Compare commits
5 Commits
EXT_v0.1.1
..
v1.1.1
| Author | SHA1 | Date | |
|---|---|---|---|
 Simon
|
d00a8dcc21 | ||
|
Simon
|
851e9ef158 | ||
|
Simon
|
8ea8ce9acd | ||
|
Simon
|
9bd4a47d35 | ||
|
Simon
|
71ca554108 |
+3
-3
@@ -40,7 +40,7 @@
|
||||
|
||||
```html
|
||||
<script
|
||||
src="https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js"
|
||||
src="https://registry.npmmirror.com/page-agent/1.1.1/files/dist/iife/page-agent.demo.js"
|
||||
crossorigin="true"
|
||||
></script>
|
||||
```
|
||||
@@ -50,8 +50,8 @@
|
||||
|
||||
| Mirrors | URL |
|
||||
| ------- | ---------------------------------------------------------------------------------- |
|
||||
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js |
|
||||
| China | https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js |
|
||||
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.1.1/dist/iife/page-agent.demo.js |
|
||||
| China | https://registry.npmmirror.com/page-agent/1.1.1/files/dist/iife/page-agent.demo.js |
|
||||
|
||||
### NPM 安装
|
||||
|
||||
|
||||
@@ -40,7 +40,7 @@ Fastest way to try PageAgent with our free Demo LLM:
|
||||
|
||||
```html
|
||||
<script
|
||||
src="https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js"
|
||||
src="https://cdn.jsdelivr.net/npm/page-agent@1.1.1/dist/iife/page-agent.demo.js"
|
||||
crossorigin="true"
|
||||
></script>
|
||||
```
|
||||
@@ -50,8 +50,8 @@ Fastest way to try PageAgent with our free Demo LLM:
|
||||
|
||||
| Mirrors | URL |
|
||||
| ------- | ---------------------------------------------------------------------------------- |
|
||||
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js |
|
||||
| China | https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js |
|
||||
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.1.1/dist/iife/page-agent.demo.js |
|
||||
| China | https://registry.npmmirror.com/page-agent/1.1.1/files/dist/iife/page-agent.demo.js |
|
||||
|
||||
### NPM Installation
|
||||
|
||||
|
||||
Generated
+22
-22
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "root",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "root",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"license": "MIT",
|
||||
"workspaces": [
|
||||
"packages/page-controller",
|
||||
@@ -1639,9 +1639,9 @@
|
||||
}
|
||||
},
|
||||
"node_modules/@isaacs/brace-expansion": {
|
||||
"version": "5.0.0",
|
||||
"resolved": "https://registry.npmjs.org/@isaacs/brace-expansion/-/brace-expansion-5.0.0.tgz",
|
||||
"integrity": "sha512-ZT55BDLV0yv0RBm2czMiZ+SqCGO7AvmOM3G/w2xhVPH+te0aKgFjmBvGlL1dH+ql2tgGO3MVrbb3jCKyvpgnxA==",
|
||||
"version": "5.0.1",
|
||||
"resolved": "https://registry.npmjs.org/@isaacs/brace-expansion/-/brace-expansion-5.0.1.tgz",
|
||||
"integrity": "sha512-WMz71T1JS624nWj2n2fnYAuPovhv7EUhk69R6i9dsVyzxt5eM3bjwvgk9L+APE1TRscGysAVMANkB0jh0LQZrQ==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
@@ -11049,24 +11049,24 @@
|
||||
},
|
||||
"packages/core": {
|
||||
"name": "@page-agent/core",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@page-agent/llms": "1.1.0",
|
||||
"@page-agent/page-controller": "1.1.0",
|
||||
"@page-agent/llms": "1.1.1",
|
||||
"@page-agent/page-controller": "1.1.1",
|
||||
"chalk": "^5.6.2",
|
||||
"zod": "^4.3.5"
|
||||
}
|
||||
},
|
||||
"packages/extension": {
|
||||
"name": "@page-agent/ext",
|
||||
"version": "0.1.1",
|
||||
"version": "0.1.3",
|
||||
"hasInstallScript": true,
|
||||
"dependencies": {
|
||||
"@page-agent/core": "1.1.0",
|
||||
"@page-agent/llms": "1.1.0",
|
||||
"@page-agent/page-controller": "1.1.0",
|
||||
"@page-agent/ui": "1.1.0",
|
||||
"@page-agent/core": "1.1.1",
|
||||
"@page-agent/llms": "1.1.1",
|
||||
"@page-agent/page-controller": "1.1.1",
|
||||
"@page-agent/ui": "1.1.1",
|
||||
"@radix-ui/react-hover-card": "^1.1.15",
|
||||
"@radix-ui/react-icons": "^1.3.2",
|
||||
"@radix-ui/react-label": "^2.1.8",
|
||||
@@ -11100,7 +11100,7 @@
|
||||
},
|
||||
"packages/llms": {
|
||||
"name": "@page-agent/llms",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"chalk": "^5.6.2",
|
||||
@@ -11108,20 +11108,20 @@
|
||||
}
|
||||
},
|
||||
"packages/page-agent": {
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@page-agent/core": "1.1.0",
|
||||
"@page-agent/llms": "1.1.0",
|
||||
"@page-agent/page-controller": "1.1.0",
|
||||
"@page-agent/ui": "1.1.0",
|
||||
"@page-agent/core": "1.1.1",
|
||||
"@page-agent/llms": "1.1.1",
|
||||
"@page-agent/page-controller": "1.1.1",
|
||||
"@page-agent/ui": "1.1.1",
|
||||
"chalk": "^5.6.2",
|
||||
"zod": "^4.3.5"
|
||||
}
|
||||
},
|
||||
"packages/page-controller": {
|
||||
"name": "@page-agent/page-controller",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"ai-motion": "^0.4.8"
|
||||
@@ -11129,12 +11129,12 @@
|
||||
},
|
||||
"packages/ui": {
|
||||
"name": "@page-agent/ui",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"license": "MIT"
|
||||
},
|
||||
"packages/website": {
|
||||
"name": "@page-agent/website",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"dependencies": {
|
||||
"@radix-ui/react-icons": "^1.3.2",
|
||||
"@radix-ui/react-separator": "^1.1.8",
|
||||
|
||||
+1
-1
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "root",
|
||||
"private": true,
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"workspaces": [
|
||||
"packages/page-controller",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@page-agent/core",
|
||||
"private": false,
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"main": "./dist/esm/page-agent-core.js",
|
||||
"module": "./dist/esm/page-agent-core.js",
|
||||
@@ -45,7 +45,7 @@
|
||||
"dependencies": {
|
||||
"chalk": "^5.6.2",
|
||||
"zod": "^4.3.5",
|
||||
"@page-agent/llms": "1.1.0",
|
||||
"@page-agent/page-controller": "1.1.0"
|
||||
"@page-agent/llms": "1.1.1",
|
||||
"@page-agent/page-controller": "1.1.1"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -144,12 +144,12 @@ Here are examples of good output patterns. Use them as reference but never copy
|
||||
</examples>
|
||||
|
||||
<output>
|
||||
You must ALWAYS respond with a valid JSON in this exact format:
|
||||
|
||||
{
|
||||
"evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
|
||||
"memory": "1-3 concise sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
|
||||
"next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
|
||||
"action":{"action": {// action-specific parameter}}
|
||||
"next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
|
||||
"action":{
|
||||
"Action name": {// Action parameters}
|
||||
}
|
||||
}
|
||||
</output>
|
||||
|
||||
@@ -0,0 +1,291 @@
|
||||
# Page Agent Extension API
|
||||
|
||||
This document describes how to integrate the Page Agent browser extension into your web application.
