Compare commits

...

17 Commits

Author SHA1 Message Date
Simon c0ce6e7d14 chore(version): bump version to 0.2.0 2026-01-15 20:47:39 +08:00
Simon 8f5f98f889 feat(agent)!: rename brain to reflection; fix undefined lines in panel 2026-01-15 20:45:40 +08:00
Simon ee4719cdcf feat: observation 2026-01-15 20:28:39 +08:00
Simon b4c82b7833 refactor: mv getBrowserState to Controller; simplify Agent 2026-01-15 20:17:50 +08:00
Simon aefc3cfb89 Merge pull request #111 from alibaba/feat/extend-agent-history-for-observation
feat: extend history type
2026-01-15 19:57:41 +08:00
Simon 7f2b8c2766 feat: extend history type 2026-01-15 19:18:25 +08:00
Simon 62e24a3050 chore(version): bump version to 0.1.0 2026-01-14 18:50:06 +08:00
Simon 4f6249a252 feat!: require user to provide LLM api. do not fallback to demo LLM
BREAKING CHANGE: LLM API will be required for agent constructor
2026-01-14 18:49:23 +08:00
Simon 62519416bb chore(version): bump version to 0.0.24 2026-01-14 18:34:55 +08:00
Simon a1e70e663d feat(PageController): exclude aria-hidden elements 2026-01-14 18:04:31 +08:00
Simon 338e317be1 chore(website): fix homepage overflow 2026-01-14 17:45:49 +08:00
Simon 9a66d5205f feat(website): display version in header and load from page-agent package 2026-01-14 17:42:18 +08:00
Simon 7d45bf6598 feat(website): update CDN links and usage 2026-01-14 17:27:35 +08:00
Simon 78ee72eea4 chore(version): bump version to 0.0.23 2026-01-14 15:46:10 +08:00
Simon 3b71c535b1 fix: clean up debug code 2026-01-14 15:23:02 +08:00
Simon 6615f7b300 Merge pull request #110 from alibaba/fix/panel-text-uncompleted
feat: add HTML escaping to Panel
2026-01-14 15:17:43 +08:00
Simon 38caae5e23 feat: add HTML escaping to Panel 2026-01-14 15:15:51 +08:00
30 changed files with 544 additions and 345 deletions
+35 -23
View File
@@ -28,7 +28,22 @@
## 🚀 快速开始
### NPM 安装
### 快速体验 (Demo CDN)
最快的体验方式:
```html
<script src="https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.demo.js" crossorigin="true"></script>
```
> ⚠️ **仅用于技术评估。** Demo 模型有速率限制和使用限制,生产环境请使用 NPM 方式。
| 位置 | URL |
| ------ | --------------------------------------------------------------------------------------- |
| 全球 | https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.demo.js |
| 中国 | https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.demo.js |
### NPM 安装(推荐)
```bash
npm install page-agent
@@ -37,40 +52,37 @@ npm install page-agent
```javascript
import { PageAgent } from 'page-agent'
// 测试接口
// @note: 限流,限制 prompt 内容,限制来源,随时变更,请替换成你自己的
// @note: 使用 DeepSeek-chat(3.2) 官方版本,使用协议和隐私策略见 DeepSeek 网站
const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
const DEMO_BASE_URL = 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
const agent = new PageAgent({
model: DEMO_MODEL,
baseURL: DEMO_BASE_URL,
apiKey: DEMO_API_KEY,
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
language: 'zh-CN',
})
await agent.execute('点击登录按钮')
```
### CDN 集成
### CDN 引入
Fastest way to try PageAgent is to include it via CDN. Demo model will be used by default.
