:100] + "..." if len(response) > 100 else response,
+        )
+
+    # Summary
+    logger.info("\n" + "=" * 80)
+    logger.info("Test Summary")
+    logger.info("=" * 80)
+    passed_count = sum(1 for _, passed in results if passed)
+    total_count = len(results)
+
+    for name, passed in results:
+        logger.info("%s %s", "✅" if passed else "❌", name)
+
+    logger.info("-" * 80)
+    logger.info(
+        "Total: %d/%d tests passed (%.1f%%)",
+        passed_count,
+        total_count,
+        100 * passed_count / total_count,
+    )
+
+    if passed_count == total_count:
+        logger.info("🎉 All tests passed!")
+    else:
+        logger.warning("⚠️  Some tests failed. Please review the logs.")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

plugins/debug/copilot_sdk_research/test_shell_permission_pattern.py

@@ -0,0 +1,90 @@
+import argparse
+import asyncio
+import logging
+import re
+from typing import Any, Dict
+
+from copilot import CopilotClient
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+logger = logging.getLogger(__name__)
+
+
+def build_permission_handler(allow_all: bool, allow_shell: bool, pattern: str):
+    async def on_permission_request(request: Dict[str, Any], context: Dict[str, str]):
+        kind = request.get("kind")
+        # Shell requests use 'fullCommandText' not 'command'
+        command = request.get("fullCommandText", "") or request.get("command", "")
+        logger.info("permission.request FULL: %s", request)
+        logger.info("permission.request kind=%s command=%r", kind, command)
+
+        if allow_all:
+            return {"kind": "approved"}
+
+        if kind in ("read", "url"):
+            return {"kind": "approved"}
+
+        if kind == "shell":
+            if allow_shell:
+                return {"kind": "approved"}
+
+            if pattern and command:
+                try:
+                    if re.match(pattern, command):
+                        return {"kind": "approved"}
+                except re.error as exc:
+                    logger.error("Invalid regex pattern: %s (%s)", pattern, exc)
+
+        return {"kind": "denied-by-rules", "rules": [{"kind": "debug-shell-pattern"}]}
+
+    return on_permission_request
+
+
+async def main():
+    parser = argparse.ArgumentParser(
+        description="Test shell permission regex with GitHub Copilot SDK."
+    )
+    parser.add_argument(
+        "--pattern", default="", help="Regex pattern for auto-approving shell commands."
+    )
+    parser.add_argument(
+        "--allow-shell", action="store_true", help="Auto-approve all shell commands."
+    )
+    parser.add_argument(
+        "--allow-all", action="store_true", help="Auto-approve all permission requests."
+    )
+    parser.add_argument(
+        "--prompt",
+        default="请执行: ls -la",
+        help="Prompt to trigger a shell tool request.",
+    )
+    parser.add_argument("--model", default="gpt-5-mini", help="Model ID for testing.")
+
+    args = parser.parse_args()
+
+    client = CopilotClient()
+    await client.start()
+
+    session = await client.create_session(
+        {
+            "model": args.model,
+            "on_permission_request": build_permission_handler(
+                allow_all=args.allow_all,
+                allow_shell=args.allow_shell,
+                pattern=args.pattern,
+            ),
+        }
+    )
+
+    logger.info("Sending prompt: %s", args.prompt)
+    response = await session.send_and_wait({"prompt": args.prompt})
+    logger.info("Response: %s", response.data.content)
+
+    await client.stop()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

plugins/debug/mcp_test.py

@@ -0,0 +1,47 @@
+import asyncio
+import os
+from copilot import CopilotClient
+
+
+async def main():
+    token = os.getenv("GH_TOKEN") or os.getenv("GITHUB_TOKEN")
+    if not token:
+        print(
+            "Error: GH_TOKEN (or GITHUB_TOKEN) environment variable not set. Please export GH_TOKEN=... before running."
+        )
+        return
+
+    client = CopilotClient()
+    await client.start()
+
+    async def on_permission_request(request, _ctx):
+        if request.get("kind") == "mcp":
+            return {"kind": "approved"}
+        return {"kind": "approved"}
+
+    session = await client.create_session(
+        {
+            "model": "gpt-5-mini",
+            "mcp_servers": {
+                "github": {
+                    "type": "http",
+                    "url": "https://api.githubcopilot.com/mcp/",
+                    "headers": {"Authorization": f"Bearer {token}"},
+                    "tools": ["*"],
+                }
+            }
+        }
+    )
+
+    result = await session.send_and_wait(
+        {
+            "prompt": "Use GitHub MCP tools to find the owner of the 'awesome-openwebui' repository.",
+        },timeout=1000
+    )
+    print(result.data.content)
+
+    await client.stop()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

plugins/filters/async-context-compression/README.md

@@ -5,31 +5,10 @@
 This filter reduces token consumption in long conversations through intelligent summarization and message compression while keeping conversations coherent.
 
 ## What's new in 1.2.2
+
 - **Critical Fix**: Resolved `TypeError: 'str' object is not callable` caused by variable name conflict in logging function.
 - **Compatibility**: Enhanced `params` handling to support Pydantic objects, improving compatibility with different OpenWebUI versions.
 
-## What's new in 1.2.1
-
-- **Smart Configuration**: Automatically detects base model settings for custom models and adds `summary_model_max_context` for independent summary limits.
-- **Performance & Refactoring**: Optimized threshold parsing with caching, removed redundant code, and improved LLM response handling (JSONResponse support).
-- **Bug Fixes & Modernization**: Fixed `datetime` deprecation warnings, corrected type annotations, and replaced print statements with proper logging.
-
-## What's new in 1.2.0
-
-- **Preflight Context Check**: Before sending to the model, validates that total tokens fit within the context window. Automatically trims or drops oldest messages if exceeded.
-- **Structure-Aware Assistant Trimming**: When context exceeds the limit, long AI responses are intelligently collapsed while preserving their structure (headers H1-H6, first line, last line).
-- **Native Tool Output Trimming**: Detects and trims native tool outputs (`function_calling: "native"`), extracting only the final answer. Enable via `enable_tool_output_trimming`. **Note**: Non-native tool outputs are not fully injected into context.
-- **Consolidated Status Notifications**: Unified "Context Usage" and "Context Summary Updated" notifications with appended warnings (e.g., `| ⚠️ High Usage`) for clearer feedback.
-- **Context Usage Warning**: Emits a warning notification when context usage exceeds 90%.
-- **Enhanced Header Detection**: Optimized regex (`^#{1,6}\s+`) to avoid false positives like `#hashtag`.
-- **Detailed Token Logging**: Logs now show token breakdown for System, Head, Summary, and Tail sections with total.
-
-## What's new in 1.1.3
-- **Improved Compatibility**: Changed summary injection role from `user` to `assistant` for better compatibility across different LLMs.
-- **Enhanced Stability**: Fixed a race condition in state management that could cause "inlet state not found" warnings in high-concurrency scenarios.
-- **Bug Fixes**: Corrected default model handling to prevent misleading logs when no model is specified.
-
-
 ---
 
 ## Core Features
@@ -57,11 +36,7 @@ This filter reduces token consumption in long conversations through intelligent
 
 ### 2) Filter order
 
-It is recommended to keep this filter early in the chain so it runs before filters that mutate messages:
-
-1. Pre-filters (priority < 10) — e.g., system prompt injectors.
-2. This compression filter (priority = 10).
-3. Post-filters (priority > 10) — e.g., output formatting.
+- Recommended order: pre-filters (<10) → this filter (10) → post-filters (>10).
 
 ---
 
@@ -85,6 +60,16 @@ It is recommended to keep this filter early in the chain so it runs before filte
 
 ---
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
+## Troubleshooting ❓
+
 - **Initial system prompt is lost**: Keep `keep_first` greater than 0 to protect the initial message.
 - **Compression effect is weak**: Raise `compression_threshold_tokens` or lower `keep_first` / `keep_last` to allow more aggressive compression.
 - **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/filters/async-context-compression/README_CN.md

@@ -7,31 +7,10 @@
 本过滤器通过智能摘要和消息压缩技术，在保持对话连贯性的同时，显著降低长对话的 Token 消耗。
 
 ## 1.2.2 版本更新
+
 - **严重错误修复**: 解决了因日志函数变量名冲突导致的 `TypeError: 'str' object is not callable` 错误。
 - **兼容性增强**: 改进了 `params` 处理逻辑以支持 Pydantic 对象，提高了对不同 OpenWebUI 版本的兼容性。
 
-## 1.2.1 版本更新
-
-- **智能配置增强**: 自动检测自定义模型的基础模型配置，并新增 `summary_model_max_context` 参数以独立控制摘要模型的上下文限制。
-- **性能优化与重构**: 重构了阈值解析逻辑并增加缓存，移除了冗余的处理代码，并增强了 LLM 响应处理（支持 JSONResponse）。
-- **稳定性改进**: 修复了 `datetime` 弃用警告，修正了类型注解，并将 print 语句替换为标准日志记录。
-
-## 1.2.0 版本更新
-
-- **预检上下文检查 (Preflight Context Check)**: 在发送给模型之前，验证总 Token 是否符合上下文窗口。如果超出，自动裁剪或丢弃最旧的消息。
-- **结构感知助手裁剪 (Structure-Aware Assistant Trimming)**: 当上下文超出限制时，智能折叠过长的 AI 回复，同时保留其结构（标题 H1-H6、首行、尾行）。
-- **原生工具输出裁剪 (Native Tool Output Trimming)**: 检测并裁剪原生工具输出 (`function_calling: "native"`)，仅提取最终答案。通过 `enable_tool_output_trimming` 启用。**注意**：非原生工具调用输出不会完整注入上下文。
-- **统一状态通知**: 统一了“上下文使用情况”和“上下文摘要更新”的通知，并附加警告（例如 `| ⚠️ 高负载`），反馈更清晰。
-- **上下文使用警告**: 当上下文使用率超过 90% 时发出警告通知。
-- **增强的标题检测**: 优化了正则表达式 (`^#{1,6}\s+`) 以避免误判（如 `#hashtag`）。
-- **详细 Token 日志**: 日志现在显示 System、Head、Summary 和 Tail 部分的 Token 细分及总计。
-
-## 1.1.3 版本更新
-- **兼容性提升**: 将摘要注入角色从 `user` 改为 `assistant`，以提高在不同 LLM 之间的兼容性。
-- **稳定性增强**: 修复了状态管理中的竞态条件，解决了高并发场景下可能出现的“无法获取 inlet 状态”警告。
-- **Bug 修复**: 修正了默认模型处理逻辑，防止在未指定模型时产生误导性日志。
-
-
 ---
 
 ## 核心特性
@@ -61,11 +40,7 @@
 
 ### 2. 过滤器顺序
 
-建议将此过滤器的优先级设置得相对较高（数值较小），以确保它在其他可能修改消息内容的过滤器之前运行。一个典型的顺序可能是：
-
-1. 前置过滤器 (priority < 10) —— 例如系统提示注入。
-2. 本压缩过滤器 (priority = 10)。
-3. 后置过滤器 (priority > 10) —— 例如最终输出格式化。
+- 建议顺序：前置过滤器（<10）→ 本过滤器（10）→ 后置过滤器（>10）。
 
 ---
 
@@ -124,6 +99,16 @@
 
 ---
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
+## 故障排除 (Troubleshooting) ❓
+
 - **初始系统提示丢失**：将 `keep_first` 设置为大于 0。
 - **压缩效果不明显**：提高 `compression_threshold_tokens`，或降低 `keep_first` / `keep_last` 以增强压缩力度。
 - **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/filters/folder-memory/README.md

@@ -2,35 +2,30 @@
 
 **Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.1.0 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
----
+**Folder Memory** is an intelligent context filter plugin for OpenWebUI. It automatically extracts consistent "Project Rules" from ongoing conversations within a folder and injects them back into the folder's system prompt.
+
+## 🔥 What's New in v0.1.0
 
-### 📌 What's new in 0.1.0
 - **Initial Release**: Automated "Project Rules" management for OpenWebUI folders.
 - **Folder-Level Persistence**: Automatically updates folder system prompts with extracted rules.
 - **Optimized Performance**: Runs asynchronously and supports `PRIORITY` configuration for seamless integration with other filters.
 
----
-
-**Folder Memory** is an intelligent context filter plugin for OpenWebUI. It automatically extracts consistent "Project Rules" from ongoing conversations within a folder and injects them back into the folder's system prompt.
-
-## ✨ Features
+## ✨ Core Features
 
 - **Automatic Extraction**: Analyzes chat history every N messages to extract project rules.
 - **Non-destructive Injection**: Updates only the specific "Project Rules" block in the system prompt, preserving other instructions.
 - **Async Processing**: Runs in the background without blocking the user's chat experience.
 - **ORM Integration**: Directly updates folder data using OpenWebUI's internal models for reliability.
 
-## ⚠️ Prerequisites
+## Installation & Configuration
 
-- **Conversations must occur inside a folder.** This plugin only triggers when a chat belongs to a folder (i.e., you need to create a folder in OpenWebUI and start a conversation within it).
-
-## 📦 Installation
+### 1) Installation
 
 1. Copy `folder_memory.py` to your OpenWebUI `plugins/filters/` directory (or upload via Admin UI).
 2. Enable the filter in your **Settings** -> **Filters**.
-3. (Optional) Configure the triggering threshold (default: every 10 messages).
+3. **Prerequisite**: Conversations must occur inside a folder (create a folder and start a chat within it).
 
