chore: improve build scripts; change esm dir

chore(deps-dev): bump typescript-eslint from 8.49.0 to 8.50.0 in the development-dependencies group

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -6,32 +6,11 @@ body:
   - type: markdown
     attributes:
       value: |
-        Please follow our community communication guidelines when filing issues.
-        - Be polite and respectful.
-        - Prefer constructive, actionable feedback over venting.
-        - Include clear reproduction steps and environment details.
-        - Consider contributing a fix if possible — PRs are welcome.
+        Thanks for your interest in improving the project! Before submitting, please read our guidelines.
+        感谢您对改进项目的兴趣！提交前请阅读我们的指南。
 
-        提交 Issue 时请遵守社区沟通规范：
-        - 保持礼貌与尊重。
-        - 提供建设性、可行动的反馈，避免情绪化表达。
-        - 请包含清晰的复现步骤与环境信息。
-        - 如果可以，欢迎直接提交修复 PR。
-
-        See: CODE_OF_CONDUCT.md / CODE_OF_CONDUCT_zh.md, CONTRIBUTING.md
-
-  - type: checkboxes
-    id: community
-    attributes:
-      label: Community Communication / 社区沟通
-      description: Confirm you will communicate respectfully and constructively / 确认将以礼貌、建设性的方式沟通
-      options:
-        - label: I will be polite and respectful. / 我会保持礼貌与尊重。
-          required: true
-        - label: I will share constructive, actionable details. / 我会提供建设性、可行动的细节。
-          required: true
-        - label: I have read the Code of Conduct. / 我已阅读行为准则。
-          required: true
+        - [Code of Conduct](https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT.md)
+        - [Contributing Guide](https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md)
 
   - type: textarea
     id: description
@@ -48,7 +27,7 @@ body:
       render: typescript
       placeholder: Minimal reproduction code
     validations:
-      required: true
+      required: false
 
   - type: input
     id: browser
@@ -56,7 +35,7 @@ body:
       label: Browser
       placeholder: 'Chrome 120, Firefox 119, etc.'
     validations:
-      required: true
+      required: false
 
   - type: input
     id: version
@@ -64,4 +43,19 @@ body:
       label: version
       placeholder: '0.0.0'
     validations:
-      required: true
+      required: false
+
+  - type: checkboxes
+    id: community
+    attributes:
+      label: Community Communication / 社区沟通
+      description: Confirm you will communicate respectfully and constructively / 确认将以礼貌、建设性的方式沟通
+      options:
+        - label: I will be polite and respectful. / 我会保持礼貌与尊重。
+          required: true
+        - label: I will share constructive, actionable suggestions. / 我会提供建设性、可行动的建议。
+          required: true
+        - label: I have read the Code of Conduct. / 我已阅读行为准则。
+          required: true
+    validations:
+      required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -12,6 +12,3 @@ contact_links:
   - name: Code of Conduct / 行为准则
     url: https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT.md
     about: Community expectations and standards. 社区行为期望与标准。
-  - name: 行为准则（中文）
-    url: https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT_zh.md
-    about: 中文版社区行为准则。

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -6,19 +6,30 @@ body:
   - type: markdown
     attributes:
       value: |
-        Please follow our community communication guidelines when proposing features.
-        - Be polite and respectful.
-        - Explain the problem first, then propose solutions.
-        - Prefer constructive, actionable suggestions.
-        - Contributions are encouraged — consider opening a PR.
+        Thanks for your interest in improving the project! Before submitting, please read our guidelines.
+        感谢您对改进项目的兴趣！提交前请阅读我们的指南。
 
-        提交功能建议时请遵守社区沟通规范：
-        - 保持礼貌与尊重。
-        - 先阐述问题，再提出解决方案。
-        - 提供建设性、可行动的建议。
-        - 鼓励代码贡献，欢迎直接提交 PR。
+        - [Code of Conduct](https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT.md)
+        - [Contributing Guide](https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md)
 
-        See: CODE_OF_CONDUCT.md / CODE_OF_CONDUCT_zh.md, CONTRIBUTING.md
+  - type: textarea
+    id: description
+    attributes:
+      label: Feature Description / 功能描述
+      description: Describe the problem, solution, and any API changes. / 描述问题、解决方案以及 API 变更。
+      placeholder: |
+        **Problem**:
+        What problem does this solve?
+
+        **Solution**:
+        How should this work?
+
+        **Proposed API**:
+        ```typescript
+        // code here
+        ```
+    validations:
+      required: true
 
   - type: checkboxes
     id: community
@@ -32,27 +43,5 @@ body:
           required: true
         - label: I have read the CODE_OF_CONDUCT.md and CONTRIBUTING.md. / 我已阅读行为准则。
           required: true
-
-  - type: textarea
-    id: problem
-    attributes:
-      label: Problem
-      placeholder: What problem does this solve?
     validations:
-      required: true
-
-  - type: textarea
-    id: solution
-    attributes:
-      label: Solution
-      placeholder: How should this work?
-    validations:
-      required: true
-
-  - type: textarea
-    id: api
-    attributes:
-      label: Proposed API
-      render: typescript
-    validations:
-      required: false
+      required: true

.github/PULL_REQUEST_TEMPLATE.md

@@ -5,9 +5,12 @@ Brief description of changes.
 ## Type
 
 - [ ] Bug fix
-- [ ] New feature
-- [ ] Breaking change
+- [ ] Feature / Improvement
+- [ ] Refactor
 - [ ] Documentation
+- [ ] Website
+- [ ] Demo / Testing
+- [ ] Breaking change
 
 ## Testing
 
@@ -19,10 +22,4 @@ Closes #(issue)
 
 ## Requirements / 要求
 
-- [ ] I will be polite and respectful. / 我会保持礼貌与尊重。
-- [ ] My comments and replies are constructive and actionable. / 我的评论与回复具有建设性。
 - [ ] I have read and follow the [Code of Conduct](CODE_OF_CONDUCT.md) and [Contributing Guide](CONTRIBUTING.md) . / 我已阅读并遵守行为准则。
-
-## Contributing / 贡献
-
-Constructive suggestions and code contributions are encouraged. If this PR originated from a discussion or issue, please link it above. 欢迎建设性意见与代码贡献；如源自讨论或 Issue，请在上方关联链接。

.github/workflows/ci.yml

@@ -13,10 +13,10 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        node-version: [20, 22]
+        node-version: [20, 24, 25]
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
 
       - name: Setup Node.js ${{ matrix.node-version }}
         uses: actions/setup-node@v6
@@ -24,6 +24,13 @@ jobs:
           node-version: ${{ matrix.node-version }}
           cache: 'npm'
 
+      # test on default version of npm
+      # - 9.6~10.8 on node@20
+      # - 11.3~11.6 on node@24
+
+      - name: Node and NPM version
+        run: node --version && npm --version
+
       - name: Install dependencies
         run: npm install
 

.github/workflows/deploy-demo.yml

@@ -13,19 +13,19 @@ jobs:
       id-token: write
 
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
 
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: 20
+          node-version: 24
           cache: 'npm'
 
       - name: Install dependencies
         run: npm ci
 
       - name: Build demo
-        run: npm run build
+        run: npm run build:website
 
       - name: Setup Pages
         uses: actions/configure-pages@v5
@@ -33,7 +33,7 @@ jobs:
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v4
         with:
-          path: './dist'
+          path: './packages/website/dist'
 
       - name: Deploy to GitHub Pages
         id: deployment

.github/workflows/release.yml

@@ -13,12 +13,12 @@ jobs:
   release:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
 
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
-          node-version: 20
+          node-version: 24
           registry-url: 'https://registry.npmjs.org'
 
       # Ensure npm 11.5.1 or later is installed
@@ -29,7 +29,7 @@ jobs:
         run: npm ci
 
       - name: Build
-        run: npm run build:lib
+        run: npm run build:libs
 
-      - name: Publish to npm
-        run: npm publish
+      - name: Publish all public packages
+        run: npm publish --workspaces --access public

.gitignore

@@ -23,7 +23,13 @@ dist-ssr
 *.njsproj
 *.sln
 *.sw?
+.qoder
 
 
 # 
-.env
+.env
+
+# Copied files for npm publish (generated by prepublishOnly)
+packages/page-agent/README.md
+packages/page-agent/README-zh.md
+packages/page-agent/LICENSE

.husky/pre-commit

@@ -1 +1 @@
-npx lint-staged
+npx lint-staged --allow-empty

.vscode/extensions.json

@@ -1,3 +1,3 @@
 {
-	"recommendations": ["dbaeumer.vscode-eslint", "esbenp.prettier-vscode"]
+	"recommendations": ["dbaeumer.vscode-eslint", "prettier.prettier-vscode"]
 }

.vscode/settings.json

@@ -1,6 +1,6 @@
 {
 	"editor.fontLigatures": true,
-	"cSpell.words": ["HITL", "opensource", "retryable"],
+	"cSpell.words": ["HITL", "innerhtml", "opensource", "retryable", "wouter"],
 	"markdownlint.config": {
 		// "comment": "Relaxed rules",
 		"default": true,

AGENTS.md

@@ -2,56 +2,106 @@
 
 ## Project Overview
 
-This is a dual-architecture project with **two separate parts**:
+This is a **monorepo** with npm workspaces containing **two main packages**:
 
-1. **Core Library** (`src/`) - Pure JavaScript/TypeScript AI agent library for browser DOM automation
-2. **Demo&docs Website** (`pages/`) - React documentation and landing page
+1. **Core Library** (`packages/page-agent/`) - Pure JavaScript/TypeScript AI agent library for browser DOM automation, published as `page-agent` on npm
+2. **Website** (`packages/website/`) - React documentation and landing page. Also as demo and test page for the core lib. private package `@page-agent/website`
+
+And other internal packages:
+
+- **Page Controller** (`packages/page-controller/`) - DOM operations and element interactions. Independent of LLM.
+- **UI** (`packages/ui/`) - Panel, SimulatorMask, and i18n. Decoupled from PageAgent.
 
 ## Development Commands
 
 ### Core Commands
 
 ```bash
-npm start                    # Start React website development server
-npm run build                # Build both library AND website
-npm run build:lib            # Build pure JS library only (src/ → dist/lib/)
-npm run build:lib:watch      # Library development with auto-rebuild
+npm start                    # Start website dev server
+npm run build                # Build all packages
+npm run build:libs           # Build all libraries
+npm run build:website        # Build the website
 npm run lint                 # ESLint with TypeScript strict rules
 ```
 
 ## Architecture & Critical Patterns
 
-### Dual Build System
+### Monorepo Structure
 
-- **Website build**: `vite.config.js` → React SPA with hash routing → `dist/`
-- **Library build**: `vite.lib.config.js` → UMD/ES modules → `dist/lib/`
-- **Entry points**: `src/entry.ts` (library), `pages/main.tsx` (website)
+We adopt a very simple monorepo solution: ts reference + vite alias. 
+
+You must update tsconfig and vite config if you add/remove/rename a package.
+
+```bash
+packages/
+├── page-agent/              # npm: "page-agent" ⭐ MAIN
+│   ├── src/
+│   │   ├── PageAgent.ts     # Main AI agent class
+│   │   ├── tools/           # LLM tool definitions
+│   │   └── llms/            # LLM integration
+│   ├── vite.config.js       # Library build (ES + UMD)
+│   └── package.json
+├── website/                 # npm: "@page-agent/website" (private) ⭐ MAIN
+│   ├── src/                 # Website source
+│   └── index.html           # Entry of vite webpage
+│
+│   # ...internal packages below...
+│
+├── page-controller/         # npm: "@page-agent/page-controller"
+│   └── src/                 # DOM operations
+│       ├── PageController.ts
+│       ├── actions.ts
+│       └── dom/
+└── ui/                      # npm: "@page-agent/ui"
+    └── src/                 # Panel and Mask Effects
+        ├── Panel.ts
+        ├── SimulatorMask.ts
+        └── i18n/
+```
+
+`workspaces` must be written in topological order to guarantee build order.
+
+```json
+"workspaces": [
+    // internal deps (topological order)
+    "packages/page-controller",
+    "packages/ui",
+    "packages/page-agent",
+    "packages/website"
+],
+```
 
 ### Module Boundaries (Critical)
 
-- **Core library** (`src/`): NEVER import from `pages/` - must remain pure JavaScript
-- **Website** (`pages/`): CAN import from `src/` via `@/` alias for demos
-- **Import aliases**: `@/` → `src/`, `@pages/` → `pages/`
+- **Website** (`packages/website/`): CAN import from `page-agent` for demos. Alias `@/` → `website/src/`
+- **Page Agent** (`packages/page-agent/`): The core lib. Imports from `@page-agent/page-controller` and `@page-agent/ui`.
+- **UI** (`packages/ui/`): Panel, Mask, i18n. No dependency on page-agent.
+- **Page Controller** (`packages/page-controller/`): Pure DOM operations. No LLM or UI dependency.
+
+### PageController ↔ PageAgent Communication
+
+All communication between PageAgent and PageController is async and isolated:
+
+```typescript
+// PageAgent delegates DOM operations to PageController
+await this.pageController.updateTree()        // Refresh DOM state
+await this.pageController.clickElement(index) // Click by index
+await this.pageController.inputText(index, text)
+await this.pageController.scroll({ down: true, numPages: 1 })
+
+// PageController exposes state via async methods
+const simplifiedHTML = await this.pageController.getSimplifiedHTML()
+const pageInfo = await this.pageController.getPageInfo()
+```
+
+DOM element references and internal state (selectorMap, elementTextMap) are encapsulated in PageController.
 
 ### DOM Pipeline
 
-1. **DOM Extraction**: Convert live DOM to `FlatDomTree` via `src/dom/dom_tree/`
+1. **DOM Extraction**: Convert live DOM to `FlatDomTree` via `page-controller/src/dom/dom_tree/`
 2. **Dehydration**: DOM tree → simplified text for LLM processing
-3. **LLM Processing**: AI model returns action plans
-4. **Indexed Operations**: Map LLM responses back to specific DOM elements
-
-### Event Bus Communication
-
-Use `src/utils/bus.ts` for decoupled PageAgent ↔ UI communication:
-
-```typescript
-// Emit from PageAgent
-getEventBus().emit('panel:show')
-getEventBus().emit('panel:update', { status: 'thinking' })
-
-// Listen in UI components
-getEventBus().on('panel:show', () => panel.show())
-```
+3. **LLM Processing**: AI model returns action plans (in page-agent)
+4. **Indexed Operations**: PageAgent calls PageController methods by element index
 
 ### Hash Routing Requirement
 
@@ -71,47 +121,59 @@ Library auto-initializes when injected via script tag:
 
 Query params configure `PageAgentConfig` automatically in `src/entry.ts`.
 
-## File Organization
+## Key Files Reference
 
-### Core Library (`src/`)
+### Page Agent (`packages/page-agent/`)
 
-- `entry.ts` - CDN/UMD entry point with auto-initialization
-- `PageAgent.ts` - **Main AI agent class** orchestrating DOM operations
-- `tools/` - Agent tool implementations for web actions
-- `ui/` - UI components (Panel, SimulatorMask) with CSS modules
-- `utils/bus.ts` - **Type-safe event bus** for decoupled communication
-- `patches/` - Framework-specific optimizations (React, Antd compatibility)
-- `llms/` - LLM integration and communication layer
-- `dom/` - HTML serialization and page analysis utilities
-- `config/` - Configuration constants and settings
+| File | Description |
+|------|-------------|
+| `src/PageAgent.ts` | ⭐ Main AI agent class orchestrating tools and LLM |
+| `src/umd.ts` | CDN/UMD entry point with auto-initialization |
+| `src/tools/` | Tool definitions that call PageController methods |
+| `src/llms/` | LLM integration and communication layer |
+| `vite.config.js` | Library build configuration (ES + UMD) |
 
-### Website (`pages/`)
+### Page Controller (`packages/page-controller/`)
 
-- `main.tsx` - Site entry with hash routing setup
-- `router.tsx` - **Manual route definitions** (requires explicit registration)
-- `components/DocsLayout.tsx` - Navigation structure (hardcoded nav items)
-- `docs/[section]/[topic]/page.tsx` - Documentation pages
-- `test-pages/` - Library integration test pages
+| File | Description |
+|------|-------------|
+| `src/PageController.ts` | ⭐ Main controller class managing DOM state and actions |
+| `src/actions.ts` | Element interaction implementations (click, input, scroll) |
+| `src/dom/dom_tree/index.js` | Core DOM extraction engine (ported from browser-use) |
+| `src/dom/getPageInfo.ts` | Page scroll/size information |
+| `src/patches/` | Framework-specific optimizations (React, Antd) |
+| `src/types.ts` | TypeScript interfaces for controller |
+
+### Website (`packages/website/`)
+
+| File | Description |
+|------|-------------|
+| `src/router.tsx` | ⭐ Central routing (manual registration required) |
+| `src/components/DocsLayout.tsx` | Navigation structure (hardcoded nav items) |
+| `src/main.tsx` | Site entry with hash routing setup |
+| `src/docs/[section]/[topic]/page.tsx` | Documentation pages |
+| `src/test-pages/` | Library integration test pages |
+| `vite.config.js` | Website build configuration |
 
 ## Adding New Features
 
 ### New Documentation Page
 
-1. Create `pages/docs/<section>/<slug>/page.tsx`
-2. Add route to `pages/router.tsx` with `<Header /> + <DocsLayout>` wrapper
+1. Create `packages/website/src/docs/<section>/<slug>/page.tsx`
+2. Add route to `packages/website/src/router.tsx` with `<Header /> + <DocsLayout>` wrapper
 3. Add navigation item to `DocsLayout.tsx`
 
 ### New Agent Tool
 
-1. Implement under `src/tools/`
-2. Export via `src/tools/index.ts`
-3. Wire into `PageAgent.ts` if needed
+1. Implement tool in `packages/page-agent/src/tools/index.ts`
+2. If tool needs DOM operations, add method to PageController first
+3. Tool calls `this.pageController.methodName()` for DOM interactions
 
-### New UI Component
+### New PageController Action
 
-1. Create in `src/ui/` with colocated CSS modules
-2. Use event bus for PageAgent communication
-3. Test via `pages/test-pages/`
+1. Add action implementation in `packages/page-controller/src/actions.ts`
+2. Expose via async method in `PageController.ts`
+3. Export from `packages/page-controller/src/index.ts`
 
 ## Code Standards
 
@@ -134,28 +196,17 @@ Query params configure `PageAgentConfig` automatically in `src/entry.ts`.
 - Relative imports last
 - Blank lines between groups
 
-## Critical Files to Understand
-
-- `pages/router.tsx` - Central routing definition (manual registration required)
-- `pages/components/DocsLayout.tsx` - Navigation structure
-- `src/PageAgent.ts` - Core AI agent class with DOM manipulation
-- `src/dom/dom_tree/index.js` - DOM extraction engine
-- `src/utils/bus.ts` - Type-safe event bus system
-- `src/entry.ts` - Library entry point for CDN usage
-- `vite.config.js` / `vite.lib.config.js` - Dual build configuration
-
 ## Debugging Common Issues
 
 ### Blank Documentation Pages
 
-1. Verify route exists in `pages/router.tsx`
+1. Verify route exists in `packages/website/src/router.tsx`
 2. Check component import path
 3. Verify CSS isn't hiding content (check dark mode classes)
 4. Test with minimal component first
 
 ### Library Integration Issues
 
-1. Check `dist/lib/page-agent.umd.js` builds correctly
+1. Check `packages/page-agent/dist/lib/page-agent.umd.js` builds correctly
 2. Test CDN injection with query params
-3. Verify event bus communications are properly typed
-4. Use `pages/test-pages/` for isolated testing
+4. Use `packages/website/src/test-pages/` for isolated testing

CONTRIBUTING.md

@@ -7,11 +7,9 @@ Thank you for your interest in contributing to Page-Agent! We welcome contributi
 ### Development Setup
 
 1. **Prerequisites**
-   - Node.js 20+
-   - npm 10+
-   - typescript as required in package.json
-   - vscode or other editors that support ts/eslint/prettier
-   - make sure `eslint`, `auto-format` and `commit-lint` all work
+   - `node.js >= 20` with `npm >= 10`
+   - An editor that supports `ts/eslint/prettier`
+   - Make sure `eslint`, `prettier` and `commitlint` work well
 
 2. **Setup**
 
@@ -22,10 +20,16 @@ Thank you for your interest in contributing to Page-Agent! We welcome contributi
 
 ### Project Structure
 
-This project has **two separate parts**:
+This is a **monorepo** with npm workspaces containing **two main packages**:
 
-- **Core Library** (`src/`) - Pure JavaScript AI agent library
-- **Documentation Website** (`pages/`) - React web app for landing page and docs
+1. **Core Library** (`packages/page-agent/`) - Pure JavaScript/TypeScript AI agent library for browser DOM automation, published as `page-agent` on npm
+2. **Website** (`packages/website/`) - React documentation and landing page. Also as demo and test page for the core lib. private package `@page-agent/website`
+
+We use a simplified monorepo solution with `native npm-workspace + ts reference + vite alias`. No fancy tooling. Hoisting is required. 
+
+- When developing. Use alias so that we don't have to pre-build.
+- When bundling. Use external and disable ts `paths` alias to leave deps out.
+- When bundling `UMD` and `Website`. Bundle everything including local packages.
 
 ## 🤝 How to Contribute
 
@@ -95,19 +99,6 @@ This project has **two separate parts**:
    - Github Copilot: `./.github/copilot-instructions.md`
    - Claude Code: `./CLAUDE.md`
 
-### Core Library (`src/`)
-
-- **No React dependencies** - Pure JavaScript/TypeScript only
-- Use event bus for component communication
-- Follow browser-use patterns for DOM operations
-
-### Doc&demo Site (`pages/`)
-
-- Use React 19 + TypeScript
-- Follow hash routing patterns (`useHashLocation`)
-- Use Tailwind CSS for styling
-- Add new docs pages to both router and sidebar
-
 ## 🔧 Development Workflows
 
 ### Website Development
@@ -118,24 +109,26 @@ npm start                # React development server
 
 ### Core Lib Development and Testing
 
+> @TODO this part is outdated. Update this.
+
 - Config your LLM API
-- Start a local script
+- Start and serve a local umd script
 
    ```bash
-   npm run build:lib:watch    # Auto-rebuild on changes
+   npm run dev:umd # Serving UMD with auto rebuild at http://localhost:5173/page-agent.umd.cjs
    ```
 
 - Add a new bookmark enable it on other website
 
    ```
-   javascript:(function(){var s=document.createElement('script');s.src=`http://localhost:5173/dist/lib/page-agent.umd.cjs?t=${Math.random()}`;s.onload=()=>console.log(%27PageAgent ready!%27);document.head.appendChild(s);})();
+   javascript:(function(){var s=document.createElement('script');s.src=`http://localhost:5173/page-agent.umd.cjs?t=${Math.random()}`;s.onload=()=>console.log(%27PageAgent ready!%27);document.head.appendChild(s);})();
    ```
 
 ### Adding Documentation
 
-1. Create `pages/docs/section/page-name/page.tsx`
-2. Add route to `pages/router.tsx`
-3. Add navigation link to `pages/components/DocsLayout.tsx`
+1. Create `website/src/docs/section/page-name/page.tsx`
+2. Add route to `website/src/router.tsx`
+3. Add navigation link to `website/src/components/DocsLayout.tsx`
 
 ## 🎯 Contribution Areas
 

README-zh.md

@@ -4,13 +4,13 @@
 
 [![npm version](https://badge.fury.io/js/page-agent.svg)](https://badge.fury.io/js/page-agent) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/%3C%2F%3E-TypeScript-%230074c1.svg)](http://www.typescriptlang.org/) [![Downloads](https://img.shields.io/npm/dt/page-agent.svg)](https://www.npmjs.com/package/page-agent) [![Bundle Size](https://img.shields.io/bundlephobia/minzip/page-agent)](https://bundlephobia.com/package/page-agent) [![GitHub stars](https://img.shields.io/github/stars/alibaba/page-agent.svg)](https://github.com/alibaba/page-agent)
 
-**让你的网页支持 AI 自动化。**
-
-运行在页面内的 UI agent. 使用自然语言操作 Web 应用。
+纯 JS 实现的 GUI agent。使用自然语言操作你的 Web 应用。无须后端、客户端、浏览器插件。
 
 🌐 [English](./README.md) | **中文**
 
-👉 [🚀 **Demo**](https://alibaba.github.io/page-agent/) | [📖 **Documentation**](https://alibaba.github.io/page-agent/#/docs/introduction/overview)
+👉 <a href="https://alibaba.github.io/page-agent/" target="_blank"><b>🚀 Demo</b></a> | <a href="https://alibaba.github.io/page-agent/#/docs/introduction/overview" target="_blank"><b>📖 Documentation</b></a> 
+
+<video id="demo-video" src="https://github.com/user-attachments/assets/141bbb01-8022-4d1f-919d-9efc9a1dc1cf" width="640" crossorigin muted autoplay loop></video>
 
 ---
 
@@ -33,7 +33,7 @@
 ```html
 <!-- 临时 CDN URL. 未来会变更 -->
 <script
-	src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.2/page-agent.js"
+	src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js"
 	crossorigin="true"
 	type="text/javascript"
 ></script>
@@ -67,16 +67,14 @@ await agent.execute('点击登录按钮')
 
 ## 🏗️ 架构设计
 
-PageAgent 采用清晰的模块化架构：
+PageAgent adopts a simplified monorepo structure:
 
 ```
-src/
-├── PageAgent.ts          # Agent 主流程
-├── dom/                  # DOM 理解
-├── tools/                # 代理交互工具
-├── ui/                   # UI 组件和面板
-├── llms/                 # LLM 集成层
-└── utils/                # 事件总线和工具
+packages/
+├── page-agent/          # AI agent (npm: page-agent)
+├── page-controller/     # DOM 操作 (npm: @page-agent/page-controller)
+├── ui/                  # 面板 & 蒙层 & 模拟鼠标 (npm: @page-agent/ui)
+└── website/             # 文档站点
 ```
 
 ## 🤝 贡献

README.md

@@ -1,22 +1,22 @@
 # PageAgent 🤖🪄
 
-![banner](https://img.alicdn.com/imgextra/i1/O1CN01RY0Wvh26ATVeDIX7v_!!6000000007621-0-tps-1672-512.jpg)
+![banner](https://img.alicdn.com/imgextra/i3/O1CN01MyVCS21EoKkIHUT1s_!!6000000000398-49-tps-1280-353.webp)
 
 [![npm version](https://badge.fury.io/js/page-agent.svg)](https://badge.fury.io/js/page-agent) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/%3C%2F%3E-TypeScript-%230074c1.svg)](http://www.typescriptlang.org/) [![Downloads](https://img.shields.io/npm/dt/page-agent.svg)](https://www.npmjs.com/package/page-agent) [![Bundle Size](https://img.shields.io/bundlephobia/minzip/page-agent)](https://bundlephobia.com/package/page-agent) [![GitHub stars](https://img.shields.io/github/stars/alibaba/page-agent.svg)](https://github.com/alibaba/page-agent)
 
-**Transform your webpage into an AI-powered application with a single script tag.**
-
-An in-page UI agent in javascript. Control web interfaces with natural language.
+The GUI Agent Living in Your Webpage. Control web interfaces with natural language.
 
 🌐 **English** | [中文](./README-zh.md)
 
-👉 [🚀 **Demo**](https://alibaba.github.io/page-agent/) | [📖 **Documentation**](https://alibaba.github.io/page-agent/#/docs/introduction/overview)
+👉 <a href="https://alibaba.github.io/page-agent/" target="_blank"><b>🚀 Demo</b></a> | <a href="https://alibaba.github.io/page-agent/#/docs/introduction/overview" target="_blank"><b>📖 Documentation</b></a> 
+
+<video id="demo-video" src="https://github.com/user-attachments/assets/de8d1964-8bde-494f-a52f-2975469557a5" width="640" crossorigin muted autoplay loop></video>
 
 ---
 
 ## ✨ Features
 
-- **🎯 Easy Integration**
+- **🎯 Easy Integration** - Transform your webpage into an agent with a single script tag.
 - **🔐 Client-Side Processing**
 - **🧠 DOM Extraction**
 - **💬 Natural Language Interface**
@@ -33,7 +33,7 @@ An in-page UI agent in javascript. Control web interfaces with natural language.
 ```html
 <!-- temporary CDN URL. May change in the future -->
 <script
-	src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.2/page-agent.js"
+	src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js"
 	crossorigin="true"
 	type="text/javascript"
 ></script>
@@ -67,16 +67,14 @@ await agent.execute('Click the login button')
 
 ## 🏗️ Structure
 
-PageAgent follows a clean, modular architecture:
+PageAgent adopts a simplified monorepo structure:
 
 ```
-src/
-├── PageAgent.ts          # Agent main loop
-├── dom/                  # DOM processing
-├── tools/                # Agent tools
-├── ui/                   # UI components & panels
-├── llms/                 # LLM integration layer
-└── utils/                # Event bus & utilities
+packages/
+├── page-agent/          # AI agent (npm: page-agent)
+├── page-controller/     # DOM operations (npm: @page-agent/page-controller)
+├── ui/                  # Panel & Mask & Mouse Animation (npm: @page-agent/ui)
+└── website/             # Demo & Documentation site
 ```
 
 ## 🤝 Contributing

ROADMAP.md

@@ -4,39 +4,58 @@ The development progress and future plans for PageAgent.
 
