chore(version): bump version to 0.0.14

fix: isPageDark robust

.github/workflows/ci.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        node-version: [20, 22]
+        node-version: [20, 24, 25]
 
     steps:
       - uses: actions/checkout@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

@@ -18,14 +18,14 @@ jobs:
       - 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

.github/workflows/release.yml

@@ -18,7 +18,7 @@ jobs:
       - 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
+        run: npm run build:libs
 
       - name: Publish all public packages
         run: npm publish --workspaces --access public

.gitignore

@@ -23,6 +23,7 @@ dist-ssr
 *.njsproj
 *.sln
 *.sw?
+.qoder
 
 
 # 

.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 +1,13 @@
 {
 	"editor.fontLigatures": true,
-	"cSpell.words": ["HITL", "innerhtml", "opensource", "retryable", "wouter"],
+	"cSpell.words": [
+		"HITL",
+		"innerhtml",
+		"llms",
+		"opensource",
+		"retryable",
+		"wouter"
+	],
 	"markdownlint.config": {
 		// "comment": "Relaxed rules",
 		"default": true,

AGENTS.md

@@ -7,9 +7,10 @@ This is a **monorepo** with npm workspaces containing **two main packages**:
 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. Such as:
+And other internal packages:
 
-- **Page Controller** (`packages/page-controller/`) - DOM operations and element interactions module. Independent of LLM, can be tested in unit tests.
+- **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
 
@@ -17,24 +18,12 @@ And other internal packages. Such as:
 
 ```bash
 npm start                    # Start website dev server
-npm run dev                  # Same as start
 npm run build                # Build all packages
-npm run build:lib            # Build page-agent library only
+npm run build:libs           # Build all libraries
+npm run build:website        # Build the website
 npm run lint                 # ESLint with TypeScript strict rules
 ```
 
-### Package-specific Commands
-
-```bash
-# Core library
-npm run build --workspace=page-agent
-npm run build:watch --workspace=page-agent
-
-# Website
-npm run dev --workspace=@page-agent/website
-npm run build --workspace=@page-agent/website
-```
-
 ## Architecture & Critical Patterns
 
 ### Monorepo Structure
@@ -46,11 +35,10 @@ You must update tsconfig and vite config if you add/remove/rename a package.
 ```bash
 packages/
 ├── page-agent/              # npm: "page-agent" ⭐ MAIN
-│   ├── src/                 # AI agent source
+│   ├── src/
 │   │   ├── PageAgent.ts     # Main AI agent class
 │   │   ├── tools/           # LLM tool definitions
-│   │   ├── llms/            # LLM integration
+│   │   └── llms/            # LLM integration
-│   │   └── ui/              # UI components
 │   ├── vite.config.js       # Library build (ES + UMD)
 │   └── package.json
 ├── website/                 # npm: "@page-agent/website" (private) ⭐ MAIN
@@ -59,19 +47,25 @@ packages/
 │
 │   # ...internal packages below...
 │
-└── page-controller/         # npm: "@page-agent/page-controller"
+├── page-controller/         # npm: "@page-agent/page-controller"
-    └── src/                 # DOM operations source
+│   └── src/                 # DOM operations
-        ├── PageController.ts  # Main controller class
+│       ├── PageController.ts
-        ├── actions.ts         # Element interaction actions
+│       ├── actions.ts
-        └── dom/               # DOM tree extraction
+│       └── 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 ...
+    // internal deps (topological order)
     "packages/page-controller",
+    "packages/ui",
     "packages/page-agent",
     "packages/website"
 ],
@@ -80,8 +74,9 @@ packages/
 ### Module Boundaries (Critical)
 
 - **Website** (`packages/website/`): CAN import from `page-agent` for demos. Alias `@/` → `website/src/`
-- **Page Agent** (`packages/page-agent/`): The core lib. Imports from all internal packages. Never import from website.
+- **Page Agent** (`packages/page-agent/`): The core lib. Imports from `@page-agent/page-controller` and `@page-agent/ui`.
-- **Page Controller** (`packages/page-controller/`): Internal lib. Pure DOM operations, NO LLM dependency. Never import from page-agent.
+- **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
 
@@ -108,19 +103,6 @@ DOM element references and internal state (selectorMap, elementTextMap) are enca
 3. **LLM Processing**: AI model returns action plans (in page-agent)
 4. **Indexed Operations**: PageAgent calls PageController methods by element index
 
-### 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())
-```
-
 ### Hash Routing Requirement
 
 Uses wouter with `useHashLocation` for static hosting:
@@ -146,10 +128,8 @@ Query params configure `PageAgentConfig` automatically in `src/entry.ts`.
 | File | Description |
 |------|-------------|
 | `src/PageAgent.ts` | ⭐ Main AI agent class orchestrating tools and LLM |
-| `src/entry.ts` | CDN/UMD entry point with auto-initialization |
+| `src/umd.ts` | CDN/UMD entry point with auto-initialization |
 | `src/tools/` | Tool definitions that call PageController methods |
-| `src/utils/bus.ts` | Type-safe event bus for decoupled communication |
-| `src/ui/` | UI components (Panel, SimulatorMask) with CSS modules |
 | `src/llms/` | LLM integration and communication layer |
 | `vite.config.js` | Library build configuration (ES + UMD) |
 
@@ -195,11 +175,6 @@ Query params configure `PageAgentConfig` automatically in `src/entry.ts`.
 2. Expose via async method in `PageController.ts`
 3. Export from `packages/page-controller/src/index.ts`
 
-### New UI Component
-
-1. Create in `packages/page-agent/src/ui/` with colocated CSS modules
-2. Use event bus for PageAgent communication
-
 ## Code Standards
 
 ### TypeScript
@@ -234,5 +209,4 @@ Query params configure `PageAgentConfig` automatically in `src/entry.ts`.
 
 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 `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+
+   - `node.js >= 20` with `npm >= 10`
-   - npm 10+
+   - An editor that supports `ts/eslint/prettier`
-   - typescript as required in package.json
+   - Make sure `eslint`, `prettier` and `commitlint` work well
-   - vscode or other editors that support ts/eslint/prettier
-   - make sure `eslint`, `auto-format` and `commit-lint` all work
 
 2. **Setup**
 
@@ -27,7 +25,11 @@ This is a **monorepo** with npm workspaces containing **two main packages**:
 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. No fancy tooling. Hoisting is required.
+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
 
@@ -97,19 +99,6 @@ We use a simplified monorepo solution with native npm-workspace. No fancy toolin
    - 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
@@ -120,24 +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`
+1. Create `website/src/docs/section/page-name/page.tsx`
-2. Add route to `pages/router.tsx`
+2. Add route to `website/src/router.tsx`
-3. Add navigation link to `pages/components/DocsLayout.tsx`
+3. Add navigation link to `website/src/components/DocsLayout.tsx`
 
 ## 🎯 Contribution Areas
 

README-zh.md

@@ -31,10 +31,11 @@
 ### CDN 集成
 
