feat: 添加 JavaScript 渲染 PoC，支持通过 API 更新消息内容

docs: 更新插件安装指南，增加OpenWebUI社区推荐安装方式。
chore: release export-to-word v0.3.0
2026-01-05 09:01:42 +08:00 · 2026-01-05 00:31:18 +08:00 · 2026-01-04 03:17:35 +08:00 · 2026-01-04 03:14:28 +08:00 · 2026-01-04 02:44:33 +08:00 · 2026-01-04 02:40:46 +08:00
33 changed files with 830 additions and 104 deletions
--- a/.github/copilot-instructions.md
+++ b/.github/copilot-instructions.md
@@ -798,6 +798,49 @@ For iframe plugins to access parent document theme information, users need to co
 - [ ] 使用 logging 而非 print
 - [ ] 测试双语界面
 - [ ] **一致性检查 (Consistency Check)**:
+
+---
+
+## 🚀 高级开发模式 (Advanced Development Patterns)
+
+### 混合服务端-客户端生成 (Hybrid Server-Client Generation)
+
+对于需要复杂前端渲染（如 Mermaid 图表、ECharts）但最终生成文件（如 DOCX、PDF）的场景，建议采用混合模式：
+
+1.  **服务端 (Python)**：
+    *   处理文本解析、Markdown 转换、文档结构构建。
+    *   为复杂组件生成**占位符**（如带有特定 ID 或元数据的图片/文本块）。
+    *   将半成品文件（如 Base64 编码的 ZIP/DOCX）发送给前端。
+
+2.  **客户端 (JavaScript)**：
+    *   在浏览器中加载半成品文件（使用 JSZip 等库）。
+    *   利用浏览器能力渲染复杂组件（如 `mermaid.render`）。
+    *   将渲染结果（SVG/PNG）回填到占位符位置。
+    *   触发最终文件的下载。
+
+**优势**：
+*   无需在服务端安装 Headless Browser（如 Puppeteer），降低部署复杂度。
+*   利用用户浏览器的计算能力。
+*   支持动态、交互式内容的静态化导出。
+
+### 原生 Word 公式支持 (Native Word Math Support)
+
+对于需要生成高质量数学公式的 Word 文档，推荐使用 `latex2mathml` + `mathml2omml` 组合：
+
+1.  **LaTeX -> MathML**: 使用 `latex2mathml` 将 LaTeX 字符串转换为标准 MathML。
+2.  **MathML -> OMML**: 使用 `mathml2omml` 将 MathML 转换为 Office Math Markup Language (OMML)。
+3.  **插入 Word**: 将 OMML XML 插入到 `python-docx` 的段落中。
+
+```python
+# 示例代码
+from latex2mathml.converter import convert as latex2mathml
+from mathml2omml import convert as mathml2omml
+
+def add_math(paragraph, latex_str):
+    mathml = latex2mathml(latex_str)
+    omml = mathml2omml(mathml)
+    # ... 插入 OMML 到 paragraph._element ...
+```
    - [ ] 更新 `README.md` 插件列表
    - [ ] 更新 `README_CN.md` 插件列表
    - [ ] 更新/创建 `docs/` 下的对应文档
--- a/README.md
+++ b/README.md
@@ -60,10 +60,16 @@ This project is a collection of resources and does not require a Python environm

 ### Using Plugins

-1. Browse the `/plugins` directory and download the plugin file (`.py`) you need.
-2. Go to OpenWebUI **Admin Panel** -> **Settings** -> **Plugins**.
-3. Click the upload button and select the `.py` file you just downloaded.
-4. Once uploaded, refresh the page to enable the plugin in your chat settings or toolbar.
+1. **Install from OpenWebUI Community (Recommended)**:
+   - Visit my profile: [Fu-Jie's Profile](https://openwebui.com/u/Fu-Jie)
+   - Browse the plugins and select the one you like.
+   - Click "Get" to import it directly into your OpenWebUI instance.
+
+2. **Manual Installation**:
+   - Browse the `/plugins` directory and download the plugin file (`.py`) you need.
+   - Go to OpenWebUI **Admin Panel** -> **Settings** -> **Plugins**.
+   - Click the upload button and select the `.py` file you just downloaded.
+   - Once uploaded, refresh the page to enable the plugin in your chat settings or toolbar.

 ### Contributing

--- a/README_CN.md
+++ b/README_CN.md
@@ -87,10 +87,16 @@ OpenWebUI 增强功能集合。包含个人开发与收集的### 🧩 插件 (Pl

 ### 使用插件 (Plugins)

-1. 在 `/plugins` 目录中浏览并下载你需要的插件文件 (`.py`)。
-2. 打开 OpenWebUI 的 **管理员面板 (Admin Panel)** -> **设置 (Settings)** -> **插件 (Plugins)**。
-3. 点击上传按钮，选择刚才下载的 `.py` 文件。
-4. 上传成功后，刷新页面，你就可以在聊天设置或工具栏中启用该插件了。
+1. **从 OpenWebUI 社区安装 (推荐)**:
+   - 访问我的主页: [Fu-Jie's Profile](https://openwebui.com/u/Fu-Jie)
+   - 浏览插件列表，选择你喜欢的插件。
+   - 点击 "Get" 按钮，将其直接导入到你的 OpenWebUI 实例中。
+
+2. **手动安装**:
+   - 在 `/plugins` 目录中浏览并下载你需要的插件文件 (`.py`)。
+   - 打开 OpenWebUI 的 **管理员面板 (Admin Panel)** -> **设置 (Settings)** -> **插件 (Plugins)**。
+   - 点击上传按钮，选择刚才下载的 `.py` 文件。
+   - 上传成功后，刷新页面，你就可以在聊天设置或工具栏中启用该插件了。

 ### 贡献代码

--- a/docs/index.md
+++ b/docs/index.md
@@ -104,10 +104,16 @@ hide:

 ### Using Plugins

-1. Browse the [Plugin Center](plugins/index.md) and download the plugin file (`.py`)
-2. Open OpenWebUI **Admin Panel** → **Settings** → **Plugins**
-3. Click the upload button and select the `.py` file
-4. Refresh the page and enable the plugin in your chat settings
+1. **Install from OpenWebUI Community (Recommended)**:
+   - Visit my profile: [Fu-Jie's Profile](https://openwebui.com/u/Fu-Jie)
+   - Browse the plugins and select the one you like.
+   - Click "Get" to import it directly into your OpenWebUI instance.
+
+2. **Manual Installation**:
+   - Browse the [Plugin Center](plugins/index.md) and download the plugin file (`.py`)
+   - Open OpenWebUI **Admin Panel** → **Settings** → **Plugins**
+   - Click the upload button and select the `.py` file
+   - Refresh the page and enable the plugin in your chat settings

 ---

--- a/docs/index.zh.md
+++ b/docs/index.zh.md
@@ -104,10 +104,16 @@ hide:

 ### 使用插件

-1. 浏览[插件中心](plugins/index.md)并下载插件文件（`.py`）
-2. 打开 OpenWebUI **管理面板** → **设置** → **插件**
-3. 点击上传按钮并选择 `.py` 文件
-4. 刷新页面并在聊天设置中启用插件
+1. **从 OpenWebUI 社区安装 (推荐)**:
+   - 访问我的主页: [Fu-Jie's Profile](https://openwebui.com/u/Fu-Jie)
+   - 浏览插件列表，选择你喜欢的插件。
+   - 点击 "Get" 按钮，将其直接导入到你的 OpenWebUI 实例中。
+
+2. **手动安装**:
+   - 浏览[插件中心](plugins/index.md)并下载插件文件（`.py`）
+   - 打开 OpenWebUI **管理面板** → **设置** → **插件**
+   - 点击上传按钮并选择 `.py` 文件
+   - 刷新页面并在聊天设置中启用插件