 ## 🚀 Current Works
 
-- [x] **MVP** - Core functionality implemented
-- [x] **SPA interaction** - Single Page Application support
+- [x] **MVP** 
+  - Core functionality implemented.
+- [x] **SPA interaction** 
 - [x] **Reasoning and (short) memory**
 - [x] **Multi model provider integration and testing**
-- [x] **UI with HITL** - Human-in-the-loop user interface
+- [x] **UI with HITL** 
+  - Human-in-the-loop user interface. Agent can ask user questions.
 - [x] **Landing and doc pages**
-- [x] **Remove ai-sdk** - Only one function is being used
+- [x] **Remove `ai-sdk`** 
+  - Only one function of AI-ADK is being used.
+  - Our agent memory and thinking mechanism does not suite ai-sdk.
 - [x] **Robust LLM output**
+  - Auto-fix incomplete output format of DeepSeek and QWen.
 - [x] **Working homepage with live LLM API**
 - [x] **~~free~~ CDN**
-- [x] **Free evaluation plan?**
+- [x] **Free evaluation plan**
 - [x] **Custom actions and HITL**
 - [ ] **Hooks and Events**
   - [x] **lifecycle hooks**
   - [ ] **lifecycle events**
-- [ ] **❗Pause and intervene**
+- [ ] **User takeover** 
+  - [#64](https://github.com/alibaba/page-agent/issues/64)
 - [ ] **❗Hijack `page_open/page_change/page_unload` behavior**
 - [ ] **Custom knowledge base and instructions**
+  - [#45](https://github.com/alibaba/page-agent/issues/45)
 - [ ] **Black/white-list safeguard**
 - [ ] **Data-masking**
+  - [#44](https://github.com/alibaba/page-agent/issues/44)
+- [ ] **Improve Memory**
+  - [#66](https://github.com/alibaba/page-agent/issues/66)
+  - [#65](https://github.com/alibaba/page-agent/issues/65)
 - [ ] **Optimize for popular UI frameworks**
-- [ ] **Testing suits**
-- [ ] **Support custom llm fetch**
-- [ ] **Refactor: Separate Agent and Page-Controller** - Agent should run w/o dom
+- [x] **i18n of the website**
+  - [x] Chinese version
+  - [x] English version
+- [x] **Refactor: Separate `Agent` and `PageController`** 
+- [ ] **Chrome-ext wrapper for multi-page tasks**
 
-♻️ Following browser-use's update and contribute back
+♻️ Following browser-use's update and contribute back.
 
 ## 📋 Pending Features
 
-- [ ] **Chrome-ext wrapper**
+- [ ] **Tools for more complex tasks**
+  - todo list
+  - file sys
+- [ ] **Support custom llm fetch**
+- [ ] **Testing suits**
 - [ ] **Same-origin multi-page-app rally**
 - [ ] **Local MCP proxy**
 
 ## 🤔 To Be Decided
 
-- [ ] **Cross-origin multi-page?** - Tricky
+- [ ] **Cross-origin multi-page?** 
+  - Tricky
+  - Need some kind of "memory rally"

eslint.config.js

@@ -8,7 +8,7 @@ import globals from 'globals'
 import tseslint from 'typescript-eslint'
 
 export default defineConfig([
-	globalIgnores(['dist', 'test-pages']),
+	globalIgnores(['**/dist', '**/test-pages', '**/node_modules']),
 	{
 		plugins: {
 			'react-hooks': reactHooks,
@@ -37,8 +37,10 @@ export default defineConfig([
 		],
 		languageOptions: {
 			parserOptions: {
-				project: ['./tsconfig.json'],
-				tsconfigRootDir: import.meta.dirname,
+				// project: ['./tsconfig.json'],
+				// project: ['./packages/*/tsconfig.json'],
+				// tsconfigRootDir: import.meta.dirname,
+				projectService: true,
 			},
 			ecmaVersion: 2020,
 			globals: globals.browser,
@@ -67,6 +69,9 @@ export default defineConfig([
 			'react-dom/no-missing-button-type': 'off',
 			'react-x/no-nested-component-definitions': 'off',
 			'@typescript-eslint/prefer-optional-chain': 'off',
+
+			// 'require-await': 'off',
+			'@typescript-eslint/require-await': 'off',
 		},
 	},
 ])

index.html

@@ -1,32 +0,0 @@
-<!doctype html>
-<html lang="zh-CN">
-	<head>
-		<meta charset="UTF-8" />
-		<link
-			rel="icon"
-			type="image/svg+xml"
-			href="https://img.alicdn.com/imgextra/i3/O1CN01uo9VaC20mamWNM2Zn_!!6000000006892-55-tps-64-64.svg"
-		/>
-		<meta name="viewport" content="width=device-width, initial-scale=1.0" />
-		<title>PageAgent - 网页内的交互助手</title>
-		<meta
-			name="description"
-			content="PageAgent.js：一行 CDN 引入，为任何网站添加智能 UI Agent。现代网页 AI 自动化，极简集成，开发者专用。"
-		/>
-		<meta
-			name="keywords"
-			content="PageAgent, AI Agent, Web Automation, UI 自动化, 前端, CDN, JavaScript, React, Vite"
-		/>
-		<meta name="theme-color" content="#58c0fc" />
-		<meta name="color-scheme" content="light dark" />
-		<meta name="author" content="PageAgent.js Team" />
-		<meta property="og:title" content="PageAgent.js" />
-		<meta property="og:description" content="一行 CDN 引入，为任何网站添加智能 UI Agent。" />
-		<meta property="og:type" content="website" />
-		<meta property="og:locale" content="zh_CN" />
-	</head>
-	<body>
-		<div id="root"></div>
-		<script type="module" src="./pages/main.tsx"></script>
-	</body>
-</html>

package.json

@@ -1,89 +1,59 @@
 {
-	"name": "page-agent",
-	"private": false,
-	"version": "0.0.3",
+	"name": "root",
+	"private": true,
+	"version": "0.0.11",
 	"type": "module",
-	"main": "./dist/lib/page-agent.js",
-	"module": "./dist/lib/page-agent.js",
-	"types": "./dist/lib/PageAgent.d.ts",
-	"exports": {
-		".": {
-			"types": "./dist/lib/PageAgent.d.ts",
-			"import": "./dist/lib/page-agent.js",
-			"default": "./dist/lib/page-agent.js"
-		}
-	},
-	"files": [
-		"dist/lib/",
-		"README.md",
-		"LICENSE",
-		"NOTICE"
-	],
-	"description": "AI-powered UI agent for web applications - add intelligent automation to any webpage with a single script tag",
-	"keywords": [
-		"ai",
-		"automation",
-		"ui-agent",
-		"browser-automation",
-		"web-agent",
-		"llm",
-		"dom-interaction",
-		"intelligent-ui"
+	"workspaces": [
+		"packages/page-controller",
+		"packages/ui",
+		"packages/page-agent",
+		"packages/website"
 	],
+	"description": "AI-powered UI agent for web applications",
 	"author": "Simon<gaomeng1900>",
 	"license": "MIT",
 	"repository": {
 		"type": "git",
 		"url": "https://github.com/alibaba/page-agent.git"
 	},
+	"homepage": "https://alibaba.github.io/page-agent/",
 	"engines": {
-		"node": ">=20.0.0"
+		"node": ">=20.0.0",
+		"npm": ">=10.0.0"
 	},
 	"scripts": {
-		"dev": "vite",
-		"start": "vite",
-		"build": "tsc -b && vite build && npm run build:lib && npm run build:umd",
-		"build:lib": "MODE=lib vite build",
-		"build:lib:watch": "MODE=lib vite build --watch",
-		"build:umd": "MODE=umd vite build",
+		"start": "npm run dev --workspace=@page-agent/website",
+		"build:website": "npm run build:website --workspace=@page-agent/website",
+		"build:libs": "npm run build --workspaces --if-present",
+		"build": "npm run build:libs && npm run build:website",
+		"dev:umd": "npm run dev:umd --workspace=page-agent",
+		"version": "node scripts/sync-version.js",
 		"lint": "eslint .",
 		"prepare": "husky"
 	},
-	"dependencies": {
-		"ai-motion": "^0.4.7",
-		"chalk": "^5.6.2",
-		"zod": "^4.1.12"
-	},
 	"devDependencies": {
-		"@commitlint/cli": "^20.1.0",
-		"@commitlint/config-conventional": "^20.0.0",
-		"@eslint/js": "^9.37.0",
-		"@microsoft/api-extractor": "^7.53.1",
-		"@tailwindcss/vite": "^4.1.14",
-		"@trivago/prettier-plugin-sort-imports": "^5.2.2",
-		"@types/react": "^19.2.2",
-		"@types/react-dom": "^19.2.1",
-		"@vitejs/plugin-react-swc": "^4.1.0",
+		"@commitlint/cli": "^20.2.0",
+		"@commitlint/config-conventional": "^20.2.0",
+		"@eslint/js": "^9.39.2",
+		"@microsoft/api-extractor": "^7.55.2",
+		"@trivago/prettier-plugin-sort-imports": "^6.0.0",
+		"concurrently": "^9.2.1",
 		"dotenv": "^17.2.3",
-		"eslint": "^9.37.0",
+		"eslint": "^9.39.2",
 		"eslint-config-prettier": "^10.1.8",
-		"eslint-plugin-react-dom": "^2.0.6",
-		"eslint-plugin-react-hooks": "^7.0.0",
-		"eslint-plugin-react-refresh": "^0.4.23",
-		"eslint-plugin-react-x": "^2.0.6",
+		"eslint-plugin-react-dom": "^2.3.13",
+		"eslint-plugin-react-hooks": "^7.0.1",
+		"eslint-plugin-react-refresh": "^0.4.25",
+		"eslint-plugin-react-x": "^2.3.13",
 		"globals": "^16.4.0",
 		"husky": "^9.1.7",
 		"lint-staged": "^16.2.4",
-		"prettier": "^3.6.2",
-		"react": "^19.2.0",
-		"react-dom": "^19.2.0",
-		"tailwindcss": "^4.1.14",
+		"prettier": "^3.7.4",
 		"typescript": "^5.9.3",
-		"typescript-eslint": "^8.46.0",
+		"typescript-eslint": "^8.50.0",
 		"unplugin-dts": "^1.0.0-beta.6",
-		"vite": "^7.1.9",
-		"vite-plugin-css-injected-by-js": "^3.5.2",
-		"wouter": "^3.7.1"
+		"vite": "^7.3.0",
+		"vite-plugin-css-injected-by-js": "^3.5.2"
 	},
 	"lint-staged": {
 		"*.{js,ts,cjs,cts,mjs,mts}": [

packages/page-agent/package.json

@@ -0,0 +1,52 @@
+{
+	"name": "page-agent",
+	"private": false,
+	"version": "0.0.11",
+	"type": "module",
+	"main": "./dist/esm/page-agent.js",
+	"module": "./dist/esm/page-agent.js",
+	"types": "./dist/esm/PageAgent.d.ts",
+	"exports": {
+		".": {
+			"types": "./dist/esm/PageAgent.d.ts",
+			"import": "./dist/esm/page-agent.js",
+			"default": "./dist/esm/page-agent.js"
+		}
+	},
+	"files": [
+		"dist/"
+	],
+	"description": "GUI agent for web applications - add intelligent automation to any webpage with a single script",
+	"keywords": [
+		"ai",
+		"automation",
+		"ui-agent",
+		"GUI-agent",
+		"browser-automation",
+		"web-agent",
+		"llm",
+		"dom-interaction",
+		"web-automation",
+		"GUI-simulation"
+	],
+	"author": "Simon<gaomeng1900>",
+	"license": "MIT",
+	"repository": {
+		"type": "git",
+		"url": "https://github.com/alibaba/page-agent.git"
+	},
+	"homepage": "https://alibaba.github.io/page-agent/",
+	"scripts": {
+		"build": "vite build && MODE=umd vite build",
+		"serve": "npx serve dist/umd -p 5173",
+		"dev:umd": "concurrently \"MODE=umd vite build --watch\" \"npm run serve\"",
+		"prepublishOnly": "node -e \"const fs=require('fs');['README.md','LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
+		"postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+	},
+	"dependencies": {
+		"chalk": "^5.6.2",
+		"zod": "^4.2.0",
+		"@page-agent/page-controller": "0.0.11",
+		"@page-agent/ui": "0.0.11"
+	}
+}

packages/page-agent/src/PageAgent.ts

@@ -2,24 +2,18 @@
  * Copyright (C) 2025 Alibaba Group Holding Limited
  * All rights reserved.
  */
+import { PageController } from '@page-agent/page-controller'
+import { Panel, SimulatorMask } from '@page-agent/ui'
 import chalk from 'chalk'
 import zod from 'zod'
 
 import type { PageAgentConfig } from './config'
-import { MAX_STEPS, VIEWPORT_EXPANSION } from './config/constants'
-import * as dom from './dom'
-import { FlatDomTree, InteractiveElementDomNode } from './dom/dom_tree/type'
-import { getPageInfo } from './dom/getPageInfo'
-import { I18n } from './i18n'
+import { MAX_STEPS } from './config/constants'
 import { LLM, type Tool } from './llms'
-import { patchReact } from './patches/react'
 import SYSTEM_PROMPT from './prompts/system_prompt.md?raw'
 import { tools } from './tools'
-import { Panel, getToolCompletedText, getToolExecutingText } from './ui/Panel'
-import { SimulatorMask } from './ui/SimulatorMask'
 import { trimLines, uid, waitUntil } from './utils'
 import { assert } from './utils/assert'
-import { getEventBus } from './utils/bus'
 
 export type { PageAgentConfig }
 export { tool, type PageAgentTool } from './tools'
@@ -74,8 +68,6 @@ export interface ExecutionResult {
 export class PageAgent extends EventTarget {
 	config: PageAgentConfig
 	id = uid()
-	bus = getEventBus(this.id)
-	i18n: I18n
 	panel: Panel
 	tools: typeof tools
 	paused = false
@@ -86,20 +78,12 @@ export class PageAgent extends EventTarget {
 	#llm: LLM
 	#totalWaitTime = 0
 	#abortController = new AbortController()
+	#llmRetryListener: ((e: Event) => void) | null = null
+	#llmErrorListener: ((e: Event) => void) | null = null
+	#beforeUnloadListener: ((e: Event) => void) | null = null
 
-	/** Corresponds to eval_page in browser-use */
-	flatTree: FlatDomTree | null = null
-	/**
-	 * All highlighted index-mapped interactive elements
-	 * Corresponds to DOMState.selector_map in browser-use
-	 */
-	selectorMap = new Map<number, InteractiveElementDomNode>()
-	/** highlight index -> element text */
-	elementTextMap = new Map<number, string>()
-	/** Corresponds to clickable_elements_to_string in browser-use */
-	simplifiedHTML = '<EMPTY>'
-	/** last time the tree was updated */
-	lastTimeUpdate = 0
+	/** PageController for DOM operations */
+	pageController: PageController
 
 	/** Fullscreen mask */
 	mask = new SimulatorMask()
@@ -110,11 +94,34 @@ export class PageAgent extends EventTarget {
 		super()
 
 		this.config = config
-		this.#llm = new LLM(this.config, this.id)
-		this.i18n = new I18n(this.config.language)
-		this.panel = new Panel(this)
+		this.#llm = new LLM(this.config)
+		this.panel = new Panel({
+			language: this.config.language,
+			onExecuteTask: (task) => this.execute(task),
+			onStop: () => this.dispose(),
+			onPauseToggle: () => {
+				this.paused = !this.paused
+				return this.paused
+			},
+			getPaused: () => this.paused,
+		})
 		this.tools = new Map(tools)
 
+		// Initialize PageController with config
+		this.pageController = new PageController(this.config)
+
+		// Listen to LLM events
+		this.#llmRetryListener = (e) => {
+			const { current, max } = (e as CustomEvent).detail
+			this.panel.update({ type: 'retry', current, max })
+		}
+		this.#llmErrorListener = (e) => {
+			const { error } = (e as CustomEvent).detail
+			this.panel.update({ type: 'error', message: `step failed: ${error.message}` })
+		}
+		this.#llm.addEventListener('retry', this.#llmRetryListener)
+		this.#llm.addEventListener('error', this.#llmErrorListener)
+
 		if (this.config.customTools) {
 			for (const [name, tool] of Object.entries(this.config.customTools)) {
 				if (tool === null) {
@@ -125,11 +132,14 @@ export class PageAgent extends EventTarget {
 			}
 		}
 
-		patchReact(this)
+		if (!this.config.experimentalScriptExecutionTool) {
+			this.tools.delete('execute_javascript')
+		}
 
-		window.addEventListener('beforeunload', (e) => {
+		this.#beforeUnloadListener = (e) => {
 			if (!this.disposed) this.dispose('PAGE_UNLOADING')
-		})
+		}
+		window.addEventListener('beforeunload', this.#beforeUnloadListener)
 	}
 
 	/**
@@ -150,13 +160,10 @@ export class PageAgent extends EventTarget {
 		// Show mask and panel
 		this.mask.show()
 
-		this.bus.emit('panel:show')
-		this.bus.emit('panel:reset')
+		this.panel.show()
+		this.panel.reset()
 
-		this.bus.emit('panel:update', {
-			type: 'input',
-			displayText: this.task,
-		})
+		this.panel.update({ type: 'input', task: this.task })
 
 		if (this.#abortController) {
 			this.#abortController.abort()
@@ -171,7 +178,7 @@ export class PageAgent extends EventTarget {
 			while (true) {
 				await onBeforeStep.call(this, step)
 
-				console.group(`step: ${step + 1}`)
+				console.group(`step: ${step}`)
 
 				// abort
 				if (this.#abortController.signal.aborted) throw new Error('AbortError')
@@ -180,10 +187,7 @@ export class PageAgent extends EventTarget {
 
 				// Update status to thinking
 				console.log(chalk.blue('Thinking...'))
-				this.bus.emit('panel:update', {
-					type: 'thinking',
-					displayText: this.i18n.t('ui.panel.thinking'),
-				})
+				this.panel.update({ type: 'thinking' })
 
 				const result = await this.#llm.invoke(
 					[
@@ -193,7 +197,7 @@ export class PageAgent extends EventTarget {
 						},
 						{
 							role: 'user',
-							content: this.#assembleUserPrompt(),
+							content: await this.#assembleUserPrompt(),
 						},
 					],
 					{ AgentOutput: this.#packMacroTool() },
@@ -313,22 +317,14 @@ export class PageAgent extends EventTarget {
 					`)
 
 				console.log(brain)
-				this.bus.emit('panel:update', {
-					type: 'thinking',
-					displayText: brain,
-				})
+				this.panel.update({ type: 'thinking', text: brain })
 
 				// Find the corresponding tool
 				const tool = tools.get(toolName)
 				assert(tool, `Tool ${toolName} not found. (@note should have been caught before this!!!)`)
 
 				console.log(chalk.blue.bold(`Executing tool: ${toolName}`), toolInput)
-				this.bus.emit('panel:update', {
-					type: 'tool_executing',
-					toolName,
-					toolArgs: toolInput,
-					displayText: getToolExecutingText(toolName, toolInput, this.i18n),
-				})
+				this.panel.update({ type: 'toolExecuting', toolName, args: toolInput })
 
 				const startTime = Date.now()
 
@@ -350,16 +346,13 @@ export class PageAgent extends EventTarget {
 				}
 
 				// Briefly display execution result
-				const displayResult = getToolCompletedText(toolName, toolInput, this.i18n)
-				if (displayResult)
-					this.bus.emit('panel:update', {
-						type: 'tool_executing',
-						toolName,
-						toolArgs: toolInput,
-						toolResult: result,
-						displayText: displayResult,
-						duration,
-					})
+				this.panel.update({
+					type: 'toolCompleted',
+					toolName,
+					args: toolInput,
+					result,
+					duration,
+				})
 
 				// Wait a moment to let user see the result
 				await new Promise((resolve) => setTimeout(resolve, 100))
@@ -388,7 +381,7 @@ export class PageAgent extends EventTarget {
 		return systemPrompt
 	}
 
-	#assembleUserPrompt(): string {
+	async #assembleUserPrompt(): Promise<string> {
 		let prompt = ''
 
 		// <agent_history>
@@ -426,62 +419,65 @@ export class PageAgent extends EventTarget {
 
 		// <browser_state>
 
-		prompt += this.#getBrowserState()
+		prompt += await this.#getBrowserState()
 
 		return trimLines(prompt)
 	}
 
 	#onDone(text: string, success = true) {
-		dom.cleanUpHighlights()
+		this.pageController.cleanUpHighlights()
 
 		// Update panel status
-		this.bus.emit('panel:update', {
-			type: success ? 'output' : 'error',
-			displayText: text,
-		})
+		if (success) {
+			this.panel.update({ type: 'output', text })
+		} else {
+			this.panel.update({ type: 'error', message: text })
+		}
 
 		// Task completed
-		this.bus.emit('panel:update', {
-			type: 'completed',
-			displayText: this.i18n.t('ui.panel.taskCompleted'),
-		})
+		this.panel.update({ type: 'completed' })
 
 		this.mask.hide()
 
 		this.#abortController.abort()
 	}
 
-	#getBrowserState(): string {
-		const pageUrl = window.location.href
-		const pageTitle = document.title
-		const pi = getPageInfo()
+	async #getBrowserState(): Promise<string> {
+		const pageUrl = await this.pageController.getCurrentUrl()
+		const pageTitle = await this.pageController.getPageTitle()
+		const pi = await this.pageController.getPageInfo()
+		const viewportExpansion = await this.pageController.getViewportExpansion()
 
-		this.#updateTree()
+		this.mask.wrapper.style.pointerEvents = 'none'
+		await this.pageController.updateTree()
+		this.mask.wrapper.style.pointerEvents = 'auto'
+
+		const simplifiedHTML = await this.pageController.getSimplifiedHTML()
 
 		let prompt = trimLines(`<browser_state>
 			Current Page: [${pageTitle}](${pageUrl})
 
 			Page info: ${pi.viewport_width}x${pi.viewport_height}px viewport, ${pi.page_width}x${pi.page_height}px total page size, ${pi.pages_above.toFixed(1)} pages above, ${pi.pages_below.toFixed(1)} pages below, ${pi.total_pages.toFixed(1)} total pages, at ${(pi.current_page_position * 100).toFixed(0)}% of page
 