 ```html
-<!-- 临时 CDN URL. 未来会变更 -->
+// CDN        - https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js
-<script
+// Mirror(CN) - https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js
-	src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js"
+<script 
-	crossorigin="true"
+	src="https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js" 
+	crossorigin="true" 
 	type="text/javascript"
 ></script>
 ```
@@ -72,12 +73,9 @@ PageAgent adopts a simplified monorepo structure:
 ```
 packages/
 ├── page-agent/          # AI agent (npm: page-agent)
-│   ├── PageAgent        # Agent main loop
+├── page-controller/     # DOM 操作 (npm: @page-agent/page-controller)
-│   ├── tools/           # LLM tool definitions
+├── ui/                  # 面板 & 蒙层 & 模拟鼠标 (npm: @page-agent/ui)
-│   ├── ui/              # UI components & panels
+└── website/             # 文档站点
-│   └── llms/            # LLM integration layer
-├── page-controller/     # DOM operations (npm: @page-agent/page-controller)
-└── website/             # Documentation site
 ```
 
 ## 🤝 贡献

README.md

@@ -1,6 +1,6 @@
 # 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)
 
@@ -31,10 +31,11 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua
 ### CDN Integration
 
 ```html
-<!-- temporary CDN URL. May change in the future -->
+// CDN        - https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js
-<script
+// Mirror(CN) - https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js
-	src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js"
+<script 
-	crossorigin="true"
+	src="https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js" 
+	crossorigin="true" 
 	type="text/javascript"
 ></script>
 ```
@@ -72,11 +73,8 @@ PageAgent adopts a simplified monorepo structure:
 ```
 packages/
 ├── page-agent/          # AI agent (npm: page-agent)
-│   ├── PageAgent        # Agent main loop
-│   ├── tools/           # LLM tool definitions
-│   ├── ui/              # UI components & panels
-│   └── llms/            # LLM integration layer
 ├── page-controller/     # DOM operations (npm: @page-agent/page-controller)
+├── ui/                  # Panel & Mask & Mouse Animation (npm: @page-agent/ui)
 └── website/             # Demo & Documentation site
 ```
 

ROADMAP.md

@@ -24,33 +24,33 @@ The development progress and future plans for PageAgent.
 - [ ] **Hooks and Events**
   - [x] **lifecycle hooks**
   - [ ] **lifecycle events**
-- [ ] **❗Pause and intervene** 
+- [ ] **User takeover** 
-  - Current pause does not allow user intervention.
+  - [#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**
-  - Current phrasing can cause logic-loop for some models.
+  - [#66](https://github.com/alibaba/page-agent/issues/66)
-  - Test adding `Action` to memory.
+  - [#65](https://github.com/alibaba/page-agent/issues/65)
-- [ ] **Tools for more complex tasks**
-  - todo list
-  - file sys
 - [ ] **Optimize for popular UI frameworks**
 - [x] **i18n of the website**
   - [x] Chinese version
   - [x] English version
-- [ ] **Testing suits**
+- [x] **Refactor: Separate `Agent` and `PageController`** 
-- [ ] **Support custom llm fetch**
+- [ ] **Chrome-ext wrapper for multi-page tasks**
-- [ ] **Refactor: Separate `Agent` and `Page-Controller`** 
-  - Agent should be able to run w/o dom. 
-  - Actions should be able to be injected through iframe.
 
 ♻️ 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**
 

package.json

@@ -1,10 +1,12 @@
 {
 	"name": "root",
 	"private": true,
-	"version": "0.0.7",
+	"version": "0.0.14",
 	"type": "module",
 	"workspaces": [
 		"packages/page-controller",
+		"packages/ui",
+		"packages/llms",
 		"packages/page-agent",
 		"packages/website"
 	],
@@ -21,35 +23,37 @@
 		"npm": ">=10.0.0"
 	},
 	"scripts": {
-		"dev": "npm run dev --workspace=@page-agent/website",
 		"start": "npm run dev --workspace=@page-agent/website",
-		"build": "npm run build --workspaces --if-present",
+		"build:website": "npm run build:website --workspace=@page-agent/website",
-		"build:lib": "npm run build --workspace=page-agent",
+		"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"
 	},
 	"devDependencies": {
-		"@commitlint/cli": "^20.1.0",
+		"@commitlint/cli": "^20.2.0",
-		"@commitlint/config-conventional": "^20.0.0",
+		"@commitlint/config-conventional": "^20.2.0",
-		"@eslint/js": "^9.39.1",
+		"@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": "^9.39.1",
+		"eslint": "^9.39.2",
 		"eslint-config-prettier": "^10.1.8",
-		"eslint-plugin-react-dom": "^2.3.9",
+		"eslint-plugin-react-dom": "^2.3.13",
 		"eslint-plugin-react-hooks": "^7.0.1",
-		"eslint-plugin-react-refresh": "^0.4.24",
+		"eslint-plugin-react-refresh": "^0.4.25",
-		"eslint-plugin-react-x": "^2.3.9",
+		"eslint-plugin-react-x": "^2.3.13",
 		"globals": "^16.4.0",
 		"husky": "^9.1.7",
 		"lint-staged": "^16.2.4",
-		"prettier": "^3.6.2",
+		"prettier": "^3.7.4",
 		"typescript": "^5.9.3",
-		"typescript-eslint": "^8.48.1",
+		"typescript-eslint": "^8.50.0",
-		"vite": "^7.2.6",
-		"@microsoft/api-extractor": "^7.55.1",
 		"unplugin-dts": "^1.0.0-beta.6",
+		"vite": "^7.3.0",
 		"vite-plugin-css-injected-by-js": "^3.5.2"
 	},
 	"lint-staged": {

packages/llms/README.md

@@ -0,0 +1,41 @@
+# @page-agent/llms
+
+LLM client with a **reflection-before-action** mental model for page-agent.
+
+## Why This Package Exists
+
+The LLM module and the agent logic are inherently coupled. This package exists not to decouple them, but to **define the interface contract** between the LLM and the agent.
+
+The core abstraction is the `MacroToolInput` — a structured output format that **forces the model to reflect before acting**.
+
+## The Reflection-Before-Action Model
+
+Every tool call must first output its reasoning state before the actual action:
+
+```typescript
+interface MacroToolInput {
+  // Reflection (mandatory before any action)
+  evaluation_previous_goal?: string  // How well did the previous action work?
+  memory?: string                     // Key information to remember
+  next_goal?: string                  // What to accomplish next
+
+  // Action (the actual operation)
+  action: Record<string, any>
+}
+```
+
+This design ensures that:
+
+1. **The model evaluates its previous action** before deciding the next step
+2. **Working memory is explicitly maintained** across conversation turns
+3. **Goals are clearly stated**, making the agent's reasoning transparent and debuggable
+
+## Key Components
+
+| Export | Description |
+|--------|-------------|
+| `LLM` | Main LLM client class with retry logic |
+| `MacroToolInput` | The reflection-before-action input schema |
+| `AgentBrain` | Agent's thinking state (eval, memory, goal) |
+| `LLMConfig` | Configuration for LLM connection |