|
||||
|
||||
## Installation
|
||||
|
||||
### 1. Install the browser extension
|
||||
|
||||
Install the Page Agent extension from the Chrome Web Store.
|
||||
|
||||
### 2. Install type definitions (recommended)
|
||||
|
||||
```bash
|
||||
npm install @page-agent/core --save-dev
|
||||
```
|
||||
|
||||
### 3. Set up authentication
|
||||
|
||||
The extension only injects APIs when it detects a valid token in `localStorage`.
|
||||
|
||||
1. Open the extension's side panel to get your authorization token
|
||||
2. Set the token in your page:
|
||||
|
||||
```typescript
|
||||
localStorage.setItem('PageAgentExtUserAuthToken', 'your-token')
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
```typescript
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentStatus,
|
||||
ExecutionResult,
|
||||
HistoricalEvent,
|
||||
} from '@page-agent/core'
|
||||
|
||||
// Wait for extension injection (up to 1 second)
|
||||
async function waitForExtension(timeout = 1000): Promise<boolean> {
|
||||
const start = Date.now()
|
||||
while (Date.now() - start < timeout) {
|
||||
if (window.PAGE_AGENT_EXT) return true
|
||||
await new Promise((r) => setTimeout(r, 100))
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Usage
|
||||
if (await waitForExtension()) {
|
||||
const result = await window.PAGE_AGENT_EXT!.execute('Click the login button', {
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: 'your-api-key',
|
||||
model: 'gpt-5.2',
|
||||
onStatusChange: (status) => console.log('Status:', status),
|
||||
onActivity: (activity) => console.log('Activity:', activity),
|
||||
})
|
||||
console.log('Result:', result)
|
||||
}
|
||||
```
|
||||
|
||||
## Global API
|
||||
|
||||
The extension injects the following APIs into the `window` object:
|
||||
|
||||
### `window.PAGE_AGENT_EXT_VERSION`
|
||||
|
||||
Extension version string (e.g., `"1.0.0"`). This is exposed separately to allow version checking before accessing the main API object.
|
||||
|
||||
### `window.PAGE_AGENT_EXT`
|
||||
|
||||
Main API namespace object containing:
|
||||
|
||||
#### `PAGE_AGENT_EXT.execute(task, config)`
|
||||
|
||||
Execute an agent task.
|
||||
|
||||
**Parameters:**
|
||||
|
||||
| Name | Type | Required | Description |
|
||||
|------|------|----------|-------------|
|
||||
| `task` | `string` | Yes | Task description |
|
||||
| `config` | `ExecuteConfig` | Yes | Execution configuration (LLM settings, options, and event callbacks) |
|
||||
|
||||
**Returns:** `Promise<ExecutionResult>`
|
||||
|
||||
#### `PAGE_AGENT_EXT.dispose()`
|
||||
|
||||
Stop and destroy the current running agent.
|
||||
|
||||
## Types
|
||||
|
||||
Install `@page-agent/core` for full type definitions:
|
||||
|
||||
```typescript
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentStatus,
|
||||
ExecutionResult,
|
||||
HistoricalEvent,
|
||||
} from '@page-agent/core'
|
||||
|
||||
export interface ExecuteConfig {
|
||||
baseURL: string
|
||||
apiKey: string
|
||||
model: string
|
||||
|
||||
/**
|
||||
* Whether to include the initial tab (that holds this main world script) in the task.
|
||||
* @default true
|
||||
*/
|
||||
includeInitialTab?: boolean
|
||||
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
onActivity?: (activity: AgentActivity) => void
|
||||
onHistoryUpdate?: (history: HistoricalEvent[]) => void
|
||||
onDispose?: () => void
|
||||
}
|
||||
|
||||
export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
|
||||
```
|
||||
|
||||
### AgentStatus
|
||||
|
||||
```typescript
|
||||
type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
|
||||
```
|
||||
|
||||
| Status | Description |
|
||||
|--------|-------------|
|
||||
| `idle` | Agent is idle, ready to execute |
|
||||
| `running` | Agent is executing a task |
|
||||
| `completed` | Task completed successfully |
|
||||
| `error` | Task failed with an error |
|
||||
|
||||
### AgentActivity
|
||||
|
||||
```typescript
|
||||
type AgentActivity =
|
||||
| { type: 'thinking' }
|
||||
| { type: 'executing'; tool: string; input: unknown }
|
||||
| { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
|
||||
| { type: 'retrying'; attempt: number; maxAttempts: number }
|
||||
| { type: 'error'; message: string }
|
||||
```
|
||||
|
||||
| Type | Description |
|
||||
|------|-------------|
|
||||
| `thinking` | Agent is analyzing the page and planning |
|
||||
| `executing` | Agent is executing a tool action |
|
||||
| `executed` | Tool execution completed |
|
||||
| `retrying` | Retrying after a failure |
|
||||
| `error` | An error occurred |
|
||||
|
||||
### HistoricalEvent
|
||||
|
||||
```typescript
|
||||
type HistoricalEvent =
|
||||
| { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
|
||||
| { type: 'observation'; content: string }
|
||||
| { type: 'user_takeover' }
|
||||
| { type: 'retry'; message: string; attempt: number; maxAttempts: number }
|
||||
| { type: 'error'; message: string; rawResponse?: unknown }
|
||||
```
|
||||
|
||||
### ExecutionResult
|
||||
|
||||
```typescript
|
||||
interface ExecutionResult {
|
||||
success: boolean
|
||||
data: string
|
||||
history: HistoricalEvent[]
|
||||
}
|
||||
```
|
||||
|
||||
## Usage Examples
|
||||
|
||||
### Basic Execution
|
||||
|
||||
```typescript
|
||||
const result = await window.PAGE_AGENT_EXT!.execute(
|
||||
'Fill in the email field with test@example.com and click Submit',
|
||||
{
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
}
|
||||
)
|
||||
|
||||
if (result.success) {
|
||||
console.log('Task completed:', result.data)
|
||||
} else {
|
||||
console.error('Task failed')
|
||||
}
|
||||
```
|
||||
|
||||
### Exclude Initial Tab
|
||||
|
||||
By default, the agent includes the initial tab (where the script runs) in the task. Set `includeInitialTab: false` to exclude it:
|
||||
|
||||
```typescript
|
||||
const result = await window.PAGE_AGENT_EXT!.execute(
|
||||
'Open a new tab and search for page-agent on GitHub',
|
||||
{
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
includeInitialTab: false, // Agent will open new tabs only
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
### With Event Callbacks
|
||||
|
||||
```typescript
|
||||
await window.PAGE_AGENT_EXT!.execute('Navigate to the settings page', {
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
onStatusChange: (status) => {
|
||||
updateUI({ agentStatus: status })
|
||||
},
|
||||
onActivity: (activity) => {
|
||||
switch (activity.type) {
|
||||
case 'thinking':
|
||||
showSpinner('Agent is thinking...')