 ---

--- a/docs/js-visualization-guide.md
+++ b/docs/js-visualization-guide.md
@@ -0,0 +1,290 @@
+# 使用 JavaScript 生成可视化内容的技术方案
+
+## 概述
+
+本文档描述了在 OpenWebUI Action 插件中使用浏览器端 JavaScript 代码生成可视化内容（如思维导图、信息图等）并将结果保存到消息中的技术方案。
+
+## 核心架构
+
+```mermaid
+sequenceDiagram
+    participant Plugin as Python 插件
+    participant EventCall as __event_call__
+    participant Browser as 浏览器 (JS)
+    participant API as OpenWebUI API
+    participant DB as 数据库
+
+    Plugin->>EventCall: 1. 发送 execute 事件 (含 JS 代码)
+    EventCall->>Browser: 2. 执行 JS 代码
+    Browser->>Browser: 3. 加载可视化库 (D3/Markmap/AntV)
+    Browser->>Browser: 4. 渲染可视化内容
+    Browser->>Browser: 5. 转换为 Base64 Data URI
+    Browser->>API: 6. GET 获取当前消息内容
+    API-->>Browser: 7. 返回消息数据
+    Browser->>API: 8. POST 追加 Markdown 图片到消息
+    API->>DB: 9. 保存更新后的消息
+```
+
+## 关键步骤
+
+### 1. Python 端通过 `__event_call__` 执行 JS
+
+Python 插件**不直接修改 `body["messages"]`**，而是通过 `__event_call__` 发送 JS 代码让浏览器执行：
+
+```python
+async def action(
+    self,
+    body: dict,
+    __user__: dict = None,
+    __event_emitter__=None,
+    __event_call__: Optional[Callable[[Any], Awaitable[None]]] = None,
+    __metadata__: Optional[dict] = None,
+    __request__: Request = None,
+) -> dict:
+    # 从 body 获取 chat_id 和 message_id
+    chat_id = body.get("chat_id", "")
+    message_id = body.get("id", "")  # 注意：body["id"] 是 message_id
+    
+    # 通过 __event_call__ 执行 JS 代码
+    if __event_call__:
+        await __event_call__({
+            "type": "execute",
+            "data": {
+                "code": f"""
+(async function() {{
+    const chatId = "{chat_id}";
+    const messageId = "{message_id}";
+    // ... JS 渲染和 API 更新逻辑 ...
+}})();
+                """
+            },
+        })
+    
+    # 不修改 body，直接返回
+    return body
+```
+
+### 2. JavaScript 加载可视化库
+
+在浏览器端动态加载所需的 JS 库：
+
+```javascript
+// 加载 D3.js
+if (!window.d3) {
+    await new Promise((resolve, reject) => {
+        const script = document.createElement('script');
+        script.src = 'https://cdn.jsdelivr.net/npm/d3@7';
+        script.onload = resolve;
+        script.onerror = reject;
+        document.head.appendChild(script);
+    });
+}
+
+// 加载 Markmap (思维导图)
+if (!window.markmap) {
+    await loadScript('https://cdn.jsdelivr.net/npm/markmap-lib@0.17');
+    await loadScript('https://cdn.jsdelivr.net/npm/markmap-view@0.17');
+}
+```
+
+### 3. 渲染并转换为 Data URI
+
+```javascript
+// 创建 SVG 元素
+const svg = document.createElementNS('http://www.w3.org/2000/svg', 'svg');
+svg.setAttribute('width', '800');
+svg.setAttribute('height', '600');
+svg.setAttribute('xmlns', 'http://www.w3.org/2000/svg');
+
+// ... 执行渲染逻辑 (添加图形元素) ...
+
+// 转换为 Base64 Data URI
+const svgData = new XMLSerializer().serializeToString(svg);
+const base64 = btoa(unescape(encodeURIComponent(svgData)));
+const dataUri = 'data:image/svg+xml;base64,' + base64;
+```
+
+### 4. 获取当前消息内容
+
+由于 Python 端不传递原始内容，JS 需要通过 API 获取：
+
+```javascript
+const token = localStorage.getItem('token');
+
+// 获取当前聊天数据
+const getResponse = await fetch(`/api/v1/chats/${chatId}`, {
+    method: 'GET',
+    headers: {
+        'Authorization': `Bearer ${token}`
+    }
+});
+
+const chatData = await getResponse.json();
+
+// 查找目标消息
+let originalContent = '';
+if (chatData.chat && chatData.chat.messages) {
+    const targetMsg = chatData.chat.messages.find(m => m.id === messageId);
+    if (targetMsg && targetMsg.content) {
+        originalContent = targetMsg.content;
+    }
+}
+```
+
+### 5. 调用 API 更新消息
+
+```javascript
+// 构造新内容：原始内容 + Markdown 图片
+const markdownImage = `![可视化图片](${dataUri})`;
+const newContent = originalContent + '\n\n' + markdownImage;
+
+// 调用 API 更新消息
+const response = await fetch(`/api/v1/chats/${chatId}/messages/${messageId}/event`, {
+    method: 'POST',
+    headers: {
+        'Content-Type': 'application/json',
+        'Authorization': `Bearer ${token}`
+    },
+    body: JSON.stringify({
+        type: 'chat:message',
+        data: { content: newContent }
+    })
+});
+
+if (response.ok) {
+    console.log('消息更新成功！');
+}
+```
+
+## 完整示例
+
+参考 [js_render_poc.py](../plugins/actions/js-render-poc/js_render_poc.py) 获取完整的 PoC 实现。
+
+## 事件类型
+
+| 类型 | 用途 |
+|------|------|
+| `chat:message:delta` | 增量更新（追加文本） |
+| `chat:message` | 完全替换消息内容 |
+
+```javascript
+// 增量更新
+{ type: "chat:message:delta", data: { content: "追加的内容" } }
+
+// 完全替换
+{ type: "chat:message", data: { content: "完整的新内容" } }
+```
+
+## 关键数据来源
+
+| 数据 | 来源 | 说明 |
+|------|------|------|
+| `chat_id` | `body["chat_id"]` | 聊天会话 ID |
+| `message_id` | `body["id"]` | ⚠️ 注意：是 `body["id"]`，不是 `body["message_id"]` |
+| `token` | `localStorage.getItem('token')` | 用户认证 Token |
+| `originalContent` | 通过 API `GET /api/v1/chats/{chatId}` 获取 | 当前消息内容 |
+
+## Python 端 API
+
+| 参数 | 类型 | 说明 |
+|------|------|------|
+| `__event_emitter__` | Callable | 发送状态/通知事件 |
+| `__event_call__` | Callable | 执行 JS 代码（用于可视化渲染） |
+| `__metadata__` | dict | 元数据（可能为 None） |
+| `body` | dict | 请求体，包含 messages、chat_id、id 等 |
+
+### body 结构示例
+
+```json
+{
+  "model": "gemini-3-flash-preview",
+  "messages": [...],
+  "chat_id": "ac2633a3-5731-4944-98e3-bf9b3f0ef0ab",
+  "id": "2e0bb7d4-dfc0-43d7-b028-fd9e06c6fdc8",
+  "session_id": "bX30sHI8r4_CKxCdAAAL"
+}
+```
+
+### 常用事件
+
+```python
+# 发送状态更新
+await __event_emitter__({
+    "type": "status",
+    "data": {"description": "正在渲染...", "done": False}
+})
+
+# 执行 JS 代码
+await __event_call__({
+    "type": "execute",
+    "data": {"code": "console.log('Hello from Python!')"}
+})
+
+# 发送通知
+await __event_emitter__({
+    "type": "notification",
+    "data": {"type": "success", "content": "渲染完成！"}
+})
+```
+
+## 适用场景
+
+- **思维导图** (Markmap)
+- **信息图** (AntV Infographic)
+- **流程图** (Mermaid)
+- **数据图表** (ECharts, Chart.js)
+- **任何需要 JS 渲染的可视化内容**
+
+## 注意事项
+
+### 1. 竞态条件问题
+
+⚠️ **多次快速点击会导致内容覆盖问题**
+
+由于 API 调用是异步的，如果用户快速多次触发 Action：
+- 第一次点击：获取原始内容 A → 渲染 → 更新为 A+图片1
+- 第二次点击：可能获取到旧内容 A（第一次还没保存完）→ 更新为 A+图片2
+
+结果：图片1 被覆盖丢失！
+
+**解决方案**：
+- 添加防抖（debounce）机制
+- 使用锁/标志位防止重复执行
+- 或使用 `chat:message:delta` 增量更新
+
+### 2. 不要直接修改 `body["messages"]`
+
+消息更新应由 JS 通过 API 完成，确保获取最新内容。
+
+### 3. f-string 限制
+
+Python f-string 内不能直接使用反斜杠，需要将转义字符串预先处理：
+
+```python
+# 转义 JSON 中的特殊字符
+body_json = json.dumps(data, ensure_ascii=False)
+escaped = body_json.replace("\\", "\\\\").replace("`", "\\`").replace("${", "\\${")
+```
+
+### 4. Data URI 大小限制
+
+Base64 编码会增加约 33% 的体积，复杂图片可能导致消息过大。
+
+### 5. 跨域问题
+
+确保 CDN 资源支持 CORS。
+
+### 6. API 权限
+
+确保用户 token 有权限访问和更新目标消息。
+
+## 与传统方式对比
+
+| 特性 | 传统方式 (修改 body) | 新方式 (__event_call__) |
+|------|---------------------|------------------------|
+| 消息更新 | Python 直接修改 | JS 通过 API 更新 |
+| 原始内容 | Python 传递给 JS | JS 通过 API 获取 |
+| 灵活性 | 低 | 高 |
+| 实时性 | 一次性 | 可多次更新 |
+| 复杂度 | 简单 | 中等 |
+| 竞态风险 | 低 | ⚠️ 需要处理 |
--- a/docs/plugins/actions/export-to-word.md
+++ b/docs/plugins/actions/export-to-word.md
@@ -1,9 +1,9 @@
 # Export to Word