+| `parseLLMConfig` | Parse and apply defaults to config |

packages/llms/package.json

@@ -0,0 +1,43 @@
+{
+	"name": "@page-agent/llms",
+	"version": "0.0.14",
+	"type": "module",
+	"main": "./dist/lib/page-agent-llms.js",
+	"module": "./dist/lib/page-agent-llms.js",
+	"types": "./dist/lib/index.d.ts",
+	"exports": {
+		".": {
+			"types": "./dist/lib/index.d.ts",
+			"import": "./dist/lib/page-agent-llms.js",
+			"default": "./dist/lib/page-agent-llms.js"
+		}
+	},
+	"files": [
+		"dist/"
+	],
+	"description": "LLM client with reflection-before-action mental model for page-agent",
+	"keywords": [
+		"page-agent",
+		"llm",
+		"openai",
+		"tool-calling",
+		"agent"
+	],
+	"author": "Simon<gaomeng1900>",
+	"license": "MIT",
+	"repository": {
+		"type": "git",
+		"url": "https://github.com/alibaba/page-agent.git",
+		"directory": "packages/llms"
+	},
+	"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": {
+		"chalk": "^5.6.2",
+		"zod": "^4.2.0"
+	}
+}

packages/llms/src/OpenAILenientClient.ts

@@ -1,9 +1,15 @@
 /**
  * OpenAI Client implementation
  */
-import type { MacroToolInput } from '../PageAgent'
 import { InvokeError, InvokeErrorType } from './errors'
-import type { InvokeResult, LLMClient, Message, OpenAIClientConfig, Tool } from './types'
+import type {
+	InvokeResult,
+	LLMClient,
+	MacroToolInput,
+	Message,
+	OpenAIClientConfig,
+	Tool,
+} from './types'
 import { lenientParseMacroToolCall, modelPatch, zodToOpenAITool } from './utils'
 
 export class OpenAIClient implements LLMClient {

packages/llms/src/constants.ts

@@ -0,0 +1,21 @@
+// 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
+		? import.meta.env.LLM_MODEL_NAME
+		: 'PAGE-AGENT-FREE-TESTING-RANDOM'
+
+export const DEFAULT_API_KEY: string =
+	import.meta.env.DEV && import.meta.env.LLM_API_KEY
+		? import.meta.env.LLM_API_KEY
+		: 'PAGE-AGENT-FREE-TESTING-RANDOM'
+
+export const DEFAULT_BASE_URL: string =
+	import.meta.env.DEV && import.meta.env.LLM_BASE_URL
+		? import.meta.env.LLM_BASE_URL
+		: 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
+
+// internal
+
+export const LLM_MAX_RETRIES = 2
+export const DEFAULT_TEMPERATURE = 0.7 // higher randomness helps auto-recovery
+export const DEFAULT_MAX_TOKENS = 4096

packages/llms/src/env.d.ts

@@ -0,0 +1 @@
+/// <reference types="vite/client" />

packages/llms/src/index.ts

@@ -31,26 +31,56 @@
  * - 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 { OpenAIClient } from './OpenAILenientClient'
+import {
+	DEFAULT_API_KEY,
+	DEFAULT_BASE_URL,
+	DEFAULT_MAX_TOKENS,
+	DEFAULT_MODEL_NAME,
+	DEFAULT_TEMPERATURE,
+	LLM_MAX_RETRIES,
+} from './constants'
 import { InvokeError } from './errors'
-import type { InvokeResult, LLMClient, Message, Tool } from './types'
+import type {
+	AgentBrain,
+	InvokeResult,
+	LLMClient,
+	LLMConfig,
+	MacroToolInput,
+	MacroToolResult,
+	Message,
+	Tool,
+} from './types'
 
-export type { Message, Tool, InvokeResult, LLMClient }
+export type {
+	AgentBrain,
+	InvokeResult,
+	LLMClient,
+	LLMConfig,
+	MacroToolInput,
+	MacroToolResult,
+	Message,
+	Tool,
+}
 
-export class LLM {
+export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
+	return {
+		baseURL: config.baseURL ?? DEFAULT_BASE_URL,
+		apiKey: config.apiKey ?? DEFAULT_API_KEY,
+		model: config.model ?? DEFAULT_MODEL_NAME,
+		temperature: config.temperature ?? DEFAULT_TEMPERATURE,
+		maxTokens: config.maxTokens ?? DEFAULT_MAX_TOKENS,
+		maxRetries: config.maxRetries ?? LLM_MAX_RETRIES,
+	}
+}
+
+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({
@@ -81,17 +111,13 @@ export class LLM {
 			// retry settings
 			{
 				maxRetries: this.config.maxRetries,
-				onRetry: (retries: number) => {
+				onRetry: (current: number) => {
-					this.#bus.emit('panel:update', {
+					this.dispatchEvent(
-						type: 'retry',
+						new CustomEvent('retry', { detail: { current, max: this.config.maxRetries } })
-						displayText: `retry-ing (${retries} / ${this.config.maxRetries})`,
+					)
-					})
 				},
-				onError: (error: Error, withRetry: boolean) => {
+				onError: (error: Error) => {
-					this.#bus.emit('panel:update', {
+					this.dispatchEvent(new CustomEvent('error', { detail: { error } }))
-						type: 'error',
-						displayText: `step failed: ${(error as Error).message}`,
-					})
 				},
 			}
 		)
@@ -103,7 +129,7 @@ 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
@@ -118,7 +144,7 @@ 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/llms/src/types.ts

@@ -75,3 +75,48 @@ export interface OpenAIClientConfig {
 	maxTokens?: number
 	maxRetries?: number
 }
+
+/**
+ * LLM configuration for PageAgent
+ */
+export interface LLMConfig {
+	baseURL?: string
+	apiKey?: string
+	model?: string
+	temperature?: number
+	maxTokens?: number
+	maxRetries?: number
+}
+
+/**
+ * Agent brain state - the reflection-before-action model
+ *
+ * Every tool call must first reflect on:
+ * - evaluation_previous_goal: How well did the previous action achieve its goal?
+ * - memory: Key information to remember for future steps
+ * - next_goal: What should be accomplished in the next action?
+ */
+export interface AgentBrain {
+	// thinking?: string
+	evaluation_previous_goal: string
+	memory: string
+	next_goal: string
+}
+
+/**
+ * MacroTool input structure
+ *
+ * This is the core abstraction that enforces the "reflection-before-action" mental model.
+ * Before executing any action, the LLM must output its reasoning state.
+ */
+export interface MacroToolInput extends AgentBrain {
+	action: Record<string, any>
+}
+
+/**
+ * MacroTool output structure
+ */
+export interface MacroToolResult {
+	input: MacroToolInput
+	output: string
+}

packages/llms/src/utils.ts

@@ -4,9 +4,8 @@
 import chalk from 'chalk'
 import { z } from 'zod'
 
-import type { MacroToolInput } from '../PageAgent'
 import { InvokeError, InvokeErrorType } from './errors'
-import type { Tool } from './types'
+import type { MacroToolInput, Tool } from './types'
 
 /**
  * Convert Zod schema to OpenAI tool format

packages/llms/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/llms/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"],
+	"exclude": ["dist", "node_modules"]
+}
+

packages/llms/vite.config.js

@@ -0,0 +1,37 @@
+// @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'
+
+const __dirname = dirname(fileURLToPath(import.meta.url))
+
+console.log(chalk.cyan(`📦 Building @page-agent/llms`))
+
+export default defineConfig({
+	clearScreen: false,
+	plugins: [dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true })],
+	publicDir: false,
+	esbuild: {
+		keepNames: true,
+	},
+	build: {
+		lib: {
+			entry: resolve(__dirname, 'src/index.ts'),
+			name: 'PageAgentLLMs',
+			fileName: 'page-agent-llms',
+			formats: ['es'],
+		},