-## ⚙️ Configuration (Valves)
+### 2) Configuration (Valves)
 
 | Valve | Default | Description |
 | :--- | :--- | :--- |
@@ -41,6 +36,10 @@
 | `SHOW_DEBUG_LOG` | `False` | Show detailed debug logs in the browser console. |
 | `UPDATE_ROOT_FOLDER` | `False` | If enabled, finds and updates the root folder rules instead of the current subfolder. |
 
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
 ## 🛠️ How It Works
 
 ![Folder Memory Demo](https://raw.githubusercontent.com/Fu-Jie/awesome-openwebui/main/plugins/filters/folder-memory/folder-memory-demo.png)
@@ -58,3 +57,7 @@
 ## 🗺️ Roadmap
 
 See [ROADMAP.md](./ROADMAP.md) for future plans, including "Project Knowledge" collection.
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/filters/folder-memory/README_CN.md

@@ -2,37 +2,32 @@
 
 **作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.1.0 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
----
-
-### 📌 0.1.0 版本特性
-- **首个版本发布**：专注于自动化的“项目规则”管理。
-- **文件夹级持久化**：自动将提取的规则回写到文件夹系统提示词中。
-- **性能优化**：采用异步处理机制，并支持 `PRIORITY` 配置，确保与其他过滤器（如上下文压缩）完美协作。
-
----
-
 **文件夹记忆 (Folder Memory)** 是一个 OpenWebUI 的智能上下文过滤器插件。它能自动从文件夹内的对话中提取一致性的“项目规则”，并将其回写到文件夹的系统提示词中。
 
 这确保了该文件夹内的所有未来对话都能共享相同的进化上下文和规则，无需手动更新。
 
-## ✨ 功能特性
+## 🔥 最新更新 v0.1.0
+
+- **首个版本发布**：专注于自动化的“项目规则”管理。
+- **文件夹级持久化**：自动将提取的规则回写到文件夹系统提示词中。
+- **性能优化**：采用异步处理机制，并支持 `PRIORITY` 配置，确保与其他过滤器（如上下文压缩）完美协作。
+
+## ✨ 核心特性
 
 - **自动提取**：每隔 N 条消息分析一次聊天记录，提取项目规则。
 - **无损注入**：仅更新系统提示词中的特定“项目规则”块，保留其他指令。
 - **异步处理**：在后台运行，不阻塞用户的聊天体验。
 - **ORM 集成**：直接使用 OpenWebUI 的内部模型更新文件夹数据，确保可靠性。
 
-## ⚠️ 前置条件
+## 安装与配置
 
-- **对话必须在文件夹内进行。** 此插件仅在聊天属于某个文件夹时触发（即您需要先在 OpenWebUI 中创建一个文件夹，并在其内部开始对话）。
+### 1. 安装
 
-## 📦 安装指南
-
-1. 将 `folder_memory.py` (或中文版 `folder_memory_cn.py`) 复制到 OpenWebUI 的 `plugins/filters/` 目录（或通过管理员 UI 上传）。
+1. 将 `folder_memory.py`（或中文版 `folder_memory_cn.py`）复制到 OpenWebUI 的 `plugins/filters/` 目录（或通过管理员 UI 上传）。
 2. 在 **设置** -> **过滤器** 中启用该插件。
-3. （可选）配置触发阈值（默认：每 10 条消息）。
+3. **前置条件**：对话必须在文件夹内进行（先创建文件夹并在其中开始对话）。
 
-## ⚙️ 配置 (Valves)
+### 2. 配置 (Valves)
 
 | 参数 | 默认值 | 说明 |
 | :--- | :--- | :--- |
@@ -43,6 +38,10 @@
 | `SHOW_DEBUG_LOG` | `False` | 在浏览器控制台显示详细调试日志。 |
 | `UPDATE_ROOT_FOLDER` | `False` | 如果启用，将向上查找并更新根文件夹的规则，而不是当前子文件夹。 |
 
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
 ## 🛠️ 工作原理
 
 ![Folder Memory Demo](https://raw.githubusercontent.com/Fu-Jie/awesome-openwebui/main/plugins/filters/folder-memory/folder-memory-demo.png)
@@ -60,3 +59,7 @@
 ## 🗺️ 路线图
 
 查看 [ROADMAP.md](./ROADMAP.md) 了解未来计划，包括“项目知识”收集功能。
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/filters/markdown_normalizer/README.md

@@ -4,7 +4,11 @@
 
 A content normalizer filter for Open WebUI that fixes common Markdown formatting issues in LLM outputs. It ensures that code blocks, LaTeX formulas, Mermaid diagrams, and other Markdown elements are rendered correctly.
 
-## Features
+## 🔥 What's New in v1.2.4
+
+* **Documentation Sync**: Synchronized version numbers across all documentation and code files.
+
+## ✨ Core Features
 
 * **Details Tag Normalization**: Ensures proper spacing for `<details>` tags (used for thought chains). Adds a blank line after `</details>` and ensures a newline after self-closing `<details />` tags to prevent rendering issues.
 * **Emphasis Spacing Fix**: Fixes extra spaces inside emphasis markers (e.g., `** text **` -> `**text**`) which can cause rendering failures. Includes safeguards to protect math expressions (e.g., `2 * 3 * 4`) and list variables.
@@ -19,7 +23,7 @@ A content normalizer filter for Open WebUI that fixes common Markdown formatting
 * **Table Fix**: Adds missing closing pipes in tables.
 * **XML Cleanup**: Removes leftover XML artifacts.
 
-## Usage
+## How to Use 🛠️
 
 1. Install the plugin in Open WebUI.
 2. Enable the filter globally or for specific models.
@@ -28,69 +32,38 @@ A content normalizer filter for Open WebUI that fixes common Markdown formatting
     > [!WARNING]
     > As this is an initial version, some "negative fixes" might occur (e.g., breaking valid Markdown). If you encounter issues, please check the console logs, copy the "Original" vs "Normalized" content, and submit an issue.
 
-## Configuration (Valves)
+## Configuration (Valves) ⚙️
 
-* `priority`: Filter priority (default: 50).
-* `enable_escape_fix`: Fix excessive escape characters.
-* `enable_thought_tag_fix`: Normalize thought tags.
-* `enable_details_tag_fix`: Normalize details tags (default: True).
-* `enable_code_block_fix`: Fix code block formatting.
-* `enable_latex_fix`: Normalize LaTeX formulas.
-* `enable_list_fix`: Fix list item newlines (Experimental).
-* `enable_unclosed_block_fix`: Auto-close unclosed code blocks.
-* `enable_fullwidth_symbol_fix`: Fix full-width symbols in code blocks.
-* `enable_mermaid_fix`: Fix Mermaid syntax errors.
-* `enable_heading_fix`: Fix missing space in headings.
-* `enable_table_fix`: Fix missing closing pipe in tables.
-* `enable_xml_tag_cleanup`: Cleanup leftover XML tags.
-* `enable_emphasis_spacing_fix`: Fix extra spaces in emphasis (default: False).
-* `show_status`: Show status notification when fixes are applied.
-* `show_debug_log`: Print debug logs to browser console.
+| Parameter | Default | Description |
+| :--- | :--- | :--- |
+| `priority` | `50` | Filter priority. Higher runs later (recommended after other filters). |
+| `enable_escape_fix` | `True` | Fix excessive escape characters (`\n`, `\t`, etc.). |
+| `enable_escape_fix_in_code_blocks` | `False` | Apply escape fix inside code blocks (may affect valid code). |
+| `enable_thought_tag_fix` | `True` | Normalize thought tags (`</thought>`). |
+| `enable_details_tag_fix` | `True` | Normalize `<details>` tags and add safe spacing. |
+| `enable_code_block_fix` | `True` | Fix code block formatting (indentation/newlines). |
+| `enable_latex_fix` | `True` | Normalize LaTeX delimiters (`\[` -> `$$`, `\(` -> `$`). |
+| `enable_list_fix` | `False` | Fix list item newlines (experimental). |
+| `enable_unclosed_block_fix` | `True` | Auto-close unclosed code blocks. |
+| `enable_fullwidth_symbol_fix` | `False` | Fix full-width symbols in code blocks. |
+| `enable_mermaid_fix` | `True` | Fix common Mermaid syntax errors. |
+| `enable_heading_fix` | `True` | Fix missing space in headings. |
+| `enable_table_fix` | `True` | Fix missing closing pipe in tables. |
+| `enable_xml_tag_cleanup` | `True` | Cleanup leftover XML tags. |
+| `enable_emphasis_spacing_fix` | `False` | Fix extra spaces in emphasis. |
+| `show_status` | `True` | Show status notification when fixes are applied. |
+| `show_debug_log` | `True` | Print debug logs to browser console (F12). |
 
-## Troubleshooting ❓
+## ⭐ Support
+
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
+
+## 🧩 Others
+
+### Troubleshooting ❓
 
 * **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
 
-## Changelog
+### Changelog
 
-### v1.2.4
-
-* **Documentation Updates**: Synchronized version numbers across all documentation and code files.
-
-### v1.2.3
-
-* **List Marker Protection Enhancement**: Fixed a bug where list markers (`*`) followed by plain text and emphasis were having their spaces incorrectly stripped (e.g., `*   U16 forward` became `*U16 forward`).
-* **Placeholder Support**: Confirmed that 4 or more underscores (e.g., `____`) are correctly treated as placeholders and not modified by the emphasis fix.
-
-### v1.2.2
-
-* **Code Block Indentation Fix**: Fixed an issue where code blocks nested inside lists were having their indentation incorrectly stripped. Now preserves proper indentation for nested code blocks.
-* **Underscore Emphasis Support**: Extended emphasis spacing fix to support `__` (double underscore for bold) and `___` (triple underscore for bold+italic) syntax.
-* **List Marker Protection**: Fixed a bug where list markers (`*`) followed by emphasis markers (`**`) were incorrectly merged (e.g., `*   **Yes**` became `***Yes**`). Added safeguard to prevent this.
-* **Test Suite**: Added comprehensive pytest test suite with 56 test cases covering all major features.
-
-### v1.2.1
-
-* **Emphasis Spacing Fix**: Added a new fix for extra spaces inside emphasis markers (e.g., `** text **` -> `**text**`).
-  * Uses a recursive approach to handle nested emphasis (e.g., `**bold _italic _**`).
-  * Includes safeguards to prevent modifying math expressions (e.g., `2 * 3 * 4`) or list variables.
-  * Controlled by the `enable_emphasis_spacing_fix` valve (default: True).
-
-### v1.2.0
-
-* **Details Tag Support**: Added normalization for `<details>` tags.
-  * Ensures a blank line is added after `</details>` closing tags to separate thought content from the main response.
-  * Ensures a newline is added after self-closing `<details ... />` tags to prevent them from interfering with subsequent Markdown headings (e.g., fixing `<details/>#Heading`).
-  * Includes safeguard to prevent modification of `<details>` tags inside code blocks.
-
-### v1.1.2
-
-* **Mermaid Edge Label Protection**: Implemented comprehensive protection for edge labels (text on connecting lines) to prevent them from being incorrectly modified. Now supports all Mermaid link types including solid (`--`), dotted (`-.`), and thick (`==`) lines with or without arrows.
-* **Bug Fixes**: Fixed an issue where lines without arrows (e.g., `A -- text --- B`) were not correctly protected.
-
-### v1.1.0
-
-* **Mermaid Fix Refinement**: Improved regex to handle nested parentheses in node labels (e.g., `ID("Label (text)")`) and avoided matching connection labels.
-* **HTML Safeguard Optimization**: Refined `_contains_html` to allow common tags like `<br/>`, `<b>`, `<i>`, etc., ensuring Mermaid diagrams with these tags are still normalized.
-* **Full-width Symbol Cleanup**: Fixed duplicate keys and incorrect quote mapping in `FULLWIDTH_MAP`.
-* **Bug Fixes**: Fixed missing `Dict` import in Python files.
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/filters/markdown_normalizer/README_CN.md

@@ -4,7 +4,11 @@
 
 这是一个用于 Open WebUI 的内容格式化过滤器，旨在修复 LLM 输出中常见的 Markdown 格式问题。它能确保代码块、LaTeX 公式、Mermaid 图表和其他 Markdown 元素被正确渲染。
 
-## 功能特性
+## 🔥 最新更新 v1.2.4
+
+* **文档更新**: 同步了所有文档和代码文件的版本号。
+
+## ✨ 核心特性
 
 * **Details 标签规范化**: 确保 `<details>` 标签（常用于思维链）有正确的间距。在 `</details>` 后添加空行，并在自闭合 `<details />` 标签后添加换行，防止渲染问题。
 * **强调空格修复**: 修复强调标记内部的多余空格（例如 `** 文本 **` -> `**文本**`），这会导致 Markdown 渲染失败。包含保护机制，防止误修改数学表达式（如 `2 * 3 * 4`）或列表变量。
@@ -28,69 +32,38 @@
     > [!WARNING]
     > 由于这是初版，可能会出现“负向修复”的情况（例如破坏了原本正确的格式）。如果您遇到问题，请务必查看控制台日志，复制“原始 (Original)”与“规范化 (Normalized)”的内容对比，并提交 Issue 反馈。
 
-## 配置项 (Valves)
+## 配置参数 (Valves) ⚙️
 
-* `priority`: 过滤器优先级 (默认: 50)。
-* `enable_escape_fix`: 修复过度的转义字符。
-* `enable_thought_tag_fix`: 规范化思维标签。
-* `enable_details_tag_fix`: 规范化 Details 标签 (默认: True)。
-* `enable_code_block_fix`: 修复代码块格式。
-* `enable_latex_fix`: 规范化 LaTeX 公式。
-* `enable_list_fix`: 修复列表项换行 (实验性)。
-* `enable_unclosed_block_fix`: 自动闭合未闭合的代码块。
-* `enable_fullwidth_symbol_fix`: 修复代码块中的全角符号。
-* `enable_mermaid_fix`: 修复 Mermaid 语法错误。
-* `enable_heading_fix`: 修复标题中缺失的空格。
-* `enable_table_fix`: 修复表格中缺失的闭合管道符。
-* `enable_xml_tag_cleanup`: 清理残留的 XML 标签。
-* `enable_emphasis_spacing_fix`: 修复强调语法中的多余空格 (默认: True)。
-* `show_status`: 应用修复时显示状态通知。
-* `show_debug_log`: 在浏览器控制台打印调试日志。
+| 参数 | 默认值 | 描述 |
+| :--- | :--- | :--- |
+| `priority` | `50` | 过滤器优先级。数值越大越靠后（建议在其他过滤器之后运行）。 |
+| `enable_escape_fix` | `True` | 修复过度的转义字符（`\n`, `\t` 等）。 |
+| `enable_escape_fix_in_code_blocks` | `False` | 在代码块内应用转义修复（可能影响有效代码）。 |
+| `enable_thought_tag_fix` | `True` | 规范化思维标签（`</thought>`）。 |
+| `enable_details_tag_fix` | `True` | 规范化 `<details>` 标签并添加安全间距。 |
+| `enable_code_block_fix` | `True` | 修复代码块格式（缩进/换行）。 |
+| `enable_latex_fix` | `True` | 规范化 LaTeX 定界符（`\[` -> `$$`, `\(` -> `$`）。 |
+| `enable_list_fix` | `False` | 修复列表项换行（实验性）。 |
+| `enable_unclosed_block_fix` | `True` | 自动闭合未闭合的代码块。 |
+| `enable_fullwidth_symbol_fix` | `False` | 修复代码块中的全角符号。 |
+| `enable_mermaid_fix` | `True` | 修复常见 Mermaid 语法错误。 |
+| `enable_heading_fix` | `True` | 修复标题中缺失的空格。 |
+| `enable_table_fix` | `True` | 修复表格中缺失的闭合管道符。 |
+| `enable_xml_tag_cleanup` | `True` | 清理残留的 XML 标签。 |
+| `enable_emphasis_spacing_fix` | `False` | 修复强调语法中的多余空格。 |
+| `show_status` | `True` | 应用修复时显示状态通知。 |
+| `show_debug_log` | `True` | 在浏览器控制台打印调试日志。 |
 
-## 故障排除 (Troubleshooting) ❓
+## ⭐ 支持
+
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
+
+## 其他
+
+### 故障排除 (Troubleshooting) ❓
 
 * **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
 
-## 更新日志
+### 更新日志
 
-### v1.2.4
-
-* **文档更新**: 同步了所有文档和代码文件的版本号。
-
-### v1.2.3
-
-* **列表标记保护增强**: 修复了列表标记 (`*`) 后跟普通文本和强调标记时，空格被错误剥离的问题（例如 `*   U16 前锋` 变成 `*U16 前锋`）。
-* **占位符支持**: 确认 4 个或更多下划线（如 `____`）会被正确视为占位符，不会被强调修复逻辑修改。
-
-### v1.2.2
-
-* **代码块缩进修复**: 修复了列表中嵌套代码块的缩进被错误剥离的问题。现在会正确保留嵌套代码块的缩进。
-* **下划线强调语法支持**: 扩展强调空格修复以支持 `__` (双下划线加粗) 和 `___` (三下划线加粗斜体) 语法。
-* **列表标记保护**: 修复了列表标记 (`*`) 后跟强调标记 (`**`) 被错误合并的 Bug（例如 `*   **是**` 变成 `***是**`）。添加了保护逻辑防止此问题。
-* **测试套件**: 新增完整的 pytest 测试套件，包含 56 个测试用例，覆盖所有主要功能。
-
-### v1.2.1
-
-* **强调空格修复**: 新增了对强调标记内部多余空格的修复（例如 `** 文本 **` -> `**文本**`）。
-  * 采用递归方法处理嵌套强调（例如 `**加粗 _斜体 _**`）。
-  * 包含保护机制，防止误修改数学表达式（如 `2 * 3 * 4`）或列表变量。
-  * 通过 `enable_emphasis_spacing_fix` 开关控制（默认：开启）。
-
-### v1.2.0
-
-* **Details 标签支持**: 新增了对 `<details>` 标签的规范化支持。
-  * 确保在 `</details>` 闭合标签后添加空行，将思维内容与正文分隔开。
-  * 确保在自闭合 `<details ... />` 标签后添加换行，防止其干扰后续的 Markdown 标题（例如修复 `<details/>#标题`）。
-  * 包含保护机制，防止修改代码块内部的 `<details>` 标签。
-
-### v1.1.2
-
-* **Mermaid 连线标签保护**: 实现了全面的连线标签保护机制，防止连接线上的文字被误修改。现在支持所有 Mermaid 连线类型，包括实线 (`--`)、虚线 (`-.`) 和粗线 (`==`)，无论是否带有箭头。
-* **Bug 修复**: 修复了无箭头连线（如 `A -- text --- B`）未被正确保护的问题。
-
-### v1.1.0
-
-* **Mermaid 修复优化**: 改进了正则表达式以处理节点标签中的嵌套括号（如 `ID("标签 (文本)")`），并避免误匹配连接线上的文字。
-* **HTML 保护机制优化**: 优化了 `_contains_html` 检测，允许 `<br/>`, `<b>`, `<i>` 等常见标签，确保包含这些标签的 Mermaid 图表能被正常规范化。
-* **全角符号清理**: 修复了 `FULLWIDTH_MAP` 中的重复键名和错误的引号映射。
-* **Bug 修复**: 修复了 Python 文件中缺失的 `Dict` 类型导入。
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/pipes/github-copilot-sdk/README.md

@@ -1,30 +1,32 @@
 # GitHub Copilot SDK Pipe for OpenWebUI
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.2.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.3.0 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
 
 This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/open-webui) that allows you to use GitHub Copilot models (such as `gpt-5`, `gpt-5-mini`, `claude-sonnet-4.5`) directly within OpenWebUI. It is built upon the official [GitHub Copilot SDK for Python](https://github.com/github/copilot-sdk), providing a native integration experience.
 