|
||||
break
|
||||
case 'executing':
|
||||
showSpinner(`Executing: ${activity.tool}`)
|
||||
break
|
||||
case 'executed':
|
||||
log(`${activity.tool} completed in ${activity.duration}ms`)
|
||||
break
|
||||
case 'error':
|
||||
showError(activity.message)
|
||||
break
|
||||
}
|
||||
},
|
||||
onHistoryUpdate: (history) => {
|
||||
renderHistory(history)
|
||||
},
|
||||
})
|
||||
```
|
||||
|
||||
### Stop Execution
|
||||
|
||||
```typescript
|
||||
// Start a task
|
||||
window.PAGE_AGENT_EXT!.execute('Scroll through all pages', {
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
})
|
||||
|
||||
// Later, stop it
|
||||
window.PAGE_AGENT_EXT!.dispose()
|
||||
```
|
||||
|
||||
## Window Type Declaration
|
||||
|
||||
If not using `@page-agent/core`, add this to your project:
|
||||
|
||||
```typescript
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentStatus,
|
||||
ExecutionResult,
|
||||
HistoricalEvent,
|
||||
} from '@page-agent/core'
|
||||
|
||||
interface ExecuteConfig {
|
||||
baseURL: string
|
||||
apiKey: string
|
||||
model: string
|
||||
includeInitialTab?: boolean
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
onActivity?: (activity: AgentActivity) => void
|
||||
onHistoryUpdate?: (history: HistoricalEvent[]) => void
|
||||
onDispose?: () => void
|
||||
}
|
||||
|
||||
declare global {
|
||||
interface Window {
|
||||
PAGE_AGENT_EXT_VERSION?: string
|
||||
PAGE_AGENT_EXT?: {
|
||||
version: string
|
||||
execute: (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
|
||||
dispose: () => void
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,291 @@
|
||||
# Page Agent 浏览器插件 API
|
||||
|
||||
本文档介绍如何在网页应用中接入 Page Agent 浏览器插件。
|
||||
|
||||
## 安装
|
||||
|
||||
### 1. 安装浏览器插件
|
||||
|
||||
从 Chrome 应用商店安装 Page Agent 插件。
|
||||
|
||||
### 2. 安装类型定义（推荐）
|
||||
|
||||
```bash
|
||||
npm install @page-agent/core --save-dev
|
||||
```
|
||||
|
||||
### 3. 配置认证
|
||||
|
||||
插件在页面加载后检测 `localStorage` 中的 token，匹配时才会注入 API。
|
||||
|
||||
1. 打开插件的侧边栏面板，获取授权 token
|
||||
2. 在页面中设置 token：
|
||||
|
||||
```typescript
|
||||
localStorage.setItem('PageAgentExtUserAuthToken', 'your-token')
|
||||
```
|
||||
|
||||
## 快速开始
|
||||
|
||||
```typescript
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentStatus,
|
||||
ExecutionResult,
|
||||
HistoricalEvent,
|
||||
} from '@page-agent/core'
|
||||
|
||||
// 等待插件注入（最多 1 秒）
|
||||
async function waitForExtension(timeout = 1000): Promise<boolean> {
|
||||
const start = Date.now()
|
||||
while (Date.now() - start < timeout) {
|
||||
if (window.PAGE_AGENT_EXT) return true
|
||||
await new Promise((r) => setTimeout(r, 100))
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// 使用
|
||||
if (await waitForExtension()) {
|
||||
const result = await window.PAGE_AGENT_EXT!.execute('点击登录按钮', {
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: 'your-api-key',
|
||||
model: 'gpt-5.2',
|
||||
onStatusChange: (status) => console.log('状态:', status),
|
||||
onActivity: (activity) => console.log('活动:', activity),
|
||||
})
|
||||
console.log('结果:', result)
|
||||
}
|
||||
```
|
||||
|
||||
## 全局 API
|
||||
|
||||
插件在 `window` 对象上注入以下 API：
|
||||
|
||||
### `window.PAGE_AGENT_EXT_VERSION`
|
||||
|
||||
插件版本号字符串（例如 `"1.0.0"`）。单独暴露版本号，方便在访问主 API 对象前进行版本检查。
|
||||
|
||||
### `window.PAGE_AGENT_EXT`
|
||||
|
||||
主 API 命名空间对象，包含：
|
||||
|
||||
#### `PAGE_AGENT_EXT.execute(task, config)`
|
||||
|
||||
执行 Agent 任务。
|
||||
|
||||
**参数：**
|
||||
|
||||
| 名称 | 类型 | 必填 | 说明 |
|
||||
|------|------|------|------|
|
||||
| `task` | `string` | 是 | 任务描述 |
|
||||
| `config` | `ExecuteConfig` | 是 | 执行配置（LLM 设置、选项和事件回调） |
|
||||
|
||||
**返回：** `Promise<ExecutionResult>`
|
||||
|
||||
#### `PAGE_AGENT_EXT.dispose()`
|
||||
|
||||
停止并销毁当前运行的 Agent。
|
||||
|
||||
## 类型定义
|
||||
|
||||
安装 `@page-agent/core` 获取完整类型：
|
||||
|
||||
```typescript
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentStatus,
|
||||
ExecutionResult,
|
||||
HistoricalEvent,
|
||||
} from '@page-agent/core'
|
||||
|
||||
export interface ExecuteConfig {
|
||||
baseURL: string
|
||||
apiKey: string
|
||||
model: string
|
||||
|
||||
/**
|
||||
* 是否将初始标签页（运行此脚本的页面）包含在任务中。
|
||||
* @default true
|
||||
*/
|
||||
includeInitialTab?: boolean
|
||||
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
onActivity?: (activity: AgentActivity) => void
|
||||
onHistoryUpdate?: (history: HistoricalEvent[]) => void
|
||||
onDispose?: () => void
|
||||
}
|
||||
|
||||
export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
|
||||
```
|
||||
|
||||
### AgentStatus
|
||||
|
||||
```typescript
|
||||
type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
|
||||
```
|
||||
|
||||
| 状态 | 说明 |
|
||||
|------|------|
|
||||
| `idle` | 空闲，准备执行 |
|
||||
| `running` | 正在执行任务 |
|
||||
| `completed` | 任务成功完成 |
|
||||
| `error` | 任务执行失败 |
|
||||
|
||||
### AgentActivity
|
||||
|
||||
```typescript
|
||||
type AgentActivity =
|
||||
| { type: 'thinking' }
|
||||
| { type: 'executing'; tool: string; input: unknown }
|
||||
| { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
|
||||
| { type: 'retrying'; attempt: number; maxAttempts: number }
|
||||