+		outDir: resolve(__dirname, 'dist', 'lib'),
+		rollupOptions: {
+			external: ['chalk', 'zod'],
+		},
+		minify: false,
+		sourcemap: true,
+	},
+	define: {
+		'process.env.NODE_ENV': '"production"',
+	},
+})
+

packages/page-agent/package.json

@@ -1,22 +1,20 @@
 {
 	"name": "page-agent",
 	"private": false,
-	"version": "0.0.7",
+	"version": "0.0.14",
 	"type": "module",
-	"main": "./dist/lib/page-agent.js",
+	"main": "./dist/esm/page-agent.js",
-	"module": "./dist/lib/page-agent.js",
+	"module": "./dist/esm/page-agent.js",
-	"types": "./dist/lib/PageAgent.d.ts",
+	"types": "./dist/esm/PageAgent.d.ts",
 	"exports": {
 		".": {
-			"types": "./dist/lib/PageAgent.d.ts",
+			"types": "./dist/esm/PageAgent.d.ts",
-			"import": "./dist/lib/page-agent.js",
+			"import": "./dist/esm/page-agent.js",
-			"default": "./dist/lib/page-agent.js"
+			"default": "./dist/esm/page-agent.js"
 		}
 	},
 	"files": [
-		"dist/",
+		"dist/"
-		"README.md",
-		"LICENSE"
 	],
 	"description": "GUI agent for web applications - add intelligent automation to any webpage with a single script",
 	"keywords": [
@@ -39,17 +37,17 @@
 	},
 	"homepage": "https://alibaba.github.io/page-agent/",
 	"scripts": {
-		"build": "npm run build:lib && npm run build:umd",
+		"build": "vite build && vite build --config vite.umd.config.js",
-		"build:lib": "MODE=lib vite build",
+		"serve": "npx serve dist/umd -p 5173",
-		"build:umd": "MODE=umd vite build",
+		"dev:umd": "concurrently \"vite build --config vite.umd.config.js --watch\" \"npm run serve\"",
-		"build:watch": "MODE=umd vite build --watch",
 		"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": {
-		"ai-motion": "^0.4.7",
 		"chalk": "^5.6.2",
-		"zod": "^4.1.12",
+		"zod": "^4.2.0",
-		"@page-agent/page-controller": "0.0.7"
+		"@page-agent/llms": "0.0.14",
+		"@page-agent/page-controller": "0.0.14",
+		"@page-agent/ui": "0.0.14"
 	}
 }

packages/page-agent/src/PageAgent.ts

@@ -2,49 +2,28 @@
  * Copyright (C) 2025 Alibaba Group Holding Limited
  * All rights reserved.
  */
+import {
+	type AgentBrain,
+	LLM,
+	type MacroToolInput,
+	type MacroToolResult,
+	type Tool,
+} from '@page-agent/llms'
 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 } from './config/constants'
-import { I18n } from './i18n'
-import { LLM, type Tool } from './llms'
 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'
-
+export type { AgentBrain, MacroToolInput, MacroToolResult }
-export interface AgentBrain {
-	// thinking?: string
-	evaluation_previous_goal: string
-	memory: string
-	next_goal: string
-}
-
-/**
- * MacroTool input structure
- */
-export interface MacroToolInput {
-	evaluation_previous_goal?: string
-	memory?: string
-	next_goal?: string
-	action: Record<string, any>
-}
-
-/**
- * MacroTool output structure
- */
-export interface MacroToolResult {
-	input: MacroToolInput
-	output: string
-}
 
 export interface AgentHistory {
 	brain: AgentBrain
@@ -71,8 +50,6 @@ 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
@@ -83,6 +60,9 @@ 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
 
 	/** PageController for DOM operations */
 	pageController: PageController
@@ -96,14 +76,34 @@ export class PageAgent extends EventTarget {
 		super()
 
 		this.config = config
-		this.#llm = new LLM(this.config, this.id)
+		this.#llm = new LLM(this.config)
-		this.i18n = new I18n(this.config.language)
+		this.panel = new Panel({
-		this.panel = new Panel(this)
+			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) {
@@ -118,9 +118,10 @@ export class PageAgent extends EventTarget {
 			this.tools.delete('execute_javascript')
 		}
 
-		window.addEventListener('beforeunload', (e) => {
+		this.#beforeUnloadListener = (e) => {
 			if (!this.disposed) this.dispose('PAGE_UNLOADING')
-		})
+		}
+		window.addEventListener('beforeunload', this.#beforeUnloadListener)
 	}
 
 	/**
@@ -141,13 +142,10 @@ export class PageAgent extends EventTarget {
 		// Show mask and panel
 		this.mask.show()
 
-		this.bus.emit('panel:show')
+		this.panel.show()
-		this.bus.emit('panel:reset')
+		this.panel.reset()
 
-		this.bus.emit('panel:update', {
+		this.panel.update({ type: 'input', task: this.task })
-			type: 'input',
-			displayText: this.task,
-		})
 
 		if (this.#abortController) {
 			this.#abortController.abort()
@@ -171,10 +169,7 @@ export class PageAgent extends EventTarget {
 
 				// Update status to thinking
 				console.log(chalk.blue('Thinking...'))
-				this.bus.emit('panel:update', {
+				this.panel.update({ type: 'thinking' })
-					type: 'thinking',
-					displayText: this.i18n.t('ui.panel.thinking'),
-				})
 
 				const result = await this.#llm.invoke(
 					[
@@ -304,22 +299,14 @@ export class PageAgent extends EventTarget {
 					`)
 
 				console.log(brain)
-				this.bus.emit('panel:update', {
+				this.panel.update({ type: 'thinking', text: brain })
-					type: 'thinking',
-					displayText: 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', {
+				this.panel.update({ type: 'toolExecuting', toolName, args: toolInput })
-					type: 'tool_executing',
-					toolName,
-					toolArgs: toolInput,
-					displayText: getToolExecutingText(toolName, toolInput, this.i18n),
-				})
 
 				const startTime = Date.now()
 
@@ -341,16 +328,13 @@ export class PageAgent extends EventTarget {
 				}
 
 				// Briefly display execution result
-				const displayResult = getToolCompletedText(toolName, toolInput, this.i18n)
+				this.panel.update({
-				if (displayResult)
+					type: 'toolCompleted',
-					this.bus.emit('panel:update', {
+					toolName,
-						type: 'tool_executing',
+					args: toolInput,
-						toolName,
+					result,
-						toolArgs: toolInput,
+					duration,
-						toolResult: result,
+				})
-						displayText: displayResult,
-						duration,
-					})
 
 				// Wait a moment to let user see the result
 				await new Promise((resolve) => setTimeout(resolve, 100))
@@ -426,16 +410,14 @@ export class PageAgent extends EventTarget {
 		this.pageController.cleanUpHighlights()
 
 		// Update panel status
-		this.bus.emit('panel:update', {
+		if (success) {
-			type: success ? 'output' : 'error',
+			this.panel.update({ type: 'output', text })
-			displayText: text,
+		} else {
-		})
+			this.panel.update({ type: 'error', message: text })
+		}
 
 		// Task completed
-		this.bus.emit('panel:update', {
+		this.panel.update({ type: 'completed' })
-			type: 'completed',
-			displayText: this.i18n.t('ui.panel.taskCompleted'),
-		})
 
 		this.mask.hide()
 
@@ -497,6 +479,22 @@ export class PageAgent extends EventTarget {
 		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

@@ -1,22 +1,2 @@
-// Dev environment: use .env config if available, otherwise fallback to testing api
+// Agent-specific constants (LLM constants moved to @page-agent/llms)