-## 🚀 What's New (v0.2.3)
+> [!IMPORTANT]
+> **Active GitHub Copilot Subscription Required**
+> This plugin requires a valid GitHub Copilot subscription (Individual, Business, or Enterprise). It will verify your subscription status during authentication.
 
-* **🧩 Per-user Overrides**: Added user-level overrides for `REASONING_EFFORT`, `CLI_PATH`, `DEBUG`, `SHOW_THINKING`, and `MODEL_ID`.
-* **🧠 Thinking Output Reliability**: Thinking visibility now respects the user setting and is correctly passed into streaming.
-* **📝 Formatting Enforcement**: Added automatic formatting hints to ensure outputs are well-structured (paragraphs, lists) and addressed "tight output" issues.
+## 🚀 What's New (v0.3.0) - The Power of "Unified Ecosystem"
 
-## ✨ Core Features
+* **🔌 Zero-Config Tool Bridge**: Automatically transforms your existing OpenWebUI Functions (Tools) into Copilot-compatible tools. **Copilot now has total access to your entire WebUI toolset!**
+* **🔗 Dynamic MCP Discovery**: Seamlessly connects to MCP servers defined in **Admin Settings -> Connections**. No configuration files required—it just works.
+* **⚡ High-Performance Async Engine**: Background CLI updates and optimized event-driven streaming ensure lightning-fast responses without UI lag.
+* **🛡️ Robust Interoperability**: Advanced sanitization and dynamic Pydantic model generation ensure smooth integration even with complex third-party tools.
 
-* **🚀 Official SDK Integration**: Built on the official SDK for stability and reliability.
-* **🛠️ Custom Tools Support**: Example tools included (random number). Easy to extend with your own tools.
-* **💬 Multi-turn Conversation**: Automatically concatenates history context so Copilot understands your previous messages.
-* **🌊 Streaming Output**: Supports typewriter effect for fast responses.
-* **🖼️ Multimodal Support**: Supports image uploads, automatically converting them to attachments for Copilot (requires model support).
-* **🛠️ Zero-config Installation**: Automatically detects and downloads the GitHub Copilot CLI, ready to use out of the box.
-* **🔑 Secure Authentication**: Supports Fine-grained Personal Access Tokens for minimized permissions.
-* **🐛 Debug Mode**: Built-in detailed log output (browser console) for easy troubleshooting.
-* **⚠️ Single Node Only**: Due to local session storage, this plugin currently supports single-node OpenWebUI deployment or multi-node with sticky sessions enabled.
+## ✨ Key Capabilities
 
-## 📦 Installation & Usage
+* **🌉 The Ultimate Bridge**: The first and only plugin that creates a seamless bridge between **OpenWebUI Tools** and **GitHub Copilot SDK**.
+* **🚀 Official & Native**: Built directly on the official Python SDK, providing the most stable and authentic Copilot experience.
+* **🌊 Advanced Streaming (Thought Process)**: Supports full model reasoning/thinking display with typewriter effects.
+* **🖼️ Intelligent Multimodal**: Full support for images and attachments, enabling Copilot to "see" your workspace.
+* **🛠️ Effortless Setup**: Automatic CLI detection, version enforcement, and dependency management.
+* **🔑 Dual-Layer Security**: Supports secure OAuth flow for Chat and standard PAT for extended MCP capabilities.
 
-### 1. Import Function
+## Installation & Configuration
+
+### 1) Import Function
 
 1. Open OpenWebUI.
 2. Go to **Workspace** -> **Functions**.
@@ -32,19 +34,17 @@ This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/
 4. Paste the content of `github_copilot_sdk.py` (or `github_copilot_sdk_cn.py` for Chinese) completely.
 5. Save.
 
-### 2. Configure Valves (Settings)
+### 2) Configure Valves (Settings)
 
 Find "GitHub Copilot" in the function list and click the **⚙️ (Valves)** icon to configure:
 
 | Parameter | Description | Default |
 | :--- | :--- | :--- |
-| **GH_TOKEN** | **(Required)** Your GitHub Token. | - |
-| **MODEL_ID** | The model name to use. | `gpt-5-mini` |
-| **CLI_PATH** | Path to the Copilot CLI. Will download automatically if not found. | `/usr/local/bin/copilot` |
+| **GH_TOKEN** | **(Required)** GitHub Access Token (PAT or OAuth Token). Access to Chat. | - |
 | **DEBUG** | Whether to enable debug logs (output to browser console). | `False` |
 | **LOG_LEVEL** | Copilot CLI log level: none, error, warning, info, debug, all. | `error` |
 | **SHOW_THINKING** | Show model reasoning/thinking process (requires streaming + model support). | `True` |
-| **SHOW_WORKSPACE_INFO** | Show session workspace path and summary in debug mode. | `True` |
+| **COPILOT_CLI_VERSION** | Specific Copilot CLI version to install/enforce. | `0.0.405` |
 | **EXCLUDE_KEYWORDS** | Exclude models containing these keywords (comma separated). | - |
 | **WORKSPACE_DIR** | Restricted workspace directory for file operations. | - |
 | **INFINITE_SESSION** | Enable Infinite Sessions (automatic context compaction). | `True` |
@@ -52,10 +52,10 @@ Find "GitHub Copilot" in the function list and click the **⚙️ (Valves)** ico
 | **BUFFER_THRESHOLD** | Buffer exhaustion threshold (0.0-1.0). | `0.95` |
 | **TIMEOUT** | Timeout for each stream chunk (seconds). | `300` |
 | **CUSTOM_ENV_VARS** | Custom environment variables (JSON format). | - |
-| **REASONING_EFFORT** | Reasoning effort level: low, medium, high. `xhigh` is supported for gpt-5.2-codex. | `medium` |
+| **REASONING_EFFORT** | Reasoning effort level: low, medium, high. `xhigh` is supported for some models. | `medium` |
 | **ENFORCE_FORMATTING** | Add formatting instructions to system prompt for better readability. | `True` |
-| **ENABLE_TOOLS** | Enable custom tools (example: random number). | `False` |
-| **AVAILABLE_TOOLS** | Available tools: 'all' or comma-separated list. | `all` |
+| **ENABLE_MCP_SERVER** | Enable Direct MCP Client connection (Recommended). | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | Enable OpenWebUI Tools (includes defined and server tools). | `True` |
 
 #### User Valves (per-user overrides)
 
@@ -63,35 +63,30 @@ These optional settings can be set per user (overrides global Valves):
 
 | Parameter | Description | Default |
 | :--- | :--- | :--- |
+| **GH_TOKEN** | Personal GitHub Token (overrides global setting). | - |
 | **REASONING_EFFORT** | Reasoning effort level (low/medium/high/xhigh). | - |
-| **CLI_PATH** | Custom path to Copilot CLI. | - |
 | **DEBUG** | Enable technical debug logs. | `False` |
-| **SHOW_THINKING** | Show model reasoning/thinking process (requires streaming + model support). | `True` |
-| **MODEL_ID** | Custom model ID. | - |
+| **SHOW_THINKING** | Show model reasoning/thinking process. | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | Enable OpenWebUI Tools (overrides global). | `True` |
+| **ENABLE_MCP_SERVER** | Enable MCP server loading (overrides global). | `True` |
+| **ENFORCE_FORMATTING** | Enforce formatting guidelines (overrides global). | `True` |
 
-### 3. Using Custom Tools (🆕 Optional)
+## ⭐ Support
 
-This pipe includes **1 example tool** to demonstrate tool calling:
+If this plugin has been useful, a star on [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) is a big motivation for me. Thank you for the support.
 
-* **🎲 generate_random_number**: Generate random integers
+### Get Token
 
-**To enable:**
+To use GitHub Copilot, you need a GitHub Personal Access Token (PAT) with appropriate permissions.
 
-1. Set `ENABLE_TOOLS: true` in Valves
-2. Try: "Give me a random number"
-
-**📚 For detailed usage and creating your own tools, see [TOOLS_USAGE.md](TOOLS_USAGE.md)**
-
-### 4. Get GH_TOKEN
-
-For security, it is recommended to use a **Fine-grained Personal Access Token**:
+**Steps to generate your token:**
 
 1. Visit [GitHub Token Settings](https://github.com/settings/tokens?type=beta).
-2. Click **Generate new token**.
-3. **Repository access**: Select **Public repositories** (Required to access Copilot permissions).
+2. Click **Generate new token (fine-grained)**.
+3. **Repository access**: Select **Public Repositories** (simplest) or **All repositories**.
 4. **Permissions**:
-    * Click **Account permissions**.
-    * Find **Copilot Requests** (It defaults to **Read-only**, no selection needed).
+    * If you chose **All repositories**, you must click **Account permissions**.
+    * Find **Copilot Requests**, and select **Access**.
 5. Generate and copy the Token.
 
 ## 📋 Dependencies
@@ -101,14 +96,13 @@ This Pipe will automatically attempt to install the following dependencies:
 * `github-copilot-sdk` (Python package)
 * `github-copilot-cli` (Binary file, installed via official script)
 
-## ⚠️ FAQ
+## Troubleshooting ❓
 
-* **Stuck on "Waiting..."**:
-  * Check if `GH_TOKEN` is correct and has `Copilot Requests` permission.
 * **Images not recognized**:
   * Ensure `MODEL_ID` is a model that supports multimodal input.
 * **Thinking not shown**:
   * Ensure **streaming is enabled** and the selected model supports reasoning output.
-* **CLI Installation Failed**:
-  * Ensure the OpenWebUI container has internet access.
-  * You can manually download the CLI and specify `CLI_PATH` in Valves.
+
+## Changelog
+
+See the full history on GitHub: [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/pipes/github-copilot-sdk/README_CN.md

@@ -1,28 +1,30 @@
 # GitHub Copilot SDK 官方管道
 
-**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.2.3 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.3.0 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
 
 这是一个用于 [OpenWebUI](https://github.com/open-webui/open-webui) 的高级 Pipe 函数，允许你直接在 OpenWebUI 中使用 GitHub Copilot 模型（如 `gpt-5`, `gpt-5-mini`, `claude-sonnet-4.5`）。它基于官方 [GitHub Copilot SDK for Python](https://github.com/github/copilot-sdk) 构建，提供了原生级的集成体验。
 
-## 🚀 最新特性 (v0.2.3)
+> [!IMPORTANT]
+> **需 GitHub Copilot 订阅**
+> 本插件需要有效的 GitHub Copilot 订阅（个人版、商业版或企业版）。插件将在认证阶段验证您的订阅状态。
 
-* **🧩 用户级覆盖**：新增 `REASONING_EFFORT`、`CLI_PATH`、`DEBUG`、`SHOW_THINKING`、`MODEL_ID` 的用户级覆盖。
-* **🧠 思考输出可靠性**：思考显示会遵循用户设置，并正确传递到流式输出中。
-* **📝 格式化输出增强**：自动优化输出格式（短句、段落、列表），并解决了在某些界面下显示过于紧凑的问题。
+## 🚀 最新特性 (v0.3.0) - “统一生态”的力量
 
-## ✨ 核心特性
+* **🔌 零配置工具桥接 (Unified Tool Bridge)**: 自动将您现有的 OpenWebUI Functions (工具) 转换为 Copilot 兼容工具。**Copilot 现在可以无缝调用您手头所有的 WebUI 工具！**
+* **🔗 动态 MCP 自动发现**: 直接联动 OpenWebUI **管理面板 -> 连接**。无需编写任何配置文件，即插即用，瞬间扩展 Copilot 能力边界。
+* **⚡ 高性能异步引擎**: 异步 CLI 更新检查与高度优化的事件驱动流式处理，确保对话毫秒级响应。
+* **🛡️ 卓越的兼容性**: 独创的动态 Pydantic 模型生成技术，确保复杂工具参数在 Copilot 端也能得到精准验证。
 
-* **🚀 官方 SDK 集成**：基于官方 SDK，稳定可靠。
-* **🛠️ 自定义工具支持**：内置示例工具（随机数）。易于扩展自定义工具。
-* **💬 多轮对话支持**：自动拼接历史上下文，Copilot 能理解你的前文。
-* **🌊 流式输出 (Streaming)**：支持打字机效果，响应迅速。
-* **🖼️ 多模态支持**：支持上传图片，自动转换为附件发送给 Copilot（需模型支持）。
-* **🛠️ 零配置安装**：自动检测并下载 GitHub Copilot CLI，开箱即用。
-* **🔑 安全认证**：支持 Fine-grained Personal Access Tokens，权限最小化。
-* **🐛 调试模式**：内置详细的日志输出（浏览器控制台），方便排查问题。
-* **⚠️ 仅支持单节点**：由于会话状态存储在本地，本插件目前仅支持 OpenWebUI 单节点部署，或开启了会话粘性 (Sticky Session) 的多节点集群。
+## ✨ 核心能力
 
-## 📦 安装与使用
+* **🌉 强大的生态桥接**: 首个且唯一完美打通 **OpenWebUI Tools** 与 **GitHub Copilot SDK** 的插件。
+* **🚀 官方原生产体验**: 基于官方 Python SDK 构建，提供最稳定、最纯正的 Copilot 交互体验。
+* **🌊 深度推理展示**: 完整支持模型思考过程 (Thinking Process) 的流式渲染。
+* **🖼️ 智能多模态**: 支持图像识别与附件上传，让 Copilot 拥有视觉能力。
+* **🛠️ 极简部署流程**: 自动检测环境、自动下载 CLI、自动管理依赖，全自动化开箱即用。
+* **🔑 安全认证体系**: 完美支持 OAuth 授权与 PAT 模式，兼顾便捷与安全性。
+
+## 安装与配置
 