-			${VIEWPORT_EXPANSION === -1 ? 'Interactive elements from top layer of the current page (full page):' : 'Interactive elements from top layer of the current page inside the viewport:'}
+			${viewportExpansion === -1 ? 'Interactive elements from top layer of the current page (full page):' : 'Interactive elements from top layer of the current page inside the viewport:'}
 
 		`)
 
 		// Page header info
 		const has_content_above = pi.pixels_above > 4
-		if (has_content_above && VIEWPORT_EXPANSION !== -1) {
+		if (has_content_above && viewportExpansion !== -1) {
 			prompt += `... ${pi.pixels_above} pixels above (${pi.pages_above.toFixed(1)} pages) - scroll to see more ...\n`
 		} else {
 			prompt += `[Start of page]\n`
 		}
 
 		// Current viewport info
-		prompt += this.simplifiedHTML
+		prompt += simplifiedHTML
 		prompt += `\n`
 
 		// Page footer info
 		const has_content_below = pi.pixels_below > 4
-		if (has_content_below && VIEWPORT_EXPANSION !== -1) {
+		if (has_content_below && viewportExpansion !== -1) {
 			prompt += `... ${pi.pixels_below} pixels below (${pi.pages_below.toFixed(1)} pages) - scroll to see more ...\n`
 		} else {
 			prompt += `[End of page]\n`
@@ -492,42 +488,31 @@ export class PageAgent extends EventTarget {
 		return prompt
 	}
 
-	/**
-	 * Update document tree
-	 */
-	#updateTree() {
-		this.dispatchEvent(new Event('beforeUpdate'))
-		this.lastTimeUpdate = Date.now()
-		dom.cleanUpHighlights()
-		this.mask.wrapper.style.pointerEvents = 'none'
-		this.flatTree = dom.getFlatTree({
-			...this.config,
-			interactiveBlacklist: [
-				...(this.config.interactiveBlacklist || []),
-				...document.querySelectorAll('[data-page-agent-not-interactive]').values(),
-			],
-		})
-		this.mask.wrapper.style.pointerEvents = 'auto'
-		this.simplifiedHTML = dom.flatTreeToString(this.flatTree, this.config.include_attributes)
-		this.selectorMap.clear()
-		this.selectorMap = dom.getSelectorMap(this.flatTree)
-		this.elementTextMap.clear()
-		this.elementTextMap = dom.getElementTextMap(this.simplifiedHTML)
-		this.dispatchEvent(new Event('afterUpdate'))
-	}
-
 	dispose(reason?: string) {
 		console.log('Disposing PageAgent...')
 		this.disposed = true
-		dom.cleanUpHighlights()
-		this.flatTree = null
-		this.selectorMap.clear()
-		this.elementTextMap.clear()
+		this.pageController.dispose()
 		this.panel.dispose()
 		this.mask.dispose()
 		this.history = []
 		this.#abortController.abort(reason ?? 'PageAgent disposed')
 
+		// Clean up LLM event listeners
+		if (this.#llmRetryListener) {
+			this.#llm.removeEventListener('retry', this.#llmRetryListener)
+			this.#llmRetryListener = null
+		}
+		if (this.#llmErrorListener) {
+			this.#llm.removeEventListener('error', this.#llmErrorListener)
+			this.#llmErrorListener = null
+		}
+
+		// Clean up window event listeners
+		if (this.#beforeUnloadListener) {
+			window.removeEventListener('beforeunload', this.#beforeUnloadListener)
+			this.#beforeUnloadListener = null
+		}
+
 		this.config.onDispose?.call(this, reason)
 	}
 }

packages/page-agent/src/config/constants.ts

@@ -1,10 +1,3 @@
-/**
- * @note Since isTopElement depends on elementFromPoint,
- * it returns null when out of viewport, this feature has no practical use, only differ between -1 and 0
- */
-// export const VIEWPORT_EXPANSION = 100
-export const VIEWPORT_EXPANSION = -1
-
 // Dev environment: use .env config if available, otherwise fallback to testing api
 export const DEFAULT_MODEL_NAME: string =
 	import.meta.env.DEV && import.meta.env.LLM_MODEL_NAME

packages/page-agent/src/config/index.ts

@@ -1,8 +1,8 @@
-import type { AgentHistory, ExecutionResult, PageAgent } from '@/PageAgent'
-import type { DomConfig } from '@/dom'
-import type { SupportedLanguage } from '@/i18n'
-import type { PageAgentTool } from '@/tools'
+import type { PageControllerConfig } from '@page-agent/page-controller'
+import type { SupportedLanguage } from '@page-agent/ui'
 
+import type { AgentHistory, ExecutionResult, PageAgent } from '../PageAgent'
+import type { PageAgentTool } from '../tools'
 import {
 	DEFAULT_API_KEY,
 	DEFAULT_BASE_URL,
@@ -72,6 +72,14 @@ export interface AgentConfig {
 
 	// page behavior hooks
 
+	/**
+	 * @experimental
+	 * Enable the experimental script execution tool that allows executing generated JavaScript code on the page.
+	 * @note Can cause unpredictable side effects.
+	 * @note May bypass some safe guards and data-masking mechanisms.
+	 */
+	experimentalScriptExecutionTool?: boolean
+
 	/**
 	 * TODO: @unimplemented
 	 * hook when action causes a new page to be opened
@@ -87,7 +95,7 @@ export interface AgentConfig {
 	experimentalPreventNewPage?: boolean
 }
 
-export type PageAgentConfig = LLMConfig & AgentConfig & DomConfig
+export type PageAgentConfig = LLMConfig & AgentConfig & PageControllerConfig
 
 export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
 	return {

packages/page-agent/src/env.d.ts

@@ -1,5 +1,5 @@
 /// <reference types="vite/client" />
-import type { PageAgent } from './src/PageAgent'
+import type { PageAgent } from './PageAgent'
 
 declare module '*.module.css' {
 	const classes: Record<string, string>
@@ -11,15 +11,10 @@ declare module '*.md?raw' {
 	export default content
 }
 
-/**
- * for local dev and umd demo
- */
-
 declare global {
 	interface Window {
 		pageAgent?: PageAgent
 		PageAgent: typeof PageAgent
-
 		__PAGE_AGENT_IDS__: string[]
 	}
 }

packages/page-agent/src/llms/OpenAILenientClient.ts

@@ -1,8 +1,7 @@
 /**
  * OpenAI Client implementation
  */
-import type { MacroToolInput } from '@/PageAgent'
-
+import type { MacroToolInput } from '../PageAgent'
 import { InvokeError, InvokeErrorType } from './errors'
 import type { InvokeResult, LLMClient, Message, OpenAIClientConfig, Tool } from './types'
 import { lenientParseMacroToolCall, modelPatch, zodToOpenAITool } from './utils'

packages/page-agent/src/llms/index.ts

@@ -31,27 +31,21 @@
  * - 永远使用 tool call 来返回结构化数据，禁止模型直接返回（视为出错）
  * - 不能假设 tool 参数合法，必须有修复机制，而且修复也应该使用 tool call 返回
  */
-import type { LLMConfig } from '@/config'
-import { parseLLMConfig } from '@/config'
-import { EventBus, getEventBus } from '@/utils/bus'
-
+import type { LLMConfig } from '../config'
+import { parseLLMConfig } from '../config'
 import { OpenAIClient } from './OpenAILenientClient'
 import { InvokeError } from './errors'
 import type { InvokeResult, LLMClient, Message, Tool } from './types'
 
 export type { Message, Tool, InvokeResult, LLMClient }
 
-export class LLM {
+export class LLM extends EventTarget {
 	config: Required<LLMConfig>
-	id: string
 	client: LLMClient
-	#bus: EventBus
 
-	constructor(config: LLMConfig, id: string) {
+	constructor(config: LLMConfig) {
+		super()
 		this.config = parseLLMConfig(config)
-		this.id = id
-
-		this.#bus = getEventBus(id)
 
 		// Default to OpenAI client
 		this.client = new OpenAIClient({
@@ -82,17 +76,13 @@ export class LLM {
 			// retry settings
 			{
 				maxRetries: this.config.maxRetries,
-				onRetry: (retries: number) => {
-					this.#bus.emit('panel:update', {
-						type: 'retry',
-						displayText: `retry-ing (${retries} / ${this.config.maxRetries})`,
-					})
+				onRetry: (current: number) => {
+					this.dispatchEvent(
+						new CustomEvent('retry', { detail: { current, max: this.config.maxRetries } })
+					)
 				},
-				onError: (error: Error, withRetry: boolean) => {
-					this.#bus.emit('panel:update', {
-						type: 'error',
-						displayText: `step failed: ${(error as Error).message}`,
-					})
+				onError: (error: Error) => {
+					this.dispatchEvent(new CustomEvent('error', { detail: { error } }))
 				},
 			}
 		)
@@ -104,7 +94,7 @@ async function withRetry<T>(
 	settings: {
 		maxRetries: number
 		onRetry: (retries: number) => void
-		onError: (error: Error, withRetry: boolean) => void
+		onError: (error: Error) => void
 	}
 ): Promise<T> {
 	let retries = 0
@@ -119,7 +109,7 @@ async function withRetry<T>(
 			return await fn()
 		} catch (error: unknown) {
 			console.error(error)
-			settings.onError(error as Error, retries < settings.maxRetries)
+			settings.onError(error as Error)
 
 			// do not retry if aborted by user
 			if ((error as { name?: string })?.name === 'AbortError') throw error

packages/page-agent/src/llms/utils.ts

@@ -4,8 +4,7 @@
 import chalk from 'chalk'
 import { z } from 'zod'
 
-import type { MacroToolInput } from '@/PageAgent'
-
+import type { MacroToolInput } from '../PageAgent'
 import { InvokeError, InvokeErrorType } from './errors'
 import type { Tool } from './types'
 
@@ -42,6 +41,7 @@ export function lenientParseMacroToolCall(
 	// check
 	switch (choice.finish_reason) {
 		case 'tool_calls':
+		case 'function_call': // gemini
 		case 'stop': // will try a robust parse
 			// ✅ Normal
 			break

packages/page-agent/src/tools/index.ts

@@ -4,23 +4,8 @@
  */
 import zod, { type z } from 'zod'
 
-import type { PageAgent } from '@/PageAgent'
-
-import {
-	clickElement,
-	getElementByIndex,
-	getSystemInfo,
-	inputTextElement,
-	scrollHorizontally,
-	scrollVertically,
-	selectOptionElement,
-	waitFor,
-} from './actions'
-// debug
-import * as utils from './actions'
-
-// @ts-expect-error debug only
-window.utils = utils
+import type { PageAgent } from '../PageAgent'
+import { waitFor } from '../utils'
 
 /**
  * Internal tool definition that has access to PageAgent `this` context
@@ -42,18 +27,6 @@ export function tool<TParams>(options: PageAgentTool<TParams>): PageAgentTool<TP
  */
 export const tools = new Map<string, PageAgentTool>()
 
-// tools.set(
-// 	'get_current_html',
-// 	tool({
-// 		description: 'Get the current (updated) simplified HTML of the page',
-// 		inputSchema: zod.object({}),
-// 		execute: function (this: PageAgent) {
-// 			this.updateTree()
-// 			return this.simplifiedHTML
-// 		},
-// 	})
-// )
-
 tools.set(
 	'done',
 	tool({
@@ -80,11 +53,11 @@ tools.set(
 			seconds: zod.number().min(1).max(10).default(1),
 		}),
 		execute: async function (this: PageAgent, input) {
-			const lastTimeUpdate = this.lastTimeUpdate
+			const lastTimeUpdate = await this.pageController.getLastUpdateTime()
 			const actualWaitTime = Math.max(0, input.seconds - (Date.now() - lastTimeUpdate) / 1000)
 			console.log(`actualWaitTime: ${actualWaitTime} seconds`)
 			await waitFor(actualWaitTime)
-			return `✅ Waited for ${input.seconds} seconds.` + (await getSystemInfo())
+			return `✅ Waited for ${input.seconds} seconds.`
 		},
 	})
 )
@@ -99,7 +72,7 @@ tools.set(
 		}),
 		execute: async function (this: PageAgent, input) {
 			const answer = await this.panel.askUser(input.question)
-			return `✅ Received user answer: ${answer}` + (await getSystemInfo())
+			return `✅ Received user answer: ${answer}`
 		},
 	})
 )
@@ -112,16 +85,8 @@ tools.set(
 			index: zod.int().min(0),
 		}),
 		execute: async function (this: PageAgent, input) {
-			const element = getElementByIndex(this, input.index)
-			const elemText = this.elementTextMap.get(input.index)
-			await clickElement(element)
-
-			// @workaround: Handle links that open in new tabs
-			if (element instanceof HTMLAnchorElement && element.target === '_blank') {
-				return `⚠️ Clicked link that opens in a new tab (${elemText ? elemText : input.index}). You are not capable of reading new tabs.`
-			}
-
-			return `✅ Clicked element (${elemText ? elemText : input.index}).` + (await getSystemInfo())
+			const result = await this.pageController.clickElement(input.index)
+			return result.message
 		},
 	})
 )
@@ -135,13 +100,8 @@ tools.set(
 			text: zod.string(),
 		}),
 		execute: async function (this: PageAgent, input) {
-			const element = getElementByIndex(this, input.index)
-			const elemText = this.elementTextMap.get(input.index)
-			await inputTextElement(element, input.text)
-			return (
-				`✅ Input text (${input.text}) into element (${elemText ? elemText : input.index}).` +
-				(await getSystemInfo())
-			)
+			const result = await this.pageController.inputText(input.index, input.text)
+			return result.message
 		},
 	})
 )
@@ -156,13 +116,8 @@ tools.set(
 			text: zod.string(),
 		}),
 		execute: async function (this: PageAgent, input) {
-			const element = getElementByIndex(this, input.index)
-			const elemText = this.elementTextMap.get(input.index)
-			await selectOptionElement(element as HTMLSelectElement, input.text)
-			return (
-				`✅ Selected option (${input.text}) in element (${elemText ? elemText : input.index}).` +
-				(await getSystemInfo())
-			)
+			const result = await this.pageController.selectOption(input.index, input.text)
+			return result.message
 		},
 	})
 )
@@ -182,13 +137,11 @@ tools.set(
 			index: zod.number().int().min(0).optional(),
 		}),
 		execute: async function (this: PageAgent, input) {
-			const { down, num_pages, index, pixels } = input
-
-			const scroll_amount = pixels ? pixels : num_pages * (down ? 1 : -1) * window.innerHeight
-
-			const element = index !== undefined ? getElementByIndex(this, index) : null
-
-			return (await scrollVertically(down, scroll_amount, element)) + (await getSystemInfo())
+			const result = await this.pageController.scroll({
+				...input,
+				numPages: input.num_pages,
+			})
+			return result.message
 		},
 	})
 )
@@ -204,13 +157,23 @@ tools.set(
 			index: zod.number().int().min(0).optional(),
 		}),
 		execute: async function (this: PageAgent, input) {
-			const { right, pixels, index } = input
+			const result = await this.pageController.scrollHorizontally(input)
+			return result.message
+		},
+	})
+)
 
-			const scroll_amount = pixels * (right ? 1 : -1)
-
-			const element = index !== undefined ? getElementByIndex(this, index) : null
-
-			return (await scrollHorizontally(right, scroll_amount, element)) + (await getSystemInfo())
+tools.set(
+	'execute_javascript',
+	tool({
+		description:
+			'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution!',
+		inputSchema: zod.object({
+			script: zod.string(),
+		}),
+		execute: async function (this: PageAgent, input) {
+			const result = await this.pageController.executeJavascript(input.script)
+			return result.message
 		},
 	})
 )

packages/page-agent/src/umd.ts

@@ -37,4 +37,4 @@ if (currentScript) {
 
 console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
 
-window.pageAgent.bus.emit('panel:show') // Show panel
+window.pageAgent.panel.show() // Show panel

packages/page-agent/src/utils/bus.ts

@@ -1,30 +1,9 @@
-/**
- * Type-safe event bus for decoupling PageAgent and Panel
- */
-import type { Step } from '@/ui/UIState'
-
 /**
  * Event mapping definitions
  * @note Event bus callbacks must be repeatable without errors
  */
 export interface PageAgentEventMap {
-	// Panel control events
-	// call panel.show()
-	'panel:show': { params: undefined }
-	// call panel.hide()
-	'panel:hide': { params: undefined }
-	// call panel.reset()
-	'panel:reset': { params: undefined }
-	// call panel.update()
-	'panel:update': { params: Omit<Step, 'id' | 'stepNumber' | 'timestamp'> }
-	// call panel.expand()
-	'panel:expand': { params: undefined }
-	// call panel.collapse()
-	'panel:collapse': { params: undefined }
-
 	// PageAgent status events
-	// 'agent:beforeUpdate': { params: undefined }
-	// 'agent:afterUpdate': { params: undefined }
 	// 'agent:execute': { params: { task: string } }
 	// 'agent:done': { params: { text: string; success: boolean } }
 	// 'agent:paused': { params: undefined }
@@ -33,8 +12,7 @@ export interface PageAgentEventMap {
 	// 'agent:error': { params: { error: string | Error } }
 
 	// Task status change events
-	// 'task:start': { params: { task: string } }
-	// 'task:step': { params: Omit<AgentStep, 'id' | 'stepNumber' | 'timestamp'> }
+	'task:start': { params: { task: string } }
 	// 'task:complete': { params: { text: string; success: boolean } }
 	// 'task:error': { params: { error: string | Error } }
 
@@ -69,10 +47,7 @@ class EventBus extends EventTarget {
 	/**
 	 * Listen to built-in events
 	 */
-	on<T extends keyof PageAgentEventMap>(
-		event: T,
-		handler: EventHandler<T & keyof PageAgentEventMap>
-	): void {
+	on<T extends keyof PageAgentEventMap>(event: T, handler: EventHandler<T>): void {
 		const wrappedHandler = (e: Event) => {
 			const customEvent = e as CustomEvent
 			const params = customEvent.detail?.[0]
@@ -84,10 +59,7 @@ class EventBus extends EventTarget {
 	/**
 	 * Listen to built-in events (one-time)
 	 */
-	once<T extends keyof PageAgentEventMap>(
-		event: T,
-		handler: EventHandler<T & keyof PageAgentEventMap>
-	): void {
+	once<T extends keyof PageAgentEventMap>(event: T, handler: EventHandler<T>): void {
 		const wrappedHandler = (e: Event) => {
 			const customEvent = e as CustomEvent
 			const params = customEvent.detail?.[0]

packages/page-agent/src/utils/index.ts

@@ -20,6 +20,10 @@ export async function waitUntil(check: () => boolean, timeout = 60 * 60_1000): P
 	})
 }
 
+export async function waitFor(seconds: number): Promise<void> {
+	await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
+}
+
 //
 
 export function truncate(text: string, maxLength: number): string {

packages/page-agent/tsconfig.dts.json

@@ -0,0 +1,9 @@
+{
+	"extends": "./tsconfig.json",
+	"compilerOptions": {
+		// @workaround DTS bug
+		// dts do not work with monorepo path mapping
+		// disable path mapping for it
+		"paths": {}
+	}
+}

packages/page-agent/tsconfig.json

@@ -0,0 +1,22 @@
+{
+	"extends": "../../tsconfig.base.json",
+	"compilerOptions": {
+		"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
+		"noEmit": false,
+		"allowImportingTsExtensions": false,
+		"baseUrl": ".",
+		"outDir": "dist",
+		"paths": {
+			//
+			"@page-agent/page-controller": ["../page-controller/src/PageController.ts"],
+			"@page-agent/ui": ["../ui/src/index.ts"]
+		}
+	},
+	"include": ["**/*.ts"],
+	"exclude": ["dist", "node_modules"],
+	"references": [
+		//
+		{ "path": "../page-controller" },
+		{ "path": "../ui" }
+	]
+}

packages/page-agent/vite.config.js

@@ -1,9 +1,4 @@
 // @ts-check
-// ============================================================================
-// Export Configuration Based on MODE Environment Variable
-// ============================================================================
-import tailwindcss from '@tailwindcss/vite'
-import react from '@vitejs/plugin-react-swc'
 import chalk from 'chalk'
 import 'dotenv/config'
 import process from 'node:process'
@@ -13,44 +8,18 @@ import { fileURLToPath } from 'url'
 import { defineConfig } from 'vite'
 import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
 
-const __filename = fileURLToPath(import.meta.url)
-const __dirname = dirname(__filename)
-
-// Website Config (React Documentation Site)
-
-/** @type {import('vite').UserConfig} */
-const websiteConfig = {
-	// https://vite.dev/config/
-	base: './',
-	plugins: [react(), tailwindcss()],
-	resolve: {
-		alias: {
-			'@': resolve(__dirname, 'src'),
-			'@pages': resolve(__dirname, 'pages'),
-		},
-	},
-	define: {
-		'import.meta.env.LLM_MODEL_NAME': JSON.stringify(process.env.LLM_MODEL_NAME),
-		'import.meta.env.LLM_API_KEY': JSON.stringify(process.env.LLM_API_KEY),
-		'import.meta.env.LLM_BASE_URL': JSON.stringify(process.env.LLM_BASE_URL),
-	},
-}
+const __dirname = dirname(fileURLToPath(import.meta.url))
 
 // ============================================================================
-// Library Config (ES Module for NPM Package)
+// ES Module for NPM Package
 // ============================================================================
 /** @type {import('vite').UserConfig} */
-const libConfig = {
-	// Library build configuration
+const esmConfig = {
+	clearScreen: false,
 	plugins: [
-		dts({ tsconfigPath: './tsconfig.json', bundleTypes: true }),
+		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
 		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
 	],
-	resolve: {
-		alias: {
-			'@': resolve(__dirname, 'src'),
-		},
-	},
 	publicDir: false,
 	esbuild: {
 		keepNames: true,
@@ -62,11 +31,15 @@ const libConfig = {
 			fileName: 'page-agent',
 			formats: ['es'],
 		},
-		outDir: resolve(__dirname, 'dist', 'lib'),
+		outDir: resolve(__dirname, 'dist', 'esm'),
 		rollupOptions: {
-			external: ['ai', 'ai-motion', 'chalk', 'zod'],
+			external: [
+				'chalk',
+				'zod',
+				// all the internal packages
+				/^@page-agent\//,
+			],
 		},
-		// minify: 'terser',
 		minify: false,
 		sourcemap: true,
 		cssCodeSplit: true,
@@ -77,29 +50,37 @@ const libConfig = {
 }
 
 // ============================================================================
-// UMD Config (Browser Bundle for CDN)
+// UMD Bundle for CDN
+// - alias all local packages so that they can be build in
+// - no external
+// - no d.ts. dts does not work with monorepo aliasing
 // ============================================================================
 /** @type {import('vite').UserConfig} */
 const umdConfig = {
-	// Library build configuration
 	plugins: [cssInjectedByJsPlugin({ relativeCSSInjection: true })],
-	resolve: {
-		alias: {
-			'@': resolve(__dirname, 'src'),
-		},
-	},
 	publicDir: false,
 	esbuild: {
 		keepNames: true,
 	},
+	resolve: {
+		alias: {
+			'@page-agent/page-controller': resolve(__dirname, '../page-controller/src/PageController.ts'),
+			'@page-agent/ui': resolve(__dirname, '../ui/src/index.ts'),
+		},
+	},
 	build: {
 		lib: {
-			entry: resolve(__dirname, 'src/entry.ts'),
+			entry: resolve(__dirname, 'src/umd.ts'),
 			name: 'PageAgent',
 			fileName: 'page-agent',
 			formats: ['umd'],
 		},
 		outDir: resolve(__dirname, 'dist', 'umd'),
+		rollupOptions: {
+			output: {
+				entryFileNames: 'page-agent.js', // 强制指定完整文件名
+			},
+		},
 		cssCodeSplit: true,
 	},
 	define: {
@@ -109,19 +90,15 @@ const umdConfig = {
 
 // ============================================================================
 
-// ============================================================================
-
 const MODE = process.env.MODE
 