 <span class="category-badge action">Action</span>
-<span class="version-badge">v0.1.0</span>
+<span class="version-badge">v0.2.0</span>

-Export chat conversations to Word (.docx) with Markdown formatting, syntax highlighting, and smarter filenames.
+Export conversation to Word (.docx) with **syntax highlighting**, **native math equations**, **Mermaid diagrams**, **citations**, and **enhanced table formatting**.

 ---

@@ -13,11 +13,17 @@ The Export to Word plugin converts chat messages from Markdown to a polished Wor

 ## Features

- :material-file-word-box: **DOCX Export**: Generate Word files with one click
- :material-format-bold: **Rich Markdown Support**: Headings, bold/italic, lists, tables
- :material-code-tags: **Syntax Highlighting**: Pygments-powered code blocks
- :material-format-quote-close: **Styled Blockquotes**: Left-border gray quote styling
- :material-file-document-outline: **Smart Filenames**: Configurable title source (Chat Title, AI Generated, or Markdown Title)
+- :material-file-word-box: **One-Click Export**: Adds an "Export to Word" action button to the chat.
+- :material-format-bold: **Markdown Conversion**: Converts Markdown syntax to Word formatting (headings, bold, italic, code, tables, lists).
+- :material-code-tags: **Syntax Highlighting**: Code blocks are highlighted with Pygments (supports 500+ languages).
+- :material-sigma: **Native Math Equations**: LaTeX math (`$$...$$`, `\[...\]`, `$...$`, `\(...\)`) converted to editable Word equations.
+- :material-graph: **Mermaid Diagrams**: Mermaid flowcharts and sequence diagrams rendered as images in the document.
+- :material-book-open-page-variant: **Citations & References**: Auto-generates a References section from OpenWebUI sources with clickable citation links.
+- :material-brain-off: **Reasoning Stripping**: Automatically removes AI thinking blocks (`<think>`, `<analysis>`) from exports.
+- :material-table: **Enhanced Tables**: Smart column widths, column alignment (`:---`, `---:`, `:---:`), header row repeat across pages.
+- :material-format-quote-close: **Blockquote Support**: Markdown blockquotes are rendered with left border and gray styling.
+- :material-translate: **Multi-language Support**: Properly handles both Chinese and English text.
+- :material-file-document-outline: **Smarter Filenames**: Configurable title source (Chat Title, AI Generated, or Markdown Title).

 ---

@@ -25,9 +31,14 @@ The Export to Word plugin converts chat messages from Markdown to a polished Wor

 You can configure the following settings via the **Valves** button in the plugin settings:

-| Valve          | Description                                                                                 | Default      |
-| :------------- | :------------------------------------------------------------------------------------------ | :----------- |
+| Valve | Description | Default |
+| :--- | :--- | :--- |
 | `TITLE_SOURCE` | Source for document title/filename. Options: `chat_title`, `ai_generated`, `markdown_title` | `chat_title` |
+| `MERMAID_JS_URL` | URL for the Mermaid.js library (for diagram rendering). | `https://cdn.jsdelivr.net/npm/mermaid@10.9.1/dist/mermaid.min.js` |
+| `MERMAID_PNG_SCALE` | Scale factor for Mermaid PNG generation (Resolution). Higher = clearer but larger file size. | `3.0` |
+| `MERMAID_DISPLAY_SCALE` | Scale factor for Mermaid visual size in Word. >1.0 to enlarge, <1.0 to shrink. | `1.5` |
+| `MERMAID_OPTIMIZE_LAYOUT` | Automatically convert LR (Left-Right) flowcharts to TD (Top-Down) for better fit. | `True` |
+| `MERMAID_CAPTIONS_ENABLE` | Enable/disable figure captions for Mermaid diagrams. | `True` |

 ---

@@ -47,31 +58,37 @@ You can configure the following settings via the **Valves** button in the plugin

