Merge pull request #108 from alibaba/feat/dual-umd

feat: add `cdn` packages for iife builds
2026-01-13 20:58:37 +08:00
parent 8b1e91d665 3b21c42cdb
commit 066b045822
9 changed files with 185 additions and 27 deletions
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -9,6 +9,7 @@ This is a **monorepo** with npm workspaces:

 Internal packages:

+- **CDN** (`packages/cdn/`) - IIFE builds for script tag usage (npm: `@page-agent/cdn`)
 - **LLMs** (`packages/llms/`) - LLM client with reflection-before-action mental model
 - **Page Controller** (`packages/page-controller/`) - DOM operations and visual feedback (SimulatorMask), independent of LLM
 - **UI** (`packages/ui/`) - Panel and i18n. Decoupled from PageAgent
@@ -31,6 +32,7 @@ Simple monorepo solution: TypeScript references + Vite aliases. Update tsconfig
 ```
 packages/
 ├── page-agent/              # npm: "page-agent" ⭐ MAIN
+├── cdn/                     # npm: "@page-agent/cdn" (IIFE builds)
 ├── website/                 # @page-agent/website (private)
 ├── llms/                    # @page-agent/llms
 ├── page-controller/         # @page-agent/page-controller
@@ -69,42 +71,43 @@ const pageInfo = await this.pageController.getPageInfo()
 3. **LLM Processing**: AI returns action plans (page-agent)
 4. **Indexed Operations**: PageAgent calls PageController by element index

-### CDN Auto-Injection
+### CDN Builds (`packages/cdn/`)

-Library auto-initializes via script tag:
+Two IIFE builds for script tag usage:

-```html
-<script src="page-agent.js?model=gpt-4"></script>
-```
+| Build | File                 | Description                      |
+| ----- | -------------------- | -------------------------------- |
+| Demo  | `page-agent.demo.js` | Auto-init with built-in test API |
+| Full  | `page-agent.js`      | Exposes `PageAgent` class only   |

-Query params configure `PageAgentConfig` in `src/umd.ts`.
+Demo build supports query params (e.g., `?model=gpt-4&lang=en-US`).

 ## Key Files Reference

 ### Page Agent (`packages/page-agent/`)

-| File | Description |
-|------|-------------|
-| `src/PageAgent.ts` | ⭐ Main AI agent class |
-| `src/umd.ts` | CDN/UMD entry with auto-init |
-| `src/tools/` | Tool definitions calling PageController |
+| File               | Description                             |
+| ------------------ | --------------------------------------- |
+| `src/PageAgent.ts` | ⭐ Main AI agent class                  |
+| `src/umd.ts`       | CDN/UMD entry with auto-init            |
+| `src/tools/`       | Tool definitions calling PageController |

 ### LLMs (`packages/llms/`)

-| File | Description |
-|------|-------------|
-| `src/index.ts` | ⭐ LLM class with retry logic |
-| `src/types.ts` | MacroToolInput, AgentBrain, LLMConfig |
-| `src/OpenAILenientClient.ts` | OpenAI-compatible client |
+| File                         | Description                           |
+| ---------------------------- | ------------------------------------- |
+| `src/index.ts`               | ⭐ LLM class with retry logic         |
+| `src/types.ts`               | MacroToolInput, AgentBrain, LLMConfig |
+| `src/OpenAILenientClient.ts` | OpenAI-compatible client              |

 ### Page Controller (`packages/page-controller/`)

-| File | Description |
-|------|-------------|
-| `src/PageController.ts` | ⭐ Main controller class with optional mask support |
-| `src/SimulatorMask.ts` | Visual overlay blocking user interaction during automation |
-| `src/actions.ts` | Element interactions (click, input, scroll) |
-| `src/dom/dom_tree/index.js` | Core DOM extraction engine |
+| File                        | Description                                                |
+| --------------------------- | ---------------------------------------------------------- |
+| `src/PageController.ts`     | ⭐ Main controller class with optional mask support        |
+| `src/SimulatorMask.ts`      | Visual overlay blocking user interaction during automation |
+| `src/actions.ts`            | Element interactions (click, input, scroll)                |
+| `src/dom/dom_tree/index.js` | Core DOM extraction engine                                 |

 ## Adding New Features

--- a/README-zh.md
+++ b/README-zh.md
@@ -81,6 +81,7 @@ packages/
 ├── llms/                # LLM 客户端 (npm: @page-agent/llms)
 ├── page-controller/     # DOM 操作 & 蒙层 & 模拟鼠标 (npm: @page-agent/page-controller)
 ├── ui/                  # 面板 & i18n (npm: @page-agent/ui)
+├── cdn/                 # CDN IIFE builds (npm: @page-agent/cdn)
 └── website/             # 文档站点
 ```