-console.log(chalk.cyan(`📦 Build mode: ${chalk.bold(MODE || 'website')}`))
+console.log(chalk.cyan(`📦 Build mode: ${chalk.bold(MODE || 'esm')}`))
 
 let config
-if (MODE === 'lib') {
-	config = libConfig
-} else if (MODE === 'umd') {
+if (MODE === 'umd') {
 	config = umdConfig
 } else {
-	config = websiteConfig
+	config = esmConfig
 }
 
 export default defineConfig(config)

packages/page-controller/package.json

@@ -0,0 +1,38 @@
+{
+	"name": "@page-agent/page-controller",
+	"version": "0.0.11",
+	"type": "module",
+	"main": "./dist/lib/page-controller.js",
+	"module": "./dist/lib/page-controller.js",
+	"types": "./dist/lib/PageController.d.ts",
+	"exports": {
+		".": {
+			"types": "./dist/lib/PageController.d.ts",
+			"import": "./dist/lib/page-controller.js",
+			"default": "./dist/lib/page-controller.js"
+		}
+	},
+	"files": [
+		"dist/"
+	],
+	"description": "Page controller for page-agent - DOM operations and element interactions",
+	"keywords": [
+		"page-agent",
+		"dom",
+		"browser-automation",
+		"web-automation"
+	],
+	"author": "Simon<gaomeng1900>",
+	"license": "MIT",
+	"repository": {
+		"type": "git",
+		"url": "https://github.com/alibaba/page-agent.git",
+		"directory": "packages/page-controller"
+	},
+	"homepage": "https://alibaba.github.io/page-agent/",
+	"scripts": {
+		"build": "vite build",
+		"prepublishOnly": "node -e \"const fs=require('fs');['LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
+		"postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+	}
+}

packages/page-controller/src/PageController.ts

@@ -0,0 +1,339 @@
+/**
+ * Copyright (C) 2025 Alibaba Group Holding Limited
+ * All rights reserved.
+ *
+ * PageController - Manages DOM operations and element interactions.
+ * Designed to be independent of LLM and can be tested in unit tests.
+ * All public methods are async for potential remote calling support.
+ */
+import {
+	clickElement,
+	getElementByIndex,
+	inputTextElement,
+	scrollHorizontally,
+	scrollVertically,
+	selectOptionElement,
+} from './actions'
+import { VIEWPORT_EXPANSION } from './constants'
+import * as dom from './dom'
+import type { FlatDomTree, InteractiveElementDomNode } from './dom/dom_tree/type'
+import { getPageInfo } from './dom/getPageInfo'
+import { patchReact } from './patches/react'
+
+/**
+ * Configuration for PageController
+ */
+export interface PageControllerConfig extends dom.DomConfig {
+	viewportExpansion?: number
+}
+
+interface ActionResult {
+	success: boolean
+	message: string
+}
+
+/**
+ * PageController manages DOM state and element interactions.
+ * It provides async methods for all DOM operations, keeping state isolated.
+ *
+ * @lifecycle
+ * - beforeUpdate: Emitted before the DOM tree is updated.
+ * - afterUpdate: Emitted after the DOM tree is updated.
+ */
+export class PageController extends EventTarget {
+	private config: PageControllerConfig
+
+	/** Corresponds to eval_page in browser-use */
+	private flatTree: FlatDomTree | null = null
+
+	/**
+	 * All highlighted index-mapped interactive elements
+	 * Corresponds to DOMState.selector_map in browser-use
+	 */
+	private selectorMap = new Map<number, InteractiveElementDomNode>()
+
+	/** Index -> element text description mapping */
+	private elementTextMap = new Map<number, string>()
+
+	/**
+	 * Simplified HTML for LLM consumption.
+	 * Corresponds to clickable_elements_to_string in browser-use
+	 */
+	private simplifiedHTML = '<EMPTY>'
+
+	/** last time the tree was updated */
+	private lastTimeUpdate = 0
+
+	constructor(config: PageControllerConfig = {}) {
+		super()
+
+		this.config = config
+
+		patchReact(this)
+	}
+
+	// ======= State Queries =======
+
+	/**
+	 * Get current page URL
+	 */
+	async getCurrentUrl(): Promise<string> {
+		return window.location.href
+	}
+
+	/**
+	 * Get current page title
+	 */
+	async getPageTitle(): Promise<string> {
+		return document.title
+	}
+
+	/**
+	 * Get page scroll and size info
+	 */
+	async getPageInfo() {
+		return getPageInfo()
+	}
+
+	/**
+	 * Get the simplified HTML representation of the page.
+	 * This is used by LLM to understand the page structure.
+	 */
+	async getSimplifiedHTML(): Promise<string> {
+		return this.simplifiedHTML
+	}
+
+	/**
+	 * Get text description for an element by index
+	 */
+	async getElementText(index: number): Promise<string | undefined> {
+		return this.elementTextMap.get(index)
+	}
+
+	/**
+	 * Get total number of indexed interactive elements
+	 */
+	async getElementCount(): Promise<number> {
+		return this.selectorMap.size
+	}
+
+	/**
+	 * Get last tree update timestamp
+	 */
+	async getLastUpdateTime(): Promise<number> {
+		return this.lastTimeUpdate
+	}
+
+	/**
+	 * Get the viewport expansion setting
+	 */
+	async getViewportExpansion(): Promise<number> {
+		return this.config.viewportExpansion ?? VIEWPORT_EXPANSION
+	}
+
+	// ======= DOM Tree Operations =======
+
+	/**
+	 * Update DOM tree, returns simplified HTML for LLM.
+	 * This is the main method to refresh the page state.
+	 */
+	async updateTree(): Promise<string> {
+		this.dispatchEvent(new Event('beforeUpdate'))
+
+		this.lastTimeUpdate = Date.now()
+
+		dom.cleanUpHighlights()
+
+		const blacklist = [
+			...(this.config.interactiveBlacklist || []),
+			...document.querySelectorAll('[data-page-agent-not-interactive]').values(),
+		]
+
+		this.flatTree = dom.getFlatTree({
+			...this.config,
+			interactiveBlacklist: blacklist,
+		})
+
+		this.simplifiedHTML = dom.flatTreeToString(this.flatTree, this.config.include_attributes)
+
+		this.selectorMap.clear()
+		this.selectorMap = dom.getSelectorMap(this.flatTree)
+
+		this.elementTextMap.clear()
+		this.elementTextMap = dom.getElementTextMap(this.simplifiedHTML)
+
+		this.dispatchEvent(new Event('afterUpdate'))
+
+		return this.simplifiedHTML
+	}
+
+	/**
+	 * Clean up all element highlights
+	 */
+	async cleanUpHighlights(): Promise<void> {
+		dom.cleanUpHighlights()
+	}
+
+	// ======= Element Actions =======
+
+	/**
+	 * Click element by index
+	 */
+	async clickElement(index: number): Promise<ActionResult> {
+		try {
+			const element = getElementByIndex(this.selectorMap, index)
+			const elemText = this.elementTextMap.get(index)
+			await clickElement(element)
+
+			// Handle links that open in new tabs
+			if (element instanceof HTMLAnchorElement && element.target === '_blank') {
+				return {
+					success: true,
+					message: `✅ Clicked element (${elemText ?? index}). ⚠️ Link opens in a new tab. You are not capable of reading new tabs.`,
+				}
+			}
+
+			return {
+				success: true,
+				message: `✅ Clicked element (${elemText ?? index}).`,
+			}
+		} catch (error) {
+			return {
+				success: false,
+				message: `❌ Failed to click element: ${error}`,
+			}
+		}
+	}
+
+	/**
+	 * Input text into element by index
+	 */
+	async inputText(index: number, text: string): Promise<ActionResult> {
+		try {
+			const element = getElementByIndex(this.selectorMap, index)
+			const elemText = this.elementTextMap.get(index)
+			await inputTextElement(element, text)
+
+			return {
+				success: true,
+				message: `✅ Input text (${text}) into element (${elemText ?? index}).`,
+			}
+		} catch (error) {
+			return {
+				success: false,
+				message: `❌ Failed to input text: ${error}`,
+			}
+		}
+	}
+
+	/**
+	 * Select dropdown option by index and option text
+	 */
+	async selectOption(index: number, optionText: string): Promise<ActionResult> {
+		try {
+			const element = getElementByIndex(this.selectorMap, index)
+			const elemText = this.elementTextMap.get(index)
+			await selectOptionElement(element as HTMLSelectElement, optionText)
+
+			return {
+				success: true,
+				message: `✅ Selected option (${optionText}) in element (${elemText ?? index}).`,
+			}
+		} catch (error) {
+			return {
+				success: false,
+				message: `❌ Failed to select option: ${error}`,
+			}
+		}
+	}
+
+	/**
+	 * Scroll vertically
+	 */
+	async scroll(options: {
+		down: boolean
+		numPages: number
+		pixels?: number
+		index?: number
+	}): Promise<ActionResult> {
+		try {
+			const { down, numPages, pixels, index } = options
+
+			const scrollAmount = pixels ?? numPages * (down ? 1 : -1) * window.innerHeight
+
+			const element = index !== undefined ? getElementByIndex(this.selectorMap, index) : null
+
+			const message = await scrollVertically(down, scrollAmount, element)
+
+			return {
+				success: true,
+				message,
+			}
+		} catch (error) {
+			return {
+				success: false,
+				message: `❌ Failed to scroll: ${error}`,
+			}
+		}
+	}
+
+	/**
+	 * Scroll horizontally
+	 */
+	async scrollHorizontally(options: {
+		right: boolean
+		pixels: number
+		index?: number
+	}): Promise<ActionResult> {
+		try {
+			const { right, pixels, index } = options
+
+			const scrollAmount = pixels * (right ? 1 : -1)
+
+			const element = index !== undefined ? getElementByIndex(this.selectorMap, index) : null
+
+			const message = await scrollHorizontally(right, scrollAmount, element)
+
+			return {
+				success: true,
+				message,
+			}
+		} catch (error) {
+			return {
+				success: false,
+				message: `❌ Failed to scroll horizontally: ${error}`,
+			}
+		}
+	}
+
+	/**
+	 * Execute arbitrary JavaScript on the page
+	 */
+	async executeJavascript(script: string): Promise<ActionResult> {
+		try {
+			// Wrap script in async function to support await
+			const asyncFunction = eval(`(async () => { ${script} })`)
+			const result = await asyncFunction()
+			return {
+				success: true,
+				message: `✅ Executed JavaScript. Result: ${result}`,
+			}
+		} catch (error) {
+			return {
+				success: false,
+				message: `❌ Error executing JavaScript: ${error}`,
+			}
+		}
+	}
+
+	/**
+	 * Dispose and clean up resources
+	 */
+	dispose(): void {
+		dom.cleanUpHighlights()
+		this.flatTree = null
+		this.selectorMap.clear()
+		this.elementTextMap.clear()
+		this.simplifiedHTML = '<EMPTY>'
+	}
+}

packages/page-controller/src/actions.ts

@@ -2,26 +2,14 @@
  * Copyright (C) 2025 Alibaba Group Holding Limited
  * All rights reserved.
  */
-import type { PageAgent } from '../PageAgent'
+import type { InteractiveElementDomNode } from './dom/dom_tree/type'
 
 // ======= general utils =======
 
-export async function waitFor(seconds: number): Promise<void> {
+async function waitFor(seconds: number): Promise<void> {
 	await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
 }
 
-let currentUrl = window.location.href
-export async function getSystemInfo() {
-	// If current URL is already up to date, no need to add message
-	if (currentUrl === window.location.href) return ''
-
-	await waitFor(0.3) // Wait a bit longer for page to load
-
-	currentUrl = window.location.href
-
-	return `\n<sys> Current URL changed to: ${currentUrl} </sys>`
-}
-
 // ======= dom utils =======
 
 export async function movePointerToElement(element: HTMLElement) {
@@ -35,10 +23,13 @@ export async function movePointerToElement(element: HTMLElement) {
 }
 
 /**
- * Get the HTMLElement by index from the selectorMap in PageAgent.
+ * Get the HTMLElement by index from a selectorMap.
  */
-export function getElementByIndex(pageAgent: PageAgent, index: number): HTMLElement {
-	const interactiveNode = pageAgent.selectorMap.get(index)
+export function getElementByIndex(
+	selectorMap: Map<number, InteractiveElementDomNode>,
+	index: number
+): HTMLElement {
+	const interactiveNode = selectorMap.get(index)
 	if (!interactiveNode) {
 		throw new Error(`No interactive element found at index ${index}`)
 	}
@@ -170,7 +161,6 @@ export async function selectOptionElement(selectElement: HTMLSelectElement, opti
 	await waitFor(0.1) // Wait to ensure change event processing completes
 }
 
-// eslint-disable-next-line @typescript-eslint/require-await
 export async function scrollIntoViewIfNeeded(element: HTMLElement) {
 	const el = element as any
 	if (el.scrollIntoViewIfNeeded) {

packages/page-controller/src/constants.ts

@@ -0,0 +1,16 @@
+/**
+ * Copyright (C) 2025 Alibaba Group Holding Limited
+ * All rights reserved.
+ */
+
+/**
+ * Viewport expansion for DOM tree extraction.
+ * -1 means full page (no viewport restriction)
+ * 0 means viewport only
+ * positive values expand the viewport by that many pixels
+ *
+ * @note Since isTopElement depends on elementFromPoint,
+ * it returns null when out of viewport, this feature has no practical use, only differ between -1 and 0
+ */
+// export const VIEWPORT_EXPANSION = 100
+export const VIEWPORT_EXPANSION = -1

packages/page-controller/src/dom/index.ts

@@ -1,11 +1,11 @@
-import { VIEWPORT_EXPANSION } from '@/config/constants'
-import domTree from '@/dom/dom_tree/index'
+import { VIEWPORT_EXPANSION } from '../constants'
+import domTree from './dom_tree/index.js'
 import {
 	ElementDomNode,
 	FlatDomTree,
 	InteractiveElementDomNode,
 	TextDomNode,
-} from '@/dom/dom_tree/type'
+} from './dom_tree/type'
 
 export interface DomConfig {
 	interactiveBlacklist?: (Element | (() => Element))[]

packages/page-controller/src/patches/antd.ts

@@ -1,4 +1,4 @@
-import type { PageAgent } from '@/PageAgent'
+import type { PageController } from '../PageController'
 
 const clearFunctions = [] as (() => void)[]
 
@@ -11,9 +11,9 @@ function fixAntdSelect() {
 	// for (const select of selects) {}
 }
 
-export function patchAntd(pageAgent: PageAgent) {
-	pageAgent.addEventListener('beforeUpdate', fixAntdSelect)
-	pageAgent.addEventListener('afterUpdate', () => {
+export function patchAntd(pageController: PageController) {
+	pageController.addEventListener('beforeUpdate', fixAntdSelect)
+	pageController.addEventListener('afterUpdate', () => {
 		for (const fn of clearFunctions) fn()
 		clearFunctions.length = 0
 	})

packages/page-controller/src/patches/react.ts

@@ -1,7 +1,7 @@
-import type { PageAgent } from '@/PageAgent'
+import type { PageController } from '../PageController'
 
 // Find common React root elements and add data-page-agent-not-interactive attribute
-export function patchReact(pageAgent: PageAgent) {
+export function patchReact(pageController: PageController) {
 	const reactRootElements = document.querySelectorAll(
 		'[data-reactroot], [data-reactid], [data-react-checksum], #root, #app, [id^="root-"], [id^="app-"], #adex-wrapper, #adex-root'
 	)

packages/page-controller/tsconfig.dts.json

@@ -0,0 +1,9 @@
+{
+	"extends": "./tsconfig.json",
+	"compilerOptions": {
+		// @workaround DTS bug
+		// dts do not work with monorepo path mapping
+		// disable path mapping for it
+		"paths": {}
+	}
+}

packages/page-controller/tsconfig.json

@@ -0,0 +1,12 @@
+{
+	"extends": "../../tsconfig.base.json",
+	"compilerOptions": {
+		"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
+		"noEmit": false,
+		"allowImportingTsExtensions": false,
+		"baseUrl": ".",
+		"outDir": "dist"
+	},
+	"include": ["**/*.ts", "**/*.js"],
+	"exclude": ["dist", "node_modules"]
+}

packages/page-controller/vite.config.js

@@ -0,0 +1,41 @@
+// @ts-check
+import chalk from 'chalk'
+import { dirname, resolve } from 'path'
+import dts from 'unplugin-dts/vite'
+import { fileURLToPath } from 'url'
+import { defineConfig } from 'vite'
+import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
+
+const __dirname = dirname(fileURLToPath(import.meta.url))
+
+console.log(chalk.cyan(`📦 Building @page-agent/page-controller`))
+
+export default defineConfig({
+	clearScreen: false,
+	plugins: [
+		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
+		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
+	],
+	publicDir: false,
+	esbuild: {
+		keepNames: true,
+	},
+	build: {
+		lib: {
+			entry: resolve(__dirname, 'src/PageController.ts'),
+			name: 'PageController',
+			fileName: 'page-controller',
+			formats: ['es'],
+		},
+		outDir: resolve(__dirname, 'dist', 'lib'),
+		rollupOptions: {
+			external: ['@page-agent/*'],
+		},
+		minify: false,
+		sourcemap: true,
+		cssCodeSplit: true,
+	},
+	define: {
+		'process.env.NODE_ENV': '"production"',
+	},
+})

packages/ui/package.json

@@ -0,0 +1,41 @@
+{
+	"name": "@page-agent/ui",
+	"version": "0.0.11",
+	"type": "module",
+	"main": "./dist/lib/page-agent-ui.js",
+	"module": "./dist/lib/page-agent-ui.js",
+	"types": "./dist/lib/index.d.ts",
+	"exports": {
+		".": {
+			"types": "./dist/lib/index.d.ts",
+			"import": "./dist/lib/page-agent-ui.js",
+			"default": "./dist/lib/page-agent-ui.js"
+		}
+	},
+	"files": [
+		"dist/"
+	],
+	"description": "UI components for page-agent - Panel, SimulatorMask, and i18n",
+	"keywords": [
+		"page-agent",
+		"ui",
+		"panel",
+		"i18n"
+	],
+	"author": "Simon<gaomeng1900>",
+	"license": "MIT",
+	"repository": {
+		"type": "git",
+		"url": "https://github.com/alibaba/page-agent.git",
+		"directory": "packages/ui"
+	},
+	"homepage": "https://alibaba.github.io/page-agent/",
+	"scripts": {
+		"build": "vite build",
+		"prepublishOnly": "node -e \"const fs=require('fs');['LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
+		"postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+	},
+	"dependencies": {
+		"ai-motion": "^0.4.7"
+	}
+}

packages/ui/src/Panel.module.css

@@ -33,8 +33,7 @@
 	/* 响应式设计 */
 	@media (max-width: 480px) {
 		width: calc(100vw - 40px);
-		left: 20px;
-		transform: none;
+		--width: calc(100vw - 40px);
 	}
 
 	.background {

packages/ui/src/Panel.ts

@@ -1,12 +1,35 @@
-import type { PageAgent } from '@/PageAgent'
-import type { I18n } from '@/i18n'
-import { truncate } from '@/utils'
-import type { EventBus } from '@/utils/bus'
-
 import { type Step, UIState } from './UIState'
+import { I18n, type SupportedLanguage } from './i18n'
+import { truncate } from './utils'
 
 import styles from './Panel.module.css'
 
+/**
+ * Panel configuration
+ */
+export interface PanelConfig {
+	language?: SupportedLanguage
+	onExecuteTask: (task: string) => void
+	onStop: () => void
+	onPauseToggle: () => boolean // returns new paused state
+	getPaused: () => boolean
+}
+
+/**
+ * Semantic update types - Panel handles i18n internally
+ */
+export type PanelUpdate =
+	| { type: 'thinking'; text?: string } // text is optional, defaults to i18n thinking text
+	| { type: 'input'; task: string }
+	| { type: 'question'; question: string }
+	| { type: 'userAnswer'; input: string }
+	| { type: 'retry'; current: number; max: number }
+	| { type: 'error'; message: string }
+	| { type: 'output'; text: string }
+	| { type: 'completed' }
+	| { type: 'toolExecuting'; toolName: string; args: any }
+	| { type: 'toolCompleted'; toolName: string; args: any; result?: string; duration?: number }
+
 /**
  * Agent control panel
  */
@@ -20,11 +43,11 @@ export class Panel {
 	#stopButton: HTMLElement
 	#inputSection: HTMLElement
 	#taskInput: HTMLInputElement
-	#bus: EventBus
 
 	#state = new UIState()
 	#isExpanded = false
-	#pageAgent: PageAgent
+	#config: PanelConfig
+	#i18n: I18n
 	#userAnswerResolver: ((input: string) => void) | null = null
 	#isWaitingForUserAnswer: boolean = false
 	#headerUpdateTimer: ReturnType<typeof setInterval> | null = null
@@ -35,9 +58,9 @@ export class Panel {
 		return this.#wrapper
 	}
 
-	constructor(pageAgent: PageAgent) {
-		this.#pageAgent = pageAgent
-		this.#bus = pageAgent.bus
+	constructor(config: PanelConfig) {
+		this.#config = config
+		this.#i18n = new I18n(config.language ?? 'en-US')
 		this.#wrapper = this.#createWrapper()
 		this.#indicator = this.#wrapper.querySelector(`.${styles.indicator}`)!
 		this.#statusText = this.#wrapper.querySelector(`.${styles.statusText}`)!
@@ -50,16 +73,8 @@ export class Panel {
 
 		this.#setupEventListeners()
 		this.#startHeaderUpdateLoop()
-		// this.#expand() // debug
 
 		this.#showInputArea()
-
-		this.#bus.on('panel:show', () => this.#show())
-		this.#bus.on('panel:hide', () => this.#hide())
-		this.#bus.on('panel:reset', () => this.#reset())
-		this.#bus.on('panel:update', (stepData) => this.#update(stepData))
-		this.#bus.on('panel:expand', () => this.#expand())
-		this.#bus.on('panel:collapse', () => this.#collapse())
 	}
 
 	/**
@@ -72,18 +87,67 @@ export class Panel {
 			this.#userAnswerResolver = resolve
 
 			// Update state to `running`
-			this.#update({
+			this.#updateInternal({
 				type: 'output',
-				displayText: this.#pageAgent.i18n.t('ui.panel.question', { question }),
+				displayText: this.#i18n.t('ui.panel.question', { question }),
 			}) // Expand history panel
 			if (!this.#isExpanded) {
 				this.#expand()
 			}
 
-			this.#showInputArea(this.#pageAgent.i18n.t('ui.panel.userAnswerPrompt'))
+			this.#showInputArea(this.#i18n.t('ui.panel.userAnswerPrompt'))
 		})
 	}
 
+	// ========== Public control methods ==========
+
+	show(): void {
+		this.wrapper.style.display = 'block'
+		void this.wrapper.offsetHeight
+		this.wrapper.style.opacity = '1'
+		this.wrapper.style.transform = 'translateX(-50%) translateY(0)'
+	}
+
+	hide(): void {
+		this.wrapper.style.opacity = '0'
+		this.wrapper.style.transform = 'translateX(-50%) translateY(20px)'
+		this.wrapper.style.display = 'none'
+	}
+
+	reset(): void {
+		this.#state.reset()
+		this.#statusText.textContent = this.#i18n.t('ui.panel.ready')
+		this.#updateStatusIndicator('thinking')
+		this.#updateHistory()
+		this.#collapse()
+		// Reset pause state via callback
+		if (this.#config.getPaused()) {
+			this.#config.onPauseToggle()
+		}
+		this.#updatePauseButton()
+		// Reset user input state
+		this.#isWaitingForUserAnswer = false
+		this.#userAnswerResolver = null
+		// Show input area
+		this.#showInputArea()
+	}
+
+	expand(): void {
+		this.#expand()
+	}
+
+	collapse(): void {
+		this.#collapse()
+	}
+
+	/**
+	 * Update panel with semantic data - i18n handled internally
+	 */
+	update(data: PanelUpdate): void {
+		const stepData = this.#toStepData(data)
+		this.#updateInternal(stepData)
+	}
+
 	/**
 	 * Dispose panel
 	 */
@@ -93,10 +157,102 @@ export class Panel {
 		this.wrapper.remove()
 	}
 
+	// ========== Private methods ==========
+
 	/**
-	 * Update status
+	 * Convert semantic update to step data with i18n
 	 */
-	#update(stepData: Omit<Step, 'id' | 'stepNumber' | 'timestamp'>): void {
+	#toStepData(data: PanelUpdate): Omit<Step, 'id' | 'stepNumber' | 'timestamp'> {
+		switch (data.type) {
+			case 'thinking':
+				return { type: 'thinking', displayText: data.text ?? this.#i18n.t('ui.panel.thinking') }
+			case 'input':
+				return { type: 'input', displayText: data.task }
+			case 'question':
+				return {
+					type: 'output',
+					displayText: this.#i18n.t('ui.panel.question', { question: data.question }),
+				}
+			case 'userAnswer':
+				return {
+					type: 'input',
+					displayText: this.#i18n.t('ui.panel.userAnswer', { input: data.input }),
+				}
+			case 'retry':
+				return { type: 'retry', displayText: `retry-ing (${data.current} / ${data.max})` }
+			case 'error':
+				return { type: 'error', displayText: data.message }
+			case 'output':
+				return { type: 'output', displayText: data.text }
+			case 'completed':
+				return { type: 'completed', displayText: this.#i18n.t('ui.panel.taskCompleted') }
+			case 'toolExecuting':
+				return {
+					type: 'tool_executing',
+					toolName: data.toolName,
+					toolArgs: data.args,
+					displayText: this.#getToolExecutingText(data.toolName, data.args),
+				}
+			case 'toolCompleted': {
+				const displayText = this.#getToolCompletedText(data.toolName, data.args)
+				if (!displayText) return { type: 'tool_executing', displayText: '' } // will be filtered
+				return {
+					type: 'tool_executing',
+					toolName: data.toolName,
+					toolArgs: data.args,
+					toolResult: data.result,
+					displayText,
+					duration: data.duration,
+				}
+			}
+		}
+	}
+
+	#getToolExecutingText(toolName: string, args: any): string {
+		switch (toolName) {
+			case 'click_element_by_index':
+				return this.#i18n.t('ui.tools.clicking', { index: args.index })
+			case 'input_text':
+				return this.#i18n.t('ui.tools.inputting', { index: args.index })
+			case 'select_dropdown_option':
+				return this.#i18n.t('ui.tools.selecting', { text: args.text })
+			case 'scroll':
+				return this.#i18n.t('ui.tools.scrolling')
+			case 'wait':
+				return this.#i18n.t('ui.tools.waiting', { seconds: args.seconds })
+			case 'done':
+				return this.#i18n.t('ui.tools.done')
+			default:
+				return this.#i18n.t('ui.tools.executing', { toolName })
+		}
+	}
+
+	#getToolCompletedText(toolName: string, args: any): string | null {
+		switch (toolName) {
+			case 'click_element_by_index':
+				return this.#i18n.t('ui.tools.clicked', { index: args.index })
+			case 'input_text':
+				return this.#i18n.t('ui.tools.inputted', { text: args.text })
+			case 'select_dropdown_option':
+				return this.#i18n.t('ui.tools.selected', { text: args.text })
+			case 'scroll':
+				return this.#i18n.t('ui.tools.scrolled')
+			case 'wait':
+				return this.#i18n.t('ui.tools.waited')
+			case 'done':
+				return null
+			default:
+				return null
+		}
+	}
+
+	/**
+	 * Update status (internal)
+	 */
+	#updateInternal(stepData: Omit<Step, 'id' | 'stepNumber' | 'timestamp'>): void {
+		// Skip empty displayText (filtered toolCompleted for 'done')
+		if (!stepData.displayText) return
+
 		const step = this.#state.addStep(stepData)
 