| Location | URL |
| -------- | ----------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js |
| China | https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js |
适用于无法使用 NPM 的环境,用法与 NPM 一致:
```html
<script
src="https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js"
crossorigin="true"
type="text/javascript"
></script>
<script src="https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.js" crossorigin="true"></script>
<script>
const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
})
await agent.execute('点击登录按钮')
</script>
```
| 位置 | URL |
| ------ | ----------------------------------------------------------------------------------- |
| 全球 | https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.js |
| 中国 | https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.js |
## 🏗️ 架构设计
PageAgent adopts a simplified monorepo structure:
+35 -23
View File
@@ -28,7 +28,22 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua
## 🚀 Quick Start
### NPM Installation
### Quick Try (Demo CDN)
Fastest way to try PageAgent:
```html
<script src="https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.demo.js" crossorigin="true"></script>
```
> ⚠️ **For technical evaluation only.** Demo model has rate limits and usage restrictions. Use NPM for production.
| Location | URL |
| -------- | --------------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.demo.js |
| China | https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.demo.js |
### NPM Installation (Recommended)
```bash
npm install page-agent
@@ -37,40 +52,37 @@ npm install page-agent
```javascript
import { PageAgent } from 'page-agent'
// test server
// @note: rate limit. prompt limit. Origin limit. May change anytime. Use your own llm!
// @note Using official DeepSeek-chat(3.2). Go to DeepSeek website for privacy policy.
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 agent = new PageAgent({
model: DEMO_MODEL,
baseURL: DEMO_BASE_URL,
apiKey: DEMO_API_KEY,
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
language: 'en-US',
})
await agent.execute('Click the login button')
```
### CDN Integration
### CDN Build
Fastest way to try PageAgent is to include it via CDN. Demo model will be used by default.
| Location | URL |
| -------- | ----------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js |
| China | https://registry.npmmirror.com/page-agent/latest/files/dist/umd/page-agent.js |
For environments where NPM is not available. Usage is identical to NPM:
```html
<script
src="https://cdn.jsdelivr.net/npm/page-agent@latest/dist/umd/page-agent.js"
crossorigin="true"
type="text/javascript"
></script>
<script src="https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.js" crossorigin="true"></script>
<script>
const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
})
await agent.execute('Click the login button')
</script>
```
| Location | URL |
| -------- | ----------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.js |
| China | https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.js |
## 🏗️ Structure
PageAgent adopts a simplified monorepo structure:
+12 -12
View File
@@ -1,12 +1,12 @@
{
"name": "root",
"version": "0.0.22",
"version": "0.2.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "root",
"version": "0.0.22",
"version": "0.2.0",
"license": "MIT",
"workspaces": [
"packages/page-controller",
@@ -8147,15 +8147,15 @@
},
"packages/cdn": {
"name": "@page-agent/cdn",
"version": "0.0.22",
"version": "0.2.0",
"license": "MIT",
"dependencies": {
"page-agent": "0.0.22"
"page-agent": "0.2.0"
}
},
"packages/llms": {
"name": "@page-agent/llms",
"version": "0.0.22",
"version": "0.2.0",
"license": "MIT",
"dependencies": {
"chalk": "^5.6.2",
@@ -8163,19 +8163,19 @@
}
},
"packages/page-agent": {
"version": "0.0.22",
"version": "0.2.0",
"license": "MIT",
"dependencies": {
"@page-agent/llms": "0.0.22",
"@page-agent/page-controller": "0.0.22",
"@page-agent/ui": "0.0.22",
"@page-agent/llms": "0.2.0",
"@page-agent/page-controller": "0.2.0",
"@page-agent/ui": "0.2.0",