--- a/README.md
+++ b/README.md
@@ -81,6 +81,7 @@ packages/
 ├── llms/                # LLM client (npm: @page-agent/llms)
 ├── page-controller/     # DOM operations & Visual Mask (npm: @page-agent/page-controller)
 ├── ui/                  # Panel & i18n (npm: @page-agent/ui)
+├── cdn/                 # CDN IIFE builds (npm: @page-agent/cdn)
 └── website/             # Demo & Documentation site
 ```

--- a/package-lock.json
+++ b/package-lock.json
@@ -13,6 +13,7 @@
 				"packages/ui",
 				"packages/llms",
 				"packages/page-agent",
+				"packages/cdn",
 				"packages/website"
 			],
 			"devDependencies": {
@@ -1597,6 +1598,10 @@
 				"url": "https://github.com/sponsors/epoberezkin"
 			}
 		},
+		"node_modules/@page-agent/cdn": {
+			"resolved": "packages/cdn",
+			"link": true
+		},
 		"node_modules/@page-agent/llms": {
 			"resolved": "packages/llms",
 			"link": true
@@ -8140,6 +8145,14 @@
 				"zod": "^3.25.0 || ^4.0.0"
 			}
 		},
+		"packages/cdn": {
+			"name": "@page-agent/cdn",
+			"version": "0.0.21",
+			"license": "MIT",
+			"dependencies": {
+				"page-agent": "0.0.21"
+			}
+		},
 		"packages/llms": {
 			"name": "@page-agent/llms",
 			"version": "0.0.21",
@@ -8163,16 +8176,16 @@
 		"packages/page-controller": {
 			"name": "@page-agent/page-controller",
 			"version": "0.0.21",
-			"license": "MIT"
-		},
-		"packages/ui": {
-			"name": "@page-agent/ui",
-			"version": "0.0.21",
 			"license": "MIT",
 			"dependencies": {
 				"ai-motion": "^0.4.8"
 			}
 		},
+		"packages/ui": {
+			"name": "@page-agent/ui",
+			"version": "0.0.21",
+			"license": "MIT"
+		},
 		"packages/website": {
 			"name": "@page-agent/website",
 			"version": "0.0.21",
--- a/package.json
+++ b/package.json
@@ -8,6 +8,7 @@
 		"packages/ui",
 		"packages/llms",
 		"packages/page-agent",
+		"packages/cdn",
 		"packages/website"
 	],
 	"description": "AI-powered UI agent for web applications",
--- a/packages/cdn/package.json
+++ b/packages/cdn/package.json
@@ -0,0 +1,23 @@
+{
+	"name": "@page-agent/cdn",
+	"private": false,
+	"version": "0.0.21",
+	"type": "module",
+	"files": [
+		"dist/"
+	],
+	"description": "CDN builds for page-agent - IIFE bundles for script tag usage",
+	"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 && vite build --mode demo"
+	},
+	"dependencies": {
+		"page-agent": "0.0.21"
+	}
+}
--- a/packages/cdn/src/demo.js
+++ b/packages/cdn/src/demo.js
@@ -0,0 +1,59 @@
+// @ts-nocheck
+/**
+ * Demo CDN build for page-agent
+ * Auto-initializes with built-in demo API for testing
+ *
+ * Usage:
+ *   <script src="https://unpkg.com/@page-agent/cdn/dist/page-agent.demo.js"></script>
+ */
+import { PageAgent } from 'page-agent'
+
+// 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 IIFE
+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'
+
+// Demo warning
+console.log(
+	'%c⚠️ DEMO MODE %c\n' +
+		'This build uses a shared testing LLM with rate limits.\n' +
+		'For production, use page-agent.js with your own API key:\n' +
+		'https://alibaba.github.io/page-agent/#/docs/features/models',
+	'background: #f59e0b; color: #000; font-size: 14px; font-weight: bold; padding: 4px 8px; border-radius: 4px;',
+	'color: #f59e0b; font-size: 12px;'
+)
+
+// in case document.x is not ready yet
+setTimeout(() => {
+	const currentScript = document.currentScript
+
+	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') || 'zh-CN'
+		const config = { 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()
+})
--- a/packages/cdn/src/full.js
+++ b/packages/cdn/src/full.js
@@ -0,0 +1,15 @@
+// @ts-nocheck
+/**
+ * Full CDN build for page-agent
+ * Exposes PageAgent class for manual instantiation and configuration
+ *
+ * Usage:
+ *   <script src="https://unpkg.com/@page-agent/cdn/dist/page-agent.js"></script>
+ *   <script>
+ *     const agent = new PageAgent({ model: 'gpt-4o', apiKey: 'your-key' })
+ *     agent.panel.show()
+ *   </script>
+ */
+import { PageAgent } from 'page-agent'
+
+export { PageAgent }
--- a/packages/cdn/vite.config.js
+++ b/packages/cdn/vite.config.js
@@ -0,0 +1,42 @@
+// @ts-nocheck
+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))
+
+/**
+ * CDN IIFE builds for page-agent
+ *
+ * Build targets (via --mode):
+ * - demo: page-agent.demo.js with auto-init and built-in API
+ * - full (default): page-agent.js exposes PageAgent class only
+ */
+export default defineConfig(({ mode }) => {
+	const isDemo = mode === 'demo'
+	const entry = isDemo ? resolve(__dirname, 'src/demo.js') : resolve(__dirname, 'src/full.js')
+	const fileName = isDemo ? 'page-agent.demo' : 'page-agent'
+
+	return {
+		plugins: [cssInjectedByJsPlugin({ relativeCSSInjection: true })],
+		publicDir: false,
+		esbuild: {
+			keepNames: true,
+		},
+		build: {
+			lib: {
+				entry,
+				name: 'PageAgent',
+				fileName: () => `${fileName}.js`,
+				formats: ['iife'],
+			},
+			outDir: resolve(__dirname, 'dist'),
+			emptyOutDir: !isDemo, // only empty on first build (full)
+			minify: false,
+		},
+		define: {
+			'process.env.NODE_ENV': '"production"',
+		},
+	}
+})