 ---

-## Supported Markdown
+## Supported Markdown Syntax

-| Syntax                              | Word Result                    |
-| :---------------------------------- | :----------------------------- |
-| `# Heading 1` to `###### Heading 6` | Heading levels 1-6             |
-| `**bold**` / `__bold__`             | Bold text                      |
-| `*italic*` / `_italic_`             | Italic text                    |
-| `***bold italic***`                 | Bold + Italic                  |
-| `` `inline code` ``                 | Monospace with gray background |
-| <code>``` code block ```</code>     | Syntax-highlighted code block  |
-| `> blockquote`                      | Left-bordered gray italic text |
-| `[link](url)`                       | Blue underlined link           |
-| `~~strikethrough~~`                 | Strikethrough                  |
-| `- item` / `* item`                 | Bullet list                    |
-| `1. item`                           | Numbered list                  |
-| Markdown tables                     | Grid table                     |
-| `---` / `***`                       | Horizontal rule                |
+| Syntax | Word Result |
+| :--- | :--- |
+| `# Heading 1` to `###### Heading 6` | Heading levels 1-6 |
+| `**bold**` or `__bold__` | Bold text |
+| `*italic*` or `_italic_` | Italic text |
+| `***bold italic***` | Bold + Italic |
+| `` `inline code` `` | Monospace with gray background |
+| ` ``` code block ``` ` | **Syntax highlighted** code block |
+| `> blockquote` | Left-bordered gray italic text |
+| `[link](url)` | Blue underlined link text |
+| `~~strikethrough~~` | Strikethrough text |
+| `- item` or `* item` | Bullet list |
+| `1. item` | Numbered list |
+| Markdown tables | **Enhanced table** with smart widths |
+| `---` or `***` | Horizontal rule |
+| `$$LaTeX$$` or `\[LaTeX\]` | **Native Word equation** (display) |
+| `$LaTeX$` or `\(LaTeX\)` | **Native Word equation** (inline) |
+| ` ```mermaid ... ``` ` | **Mermaid diagram** as image |
+| `[1]` citation markers | **Clickable links** to References |

 ---

 ## Requirements

 !!! note "Prerequisites"
-    - `python-docx==1.1.2` (document generation)
-    - `Pygments>=2.15.0` (syntax highlighting, optional but recommended)
+    - `python-docx==1.1.2` - Word document generation
+    - `Pygments>=2.15.0` - Syntax highlighting
+    - `latex2mathml` - LaTeX to MathML conversion
+    - `mathml2omml` - MathML to Office Math (OMML) conversion

 ---

--- a/docs/plugins/actions/export-to-word.zh.md
+++ b/docs/plugins/actions/export-to-word.zh.md
@@ -1,9 +1,9 @@
 # Export to Word（导出为 Word）

 <span class="category-badge action">Action</span>
-<span class="version-badge">v0.1.0</span>
+<span class="version-badge">v0.2.0</span>

-将聊天记录按 Markdown 格式导出为 Word (.docx)，支持语法高亮、引用样式和更智能的文件命名。
+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。

 ---

@@ -13,11 +13,17 @@ Export to Word 插件会把聊天消息从 Markdown 转成精致的 Word 文档

 ## 功能特性

- :material-file-word-box: **DOCX 导出**：一键生成 Word 文件
- :material-format-bold: **丰富 Markdown 支持**：标题、粗斜体、列表、表格
- :material-code-tags: **语法高亮**：Pygments 驱动的代码块上色
- :material-format-quote-close: **引用样式**：左侧边框的灰色斜体引用
- :material-file-document-outline: **智能文件名**：可配置标题来源（对话标题、AI 生成或 Markdown 标题）
+- :material-file-word-box: **一键导出**：在聊天界面添加"导出为 Word"动作按钮。
+- :material-format-bold: **Markdown 转换**：将 Markdown 语法转换为 Word 格式（标题、粗体、斜体、代码、表格、列表）。
+- :material-code-tags: **代码语法高亮**：使用 Pygments 库为代码块添加语法高亮（支持 500+ 种语言）。
+- :material-sigma: **原生数学公式**：LaTeX 公式（`$$...$$`、`\[...\]`、`$...$`、`\(...\)`）转换为可编辑的 Word 公式。
+- :material-graph: **Mermaid 图表**：Mermaid 流程图和时序图渲染为文档中的图片。
+- :material-book-open-page-variant: **引用与参考**：自动从 OpenWebUI 来源生成参考资料章节，支持可点击的引用链接。
+- :material-brain-off: **移除思考过程**：自动移除 AI 思考块（`<think>`、`<analysis>`）。
+- :material-table: **增强表格**：智能列宽、列对齐（`:---`、`---:`、`:---:`）、表头跨页重复。
+- :material-format-quote-close: **引用块支持**：Markdown 引用块渲染为带左侧边框的灰色斜体样式。
+- :material-translate: **多语言支持**：正确处理中文和英文文本，无乱码问题。
+- :material-file-document-outline: **智能文件名**：可配置标题来源（对话标题、AI 生成或 Markdown 标题）。

 ---

@@ -25,9 +31,14 @@ Export to Word 插件会把聊天消息从 Markdown 转成精致的 Word 文档

 您可以通过插件设置中的 **Valves** 按钮配置以下选项：

-| Valve          | 说明                                                                                                             | 默认值       |
-| :------------- | :--------------------------------------------------------------------------------------------------------------- | :----------- |
+| Valve | 说明 | 默认值 |
+| :--- | :--- | :--- |
 | `TITLE_SOURCE` | 文档标题/文件名的来源。选项：`chat_title` (对话标题), `ai_generated` (AI 生成), `markdown_title` (Markdown 标题) | `chat_title` |
+| `MERMAID_JS_URL` | Mermaid.js 库的 URL（用于图表渲染）。 | `https://cdn.jsdelivr.net/npm/mermaid@10.9.1/dist/mermaid.min.js` |
+| `MERMAID_PNG_SCALE` | Mermaid PNG 生成缩放比例（分辨率）。越高越清晰但文件越大。 | `3.0` |
+| `MERMAID_DISPLAY_SCALE` | Mermaid 在 Word 中的显示比例（视觉大小）。>1.0 放大, <1.0 缩小。 | `1.5` |
+| `MERMAID_OPTIMIZE_LAYOUT` | 优化 Mermaid 布局: 自动将 LR (左右) 转换为 TD (上下) 以适应页面。 | `True` |
+| `MERMAID_CAPTIONS_ENABLE` | 启用/禁用 Mermaid 图表的图注。 | `True` |