-export const DEFAULT_MODEL_NAME: string =
-	import.meta.env.DEV && import.meta.env.LLM_MODEL_NAME
-		? import.meta.env.LLM_MODEL_NAME
-		: 'PAGE-AGENT-FREE-TESTING-RANDOM'
-
-export const DEFAULT_API_KEY: string =
-	import.meta.env.DEV && import.meta.env.LLM_API_KEY
-		? import.meta.env.LLM_API_KEY
-		: 'PAGE-AGENT-FREE-TESTING-RANDOM'
-
-export const DEFAULT_BASE_URL: string =
-	import.meta.env.DEV && import.meta.env.LLM_BASE_URL
-		? import.meta.env.LLM_BASE_URL
-		: 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
-
-// internal
-
-export const LLM_MAX_RETRIES = 2
 export const MAX_STEPS = 20
-export const DEFAULT_TEMPERATURE = 0.7 // higher randomness helps auto-recovery
-export const DEFAULT_MAX_TOKENS = 4096

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

@@ -1,25 +1,11 @@
+import type { LLMConfig } from '@page-agent/llms'
 import type { PageControllerConfig } from '@page-agent/page-controller'
+import type { SupportedLanguage } from '@page-agent/ui'
 
 import type { AgentHistory, ExecutionResult, PageAgent } from '../PageAgent'
-import type { SupportedLanguage } from '../i18n'
 import type { PageAgentTool } from '../tools'
-import {
-	DEFAULT_API_KEY,
-	DEFAULT_BASE_URL,
-	DEFAULT_MAX_TOKENS,
-	DEFAULT_MODEL_NAME,
-	DEFAULT_TEMPERATURE,
-	LLM_MAX_RETRIES,
-} from './constants'
 
-export interface LLMConfig {
+export type { LLMConfig }
-	baseURL?: string
-	apiKey?: string
-	model?: string
-	temperature?: number
-	maxTokens?: number
-	maxRetries?: number
-}
 
 export interface AgentConfig {
 	// theme?: 'light' | 'dark'
@@ -96,14 +82,3 @@ export interface AgentConfig {
 }
 
 export type PageAgentConfig = LLMConfig & AgentConfig & PageControllerConfig
-
-export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
-	return {
-		baseURL: config.baseURL ?? DEFAULT_BASE_URL,
-		apiKey: config.apiKey ?? DEFAULT_API_KEY,
-		model: config.model ?? DEFAULT_MODEL_NAME,
-		temperature: config.temperature ?? DEFAULT_TEMPERATURE,
-		maxTokens: config.maxTokens ?? DEFAULT_MAX_TOKENS,
-		maxRetries: config.maxRetries ?? LLM_MAX_RETRIES,
-	}
-}

packages/page-agent/src/entry.ts

@@ -1,40 +0,0 @@
-/**
- * Auto-run entry for page-agent.js. Insert this script into your page to get page-agent functionality.
- */
-import { PageAgent, type PageAgentConfig } from './PageAgent'
-
-// Clean up existing instances to prevent multiple injections from bookmarklet
-if (window.pageAgent) {
-	window.pageAgent.dispose()
-}
-
-// Mount to global window object
-window.PageAgent = PageAgent
-
-// Export for ES module usage
-// export { PageAgent }
-
-console.log('🚀 page-agent.js loaded!')
-
-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'
-
-const currentScript = document.currentScript as HTMLScriptElement | null
-if (currentScript) {
-	console.log('🚀 page-agent.js detected current script:', currentScript.src)
-	const url = new URL(currentScript.src)
-	const model = url.searchParams.get('model') || DEMO_MODEL
-	const baseURL = url.searchParams.get('baseURL') || DEMO_BASE_URL
-	const apiKey = url.searchParams.get('apiKey') || DEMO_API_KEY
-	const language = (url.searchParams.get('lang') as 'zh-CN' | 'en-US') || 'zh-CN'
-	const config: PageAgentConfig = { model, baseURL, apiKey, language }
-	window.pageAgent = new PageAgent(config)
-} else {
-	console.log('🚀 page-agent.js no current script detected, using default demo config')
-	window.pageAgent = new PageAgent()
-}
-
-console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
-
-window.pageAgent.bus.emit('panel:show') // Show panel

packages/page-agent/src/umd.ts

@@ -0,0 +1,44 @@
+/**
+ * Auto-run entry for page-agent.js. Insert this script into your page to get page-agent functionality.
+ */
+import { PageAgent, type PageAgentConfig } from './PageAgent'
+
+// Clean up existing instances to prevent multiple injections from bookmarklet
+if (window.pageAgent) {
+	window.pageAgent.dispose()
+}
+
+// Mount to global window object
+window.PageAgent = PageAgent
+
+// Export for ES module usage
+// export { PageAgent }
+
+console.log('🚀 page-agent.js loaded!')
+
+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'
+
+// in case document.x is not ready yet
+// @todo give a switch to disable auto-init
+setTimeout(() => {
+	const currentScript = document.currentScript as HTMLScriptElement | null
+	if (currentScript) {
+		console.log('🚀 page-agent.js detected current script:', currentScript.src)
+		const url = new URL(currentScript.src)
+		const model = url.searchParams.get('model') || DEMO_MODEL
+		const baseURL = url.searchParams.get('baseURL') || DEMO_BASE_URL
+		const apiKey = url.searchParams.get('apiKey') || DEMO_API_KEY
+		const language = (url.searchParams.get('lang') as 'zh-CN' | 'en-US') || 'zh-CN'
+		const config: PageAgentConfig = { model, baseURL, apiKey, language }
+		window.pageAgent = new PageAgent(config)
+	} else {
+		console.log('🚀 page-agent.js no current script detected, using default demo config')
+		window.pageAgent = new PageAgent()
+	}
+
+	console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
+
+	window.pageAgent.panel.show() // Show panel
+})

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

@@ -1,27 +1,8 @@
-/**
- * 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:execute': { params: { task: string } }
 	// 'agent:done': { params: { text: string; success: boolean } }
@@ -31,8 +12,7 @@ export interface PageAgentEventMap {
 	// 'agent:error': { params: { error: string | Error } }
 
 	// Task status change events
-	// 'task:start': { params: { task: string } }
+	'task:start': { params: { task: string } }
-	// 'task:step': { params: Omit<AgentStep, 'id' | 'stepNumber' | 'timestamp'> }
 	// 'task:complete': { params: { text: string; success: boolean } }
 	// 'task:error': { params: { error: string | Error } }
 

packages/page-agent/tsconfig.json

@@ -7,10 +7,18 @@
 		"baseUrl": ".",
 		"outDir": "dist",
 		"paths": {
-			"@page-agent/page-controller": ["../page-controller/src/PageController.ts"]
+			//
+			"@page-agent/llms": ["../llms/src/index.ts"],
+			"@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" }]
+	"references": [
+		//
+		{ "path": "../llms" },
+		{ "path": "../page-controller" },
+		{ "path": "../ui" }
+	]
 }

packages/page-agent/vite.config.js

@@ -1,7 +1,4 @@
 // @ts-check
-import chalk from 'chalk'
-import 'dotenv/config'
-import process from 'node:process'
 import { dirname, resolve } from 'path'
 import dts from 'unplugin-dts/vite'
 import { fileURLToPath } from 'url'
@@ -10,15 +7,11 @@ import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
 
 const __dirname = dirname(fileURLToPath(import.meta.url))
 
-// ============================================================================
+// ES Module for NPM Package