 ### 1. 导入函数
 
@@ -38,24 +40,22 @@
 
 | 参数 | 说明 | 默认值 |
 | :--- | :--- | :--- |
-| **GH_TOKEN** | **(必填)** 你的 GitHub Token。 | - |
-| **MODEL_ID** | 使用的模型名称。 | `gpt-5-mini` |
-| **CLI_PATH** | Copilot CLI 的路径。如果未找到会自动下载。 | `/usr/local/bin/copilot` |
+| **GH_TOKEN** | **(必填)** GitHub 访问令牌 (PAT 或 OAuth Token)。用于聊天。 | - |
 | **DEBUG** | 是否开启调试日志（输出到浏览器控制台）。 | `False` |
 | **LOG_LEVEL** | Copilot CLI 日志级别: none, error, warning, info, debug, all。 | `error` |
 | **SHOW_THINKING** | 是否显示模型推理/思考过程（需开启流式 + 模型支持）。 | `True` |
-| **SHOW_WORKSPACE_INFO** | 在调试模式下显示会话工作空间路径和摘要。 | `True` |
-| **EXCLUDE_KEYWORDS** | 排除包含这些关键词的模型 (逗号分隔)。 | - |
-| **WORKSPACE_DIR** | 文件操作的受限工作目录。 | - |
-| **INFINITE_SESSION** | 启用无限会话 (自动上下文压缩)。 | `True` |
+| **COPILOT_CLI_VERSION** | 指定安装/强制使用的 Copilot CLI 版本。 | `0.0.405` |
+| **EXCLUDE_KEYWORDS** | 排除包含这些关键词的模型（逗号分隔）。 | - |
+| **WORKSPACE_DIR** | 文件操作的受限工作区目录。 | - |
+| **INFINITE_SESSION** | 启用无限会话（自动上下文压缩）。 | `True` |
 | **COMPACTION_THRESHOLD** | 后台压缩阈值 (0.0-1.0)。 | `0.8` |
-| **BUFFER_THRESHOLD** | 缓冲耗尽阈值 (0.0-1.0)。 | `0.95` |
-| **TIMEOUT** | 流式数据块超时时间 (秒)。 | `300` |
+| **BUFFER_THRESHOLD** | 缓冲区耗尽阈值 (0.0-1.0)。 | `0.95` |
+| **TIMEOUT** | 每个流式分块超时（秒）。 | `300` |
 | **CUSTOM_ENV_VARS** | 自定义环境变量 (JSON 格式)。 | - |
-| **ENABLE_TOOLS** | 启用自定义工具 (示例：随机数)。 | `False` |
-| **AVAILABLE_TOOLS** | 可用工具: 'all' 或逗号分隔列表。 | `all` |
-| **REASONING_EFFORT** | 推理强度级别：low, medium, high。`gpt-5.2-codex`额外支持`xhigh`。 | `medium` |
-| **ENFORCE_FORMATTING** | 是否强制添加格式化指导，以提高输出可读性。 | `True` |
+| **REASONING_EFFORT** | 推理强度级别: low, medium, high. `xhigh` 仅部分模型支持。 | `medium` |
+| **ENFORCE_FORMATTING** | 在系统提示词中添加格式化指导。 | `True` |
+| **ENABLE_MCP_SERVER** | 启用直接 MCP 客户端连接 (建议)。 | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | 启用 OpenWebUI 工具 (包括自定义和服务器工具)。 | `True` |
 
 #### 用户 Valves（按用户覆盖）
 
@@ -63,36 +63,31 @@
 
 | 参数 | 说明 | 默认值 |
 | :--- | :--- | :--- |
+| **GH_TOKEN** | 个人 GitHub Token（覆盖全局设置）。 | - |
 | **REASONING_EFFORT** | 推理强度级别（low/medium/high/xhigh）。 | - |
-| **CLI_PATH** | 自定义 Copilot CLI 路径。 | - |
 | **DEBUG** | 是否启用技术调试日志。 | `False` |
-| **SHOW_THINKING** | 是否显示思考过程（需开启流式 + 模型支持）。 | `True` |
-| **MODEL_ID** | 自定义模型 ID。 | - |
+| **SHOW_THINKING** | 是否显示思考过程。 | `True` |
+| **ENABLE_OPENWEBUI_TOOLS** | 启用 OpenWebUI 工具（覆盖全局设置）。 | `True` |
+| **ENABLE_MCP_SERVER** | 启用动态 MCP 服务器加载（覆盖全局设置）。 | `True` |
+| **ENFORCE_FORMATTING** | 强制启用格式化指导（覆盖全局设置）。 | `True` |
 
-### 3. 使用自定义工具 (🆕 可选)
+## ⭐ 支持
 
-本 Pipe 内置了 **1 个示例工具**来展示工具调用功能：
+如果这个插件对你有帮助，欢迎到 [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) 点个 Star，这将是我持续改进的动力，感谢支持。
 
-* **🎲 generate_random_number**：生成随机整数
+### 获取 Token
 
-**启用方法：**
+要使用 GitHub Copilot，您需要一个具有适当权限的 GitHub 个人访问令牌 (PAT)。
 
-1. 在 Valves 中设置 `ENABLE_TOOLS: true`
-2. 尝试问：“给我一个随机数”
+**获取步骤：**
 
-**📚 详细使用说明和创建自定义工具，请参阅 [TOOLS_USAGE.md](TOOLS_USAGE.md)**
-
-### 4. 获取 GH_TOKEN
-
-为了安全起见，推荐使用 **Fine-grained Personal Access Token**：
-
-1. 访问 [GitHub Token Settings](https://github.com/settings/tokens?type=beta)。
-2. 点击 **Generate new token**。
-3. **Repository access**: 选择 **Public repositories** (必须选择此项才能看到 Copilot 权限)。
+1. 访问 [GitHub 令牌设置](https://github.com/settings/tokens?type=beta)。
+2. 点击 **Generate new token (fine-grained)**。
+3. **Repository access**: 选择 **Public Repositories** (最简单) 或 **All repositories**。
 4. **Permissions**:
-    * 点击 **Account permissions**。
-    * 找到 **Copilot Requests** (默认即为 **Read-only**，无需手动修改)。
-5. 生成并复制 Token。
+    * 如果您选择了 **All repositories**，则必须点击 **Account permissions**。
+    * 找到 **Copilot Requests**，选择 **Access**。
+5. 生成并复制令牌。
 
 ## 📋 依赖说明
 
@@ -101,14 +96,13 @@
 * `github-copilot-sdk` (Python 包)
 * `github-copilot-cli` (二进制文件，通过官方脚本安装)
 
-## ⚠️ 常见问题
+## 故障排除 (Troubleshooting) ❓
 
-* **一直显示 "Waiting..."**：
-  * 检查 `GH_TOKEN` 是否正确且拥有 `Copilot Requests` 权限。
-* **图片无法识别**：
+* **图片及多模态使用说明**：
   * 确保 `MODEL_ID` 是支持多模态的模型。
-* **CLI 安装失败**：
-  * 确保 OpenWebUI 容器有外网访问权限。
-  * 你可以手动下载 CLI 并挂载到容器中，然后在 Valves 中指定 `CLI_PATH`。
 * **看不到思考过程**：
   * 确认已开启**流式输出**，且所选模型支持推理输出。
+
+## 更新日志
+
+完整历史请查看 GitHub 项目： [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)

plugins/pipes/github-copilot-sdk/TOOLS_USAGE.md

@@ -0,0 +1,187 @@
+# 🛠️ Custom Tools Usage / 自定义工具使用指南
+
+## Overview / 概览
+
+This pipe supports **OpenWebUI Native Tools** (Functions) and **Custom Python Tools**.
+本 Pipe 支持 **OpenWebUI 原生工具** (Functions) 和 **自定义 Python 工具**。
+
+---
+
+## 🚀 OpenWebUI Native Tools / OpenWebUI 原生工具 (v0.3.0)
+
+**New in v0.3.0**: You can use any tool defined in OpenWebUI directly with Copilot.
+**v0.3.0 新增**: 您可以直接在 Copilot 中使用 OpenWebUI 中定义的任何工具。
+
+**How to use / 如何使用:**
+
+1. Go to **Workspace** -> **Tools**.
+2. Create a tool (e.g. `get_weather`).
+3. In Copilot Chat settings (Valves), ensure `ENABLE_OPENWEBUI_TOOLS` is `True` (default).
+4. Ask Copilot: "Search for the latest news" or "Check weather".
+
+**Note / 注意:**
+
+- Tool names are automatically sanitized to match Copilot SDK requirements (e.g. `my.tool` -> `my_tool`).
+- 工具名称会自动净化以符合 Copilot SDK 要求（例如 `my.tool` 变为 `my_tool`）。
+
+---
+
+## 📦 Python Custom Tools / Python 自定义工具
+
+This pipe includes **1 example custom tool** that demonstrates how to use GitHub Copilot SDK's tool calling feature directly in Python code.
+本 Pipe 包含 **1 个示例自定义工具**，展示如何使用 GitHub Copilot SDK 的工具调用功能。
+
+### 1. `generate_random_number` / 生成随机数
+
+**Description:** Generate a random integer
+**描述：** 生成随机整数
+
+**Parameters / 参数:**
+
+- `min` (optional): Minimum value (default: 1)
+- `max` (optional): Maximum value (default: 100)
+- `min` (可选): 最小值 (默认: 1)
+- `max` (可选): 最大值 (默认: 100)
+
+**Example / 示例:**
+
+```
+User: "Give me a random number between 1 and 10"
+Copilot: [calls generate_random_number with min=1, max=10] "Generated random number: 7"
+
+用户: "给我一个 1 到 10 之间的随机数"
+Copilot: [调用 generate_random_number，参数 min=1, max=10] "生成的随机数: 7"
+```
+
+---
+
+## ⚙️ Configuration / 配置
+
+### Enable Tools / 启用工具
+
+In Valves configuration:
+在 Valves 配置中：
+
+```
+ENABLE_TOOLS: true
+AVAILABLE_TOOLS: all
+```
+
+### Select Specific Tools / 选择特定工具
+
+Instead of enabling all tools, specify which ones to use:
+不启用所有工具，而是指定要使用的工具：
+
+```
+ENABLE_TOOLS: true
+AVAILABLE_TOOLS: generate_random_number
+```
+
+---
+
+## 🔧 How Tool Calling Works / 工具调用的工作原理
+
+```
+1. User asks a question / 用户提问
+        ↓
+2. Copilot decides if it needs a tool / Copilot 决定是否需要工具
+        ↓
+3. If yes, Copilot calls the appropriate tool / 如果需要，调用相应工具
+        ↓
+4. Tool executes and returns result / 工具执行并返回结果
+        ↓
+5. Copilot uses the result to answer / Copilot 使用结果回答
+```
+
+### Visual Feedback / 可视化反馈
+
+When tools are called, you'll see:
+当工具被调用时，你会看到：
+
+```
+🔧 **Calling tool**: `generate_random_number`
+✅ **Tool `generate_random_number` completed**
+
+Generated random number: 7
+```
+
+---
+
+## 📚 Creating Your Own Tools / 创建自定义工具
+
+Want to add your own Python tools? Follow this pattern (module-level tools):
+想要添加自己的 Python 工具？遵循这个模式（模块级工具）：
+
+```python
+from pydantic import BaseModel, Field
+from copilot import define_tool
+
+class MyToolParams(BaseModel):
+    param_name: str = Field(description="Parameter description")
+
+
+@define_tool(description="Clear description of what the tool does and when to use it")
+async def my_tool(params: MyToolParams) -> str:
+    # Do something
+    result = do_something(params.param_name)
+    return f"Result: {result}"
+```
+
+Then register it in `_initialize_custom_tools()`:
+然后将它添加到 `_initialize_custom_tools()`:
+
+```python
+def _initialize_custom_tools(self):
+    if not self.valves.ENABLE_TOOLS:
+        return []
+
+    all_tools = {
+        "generate_random_number": generate_random_number,
+        "my_tool": my_tool,  # ✅ Add here
+    }
+
+    if self.valves.AVAILABLE_TOOLS == "all":
+        return list(all_tools.values())
+
+    enabled = [t.strip() for t in self.valves.AVAILABLE_TOOLS.split(",")]
+    return [all_tools[name] for name in enabled if name in all_tools]
+```
+
+---
+
+## ⚠️ Important Notes / 重要说明
+
+### Security / 安全性
+
+- Tools run in the same process as the pipe
+- Be careful with tools that execute code or access files
+- Always validate input parameters
+
+- 工具在与 Pipe 相同的进程中运行
+- 谨慎处理执行代码或访问文件的工具
+- 始终验证输入参数
+
+### Performance / 性能
+
+- Tool execution is synchronous during streaming
+- Long-running tools may cause delays
+- Consider adding timeouts for external API calls
+
+- 工具执行在流式传输期间是同步的
+- 长时间运行的工具可能导致延迟
+- 考虑为外部 API 调用添加超时
+
+### Debugging / 调试
+
+- Enable `DEBUG: true` to see tool events in the browser console
+- Check tool calls in `🔧 Calling tool` messages
+- Tool errors are displayed in the response
+
+- 启用 `DEBUG: true` 在浏览器控制台查看工具事件
+- 在 `🔧 Calling tool` 消息中检查工具调用
+- 工具错误会显示在响应中
+
+---
+
+**Version:** 0.3.0
+**Last Updated:** 2026-02-05

plugins/pipes/github-copilot-sdk/github_copilot_sdk.py

@@ -5,11 +5,12 @@ author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui
 openwebui_id: ce96f7b4-12fc-4ac3-9a01-875713e69359
 description: Integrate GitHub Copilot SDK. Supports dynamic models, multi-turn conversation, streaming, multimodal input, infinite sessions, and frontend debug logging.
-version: 0.2.3
-requirements: github-copilot-sdk
+version: 0.3.0
+requirements: github-copilot-sdk==0.1.22
 """
 
 import os
+import re
 import json
 import base64
 import tempfile
@@ -17,44 +18,34 @@ import asyncio
 import logging
 import shutil
 import subprocess
+import hashlib
+from pathlib import Path
 from typing import Optional, Union, AsyncGenerator, List, Any, Dict
-from pydantic import BaseModel, Field
+from types import SimpleNamespace
+from pydantic import BaseModel, Field, create_model
 
 # Import copilot SDK modules
 from copilot import CopilotClient, define_tool
 
+# Import Tool Server Connections and Tool System from OpenWebUI Config
+from open_webui.config import TOOL_SERVER_CONNECTIONS
+from open_webui.utils.tools import get_tools as get_openwebui_tools
+from open_webui.models.tools import Tools
+from open_webui.models.users import Users
+
 # Setup logger
 logger = logging.getLogger(__name__)
 