| { type: 'error'; message: string }
|
||||
```
|
||||
|
||||
| 类型 | 说明 |
|
||||
|------|------|
|
||||
| `thinking` | Agent 正在分析页面并规划 |
|
||||
| `executing` | 正在执行工具操作 |
|
||||
| `executed` | 工具执行完成 |
|
||||
| `retrying` | 失败后重试 |
|
||||
| `error` | 发生错误 |
|
||||
|
||||
### HistoricalEvent
|
||||
|
||||
```typescript
|
||||
type HistoricalEvent =
|
||||
| { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
|
||||
| { type: 'observation'; content: string }
|
||||
| { type: 'user_takeover' }
|
||||
| { type: 'retry'; message: string; attempt: number; maxAttempts: number }
|
||||
| { type: 'error'; message: string; rawResponse?: unknown }
|
||||
```
|
||||
|
||||
### ExecutionResult
|
||||
|
||||
```typescript
|
||||
interface ExecutionResult {
|
||||
success: boolean
|
||||
data: string
|
||||
history: HistoricalEvent[]
|
||||
}
|
||||
```
|
||||
|
||||
## 使用示例
|
||||
|
||||
### 基础执行
|
||||
|
||||
```typescript
|
||||
const result = await window.PAGE_AGENT_EXT!.execute(
|
||||
'在邮箱输入框填入 test@example.com 然后点击提交',
|
||||
{
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
}
|
||||
)
|
||||
|
||||
if (result.success) {
|
||||
console.log('任务完成:', result.data)
|
||||
} else {
|
||||
console.error('任务失败')
|
||||
}
|
||||
```
|
||||
|
||||
### 排除初始标签页
|
||||
|
||||
默认情况下，Agent 会将初始标签页（运行脚本的页面）包含在任务中。设置 `includeInitialTab: false` 可以排除它：
|
||||
|
||||
```typescript
|
||||
const result = await window.PAGE_AGENT_EXT!.execute(
|
||||
'打开新标签页并在 GitHub 上搜索 page-agent',
|
||||
{
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
includeInitialTab: false, // Agent 只会打开新标签页
|
||||
}
|
||||
)
|
||||
```
|
||||
|
||||
### 使用事件回调
|
||||
|
||||
```typescript
|
||||
await window.PAGE_AGENT_EXT!.execute('导航到设置页面', {
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
onStatusChange: (status) => {
|
||||
updateUI({ agentStatus: status })
|
||||
},
|
||||
onActivity: (activity) => {
|
||||
switch (activity.type) {
|
||||
case 'thinking':
|
||||
showSpinner('Agent 正在思考...')
|
||||
break
|
||||
case 'executing':
|
||||
showSpinner(`正在执行: ${activity.tool}`)
|
||||
break
|
||||
case 'executed':
|
||||
log(`${activity.tool} 完成，耗时 ${activity.duration}ms`)
|
||||
break
|
||||
case 'error':
|
||||
showError(activity.message)
|
||||
break
|
||||
}
|
||||
},
|
||||
onHistoryUpdate: (history) => {
|
||||
renderHistory(history)
|
||||
},
|
||||
})
|
||||
```
|
||||
|
||||
### 停止执行
|
||||
|
||||
```typescript
|
||||
// 启动任务
|
||||
window.PAGE_AGENT_EXT!.execute('滚动浏览所有页面', {
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: process.env.OPENAI_API_KEY!,
|
||||
model: 'gpt-5.2',
|
||||
})
|
||||
|
||||
// 稍后停止
|
||||
window.PAGE_AGENT_EXT!.dispose()
|
||||
```
|
||||
|
||||
## Window 类型声明
|
||||
|
||||
如果不使用 `@page-agent/core`，可以添加以下声明：
|
||||
|
||||
```typescript
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentStatus,
|
||||
ExecutionResult,
|
||||
HistoricalEvent,
|
||||
} from '@page-agent/core'
|
||||
|
||||
interface ExecuteConfig {
|
||||
baseURL: string
|
||||
apiKey: string
|
||||
model: string
|
||||
includeInitialTab?: boolean
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
onActivity?: (activity: AgentActivity) => void
|
||||
onHistoryUpdate?: (history: HistoricalEvent[]) => void
|
||||
onDispose?: () => void
|
||||
}
|
||||
|
||||
declare global {
|
||||
interface Window {
|
||||
PAGE_AGENT_EXT_VERSION?: string
|
||||
PAGE_AGENT_EXT?: {
|
||||
version: string
|
||||
execute: (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
|
||||
dispose: () => void
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@page-agent/ext",
|
||||
"private": true,
|
||||
"version": "0.1.1",
|
||||
"version": "0.1.3",
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
"dev": "wxt",
|
||||
@@ -23,10 +23,10 @@
|
||||
"wxt": "^0.20.13"
|
||||
},
|
||||
"dependencies": {
|
||||
"@page-agent/core": "1.1.0",
|
||||
"@page-agent/llms": "1.1.0",
|
||||
"@page-agent/page-controller": "1.1.0",
|
||||
"@page-agent/ui": "1.1.0",
|
||||
"@page-agent/core": "1.1.1",
|
||||
"@page-agent/llms": "1.1.1",
|
||||
"@page-agent/page-controller": "1.1.1",
|
||||
"@page-agent/ui": "1.1.1",
|
||||
"@radix-ui/react-hover-card": "^1.1.15",
|
||||
"@radix-ui/react-icons": "^1.3.2",
|
||||
"@radix-ui/react-label": "^2.1.8",
|
||||
|
||||
@@ -17,7 +17,7 @@ function detectLanguage(): 'en-US' | 'zh-CN' {
|
||||
* - can be used from a side panel or a content script
|
||||
*/
|
||||
export class MultiPageAgent extends PageAgentCore {
|
||||
constructor(config: Omit<PageAgentConfig, 'pageController'>) {
|
||||
constructor(config: Omit<PageAgentConfig, 'pageController'> & { includeInitialTab?: boolean }) {
|
||||
// multi page controller
|
||||
const tabsController = new TabsController()
|
||||
const pageController = new RemotePageController(tabsController)
|
||||
@@ -31,6 +31,9 @@ export class MultiPageAgent extends PageAgentCore {
|
||||
`Default working language: **${targetLanguage}**`
|
||||
)
|
||||
|
||||
// include initial tab for controlling
|
||||
const includeInitialTab = config.includeInitialTab ?? true
|
||||
|
||||
/**
|
||||
* When the agent is in side-panel and user closed the side-panel.