 		// Queue header text update (will be processed by periodic check)
@@ -121,59 +277,20 @@ export class Panel {
 		}
 	}
 
-	/**
-	 * Show panel
-	 */
-	#show(): void {
-		this.wrapper.style.display = 'block'
-		// Force reflow to trigger animation
-		void this.wrapper.offsetHeight
-		this.wrapper.style.opacity = '1'
-		this.wrapper.style.transform = 'translateX(-50%) translateY(0)'
-	}
-
-	/**
-	 * Hide panel
-	 */
-	#hide(): void {
-		this.wrapper.style.opacity = '0'
-		this.wrapper.style.transform = 'translateX(-50%) translateY(20px)'
-		this.wrapper.style.display = 'none'
-	}
-
-	/**
-	 * Reset state
-	 */
-	#reset(): void {
-		this.#state.reset()
-		this.#statusText.textContent = this.#pageAgent.i18n.t('ui.panel.ready')
-		this.#updateStatusIndicator('thinking')
-		this.#updateHistory()
-		this.#collapse()
-		// Reset pause state
-		this.#pageAgent.paused = false
-		this.#updatePauseButton()
-		// Reset user input state
-		this.#isWaitingForUserAnswer = false
-		this.#userAnswerResolver = null
-		// Show input area
-		this.#showInputArea()
-	}
-
 	/**
 	 * Toggle pause state
 	 */
 	#togglePause(): void {
-		this.#pageAgent.paused = !this.#pageAgent.paused
+		const paused = this.#config.onPauseToggle()
 		this.#updatePauseButton()
 
 		// Update status display
-		if (this.#pageAgent.paused) {
-			this.#statusText.textContent = this.#pageAgent.i18n.t('ui.panel.paused')
-			this.#updateStatusIndicator('thinking') // Use existing thinking state
+		if (paused) {
+			this.#statusText.textContent = this.#i18n.t('ui.panel.paused')
+			this.#updateStatusIndicator('thinking')
 		} else {
-			this.#statusText.textContent = this.#pageAgent.i18n.t('ui.panel.continueExecution')
-			this.#updateStatusIndicator('tool_executing') // Restore to execution state
+			this.#statusText.textContent = this.#i18n.t('ui.panel.continueExecution')
+			this.#updateStatusIndicator('tool_executing')
 		}
 	}
 
@@ -181,13 +298,14 @@ export class Panel {
 	 * Update pause button state
 	 */
 	#updatePauseButton(): void {
-		if (this.#pageAgent.paused) {
+		const paused = this.#config.getPaused()
+		if (paused) {
 			this.#pauseButton.textContent = '▶'
-			this.#pauseButton.title = this.#pageAgent.i18n.t('ui.panel.continue')
+			this.#pauseButton.title = this.#i18n.t('ui.panel.continue')
 			this.#pauseButton.classList.add(styles.paused)
 		} else {
 			this.#pauseButton.textContent = '⏸︎'
-			this.#pauseButton.title = this.#pageAgent.i18n.t('ui.panel.pause')
+			this.#pauseButton.title = this.#i18n.t('ui.panel.pause')
 			this.#pauseButton.classList.remove(styles.paused)
 		}
 	}
@@ -197,12 +315,12 @@ export class Panel {
 	 */
 	#stopAgent(): void {
 		// Update status display
-		this.#update({
+		this.#updateInternal({
 			type: 'error',
-			displayText: this.#pageAgent.i18n.t('ui.panel.taskTerminated'),
+			displayText: this.#i18n.t('ui.panel.taskTerminated'),
 		})
 
-		this.#pageAgent.dispose()
+		this.#config.onStop()
 	}
 
 	/**
@@ -219,7 +337,7 @@ export class Panel {
 			// Handle user input mode
 			this.#handleUserAnswer(input)
 		} else {
-			this.#pageAgent.execute(input)
+			this.#config.onExecuteTask(input)
 		}
 	}
 
@@ -228,9 +346,9 @@ export class Panel {
 	 */
 	#handleUserAnswer(input: string): void {
 		// Add user input to history
-		this.#update({
+		this.#updateInternal({
 			type: 'input',
-			displayText: this.#pageAgent.i18n.t('ui.panel.userAnswer', { input }),
+			displayText: this.#i18n.t('ui.panel.userAnswer', { input }),
 		})
 
 		// Reset state
@@ -249,7 +367,7 @@ export class Panel {
 	#showInputArea(placeholder?: string): void {
 		// Clear input field
 		this.#taskInput.value = ''
-		this.#taskInput.placeholder = placeholder || this.#pageAgent.i18n.t('ui.panel.taskInput')
+		this.#taskInput.placeholder = placeholder || this.#i18n.t('ui.panel.taskInput')
 		this.#inputSection.classList.remove(styles.hidden)
 		// Focus on input field
 		setTimeout(() => {
@@ -295,23 +413,23 @@ export class Panel {
 						stepNumber: 0,
 						timestamp: new Date(),
 						type: 'thinking',
-						displayText: this.#pageAgent.i18n.t('ui.panel.waitingPlaceholder'),
+						displayText: this.#i18n.t('ui.panel.waitingPlaceholder'),
 					})}
 				</div>
 			</div>
 			<div class="${styles.header}">
 				<div class="${styles.statusSection}">
 					<div class="${styles.indicator} ${styles.thinking}"></div>
-					<div class="${styles.statusText}">${this.#pageAgent.i18n.t('ui.panel.ready')}</div>
+					<div class="${styles.statusText}">${this.#i18n.t('ui.panel.ready')}</div>
 				</div>
 				<div class="${styles.controls}">
-					<button class="${styles.controlButton} ${styles.expandButton}" title="${this.#pageAgent.i18n.t('ui.panel.expand')}">
+					<button class="${styles.controlButton} ${styles.expandButton}" title="${this.#i18n.t('ui.panel.expand')}">
 						▼
 					</button>
-					<button class="${styles.controlButton} ${styles.pauseButton}" title="${this.#pageAgent.i18n.t('ui.panel.pause')}">
+					<button class="${styles.controlButton} ${styles.pauseButton}" title="${this.#i18n.t('ui.panel.pause')}">
 						⏸︎
 					</button>
-					<button class="${styles.controlButton} ${styles.stopButton}" title="${this.#pageAgent.i18n.t('ui.panel.stop')}">
+					<button class="${styles.controlButton} ${styles.stopButton}" title="${this.#i18n.t('ui.panel.stop')}">
 						X
 					</button>
 				</div>
@@ -502,8 +620,8 @@ export class Panel {
 			// Check if this is a result from done tool
 			if (step.toolName === 'done') {
 				// Judge success or failure based on result
-				const failureKeyword = this.#pageAgent.i18n.t('ui.tools.resultFailure')
-				const errorKeyword = this.#pageAgent.i18n.t('ui.tools.resultError')
+				const failureKeyword = this.#i18n.t('ui.tools.resultFailure')
+				const errorKeyword = this.#i18n.t('ui.tools.resultError')
 				const isSuccess =
 					!step.toolResult ||
 					(!step.toolResult.includes(failureKeyword) && !step.toolResult.includes(errorKeyword))
@@ -532,7 +650,7 @@ export class Panel {
 		}
 
 		const durationText = step.duration ? ` · ${step.duration}ms` : ''
-		const stepLabel = this.#pageAgent.i18n.t('ui.panel.step', {
+		const stepLabel = this.#i18n.t('ui.panel.step', {
 			number: step.stepNumber.toString(),
 			time,
 			duration: durationText || '', // Explicitly pass empty string to replace template
@@ -551,47 +669,3 @@ export class Panel {
 		`
 	}
 }
-
-/**
- * Get display text for tool execution
- */
-export function getToolExecutingText(toolName: string, args: any, i18n: I18n): string {
-	switch (toolName) {
-		case 'click_element_by_index':
-			return i18n.t('ui.tools.clicking', { index: args.index })
-		case 'input_text':
-			return i18n.t('ui.tools.inputting', { index: args.index })
-		case 'select_dropdown_option':
-			return i18n.t('ui.tools.selecting', { text: args.text })
-		case 'scroll':
-			return i18n.t('ui.tools.scrolling')
-		case 'wait':
-			return i18n.t('ui.tools.waiting', { seconds: args.seconds })
-		case 'done':
-			return i18n.t('ui.tools.done')
-		default:
-			return i18n.t('ui.tools.executing', { toolName })
-	}
-}
-
-/**
- * Get display text for tool completion
- */
-export function getToolCompletedText(toolName: string, args: any, i18n: I18n): string | null {
-	switch (toolName) {
-		case 'click_element_by_index':
-			return i18n.t('ui.tools.clicked', { index: args.index })
-		case 'input_text':
-			return i18n.t('ui.tools.inputted', { text: args.text })
-		case 'select_dropdown_option':
-			return i18n.t('ui.tools.selected', { text: args.text })
-		case 'scroll':
-			return i18n.t('ui.tools.scrolled')
-		case 'wait':
-			return i18n.t('ui.tools.waited')
-		case 'done':
-			return null
-		default:
-			return null
-	}
-}

packages/ui/src/SimulatorMask.ts

@@ -1,6 +1,6 @@
 import { Motion } from 'ai-motion'
 
-import { isPageDark } from '@/utils/checkDarkMode'
+import { isPageDark } from './checkDarkMode'
 
 import styles from './SimulatorMask.module.css'
 import cursorStyles from './cursor.module.css'

packages/ui/src/env.d.ts

@@ -0,0 +1,6 @@
+/// <reference types="vite/client" />
+
+declare module '*.module.css' {
+	const classes: Record<string, string>
+	export default classes
+}

packages/ui/src/index.ts

@@ -0,0 +1,4 @@
+export { Panel, type PanelConfig, type PanelUpdate } from './Panel'
+export { SimulatorMask } from './SimulatorMask'
+export { UIState, type Step, type AgentStatus } from './UIState'
+export { I18n, type SupportedLanguage, type TranslationKey } from './i18n'

packages/ui/src/utils.ts

@@ -0,0 +1,6 @@
+export function truncate(text: string, maxLength: number): string {
+	if (text.length > maxLength) {
+		return text.substring(0, maxLength) + '...'
+	}
+	return text
+}

packages/ui/tsconfig.dts.json

@@ -0,0 +1,10 @@
+{
+	"extends": "./tsconfig.json",
+	"compilerOptions": {
+		// @workaround DTS bug
+		// dts do not work with monorepo path mapping
+		// disable path mapping for it
+		"paths": {}
+	}
+}
+

packages/ui/tsconfig.json

@@ -0,0 +1,13 @@
+{
+	"extends": "../../tsconfig.base.json",
+	"compilerOptions": {
+		"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
+		"noEmit": false,
+		"allowImportingTsExtensions": false,
+		"baseUrl": ".",
+		"outDir": "dist"
+	},
+	"include": ["**/*.ts", "**/*.js"],
+	"exclude": ["dist", "node_modules"]
+}
+

packages/ui/vite.config.js

@@ -0,0 +1,41 @@
+// @ts-check
+import chalk from 'chalk'
+import { dirname, resolve } from 'path'
+import dts from 'unplugin-dts/vite'
+import { fileURLToPath } from 'url'
+import { defineConfig } from 'vite'
+import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
+
+const __dirname = dirname(fileURLToPath(import.meta.url))
+
+console.log(chalk.cyan(`📦 Building @page-agent/ui`))
+
+export default defineConfig({
+	clearScreen: false,
+	plugins: [
+		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
+		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
+	],
+	publicDir: false,
+	esbuild: {
+		keepNames: true,
+	},
+	build: {
+		lib: {
+			entry: resolve(__dirname, 'src/index.ts'),
+			name: 'PageAgentUI',
+			fileName: 'page-agent-ui',
+			formats: ['es'],
+		},
+		outDir: resolve(__dirname, 'dist', 'lib'),
+		rollupOptions: {
+			external: ['ai-motion'],
+		},
+		minify: false,
+		sourcemap: true,
+		cssCodeSplit: true,
+	},
+	define: {
+		'process.env.NODE_ENV': '"production"',
+	},
+})

packages/website/README.md

@@ -0,0 +1 @@
+# Landing Page & Docs

packages/website/index.html

@@ -0,0 +1,60 @@
+<!doctype html>
+<html lang="zh-CN">
+	<head>
+		<meta charset="UTF-8" />
+		<link
+			rel="icon"
+			type="image/svg+xml"
+			href="https://img.alicdn.com/imgextra/i2/O1CN012eGDRI1X6nnMt9clU_!!6000000002875-49-tps-64-64.webp"
+		/>
+		<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+		<title>PageAgent - The GUI Agent Living in Your Webpage</title>
+		<meta
+			name="description"
+			content="PageAgent.js: Intelligent GUI Agent for any website. Modern web AI automation with minimal integration."
+		/>
+		<meta
+			name="keywords"
+			content="PageAgent, AI Agent, GUI Agent, Web Automation, GUI Automation, Frontend, CDN, JavaScript, React, Vite, LLM"
+		/>
+		<meta
+			property="og:image"
+			content="https://img.alicdn.com/imgextra/i3/O1CN01JPT4Fj1FJTfmHfNxO_!!6000000000466-49-tps-512-512.webp"
+		/>
+		<meta property="og:url" content="https://alibaba.github.io/page-agent" />
+		<meta property="og:type" content="website" />
+		<meta name="theme-color" content="#58c0fc" />
+		<meta name="color-scheme" content="light dark" />
+		<meta name="author" content="PageAgent.js Team" />
+		<meta property="og:title" content="PageAgent.js - AI-powered GUI Agent" />
+		<meta property="og:description" content="The GUI Agent living in your website." />
+		<meta property="og:type" content="website" />
+		<meta property="og:locale" content="en_US" />
+		<meta property="og:locale:alternate" content="zh_CN" />
+
+		<!-- Google tag (gtag.js) -->
+		<script async src="https://www.googletagmanager.com/gtag/js?id=G-HCGRJTN3HM"></script>
+		<script>
+			window.dataLayer = window.dataLayer || []
+			function gtag() {
+				dataLayer.push(arguments)
+			}
+			gtag('js', new Date())
+
+			gtag('config', 'G-HCGRJTN3HM')
+		</script>
+	</head>
+	<body>
+		<div id="root"></div>
+		<script type="module" src="./src/main.tsx"></script>
+		<script>
+			// Dynamically update html lang attribute based on i18n detection
+			const updateHtmlLang = () => {
+				const lang = localStorage.getItem('i18nextLng') || navigator.language || 'zh-CN'
+				document.documentElement.lang = lang
+			}
+			updateHtmlLang()
+			window.addEventListener('storage', updateHtmlLang)
+		</script>
+	</body>
+</html>

packages/website/package.json

@@ -0,0 +1,25 @@
+{
+	"name": "@page-agent/website",
+	"private": true,
+	"version": "0.0.11",
+	"type": "module",
+	"scripts": {
+		"dev": "vite",
+		"build:website": "vite build",
+		"preview": "vite preview",
+		"typecheck": "tsc --noEmit"
+	},
+	"devDependencies": {
+		"@tailwindcss/vite": "^4.1.18",
+		"@types/react": "^19.2.2",
+		"@types/react-dom": "^19.2.1",
+		"@vitejs/plugin-react-swc": "^4.1.0",
+		"i18next": "^25.7.3",
+		"i18next-browser-languagedetector": "^8.2.0",
+		"react": "^19.2.3",
+		"react-dom": "^19.2.3",
+		"react-i18next": "^16.5.0",
+		"tailwindcss": "^4.1.14",
+		"wouter": "^3.8.1"
+	}
+}

packages/website/src/components/BetaNotice.tsx

@@ -1,17 +1,19 @@
+import { useTranslation } from 'react-i18next'
+
 export default function BetaNotice() {
+	const { t } = useTranslation('common')
+
 	return (
 		<div className="bg-orange-50 dark:bg-orange-900/20 border border-orange-200 dark:border-orange-800 rounded-lg p-4 mb-8">
 			<div className="flex items-start">
-				<div className="flex-shrink-0">
+				<div className="shrink-0">
 					<span className="text-xl">🚧</span>
 				</div>
 				<div className="ml-3">
 					<h3 className="text-sm font-medium text-orange-800 dark:text-orange-200 mb-1">
-						Beta 阶段
+						{t('beta_notice.title')}
 					</h3>
-					<p className="text-sm text-orange-700 dark:text-orange-300">
-						当前功能未完成，接口可能随时变更。正式版本发布前请勿用于生产环境。
-					</p>
+					<p className="text-sm text-orange-700 dark:text-orange-300">{t('beta_notice.content')}</p>
 				</div>
 			</div>
 		</div>

packages/website/src/components/CodeEditor.tsx

@@ -28,7 +28,7 @@ const CodeEditor: React.FC<CodeEditorProps> = ({
 
 	// 使用 Tailwind 的 dark: 前缀实现自动主题切换
 	const containerClasses =
-		'bg-gradient-to-br from-gray-50 to-gray-100 dark:from-gray-900 dark:to-gray-800 border-gray-300 dark:border-gray-700'
+		'bg-linear-to-br from-gray-50 to-gray-100 dark:from-gray-900 dark:to-gray-800 border-gray-300 dark:border-gray-700'
 	const headerClasses = 'bg-gray-100 dark:bg-gray-800 border-gray-300 dark:border-gray-700'
 	const headerTextClasses = 'text-gray-700 dark:text-gray-300'
 	const languageTextClasses = 'text-gray-600 dark:text-gray-400'
@@ -72,7 +72,7 @@ const CodeEditor: React.FC<CodeEditorProps> = ({
 				<div className="flex">
 					{/* 行号 */}
 					{showLineNumbers && (
-						<div className={`flex-shrink-0 px-4 py-4 ${lineNumbersClasses} border-r select-none`}>
+						<div className={`shrink-0 px-4 py-4 ${lineNumbersClasses} border-r select-none`}>
 							<div className="text-xs font-mono leading-6">
 								{lines.map((line, lineIdx) => {
 									const lineNum = lineIdx + 1

packages/website/src/components/DocsLayout.tsx

@@ -0,0 +1,98 @@
+import { ReactNode } from 'react'
+import { useTranslation } from 'react-i18next'
+import { Link, useLocation } from 'wouter'
+
+interface DocsLayoutProps {
+	children: ReactNode
+}
+
+interface NavItem {
+	title: string
+	path: string
+}
+
+interface NavSection {
+	title: string
+	items: NavItem[]
+}
+
+export default function DocsLayout({ children }: DocsLayoutProps) {
+	const { t } = useTranslation('common')
+	const [location] = useLocation()
+
+	const navigationSections: NavSection[] = [
+		{
+			title: t('nav.introduction'),
+			items: [
+				{ title: t('nav.overview'), path: '/docs/introduction/overview' },
+				{ title: t('nav.quick_start'), path: '/docs/introduction/quick-start' },
+				{ title: t('nav.limitations'), path: '/docs/introduction/limitations' },
+			],
+		},
+		{
+			title: t('nav.features'),
+			items: [
+				{ title: t('nav.model_integration'), path: '/docs/features/model-integration' },
+				{ title: t('nav.custom_tools'), path: '/docs/features/custom-tools' },
+				{ title: t('nav.knowledge_injection'), path: '/docs/features/knowledge-injection' },
+				{ title: t('nav.security_permissions'), path: '/docs/features/security-permissions' },
+				{ title: t('nav.data_masking'), path: '/docs/features/data-masking' },
+			],
+		},
+		{
+			title: t('nav.integration'),
+			items: [
+				{ title: t('nav.cdn_setup'), path: '/docs/integration/cdn-setup' },
+				{ title: t('nav.configuration'), path: '/docs/integration/configuration' },
+				{ title: t('nav.best_practices'), path: '/docs/integration/best-practices' },
+				{ title: t('nav.third_party_agent'), path: '/docs/integration/third-party-agent' },
+			],
+		},
+	]
+
+	return (
+		<div className="max-w-7xl mx-auto px-6 py-8 overflow-x-auto">
+			<div className="flex gap-8 min-w-[900px]">
+				{/* Sidebar */}
+				<aside className="w-64 shrink-0" role="complementary" aria-label="文档导航">
+					<div className="sticky top-8">
+						<nav className="space-y-8" role="navigation" aria-label="文档章节">
+							{navigationSections.map((section) => (
+								<section key={section.title}>
+									<h3 className="font-semibold text-gray-600 dark:text-gray-400 uppercase tracking-wider mb-3">
+										{section.title}
+									</h3>
+									<ul className="space-y-2" role="list">
+										{section.items.map((item) => {
+											const isActive = location === item.path
+											return (
+												<li key={item.path}>
+													<Link
+														href={item.path}
+														className={`block px-3 py-2 rounded-lg transition-colors duration-200 ${
+															isActive
+																? 'bg-blue-100 dark:bg-blue-900/30 text-blue-700 dark:text-blue-300 font-medium'
+																: 'text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white hover:bg-gray-100 dark:hover:bg-gray-800'
+														}`}
+														aria-current={isActive ? 'page' : undefined}
+													>
+														{item.title}
+													</Link>
+												</li>
+											)
+										})}
+									</ul>
+								</section>
+							))}
+						</nav>
+					</div>
+				</aside>
+
+				{/* Main Content */}
+				<main className="flex-1 min-w-0" id="main-content" role="main">
+					<div className="prose prose-lg dark:prose-invert max-w-none">{children}</div>
+				</main>
+			</div>
+		</div>
+	)
+}

packages/website/src/components/Footer.tsx

@@ -1,4 +1,8 @@
+import { useTranslation } from 'react-i18next'
+
 export default function Footer() {
+	const { t } = useTranslation('common')
+
 	return (
 		<footer
 			className="bg-gray-50 dark:bg-gray-900 border-t border-gray-200 dark:border-gray-700"
@@ -6,14 +10,14 @@ export default function Footer() {
 		>
 			<div className="max-w-7xl mx-auto px-6 py-6">
 				<div className="flex flex-col md:flex-row justify-between items-center space-y-4 md:space-y-0">
-					<p className="text-foreground/80 text-sm">© 2025 page-agent. All rights reserved.</p>
+					<p className="text-gray-600 dark:text-gray-300 text-sm">{t('footer.copyright')}</p>
 					<div className="flex items-center space-x-6">
 						<a
 							href="https://github.com/alibaba/page-agent"
 							target="_blank"
 							rel="noopener noreferrer"
-							className="text-foreground/80 hover:text-foreground transition-colors duration-200"
-							aria-label="访问 GitHub 仓库"
+							className="text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white transition-colors duration-200"
+							aria-label={t('footer.github_label')}
 						>
 							<svg className="w-5 h-5" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true">
 								<path d="M12 0c-6.626 0-12 5.373-12 12 0 5.302 3.438 9.8 8.207 11.387.599.111.793-.261.793-.577v-2.234c-3.338.726-4.033-1.416-4.033-1.416-.546-1.387-1.333-1.756-1.333-1.756-1.089-.745.083-.729.083-.729 1.205.084 1.839 1.237 1.839 1.237 1.07 1.834 2.807 1.304 3.492.997.107-.775.418-1.305.762-1.604-2.665-.305-5.467-1.334-5.467-5.931 0-1.311.469-2.381 1.236-3.221-.124-.303-.535-1.524.117-3.176 0 0 1.008-.322 3.301 1.23.957-.266 1.983-.399 3.003-.404 1.02.005 2.047.138 3.006.404 2.291-1.552 3.297-1.23 3.297-1.23.653 1.653.242 2.874.118 3.176.77.84 1.235 1.911 1.235 3.221 0 4.609-2.807 5.624-5.479 5.921.43.372.823 1.102.823 2.222v3.293c0 .319.192.694.801.576 4.765-1.589 8.199-6.086 8.199-11.386 0-6.627-5.373-12-12-12z" />