 
-class RandomNumberParams(BaseModel):
-    min: int = Field(description="Minimum value (inclusive)")
-    max: int = Field(description="Maximum value (inclusive)")
-
-
-@define_tool(description="Generate a random integer within a specified range.")
-async def generate_random_number(params: RandomNumberParams) -> str:
-    import random
-
-    if params.min >= params.max:
-        raise ValueError("min must be less than max")
-    number = random.randint(params.min, params.max)
-    return f"Generated random number: {number}"
-
-
 class Pipe:
     class Valves(BaseModel):
         GH_TOKEN: str = Field(
             default="",
             description="GitHub Fine-grained Token (Requires 'Copilot Requests' permission)",
         )
-        MODEL_ID: str = Field(
-            default="gpt-5-mini",
-            description="Default Copilot model name (used when dynamic fetching fails)",
-        )
-        CLI_PATH: str = Field(
-            default="/usr/local/bin/copilot",
-            description="Path to Copilot CLI",
+        COPILOT_CLI_VERSION: str = Field(
+            default="0.0.405",
+            description="Specific Copilot CLI version to install/enforce (e.g. '0.0.405'). Leave empty for latest.",
         )
         DEBUG: bool = Field(
             default=False,
@@ -68,10 +59,6 @@ class Pipe:
             default=True,
             description="Show model reasoning/thinking process",
         )
-        SHOW_WORKSPACE_INFO: bool = Field(
-            default=True,
-            description="Show session workspace path and summary in debug mode",
-        )
         EXCLUDE_KEYWORDS: str = Field(
             default="",
             description="Exclude models containing these keywords (comma separated, e.g.: codex, haiku)",
@@ -100,13 +87,14 @@ class Pipe:
             default="",
             description='Custom environment variables (JSON format, e.g., {"VAR": "value"})',
         )
-        ENABLE_TOOLS: bool = Field(
-            default=False,
-            description="Enable custom tools (example: random number)",
+
+        ENABLE_OPENWEBUI_TOOLS: bool = Field(
+            default=True,
+            description="Enable OpenWebUI Tools (includes defined Tools and Tool Server Tools).",
         )
-        AVAILABLE_TOOLS: str = Field(
-            default="all",
-            description="Available tools: 'all' or comma-separated list (e.g., 'generate_random_number')",
+        ENABLE_MCP_SERVER: bool = Field(
+            default=True,
+            description="Enable Direct MCP Client connection (Recommended).",
         )
         REASONING_EFFORT: str = Field(
             default="medium",
@@ -118,14 +106,14 @@ class Pipe:
         )
 
     class UserValves(BaseModel):
+        GH_TOKEN: str = Field(
+            default="",
+            description="Personal GitHub Fine-grained Token (overrides global setting)",
+        )
         REASONING_EFFORT: str = Field(
             default="",
             description="Reasoning effort level (low, medium, high, xhigh). Leave empty to use global setting.",
         )
-        CLI_PATH: str = Field(
-            default="",
-            description="Custom path to Copilot CLI. Leave empty to use global setting.",
-        )
         DEBUG: bool = Field(
             default=False,
             description="Enable technical debug logs (connection info, etc.)",
@@ -134,9 +122,18 @@ class Pipe:
             default=True,
             description="Show model reasoning/thinking process",
         )
-        MODEL_ID: str = Field(
-            default="",
-            description="Custom model ID (e.g. gpt-4o). Leave empty to use global default.",
+        ENABLE_OPENWEBUI_TOOLS: bool = Field(
+            default=True,
+            description="Enable OpenWebUI Tools (includes defined Tools and Tool Server Tools).",
+        )
+        ENABLE_MCP_SERVER: bool = Field(
+            default=True,
+            description="Enable dynamic MCP server loading (overrides global).",
+        )
+
+        ENFORCE_FORMATTING: bool = Field(
+            default=True,
+            description="Enforce formatting guidelines (overrides global)",
         )
 
     def __init__(self):
@@ -147,6 +144,7 @@ class Pipe:
         self.temp_dir = tempfile.mkdtemp(prefix="copilot_images_")
         self.thinking_started = False
         self._model_cache = []  # Model list cache
+        self._last_update_check = 0  # Timestamp of last CLI update check
 
     def __del__(self):
         try:
@@ -183,23 +181,269 @@ class Pipe:
     # ==================== Custom Tool Examples ====================
     # Tool registration: Add @define_tool decorated functions at module level,
     # then register them in _initialize_custom_tools() -> all_tools dict.
-    def _initialize_custom_tools(self):
+    async def _initialize_custom_tools(self, __user__=None, __event_call__=None):
         """Initialize custom tools based on configuration"""
-        if not self.valves.ENABLE_TOOLS:
+        if not self.valves.ENABLE_OPENWEBUI_TOOLS:
             return []
 
-        # Define all available tools (register new tools here)
-        all_tools = {
-            "generate_random_number": generate_random_number,
+        # Load OpenWebUI tools dynamically
+        openwebui_tools = await self._load_openwebui_tools(
+            __user__=__user__, __event_call__=__event_call__
+        )
+
+        return openwebui_tools
+
+    def _json_schema_to_python_type(self, schema: dict) -> Any:
+        """Convert JSON Schema type to Python type for Pydantic models."""
+        if not isinstance(schema, dict):
+            return Any
+
+        schema_type = schema.get("type")
+        if isinstance(schema_type, list):
+            schema_type = next((t for t in schema_type if t != "null"), schema_type[0])
+
+        if schema_type == "string":
+            return str
+        if schema_type == "integer":
+            return int
+        if schema_type == "number":
+            return float
+        if schema_type == "boolean":
+            return bool
+        if schema_type == "object":
+            return Dict[str, Any]
+        if schema_type == "array":
+            items_schema = schema.get("items", {})
+            item_type = self._json_schema_to_python_type(items_schema)
+            return List[item_type]
+
+        return Any
+
+    def _convert_openwebui_tool(self, tool_name: str, tool_dict: dict):
+        """Convert OpenWebUI tool definition to Copilot SDK tool."""
+        # Sanitize tool name to match pattern ^[a-zA-Z0-9_-]+$
+        sanitized_tool_name = re.sub(r"[^a-zA-Z0-9_-]", "_", tool_name)
+
+        # If sanitized name is empty or consists only of separators (e.g. pure Chinese name), generate a fallback name
+        if not sanitized_tool_name or re.match(r"^[_.-]+$", sanitized_tool_name):
+            hash_suffix = hashlib.md5(tool_name.encode("utf-8")).hexdigest()[:8]
+            sanitized_tool_name = f"tool_{hash_suffix}"
+
+        if sanitized_tool_name != tool_name:
+            logger.debug(
+                f"Sanitized tool name '{tool_name}' to '{sanitized_tool_name}'"
+            )
+
+        spec = tool_dict.get("spec", {}) if isinstance(tool_dict, dict) else {}
+        params_schema = spec.get("parameters", {}) if isinstance(spec, dict) else {}
+        properties = params_schema.get("properties", {})
+        required = params_schema.get("required", [])
+
+        if not isinstance(properties, dict):
+            properties = {}
+        if not isinstance(required, list):
+            required = []
+
+        required_set = set(required)
+        fields = {}
+        for param_name, param_schema in properties.items():
+            param_type = self._json_schema_to_python_type(param_schema)
+            description = ""
+            if isinstance(param_schema, dict):
+                description = param_schema.get("description", "")
+
+            if param_name in required_set:
+                if description:
+                    fields[param_name] = (
+                        param_type,
+                        Field(..., description=description),
+                    )
+                else:
+                    fields[param_name] = (param_type, ...)
+            else:
+                optional_type = Optional[param_type]
+                if description:
+                    fields[param_name] = (
+                        optional_type,
+                        Field(default=None, description=description),
+                    )
+                else:
+                    fields[param_name] = (optional_type, None)
+
+        if fields:
+            ParamsModel = create_model(f"{sanitized_tool_name}_Params", **fields)
+        else:
+            ParamsModel = create_model(f"{sanitized_tool_name}_Params")
+
+        tool_callable = tool_dict.get("callable")
+        tool_description = spec.get("description", "") if isinstance(spec, dict) else ""
+        if not tool_description and isinstance(spec, dict):
+            tool_description = spec.get("summary", "")
+
+        # Critical: If the tool name was sanitized (e.g. Chinese -> Hash), instructions are lost.
+        # We must inject the original name into the description so the model knows what it is.
+        if sanitized_tool_name != tool_name:
+            tool_description = f"Function '{tool_name}': {tool_description}"
+
+        async def _tool(params):
+            payload = params.model_dump() if hasattr(params, "model_dump") else {}
+            return await tool_callable(**payload)
+
+        _tool.__name__ = sanitized_tool_name
+        _tool.__doc__ = tool_description
+
+        # Debug log for tool conversion
+        logger.debug(
+            f"Converting tool '{sanitized_tool_name}': {tool_description[:50]}..."
+        )
+
+        # Core Fix: Explicitly pass params_type and name
+        return define_tool(
+            name=sanitized_tool_name,
+            description=tool_description,
+            params_type=ParamsModel,
+        )(_tool)
+
+    def _build_openwebui_request(self):
+        """Build a minimal request-like object for OpenWebUI tool loading."""
+        app_state = SimpleNamespace(
+            config=SimpleNamespace(
+                TOOL_SERVER_CONNECTIONS=TOOL_SERVER_CONNECTIONS.value
+            ),
+            TOOLS={},
+        )
+        app = SimpleNamespace(state=app_state)
+        request = SimpleNamespace(
+            app=app,
+            cookies={},
+            state=SimpleNamespace(token=SimpleNamespace(credentials="")),
+        )
+        return request
+
+    async def _load_openwebui_tools(self, __user__=None, __event_call__=None):
+        """Load OpenWebUI tools and convert them to Copilot SDK tools."""
+        if isinstance(__user__, (list, tuple)):
+            user_data = __user__[0] if __user__ else {}
+        elif isinstance(__user__, dict):
+            user_data = __user__
+        else:
+            user_data = {}
+
+        if not user_data:
+            return []
+
+        user_id = user_data.get("id") or user_data.get("user_id")
+        if not user_id:
+            return []
+
+        user = Users.get_user_by_id(user_id)
+        if not user:
+            return []
+
+        # 1. Get User defined tools (Python scripts)
+        tool_items = Tools.get_tools_by_user_id(user_id, permission="read")
+        tool_ids = [tool.id for tool in tool_items] if tool_items else []
+
+        # 2. Get OpenAPI Tool Server tools
+        # We manually add enabled OpenAPI servers to the list because Tools.get_tools_by_user_id only checks the DB.
+        # open_webui.utils.tools.get_tools handles the actual loading and access control.
+        if hasattr(TOOL_SERVER_CONNECTIONS, "value"):
+            for server in TOOL_SERVER_CONNECTIONS.value:
+                # We only add 'openapi' servers here because get_tools currently only supports 'openapi' (or defaults to it).
+                # MCP tools are handled separately via ENABLE_MCP_SERVER.
+                if server.get("type") == "openapi":
+                    # Format expected by get_tools: "server:<id>" implies types="openapi"
+                    server_id = server.get("id")
+                    if server_id:
+                        tool_ids.append(f"server:{server_id}")
+
+        if not tool_ids:
+            return []
+
+        request = self._build_openwebui_request()
+        extra_params = {
+            "__request__": request,
+            "__user__": user_data,
+            "__event_emitter__": None,
+            "__event_call__": __event_call__,
+            "__chat_id__": None,
+            "__message_id__": None,
+            "__model_knowledge__": [],
         }
 
-        # Filter based on configuration
-        if self.valves.AVAILABLE_TOOLS == "all":
-            return list(all_tools.values())
+        tools_dict = await get_openwebui_tools(request, tool_ids, user, extra_params)
+        if not tools_dict:
+            return []
 
-        # Only enable specified tools
-        enabled = [t.strip() for t in self.valves.AVAILABLE_TOOLS.split(",")]
-        return [all_tools[name] for name in enabled if name in all_tools]
+        converted_tools = []
+        for tool_name, tool_def in tools_dict.items():
+            try:
+                converted_tools.append(
+                    self._convert_openwebui_tool(tool_name, tool_def)
+                )
+            except Exception as e:
+                await self._emit_debug_log(
+                    f"Failed to load OpenWebUI tool '{tool_name}': {e}",
+                    __event_call__,
+                )
+
+        return converted_tools
+
+    def _parse_mcp_servers(self) -> Optional[dict]:
+        """
+        Dynamically load MCP servers from OpenWebUI TOOL_SERVER_CONNECTIONS.
+        Returns a dict of mcp_servers compatible with CopilotClient.
+        """
+        if not self.valves.ENABLE_MCP_SERVER:
+            return None
+
+        mcp_servers = {}
+
+        # Iterate over OpenWebUI Tool Server Connections
+        if hasattr(TOOL_SERVER_CONNECTIONS, "value"):
+            connections = TOOL_SERVER_CONNECTIONS.value
+        else:
+            connections = []
+
+        for conn in connections:
+            if conn.get("type") == "mcp":
+                info = conn.get("info", {})
+                # Use ID from info or generate one
+                raw_id = info.get("id", f"mcp-server-{len(mcp_servers)}")
+
+                # Sanitize server_id (using same logic as tools)
+                server_id = re.sub(r"[^a-zA-Z0-9_-]", "_", raw_id)
+                if not server_id or re.match(r"^[_.-]+$", server_id):
+                    hash_suffix = hashlib.md5(raw_id.encode("utf-8")).hexdigest()[:8]
+                    server_id = f"server_{hash_suffix}"
+
+                url = conn.get("url")
+                if not url:
+                    continue
+
+                # Build Headers (Handle Auth)
+                headers = {}
+                auth_type = conn.get("auth_type", "bearer")
+                key = conn.get("key", "")
+
+                if auth_type == "bearer" and key:
+                    headers["Authorization"] = f"Bearer {key}"
+                elif auth_type == "basic" and key:
+                    headers["Authorization"] = f"Basic {key}"
+
+                # Merge custom headers if any
+                custom_headers = conn.get("headers", {})
+                if isinstance(custom_headers, dict):
+                    headers.update(custom_headers)
+
+                mcp_servers[server_id] = {
+                    "type": "http",
+                    "url": url,
+                    "headers": headers,
+                    "tools": ["*"],  # Enable all tools by default
+                }
+
+        return mcp_servers if mcp_servers else None
 
     async def _emit_debug_log(self, message: str, __event_call__=None):
         """Emit debug log to frontend (console) when DEBUG is enabled."""
@@ -390,9 +634,31 @@ class Pipe:
 
         return system_prompt_content, system_prompt_source
 
+    def _get_workspace_dir(self) -> str:
+        """Get the effective workspace directory with smart defaults."""
+        if self.valves.WORKSPACE_DIR:
+            return self.valves.WORKSPACE_DIR
+
+        # Smart default for OpenWebUI container
+        if os.path.exists("/app/backend/data"):
+            cwd = "/app/backend/data/copilot_workspace"
+        else:
+            # Local fallback: subdirectory in current working directory
+            cwd = os.path.join(os.getcwd(), "copilot_workspace")
+
+        # Ensure directory exists
+        if not os.path.exists(cwd):
+            try:
+                os.makedirs(cwd, exist_ok=True)
+            except Exception as e:
+                print(f"Error creating workspace {cwd}: {e}")
+                return os.getcwd()  # Fallback to CWD if creation fails
+
+        return cwd
+
     def _build_client_config(self, body: dict) -> dict:
         """Build CopilotClient config from valves and request body."""
-        cwd = self.valves.WORKSPACE_DIR if self.valves.WORKSPACE_DIR else os.getcwd()
+        cwd = self._get_workspace_dir()
         client_config = {}
         if os.environ.get("COPILOT_CLI_PATH"):
             client_config["cli_path"] = os.environ["COPILOT_CLI_PATH"]
@@ -418,7 +684,6 @@ class Pipe:
         custom_tools: List[Any],
         system_prompt_content: Optional[str],
         is_streaming: bool,
-        reasoning_effort: str = "",
     ):
         """Build SessionConfig for Copilot SDK."""
         from copilot.types import SessionConfig, InfiniteSessionConfig
@@ -470,9 +735,9 @@ class Pipe:
             "infinite_sessions": infinite_session_config,
         }
 