|
||||
* There is no chance for isAgentRunning to be set false.
|
||||
@@ -47,7 +50,7 @@ export class MultiPageAgent extends PageAgentCore {
|
||||
customSystemPrompt: systemPrompt,
|
||||
|
||||
onBeforeTask: async (agent) => {
|
||||
await tabsController.init(agent.task)
|
||||
await tabsController.init(agent.task, includeInitialTab)
|
||||
|
||||
heartBeatInterval = window.setInterval(() => {
|
||||
chrome.storage.local.set({
|
||||
|
||||
@@ -12,7 +12,7 @@ export class TabsController extends EventTarget {
|
||||
private task: string = ''
|
||||
private windowId: number | null = null
|
||||
|
||||
async init(task: string) {
|
||||
async init(task: string, includeInitialTab: boolean = true) {
|
||||
this.task = task
|
||||
this.tabs = []
|
||||
this.currentTabId = null
|
||||
@@ -26,17 +26,19 @@ export class TabsController extends EventTarget {
|
||||
})
|
||||
|
||||
this.initialTabId = result.tabId
|
||||
this.currentTabId = result.tabId
|
||||
|
||||
this.tabs.push({
|
||||
id: result.tabId,
|
||||
isInitial: true,
|
||||
})
|
||||
|
||||
if (!this.initialTabId) {
|
||||
throw new Error('Failed to get initial tab ID')
|
||||
}
|
||||
|
||||
if (includeInitialTab) {
|
||||
this.currentTabId = this.initialTabId
|
||||
this.tabs.push({
|
||||
id: result.tabId,
|
||||
isInitial: true,
|
||||
})
|
||||
}
|
||||
|
||||
await this.updateCurrentTabId(this.currentTabId)
|
||||
|
||||
const tabChangeHandler = (message: any): void => {
|
||||
@@ -230,6 +232,10 @@ export class TabsController extends EventTarget {
|
||||
`| ${tab.id} | ${url} | ${title} | ${this.currentTabId === tab.id ? '✅' : ''} |`
|
||||
)
|
||||
}
|
||||
if (!this.tabs.length) {
|
||||
summaries.push('\nNo tabs available. Open a tab if needed.')
|
||||
}
|
||||
|
||||
return summaries.join('\n')
|
||||
}
|
||||
|
||||
|
||||
@@ -136,12 +136,12 @@ Here are examples of good output patterns. Use them as reference but never copy
|
||||
</examples>
|
||||
|
||||
<output>
|
||||
You must ALWAYS respond with a valid JSON in this exact format:
|
||||
|
||||
{
|
||||
"evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
|
||||
"memory": "1-3 concise sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
|
||||
"next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
|
||||
"action":{"action_name": {// action-specific parameter}}
|
||||
"next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
|
||||
"action":{
|
||||
"Action name": {// Action parameters}
|
||||
}
|
||||
}
|
||||
</output>
|
||||
|
||||
@@ -69,11 +69,11 @@ async function exposeAgentToPage() {
|
||||
}
|
||||
|
||||
try {
|
||||
const { task, llmConfig } = payload
|
||||
const { task, config } = payload
|
||||
|
||||
// create when used
|
||||
|
||||
multiPageAgent = new MultiPageAgent(llmConfig)
|
||||
multiPageAgent = new MultiPageAgent(config)
|
||||
|
||||
// events
|
||||
|
||||
|
||||
@@ -1,39 +1,38 @@
|
||||
import type { AgentActivity, AgentStatus, ExecutionResult, HistoricalEvent } from '@page-agent/core'
|
||||
import type { LLMConfig } from '@page-agent/llms'
|
||||
|
||||
export interface ExecuteHooks {
|
||||
export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
|
||||
|
||||
export interface ExecuteConfig {
|
||||
baseURL: string
|
||||
apiKey: string
|
||||
model: string
|
||||
|
||||
/**
|
||||
* Whether to include the initial tab (that holds this main world script) in the task.
|
||||
* @default true
|
||||
*/
|
||||
includeInitialTab?: boolean
|
||||
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
onActivity?: (activity: AgentActivity) => void
|
||||
onHistoryUpdate?: (history: HistoricalEvent[]) => void
|
||||
onDispose?: () => void
|
||||
}
|
||||
|
||||
export type Execute = (
|
||||
task: string,
|
||||
llmConfig: LLMConfig,
|
||||
hooks?: ExecuteHooks
|
||||
) => Promise<ExecutionResult>
|
||||
|
||||
export default defineUnlistedScript(() => {
|
||||
const w = window as any
|
||||
|
||||
let _lastId = 0
|
||||
function getId() {
|
||||
_lastId += 1
|
||||
return _lastId
|
||||
}
|
||||
|
||||
w.PAGE_AGENT_EXT_INSTALLED = true
|
||||
w.PAGE_AGENT_EXT_VERSION = __EXT_VERSION__
|
||||
w.PAGE_AGENT_EXT_CORE_VERSION = __CORE_VERSION__
|
||||
|
||||
w.execute = async (task: string, llmConfig: LLMConfig, hooks?: ExecuteHooks) => {
|
||||
const execute: Execute = async (task, config) => {
|
||||
if (typeof task !== 'string') throw new Error('Task must be a string')
|
||||
if (task.trim().length === 0) throw new Error('Task cannot be empty')
|
||||
if (!llmConfig) throw new Error('LLM config is required')
|
||||
if (!llmConfig.baseURL) throw new Error('LLM config must have a baseURL')
|
||||
if (!llmConfig.apiKey) throw new Error('LLM config must have an apiKey')
|
||||
if (!llmConfig.model) throw new Error('LLM config must have a model')
|
||||
if (!config) throw new Error('Config is required')
|
||||
if (!config.baseURL) throw new Error('Config must have a baseURL')
|
||||
if (!config.apiKey) throw new Error('Config must have an apiKey')
|
||||
if (!config.model) throw new Error('Config must have a model')
|
||||
|
||||
const id = getId()
|
||||
|
||||
@@ -46,30 +45,31 @@ export default defineUnlistedScript(() => {
|
||||
|
||||
// events
|
||||
|
||||
if (data.action === 'status_change_event' && hooks?.onStatusChange) {
|
||||
hooks.onStatusChange(data.payload)
|
||||
if (data.action === 'status_change_event' && config.onStatusChange) {
|
||||
config.onStatusChange(data.payload)
|
||||
return
|
||||
}
|
||||
|
||||
if (data.action === 'activity_event' && hooks?.onActivity) {
|
||||
hooks.onActivity(data.payload)
|
||||
if (data.action === 'activity_event' && config.onActivity) {
|
||||
config.onActivity(data.payload)
|
||||
return
|
||||
}
|
||||
|
||||
if (data.action === 'history_change_event' && hooks?.onHistoryUpdate) {
|
||||
hooks.onHistoryUpdate(data.payload)
|
||||
if (data.action === 'history_change_event' && config.onHistoryUpdate) {
|
||||
config.onHistoryUpdate(data.payload)
|
||||
return
|
||||
}
|
||||
|
||||