-// Library Config (ES Module for NPM Package)
+export default defineConfig({
-// ============================================================================
-/** @type {import('vite').UserConfig} */
-const libConfig = {
 	clearScreen: false,
 	plugins: [
 		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
-		// dts({ tsconfigPath: './tsconfig.json', bundleTypes: true, compilerOptions: { paths: {} } }),
 		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
 	],
 	publicDir: false,
@@ -32,9 +25,14 @@ const libConfig = {
 			fileName: 'page-agent',
 			formats: ['es'],
 		},
-		outDir: resolve(__dirname, 'dist', 'lib'),
+		outDir: resolve(__dirname, 'dist', 'esm'),
 		rollupOptions: {
-			external: ['ai', 'ai-motion', 'chalk', 'zod', '@page-agent/*'],
+			external: [
+				'chalk',
+				'zod',
+				// all the internal packages
+				/^@page-agent\//,
+			],
 		},
 		minify: false,
 		sourcemap: true,
@@ -43,49 +41,4 @@ const libConfig = {
 	define: {
 		'process.env.NODE_ENV': '"production"',
 	},
-}
+})
-
-// ============================================================================
-// UMD Config (Browser Bundle for CDN)
-// ============================================================================
-/** @type {import('vite').UserConfig} */
-const umdConfig = {
-	plugins: [cssInjectedByJsPlugin({ relativeCSSInjection: true })],
-	publicDir: false,
-	esbuild: {
-		keepNames: true,
-	},
-	resolve: {
-		alias: {
-			'@page-agent/page-controller': resolve(__dirname, '../page-controller/src/PageController.ts'),
-		},
-	},
-	build: {
-		lib: {
-			entry: resolve(__dirname, 'src/entry.ts'),
-			name: 'PageAgent',
-			fileName: 'page-agent',
-			formats: ['umd'],
-		},
-		outDir: resolve(__dirname, 'dist', 'umd'),
-		cssCodeSplit: true,
-	},
-	define: {
-		'process.env.NODE_ENV': '"production"',
-	},
-}
-
-// ============================================================================
-
-const MODE = process.env.MODE
-
-console.log(chalk.cyan(`📦 Build mode: ${chalk.bold(MODE || 'lib')}`))
-
-let config
-if (MODE === 'umd') {
-	config = umdConfig
-} else {
-	config = libConfig
-}
-
-export default defineConfig(config)

packages/page-agent/vite.umd.config.js

@@ -0,0 +1,45 @@
+// @ts-check
+import { dirname, resolve } from 'path'
+import { fileURLToPath } from 'url'
+import { defineConfig } from 'vite'
+import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
+
+const __dirname = dirname(fileURLToPath(import.meta.url))
+
+// 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
+export default defineConfig({
+	plugins: [cssInjectedByJsPlugin({ relativeCSSInjection: true })],
+	publicDir: false,
+	esbuild: {
+		keepNames: true,
+	},
+	resolve: {
+		alias: {
+			'@page-agent/page-controller': resolve(__dirname, '../page-controller/src/PageController.ts'),
+			'@page-agent/llms': resolve(__dirname, '../llms/src/index.ts'),
+			'@page-agent/ui': resolve(__dirname, '../ui/src/index.ts'),
+		},
+	},
+	build: {
+		lib: {
+			entry: resolve(__dirname, 'src/umd.ts'),
+			name: 'PageAgent',
+			fileName: 'page-agent',
+			formats: ['umd'],
+		},
+		outDir: resolve(__dirname, 'dist', 'umd'),
+		rollupOptions: {
+			output: {
+				// force use .js as extension
+				entryFileNames: 'page-agent.js',
+			},
+		},
+		cssCodeSplit: true,
+	},
+	define: {
+		'process.env.NODE_ENV': '"production"',
+	},
+})

packages/page-controller/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@page-agent/page-controller",
-	"version": "0.0.7",
+	"version": "0.0.14",
 	"type": "module",
 	"main": "./dist/lib/page-controller.js",
 	"module": "./dist/lib/page-controller.js",
@@ -13,9 +13,7 @@
 		}
 	},
 	"files": [
-		"dist/",
+		"dist/"
-		"README.md",
-		"LICENSE"
 	],
 	"description": "Page controller for page-agent - DOM operations and element interactions",
 	"keywords": [
@@ -28,12 +26,12 @@
 	"license": "MIT",
 	"repository": {
 		"type": "git",
-		"url": "https://github.com/alibaba/page-agent.git"
+		"url": "https://github.com/alibaba/page-agent.git",
+		"directory": "packages/page-controller"
 	},
 	"homepage": "https://alibaba.github.io/page-agent/",
 	"scripts": {
 		"build": "vite build",
-		"build:watch": "vite build --watch",
 		"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/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/vite.config.js

@@ -13,7 +13,7 @@ console.log(chalk.cyan(`📦 Building @page-agent/page-controller`))
 export default defineConfig({
 	clearScreen: false,
 	plugins: [
-		dts({ tsconfigPath: './tsconfig.json', bundleTypes: true }),
+		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
 		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
 	],
 	publicDir: false,
@@ -29,7 +29,7 @@ export default defineConfig({
 		},
 		outDir: resolve(__dirname, 'dist', 'lib'),
 		rollupOptions: {
-			external: [],
+			external: ['@page-agent/*'],
 		},
 		minify: false,
 		sourcemap: true,

packages/ui/package.json

@@ -0,0 +1,41 @@
+{
+	"name": "@page-agent/ui",
+	"version": "0.0.14",
+	"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.ts

@@ -1,11 +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
  */
@@ -19,11 +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
@@ -34,9 +58,9 @@ export class Panel {
 		return this.#wrapper
 	}
 
-	constructor(pageAgent: PageAgent) {
+	constructor(config: PanelConfig) {
-		this.#pageAgent = pageAgent
+		this.#config = config
-		this.#bus = pageAgent.bus
+		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}`)!
@@ -49,16 +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())
 	}
 
 	/**
@@ -71,18 +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
 	 */
@@ -92,10 +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)
@@ -120,59 +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) {
+		if (paused) {
-			this.#statusText.textContent = this.#pageAgent.i18n.t('ui.panel.paused')
+			this.#statusText.textContent = this.#i18n.t('ui.panel.paused')
-			this.#updateStatusIndicator('thinking') // Use existing thinking state
+			this.#updateStatusIndicator('thinking')
 		} else {
-			this.#statusText.textContent = this.#pageAgent.i18n.t('ui.panel.continueExecution')
+			this.#statusText.textContent = this.#i18n.t('ui.panel.continueExecution')
-			this.#updateStatusIndicator('tool_executing') // Restore to execution state
+			this.#updateStatusIndicator('tool_executing')
 		}
 	}
 
@@ -180,13 +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)
 		}
 	}
@@ -196,12 +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()
 	}
 
 	/**
@@ -218,7 +337,7 @@ export class Panel {
 			// Handle user input mode
 			this.#handleUserAnswer(input)
 		} else {
-			this.#pageAgent.execute(input)
+			this.#config.onExecuteTask(input)
 		}
 	}
 
@@ -227,9 +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