"chalk": "^5.6.2",
"zod": "^4.3.5"
}
},
"packages/page-controller": {
"name": "@page-agent/page-controller",
"version": "0.0.22",
"version": "0.2.0",
"license": "MIT",
"dependencies": {
"ai-motion": "^0.4.8"
@@ -8183,12 +8183,12 @@
},
"packages/ui": {
"name": "@page-agent/ui",
"version": "0.0.22",
"version": "0.2.0",
"license": "MIT"
},
"packages/website": {
"name": "@page-agent/website",
"version": "0.0.22",
"version": "0.2.0",
"dependencies": {
"@radix-ui/react-icons": "^1.3.2",
"@radix-ui/react-separator": "^1.1.8",
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "root",
"private": true,
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"workspaces": [
"packages/page-controller",
+2 -2
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/cdn",
"private": false,
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"files": [
"dist/"
@@ -18,6 +18,6 @@
"build": "vite build && vite build --mode demo"
},
"dependencies": {
"page-agent": "0.0.22"
"page-agent": "0.2.0"
}
}
+6 -1
View File
@@ -50,7 +50,12 @@ setTimeout(() => {
window.pageAgent = new PageAgent(config)
} else {
console.log('🚀 page-agent.js no current script detected, using default demo config')
window.pageAgent = new PageAgent()
const config = {
model: DEMO_MODEL,
baseURL: DEMO_BASE_URL,
apiKey: DEMO_API_KEY,
}
window.pageAgent = new PageAgent(config)
}
console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/llms",
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"main": "./dist/lib/page-agent-llms.js",
"module": "./dist/lib/page-agent-llms.js",
+1 -18
View File
@@ -1,20 +1,3 @@
// 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
// Internal constants
export const LLM_MAX_RETRIES = 2
export const DEFAULT_TEMPERATURE = 0.7 // higher randomness helps auto-recovery
+12 -10
View File
@@ -1,21 +1,23 @@
import { OpenAIClient } from './OpenAIClient'
import {
DEFAULT_API_KEY,
DEFAULT_BASE_URL,
DEFAULT_MODEL_NAME,
DEFAULT_TEMPERATURE,
LLM_MAX_RETRIES,
} from './constants'
import { DEFAULT_TEMPERATURE, LLM_MAX_RETRIES } from './constants'
import { InvokeError } from './errors'
import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
export type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool }
export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
// Runtime validation as defensive programming (types already guarantee these)
if (!config.baseURL || !config.apiKey || !config.model) {
throw new Error(
'[PageAgent] LLM configuration required. Please provide: baseURL, apiKey, model. ' +
'See: https://alibaba.github.io/page-agent/#/docs/features/models'
)
}
return {
baseURL: config.baseURL ?? DEFAULT_BASE_URL,
apiKey: config.apiKey ?? DEFAULT_API_KEY,
model: config.model ?? DEFAULT_MODEL_NAME,
baseURL: config.baseURL,
apiKey: config.apiKey,
model: config.model,
temperature: config.temperature ?? DEFAULT_TEMPERATURE,
maxRetries: config.maxRetries ?? LLM_MAX_RETRIES,
customFetch: (config.customFetch ?? fetch).bind(globalThis), // fetch will be illegal unless bound
+3 -3
View File
@@ -87,9 +87,9 @@ export interface InvokeResult<TResult = unknown> {
* LLM configuration
*/
export interface LLMConfig {
baseURL?: string
apiKey?: string
model?: string
baseURL: string
apiKey: string
model: string
temperature?: number
maxRetries?: number
+4 -4
View File
@@ -1,7 +1,7 @@
{
"name": "page-agent",
"private": false,
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"main": "./dist/esm/page-agent.js",
"module": "./dist/esm/page-agent.js",
@@ -46,8 +46,8 @@
"dependencies": {
"chalk": "^5.6.2",
"zod": "^4.3.5",
"@page-agent/llms": "0.0.22",
"@page-agent/page-controller": "0.0.22",
"@page-agent/ui": "0.0.22"
"@page-agent/llms": "0.2.0",
"@page-agent/page-controller": "0.2.0",
"@page-agent/ui": "0.2.0"
}
}
+141 -79
View File
@@ -16,7 +16,7 @@ import { normalizeResponse, trimLines, uid, waitUntil } from './utils'
import { assert } from './utils/assert'
/**
* Agent brain state - the reflection-before-action model
* Agent reflection 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?