if (data.action === 'dispose_event' && hooks?.onDispose) {
|
||||
hooks.onDispose()
|
||||
if (data.action === 'dispose_event' && config.onDispose) {
|
||||
config.onDispose()
|
||||
window.removeEventListener('message', handleMessage)
|
||||
return
|
||||
}
|
||||
|
||||
// result
|
||||
|
||||
if (data.action !== 'execute_result') return
|
||||
|
||||
// execute_result
|
||||
|
||||
window.removeEventListener('message', handleMessage)
|
||||
|
||||
if (data.error) {
|
||||
@@ -79,6 +79,7 @@ export default defineUnlistedScript(() => {
|
||||
}
|
||||
}
|
||||
|
||||
// @note will be removed on dispose or result
|
||||
window.addEventListener('message', handleMessage)
|
||||
})
|
||||
|
||||
@@ -87,7 +88,15 @@ export default defineUnlistedScript(() => {
|
||||
channel: 'PAGE_AGENT_EXT_REQUEST',
|
||||
id,
|
||||
action: 'execute',
|
||||
payload: { task, llmConfig },
|
||||
payload: {
|
||||
task,
|
||||
config: {
|
||||
baseURL: config.baseURL,
|
||||
apiKey: config.apiKey,
|
||||
model: config.model,
|
||||
includeInitialTab: config.includeInitialTab,
|
||||
},
|
||||
},
|
||||
},
|
||||
'*'
|
||||
)
|
||||
@@ -95,7 +104,7 @@ export default defineUnlistedScript(() => {
|
||||
return promise
|
||||
}
|
||||
|
||||
w.dispose = () => {
|
||||
const dispose = () => {
|
||||
const id = getId()
|
||||
|
||||
window.postMessage(
|
||||
@@ -107,4 +116,11 @@ export default defineUnlistedScript(() => {
|
||||
'*'
|
||||
)
|
||||
}
|
||||
|
||||
;(window as any).PAGE_AGENT_EXT_VERSION = __EXT_VERSION__
|
||||
;(window as any).PAGE_AGENT_EXT = {
|
||||
version: __EXT_VERSION__,
|
||||
execute,
|
||||
dispose,
|
||||
}
|
||||
})
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@page-agent/llms",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"main": "./dist/lib/page-agent-llms.js",
|
||||
"module": "./dist/lib/page-agent-llms.js",
|
||||
|
||||
@@ -74,6 +74,10 @@ export function modelPatch(body: Record<string, any>) {
|
||||
} else if (modelName.startsWith('gpt-51')) {
|
||||
debug('Applying GPT-51 patch: disable reasoning')
|
||||
body.reasoning_effort = 'none'
|
||||
} else if (modelName.startsWith('gpt-5-mini')) {
|
||||
debug('Applying GPT-5-mini patch: set reasoning effort to low, temperature to 1')
|
||||
body.reasoning_effort = 'low'
|
||||
body.temperature = 1
|
||||
} else if (modelName.startsWith('gpt-5')) {
|
||||
debug('Applying GPT-5 patch: set reasoning effort to low')
|
||||
body.reasoning_effort = 'low'
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "page-agent",
|
||||
"private": false,
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"main": "./dist/esm/page-agent.js",
|
||||
"module": "./dist/esm/page-agent.js",
|
||||
@@ -46,9 +46,9 @@
|
||||
"dependencies": {
|
||||
"chalk": "^5.6.2",
|
||||
"zod": "^4.3.5",
|
||||
"@page-agent/llms": "1.1.0",
|
||||
"@page-agent/page-controller": "1.1.0",
|
||||
"@page-agent/core": "1.1.0",
|
||||
"@page-agent/ui": "1.1.0"
|
||||
"@page-agent/llms": "1.1.1",
|
||||
"@page-agent/page-controller": "1.1.1",
|
||||
"@page-agent/core": "1.1.1",
|
||||
"@page-agent/ui": "1.1.1"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@page-agent/page-controller",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"main": "./dist/lib/page-controller.js",
|
||||
"module": "./dist/lib/page-controller.js",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@page-agent/ui",
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"main": "./dist/lib/page-agent-ui.js",
|
||||
"module": "./dist/lib/page-agent-ui.js",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@page-agent/website",
|
||||
"private": true,
|
||||
"version": "1.1.0",
|
||||
"version": "1.1.1",
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
"dev": "vite --host 0.0.0.0",
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
// Demo build (auto-init with demo LLM, for quick testing)
|
||||
export const CDN_DEMO_URL =
|
||||
'https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js'
|
||||
'https://cdn.jsdelivr.net/npm/page-agent@1.1.1/dist/iife/page-agent.demo.js'
|
||||
export const CDN_DEMO_CN_URL =
|
||||
'https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js'
|
||||
'https://registry.npmmirror.com/page-agent/1.1.1/files/dist/iife/page-agent.demo.js'
|
||||
|
||||
// Demo LLM for website testing
|
||||
export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
|
||||
|
||||
@@ -103,13 +103,13 @@ export default function ChromeExtension() {
|
||||
isZh
|
||||
? `// 1. 用户安装扩展并在扩展设置中配置 auth token
|
||||
// 2. 你的页面读取相同的 token 并存入 localStorage
|
||||
// 3. Token 匹配后，扩展会暴露 window.execute() 和 window.dispose()
|
||||
// 3. Token 匹配后，扩展会暴露 window.PAGE_AGENT_EXT 对象
|
||||
|
||||
// ⚠️ 请在扩展弹窗中查看你的 auth token，然后填入下方
|
||||
localStorage.setItem('PageAgentExtUserAuthToken', '<从扩展中获取的-token>')`
|
||||
: `// 1. User installs extension and sets an auth token in extension settings
|
||||
// 2. Your page reads the same token and stores it in localStorage
|
||||
// 3. After token match, extension exposes window.execute() and window.dispose()
|
||||
// 3. After token match, extension exposes window.PAGE_AGENT_EXT object
|
||||
|
||||
// ⚠️ Check your extension popup for the auth token
|
||||
localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')`
|
||||
@@ -122,25 +122,54 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
|
||||
<section>
|
||||
<h2 className="text-2xl font-bold mb-4">{isZh ? 'API 参考' : 'API Reference'}</h2>
|
||||
|
||||
<h3 className="text-xl font-semibold mb-3">window.execute(task, llmConfig, hooks?)</h3>
|
||||
{/* AI Assistant Instructions */}
|
||||
<section className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
|
||||
<h3 className="text-lg font-semibold text-purple-900 dark:text-purple-300 mb-2">
|
||||
🤖 {isZh ? '给 AI 编程助手的文档' : 'Instructions for Your AI Assistant'}
|
||||
</h3>
|
||||
<p className="text-gray-600 dark:text-gray-300 mb-3 text-sm">
|
||||
{isZh
|
||||
? '如果你在使用 AI 编程助手（如 Cursor、GitHub Copilot），可以将以下文档链接提供给它，让它更好地理解和使用 Page Agent 扩展 API：'