-        # Add reasoning_effort if not default (medium)
-        if reasoning_effort and reasoning_effort.lower() != "medium":
-            session_params["reasoning_effort"] = reasoning_effort.lower()
+        mcp_servers = self._parse_mcp_servers()
+        if mcp_servers:
+            session_params["mcp_servers"] = mcp_servers
 
         return SessionConfig(**session_params)
 
@@ -628,8 +893,8 @@ class Pipe:
                 # Return default model on failure
                 return [
                     {
-                        "id": f"{self.id}-{self.valves.MODEL_ID}",
-                        "name": f"GitHub Copilot ({self.valves.MODEL_ID})",
+                        "id": f"{self.id}-gpt-5-mini",
+                        "name": f"GitHub Copilot (gpt-5-mini)",
                     }
                 ]
             finally:
@@ -638,8 +903,8 @@ class Pipe:
             await self._emit_debug_log(f"Pipes Error: {e}")
             return [
                 {
-                    "id": f"{self.id}-{self.valves.MODEL_ID}",
-                    "name": f"GitHub Copilot ({self.valves.MODEL_ID})",
+                    "id": f"{self.id}-gpt-5-mini",
+                    "name": f"GitHub Copilot (gpt-5-mini)",
                 }
             ]
 
@@ -654,30 +919,93 @@ class Pipe:
         return client
 
     def _setup_env(self, __event_call__=None):
-        cli_path = self.valves.CLI_PATH
-        found = False
+        # Default CLI path logic
+        cli_path = "/usr/local/bin/copilot"
+        if os.environ.get("COPILOT_CLI_PATH"):
+            cli_path = os.environ["COPILOT_CLI_PATH"]
 
+        target_version = self.valves.COPILOT_CLI_VERSION.strip()
+        found = False
+        current_version = None
+
+        # internal helper to get version
+        def get_cli_version(path):
+            try:
+                output = (
+                    subprocess.check_output(
+                        [path, "--version"], stderr=subprocess.STDOUT
+                    )
+                    .decode()
+                    .strip()
+                )
+                # Copilot CLI version output format is usually just the version number or "copilot version X.Y.Z"
+                # We try to extract X.Y.Z
+                match = re.search(r"(\d+\.\d+\.\d+)", output)
+                return match.group(1) if match else output
+            except Exception:
+                return None
+
+        # Check default path
         if os.path.exists(cli_path):
             found = True
+            current_version = get_cli_version(cli_path)
 
+        # Check system path if not found
         if not found:
             sys_path = shutil.which("copilot")
             if sys_path:
                 cli_path = sys_path
                 found = True
+                current_version = get_cli_version(cli_path)
+
+        # Determine if we need to install or update
+        should_install = False
+        install_reason = ""
 
         if not found:
+            should_install = True
+            install_reason = "CLI not found"
+        elif target_version:
+            # Normalize versions for comparison (remove 'v' prefix)
+            norm_target = target_version.lstrip("v")
+            norm_current = current_version.lstrip("v") if current_version else ""
+
+            if norm_target != norm_current:
+                should_install = True
+                install_reason = f"Version mismatch (Current: {current_version}, Target: {target_version})"
+
+        if should_install:
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    f"Installing Copilot CLI: {install_reason}...", __event_call__
+                )
             try:
+                env = os.environ.copy()
+                if target_version:
+                    env["VERSION"] = target_version
+
                 subprocess.run(
                     "curl -fsSL https://gh.io/copilot-install | bash",
                     shell=True,
                     check=True,
+                    env=env,
                 )
-                if os.path.exists(self.valves.CLI_PATH):
-                    cli_path = self.valves.CLI_PATH
+
+                # Check default install location first, then system path
+                if os.path.exists("/usr/local/bin/copilot"):
+                    cli_path = "/usr/local/bin/copilot"
                     found = True
-            except:
-                pass
+                elif shutil.which("copilot"):
+                    cli_path = shutil.which("copilot")
+                    found = True
+
+                if found:
+                    current_version = get_cli_version(cli_path)
+            except Exception as e:
+                if self.valves.DEBUG:
+                    self._emit_debug_log_sync(
+                        f"Failed to install Copilot CLI: {e}", __event_call__
+                    )
 
         if found:
             os.environ["COPILOT_CLI_PATH"] = cli_path
@@ -687,25 +1015,9 @@ class Pipe:
 
             if self.valves.DEBUG:
                 self._emit_debug_log_sync(
-                    f"Copilot CLI found at: {cli_path}", __event_call__
+                    f"Copilot CLI found at: {cli_path} (Version: {current_version})",
+                    __event_call__,
                 )
-                try:
-                    # Try to get version to confirm it's executable
-                    ver = (
-                        subprocess.check_output(
-                            [cli_path, "--version"], stderr=subprocess.STDOUT
-                        )
-                        .decode()
-                        .strip()
-                    )
-                    self._emit_debug_log_sync(
-                        f"Copilot CLI Version: {ver}", __event_call__
-                    )
-                except Exception as e:
-                    self._emit_debug_log_sync(
-                        f"Warning: Copilot CLI found but failed to run: {e}",
-                        __event_call__,
-                    )
         else:
             if self.valves.DEBUG:
                 self._emit_debug_log_sync(
@@ -722,6 +1034,8 @@ class Pipe:
                     "Warning: GH_TOKEN is not set.", __event_call__
                 )
 
+        self._sync_mcp_config(__event_call__)
+
     def _process_images(self, messages, __event_call__=None):
         attachments = []
         text_content = ""
@@ -779,8 +1093,8 @@ class Pipe:
                 "gpt-5.2-codex"
                 not in self._collect_model_ids(
                     body={},
-                    request_model=self.valves.MODEL_ID,
-                    real_model_id=self.valves.MODEL_ID,
+                    request_model=self.id,
+                    real_model_id=None,
                 )[0].lower()
             ):
                 # Fallback to high if not supported
@@ -823,6 +1137,53 @@ class Pipe:
         except Exception as e:
             self._emit_debug_log_sync(f"Config sync check failed: {e}", __event_call__)
 
+    async def _update_copilot_cli(self, cli_path: str, __event_call__=None):
+        """Async task to update Copilot CLI if needed."""
+        import time
+
+        try:
+            # Check frequency (e.g., once every hour)
+            now = time.time()
+            if now - self._last_update_check < 3600:
+                return
+
+            self._last_update_check = now
+
+            # Simple check if "update" command is available or if we should just run it
+            # The user requested "async attempt to update copilot cli"
+
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    "Triggering async Copilot CLI update check...", __event_call__
+                )
+
+            # We create a subprocess to run the update
+            process = await asyncio.create_subprocess_exec(
+                cli_path,
+                "update",
+                stdout=asyncio.subprocess.PIPE,
+                stderr=asyncio.subprocess.PIPE,
+            )
+
+            stdout, stderr = await process.communicate()
+
+            if self.valves.DEBUG:
+                output = stdout.decode().strip() or stderr.decode().strip()
+                if output:
+                    self._emit_debug_log_sync(
+                        f"Async CLI Update result: {output}", __event_call__
+                    )
+
+        except Exception as e:
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    f"Async CLI Update failed: {e}", __event_call__
+                )
+
+    def _sync_mcp_config(self, __event_call__=None):
+        """Deprecated: MCP config is now handled dynamically via session config."""
+        pass
+
     # ==================== Internal Implementation ====================
     # _pipe_impl() contains the main request handling logic.
     # ================================================================
@@ -835,12 +1196,22 @@ class Pipe:
         __event_call__=None,
     ) -> Union[str, AsyncGenerator]:
         self._setup_env(__event_call__)
+
+        cwd = self._get_workspace_dir()
+        if self.valves.DEBUG:
+            await self._emit_debug_log(f"Agent working in: {cwd}", __event_call__)
+
         if not self.valves.GH_TOKEN:
             return "Error: Please configure GH_TOKEN in Valves."
 
+        # Trigger async CLI update if configured
+        cli_path = os.environ.get("COPILOT_CLI_PATH")
+        if cli_path:
+            asyncio.create_task(self._update_copilot_cli(cli_path, __event_call__))
+
         # Parse user selected model
         request_model = body.get("model", "")
-        real_model_id = self.valves.MODEL_ID  # Default value
+        real_model_id = request_model
 
         # Determine effective reasoning effort and debug setting
         if __user__:
@@ -877,6 +1248,14 @@ class Pipe:
             await self._emit_debug_log(
                 f"Using selected model: {real_model_id}", __event_call__
             )
+        elif __metadata__ and __metadata__.get("base_model_id"):
+            base_model_id = __metadata__.get("base_model_id", "")
+            if base_model_id.startswith(f"{self.id}-"):
+                real_model_id = base_model_id[len(f"{self.id}-") :]
+                await self._emit_debug_log(
+                    f"Using base model: {real_model_id} (derived from custom model {request_model})",
+                    __event_call__,
+                )
 
         messages = body.get("messages", [])
         if not messages:
@@ -918,26 +1297,58 @@ class Pipe:
             await client.start()
 
             # Initialize custom tools
-            custom_tools = self._initialize_custom_tools()
+            custom_tools = await self._initialize_custom_tools(
+                __user__=__user__, __event_call__=__event_call__
+            )
             if custom_tools:
                 tool_names = [t.name for t in custom_tools]
                 await self._emit_debug_log(
                     f"Enabled {len(custom_tools)} custom tools: {tool_names}",
                     __event_call__,
                 )
+                if self.valves.DEBUG:
+                    for t in custom_tools:
+                        await self._emit_debug_log(
+                            f"📋 Tool Detail: {t.name} - {t.description[:100]}...",
+                            __event_call__,
+                        )
+
+            # Check MCP Servers
+            mcp_servers = self._parse_mcp_servers()
+            mcp_server_names = list(mcp_servers.keys()) if mcp_servers else []
+            if mcp_server_names:
+                await self._emit_debug_log(
+                    f"🔌 MCP Servers Configured: {mcp_server_names}",
+                    __event_call__,
+                )
+
+            else:
+                await self._emit_debug_log(
+                    "ℹ️ No MCP tool servers found in OpenWebUI Connections.",
+                    __event_call__,
+                )
 
             # Create or Resume Session
             session = None
             if chat_id:
                 try:
-                    session = await client.resume_session(chat_id)
+                    # Prepare resume config
+                    resume_params = {}
+                    if mcp_servers:
+                        resume_params["mcp_servers"] = mcp_servers
+
+                    session = (
+                        await client.resume_session(chat_id, resume_params)
+                        if resume_params
+                        else await client.resume_session(chat_id)
+                    )
                     await self._emit_debug_log(
-                        f"Resumed session: {chat_id} (Note: Formatting guidelines only apply to NEW sessions. Create a new chat to use updated formatting.)",
+                        f"Resumed session: {chat_id} (Reasoning: {effective_reasoning_effort or 'default'})",
                         __event_call__,
                     )
 
-                    # Show workspace info if available
-                    if self.valves.DEBUG and self.valves.SHOW_WORKSPACE_INFO:
+                    # Show workspace info of available
+                    if self.valves.DEBUG:
                         if session.workspace_path:
                             await self._emit_debug_log(
                                 f"Session workspace: {session.workspace_path}",
@@ -990,7 +1401,7 @@ class Pipe:
                 )
 
                 # Show workspace info for new sessions
-                if self.valves.DEBUG and self.valves.SHOW_WORKSPACE_INFO:
+                if self.valves.DEBUG:
                     if session.workspace_path:
                         await self._emit_debug_log(
                             f"Session workspace: {session.workspace_path}",
@@ -1012,7 +1423,11 @@ class Pipe:
             if body.get("stream", False):
                 init_msg = ""
                 if self.valves.DEBUG:
-                    init_msg = f"> [Debug] Agent working in: {os.getcwd()}\n"
+                    init_msg = (
+                        f"> [Debug] Agent working in: {self._get_workspace_dir()}\n"
+                    )
+                    if mcp_server_names:
+                        init_msg += f"> [Debug] 🔌 Connected MCP Servers: {', '.join(mcp_server_names)}\n"
 
                 # Transfer client ownership to stream_response
                 should_stop_client = False

plugins/pipes/github-copilot-sdk/github_copilot_sdk_cn.py

@@ -4,11 +4,12 @@ author: Fu-Jie
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 funding_url: https://github.com/open-webui
 description: 集成 GitHub Copilot SDK。支持动态模型、多轮对话、流式输出、多模态输入、无限会话及前端调试日志。
-version: 0.2.3
-requirements: github-copilot-sdk
+version: 0.3.0
+requirements: github-copilot-sdk==0.1.22
 """
 
 import os
+import re
 import time
 import json
 import base64
@@ -18,46 +19,36 @@ import logging
 import shutil
 import subprocess
 import sys
-from typing import Optional, Union, AsyncGenerator, List, Any, Dict
-from pydantic import BaseModel, Field
+import hashlib
+from pathlib import Path
+from typing import Optional, Union, AsyncGenerator, List, Any, Dict, Callable
+from types import SimpleNamespace
+from pydantic import BaseModel, Field, create_model
 from datetime import datetime, timezone
 import contextlib
 
 # 导入 Copilot SDK 模块
 from copilot import CopilotClient, define_tool
 
+# 导入 OpenWebUI 配置和工具模块
+from open_webui.config import TOOL_SERVER_CONNECTIONS
+from open_webui.utils.tools import get_tools as get_openwebui_tools
+from open_webui.models.tools import Tools
+from open_webui.models.users import Users
+
 # Setup logger
 logger = logging.getLogger(__name__)
 