@@ -248,7 +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(() => {
@@ -294,23 +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>
@@ -501,8 +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 failureKeyword = this.#i18n.t('ui.tools.resultFailure')
-				const errorKeyword = this.#pageAgent.i18n.t('ui.tools.resultError')
+				const errorKeyword = this.#i18n.t('ui.tools.resultError')
 				const isSuccess =
 					!step.toolResult ||
 					(!step.toolResult.includes(failureKeyword) && !step.toolResult.includes(errorKeyword))
@@ -531,7 +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
@@ -550,47 +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/checkDarkMode.ts

@@ -3,14 +3,14 @@
  * @returns {boolean} - True if a common dark mode class is found.
  */
 function hasDarkModeClass() {
-	const DFEAULT_DARK_MODE_CLASSES = ['dark', 'dark-mode', 'theme-dark', 'night', 'night-mode']
+	const DEFAULT_DARK_MODE_CLASSES = ['dark', 'dark-mode', 'theme-dark', 'night', 'night-mode']
 
 	const htmlElement = document.documentElement
-	const bodyElement = document.body
+	const bodyElement = document.body || document.documentElement // can be null in some cases
 
 	// Check class names on <html> and <body>
-	for (const className of DFEAULT_DARK_MODE_CLASSES) {
+	for (const className of DEFAULT_DARK_MODE_CLASSES) {
-		if (htmlElement.classList.contains(className) || bodyElement.classList.contains(className)) {
+		if (htmlElement.classList.contains(className) || bodyElement?.classList.contains(className)) {
 			return true
 		}
 	}
@@ -70,7 +70,7 @@ function isColorDark(colorString: string, threshold = 128) {
 function isBackgroundDark() {
 	// We check both <html> and <body> because some pages set the color on <html>
 	const htmlStyle = window.getComputedStyle(document.documentElement)
-	const bodyStyle = window.getComputedStyle(document.body)
+	const bodyStyle = window.getComputedStyle(document.body || document.documentElement)
 
 	// Get background colors
 	const htmlBgColor = htmlStyle.backgroundColor
@@ -93,18 +93,23 @@ function isBackgroundDark() {
  * @returns {boolean} - True if the page is likely dark.
  */
 export function isPageDark() {
-	// Strategy 1: Check for common dark mode classes
+	try {
-	if (hasDarkModeClass()) {
+		// Strategy 1: Check for common dark mode classes
-		return true
+		if (hasDarkModeClass()) {
+			return true
+		}
+
+		// Strategy 2: Analyze the computed background color
+		if (isBackgroundDark()) {
+			return true
+		}
+
+		// @TODO add more checks here, e.g., analyzing text color,
+		// or checking the background of major layout elements like <main> or #app.
+
+		return false
+	} catch (error) {
+		console.warn('Error determining if page is dark:', error)
+		return false
 	}
-
-	// Strategy 2: Analyze the computed background color
-	if (isBackgroundDark()) {
-		return true
-	}
-
-	// @TODO add more checks here, e.g., analyzing text color,
-	// or checking the background of major layout elements like <main> or #app.
-
-	return false
 }

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/package.json

@@ -1,26 +1,25 @@
 {
 	"name": "@page-agent/website",
 	"private": true,
-	"version": "0.0.7",
+	"version": "0.0.14",
 	"type": "module",
 	"scripts": {
 		"dev": "vite",
-		"build": "vite build",
+		"build:website": "vite build",
 		"preview": "vite preview",
 		"typecheck": "tsc --noEmit"
 	},
 	"devDependencies": {
-		"page-agent": "*",
+		"@tailwindcss/vite": "^4.1.18",
-		"@tailwindcss/vite": "^4.1.14",
 		"@types/react": "^19.2.2",
 		"@types/react-dom": "^19.2.1",
 		"@vitejs/plugin-react-swc": "^4.1.0",
-		"i18next": "^25.7.1",
+		"i18next": "^25.7.3",
 		"i18next-browser-languagedetector": "^8.2.0",
-		"react": "^19.2.0",
+		"react": "^19.2.3",
-		"react-dom": "^19.2.0",
+		"react-dom": "^19.2.3",
-		"react-i18next": "^16.1.4",
+		"react-i18next": "^16.5.0",
 		"tailwindcss": "^4.1.14",
-		"wouter": "^3.7.1"
+		"wouter": "^3.8.1"
 	}
 }

packages/website/src/constants.ts

@@ -0,0 +1,3 @@
+export const CDN_URL = 'https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js'
+export const CDN_CN_URL =
+	'https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js'

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

@@ -1,5 +1,6 @@
 import BetaNotice from '@/components/BetaNotice'
 import CodeEditor from '@/components/CodeEditor'
+import { CDN_CN_URL, CDN_URL } from '@/constants'
 
 export default function CdnSetup() {
 	return (
@@ -15,11 +16,16 @@ export default function CdnSetup() {
 			<CodeEditor
 				className="mb-8"
 				code={`
-// 仅供测试使用，稳定 CDN 待定
+// CDN: \t${CDN_URL}
-<script src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js" crossorigin="true" type="text/javascript"></script>
+// Mirror: \t${CDN_CN_URL}
+<script 
+	src="${CDN_URL}" 
+	crossorigin="true" 
+	type="text/javascript"
+></script>
 
 <script>
-	window.pageAgent.panel.show()
+	// window.pageAgent
 </script>`}
 			/>
 

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

@@ -8,7 +8,7 @@ export default function Overview() {
 			{/* 头图 */}
 			<figure className="mb-8 rounded-xl overflow-hidden">
 				<img
-					src="https://img.alicdn.com/imgextra/i1/O1CN01RY0Wvh26ATVeDIX7v_!!6000000007621-0-tps-1672-512.jpg"
+					src="https://img.alicdn.com/imgextra/i3/O1CN014xLeic1gnF2iWdzjJ_!!6000000004186-49-tps-1280-353.webp"
 					alt="page-agent"
 					className="w-full h-64 object-cover"
 				/>

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

@@ -2,6 +2,7 @@ import { useTranslation } from 'react-i18next'
 
 import BetaNotice from '@/components/BetaNotice'
 import CodeEditor from '@/components/CodeEditor'
+import { CDN_CN_URL, CDN_URL } from '@/constants'
 
 export default function QuickStart() {
 	const { t } = useTranslation('docs')
@@ -23,8 +24,9 @@ export default function QuickStart() {
 						<div>
 							<p className="text-sm font-medium mb-2">{t('quick_start.step1_cdn')}</p>
 							<CodeEditor
-								code={`// 仅供测试使用
+								code={`// CDN: \t${CDN_URL}
-<script src="https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js" crossorigin="true" type="text/javascript"></script>`}
+// Mirror: \t${CDN_CN_URL}
+<script src="${CDN_URL}" crossorigin="true" type="text/javascript"></script>`}
 								language="html"
 							/>
 						</div>

packages/website/src/i18n/locales/en-US/home.ts

@@ -18,6 +18,9 @@ export default {
 		step1_content: 'Show your bookmarks bar',
 		step2_title: 'Step 2:',
 		step2_content: 'Drag this button to your bookmarks',
+		cdn_label: 'CDN Source',
+		cdn_international: 'International',
+		cdn_china: 'China Mirror',
 		step3_title: 'Step 3:',
 		step3_content: 'Click the bookmark on any site to activate',
 		notice_title: '⚠️ Heads Up',