|
||||
: 'If you are using an AI coding assistant (like Cursor, GitHub Copilot), share these documentation links with it for better understanding of Page Agent Extension API:'}
|
||||
</p>
|
||||
<div className="space-y-2">
|
||||
<a
|
||||
href="https://github.com/alibaba/page-agent/blob/main/packages/extension/docs/extension_api.md"
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline"
|
||||
>
|
||||
📄 {isZh ? '英文版 API 文档' : 'API Documentation (English)'}
|
||||
</a>
|
||||
<a
|
||||
href="https://github.com/alibaba/page-agent/blob/main/packages/extension/docs/extension_api_zh.md"
|
||||
target="_blank"
|
||||
rel="noopener noreferrer"
|
||||
className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline"
|
||||
>
|
||||
📄 {isZh ? '中文版 API 文档' : 'API Documentation (Chinese)'}
|
||||
</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<h3 className="text-xl font-semibold my-3">PAGE_AGENT_EXT.execute(task, config)</h3>
|
||||
<p className="text-gray-600 dark:text-gray-300 mb-4">
|
||||
{isZh
|
||||
? '使用 LLM 配置执行任务。返回一个 Promise，在任务完成时 resolve。可选的 hooks 参数用于监听任务执行过程中的事件。'
|
||||
: 'Execute a task with LLM configuration. Returns a Promise that resolves when the task completes. Optional hooks parameter for listening to events during task execution.'}
|
||||
? '使用配置执行任务。返回一个 Promise，在任务完成时 resolve。config 参数包含 LLM 设置、选项和事件回调。'
|
||||
: 'Execute a task with configuration. Returns a Promise that resolves when the task completes. Config includes LLM settings, options, and event callbacks.'}
|
||||
</p>
|
||||
|
||||
<CodeEditor
|
||||
code={
|
||||
isZh
|
||||
? `// 使用 LLM 配置和 hooks 执行任务
|
||||
const result = await window.execute(
|
||||
? `// 使用配置执行任务
|
||||
const result = await window.PAGE_AGENT_EXT.execute(
|
||||
'在 GitHub 上搜索 "page-agent" 并打开第一个结果',
|
||||
{
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: 'your-api-key',
|
||||
model: 'gpt-5-2'
|
||||
},
|
||||
{
|
||||
model: 'gpt-5-2',
|
||||
// includeInitialTab: false, // 设为 false 排除初始标签页
|
||||
onStatusChange: status => console.log('状态变化:', status),
|
||||
onActivity: activity => console.log('活动:', activity),
|
||||
onHistoryUpdate: history => console.log('历史更新:', history),
|
||||
@@ -149,15 +178,14 @@ const result = await window.execute(
|
||||
)
|
||||
|
||||
console.log(result) // 任务执行结果`
|
||||
: `// Execute a task with LLM configuration and hooks
|
||||
const result = await window.execute(
|
||||
: `// Execute a task with configuration
|
||||
const result = await window.PAGE_AGENT_EXT.execute(
|
||||
'Search for "page-agent" on GitHub and open the first result',
|
||||
{
|
||||
baseURL: 'https://api.openai.com/v1',
|
||||
apiKey: 'your-api-key',
|
||||
model: 'gpt-5-2'
|
||||
},
|
||||
{
|
||||
model: 'gpt-5-2',
|
||||
// includeInitialTab: false, // Set to false to exclude initial tab
|
||||
onStatusChange: status => console.log('Status change:', status),
|
||||
onActivity: activity => console.log('Activity:', activity),
|
||||
onHistoryUpdate: history => console.log('History update:', history),
|
||||
@@ -170,7 +198,7 @@ console.log(result) // Task execution result`
|
||||
language="javascript"
|
||||
/>
|
||||
|
||||
<h3 className="text-xl font-semibold mt-6 mb-3">window.dispose()</h3>
|
||||
<h3 className="text-xl font-semibold mt-6 mb-3">PAGE_AGENT_EXT.dispose()</h3>
|
||||
<p className="text-gray-600 dark:text-gray-300 mb-4">
|
||||
{isZh
|
||||
? '停止当前正在运行的任务。停止后 Agent 可以重新使用。'
|
||||
@@ -181,49 +209,34 @@ console.log(result) // Task execution result`
|
||||
code={
|
||||
isZh
|
||||
? `// 停止当前任务
|
||||
window.dispose()`
|
||||
window.PAGE_AGENT_EXT.dispose()`
|
||||
: `// Stop current task execution
|
||||
window.dispose()`
|
||||
window.PAGE_AGENT_EXT.dispose()`
|
||||
}
|
||||
language="javascript"
|
||||
/>
|
||||
</section>
|
||||
|
||||
{/* LLM Config */}
|
||||
{/* ExecuteConfig */}
|
||||
<section>
|
||||
<h2 className="text-2xl font-bold mb-4">{isZh ? 'LLM 配置' : 'LLM Configuration'}</h2>
|
||||
|
||||
<CodeEditor
|
||||
code={
|
||||
isZh
|
||||
? `interface LLMConfig {
|
||||
baseURL: string // LLM API 端点
|
||||
apiKey: string // API 密钥
|
||||
model: string // 模型名称
|
||||
}`
|
||||
: `interface LLMConfig {
|
||||
baseURL: string // LLM API endpoint
|
||||
apiKey: string // API key
|
||||
model: string // Model name
|
||||
}`
|
||||
}
|
||||
language="typescript"
|
||||
/>
|
||||
</section>
|
||||
|
||||
{/* Execute Hooks */}
|
||||
<section>
|
||||
<h2 className="text-2xl font-bold mb-4">{isZh ? 'Execute Hooks' : 'Execute Hooks'}</h2>
|
||||
<h2 className="text-2xl font-bold mb-4">{isZh ? '执行配置' : 'Execute Configuration'}</h2>
|
||||
<p className="text-gray-600 dark:text-gray-300 mb-4">
|
||||
{isZh
|
||||
? '通过 hooks 参数，你可以监听任务执行过程中的各种事件，实现实时更新 UI、日志记录等功能。'
|
||||
: 'With hooks parameter, you can listen to various events during task execution for real-time UI updates, logging, and more.'}
|
||||
? 'config 参数包含 LLM 设置、选项和事件回调，用于控制任务执行行为。'
|
||||
: 'The config parameter includes LLM settings, options, and event callbacks to control task execution behavior.'}
|
||||
</p>
|
||||
|
||||
<CodeEditor
|
||||
code={
|
||||
isZh
|
||||
? `interface ExecuteHooks {
|
||||
? `interface ExecuteConfig {
|
||||
baseURL: string // LLM API 端点
|
||||
apiKey: string // API 密钥
|
||||
model: string // 模型名称
|
||||
|
||||
// 是否将初始标签页包含在任务中，默认 true
|
||||
includeInitialTab?: boolean
|
||||
|
||||
// Agent 状态变化时调用（idle, running, error, completed 等）
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
|
||||
@@ -236,7 +249,14 @@ window.dispose()`
|
||||
// Agent 被停止时调用
|
||||
onDispose?: () => void
|
||||
}`
|
||||
: `interface ExecuteHooks {
|
||||
: `interface ExecuteConfig {
|
||||
baseURL: string // LLM API endpoint
|
||||
apiKey: string // API key
|
||||
model: string // Model name
|
||||
|
||||
// Whether to include the initial tab in the task, default true
|
||||
includeInitialTab?: boolean
|
||||
|
||||
// Called when agent status changes (idle, running, error, completed, etc.)