packages/website/src/components/Header.tsx

@@ -0,0 +1,142 @@
+import { useState } from 'react'
+import { useTranslation } from 'react-i18next'
+import { Link } from 'wouter'
+
+import LanguageSwitcher from './LanguageSwitcher'
+import ThemeSwitcher from './ThemeSwitcher'
+import { BookIcon, CloseIcon, GithubIcon, MenuIcon } from './icons'
+
+export default function Header() {
+	const { t } = useTranslation('common')
+	const [mobileMenuOpen, setMobileMenuOpen] = useState(false)
+
+	return (
+		<>
+			<header
+				className="relative z-50 bg-white/80 dark:bg-gray-900/80 backdrop-blur-md border-b border-gray-200 dark:border-gray-700"
+				role="banner"
+			>
+				<div className="max-w-7xl mx-auto px-6 py-4">
+					<div className="flex items-center justify-between gap-2">
+						{/* Logo */}
+						<Link
+							href="/"
+							className="flex items-center gap-2 sm:gap-3 group shrink-0"
+							aria-label={t('header.logo_alt')}
+							onClick={() => setMobileMenuOpen(false)}
+						>
+							<img
+								src="https://img.alicdn.com/imgextra/i2/O1CN01HB8ylu1uozANEMZw2_!!6000000006085-49-tps-128-128.webp"
+								alt="PageAgent Logo"
+								className="w-10 h-10 rounded-xl group-hover:scale-110 transition-transform duration-200"
+							/>
+							<div>
+								<span className="text-base sm:text-xl font-bold text-gray-900 dark:text-white block leading-tight">
+									page-agent
+								</span>
+								<p className="hidden sm:block text-xs text-gray-600 dark:text-gray-300">
+									{t('header.slogan')}
+								</p>
+							</div>
+						</Link>
+
+						{/* Mobile Icon Navigation (横向滚动) */}
+						<nav
+							className="md:hidden flex items-center gap-1 overflow-x-auto scrollbar-hide flex-1"
+							role="navigation"
+							aria-label="Mobile navigation"
+						>
+							<Link
+								href="/docs/introduction/overview"
+								className="p-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200 shrink-0"
+								aria-label={t('header.nav_docs')}
+							>
+								<BookIcon className="w-5 h-5" />
+							</Link>
+							<a
+								href="https://github.com/alibaba/page-agent"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="p-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200 shrink-0"
+								aria-label={t('header.nav_source')}
+							>
+								<GithubIcon className="w-5 h-5" />
+							</a>
+						</nav>
+
+						{/* Desktop Navigation */}
+						<nav
+							className="hidden md:flex items-center space-x-6"
+							role="navigation"
+							aria-label={t('header.nav_docs')}
+						>
+							<Link
+								href="/docs/introduction/overview"
+								className="flex items-center gap-1.5 text-gray-600 dark:text-gray-300 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
+							>
+								<BookIcon />
+								{t('header.nav_docs')}
+							</Link>
+							<a
+								href="https://github.com/alibaba/page-agent"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="flex items-center gap-1.5 text-gray-600 dark:text-gray-300 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
+								aria-label={t('header.nav_source')}
+							>
+								<GithubIcon />
+								{t('header.nav_source')}
+							</a>
+							<ThemeSwitcher />
+							<LanguageSwitcher />
+						</nav>
+
+						{/* Mobile menu button */}
+						<button
+							type="button"
+							className="md:hidden p-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 transition-colors duration-200 shrink-0"
+							aria-label={t('header.mobile_menu')}
+							aria-expanded={mobileMenuOpen}
+							aria-controls="mobile-menu"
+							onClick={() => setMobileMenuOpen(!mobileMenuOpen)}
+						>
+							{mobileMenuOpen ? <CloseIcon /> : <MenuIcon />}
+						</button>
+					</div>
+
+					{/* Mobile Navigation */}
+					{mobileMenuOpen && (
+						<nav
+							id="mobile-menu"
+							className="md:hidden pt-4 pb-2 space-y-3 border-t border-gray-200 dark:border-gray-700 mt-4"
+							role="navigation"
+						>
+							<Link
+								href="/docs/introduction/overview"
+								className="flex items-center gap-2 px-3 py-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
+								onClick={() => setMobileMenuOpen(false)}
+							>
+								<BookIcon className="w-5 h-5" />
+								{t('header.nav_docs')}
+							</Link>
+							<a
+								href="https://github.com/alibaba/page-agent"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="flex items-center gap-2 px-3 py-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
+								aria-label={t('header.nav_source')}
+							>
+								<GithubIcon className="w-5 h-5" />
+								{t('header.nav_source')}
+							</a>
+							<div className="flex items-center gap-3 px-3 py-2">
+								<ThemeSwitcher />
+								<LanguageSwitcher />
+							</div>
+						</nav>
+					)}
+				</div>
+			</header>
+		</>
+	)
+}

packages/website/src/components/HighlightSyntax.module.css

@@ -0,0 +1,126 @@
+.syntax {
+	white-space: pre-wrap;
+	word-break: break-word;
+	overflow-wrap: break-word;
+	font-family: monospace;
+	color: #171717;
+}
+
+:global(.dark) .syntax {
+	color: #e0e0e0;
+}
+
+/* JavaScript/TypeScript 关键字 */
+.keyword {
+	color: #d73a49;
+	font-weight: 600;
+}
+
+:global(.dark) .keyword {
+	color: #ff6b6b;
+}
+
+/* TypeScript 特定关键字 (interface, type, enum, etc.) */
+.tsKeyword {
+	color: #af00db;
+	font-weight: 600;
+}
+
+:global(.dark) .tsKeyword {
+	color: #c792ea;
+}
+
+/* TypeScript 内置类型 */
+.type {
+	color: #267f99;
+	font-weight: 500;
+}
+
+:global(.dark) .type {
+	color: #4ec9b0;
+}
+
+/* 字符串 */
+.string {
+	color: #1d6eca;
+}
+
+:global(.dark) .string {
+	color: #4fc3f7;
+}
+
+/* 数字 */
+.number {
+	color: #00c583;
+}
+
+:global(.dark) .number {
+	color: #66bb6a;
+}
+
+/* 布尔值和字面量 (true, false, null, undefined) */
+.literal {
+	color: #0000ff;
+	font-weight: 500;
+}
+
+:global(.dark) .literal {
+	color: #569cd6;
+}
+
+/* 注释 */
+.comment {
+	color: #6a737d;
+	font-style: italic;
+}
+
+:global(.dark) .comment {
+	color: #9e9e9e;
+}
+
+/* 装饰器 (@decorator) */
+.decorator {
+	color: #e0aa00;
+	font-weight: 500;
+}
+
+:global(.dark) .decorator {
+	color: #dcdcaa;
+}
+
+/* 箭头函数 (=>) */
+.arrow {
+	color: #d73a49;
+	font-weight: bold;
+}
+
+:global(.dark) .arrow {
+	color: #ff6b6b;
+}
+
+/* 标识符（变量名、函数名等） */
+.identifier {
+	color: #171717;
+}
+
+:global(.dark) .identifier {
+	color: #e0e0e0;
+}
+
+/* 属性访问 (.property) */
+.property {
+	color: #0550ae;
+}
+
+:global(.dark) .property {
+	color: #9cdcfe;
+}
+
+/* 运算符 */
+.operator {
+	color: #5a5a5a;
+}
+
+:global(.dark) .operator {
+	color: #d4d4d4;
+}

packages/website/src/components/HighlightSyntax.tsx

@@ -0,0 +1,176 @@
+/**
+ * js 语法高亮组件，适合在文章中演示代码片段
+ */
+import React from 'react'
+
+import styles from './HighlightSyntax.module.css'
+
+interface HighlightSyntaxProps {
+	code: string
+}
+
+// JavaScript/TypeScript 关键字
+const keywords =
+	'async|await|function|const|let|var|if|else|for|while|return|try|catch|finally|class|extends|from|import|export|default|undefined|throw|break|continue|switch|case|do|with|yield|delete|typeof|void|static|get|set|super|debugger'
+
+// TypeScript 特定关键字
+const tsKeywords =
+	'interface|type|enum|namespace|module|declare|abstract|implements|public|private|protected|readonly|as|satisfies|infer|keyof|is'
+
+// 布尔值和空值
+const literals = 'true|false|null|undefined|NaN|Infinity'
+
+// TypeScript 内置类型
+const tsTypes =
+	'string|number|boolean|any|unknown|never|void|object|symbol|bigint|Array|Promise|Record|Partial|Required|Readonly|Pick|Omit|Exclude|Extract|NonNullable|ReturnType|Parameters|ConstructorParameters|InstanceType|ThisType|Uppercase|Lowercase|Capitalize|Uncapitalize'
+
+// 辅助函数：转义 HTML 特殊字符
+function escapeHtml(text: string): string {
+	return text.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;')
+}
+
+// 语法高亮函数，先提取 token 再转义和高亮
+function highlightSyntax(code: string): string {
+	// 构建正则模式，包含更多 token 类型（在原始文本上匹配）
+	const pattern = new RegExp(
+		'(' +
+			// 1. 字符串（双引号、单引号、模板字符串）
+			'"([^"\\\\]|\\\\.)*"|' +
+			"'([^'\\\\]|\\\\.)*'|" +
+			'`([^`\\\\]|\\\\.)*`|' +
+			// 2. 注释（单行和多行）
+			'//[^\\n]*|' +
+			'/\\*[\\s\\S]*?\\*/|' +
+			// 3. 装饰器
+			'@[a-zA-Z_$][\\w$]*|' +
+			// 4. 数字（包括小数、十六进制、科学计数法）
+			'\\b0[xX][0-9a-fA-F]+\\b|' +
+			'\\b\\d+\\.?\\d*(?:[eE][+-]?\\d+)?\\b|' +
+			// 5. TypeScript/JavaScript 关键字
+			'\\b(?:' +
+			keywords +
+			'|' +
+			tsKeywords +
+			'|' +
+			literals +
+			')\\b|' +
+			// 6. TypeScript 内置类型
+			'\\b(?:' +
+			tsTypes +
+			')\\b|' +
+			// 7. 箭头函数
+			'=>|' +
+			// 8. 函数调用（函数名后跟括号）
+			'\\b[a-zA-Z_$][\\w$]*(?=\\()|' +
+			// 9. 属性访问
+			'\\.[a-zA-Z_$][\\w$]*|' +
+			// 10. 运算符和特殊符号
+			'[+\\-*/%&|^!~<>=?:]+|' +
+			'[{}\\[\\]();,.]' +
+			')',
+		'g'
+	)
+
+	const tokens: string[] = []
+	let lastIndex = 0
+	let match: RegExpExecArray | null
+	while ((match = pattern.exec(code)) !== null) {
+		if (match.index > lastIndex) {
+			const gap = code.slice(lastIndex, match.index)
+			// 将间隙按空白符分割，保留空白符
+			tokens.push(...gap.split(/(\s+)/))
+		}
+		tokens.push(match[0])
+		lastIndex = pattern.lastIndex
+	}
+	if (lastIndex < code.length) {
+		tokens.push(...code.slice(lastIndex).split(/(\s+)/))
+	}
+
+	const highlighted = tokens
+		.map((token) => {
+			// 空白符直接返回
+			if (/^\s+$/.test(token)) {
+				return token
+			}
+
+			// 1. 注释（单行和多行）
+			if (/^\/\/.*$/.test(token) || /^\/\*[\s\S]*?\*\/$/.test(token)) {
+				return `<span class="${styles.comment}">${escapeHtml(token)}</span>`
+			}
+
+			// 2. 字符串
+			if (
+				/^"([^"\\]|\\.)*"$/.test(token) ||
+				/^'([^'\\]|\\.)*'$/.test(token) ||
+				/^`([^`\\]|\\.)*`$/.test(token)
+			) {
+				return `<span class="${styles.string}">${escapeHtml(token)}</span>`
+			}
+
+			// 3. 数字
+			if (/^(0[xX][0-9a-fA-F]+|\d+\.?\d*(?:[eE][+-]?\d+)?)$/.test(token)) {
+				return `<span class="${styles.number}">${escapeHtml(token)}</span>`
+			}
+
+			// 4. 布尔值和特殊字面量
+			if (new RegExp(`^(?:${literals})$`).test(token)) {
+				return `<span class="${styles.literal}">${escapeHtml(token)}</span>`
+			}
+
+			// 5. JavaScript/TypeScript 关键字
+			if (new RegExp(`^(?:${keywords})$`).test(token)) {
+				return `<span class="${styles.keyword}">${escapeHtml(token)}</span>`
+			}
+
+			// 6. TypeScript 特定关键字
+			if (new RegExp(`^(?:${tsKeywords})$`).test(token)) {
+				return `<span class="${styles.tsKeyword}">${escapeHtml(token)}</span>`
+			}
+
+			// 7. TypeScript 内置类型
+			if (new RegExp(`^(?:${tsTypes})$`).test(token)) {
+				return `<span class="${styles.type}">${escapeHtml(token)}</span>`
+			}
+
+			// 8. 装饰器
+			if (/^@[a-zA-Z_$][\w$]*$/.test(token)) {
+				return `<span class="${styles.decorator}">${escapeHtml(token)}</span>`
+			}
+
+			// 9. 箭头函数
+			if (token === '=>') {
+				return `<span class="${styles.arrow}">${escapeHtml(token)}</span>`
+			}
+
+			// 10. 函数调用和标识符
+			if (/^[a-zA-Z_$][\w$]*$/.test(token)) {
+				return `<span class="${styles.identifier}">${escapeHtml(token)}</span>`
+			}
+
+			// 11. 属性访问
+			if (/^\.[a-zA-Z_$][\w$]*$/.test(token)) {
+				return `<span class="${styles.property}">${escapeHtml(token)}</span>`
+			}
+
+			// 12. 运算符
+			if (/^[+\-*/%&|^!~<>=?:]+$/.test(token)) {
+				return `<span class="${styles.operator}">${escapeHtml(token)}</span>`
+			}
+
+			// 13. 其他符号，需要转义
+			return escapeHtml(token)
+		})
+		.join('')
+
+	return highlighted
+}
+
+const HighlightSyntaxClient: React.FC<HighlightSyntaxProps> = ({ code }) => {
+	const htmlContent = highlightSyntax(code)
+
+	// eslint-disable-next-line react-dom/no-dangerously-set-innerhtml
+	return <code className={styles.syntax} dangerouslySetInnerHTML={{ __html: htmlContent }} />
+}
+
+export default HighlightSyntaxClient

packages/website/src/components/LanguageSwitcher.tsx

@@ -0,0 +1,115 @@
+import { useEffect, useRef, useState } from 'react'
+import { useTranslation } from 'react-i18next'
+
+export default function LanguageSwitcher() {
+	const { i18n, t } = useTranslation('common')
+	const [isOpen, setIsOpen] = useState(false)
+	const dropdownRef = useRef<HTMLDivElement>(null)
+
+	const currentLang = i18n.language
+
+	const languages = [
+		{ code: 'zh-CN', label: '中文' },
+		{ code: 'en-US', label: 'English' },
+	]
+
+	const currentLanguage = languages.find((lang) => lang.code === currentLang) || languages[0]
+
+	const handleLanguageChange = (langCode: string) => {
+		i18n.changeLanguage(langCode)
+		setIsOpen(false)
+	}
+
+	// Close dropdown when clicking outside
+	useEffect(() => {
+		const handleClickOutside = (event: MouseEvent) => {
+			if (dropdownRef.current && !dropdownRef.current.contains(event.target as Node)) {
+				setIsOpen(false)
+			}
+		}
+
+		if (isOpen) {
+			document.addEventListener('mousedown', handleClickOutside)
+		}
+
+		return () => {
+			document.removeEventListener('mousedown', handleClickOutside)
+		}
+	}, [isOpen])
+
+	return (
+		<div className="relative" ref={dropdownRef}>
+			<button
+				onClick={() => setIsOpen(!isOpen)}
+				className="flex items-center gap-2 px-3 py-1.5 rounded-lg bg-gray-100 dark:bg-gray-800 hover:bg-gray-200 dark:hover:bg-gray-700 transition-colors text-sm font-medium border border-gray-200 dark:border-gray-700 text-gray-700 dark:text-gray-300"
+				aria-label={t('language.switch_label')}
+				aria-expanded={isOpen}
+				aria-haspopup="true"
+			>
+				<svg
+					className="w-4 h-4"
+					fill="none"
+					stroke="currentColor"
+					viewBox="0 0 24 24"
+					aria-hidden="true"
+				>
+					<path
+						strokeLinecap="round"
+						strokeLinejoin="round"
+						strokeWidth={2}
+						d="M3 5h12M9 3v2m1.048 9.5A18.022 18.022 0 016.412 9m6.088 9h7M11 21l5-10 5 10M12.751 5C11.783 10.77 8.07 15.61 3 18.129"
+					/>
+				</svg>
+				<span>{currentLanguage.label}</span>
+				<svg
+					className={`w-4 h-4 transition-transform duration-200 ${isOpen ? 'rotate-180' : ''}`}
+					fill="none"
+					stroke="currentColor"
+					viewBox="0 0 24 24"
+					aria-hidden="true"
+				>
+					<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M19 9l-7 7-7-7" />
+				</svg>
+			</button>
+
+			{isOpen && (
+				<div
+					className="absolute right-0 mt-2 w-40 bg-white dark:bg-gray-800 rounded-lg shadow-lg border border-gray-200 dark:border-gray-700 py-1 z-50"
+					role="menu"
+					aria-orientation="vertical"
+				>
+					{languages.map((lang) => (
+						<button
+							key={lang.code}
+							onClick={() => handleLanguageChange(lang.code)}
+							className={`w-full flex items-center gap-2 px-4 py-2 text-sm text-left hover:bg-gray-100 dark:hover:bg-gray-700 transition-colors ${
+								currentLang === lang.code
+									? 'bg-blue-50 dark:bg-blue-900/20 text-blue-700 dark:text-blue-300'
+									: 'text-gray-700 dark:text-gray-300'
+							}`}
+							role="menuitem"
+						>
+							<span>{lang.label}</span>
+							{currentLang === lang.code && (
+								<svg
+									className="w-4 h-4 ml-auto"
+									fill="none"
+									stroke="currentColor"
+									viewBox="0 0 24 24"
+									aria-hidden="true"
+								>
+									<path
+										strokeLinecap="round"
+										strokeLinejoin="round"
+										strokeWidth={2}
+										d="M5 13l4 4L19 7"
+									/>
+								</svg>
+							)}
+						</button>
+					))}
+				</div>
+			)}
+		</div>
+	)
+}

packages/website/src/components/ThemeSwitcher.tsx

@@ -0,0 +1,133 @@
+import { useEffect, useState } from 'react'
+
+type Theme = 'light' | 'dark'
+
+export default function ThemeSwitcher() {
+	const [theme, setTheme] = useState<Theme>(() => {
+		// 初始化时读取保存的主题
+		if (typeof window !== 'undefined') {
+			const savedTheme = localStorage.getItem('theme') as Theme | null
+			if (savedTheme === 'light' || savedTheme === 'dark') {
+				return savedTheme
+			}
+			// 默认跟随系统
+			return window.matchMedia('(prefers-color-scheme: dark)').matches ? 'dark' : 'light'
+		}
+		return 'light'
+	})
+
+	useEffect(() => {
+		// 应用主题
+		if (theme === 'dark') {
+			document.documentElement.classList.add('dark')
+			document.documentElement.style.colorScheme = 'dark'
+		} else {
+			document.documentElement.classList.remove('dark')
+			document.documentElement.style.colorScheme = 'light'
+		}
+		// 保存到 localStorage
+		localStorage.setItem('theme', theme)
+	}, [theme])
+
+	// 监听系统主题变化
+	useEffect(() => {
+		const mediaQuery = window.matchMedia('(prefers-color-scheme: dark)')
+
+		const handleSystemThemeChange = (e: MediaQueryListEvent) => {
+			// 只有在用户未手动设置时才自动跟随系统
+			const savedTheme = localStorage.getItem('theme')
+			if (!savedTheme) {
+				setTheme(e.matches ? 'dark' : 'light')
+			}
+		}
+
+		mediaQuery.addEventListener('change', handleSystemThemeChange)
+		return () => mediaQuery.removeEventListener('change', handleSystemThemeChange)
+	}, [])
+
+	const toggleTheme = () => {
+		setTheme((prev) => (prev === 'light' ? 'dark' : 'light'))
+	}
+
+	return (
+		<button
+			onClick={toggleTheme}
+			className="relative inline-flex items-center h-8 w-16 rounded-full transition-colors duration-300 ease-in-out focus:outline-none"
+			style={{
+				backgroundColor: theme === 'dark' ? '#1e293b' : '#e0f2fe',
+			}}
+			aria-label={theme === 'light' ? 'Switch to dark mode' : 'Switch to light mode'}
+			role="switch"
+			aria-checked={theme === 'dark'}
+		>
+			{/* 滑块 */}
+			<span
+				className="inline-block h-6 w-6 transform rounded-full transition-all duration-300 ease-in-out shadow-md"
+				style={{
+					backgroundColor: theme === 'dark' ? '#475569' : '#fbbf24',
+					transform: theme === 'dark' ? 'translateX(2.25rem)' : 'translateX(0.25rem)',
+				}}
+			>
+				{/* 图标 */}
+				<span className="flex items-center justify-center h-full w-full">
+					{theme === 'light' ? (
+						// 太阳图标
+						<svg
+							className="w-4 h-4 text-white"
+							fill="currentColor"
+							viewBox="0 0 20 20"
+							aria-hidden="true"
+						>
+							<path
+								fillRule="evenodd"
+								d="M10 2a1 1 0 011 1v1a1 1 0 11-2 0V3a1 1 0 011-1zm4 8a4 4 0 11-8 0 4 4 0 018 0zm-.464 4.95l.707.707a1 1 0 001.414-1.414l-.707-.707a1 1 0 00-1.414 1.414zm2.12-10.607a1 1 0 010 1.414l-.706.707a1 1 0 11-1.414-1.414l.707-.707a1 1 0 011.414 0zM17 11a1 1 0 100-2h-1a1 1 0 100 2h1zm-7 4a1 1 0 011 1v1a1 1 0 11-2 0v-1a1 1 0 011-1zM5.05 6.464A1 1 0 106.465 5.05l-.708-.707a1 1 0 00-1.414 1.414l.707.707zm1.414 8.486l-.707.707a1 1 0 01-1.414-1.414l.707-.707a1 1 0 011.414 1.414zM4 11a1 1 0 100-2H3a1 1 0 000 2h1z"
+								clipRule="evenodd"
+							/>
+						</svg>
+					) : (
+						// 月亮图标
+						<svg
+							className="w-4 h-4 text-slate-200"
+							fill="currentColor"
+							viewBox="0 0 20 20"
+							aria-hidden="true"
+						>
+							<path d="M17.293 13.293A8 8 0 016.707 2.707a8.001 8.001 0 1010.586 10.586z" />
+						</svg>
+					)}
+				</span>
+			</span>
+
+			{/* 背景装饰 */}
+			<span
+				className="absolute inset-0 flex items-center justify-between px-2 pointer-events-none"
+				aria-hidden="true"
+			>
+				{/* 左侧太阳（浅色模式时显示） */}
+				<span
+					className={`transition-opacity duration-300 ${
+						theme === 'light' ? 'opacity-0' : 'opacity-40'
+					}`}
+				>
+					<svg className="w-4 h-4 text-sky-400" fill="currentColor" viewBox="0 0 20 20">
+						<path
+							fillRule="evenodd"
+							d="M10 2a1 1 0 011 1v1a1 1 0 11-2 0V3a1 1 0 011-1zm4 8a4 4 0 11-8 0 4 4 0 018 0zm-.464 4.95l.707.707a1 1 0 001.414-1.414l-.707-.707a1 1 0 00-1.414 1.414zm2.12-10.607a1 1 0 010 1.414l-.706.707a1 1 0 11-1.414-1.414l.707-.707a1 1 0 011.414 0zM17 11a1 1 0 100-2h-1a1 1 0 100 2h1zm-7 4a1 1 0 011 1v1a1 1 0 11-2 0v-1a1 1 0 011-1zM5.05 6.464A1 1 0 106.465 5.05l-.708-.707a1 1 0 00-1.414 1.414l.707.707zm1.414 8.486l-.707.707a1 1 0 01-1.414-1.414l.707-.707a1 1 0 011.414 1.414zM4 11a1 1 0 100-2H3a1 1 0 000 2h1z"
+							clipRule="evenodd"
+						/>
+					</svg>
+				</span>
+				{/* 右侧月亮（深色模式时显示） */}
+				<span
+					className={`transition-opacity duration-300 ${
+						theme === 'dark' ? 'opacity-0' : 'opacity-40'
+					}`}
+				>
+					<svg className="w-4 h-4 text-slate-400" fill="currentColor" viewBox="0 0 20 20">
+						<path d="M17.293 13.293A8 8 0 016.707 2.707a8.001 8.001 0 1010.586 10.586z" />
+					</svg>
+				</span>
+			</span>
+		</button>
+	)
+}

packages/website/src/components/icons.tsx

@@ -0,0 +1,75 @@
+// SVG图标组件集合，用于Header等地方复用
+
+interface IconProps {
+	className?: string
+	'aria-hidden'?: boolean
+}
+
+export function BookIcon({ className = 'w-4 h-4', ...props }: IconProps) {
+	return (
+		<svg
+			className={className}
+			fill="none"
+			stroke="currentColor"
+			viewBox="0 0 24 24"
+			aria-hidden="true"
+			{...props}
+		>
+			<path
+				strokeLinecap="round"
+				strokeLinejoin="round"
+				strokeWidth={2}
+				d="M12 6.253v13m0-13C10.832 5.477 9.246 5 7.5 5S4.168 5.477 3 6.253v13C4.168 18.477 5.754 18 7.5 18s3.332.477 4.5 1.253m0-13C13.168 5.477 14.754 5 16.5 5c1.747 0 3.332.477 4.5 1.253v13C19.832 18.477 18.247 18 16.5 18c-1.746 0-3.332.477-4.5 1.253"
+			/>
+		</svg>
+	)
+}
+
+export function GithubIcon({ className = 'w-4 h-4', ...props }: IconProps) {
+	return (
+		<svg
+			className={className}
+			fill="currentColor"
+			viewBox="0 0 24 24"
+			aria-hidden="true"
+			{...props}
+		>
+			<path d="M12 0c-6.626 0-12 5.373-12 12 0 5.302 3.438 9.8 8.207 11.387.599.111.793-.261.793-.577v-2.234c-3.338.726-4.033-1.416-4.033-1.416-.546-1.387-1.333-1.756-1.333-1.756-1.089-.745.083-.729.083-.729 1.205.084 1.839 1.237 1.839 1.237 1.07 1.834 2.807 1.304 3.492.997.107-.775.418-1.305.762-1.604-2.665-.305-5.467-1.334-5.467-5.931 0-1.311.469-2.381 1.236-3.221-.124-.303-.535-1.524.117-3.176 0 0 1.008-.322 3.301 1.23.957-.266 1.983-.399 3.003-.404 1.02.005 2.047.138 3.006.404 2.291-1.552 3.297-1.23 3.297-1.23.653 1.653.242 2.874.118 3.176.77.84 1.235 1.911 1.235 3.221 0 4.609-2.807 5.624-5.479 5.921.43.372.823 1.102.823 2.222v3.293c0 .319.192.694.801.576 4.765-1.589 8.199-6.086 8.199-11.386 0-6.627-5.373-12-12-12z" />
+		</svg>
+	)
+}
+
+export function MenuIcon({ className = 'w-6 h-6', ...props }: IconProps) {
+	return (
+		<svg
+			className={className}
+			fill="none"
+			stroke="currentColor"
+			viewBox="0 0 24 24"
+			aria-hidden="true"
+			{...props}
+		>
+			<path
+				strokeLinecap="round"
+				strokeLinejoin="round"
+				strokeWidth={2}
+				d="M4 6h16M4 12h16M4 18h16"
+			/>
+		</svg>
+	)
+}
+
+export function CloseIcon({ className = 'w-6 h-6', ...props }: IconProps) {
+	return (
+		<svg
+			className={className}
+			fill="none"
+			stroke="currentColor"
+			viewBox="0 0 24 24"
+			aria-hidden="true"
+			{...props}
+		>
+			<path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M6 18L18 6M6 6l12 12" />
+		</svg>
+	)
+}

packages/website/src/docs/features/custom-tools/page.tsx

@@ -1,21 +1,24 @@
-import BetaNotice from '@pages/components/BetaNotice'
-import CodeEditor from '@pages/components/CodeEditor'
+import { useTranslation } from 'react-i18next'
+
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function CustomTools() {
+	const { t } = useTranslation('docs')
+
 	return (
 		<div>
-			<h1 className="text-4xl font-bold mb-6">自定义工具</h1>
+			<h1 className="text-4xl font-bold mb-6">{t('custom_tools.title')}</h1>
 