packages/website/src/i18n/locales/zh-CN/home.ts

@@ -17,6 +17,9 @@ export default {
 		step1_content: '显示收藏夹栏',
 		step2_title: '步骤 2:',
 		step2_content: '拖拽下面按钮到收藏夹栏',
+		cdn_label: 'CDN 源',
+		cdn_international: '国际',
+		cdn_china: '国内镜像',
 		step3_title: '步骤 3:',
 		step3_content: '在其他网站点击收藏夹中的按钮即可使用',
 		notice_title: '⚠️ 注意',

packages/website/src/main.tsx

@@ -4,8 +4,8 @@ import { useHashLocation } from 'wouter/use-hash-location'
 
 import './i18n/config'
 import './i18n/types'
-import { default as PagesRouter } from './router.tsx'
+import { default as PagesRouter } from './router'
-import { default as TestPagesRouter } from './test-pages/router.tsx'
+import { default as TestPagesRouter } from './test-pages/router'
 
 import './index.css'
 

packages/website/src/page.tsx

@@ -6,23 +6,27 @@ import { Link, useSearchParams } from 'wouter'
 
 import Footer from './components/Footer'
 import Header from './components/Header'
+import { CDN_CN_URL, CDN_URL } from './constants'
 
-const injection = encodeURI(
+function getInjection(useCN?: boolean) {
-	"javascript:(function(){var s=document.createElement('script');s.src=`https://hwcxiuzfylggtcktqgij.supabase.co/storage/v1/object/public/demo-public/v0.0.4/page-agent.js?t=${Math.random()}`;s.setAttribute('crossorigin', true);s.type=`text/javascript`;s.onload=()=>console.log('PageAgent script loaded!');document.body.appendChild(s);})();"
+	const cdn = useCN ? CDN_CN_URL : CDN_URL
-)
 
-const injectionA = `
+	const injection = encodeURI(
-<a
+		`javascript:(function(){var s=document.createElement('script');s.src=\`${cdn}?t=\${Math.random()}\`;s.setAttribute('crossorigin', true);s.type="text/javascript";s.onload=()=>console.log('PageAgent script loaded!');document.body.appendChild(s);})();`
-	href=${injection}
+	)
-	class="inline-flex items-center text-xs px-3 py-2 bg-blue-500 text-white font-medium rounded-lg hover:shadow-md transform hover:scale-105 transition-all duration-200 cursor-move border-2 border-dashed border-green-300"
-	draggable="true"
-	onclick="return false;"
-	title="Drag me to your bookmarks bar!"
->
-	✨PageAgent
-</a>
 
-`
+	return `
+	<a
+		href=${injection}
+		class="inline-flex items-center text-xs px-3 py-2 bg-blue-500 text-white font-medium rounded-lg hover:shadow-md transform hover:scale-105 transition-all duration-200 cursor-move border-2 border-dashed border-green-300"
+		draggable="true"
+		onclick="return false;"
+		title="Drag me to your bookmarks bar!"
+	>
+		✨PageAgent
+	</a>
+	`
+}
 
 export default function HomePage() {
 	const { t, i18n } = useTranslation(['home', 'common'])
@@ -38,6 +42,7 @@ export default function HomePage() {
 	const isOther = params.has('try_other')
 
 	const [activeTab, setActiveTab] = useState<'try' | 'other'>(isOther ? 'other' : 'try')
+	const [cdnSource, setCdnSource] = useState<'international' | 'china'>('international')
 
 	const handleExecute = async () => {
 		if (!task.trim()) return
@@ -194,10 +199,25 @@ export default function HomePage() {
 																</span>{' '}
 																{t('home:try_other.step2_content')}
 															</p>
-															<div
+															<div className="flex items-center justify-center gap-3">
-																className="flex items-center justify-center gap-2 text-gray-500 dark:text-gray-400"
+																<select
-																dangerouslySetInnerHTML={{ __html: injectionA }}
+																	value={cdnSource}
-															></div>
+																	onChange={(e) =>
+																		setCdnSource(e.target.value as 'international' | 'china')
+																	}
+																	className="px-2 py-1.5 text-xs border border-gray-300 dark:border-gray-500 rounded bg-white dark:bg-gray-600 text-gray-700 dark:text-gray-200"
+																>
+																	<option value="international">
+																		{t('home:try_other.cdn_international')}
+																	</option>
+																	<option value="china">{t('home:try_other.cdn_china')}</option>
+																</select>
+																<div
+																	dangerouslySetInnerHTML={{
+																		__html: getInjection(cdnSource === 'china'),
+																	}}
+																></div>
+															</div>
 														</div>
 
 														{/* Usage Instructions */}

packages/website/tsconfig.json

@@ -11,11 +11,19 @@
 			"@/*": ["src/*"],
 
 			// Simplified monorepo solution (raw npm workspace with hoisting)
+			"page-agent": ["../page-agent/src/PageAgent.ts"],
+			"@page-agent/llms": ["../llms/src/index.ts"],
 			"@page-agent/page-controller": ["../page-controller/src/PageController.ts"],
-			"page-agent": ["../page-agent/src/PageAgent.ts"]
+			"@page-agent/ui": ["../ui/src/index.ts"]
 		}
 	},
 	"include": ["**/*.ts", "**/*.tsx"],
 	"exclude": ["dist", "node_modules"],
-	"references": [{ "path": "../page-controller" }, { "path": "../page-agent" }]
+	"references": [
+		//
+		{ "path": "../llms" },
+		{ "path": "../page-agent" },
+		{ "path": "../page-controller" },
+		{ "path": "../ui" }
+	]
 }

packages/website/vite.config.js

@@ -1,6 +1,6 @@
 import tailwindcss from '@tailwindcss/vite'
 import react from '@vitejs/plugin-react-swc'
-import 'dotenv/config'
+import { config as dotenvConfig } from 'dotenv'
 import process from 'node:process'
 import { dirname, resolve } from 'path'
 import { fileURLToPath } from 'url'
@@ -8,6 +8,9 @@ import { defineConfig } from 'vite'
 
 const __dirname = dirname(fileURLToPath(import.meta.url))
 
+// Load .env from repo root
+dotenvConfig({ path: resolve(__dirname, '../../.env') })
+
 // Website Config (React Documentation Site)
 export default defineConfig({
 	base: './',
@@ -19,7 +22,9 @@ export default defineConfig({
 			'@': resolve(__dirname, 'src'),
 
 			// Monorepo packages (always bundle local code instead of npm versions)
+			'@page-agent/llms': resolve(__dirname, '../llms/src/index.ts'),
 			'@page-agent/page-controller': resolve(__dirname, '../page-controller/src/PageController.ts'),
+			'@page-agent/ui': resolve(__dirname, '../ui/src/index.ts'),
 			'page-agent': resolve(__dirname, '../page-agent/src/PageAgent.ts'),
 		},
 	},

scripts/sync-version.js

@@ -102,6 +102,7 @@ console.log(chalk.green.bold(`\n✓ Version synced: ${newVersion}\n`))
 if (hasChanges) {
 	const tagName = `v${newVersion}`
 	console.log(chalk.cyan.bold('📋 Next steps:\n'))
+	console.log(chalk.blueBright(`npm i`))
 	console.log(
 		chalk.blueBright(`git add . && git commit -m "chore(version): bump version to ${newVersion}"`)
 	)

tsconfig.json

@@ -2,6 +2,8 @@
 	"extends": "./tsconfig.base.json",
 	"references": [
 		{ "path": "./packages/page-controller" },
+		{ "path": "./packages/ui" },
+		{ "path": "./packages/llms" },
 		{ "path": "./packages/page-agent" },
 		{ "path": "./packages/website" }
 	],