|
||||
onStatusChange?: (status: AgentStatus) => void
|
||||
|
||||
|
||||
@@ -1,34 +1,49 @@
|
||||
import { Fragment } from 'react'
|
||||
|
||||
import CodeEditor from '@/components/CodeEditor'
|
||||
import { useLanguage } from '@/i18n/context'
|
||||
|
||||
// Recommended models: lightweight with excellent tool call capabilities
|
||||
const MODELS = {
|
||||
recommended: [
|
||||
'gpt-4.1-mini',
|
||||
'claude-haiku-4.5',
|
||||
'gemini-3-flash',
|
||||
'deepseek-3.2',
|
||||
'gpt-5.2',
|
||||
'qwen-3-max',
|
||||
],
|
||||
verified: [
|
||||
'qwen-3-plus',
|
||||
'gpt-4.1',
|
||||
'gpt-5',
|
||||
'gpt-5-mini',
|
||||
'grok-4',
|
||||
'grok-code-fast',
|
||||
'claude-sonnet-3.5',
|
||||
'claude-sonnet-4.5',
|
||||
const BASELINE = new Set([
|
||||
'gpt-5.1',
|
||||
'claude-haiku-4.5',
|
||||
'gemini-3-flash',
|
||||
'deepseek-3.2',
|
||||
'qwen3-coder-next',
|
||||
])
|
||||
|
||||
// Models grouped by brand, newest first
|
||||
const MODEL_GROUPS: Record<string, string[]> = {
|
||||
OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'],
|
||||
Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'],
|
||||
Qwen: ['qwen3-coder-next', 'qwen-3-max', 'qwen-3-plus', 'qwen3:14b (ollama)'],
|
||||
DeepSeek: ['deepseek-3.2'],
|
||||
Anthropic: [
|
||||
'claude-opus-4.6',
|
||||
'claude-opus-4.5',
|
||||
'gemini-2.5',
|
||||
'gemini-3-pro',
|
||||
'claude-sonnet-4.5',
|
||||
'claude-haiku-4.5',
|
||||
'claude-sonnet-3.5',
|
||||
],
|
||||
xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
|
||||
MoonshotAI: ['kimi-k2.5'],
|
||||
'Z.AI': ['glm-4.7'],
|
||||
}
|
||||
|
||||
const ModelBadge = ({ model, baseline }: { model: string; baseline?: boolean }) => (
|
||||
<div
|
||||
className={`px-3 py-1.5 rounded-md text-xs font-medium font-mono transition-colors ${
|
||||
baseline
|
||||
? 'bg-emerald-500 text-white shadow-sm'
|
||||
: 'bg-white/80 dark:bg-gray-800/80 text-gray-800 dark:text-gray-200 border border-gray-300 dark:border-gray-600'
|
||||
}`}
|
||||
>
|
||||
{model}
|
||||
{baseline && <span className="ml-1">⭐</span>}
|
||||
</div>
|
||||
)
|
||||
|
||||
export default function Models() {
|
||||
const { isZh } = useLanguage()
|
||||
const allModels = [...MODELS.recommended, ...MODELS.verified]
|
||||
|
||||
return (
|
||||
<div className="max-w-4xl">
|
||||
@@ -45,28 +60,23 @@ export default function Models() {
|
||||
<p className="text-sm text-gray-600 dark:text-gray-400 mb-4">
|
||||
{isZh
|
||||
? '推荐使用 ToolCall 能力强的轻量级模型。'
|
||||
: 'Recommended: Lightweight models with strong ToolCall capabilities.'}
|
||||
: 'Recommended: Fast, lightweight models with strong ToolCall capabilities.'}
|
||||
</p>
|
||||
<div className="bg-linear-to-br from-emerald-50 to-cyan-50 dark:from-emerald-950/30 dark:to-cyan-950/30 rounded-xl p-6 border border-emerald-200/50 dark:border-emerald-800/50">
|
||||
<div className="flex flex-wrap gap-2">
|
||||
{allModels.map((model) => {
|
||||
const isRecommended = MODELS.recommended.includes(model)
|
||||
return (
|
||||
<div
|
||||
key={model}
|
||||
className={`px-3 py-1.5 rounded-md text-sm font-medium font-mono transition-colors ${
|
||||
isRecommended
|
||||
? 'bg-emerald-500 text-white shadow-sm'
|
||||
: 'bg-white/80 dark:bg-gray-800/80 text-gray-800 dark:text-gray-200 border border-gray-300 dark:border-gray-600'
|
||||
}`}
|
||||
>
|
||||
{model}
|
||||
{isRecommended && <span className="ml-1">⭐</span>}
|
||||
<div className="grid grid-cols-[5rem_1fr] gap-x-3 gap-y-3 items-start">
|
||||
{Object.entries(MODEL_GROUPS).map(([brand, models]) => (
|
||||
<Fragment key={brand}>
|
||||
<span className="text-xs font-semibold text-gray-500 dark:text-gray-400 pt-2">
|
||||
{brand}
|
||||
</span>
|
||||
<div className="flex flex-wrap gap-2">
|
||||
{models.map((model) => (
|
||||
<ModelBadge key={model} model={model} baseline={BASELINE.has(model)} />
|
||||
))}
|
||||
</div>
|
||||
)
|
||||
})}
|
||||
</Fragment>
|
||||
))}
|
||||
</div>
|
||||
<p className="text-xs text-gray-600 dark:text-gray-400 mt-5">⭐ baseline models</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
+1
-1
@@ -8,7 +8,7 @@
|
||||
"skipLibCheck": true,
|
||||
"allowJs": true,
|
||||
|
||||
// "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
|
||||
"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
|
||||
// "baseUrl": "src",
|
||||
"baseUrl": ".",
|
||||
"outDir": "dist",
|
||||
|
||||
Reference in New Issue
Block a user