-			<p className="text-xl text-foreground/80 mb-8 leading-relaxed">
-				通过注册自定义工具，扩展 AI Agent 的能力边界。使用 Zod 定义严格的输入接口，让 AI
-				安全调用你的业务逻辑。
+			<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
+				{t('custom_tools.subtitle')}
 			</p>
 
 			<div className="space-y-8">
 				<section>
-					<h2 className="text-2xl font-bold mb-4">工具注册</h2>
-					<p className="text-foreground/80 mb-4">
-						每个自定义工具需要定义四个核心属性：name、description、input schema 和 execute 函数。
+					<h2 className="text-2xl font-bold mb-4">{t('custom_tools.registration')}</h2>
+					<p className="text-gray-600 dark:text-gray-300 mb-4">
+						{t('custom_tools.registration_desc')}
 					</p>
 
 					<CodeEditor
@@ -49,13 +52,12 @@ const pageAgent = new PageAgent({customTools})
 				</section>
 
 				<section>
-					<h2 className="text-2xl font-bold mb-4">页面过滤器</h2>
+					<h2 className="text-2xl font-bold mb-4">{t('custom_tools.page_filter')}</h2>
 
 					<BetaNotice />
 
-					<p className="text-foreground/80 mb-4">
-						通过 <code className="bg-gray-200 dark:bg-gray-700 px-2 py-1 rounded">pageFilter</code>{' '}
-						属性控制工具在哪些页面可见，提升安全性和用户体验。
+					<p className="text-gray-600 dark:text-gray-300 mb-4">
+						{t('custom_tools.page_filter_desc')}
 					</p>
 
 					<CodeEditor
@@ -82,16 +84,16 @@ const pageAgent = new PageAgent({customTools})
 				</section>
 
 				<section>
-					<h2 className="text-2xl font-bold mb-4">最佳实践</h2>
+					<h2 className="text-2xl font-bold mb-4">{t('custom_tools.best_practices')}</h2>
 					<div className="space-y-4">
 						<div className="p-4 bg-yellow-50 dark:bg-yellow-900/20 rounded-lg">
 							<h3 className="text-lg font-semibold text-yellow-900 dark:text-yellow-300 mb-2">
-								⚡ 性能优化
+								{t('custom_tools.bp_performance')}
 							</h3>
-							<ul className="text-foreground/80 space-y-1 text-sm">
-								<li>• 使用 pageFilter 减少不必要的工具加载</li>
-								<li>• 在 execute 函数中实现适当的缓存机制</li>
-								<li>• 避免在工具中执行耗时的同步操作</li>
+							<ul className="text-gray-600 dark:text-gray-300 space-y-1 text-sm">
+								<li>{t('custom_tools.bp_1')}</li>
+								<li>{t('custom_tools.bp_2')}</li>
+								<li>{t('custom_tools.bp_3')}</li>
 							</ul>
 						</div>
 					</div>

packages/website/src/docs/features/data-masking/page.tsx

@@ -1,5 +1,5 @@
-import BetaNotice from '@pages/components/BetaNotice'
-import CodeEditor from '@pages/components/CodeEditor'
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function DataMasking() {
 	return (
@@ -8,7 +8,7 @@ export default function DataMasking() {
 
 			<BetaNotice />
 
-			<p className="text-xl text-foreground/80 mb-6 leading-relaxed">
+			<p className="text-xl text-gray-600 dark:text-gray-300 mb-6 leading-relaxed">
 				保护敏感数据，确保 AI 处理过程中的数据安全。
 			</p>
 
@@ -19,14 +19,18 @@ export default function DataMasking() {
 					<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">
 						🔒 自动脱敏
 					</h3>
-					<p className="text-foreground/80">自动识别并脱敏手机号、身份证号、银行卡号等敏感信息。</p>
+					<p className="text-gray-600 dark:text-gray-300">
+						自动识别并脱敏手机号、身份证号、银行卡号等敏感信息。
+					</p>
 				</div>
 
 				<div className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
 					<h3 className="text-lg font-semibold mb-2 text-purple-900 dark:text-purple-300">
 						⚙️ 自定义规则
 					</h3>
-					<p className="text-foreground/80">支持自定义脱敏规则，适应不同业务场景的数据保护需求。</p>
+					<p className="text-gray-600 dark:text-gray-300">
+						支持自定义脱敏规则，适应不同业务场景的数据保护需求。
+					</p>
 				</div>
 			</div>
 

packages/website/src/docs/features/knowledge-injection/page.tsx

@@ -1,5 +1,5 @@
-import BetaNotice from '@pages/components/BetaNotice'
-import CodeEditor from '@pages/components/CodeEditor'
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function KnowledgeInjection() {
 	return (
@@ -8,7 +8,7 @@ export default function KnowledgeInjection() {
 
 			<BetaNotice />
 
-			<p className="text-xl text-foreground/80 mb-8 leading-relaxed">
+			<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
 				通过多层次的知识注入，让 AI 深度理解你的业务场景和应用逻辑，实现更精准的自动化操作。
 			</p>
 
@@ -20,8 +20,10 @@ export default function KnowledgeInjection() {
 					<h3 className="text-xl font-semibold mb-3 text-purple-900 dark:text-purple-300">
 						🎯 系统级指令
 					</h3>
-					<p className="text-foreground/80 mb-4">为 AI 设定全局行为准则和工作风格。</p>
-					<ul className="list-disc list-inside space-y-2 text-foreground/70">
+					<p className="text-gray-600 dark:text-gray-300 mb-4">
+						为 AI 设定全局行为准则和工作风格。
+					</p>
+					<ul className="list-disc list-inside space-y-2 text-gray-500 dark:text-gray-400">
 						<li>定义 AI 的工作风格和交互方式</li>
 						<li>设置安全边界和操作限制</li>
 						<li>指定错误处理和异常情况的应对策略</li>
@@ -57,13 +59,13 @@ const pageAgent = new PageAgent({
 					<h3 className="text-xl font-semibold mb-3 text-blue-900 dark:text-blue-300">
 						� 业务领域知识
 					</h3>
-					<p className="text-foreground/80 mb-4">
+					<p className="text-gray-600 dark:text-gray-300 mb-4">
 						注入应用的核心业务知识，包括产品介绍、操作流程、术语定义等，让 AI 理解业务上下文。
 					</p>
 					<div className="grid md:grid-cols-2 gap-4">
 						<div className="space-y-2">
 							<h4 className="font-semibold text-blue-800 dark:text-blue-200">产品知识</h4>
-							<ul className="list-disc list-inside text-sm text-foreground/70 space-y-1">
+							<ul className="list-disc list-inside text-sm text-gray-500 dark:text-gray-400 space-y-1">
 								<li>产品功能和特性介绍</li>
 								<li>用户角色和权限体系</li>
 								<li>业务规则和约束条件</li>
@@ -71,7 +73,7 @@ const pageAgent = new PageAgent({
 						</div>
 						<div className="space-y-2">
 							<h4 className="font-semibold text-blue-800 dark:text-blue-200">操作指南</h4>
-							<ul className="list-disc list-inside text-sm text-foreground/70 space-y-1">
+							<ul className="list-disc list-inside text-sm text-gray-500 dark:text-gray-400 space-y-1">
 								<li>标准操作流程定义</li>
 								<li>异常情况处理方案</li>
 								<li>术语和概念解释</li>
@@ -111,21 +113,25 @@ pageAgent.knowledge.setAppKnowledge(\`
 					<h3 className="text-xl font-semibold mb-3 text-green-900 dark:text-green-300">
 						📄 页面级精准指导
 					</h3>
-					<p className="text-foreground/80 mb-4">
+					<p className="text-gray-600 dark:text-gray-300 mb-4">
 						为特定页面提供精确的操作指导和元素说明，让 AI 准确理解页面结构和交互逻辑。
 					</p>
 					<div className="grid md:grid-cols-3 gap-4">
 						<div className="space-y-2">
 							<h4 className="font-semibold text-green-800 dark:text-green-200">元素标注</h4>
-							<p className="text-sm text-foreground/70">为页面元素添加语义化描述</p>
+							<p className="text-sm text-gray-500 dark:text-gray-400">为页面元素添加语义化描述</p>
 						</div>
 						<div className="space-y-2">
 							<h4 className="font-semibold text-green-800 dark:text-green-200">交互说明</h4>
-							<p className="text-sm text-foreground/70">定义元素的交互行为和预期结果</p>
+							<p className="text-sm text-gray-500 dark:text-gray-400">
+								定义元素的交互行为和预期结果
+							</p>
 						</div>
 						<div className="space-y-2">
 							<h4 className="font-semibold text-green-800 dark:text-green-200">页面逻辑</h4>
-							<p className="text-sm text-foreground/70">说明页面的业务逻辑和状态变化</p>
+							<p className="text-sm text-gray-500 dark:text-gray-400">
+								说明页面的业务逻辑和状态变化
+							</p>
 						</div>
 					</div>
 				</div>

packages/website/src/docs/features/model-integration/page.tsx

@@ -0,0 +1,164 @@
+import { useTranslation } from 'react-i18next'
+
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
+
+export default function ModelIntegration() {
+	const { t } = useTranslation('docs')
+
+	return (
+		<div>
+			<h1 className="text-4xl font-bold mb-6">{t('model_integration.title')}</h1>
+
+			<p className="text-xl text-gray-600 dark:text-gray-300 mb-6 leading-relaxed">
+				{t('model_integration.subtitle')}
+			</p>
+
+			<h2 className="text-2xl font-bold mb-3">{t('model_integration.recommended')}</h2>
+
+			<div className="grid md:grid-cols-3 gap-4 mb-6">
+				<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
+					<h3 className="text-lg font-semibold mb-2 text-green-900 dark:text-green-300">
+						{t('model_integration.model_gpt4_title')}
+					</h3>
+					<p className="text-sm text-gray-600 dark:text-gray-300 mb-2">
+						{t('model_integration.model_gpt4_badge')}
+					</p>
+					<ul className="text-sm text-gray-500 dark:text-gray-400 space-y-1">
+						<li>{t('model_integration.model_gpt4_1')}</li>
+						<li>{t('model_integration.model_gpt4_2')}</li>
+						<li>{t('model_integration.model_gpt4_3')}</li>
+					</ul>
+				</div>
+
+				<div className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
+					<h3 className="text-lg font-semibold mb-2 text-purple-900 dark:text-purple-300">
+						{t('model_integration.model_deepseek_title')}
+					</h3>
+					<p className="text-sm text-gray-600 dark:text-gray-300 mb-2">
+						{t('model_integration.model_deepseek_badge')}
+					</p>
+					<ul className="text-sm text-gray-500 dark:text-gray-400 space-y-1">
+						<li>{t('model_integration.model_deepseek_1')}</li>
+						<li>{t('model_integration.model_deepseek_2')}</li>
+						<li>{t('model_integration.model_deepseek_3')}</li>
+					</ul>
+				</div>
+
+				<div className="p-4 bg-orange-50 dark:bg-orange-900/20 rounded-lg">
+					<h3 className="text-lg font-semibold mb-2 text-orange-900 dark:text-orange-300">
+						{t('model_integration.model_qwen_title')}
+					</h3>
+					<p className="text-sm text-gray-600 dark:text-gray-300 mb-2">
+						{t('model_integration.model_qwen_badge')}
+					</p>
+					<ul className="text-sm text-gray-500 dark:text-gray-400 space-y-1">
+						<li>{t('model_integration.model_qwen_1')}</li>
+						<li>{t('model_integration.model_qwen_2')}</li>
+						<li>{t('model_integration.model_qwen_3')}</li>
+					</ul>
+				</div>
+
+				<div className="p-4 bg-orange-50 dark:bg-orange-900/20 rounded-lg">
+					<h3 className="text-lg font-semibold mb-2 text-orange-900 dark:text-orange-300">
+						{t('model_integration.model_gemini_title')}
+					</h3>
+					<p className="text-sm text-gray-600 dark:text-gray-300 mb-2">
+						{t('model_integration.model_gemini_badge')}
+					</p>
+				</div>
+			</div>
+
+			<h2 className="text-2xl font-bold mb-3">{t('model_integration.available')}</h2>
+
+			<div className="p-4 bg-emerald-50 dark:bg-emerald-900/20 rounded-lg mb-6">
+				<h3 className="text-lg font-semibold mb-3 text-emerald-900 dark:text-emerald-300">
+					{t('model_integration.available_verified')}
+				</h3>
+				<div className="flex flex-wrap gap-2">
+					<span className="inline-flex items-center rounded-full bg-emerald-100 dark:bg-emerald-900/40 text-emerald-900 dark:text-emerald-200 px-3 py-1 text-sm">
+						gpt-4.1-mini/4.1/5
+					</span>
+					<span className="inline-flex items-center rounded-full bg-emerald-100 dark:bg-emerald-900/40 text-emerald-900 dark:text-emerald-200 px-3 py-1 text-sm">
+						grok-4/grok-code-fast
+					</span>
+					<span className="inline-flex items-center rounded-full bg-emerald-100 dark:bg-emerald-900/40 text-emerald-900 dark:text-emerald-200 px-3 py-1 text-sm">
+						qwen3
+					</span>
+					<span className="inline-flex items-center rounded-full bg-emerald-100 dark:bg-emerald-900/40 text-emerald-900 dark:text-emerald-200 px-3 py-1 text-sm">
+						deepseek-v3.1/3.2
+					</span>
+					<span className="inline-flex items-center rounded-full bg-emerald-100 dark:bg-emerald-900/40 text-emerald-900 dark:text-emerald-200 px-3 py-1 text-sm">
+						claude-sonnet-4/4.5/haiku-4.5
+					</span>
+					<span className="inline-flex items-center rounded-full bg-emerald-100 dark:bg-emerald-900/40 text-emerald-900 dark:text-emerald-200 px-3 py-1 text-sm">
+						gemini-2.5
+					</span>
+				</div>
+			</div>
+
+			<h2 className="text-2xl font-bold mb-3">{t('model_integration.tips')}</h2>
+
+			<div className="p-4 bg-red-50 dark:bg-red-900/20 rounded-lg mb-6">
+				<ul className="text-sm text-gray-600 dark:text-gray-300 space-y-1 list-disc pl-5">
+					<li>{t('model_integration.tip_1')}</li>
+					<li>{t('model_integration.tip_2')}</li>
+					<li>{t('model_integration.tip_3')}</li>
+				</ul>
+			</div>
+
+			<h2 className="text-2xl font-bold mb-3">{t('model_integration.security')}</h2>
+
+			<div className="p-4 bg-yellow-50 dark:bg-yellow-900/20 border-l-4 border-yellow-500 mb-4">
+				<p className="text-sm font-semibold text-yellow-900 dark:text-yellow-200">
+					{t('model_integration.security_warning')}
+				</p>
+			</div>
+
+			<p className="text-gray-600 dark:text-gray-300 mb-4">
+				{t('model_integration.security_desc')}
+			</p>
+
+			<div className="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg mb-6">
+				<h3 className="text-lg font-semibold mb-3 text-blue-900 dark:text-blue-300">
+					{t('model_integration.security_backend_proxy')}
+				</h3>
+				<p className="text-sm text-gray-600 dark:text-gray-300 mb-3">
+					{t('model_integration.security_backend_desc')}
+				</p>
+				<ul className="text-sm text-gray-600 dark:text-gray-300 space-y-1 list-none pl-0">
+					<li>{t('model_integration.security_method_1')}</li>
+					<li>{t('model_integration.security_method_2')}</li>
+					<li>{t('model_integration.security_method_3')}</li>
+				</ul>
+			</div>
+
+			<h2 className="text-2xl font-bold mb-3">{t('model_integration.configuration')}</h2>
+
+			<CodeEditor
+				code={`
+// 百炼等其他兼容服务
+const pageAgent = new PageAgent({
+  baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
+  apiKey: 'your-api-key',
+  model: 'qwen-plus'
+});
+
+// 私有部署模型
+const pageAgent = new PageAgent({
+  baseURL: 'http://localhost:11434/v1',
+  apiKey: 'N/A',  // Ollama 通常使用任意值
+  model: 'qwen3:latest'
+});
+
+// 测试接口
+// @note: 限流，限制 prompt 内容，限制来源，随时变更，请替换成你自己的
+// @note: 使用 DeepSeek-chat(3.2) 官方版本，使用协议和隐私策略见 DeepSeek 网站
+const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
+const DEMO_BASE_URL = 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
+const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
+`}
+			/>
+		</div>
+	)
+}

packages/website/src/docs/features/security-permissions/page.tsx

@@ -1,4 +1,4 @@
-import BetaNotice from '@pages/components/BetaNotice'
+import BetaNotice from '@/components/BetaNotice'
 
 export default function SecurityPermissions() {
 	return (
@@ -7,7 +7,7 @@ export default function SecurityPermissions() {
 
 			<BetaNotice />
 
-			<p className="text-xl text-foreground/80 mb-8 leading-relaxed">
+			<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
 				page-agent 提供四种安全机制，确保 AI 操作在可控范围内进行。
 			</p>
 
@@ -19,13 +19,15 @@ export default function SecurityPermissions() {
 							<h3 className="text-lg font-semibold text-red-900 dark:text-red-300">
 								🚫 操作黑名单
 							</h3>
-							<p className="text-foreground/80">禁止 AI 操作敏感元素，如删除按钮、支付按钮等。</p>
+							<p className="text-gray-600 dark:text-gray-300">
+								禁止 AI 操作敏感元素，如删除按钮、支付按钮等。
+							</p>
 						</div>
 						<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
 							<h3 className="text-lg font-semibold text-green-900 dark:text-green-300">
 								✅ 操作白名单
 							</h3>
-							<p className="text-foreground/80">明确定义 AI 可以操作的元素范围。</p>
+							<p className="text-gray-600 dark:text-gray-300">明确定义 AI 可以操作的元素范围。</p>
 						</div>
 					</div>
 				</section>
@@ -37,13 +39,13 @@ export default function SecurityPermissions() {
 							<h3 className="text-lg font-semibold text-red-900 dark:text-red-300">
 								🚫 URL 黑名单
 							</h3>
-							<p className="text-foreground/80">禁止 AI 访问敏感页面和危险链接。</p>
+							<p className="text-gray-600 dark:text-gray-300">禁止 AI 访问敏感页面和危险链接。</p>
 						</div>
 						<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
 							<h3 className="text-lg font-semibold text-green-900 dark:text-green-300">
 								✅ URL 白名单
 							</h3>
-							<p className="text-foreground/80">限制 AI 只能访问预定义的安全页面。</p>
+							<p className="text-gray-600 dark:text-gray-300">限制 AI 只能访问预定义的安全页面。</p>
 						</div>
 					</div>
 				</section>
@@ -54,17 +56,21 @@ export default function SecurityPermissions() {
 						<h3 className="text-lg font-semibold mb-2 text-yellow-900 dark:text-yellow-300">
 							⚠️ 高危操作控制
 						</h3>
-						<p className="text-foreground/80 mb-3">
+						<p className="text-gray-600 dark:text-gray-300 mb-3">
 							在 AI 指令中明确列举高危操作，通过两种策略进行控制：
 						</p>
 						<div className="space-y-2">
 							<div className="pl-3 border-l-2 border-red-400">
 								<p className="font-medium text-red-700 dark:text-red-300">完全禁止操作</p>
-								<p className="text-sm text-foreground/70">对极高风险操作明确禁止执行</p>
+								<p className="text-sm text-gray-500 dark:text-gray-400">
+									对极高风险操作明确禁止执行
+								</p>
 							</div>
 							<div className="pl-3 border-l-2 border-orange-400">
 								<p className="font-medium text-orange-700 dark:text-orange-300">需用户确认操作</p>
-								<p className="text-sm text-foreground/70">对中等风险操作要求用户明确同意</p>
+								<p className="text-sm text-gray-500 dark:text-gray-400">
+									对中等风险操作要求用户明确同意
+								</p>
 							</div>
 						</div>
 					</div>

packages/website/src/docs/integration/best-practices/page.tsx

@@ -1,5 +1,5 @@
-import BetaNotice from '@pages/components/BetaNotice'
-import CodeEditor from '@pages/components/CodeEditor'
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function BestPractices() {
 	return (
@@ -19,7 +19,9 @@ export default function BestPractices() {
 					<h3 className="text-lg font-semibold mb-2 text-green-900 dark:text-green-300">
 						⚡ 减少 API 调用
 					</h3>
-					<p className="text-foreground/80 mb-3">合并多个操作指令，减少与 AI 模型的交互次数。</p>
+					<p className="text-gray-600 dark:text-gray-300 mb-3">
+						合并多个操作指令，减少与 AI 模型的交互次数。
+					</p>
 
 					<CodeEditor
 						code={`// 推荐：合并操作
@@ -36,7 +38,9 @@ await pageAgent.execute('点击提交按钮');`}
 					<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">
 						🎯 精确的元素描述
 					</h3>
-					<p className="text-foreground/80">使用具体、明确的元素描述，提高操作成功率。</p>
+					<p className="text-gray-600 dark:text-gray-300">
+						使用具体、明确的元素描述，提高操作成功率。
+					</p>
 				</div>
 			</div>
 
@@ -45,12 +49,12 @@ await pageAgent.execute('点击提交按钮');`}
 			<div className="space-y-3 mb-6">
 				<div className="p-3 bg-red-50 dark:bg-red-900/20 rounded-lg border-l-4 border-red-500">
 					<h3 className="font-semibold mb-1 text-red-900 dark:text-red-300">重要操作保护</h3>
-					<p className="text-foreground/80">对删除、支付等敏感操作设置黑名单保护。</p>
+					<p className="text-gray-600 dark:text-gray-300">对删除、支付等敏感操作设置黑名单保护。</p>
 				</div>
 
 				<div className="p-3 bg-yellow-50 dark:bg-yellow-900/20 rounded-lg border-l-4 border-yellow-500">
 					<h3 className="font-semibold mb-1 text-yellow-900 dark:text-yellow-300">数据脱敏</h3>
-					<p className="text-foreground/80">启用数据脱敏功能，保护用户隐私信息。</p>
+					<p className="text-gray-600 dark:text-gray-300">启用数据脱敏功能，保护用户隐私信息。</p>
 				</div>
 			</div>
 

packages/website/src/docs/integration/cdn-setup/page.tsx

@@ -1,5 +1,5 @@
-import BetaNotice from '@pages/components/BetaNotice'
-import CodeEditor from '@pages/components/CodeEditor'
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function CdnSetup() {
 	return (
@@ -16,7 +16,7 @@ export default function CdnSetup() {
 				className="mb-8"
 				code={`
 // 仅供测试使用，稳定 CDN 待定
-<script src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.2/page-agent.js" crossorigin="true" type="text/javascript"></script>
+<script src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js" crossorigin="true" type="text/javascript"></script>
 
 <script>
 	window.pageAgent.panel.show()
@@ -27,7 +27,7 @@ export default function CdnSetup() {
 				<h3 className="text-lg font-semibold mb-2 text-yellow-900 dark:text-yellow-300">
 					⚠️ 注意事项
 				</h3>
-				<ul className="text-foreground/80 space-y-1">
+				<ul className="text-gray-600 dark:text-gray-300 space-y-1">
 					<li>• 生产环境建议使用固定版本号</li>
 					<li>• 确保 HTTPS 环境下使用</li>
 					<li>• 配置 CSP 策略允许脚本执行</li>

packages/website/src/docs/integration/configuration/page.tsx

@@ -1,4 +1,4 @@
-import CodeEditor from '@pages/components/CodeEditor'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function Configuration() {
 	return (
@@ -9,7 +9,7 @@ export default function Configuration() {
 				className="mb-8"
 				language="typescript"
 				code={`// config
-type PageAgentConfig = LLMConfig & AgentConfig & DomConfig
+type PageAgentConfig = LLMConfig & AgentConfig & PageControllerConfig
 
 interface LLMConfig {
 	baseURL?: string
@@ -70,6 +70,14 @@ interface AgentConfig {
 
 	// page behavior hooks
 
+	/**
+	 * @experimental
+	 * Enable the experimental script execution tool that allows executing generated JavaScript code on the page.
+	 * @note Can cause unpredictable side effects.
+	 * @note May bypass some safe guards and data-masking mechanisms.
+	 */
+	experimentalScriptExecutionTool?: boolean
+
 	/**
 	 * TODO: @unimplemented
 	 * hook when action causes a new page to be opened
@@ -85,12 +93,13 @@ interface AgentConfig {
 	experimentalPreventNewPage?: boolean
 }
 