 ---

@@ -47,23 +58,27 @@ Export to Word 插件会把聊天消息从 Markdown 转成精致的 Word 文档

 ---

-## 支持的 Markdown
+## 支持的 Markdown 语法

-| 语法                        | Word 效果           |
-| :-------------------------- | :------------------ |
-| `# 标题1` 到 `###### 标题6` | 标题级别 1-6        |
-| `**粗体**` / `__粗体__`     | 粗体文本            |
-| `*斜体*` / `_斜体_`         | 斜体文本            |
-| `***粗斜体***`              | 粗体 + 斜体         |
-| `` `行内代码` ``            | 等宽字体 + 灰色背景 |
-| <code>``` 代码块 ```</code> | 语法高亮代码块      |
-| `> 引用文本`                | 左侧边框的灰色斜体  |
-| `[链接](url)`               | 蓝色下划线链接      |
-| `~~删除线~~`                | 删除线              |
-| `- 项目` / `* 项目`         | 无序列表            |
-| `1. 项目`                   | 有序列表            |
-| Markdown 表格               | 带边框表格          |
-| `---` / `***`               | 水平分割线          |
+| 语法 | Word 效果 |
+| :--- | :--- |
+| `# 标题1` 到 `###### 标题6` | 标题级别 1-6 |
+| `**粗体**` / `__粗体__` | 粗体文本 |
+| `*斜体*` / `_斜体_` | 斜体文本 |
+| `***粗斜体***` | 粗体 + 斜体 |
+| `` `行内代码` `` | 等宽字体 + 灰色背景 |
+| <code>``` 代码块 ```</code> | 语法高亮代码块 |
+| `> 引用文本` | 左侧边框的灰色斜体 |
+| `[链接](url)` | 蓝色下划线链接 |
+| `~~删除线~~` | 删除线 |
+| `- 项目` / `* 项目` | 无序列表 |
+| `1. 项目` | 有序列表 |
+| Markdown 表格 | **增强表格**（智能列宽） |
+| `---` / `***` | 水平分割线 |
+| `$$LaTeX$$` 或 `\[LaTeX\]` | **原生 Word 公式**（块级） |
+| `$LaTeX$` 或 `\(LaTeX\)` | **原生 Word 公式**（行内） |
+| ` ```mermaid ... ``` ` | **Mermaid 图表**（图片形式） |
+| `[1]` 引用标记 | **可点击链接**到参考资料 |

 ---

@@ -71,7 +86,9 @@ Export to Word 插件会把聊天消息从 Markdown 转成精致的 Word 文档

 !!! note "前置条件"
    - `python-docx==1.1.2`（文档生成）
-    - `Pygments>=2.15.0`（语法高亮，建议安装）
+    - `Pygments>=2.15.0`（语法高亮）
+    - `latex2mathml`（LaTeX 转 MathML）
+    - `mathml2omml`（MathML 转 Office Math）

 ---

--- a/docs/plugins/actions/index.md
+++ b/docs/plugins/actions/index.md
@@ -61,9 +61,9 @@ Actions are interactive plugins that:

    ---

-    Export the current conversation to a formatted Word doc with syntax highlighting, AI-generated titles, and perfect Markdown rendering (tables, quotes, lists).
-
-    **Version:** 0.1.1
+    Export the current conversation to a formatted Word doc with **syntax highlighting**, **native math equations**, **Mermaid diagrams**, **citations**, and **enhanced table formatting**.
+    
+    **Version:** 0.2.0

    [:octicons-arrow-right-24: Documentation](export-to-word.md)

--- a/docs/plugins/actions/index.zh.md
+++ b/docs/plugins/actions/index.zh.md
@@ -61,9 +61,9 @@ Actions 是交互式插件，能够：

    ---

-    将当前对话导出为完美格式的 Word 文档，支持代码语法高亮、AI 智能标题生成以及表格、引用等 Markdown 元素的精准渲染。
+    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：** 0.1.1
+    **版本：** 0.2.0

    [:octicons-arrow-right-24: 查看文档](export-to-word.md)

--- a/plugins/actions/ACTION_PLUGIN_TEMPLATE.py
+++ b/plugins/actions/ACTION_PLUGIN_TEMPLATE.py
@@ -315,7 +315,7 @@ class Action:
                    if role == "user"
                    else "Assistant" if role == "assistant" else role
                )
-                aggregated_parts.append(f"[{role_label} Message {i}]\n{text_content}")
+                aggregated_parts.append(f"{text_content}")

        if not aggregated_parts:
            return body  # Or handle error
--- a/plugins/actions/ACTION_PLUGIN_TEMPLATE_CN.py
+++ b/plugins/actions/ACTION_PLUGIN_TEMPLATE_CN.py
@@ -326,7 +326,7 @@ class Action:
                    if role == "user"
                    else "助手" if role == "assistant" else role
                )
-                aggregated_parts.append(f"[{role_label} 消息 {i}]\n{text_content}")
+                aggregated_parts.append(f"{text_content}")

        if not aggregated_parts:
            return body  # 或者处理错误
--- a/plugins/actions/export_to_docx/README.md
+++ b/plugins/actions/export_to_docx/README.md
@@ -75,6 +75,14 @@ All dependencies are declared in the plugin docstring.

 ## Changelog

+### v0.3.0
+
+- **Mermaid Diagrams**: Native support for rendering Mermaid diagrams as images in Word.
+- **Native Math**: Converts LaTeX equations to native Office MathML for editable equations.
+- **Citations**: Automatic bibliography generation and citation linking.
+- **Reasoning Removal**: Option to strip `<think>` blocks from the output.
+- **Table Enhancements**: Improved table formatting with smart column widths.
+
 ### v0.2.0
 - Added native math equation support (LaTeX → OMML)
 - Added Mermaid diagram rendering
--- a/plugins/actions/export_to_docx/README_CN.md
+++ b/plugins/actions/export_to_docx/README_CN.md
@@ -75,6 +75,14 @@

 ## 更新日志

+### v0.3.0
+
+- **Mermaid 图表**: 原生支持将 Mermaid 图表渲染为 Word 中的图片。
+- **原生公式**: 将 LaTeX 公式转换为原生 Office MathML，支持在 Word 中编辑。
+- **引用参考**: 自动生成参考文献列表并链接引用。
+- **移除推理**: 选项支持从输出中移除 `<think>` 推理块。
+- **表格增强**: 改进表格格式，支持智能列宽。
+
 ### v0.2.0
 - 新增原生数学公式支持（LaTeX → OMML）
 - 新增 Mermaid 图表渲染
--- a/plugins/actions/export_to_docx/export_to_word.py
+++ b/plugins/actions/export_to_docx/export_to_word.py
@@ -3,7 +3,7 @@ title: Export to Word
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.2.0
+version: 0.3.0
 icon_url: data:image/svg+xml;base64,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
 requirements: python-docx==1.1.2, latex2mathml, mathml2omml
 description: Export conversation to Word (.docx) with syntax highlighting, native math equations (LaTeX), Mermaid diagrams, citations, and enhanced table formatting.
@@ -158,6 +158,10 @@ class Action:
    ):
        logger.info(f"action:{__name__}")

+        # Reset counters for new request
+        self._mermaid_figure_counter = 0
+        self._bookmark_id_counter = 1
+
        # Parse user info
        if isinstance(__user__, (list, tuple)):
            user_language = (
--- a/plugins/actions/export_to_docx/export_to_word_cn.py
+++ b/plugins/actions/export_to_docx/export_to_word_cn.py
@@ -3,7 +3,7 @@ title: 导出为 Word
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.2.0
+version: 0.3.0
 icon_url: data:image/svg+xml;base64,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
 requirements: python-docx==1.1.2, Pygments>=2.15.0, latex2mathml, mathml2omml
 description: 将对话导出为 Word (.docx)，支持代码高亮、原生数学公式 (LaTeX)、Mermaid 图表、引用参考和增强表格格式。
@@ -158,6 +158,10 @@ class Action:
    ):
        logger.info(f"action:{__name__}")