 
-class RandomNumberParams(BaseModel):
-    min: int = Field(description="最小值（包含）")
-    max: int = Field(description="最大值（包含）")
-
-
-@define_tool(description="在指定范围内生成随机整数。")
-async def generate_random_number(params: RandomNumberParams) -> str:
-    import random
-
-    if params.min >= params.max:
-        raise ValueError("min 必须小于 max")
-    number = random.randint(params.min, params.max)
-    return f"生成的随机数: {number}"
-
-
 class Pipe:
     class Valves(BaseModel):
         GH_TOKEN: str = Field(
             default="",
-            description="GitHub 细粒度 Token（需要 Copilot Requests 权限）",
+            description="GitHub OAuth Token (来自 'gh auth token')，用于 Copilot Chat (必须)",
         )
-        MODEL_ID: str = Field(
-            default="gpt-5-mini",
-            description="默认 Copilot 模型名（动态获取失败时使用）",
-        )
-        CLI_PATH: str = Field(
-            default="/usr/local/bin/copilot",
-            description="Copilot CLI 路径",
+        COPILOT_CLI_VERSION: str = Field(
+            default="0.0.405",
+            description="指定安装/强制使用的 Copilot CLI 版本 (例如 '0.0.405')。留空则使用最新版。",
         )
         DEBUG: bool = Field(
             default=False,
@@ -71,10 +62,6 @@ class Pipe:
             default=True,
             description="显示模型推理/思考过程",
         )
-        SHOW_WORKSPACE_INFO: bool = Field(
-            default=True,
-            description="调试模式下显示会话工作空间路径与摘要",
-        )
         EXCLUDE_KEYWORDS: str = Field(
             default="",
             description="排除包含这些关键词的模型（逗号分隔，如：codex, haiku）",
@@ -103,13 +90,14 @@ class Pipe:
             default="",
             description='自定义环境变量（JSON 格式，例如 {"VAR": "value"}）',
         )
-        ENABLE_TOOLS: bool = Field(
-            default=False,
-            description="启用自定义工具（例如：随机数）",
+
+        ENABLE_OPENWEBUI_TOOLS: bool = Field(
+            default=True,
+            description="启用 OpenWebUI 工具 (包括自定义工具和工具服务器工具)。",
         )
-        AVAILABLE_TOOLS: str = Field(
-            default="all",
-            description="可用工具：'all' 或逗号分隔列表（例如：'generate_random_number'）",
+        ENABLE_MCP_SERVER: bool = Field(
+            default=True,
+            description="启用直接 MCP 客户端连接 (推荐)。",
         )
         REASONING_EFFORT: str = Field(
             default="medium",
@@ -121,25 +109,35 @@ class Pipe:
         )
 
     class UserValves(BaseModel):
+        GH_TOKEN: str = Field(
+            default="",
+            description="个人 GitHub Fine-grained Token (覆盖全局设置)",
+        )
         REASONING_EFFORT: str = Field(
             default="",
             description="推理强度级别 (low, medium, high, xhigh)。留空以使用全局设置。",
         )
-        CLI_PATH: str = Field(
-            default="",
-            description="自定义 Copilot CLI 路径。留空以使用全局设置。",
-        )
         DEBUG: bool = Field(
             default=False,
             description="启用技术调试日志（连接信息等）",
         )
         SHOW_THINKING: bool = Field(
             default=True,
-            description="显示模型推理/思考过程",
+            description="显示模型的推理/思考过程",
         )
-        MODEL_ID: str = Field(
-            default="",
-            description="自定义模型 ID (例如 gpt-4o)。留空以使用全局默认值。",
+
+        ENABLE_OPENWEBUI_TOOLS: bool = Field(
+            default=True,
+            description="启用 OpenWebUI 工具 (包括自定义工具和工具服务器工具，覆盖全局设置)。",
+        )
+        ENABLE_MCP_SERVER: bool = Field(
+            default=True,
+            description="启用动态 MCP 服务器加载 (覆盖全局设置)。",
+        )
+
+        ENFORCE_FORMATTING: bool = Field(
+            default=True,
+            description="强制启用格式化指导 (覆盖全局设置)",
         )
 
     def __init__(self):
@@ -150,6 +148,7 @@ class Pipe:
         self.temp_dir = tempfile.mkdtemp(prefix="copilot_images_")
         self.thinking_started = False
         self._model_cache = []  # 模型列表缓存
+        self._last_update_check = 0  # 上次 CLI 更新检查时间
 
     def __del__(self):
         try:
@@ -338,9 +337,31 @@ class Pipe:
 
         return system_prompt_content, system_prompt_source
 
+    def _get_workspace_dir(self) -> str:
+        """获取具有智能默认值的有效工作空间目录。"""
+        if self.valves.WORKSPACE_DIR:
+            return self.valves.WORKSPACE_DIR
+
+        # OpenWebUI 容器的智能默认值
+        if os.path.exists("/app/backend/data"):
+            cwd = "/app/backend/data/copilot_workspace"
+        else:
+            # 本地回退：当前工作目录的子目录
+            cwd = os.path.join(os.getcwd(), "copilot_workspace")
+
+        # 确保目录存在
+        if not os.path.exists(cwd):
+            try:
+                os.makedirs(cwd, exist_ok=True)
+            except Exception as e:
+                print(f"Error creating workspace {cwd}: {e}")
+                return os.getcwd()  # 如果创建失败回退到 CWD
+
+        return cwd
+
     def _build_client_config(self, body: dict) -> dict:
         """根据 Valves 和请求构建 CopilotClient 配置"""
-        cwd = self.valves.WORKSPACE_DIR if self.valves.WORKSPACE_DIR else os.getcwd()
+        cwd = self._get_workspace_dir()
         client_config = {}
         if os.environ.get("COPILOT_CLI_PATH"):
             client_config["cli_path"] = os.environ["COPILOT_CLI_PATH"]
@@ -359,6 +380,270 @@ class Pipe:
 
         return client_config
 
+    async def _initialize_custom_tools(self, __user__=None, __event_call__=None):
+        """根据配置初始化自定义工具"""
+
+        if not self.valves.ENABLE_OPENWEBUI_TOOLS:
+            return []
+
+        # 动态加载 OpenWebUI 工具
+        openwebui_tools = await self._load_openwebui_tools(
+            __user__=__user__, __event_call__=__event_call__
+        )
+
+        return openwebui_tools
+
+    def _json_schema_to_python_type(self, schema: dict) -> Any:
+        """将 JSON Schema 类型转换为 Python 类型以用于 Pydantic 模型。"""
+        if not isinstance(schema, dict):
+            return Any
+
+        schema_type = schema.get("type")
+        if isinstance(schema_type, list):
+            schema_type = next((t for t in schema_type if t != "null"), schema_type[0])
+
+        if schema_type == "string":
+            return str
+        if schema_type == "integer":
+            return int
+        if schema_type == "number":
+            return float
+        if schema_type == "boolean":
+            return bool
+        if schema_type == "object":
+            return Dict[str, Any]
+        if schema_type == "array":
+            items_schema = schema.get("items", {})
+            item_type = self._json_schema_to_python_type(items_schema)
+            return List[item_type]
+
+        return Any
+
+    def _convert_openwebui_tool(self, tool_name: str, tool_dict: dict):
+        """将 OpenWebUI 工具定义转换为 Copilot SDK 工具。"""
+        # 净化工具名称以匹配模式 ^[a-zA-Z0-9_-]+$
+        sanitized_tool_name = re.sub(r"[^a-zA-Z0-9_-]", "_", tool_name)
+
+        # 如果净化后的名称为空或仅包含分隔符（例如纯中文名称），生成回退名称
+        if not sanitized_tool_name or re.match(r"^[_.-]+$", sanitized_tool_name):
+            hash_suffix = hashlib.md5(tool_name.encode("utf-8")).hexdigest()[:8]
+            sanitized_tool_name = f"tool_{hash_suffix}"
+
+        if sanitized_tool_name != tool_name:
+            logger.debug(f"将工具名称 '{tool_name}' 净化为 '{sanitized_tool_name}'")
+
+        spec = tool_dict.get("spec", {}) if isinstance(tool_dict, dict) else {}
+        params_schema = spec.get("parameters", {}) if isinstance(spec, dict) else {}
+        properties = params_schema.get("properties", {})
+        required = params_schema.get("required", [])
+
+        if not isinstance(properties, dict):
+            properties = {}
+        if not isinstance(required, list):
+            required = []
+
+        required_set = set(required)
+        fields = {}
+        for param_name, param_schema in properties.items():
+            param_type = self._json_schema_to_python_type(param_schema)
+            description = ""
+            if isinstance(param_schema, dict):
+                description = param_schema.get("description", "")
+
+            if param_name in required_set:
+                if description:
+                    fields[param_name] = (
+                        param_type,
+                        Field(..., description=description),
+                    )
+                else:
+                    fields[param_name] = (param_type, ...)
+            else:
+                optional_type = Optional[param_type]
+                if description:
+                    fields[param_name] = (
+                        optional_type,
+                        Field(default=None, description=description),
+                    )
+                else:
+                    fields[param_name] = (optional_type, None)
+
+        if fields:
+            ParamsModel = create_model(f"{sanitized_tool_name}_Params", **fields)
+        else:
+            ParamsModel = create_model(f"{sanitized_tool_name}_Params")
+
+        tool_callable = tool_dict.get("callable")
+        tool_description = spec.get("description", "") if isinstance(spec, dict) else ""
+        if not tool_description and isinstance(spec, dict):
+            tool_description = spec.get("summary", "")
+
+        # 关键: 如果工具名称被净化（例如中文转哈希），语义会丢失。
+        # 我们必须将原始名称注入到描述中，以便模型知道它的作用。
+        if sanitized_tool_name != tool_name:
+            tool_description = f"功能 '{tool_name}': {tool_description}"
+
+        async def _tool(params):
+            payload = params.model_dump() if hasattr(params, "model_dump") else {}
+            return await tool_callable(**payload)
+
+        _tool.__name__ = sanitized_tool_name
+        _tool.__doc__ = tool_description
+
+        # 转换调试日志
+        logger.debug(
+            f"正在转换工具 '{sanitized_tool_name}': {tool_description[:50]}..."
+        )
+
+        # 核心关键点：必须显式传递 types，否则 define_tool 无法推断动态函数的参数
+        # 显式传递 name 确保 SDK 注册的名称正确
+        return define_tool(
+            name=sanitized_tool_name,
+            description=tool_description,
+            params_type=ParamsModel,
+        )(_tool)
+
+    def _build_openwebui_request(self):
+        """构建一个最小的 request 模拟对象用于 OpenWebUI 工具加载。"""
+        app_state = SimpleNamespace(
+            config=SimpleNamespace(
+                TOOL_SERVER_CONNECTIONS=TOOL_SERVER_CONNECTIONS.value
+            ),
+            TOOLS={},
+        )
+        app = SimpleNamespace(state=app_state)
+        request = SimpleNamespace(
+            app=app,
+            cookies={},
+            state=SimpleNamespace(token=SimpleNamespace(credentials="")),
+        )
+        return request
+
+    async def _load_openwebui_tools(self, __user__=None, __event_call__=None):
+        """动态加载 OpenWebUI 工具并转换为 Copilot SDK 工具。"""
+        if isinstance(__user__, (list, tuple)):
+            user_data = __user__[0] if __user__ else {}
+        elif isinstance(__user__, dict):
+            user_data = __user__
+        else:
+            user_data = {}
+
+        if not user_data:
+            return []
+
+        user_id = user_data.get("id") or user_data.get("user_id")
+        if not user_id:
+            return []
+
+        user = Users.get_user_by_id(user_id)
+        if not user:
+            return []
+
+        # 1. 获取用户自定义工具 (Python 脚本)
+        tool_items = Tools.get_tools_by_user_id(user_id, permission="read")
+        tool_ids = [tool.id for tool in tool_items] if tool_items else []
+
+        # 2. 获取 OpenAPI 工具服务器工具
+        # 我们手动添加已启用的 OpenAPI 服务器，因为 Tools.get_tools_by_user_id 仅检查数据库。
+        # open_webui.utils.tools.get_tools 会处理实际的加载和访问控制。
+        if hasattr(TOOL_SERVER_CONNECTIONS, "value"):
+            for server in TOOL_SERVER_CONNECTIONS.value:
+                # 我们在此处仅添加 'openapi' 服务器，因为 get_tools 目前似乎仅支持 'openapi' (默认为此)。
+                # MCP 工具通过 ENABLE_MCP_SERVER 单独处理。
+                if server.get("type") == "openapi":
+                    # get_tools 期望的格式: "server:<id>" 隐含 type="openapi"
+                    server_id = server.get("id")
+                    if server_id:
+                        tool_ids.append(f"server:{server_id}")
+
+        if not tool_ids:
+            return []
+
+        request = self._build_openwebui_request()
+        extra_params = {
+            "__request__": request,
+            "__user__": user_data,
+            "__event_emitter__": None,
+            "__event_call__": __event_call__,
+            "__chat_id__": None,
+            "__message_id__": None,
+            "__model_knowledge__": [],
+        }
+
+        tools_dict = await get_openwebui_tools(request, tool_ids, user, extra_params)
+        if not tools_dict:
+            return []
+
+        converted_tools = []
+        for tool_name, tool_def in tools_dict.items():
+            try:
+                converted_tools.append(
+                    self._convert_openwebui_tool(tool_name, tool_def)
+                )
+            except Exception as e:
+                await self._emit_debug_log(
+                    f"加载 OpenWebUI 工具 '{tool_name}' 失败: {e}",
+                    __event_call__,
+                )
+
+        return converted_tools
+
+    def _parse_mcp_servers(self) -> Optional[dict]:
+        """
+        从 OpenWebUI TOOL_SERVER_CONNECTIONS 动态加载 MCP 服务器配置。
+        返回兼容 CopilotClient 的 mcp_servers 字典。
+        """
+        if not self.valves.ENABLE_MCP_SERVER:
+            return None
+
+        mcp_servers = {}
+
+        # 遍历 OpenWebUI 工具服务器连接
+        if hasattr(TOOL_SERVER_CONNECTIONS, "value"):
+            connections = TOOL_SERVER_CONNECTIONS.value
+        else:
+            connections = []
+
+        for conn in connections:
+            if conn.get("type") == "mcp":
+                info = conn.get("info", {})
+                # 使用 info 中的 ID 或自动生成
+                raw_id = info.get("id", f"mcp-server-{len(mcp_servers)}")
+
+                # 净化 server_id (使用与工具相同的逻辑)
+                server_id = re.sub(r"[^a-zA-Z0-9_-]", "_", raw_id)
+                if not server_id or re.match(r"^[_.-]+$", server_id):
+                    hash_suffix = hashlib.md5(raw_id.encode("utf-8")).hexdigest()[:8]
+                    server_id = f"server_{hash_suffix}"
+
+                url = conn.get("url")
+                if not url:
+                    continue
+
+                # 构建 Header (处理认证)
+                headers = {}
+                auth_type = conn.get("auth_type", "bearer")
+                key = conn.get("key", "")
+
+                if auth_type == "bearer" and key:
+                    headers["Authorization"] = f"Bearer {key}"
+                elif auth_type == "basic" and key:
+                    headers["Authorization"] = f"Basic {key}"
+
+                # 合并自定义 headers
+                custom_headers = conn.get("headers", {})
+                if isinstance(custom_headers, dict):
+                    headers.update(custom_headers)
+
+                mcp_servers[server_id] = {
+                    "type": "http",
+                    "url": url,
+                    "headers": headers,
+                    "tools": ["*"],  # 默认启用所有工具
+                }
+
+        return mcp_servers if mcp_servers else None
+
     def _build_session_config(
         self,
         chat_id: Optional[str],
@@ -366,7 +651,6 @@ class Pipe:
         custom_tools: List[Any],
         system_prompt_content: Optional[str],
         is_streaming: bool,
-        reasoning_effort: str = "",
     ):
         """构建 Copilot SDK 的 SessionConfig"""
         from copilot.types import SessionConfig, InfiniteSessionConfig
@@ -414,11 +698,12 @@ class Pipe:
             "tools": custom_tools,
             "system_message": system_message_config,
             "infinite_sessions": infinite_session_config,
+            # 注册权限处理 Hook
         }
 
-        # 如果不是默认值（medium），添加 reasoning_effort
-        if reasoning_effort and reasoning_effort.lower() != "medium":
-            session_params["reasoning_effort"] = reasoning_effort.lower()
+        mcp_servers = self._parse_mcp_servers()
+        if mcp_servers:
+            session_params["mcp_servers"] = mcp_servers
 
         return SessionConfig(**session_params)
 
@@ -545,24 +830,6 @@ class Pipe:
 
         return system_prompt_content, system_prompt_source
 
-    def _initialize_custom_tools(self):
-        """根据配置初始化自定义工具"""
-        if not self.valves.ENABLE_TOOLS:
-            return []
-
-        # 定义所有可用工具（在此注册新工具）
-        all_tools = {
-            "generate_random_number": generate_random_number,
-        }
-
-        # 根据配置过滤
-        if self.valves.AVAILABLE_TOOLS == "all":
-            return list(all_tools.values())
-
-        # 仅启用指定的工具
-        enabled = [t.strip() for t in self.valves.AVAILABLE_TOOLS.split(",")]
-        return [all_tools[name] for name in enabled if name in all_tools]
-
     async def _emit_debug_log(self, message: str, __event_call__=None):
         """在 DEBUG 开启时将日志输出到前端控制台。"""
         if not self.valves.DEBUG:
@@ -764,8 +1031,8 @@ class Pipe:
                 # 失败时返回默认模型
                 return [
                     {
-                        "id": f"{self.id}-{self.valves.MODEL_ID}",
-                        "name": f"GitHub Copilot ({self.valves.MODEL_ID})",
+                        "id": f"{self.id}-gpt-5-mini",
+                        "name": f"GitHub Copilot (gpt-5-mini)",
                     }
                 ]
             finally:
@@ -774,8 +1041,8 @@ class Pipe:
             await self._emit_debug_log(f"Pipes Error: {e}")
             return [
                 {
-                    "id": f"{self.id}-{self.valves.MODEL_ID}",
-                    "name": f"GitHub Copilot ({self.valves.MODEL_ID})",
+                    "id": f"{self.id}-gpt-5-mini",
+                    "name": f"GitHub Copilot (gpt-5-mini)",
                 }
             ]
 