@@ -50,8 +50,12 @@ export interface MacroToolResult {
export type { PageAgentConfig }
export { tool, type PageAgentTool } from './tools'
export interface AgentHistory {
brain: Partial<AgentReflection>
/**
* A single agent step with reflection and action
*/
export interface AgentStep {
type: 'step'
reflection: Partial<AgentReflection>
action: {
name: string
input: any
@@ -66,10 +70,33 @@ export interface AgentHistory {
}
}
/**
* Persistent observation event (stays in memory)
*/
export interface ObservationEvent {
type: 'observation'
content: string
}
/**
* User takeover event
*/
export interface UserTakeoverEvent {
type: 'user_takeover'
}
/**
* Union type for all history events
*/
export type HistoryEvent = AgentStep | ObservationEvent | UserTakeoverEvent
/** @deprecated Use AgentStep instead */
export type AgentHistory = AgentStep
export interface ExecutionResult {
success: boolean
data: string
history: AgentHistory[]
history: HistoryEvent[]
}
export class PageAgent extends EventTarget {
@@ -83,7 +110,6 @@ export class PageAgent extends EventTarget {
taskId = ''
#llm: LLM
#totalWaitTime = 0
#abortController = new AbortController()
#llmRetryListener: ((e: Event) => void) | null = null
#llmErrorListener: ((e: Event) => void) | null = null
@@ -92,10 +118,18 @@ export class PageAgent extends EventTarget {
/** PageController for DOM operations */
pageController: PageController
/** History records */
history: AgentHistory[] = []
/** Runtime states for tracking across steps */
states = {
/** Accumulated wait time in seconds, used by wait tool */
totalWaitTime: 0,
/** Last known URL for detecting navigation */
lastURL: '',
}
constructor(config: PageAgentConfig = {}) {
/** History event stream */
history: HistoryEvent[] = []
constructor(config: PageAgentConfig) {
super()
this.config = config
@@ -150,6 +184,14 @@ export class PageAgent extends EventTarget {
window.addEventListener('beforeunload', this.#beforeUnloadListener)
}
/**
* Push a persistent observation to the history event stream.
* This will be visible in <agent_history> and remain in memory across steps.
*/
pushObservation(content: string): void {
this.history.push({ type: 'observation', content })
}
async execute(task: string): Promise<ExecutionResult> {
if (!task) throw new Error('Task is required')
this.task = task
@@ -177,10 +219,18 @@ export class PageAgent extends EventTarget {
this.history = []
// Reset states
this.states = {
totalWaitTime: 0,
lastURL: '',
}
try {
let step = 0
while (true) {
await this.#generateObservations(step)
await onBeforeStep.call(this, step)
console.group(`step: ${step}`)
@@ -216,23 +266,24 @@ export class PageAgent extends EventTarget {
const macroResult = result.toolResult as MacroToolResult
const input = macroResult.input
const output = macroResult.output
const brain = {
evaluation_previous_goal: input.evaluation_previous_goal || '',
memory: input.memory || '',
next_goal: input.next_goal || '',
const reflection: Partial<AgentReflection> = {
evaluation_previous_goal: input.evaluation_previous_goal,
memory: input.memory,
next_goal: input.next_goal,
}
const actionName = Object.keys(input.action)[0]
const action = {
const action: AgentStep['action'] = {
name: actionName,
input: input.action[actionName],
output: output,
}
this.history.push({
brain,
type: 'step',
reflection,
action,
usage: result.usage,
})
} as AgentStep)
console.log(chalk.green('Step finished:'), actionName)
console.groupEnd()
@@ -319,13 +370,20 @@ export class PageAgent extends EventTarget {
const toolName = Object.keys(action)[0]
const toolInput = action[toolName]
const brain = trimLines(`✅: ${input.evaluation_previous_goal}
💾: ${input.memory}
🎯: ${input.next_goal}
`)
console.log(brain)
this.panel.update({ type: 'thinking', text: brain })
// Build reflection text, only include non-empty fields
const reflectionLines: string[] = []
if (input.evaluation_previous_goal)
reflectionLines.push(`✅: ${input.evaluation_previous_goal}`)