+        # Reset counters for new request
+        self._mermaid_figure_counter = 0
+        self._bookmark_id_counter = 1
+
        # 解析用户信息
        if isinstance(__user__, (list, tuple)):
            user_language = (
@@ -1019,8 +1023,22 @@ class Action:
                            attrs=code_block_attrs,
                            source=code_text,
                        )
-                        # 插入占位符
-                        self._insert_mermaid_placeholder(doc, block)
+                        # Handle Mermaid diagram
+                        if code_block_lang == "mermaid":
+                            # Optimize layout if enabled
+                            if self.valves.MERMAID_OPTIMIZE_LAYOUT:
+                                # Replace LR with TD for graph and flowchart
+                                code_text = re.sub(
+                                    r"^(graph|flowchart)\s+LR\b",
+                                    r"\1 TD",
+                                    code_text,
+                                    flags=re.MULTILINE | re.IGNORECASE,
+                                )
+
+                            self._insert_mermaid_placeholder(doc, code_text)
+                        else:
+                            # Insert Placeholder using the block object
+                            self._insert_mermaid_placeholder(doc, block)
                    else:
                        self.add_code_block(doc, code_text, code_block_lang)

--- a/plugins/actions/flash-card/README.md
+++ b/plugins/actions/flash-card/README.md
@@ -48,3 +48,9 @@ GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
 ## License

 MIT License
+
+## Changelog
+
+### v0.2.4
+
+- Removed debug messages from output
--- a/plugins/actions/flash-card/README_CN.md
+++ b/plugins/actions/flash-card/README_CN.md
@@ -48,3 +48,9 @@ GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
 ## 许可证

 MIT License
+
+## 更新日志
+
+### v0.2.4
+
+- 移除输出中的调试信息
--- a/plugins/actions/flash-card/flash_card.py
+++ b/plugins/actions/flash-card/flash_card.py
@@ -3,7 +3,7 @@ title: Flash Card
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.2.3
+version: 0.2.4
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPjxwb2x5Z29uIHBvaW50cz0iMTIgMiAyIDcgMTIgMTIgMjIgNyAxMiAyIi8+PHBvbHlsaW5lIHBvaW50cz0iMiAxNyAxMiAyMiAyMiAxNyIvPjxwb2x5bGluZSBwb2ludHM9IjIgMTIgMTIgMTcgMjIgMTIiLz48L3N2Zz4=
 description: Quickly generates beautiful flashcards from text, extracting key points and categories.
 """
@@ -147,7 +147,7 @@ class Action:
                    if role == "user"
                    else "Assistant" if role == "assistant" else role
                )
-                aggregated_parts.append(f"[{role_label} Message {i}]\n{text_content}")
+                aggregated_parts.append(f"{text_content}")

        if not aggregated_parts:
            return body
--- a/plugins/actions/flash-card/flash_card_cn.py
+++ b/plugins/actions/flash-card/flash_card_cn.py
@@ -3,7 +3,7 @@ title: 闪记卡 (Flash Card)
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.2.3
+version: 0.2.4
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPjxwb2x5Z29uIHBvaW50cz0iMTIgMiAyIDcgMTIgMTIgMjIgNyAxMiAyIi8+PHBvbHlsaW5lIHBvaW50cz0iMiAxNyAxMiAyMiAyMiAxNyIvPjxwb2x5bGluZSBwb2ludHM9IjIgMTIgMTIgMTcgMjIgMTIiLz48L3N2Zz4=
 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。
 """
@@ -144,7 +144,7 @@ class Action:
                    if role == "user"
                    else "助手" if role == "assistant" else role
                )
-                aggregated_parts.append(f"[{role_label} 消息 {i}]\n{text_content}")
+                aggregated_parts.append(f"{text_content}")

        if not aggregated_parts:
            return body
--- a/plugins/actions/infographic/README.md
+++ b/plugins/actions/infographic/README.md
@@ -63,3 +63,9 @@ data
 ## 📄 License

 MIT License
+
+## Changelog
+
+### v1.3.2
+
+- Removed debug messages from output
--- a/plugins/actions/infographic/README_CN.md
+++ b/plugins/actions/infographic/README_CN.md
@@ -63,3 +63,9 @@ data
 ## 📄 许可证

 MIT License
+
+## 更新日志
+
+### v1.3.2
+
+- 移除输出中的调试信息
--- a/plugins/actions/infographic/infographic.py
+++ b/plugins/actions/infographic/infographic.py
@@ -3,7 +3,7 @@ title: 📊 Smart Infographic (AntV)
 author: jeff
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPgogIDxsaW5lIHgxPSIxMiIgeTE9IjIwIiB4Mj0iMTIiIHkyPSIxMCIgLz4KICA8bGluZSB4MT0iMTgiIHkxPSIyMCIgeDI9IjE4IiB5Mj0iNCIgLz4KICA8bGluZSB4MT0iNiIgeTE9IjIwIiB4Mj0iNiIgeTI9IjE2IiAvPgo8L3N2Zz4=
-version: 1.3.1
+version: 1.3.2
 description: AI-powered infographic generator based on AntV Infographic. Supports professional templates, auto-icon matching, and SVG/PNG downloads.
 """

@@ -961,9 +961,7 @@ class Action:
                        if role == "user"
                        else "Assistant" if role == "assistant" else role
                    )
-                    aggregated_parts.append(
-                        f"[{role_label} Message {i}]\n{text_content}"
-                    )
+                    aggregated_parts.append(f"{text_content}")

            if not aggregated_parts:
                raise ValueError("Unable to get valid user message content.")
--- a/plugins/actions/infographic/infographic_cn.py
+++ b/plugins/actions/infographic/infographic_cn.py
@@ -3,7 +3,7 @@ title: 📊 智能信息图 (AntV Infographic)
 author: jeff
 author_url: https://github.com/Fu-Jie/awesome-openwebui
 icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIyNCIgaGVpZ2h0PSIyNCIgdmlld0JveD0iMCAwIDI0IDI0IiBmaWxsPSJub25lIiBzdHJva2U9ImN1cnJlbnRDb2xvciIgc3Ryb2tlLXdpZHRoPSIyIiBzdHJva2UtbGluZWNhcD0icm91bmQiIHN0cm9rZS1saW5lam9pbj0icm91bmQiPgogIDxsaW5lIHgxPSIxMiIgeTE9IjIwIiB4Mj0iMTIiIHkyPSIxMCIgLz4KICA8bGluZSB4MT0iMTgiIHkxPSIyMCIgeDI9IjE4IiB5Mj0iNCIgLz4KICA8bGluZSB4MT0iNiIgeTE9IjIwIiB4Mj0iNiIgeTI9IjE2IiAvPgo8L3N2Zz4=
-version: 1.3.1
+version: 1.3.2
 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。
 """

@@ -1026,7 +1026,7 @@ class Action:
                        if role == "user"
                        else "助手" if role == "assistant" else role
                    )
-                    aggregated_parts.append(f"[{role_label} 消息 {i}]\n{text_content}")
+                    aggregated_parts.append(f"{text_content}")