@@ -807,30 +1074,93 @@ class Pipe:
         return client
 
     def _setup_env(self, __event_call__=None):
-        cli_path = self.valves.CLI_PATH
-        found = False
+        cli_path = "/usr/local/bin/copilot"
+        if os.environ.get("COPILOT_CLI_PATH"):
+            cli_path = os.environ["COPILOT_CLI_PATH"]
 
+        target_version = self.valves.COPILOT_CLI_VERSION.strip()
+        found = False
+        current_version = None
+
+        # 内部 helper: 获取版本
+        def get_cli_version(path):
+            try:
+                output = (
+                    subprocess.check_output(
+                        [path, "--version"], stderr=subprocess.STDOUT
+                    )
+                    .decode()
+                    .strip()
+                )
+                # Copilot CLI 输出通常包含 "copilot version X.Y.Z" 或直接是版本号
+                match = re.search(r"(\d+\.\d+\.\d+)", output)
+                return match.group(1) if match else output
+            except Exception:
+                return None
+
+        # 检查默认路径
         if os.path.exists(cli_path):
             found = True
+            current_version = get_cli_version(cli_path)
 
+        # 二次检查系统路径
         if not found:
             sys_path = shutil.which("copilot")
             if sys_path:
                 cli_path = sys_path
                 found = True
+                current_version = get_cli_version(cli_path)
+
+        # 判断是否需要安装/更新
+        should_install = False
+        install_reason = ""
 
         if not found:
+            should_install = True
+            install_reason = "CLI 未找到"
+        elif target_version:
+            # 标准化版本号 (移除 'v' 前缀)
+            norm_target = target_version.lstrip("v")
+            norm_current = current_version.lstrip("v") if current_version else ""
+
+            if norm_target != norm_current:
+                should_install = True
+                install_reason = (
+                    f"版本不匹配 (当前: {current_version}, 目标: {target_version})"
+                )
+
+        if should_install:
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    f"正在安装 Copilot CLI: {install_reason}...", __event_call__
+                )
             try:
+                env = os.environ.copy()
+                if target_version:
+                    env["VERSION"] = target_version
+
                 subprocess.run(
                     "curl -fsSL https://gh.io/copilot-install | bash",
                     shell=True,
                     check=True,
+                    env=env,
                 )
-                if os.path.exists(self.valves.CLI_PATH):
-                    cli_path = self.valves.CLI_PATH
+
+                # 优先检查默认安装路径，其次是系统路径
+                if os.path.exists("/usr/local/bin/copilot"):
+                    cli_path = "/usr/local/bin/copilot"
                     found = True
-            except:
-                pass
+                elif shutil.which("copilot"):
+                    cli_path = shutil.which("copilot")
+                    found = True
+
+                if found:
+                    current_version = get_cli_version(cli_path)
+            except Exception as e:
+                if self.valves.DEBUG:
+                    self._emit_debug_log_sync(
+                        f"Copilot CLI 安装失败: {e}", __event_call__
+                    )
 
         if found:
             os.environ["COPILOT_CLI_PATH"] = cli_path
@@ -840,7 +1170,14 @@ class Pipe:
 
             if self.valves.DEBUG:
                 self._emit_debug_log_sync(
-                    f"Copilot CLI 已定位: {cli_path}", __event_call__
+                    f"已找到 Copilot CLI: {cli_path} (版本: {current_version})",
+                    __event_call__,
+                )
+        else:
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    "错误: 未找到 Copilot CLI。相关 Agent 功能将被禁用。",
+                    __event_call__,
                 )
 
         if self.valves.GH_TOKEN:
@@ -850,6 +1187,8 @@ class Pipe:
             if self.valves.DEBUG:
                 self._emit_debug_log_sync("Warning: GH_TOKEN 未设置。", __event_call__)
 
+        self._sync_mcp_config(__event_call__)
+
     def _process_images(self, messages, __event_call__=None):
         attachments = []
         text_content = ""
@@ -944,9 +1283,113 @@ class Pipe:
         except Exception as e:
             self._emit_debug_log_sync(f"配置同步检查失败: {e}", __event_call__)
 
+    def _sync_mcp_config(self, __event_call__=None):
+        """已弃用：MCP 配置现在通过 SessionConfig 动态处理。"""
+        pass
+
     # ==================== 内部实现 ====================
     # _pipe_impl() 包含主请求处理逻辑。
     # ================================================
+    def _sync_copilot_config(self, reasoning_effort: str, __event_call__=None):
+        """
+        如果设置了 REASONING_EFFORT，则动态更新 ~/.copilot/config.json。
+        这提供了一个回退机制，以防 API 注入被服务器忽略。
+        """
+        if not reasoning_effort:
+            return
+
+        effort = reasoning_effort
+
+        # 检查模型是否支持 xhigh
+        # 目前只有 gpt-5.2-codex 支持 xhigh
+        if effort == "xhigh":
+            # 简单检查，使用默认模型 ID
+            if (
+                "gpt-5.2-codex"
+                not in self._collect_model_ids(
+                    body={},
+                    request_model=self.id,
+                    real_model_id=None,
+                )[0].lower()
+            ):
+                # 如果不支持则回退到 high
+                effort = "high"
+
+        try:
+            # 目标标准路径 ~/.copilot/config.json
+            config_path = os.path.expanduser("~/.copilot/config.json")
+            config_dir = os.path.dirname(config_path)
+
+            # 仅当目录存在时才继续（避免在路径错误时创建垃圾文件）
+            if not os.path.exists(config_dir):
+                return
+
+            data = {}
+            # 读取现有配置
+            if os.path.exists(config_path):
+                try:
+                    with open(config_path, "r") as f:
+                        data = json.load(f)
+                except Exception:
+                    data = {}
+
+            # 如果有变化则更新
+            current_val = data.get("reasoning_effort")
+            if current_val != effort:
+                data["reasoning_effort"] = effort
+                try:
+                    with open(config_path, "w") as f:
+                        json.dump(data, f, indent=4)
+
+                    self._emit_debug_log_sync(
+                        f"已动态更新 ~/.copilot/config.json: reasoning_effort='{effort}'",
+                        __event_call__,
+                    )
+                except Exception as e:
+                    self._emit_debug_log_sync(
+                        f"写入 config.json 失败: {e}", __event_call__
+                    )
+        except Exception as e:
+            self._emit_debug_log_sync(f"配置同步检查失败: {e}", __event_call__)
+
+    async def _update_copilot_cli(self, cli_path: str, __event_call__=None):
+        """异步任务：如果需要则更新 Copilot CLI。"""
+        import time
+
+        try:
+            # 检查频率（例如：每小时一次）
+            now = time.time()
+            if now - self._last_update_check < 3600:
+                return
+
+            self._last_update_check = now
+
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    "触发异步 Copilot CLI 更新检查...", __event_call__
+                )
+
+            # 我们创建一个子进程来运行更新
+            process = await asyncio.create_subprocess_exec(
+                cli_path,
+                "update",
+                stdout=asyncio.subprocess.PIPE,
+                stderr=asyncio.subprocess.PIPE,
+            )
+
+            stdout, stderr = await process.communicate()
+
+            if self.valves.DEBUG and process.returncode == 0:
+                self._emit_debug_log_sync("Copilot CLI 更新检查完成", __event_call__)
+            elif process.returncode != 0 and self.valves.DEBUG:
+                self._emit_debug_log_sync(
+                    f"Copilot CLI 更新失败: {stderr.decode()}", __event_call__
+                )
+
+        except Exception as e:
+            if self.valves.DEBUG:
+                self._emit_debug_log_sync(f"CLI 更新任务异常: {e}", __event_call__)
+
     async def _pipe_impl(
         self,
         body: dict,
@@ -956,12 +1399,23 @@ class Pipe:
         __event_call__=None,
     ) -> Union[str, AsyncGenerator]:
         self._setup_env(__event_call__)
+
+        cwd = self._get_workspace_dir()
+        if self.valves.DEBUG:
+            await self._emit_debug_log(f"当前工作目录: {cwd}", __event_call__)
+
+        # CLI Update Check
+        if os.environ.get("COPILOT_CLI_PATH"):
+            asyncio.create_task(
+                self._update_copilot_cli(os.environ["COPILOT_CLI_PATH"], __event_call__)
+            )
+
         if not self.valves.GH_TOKEN:
             return "Error: 请在 Valves 中配置 GH_TOKEN。"
 
         # 解析用户选择的模型
         request_model = body.get("model", "")
-        real_model_id = self.valves.MODEL_ID  # 默认值
+        real_model_id = request_model
 
         # 确定有效的推理强度和调试设置
         if __user__:
@@ -979,6 +1433,10 @@ class Pipe:
             if user_valves.REASONING_EFFORT
             else self.valves.REASONING_EFFORT
         )
+
+        # Sync config for reasoning effort (Legacy/Fallback)
+        self._sync_copilot_config(effective_reasoning_effort, __event_call__)
+
         # 如果用户启用了 DEBUG，则覆盖全局设置
         if user_valves.DEBUG:
             self.valves.DEBUG = True
@@ -995,6 +1453,14 @@ class Pipe:
             await self._emit_debug_log(
                 f"使用选择的模型: {real_model_id}", __event_call__
             )
+        elif __metadata__ and __metadata__.get("base_model_id"):
+            base_model_id = __metadata__.get("base_model_id", "")
+            if base_model_id.startswith(f"{self.id}-"):
+                real_model_id = base_model_id[len(f"{self.id}-") :]
+                await self._emit_debug_log(
+                    f"使用基础模型: {real_model_id} (继承自自定义模型 {request_model})",
+                    __event_call__,
+                )
 
         messages = body.get("messages", [])
         if not messages:
@@ -1019,32 +1485,66 @@ class Pipe:
         is_streaming = body.get("stream", False)
         await self._emit_debug_log(f"请求流式传输: {is_streaming}", __event_call__)
 
+        # 处理多模态（图像）和提取最后的消息文本
+        last_text, attachments = self._process_images(messages, __event_call__)
+
         client = CopilotClient(self._build_client_config(body))
         should_stop_client = True
         try:
             await client.start()
 
             # 初始化自定义工具
-            custom_tools = self._initialize_custom_tools()
+            custom_tools = await self._initialize_custom_tools(
+                __user__=__user__, __event_call__=__event_call__
+            )
             if custom_tools:
                 tool_names = [t.name for t in custom_tools]
                 await self._emit_debug_log(
                     f"已启用 {len(custom_tools)} 个自定义工具: {tool_names}",
                     __event_call__,
                 )
+                # 详细打印每个工具的描述 (用于调试)
+                if self.valves.DEBUG:
+                    for t in custom_tools:
+                        await self._emit_debug_log(
+                            f"📋 工具详情: {t.name} - {t.description[:100]}...",
+                            __event_call__,
+                        )
+
+            # 检查 MCP 服务器
+            mcp_servers = self._parse_mcp_servers()
+            mcp_server_names = list(mcp_servers.keys()) if mcp_servers else []
+            if mcp_server_names:
+                await self._emit_debug_log(
+                    f"🔌 MCP 服务器已配置: {mcp_server_names}",
+                    __event_call__,
+                )
+            else:
+                await self._emit_debug_log(
+                    "ℹ️ 未在 OpenWebUI 连接中发现 MCP 服务器。",
+                    __event_call__,
+                )
 
             session = None
 
             if chat_id:
                 try:
+                    # 复用已解析的 mcp_servers
+                    resume_config = (
+                        {"mcp_servers": mcp_servers} if mcp_servers else None
+                    )
                     # 尝试直接使用 chat_id 作为 session_id 恢复会话
-                    session = await client.resume_session(chat_id)
+                    session = (
+                        await client.resume_session(chat_id, resume_config)
+                        if resume_config
+                        else await client.resume_session(chat_id)
+                    )
                     await self._emit_debug_log(
                         f"已通过 ChatID 恢复会话: {chat_id}", __event_call__
                     )
 
                     # 显示工作空间信息（如果可用）
-                    if self.valves.DEBUG and self.valves.SHOW_WORKSPACE_INFO:
+                    if self.valves.DEBUG:
                         if session.workspace_path:
                             await self._emit_debug_log(
                                 f"会话工作空间: {session.workspace_path}",
@@ -1107,7 +1607,7 @@ class Pipe:
                 await self._emit_debug_log(f"创建了新会话: {new_sid}", __event_call__)
 
                 # 显示新会话的工作空间信息
-                if self.valves.DEBUG and self.valves.SHOW_WORKSPACE_INFO:
+                if self.valves.DEBUG:
                     if session.workspace_path:
                         await self._emit_debug_log(
                             f"会话工作空间: {session.workspace_path}",
@@ -1133,6 +1633,9 @@ class Pipe:
                     else:
                         init_msg = f"> [Debug] 已通过 ChatID 恢复会话: {chat_id}\n"
 
+                    if mcp_server_names:
+                        init_msg += f"> [Debug] 🔌 已连接 MCP 服务器: {', '.join(mcp_server_names)}\n"
+
                 return self.stream_response(
                     client,
                     session,

scripts/extract_plugin_versions.py

@@ -93,7 +93,11 @@ def scan_plugins_directory(plugins_dir: str) -> list[dict[str, Any]]:
         return plugins
 
     # Walk through all subdirectories
-    for root, _dirs, files in os.walk(plugins_path):
+    for root, dirs, files in os.walk(plugins_path):
+        # Exclude debug directory from scan
+        if "debug" in dirs:
+            dirs.remove("debug")
+
         for file in files:
             if file.endswith(".py") and not file.startswith("__"):
                 # Skip specific files that should not trigger release
@@ -110,6 +114,11 @@ def scan_plugins_directory(plugins_dir: str) -> list[dict[str, Any]]:
                 if metadata:
                     # Determine plugin type from directory structure
                     rel_path = os.path.relpath(file_path, plugins_dir)
+                    
+                    # Normalize file_path to always start with "plugins/" for consistent ID comparison
+                    # regardless of where we scan from (/tmp/old_repo or ./plugins)
+                    metadata["file_path"] = os.path.join("plugins", rel_path)
+                    
                     parts = rel_path.split(os.sep)
                     if len(parts) > 0:
                         metadata["type"] = parts[0]  # actions, filters, pipes, etc.

scripts/publish_plugin.py

@@ -23,7 +23,11 @@ from openwebui_community_client import get_client
 def find_existing_plugins(plugins_dir: str) -> list:
     """查找所有已发布的插件文件（有 openwebui_id 的）"""
     plugins = []
-    for root, _, files in os.walk(plugins_dir):
+    for root, dirs, files in os.walk(plugins_dir):
+        # Exclude debug directory
+        if "debug" in dirs:
+            dirs.remove("debug")
+
         for file in files:
             if file.endswith(".py") and not file.startswith("__"):
                 file_path = os.path.join(root, file)