-interface DomConfig {
+interface PageControllerConfig {
 	interactiveBlacklist?: (Element | (() => Element))[]
 	interactiveWhitelist?: (Element | (() => Element))[]
 	include_attributes?: string[]
 	highlightOpacity?: number
 	highlightLabelOpacity?: number
+	viewportExpansion?: number
 }
 
 `}

packages/website/src/docs/integration/third-party-agent/page.tsx

@@ -1,17 +1,17 @@
-import CodeEditor from '@pages/components/CodeEditor'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function ThirdPartyAgentPage() {
 	return (
 		<div>
 			<h1 className="text-4xl font-bold mb-6">接入第三方 Agent</h1>
-			<p className="mb-6 leading-relaxed">
+			<p className="mb-6 leading-relaxed text-gray-600 dark:text-gray-300">
 				将 pageAgent 作为工具接入你的答疑助手或 Agent 系统，成为你 Agent 的眼和手。
 			</p>
 
 			<div className="bg-blue-50 dark:bg-blue-900/20 rounded-lg p-4 mb-6">
 				<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">💡 核心价值</h3>
 				<p className="text-blue-800 dark:text-blue-200">
-					让你的 Agent 不再只是"嘴巴"，而是拥有"眼睛"和"手"的完整智能体。
+					让你的答疑机器人不再只是"嘴巴"，而是拥有"眼睛"和"手"的完整智能体。
 				</p>
 			</div>
 
@@ -48,26 +48,26 @@ const pageAgentTool = {
 
 			<h2 className="text-2xl font-bold mb-4">应用场景</h2>
 			<div className="grid md:grid-cols-2 gap-4 mb-6">
-				<div className="bg-gradient-to-br from-blue-50 to-purple-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
-					<h4 className="font-semibold mb-2">🤖 智能客服系统</h4>
+				<div className="bg-linear-to-br from-blue-50 to-purple-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
+					<h4 className="font-semibold mb-2 text-gray-900 dark:text-white">🤖 智能客服系统</h4>
 					<p className="text-sm text-gray-600 dark:text-gray-300">
 						客服机器人帮用户直接操作系统，如"帮我提交工单"
 					</p>
 				</div>
-				<div className="bg-gradient-to-br from-green-50 to-blue-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
-					<h4 className="font-semibold mb-2">📋 业务流程助手</h4>
+				<div className="bg-linear-to-br from-green-50 to-blue-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
+					<h4 className="font-semibold mb-2 text-gray-900 dark:text-white">📋 业务流程助手</h4>
 					<p className="text-sm text-gray-600 dark:text-gray-300">
 						引导新员工完成复杂流程，如"完成客户入职"
 					</p>
 				</div>
-				<div className="bg-gradient-to-br from-purple-50 to-pink-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
-					<h4 className="font-semibold mb-2">🎯 个人效率助手</h4>
+				<div className="bg-linear-to-br from-purple-50 to-pink-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
+					<h4 className="font-semibold mb-2 text-gray-900 dark:text-white">🎯 个人效率助手</h4>
 					<p className="text-sm text-gray-600 dark:text-gray-300">
 						跨网站帮你完成任务，如"预订会议室"
 					</p>
 				</div>
-				<div className="bg-gradient-to-br from-orange-50 to-red-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
-					<h4 className="font-semibold mb-2">🔧 运维自动化</h4>
+				<div className="bg-linear-to-br from-orange-50 to-red-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
+					<h4 className="font-semibold mb-2 text-gray-900 dark:text-white">🔧 运维自动化</h4>
 					<p className="text-sm text-gray-600 dark:text-gray-300">
 						通过自然语言操作管理后台，如"重启服务器"
 					</p>
@@ -77,12 +77,12 @@ const pageAgentTool = {
 			<h2 className="text-2xl font-bold mb-4">最佳实践</h2>
 			<div className="space-y-4 mb-6">
 				<div className="p-4 bg-gray-50 dark:bg-gray-800 rounded-lg">
-					<h3 className="text-lg font-semibold mb-2">错误处理</h3>
+					<h3 className="text-lg font-semibold mb-2 text-gray-900 dark:text-white">错误处理</h3>
 					<CodeEditor code={`// @TODO`} language="javascript" />
 				</div>
 
 				<div className="p-4 bg-gray-50 dark:bg-gray-800 rounded-lg">
-					<h3 className="text-lg font-semibold mb-2">权限控制</h3>
+					<h3 className="text-lg font-semibold mb-2 text-gray-900 dark:text-white">权限控制</h3>
 					<CodeEditor code={`// @TODO`} language="javascript" />
 				</div>
 			</div>
@@ -98,9 +98,11 @@ const pageAgentTool = {
 				</ul>
 			</div>
 
-			<div className="bg-gradient-to-r from-green-50 to-blue-50 dark:from-green-900/20 dark:to-blue-900/20 p-4 rounded-lg">
-				<h3 className="text-lg font-semibold mb-2">🎉 开始集成</h3>
-				<p className="mb-3">通过这种方式，你的 Agent 系统就能真正成为用户的智能助手。</p>
+			<div className="bg-linear-to-r from-green-50 to-blue-50 dark:from-green-900/20 dark:to-blue-900/20 p-4 rounded-lg">
+				<h3 className="text-lg font-semibold mb-2 text-gray-900 dark:text-white">🎉 开始集成</h3>
+				<p className="mb-3 text-gray-700 dark:text-gray-300">
+					通过这种方式，你的 Agent 系统就能真正成为用户的智能助手。
+				</p>
 				<a
 					href="/docs/integration/configuration"
 					className="inline-flex items-center px-4 py-2 bg-blue-600 text-white rounded-lg hover:bg-blue-700 transition-colors duration-200"

packages/website/src/docs/introduction/limitations/page.tsx

@@ -1,153 +1,141 @@
+import { useTranslation } from 'react-i18next'
+
 export default function LimitationsPage() {
+	const { t } = useTranslation('docs')
+
 	return (
 		<div className="max-w-4xl mx-auto">
 			<div className="mb-8">
-				<h1 className="text-4xl font-bold mb-4 text-gray-900 dark:text-white">使用限制</h1>
-				<p className="text-xl text-gray-600 dark:text-gray-300">
-					了解 page-agent 当前的功能边界和技术限制
-				</p>
+				<h1 className="text-4xl font-bold mb-4 text-gray-900 dark:text-white">
+					{t('limitations.title')}
+				</h1>
+				<p className="text-xl text-gray-600 dark:text-gray-300">{t('limitations.subtitle')}</p>
 			</div>
 
 			<div className="prose prose-lg dark:prose-invert max-w-none">
-				<h2 className="text-2xl font-bold mb-3">页面支持限制</h2>
+				<h2 className="text-2xl font-bold mb-3">{t('limitations.page_support')}</h2>
 				<div className="bg-blue-50 dark:bg-blue-900/20 border-l-4 border-blue-400 p-4 mb-6">
-					<h3 className="font-semibold text-blue-800 dark:text-blue-200 mb-2">单页应用限制</h3>
+					<h3 className="font-semibold text-blue-800 dark:text-blue-200 mb-2">
+						{t('limitations.spa_limit_title')}
+					</h3>
 					<ul className="text-blue-700 dark:text-blue-300 space-y-2">
-						<li>
-							• <strong>仅支持单页应用（SPA）</strong>：目前只能在单个页面内进行操作
-						</li>
-						<li>
-							• <strong>多页接力功能正在设计中</strong>：暂时无法跨页面执行连续任务
-						</li>
-						<li>
-							• <strong>无法操作未接入该能力的网站</strong>：需要目标网站主动集成 page-agent
-						</li>
+						<li>{t('limitations.spa_limit_1')}</li>
+						<li>{t('limitations.spa_limit_2')}</li>
+						<li>{t('limitations.spa_limit_3')}</li>
 					</ul>
 				</div>
 
-				<h2 className="text-2xl font-bold mb-3">交互行为限制</h2>
+				<h2 className="text-2xl font-bold mb-3">{t('limitations.interaction_limits')}</h2>
 				<div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6 mb-6">
-					<h3 className="font-semibold mb-4">支持的操作</h3>
+					<h3 className="font-semibold mb-4">{t('limitations.supported_ops')}</h3>
 					<div className="grid md:grid-cols-2 gap-4 mb-6">
 						<div className="space-y-2">
 							<div className="flex items-center text-green-600 dark:text-green-400">
 								<span className="mr-2">✅</span>
-								<span>点击操作</span>
+								<span>{t('limitations.op_click')}</span>
 							</div>
 							<div className="flex items-center text-green-600 dark:text-green-400">
 								<span className="mr-2">✅</span>
-								<span>文本输入</span>
+								<span>{t('limitations.op_input')}</span>
 							</div>
 							<div className="flex items-center text-green-600 dark:text-green-400">
 								<span className="mr-2">✅</span>
-								<span>页面滚动</span>
+								<span>{t('limitations.op_scroll')}</span>
 							</div>
 							<div className="flex items-center text-green-600 dark:text-green-400">
 								<span className="mr-2">✅</span>
-								<span>表单提交</span>
+								<span>{t('limitations.op_submit')}</span>
 							</div>
 						</div>
 						<div className="space-y-2">
 							<div className="flex items-center text-green-600 dark:text-green-400">
 								<span className="mr-2">✅</span>
-								<span>选择操作</span>
+								<span>{t('limitations.op_select')}</span>
 							</div>
-
 							<div className="flex items-center text-green-600 dark:text-green-400">
 								<span className="mr-2">✅</span>
-								<span>焦点切换</span>
+								<span>{t('limitations.op_focus')}</span>
 							</div>
 						</div>
 					</div>
 
-					<h3 className="font-semibold mb-4">不支持的操作</h3>
+					<h3 className="font-semibold mb-4">{t('limitations.unsupported_ops')}</h3>
 					<div className="grid md:grid-cols-2 gap-4">
 						<div className="space-y-2">
 							<div className="flex items-center text-red-600 dark:text-red-400">
 								<span className="mr-2">❌</span>
-								<span>鼠标悬停（hover）</span>
+								<span>{t('limitations.op_hover')}</span>
 							</div>
 							<div className="flex items-center text-red-600 dark:text-red-400">
 								<span className="mr-2">❌</span>
-								<span>拖拽操作</span>
+								<span>{t('limitations.op_drag')}</span>
 							</div>
 							<div className="flex items-center text-red-600 dark:text-red-400">
 								<span className="mr-2">❌</span>
-								<span>右键菜单</span>
+								<span>{t('limitations.op_context')}</span>
 							</div>
 						</div>
 						<div className="space-y-2">
 							<div className="flex items-center text-red-600 dark:text-red-400">
 								<span className="mr-2">❌</span>
-								<span>图形绘制</span>
+								<span>{t('limitations.op_draw')}</span>
 							</div>
 							<div className="flex items-center text-red-600 dark:text-red-400">
 								<span className="mr-2">❌</span>
-								<span>键盘快捷键</span>
+								<span>{t('limitations.op_keyboard')}</span>
 							</div>
 							<div className="flex items-center text-red-600 dark:text-red-400">
 								<span className="mr-2">❌</span>
-								<span>基于点击区域或鼠标位置的控制</span>
+								<span>{t('limitations.op_position')}</span>
 							</div>
 						</div>
 					</div>
 				</div>
 
-				<h2 className="text-2xl font-bold mb-3">网页理解限制</h2>
+				<h2 className="text-2xl font-bold mb-3">{t('limitations.understanding_limits')}</h2>
 				<div className="bg-red-50 dark:bg-red-900/20 border-l-4 border-red-400 p-4 mb-6">
-					<h3 className="font-semibold text-red-800 dark:text-red-200 mb-2">无视觉能力</h3>
-					<p className="text-red-700 dark:text-red-300 mb-3">
-						page-agent 基于 DOM 结构进行理解和操作，<strong>没有视觉识别能力</strong>
-						，无法理解以下内容：
-					</p>
+					<h3 className="font-semibold text-red-800 dark:text-red-200 mb-2">
+						{t('limitations.no_vision_title')}
+					</h3>
+					<p className="text-red-700 dark:text-red-300 mb-3">{t('limitations.no_vision_desc')}</p>
 					<ul className="text-red-700 dark:text-red-300 space-y-1">
-						<li>
-							• <strong>图片内容</strong>：无法识别图片中的文字、图标或视觉元素
-						</li>
-						<li>
-							• <strong>Canvas 画布</strong>：无法理解 Canvas 中绘制的图形和内容
-						</li>
-						<li>
-							• <strong>WebGL 3D 内容</strong>：无法操作 3D 场景中的元素
-						</li>
-						<li>
-							• <strong>SVG 图形</strong>：无法理解 SVG 中的视觉内容和路径
-						</li>
+						<li>{t('limitations.no_vision_1')}</li>
+						<li>{t('limitations.no_vision_2')}</li>
+						<li>{t('limitations.no_vision_3')}</li>
+						<li>{t('limitations.no_vision_4')}</li>
 					</ul>
 				</div>
 
-				<h2 className="text-2xl font-bold mb-3">被操作网站要求</h2>
+				<h2 className="text-2xl font-bold mb-3">{t('limitations.website_requirements')}</h2>
 				<div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6 mb-6">
 					<div className="space-y-4">
 						<div>
-							<h3 className="font-semibold mb-2">语义化和易用性</h3>
+							<h3 className="font-semibold mb-2">{t('limitations.req_semantic_title')}</h3>
 							<p className="text-gray-600 dark:text-gray-300">
-								所有操作都基于 DOM 元素的语义化标签和属性。如果页面结构不够语义化，或者没有任何
-								accessibility 特性，可能影响 AI 的理解准确性。
+								{t('limitations.req_semantic_desc')}
 							</p>
 						</div>
 						<div>
-							<h3 className="font-semibold mb-2">UI/UX</h3>
-							<p className="text-gray-600 dark:text-gray-300">
-								反常识的交互规则、基于视觉的操作提示、复杂的鼠标交互、快速出现快速消失的元素等，都会影响
-								AI 的理解和操作。
-							</p>
+							<h3 className="font-semibold mb-2">{t('limitations.req_ux_title')}</h3>
+							<p className="text-gray-600 dark:text-gray-300">{t('limitations.req_ux_desc')}</p>
 						</div>
 						<div>
-							<h3 className="font-semibold mb-2">环境要求</h3>
-							<p className="text-gray-600 dark:text-gray-300">modern browser</p>
+							<h3 className="font-semibold mb-2">{t('limitations.req_env_title')}</h3>
+							<p className="text-gray-600 dark:text-gray-300">{t('limitations.req_env_desc')}</p>
 						</div>
 					</div>
 				</div>
 
-				<h2>未来规划</h2>
+				<h2>{t('limitations.future')}</h2>
 				<div className="bg-green-50 dark:bg-green-900/20 border-l-4 border-green-400 p-4">
-					<h3 className="font-semibold text-green-800 dark:text-green-200 mb-2">即将支持</h3>
+					<h3 className="font-semibold text-green-800 dark:text-green-200 mb-2">
+						{t('limitations.future_title')}
+					</h3>
 					<ul className="text-green-700 dark:text-green-300 space-y-1">
-						<li>• 多页面接力操作能力</li>
-						<li>• 更丰富的鼠标交互支持</li>
-						<li>• 基础的视觉理解能力</li>
-						<li>• 更智能的错误恢复机制</li>
+						<li>{t('limitations.future_1')}</li>
+						<li>{t('limitations.future_2')}</li>
+						<li>{t('limitations.future_3')}</li>
+						<li>{t('limitations.future_4')}</li>
 					</ul>
 				</div>
 			</div>

packages/website/src/docs/introduction/overview/page.tsx

@@ -0,0 +1,212 @@
+import { useTranslation } from 'react-i18next'
+
+export default function Overview() {
+	const { t } = useTranslation('docs')
+
+	return (
+		<article>
+			{/* 头图 */}
+			<figure className="mb-8 rounded-xl overflow-hidden">
+				<img
+					src="https://img.alicdn.com/imgextra/i3/O1CN014xLeic1gnF2iWdzjJ_!!6000000004186-49-tps-1280-353.webp"
+					alt="page-agent"
+					className="w-full h-64 object-cover"
+				/>
+			</figure>
+
+			<div className="mb-8">
+				<h1 className="text-4xl font-bold mb-4">{t('overview.title')}</h1>
+				<p className="text-xl text-gray-600 dark:text-gray-300 mb-4 leading-relaxed">
+					{t('overview.subtitle')}
+				</p>
+
+				{/* Status Badges */}
+				<div className="flex flex-wrap gap-2 items-center">
+					<a
+						href="https://www.npmjs.com/package/page-agent"
+						target="_blank"
+						rel="noopener noreferrer"
+					>
+						<img src="https://badge.fury.io/js/page-agent.svg" alt="npm version" />
+					</a>
+					<a href="https://opensource.org/licenses/MIT" target="_blank" rel="noopener noreferrer">
+						<img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="MIT License" />
+					</a>
+					<a href="http://www.typescriptlang.org/" target="_blank" rel="noopener noreferrer">
+						<img
+							src="https://img.shields.io/badge/%3C%2F%3E-TypeScript-%230074c1.svg"
+							alt="TypeScript"
+						/>
+					</a>
+					<a
+						href="https://www.npmjs.com/package/page-agent"
+						target="_blank"
+						rel="noopener noreferrer"
+					>
+						<img src="https://img.shields.io/npm/dt/page-agent.svg" alt="Downloads" />
+					</a>
+					<a
+						href="https://bundlephobia.com/package/page-agent"
+						target="_blank"
+						rel="noopener noreferrer"
+					>
+						<img src="https://img.shields.io/bundlephobia/minzip/page-agent" alt="Bundle Size" />
+					</a>
+					<a href="https://github.com/alibaba/page-agent" target="_blank" rel="noopener noreferrer">
+						<img
+							src="https://img.shields.io/github/stars/alibaba/page-agent.svg"
+							alt="GitHub stars"
+						/>
+					</a>
+				</div>
+			</div>
+
+			<section>
+				<h2 className="text-2xl font-bold mb-4">{t('overview.what_is')}</h2>
+
+				<p className="text-gray-600 dark:text-gray-300 mb-8 leading-relaxed ">
+					{t('overview.what_is_desc')}
+				</p>
+			</section>
+
+			<section>
+				<h2 className="text-2xl font-bold mb-3">{t('overview.features_title')}</h2>
+
+				<div className="grid md:grid-cols-2 gap-4 mb-8" role="list">
+					<div className="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg">
+						<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">
+							{t('overview.feature_dom.title')}
+						</h3>
+						<p className="text-gray-700 dark:text-gray-300">{t('overview.feature_dom.desc')}</p>
+					</div>
+
+					<div className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
+						<h3 className="text-lg font-semibold mb-2 text-purple-900 dark:text-purple-300">
+							{t('overview.feature_secure.title')}
+						</h3>
+						<p className="text-gray-700 dark:text-gray-300">{t('overview.feature_secure.desc')}</p>
+					</div>
+
+					<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
+						<h3 className="text-lg font-semibold mb-2 text-green-900 dark:text-green-300">
+							{t('overview.feature_backend.title')}
+						</h3>
+						<p className="text-gray-700 dark:text-gray-300">{t('overview.feature_backend.desc')}</p>
+					</div>
+
+					<div className="p-4 bg-orange-50 dark:bg-orange-900/20 rounded-lg">
+						<h3 className="text-lg font-semibold mb-2 text-orange-900 dark:text-orange-300">
+							{t('overview.feature_accessible.title')}
+						</h3>
+						<p className="text-gray-700 dark:text-gray-300">
+							{t('overview.feature_accessible.desc')}
+						</p>
+					</div>
+				</div>
+
+				<h2 className="text-2xl font-bold mb-4">{t('overview.vs_browser_use')}</h2>
+
+				<div className="overflow-x-auto mb-8">
+					<table className="w-full border-collapse border border-gray-300 dark:border-gray-600">
+						<thead>
+							<tr className="bg-gray-50 dark:bg-gray-800">
+								<th className="border border-gray-300 dark:border-gray-600 px-4 py-3 text-left">
+									{t('overview.table_feature')}
+								</th>
+								<th className="border border-gray-300 dark:border-gray-600 px-4 py-3 text-left">
+									page-agent
+								</th>
+								<th className="border border-gray-300 dark:border-gray-600 px-4 py-3 text-left">
+									browser-use
+								</th>
+							</tr>
+						</thead>
+						<tbody>
+							<tr>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3 font-medium">
+									{t('overview.table_deployment')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_deployment_pa')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_deployment_bu')}
+								</td>
+							</tr>
+							<tr>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3 font-medium">
+									{t('overview.table_scope')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_scope_pa')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_scope_bu')}
+								</td>
+							</tr>
+							<tr>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3 font-medium">
+									{t('overview.table_user')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_user_pa')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_user_bu')}
+								</td>
+							</tr>
+							<tr>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3 font-medium">
+									{t('overview.table_scenario')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_scenario_pa')}
+								</td>
+								<td className="border border-gray-300 dark:border-gray-600 px-4 py-3">
+									{t('overview.table_scenario_bu')}
+								</td>
+							</tr>
+						</tbody>
+					</table>
+				</div>
+
+				<h2 className="text-2xl font-bold mb-4">{t('overview.use_cases_title')}</h2>
+
+				<ul className="space-y-4 mb-8">
+					<li className="flex items-start space-x-3">
+						<span className="w-6 h-6 min-w-6 bg-blue-500 text-white rounded-full flex items-center justify-center font-bold text-sm mt-0.5 shrink-0">
+							1
+						</span>
+						<div className="text-gray-700 dark:text-gray-300">
+							<strong>{t('overview.use_case1_title')}</strong> {t('overview.use_case1_desc')}
+						</div>
+					</li>
+					<li className="flex items-start space-x-3">
+						<span className="w-6 h-6 min-w-6 bg-green-500 text-white rounded-full flex items-center justify-center font-bold text-sm mt-0.5 shrink-0">
+							2
+						</span>
+						<div className="text-gray-700 dark:text-gray-300">
+							<strong>{t('overview.use_case2_title')}</strong> {t('overview.use_case2_desc')}
+						</div>
+					</li>
+					<li className="flex items-start space-x-3">
+						<span className="w-6 h-6 min-w-6 bg-purple-500 text-white rounded-full flex items-center justify-center font-bold text-sm mt-0.5 shrink-0">
+							3
+						</span>
+						<div className="text-gray-700 dark:text-gray-300">
+							<strong>{t('overview.use_case3_title')}</strong> {t('overview.use_case3_desc')}
+						</div>
+					</li>
+					<li className="flex items-start space-x-3">
+						<span className="w-6 h-6 min-w-6 bg-orange-500 text-white rounded-full flex items-center justify-center font-bold text-sm mt-0.5 shrink-0">
+							4
+						</span>
+						<div className="text-gray-700 dark:text-gray-300">
+							<strong>{t('overview.use_case4_title')}</strong> {t('overview.use_case4_desc')}
+						</div>
+					</li>
+				</ul>
+			</section>
+		</article>
+	)
+}

packages/website/src/docs/introduction/quick-start/page.tsx

@@ -1,31 +1,35 @@
-import BetaNotice from '@pages/components/BetaNotice'
-import CodeEditor from '@pages/components/CodeEditor'
+import { useTranslation } from 'react-i18next'
+
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
 
 export default function QuickStart() {
+	const { t } = useTranslation('docs')
+
 	return (
 		<div>
-			<h1 className="text-4xl font-bold mb-6">Quick Start</h1>
+			<h1 className="text-4xl font-bold mb-6">{t('quick_start.title')}</h1>
 
-			<p className=" mb-6 leading-relaxed">几分钟内完成 page-agent 的集成。</p>
+			<p className=" mb-6 leading-relaxed">{t('quick_start.subtitle')}</p>
 
-			<h2 className="text-2xl font-bold mb-3">安装步骤</h2>
+			<h2 className="text-2xl font-bold mb-3">{t('quick_start.installation')}</h2>
 
 			<div className="space-y-4 mb-6">
 				<div className="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg">
 					<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">
-						1. 引入方式
+						{t('quick_start.step1_title')}
 					</h3>
 					<div className="space-y-3">
 						<div>
-							<p className="text-sm font-medium mb-2">CDN 引入</p>
+							<p className="text-sm font-medium mb-2">{t('quick_start.step1_cdn')}</p>
 							<CodeEditor
 								code={`// 仅供测试使用
-<script src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.2/page-agent.js" crossorigin="true" type="text/javascript"></script>`}
+<script src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js" crossorigin="true" type="text/javascript"></script>`}
 								language="html"
 							/>
 						</div>
 						<div>
-							<p className="text-sm font-medium mb-2">NPM 安装</p>
+							<p className="text-sm font-medium mb-2">{t('quick_start.step1_npm')}</p>
 							<CodeEditor
 								code={`// npm install page-agent
 import PageAgent from 'page-agent'`}
@@ -37,7 +41,7 @@ import PageAgent from 'page-agent'`}
 
 				<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
 					<h3 className="text-lg font-semibold mb-2 text-green-900 dark:text-green-300">
-						2. 初始化配置
+						{t('quick_start.step2_title')}
 					</h3>
 					<CodeEditor
 						code={`// 仅供测试使用，生产环境需要配置 LLM 接入点，本工具不提供 LLM 服务
@@ -60,7 +64,7 @@ const agent = new PageAgent({
 
 				<div className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
 					<h3 className="text-lg font-semibold mb-2 text-purple-900 dark:text-purple-300">
-						3. 开始使用
+						{t('quick_start.step3_title')}
 					</h3>
 					<CodeEditor
 						code={`// 程序化执行自然语言指令

packages/website/src/env.d.ts

@@ -0,0 +1,6 @@
+/// <reference types="vite/client" />
+
+declare module '*.module.css' {
+	const classes: Record<string, string>
+	export default classes
+}