            if not aggregated_parts:
                raise ValueError("无法获取有效的用户消息内容。")
--- a/plugins/actions/js-render-poc/js_render_poc.py
+++ b/plugins/actions/js-render-poc/js_render_poc.py
@@ -0,0 +1,257 @@
+"""
+title: JS Render PoC
+author: Fu-Jie
+version: 0.6.0
+description: Proof of concept for JS rendering + API write-back pattern. JS renders SVG and updates message via API.
+"""
+
+import time
+import json
+import logging
+from typing import Optional, Callable, Awaitable, Any
+from pydantic import BaseModel, Field
+from fastapi import Request
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+class Action:
+    class Valves(BaseModel):
+        pass
+
+    def __init__(self):
+        self.valves = self.Valves()
+
+    def _extract_chat_id(self, body: dict, metadata: Optional[dict]) -> str:
+        """Extract chat_id from body or metadata"""
+        if isinstance(body, dict):
+            # body["chat_id"] 是 chat_id
+            chat_id = body.get("chat_id")
+            if isinstance(chat_id, str) and chat_id.strip():
+                return chat_id.strip()
+
+            body_metadata = body.get("metadata", {})
+            if isinstance(body_metadata, dict):
+                chat_id = body_metadata.get("chat_id")
+                if isinstance(chat_id, str) and chat_id.strip():
+                    return chat_id.strip()
+
+        if isinstance(metadata, dict):
+            chat_id = metadata.get("chat_id")
+            if isinstance(chat_id, str) and chat_id.strip():
+                return chat_id.strip()
+
+        return ""
+
+    def _extract_message_id(self, body: dict, metadata: Optional[dict]) -> str:
+        """Extract message_id from body or metadata"""
+        if isinstance(body, dict):
+            # body["id"] 是 message_id
+            message_id = body.get("id")
+            if isinstance(message_id, str) and message_id.strip():
+                return message_id.strip()
+
+            body_metadata = body.get("metadata", {})
+            if isinstance(body_metadata, dict):
+                message_id = body_metadata.get("message_id")
+                if isinstance(message_id, str) and message_id.strip():
+                    return message_id.strip()
+
+        if isinstance(metadata, dict):
+            message_id = metadata.get("message_id")
+            if isinstance(message_id, str) and message_id.strip():
+                return message_id.strip()
+
+        return ""
+
+    async def action(
+        self,
+        body: dict,
+        __user__: dict = None,
+        __event_emitter__=None,
+        __event_call__: Optional[Callable[[Any], Awaitable[None]]] = None,
+        __metadata__: Optional[dict] = None,
+        __request__: Request = None,
+    ) -> dict:
+        """
+        PoC: Use __event_call__ to execute JS that renders SVG and updates message via API.
+        """
+        # 准备调试数据
+        body_for_log = {}
+        for k, v in body.items():
+            if k == "messages":
+                body_for_log[k] = f"[{len(v)} messages]"
+            else:
+                body_for_log[k] = v
+
+        body_json = json.dumps(body_for_log, ensure_ascii=False, default=str)
+        metadata_json = (
+            json.dumps(__metadata__, ensure_ascii=False, default=str)
+            if __metadata__
+            else "null"
+        )
+
+        # 转义 JSON 中的特殊字符以便嵌入 JS
+        body_json_escaped = (
+            body_json.replace("\\", "\\\\").replace("`", "\\`").replace("${", "\\${")
+        )
+        metadata_json_escaped = (
+            metadata_json.replace("\\", "\\\\")
+            .replace("`", "\\`")
+            .replace("${", "\\${")
+        )
+
+        chat_id = self._extract_chat_id(body, __metadata__)
+        message_id = self._extract_message_id(body, __metadata__)
+
+        unique_id = f"poc_{int(time.time() * 1000)}"
+
+        if __event_emitter__:
+            await __event_emitter__(
+                {
+                    "type": "status",
+                    "data": {"description": "🔄 正在渲染...", "done": False},
+                }
+            )
+
+        if __event_call__:
+            await __event_call__(
+                {
+                    "type": "execute",
+                    "data": {
+                        "code": f"""
+(async function() {{
+    const uniqueId = "{unique_id}";
+    const chatId = "{chat_id}";
+    const messageId = "{message_id}";
+    
+    // ===== DEBUG: 输出 Python 端的数据 =====
+    console.log("[JS Render PoC] ===== DEBUG INFO (from Python) =====");
+    console.log("[JS Render PoC] body:", `{body_json_escaped}`);
+    console.log("[JS Render PoC] __metadata__:", `{metadata_json_escaped}`);
+    console.log("[JS Render PoC] Extracted: chatId=", chatId, "messageId=", messageId);
+    console.log("[JS Render PoC] =========================================");
+    
+    try {{
+        console.log("[JS Render PoC] Starting SVG render...");
+        
+        // Create SVG
+        const svg = document.createElementNS("http://www.w3.org/2000/svg", "svg");
+        svg.setAttribute("width", "200");
+        svg.setAttribute("height", "200");
+        svg.setAttribute("viewBox", "0 0 200 200");
+        svg.setAttribute("xmlns", "http://www.w3.org/2000/svg");
+        
+        const defs = document.createElementNS("http://www.w3.org/2000/svg", "defs");
+        const gradient = document.createElementNS("http://www.w3.org/2000/svg", "linearGradient");
+        gradient.setAttribute("id", "grad-" + uniqueId);
+        gradient.innerHTML = `
+            <stop offset="0%" style="stop-color:#1e88e5;stop-opacity:1" />
+            <stop offset="100%" style="stop-color:#43a047;stop-opacity:1" />
+        `;
+        defs.appendChild(gradient);
+        svg.appendChild(defs);
+        
+        const circle = document.createElementNS("http://www.w3.org/2000/svg", "circle");
+        circle.setAttribute("cx", "100");
+        circle.setAttribute("cy", "100");
+        circle.setAttribute("r", "80");
+        circle.setAttribute("fill", `url(#grad-${{uniqueId}})`);
+        svg.appendChild(circle);
+        
+        const text = document.createElementNS("http://www.w3.org/2000/svg", "text");
+        text.setAttribute("x", "100");
+        text.setAttribute("y", "105");
+        text.setAttribute("text-anchor", "middle");
+        text.setAttribute("fill", "white");
+        text.setAttribute("font-size", "16");
+        text.setAttribute("font-weight", "bold");
+        text.textContent = "PoC Success!";
+        svg.appendChild(text);
+        
+        // Convert to Base64 Data URI
+        const svgData = new XMLSerializer().serializeToString(svg);
+        const base64 = btoa(unescape(encodeURIComponent(svgData)));
+        const dataUri = "data:image/svg+xml;base64," + base64;
+        
+        console.log("[JS Render PoC] SVG rendered, data URI length:", dataUri.length);
+        
+        // Call API - 完全替换方案（更稳定）
+        if (chatId && messageId) {{
+            const token = localStorage.getItem("token");
+            
+            // 1. 获取当前消息内容
+            const getResponse = await fetch(`/api/v1/chats/${{chatId}}`, {{
+                method: "GET",
+                headers: {{ "Authorization": `Bearer ${{token}}` }}
+            }});
+            
+            if (!getResponse.ok) {{
+                throw new Error("Failed to get chat data: " + getResponse.status);
+            }}
+            
+            const chatData = await getResponse.json();
+            console.log("[JS Render PoC] Got chat data");
+            
+            let originalContent = "";
+            if (chatData.chat && chatData.chat.messages) {{
+                const targetMsg = chatData.chat.messages.find(m => m.id === messageId);
+                if (targetMsg && targetMsg.content) {{
+                    originalContent = targetMsg.content;
+                    console.log("[JS Render PoC] Found original content, length:", originalContent.length);
+                }}
+            }}
+            
+            // 2. 移除已存在的 PoC 图片（如果有的话）
+            // 匹配 ![JS Render PoC 生成的 SVG](data:...) 格式
+            const pocImagePattern = /\\n*!\\[JS Render PoC[^\\]]*\\]\\(data:image\\/svg\\+xml;base64,[^)]+\\)/g;
+            let cleanedContent = originalContent.replace(pocImagePattern, "");
+            // 移除可能残留的多余空行
+            cleanedContent = cleanedContent.replace(/\\n{{3,}}/g, "\\n\\n").trim();
+            
+            if (cleanedContent !== originalContent) {{
+                console.log("[JS Render PoC] Removed existing PoC image(s)");
+            }}
+            
+            // 3. 添加新的 Markdown 图片
+            const markdownImage = `![JS Render PoC 生成的 SVG](${{dataUri}})`;
+            const newContent = cleanedContent + "\\n\\n" + markdownImage;
+            
+            // 3. 使用 chat:message 完全替换
+            const updateResponse = await fetch(`/api/v1/chats/${{chatId}}/messages/${{messageId}}/event`, {{
+                method: "POST",
+                headers: {{
+                    "Content-Type": "application/json",
+                    "Authorization": `Bearer ${{token}}`
+                }},
+                body: JSON.stringify({{
+                    type: "chat:message",
+                    data: {{ content: newContent }}
+                }})
+            }});
+            
+            if (updateResponse.ok) {{
+                console.log("[JS Render PoC] ✅ Message updated successfully!");
+            }} else {{
+                console.error("[JS Render PoC] API error:", updateResponse.status, await updateResponse.text());
+            }}
+        }} else {{
+            console.warn("[JS Render PoC] ⚠️ Missing chatId or messageId, cannot persist.");
+        }}
+        
+    }} catch (error) {{
+        console.error("[JS Render PoC] Error:", error);
+    }}
+}})();
+                        """
+                    },
+                }
+            )
+
+        if __event_emitter__:
+            await __event_emitter__(
+                {"type": "status", "data": {"description": "✅ 渲染完成", "done": True}}
+            )
+
+        return body
--- a/plugins/actions/smart-mind-map/README.md
+++ b/plugins/actions/smart-mind-map/README.md
@@ -1,6 +1,6 @@
 # Smart Mind Map - Mind Mapping Generation Plugin

-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.8.0 | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.8.2 | **License:** MIT

 > **Important**: To ensure the maintainability and usability of all plugins, each plugin should be accompanied by clear and comprehensive documentation to ensure its functionality, configuration, and usage are well explained.

@@ -277,7 +277,11 @@ This plugin uses only OpenWebUI's built-in dependencies. **No additional package

 ## Changelog

-### v0.8.0 (Current Version)
+### v0.8.2
+
+- Removed debug messages from output
+
+### v0.8.0 (Previous Version)

 **Major Features:**

--- a/plugins/actions/smart-mind-map/README_CN.md
+++ b/plugins/actions/smart-mind-map/README_CN.md
@@ -1,6 +1,6 @@
 # 思维导图 - 思维导图生成插件

-**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 0.8.0 | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 0.8.2 | **许可证:** MIT

 > **重要提示**：为了确保所有插件的可维护性和易用性，每个插件都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。

@@ -277,7 +277,11 @@

 ## 更新日志

-### v0.8.0（当前版本）
+### v0.8.2
+
+- 移除输出中的调试信息
+
+### v0.8.0 (Previous Version)

 **主要功能：**

--- a/plugins/actions/smart-mind-map/smart_mind_map.py
+++ b/plugins/actions/smart-mind-map/smart_mind_map.py
@@ -3,7 +3,7 @@ title: Smart Mind Map
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.8.1
+version: 0.8.2
 icon_url: data:image/svg+xml;base64,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
 description: Intelligently analyzes text content and generates interactive mind maps to help users structure and visualize knowledge.
 """
@@ -960,7 +960,7 @@ class Action:
                    if role == "user"
                    else "Assistant" if role == "assistant" else role
                )
-                aggregated_parts.append(f"[{role_label} Message {i}]\n{text_content}")
+                aggregated_parts.append(f"{text_content}")

        if not aggregated_parts:
            error_message = "Unable to retrieve valid user message content."
--- a/plugins/actions/smart-mind-map/smart_mind_map_cn.py
+++ b/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
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.8.1
+version: 0.8.2
 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。
 """
@@ -957,7 +957,7 @@ class Action:
                    if role == "user"
                    else "助手" if role == "assistant" else role
                )
-                aggregated_parts.append(f"[{role_label} 消息 {i}]\n{text_content}")
+                aggregated_parts.append(f"{text_content}")

        if not aggregated_parts:
            error_message = "无法获取有效的用户消息内容。"
--- a/plugins/actions/summary/README.md
+++ b/plugins/actions/summary/README.md
@@ -22,3 +22,9 @@ GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
 ## License

 MIT License
+
+## Changelog
+
+### v0.1.2
+
+- Removed debug messages from output
--- a/plugins/actions/summary/README_CN.md
+++ b/plugins/actions/summary/README_CN.md
@@ -22,3 +22,9 @@ GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
 ## 许可证

 MIT License
+
+## 更新日志
+
+### v0.1.2
+
+- 移除输出中的调试信息
--- a/plugins/actions/summary/summary.py
+++ b/plugins/actions/summary/summary.py
@@ -3,7 +3,7 @@ title: Deep Reading & Summary
 author: Fu-Jie
 author_url: https://github.com/Fu-Jie
 funding_url: https://github.com/Fu-Jie/awesome-openwebui
-version: 0.1.1
+version: 0.1.2
 icon_url: data:image/svg+xml;base64,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
 description: Provides deep reading analysis and summarization for long texts.
 requirements: jinja2, markdown
@@ -529,9 +529,7 @@ class Action:
                        if role == "user"
                        else "Assistant" if role == "assistant" else role
                    )
-                    aggregated_parts.append(
-                        f"[{role_label} Message {i}]\n{text_content}"
-                    )
+                    aggregated_parts.append(f"{text_content}")

            if not aggregated_parts:
                raise ValueError("Unable to get valid user message content.")
--- a/plugins/actions/summary/summary_cn.py
+++ b/plugins/actions/summary/summary_cn.py
@@ -1,7 +1,7 @@
 """
 title: 精读 (Deep Reading)
 icon_url: data:image/svg+xml;base64,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
-version: 0.1.1
+version: 0.1.2
 description: 深度分析长篇文本，提炼详细摘要、关键信息点和可执行的行动建议，适合工作和学习场景。
 requirements: jinja2, markdown
 """
@@ -528,7 +528,7 @@ class Action:
                        if role == "user"
                        else "助手" if role == "assistant" else role
                    )
-                    aggregated_parts.append(f"[{role_label} 消息 {i}]\n{text_content}")
+                    aggregated_parts.append(f"{text_content}")

            if not aggregated_parts:
                raise ValueError("无法获取有效的用户消息内容。")
Author	SHA1	Message	Date
fujie	28d55c1469	feat: 添加 JavaScript 渲染 PoC，支持通过 API 更新消息内容	2026-01-05 09:01:42 +08:00
fujie	59933e9361	docs: 更新插件安装指南，增加OpenWebUI社区推荐安装方式。	2026-01-05 00:31:18 +08:00
fujie	7cbd0e2920	chore: release export-to-word v0.3.0	2026-01-04 03:17:35 +08:00
fujie	88038b35cc	chore: release plugins (remove debug messages)	2026-01-04 03:14:28 +08:00
fujie	1fd7d90284	fix: sync mermaid layout optimization to cn plugin	2026-01-04 02:44:33 +08:00
fujie	aee9c93bfb	docs: update documentation for Export to Word plugin (v0.2.0)	2026-01-04 02:40:46 +08:00