if (input.memory) reflectionLines.push(`💾: ${input.memory}`)
if (input.next_goal) reflectionLines.push(`🎯: ${input.next_goal}`)
const reflectionText = reflectionLines.length > 0 ? reflectionLines.join('\n') : ''
if (reflectionText) {
console.log(reflectionText)
this.panel.update({ type: 'thinking', text: reflectionText })
}
// Find the corresponding tool
const tool = tools.get(toolName)
@@ -337,20 +395,14 @@ export class PageAgent extends EventTarget {
const startTime = Date.now()
// Execute tool, bind `this` to PageAgent
let result = await tool.execute.bind(this)(toolInput)
const result = await tool.execute.bind(this)(toolInput)
const duration = Date.now() - startTime
console.log(chalk.green.bold(`Tool (${toolName}) executed for ${duration}ms`), result)
if (toolName === 'wait') {
this.#totalWaitTime += Math.round(toolInput.seconds + duration / 1000)
result += `\n<sys> You have waited ${this.#totalWaitTime} seconds accumulatively.`
if (this.#totalWaitTime >= 3)
result += '\nDo NOT wait any longer unless you have a good reason.\n'
result += '</sys>'
} else {
// For other tools, reset wait time
this.#totalWaitTime = 0
// Reset wait time for non-wait tools
if (toolName !== 'wait') {
this.states.totalWaitTime = 0
}
// Briefly display execution result
@@ -427,6 +479,34 @@ export class PageAgent extends EventTarget {
return result
}
/**
* Generate observations before each step
* - URL change detection
* - Too many steps warning
* @todo loop detection
* @todo console error
*/
async #generateObservations(stepCount: number): Promise<void> {
// Detect URL change
const currentURL = await this.pageController.getCurrentUrl()
if (currentURL !== this.states.lastURL) {
this.pushObservation(`Page navigated to → ${currentURL}`)
this.states.lastURL = currentURL
}
// Warn about remaining steps
const remaining = MAX_STEPS - stepCount
if (remaining === 5) {
this.pushObservation(
`⚠️ Only ${remaining} steps remaining. Consider wrapping up or calling done with partial results.`
)
} else if (remaining === 2) {
this.pushObservation(
`⚠️ Critical: Only ${remaining} steps left! You must finish the task or call done immediately.`
)
}
}
async #assembleUserPrompt(): Promise<string> {
let prompt = ''
@@ -438,31 +518,42 @@ export class PageAgent extends EventTarget {
// - <step_info>
// <agent_state>
const stepCount = this.history.filter((e) => e.type === 'step').length
prompt += `<agent_state>
<user_request>
${this.task}
</user_request>
<step_info>
Step ${this.history.length + 1} of ${MAX_STEPS} max possible steps
Step ${stepCount + 1} of ${MAX_STEPS} max possible steps
Current date and time: ${new Date().toISOString()}
</step_info>
</agent_state>
`
// <agent_history>
// - <step_>
// - <step_N> for steps
// - <sys> for observations and system messages
prompt += '\n<agent_history>\n'
this.history.forEach((history, index) => {
prompt += `<step_${index + 1}>
Evaluation of Previous Step: ${history.brain.evaluation_previous_goal}
Memory: ${history.brain.memory}
Next Goal: ${history.brain.next_goal}
Action Results: ${history.action.output}
</step_${index + 1}>
let stepIndex = 0
for (const event of this.history) {
if (event.type === 'step') {
stepIndex++
prompt += `<step_${stepIndex}>
Evaluation of Previous Step: ${event.reflection.evaluation_previous_goal}
Memory: ${event.reflection.memory}
Next Goal: ${event.reflection.next_goal}
Action Results: ${event.action.output}
</step_${stepIndex}>
`
})
} else if (event.type === 'observation') {
prompt += `<sys>${event.content}</sys>\n`
} else if (event.type === 'user_takeover') {
prompt += `<sys>User took over control and made changes to the page.</sys>\n`
}
}
prompt += '</agent_history>\n\n'
@@ -492,51 +583,22 @@ export class PageAgent extends EventTarget {
}
async #getBrowserState(): Promise<string> {
const pageUrl = await this.pageController.getCurrentUrl()
const pageTitle = await this.pageController.getPageTitle()
const pi = await this.pageController.getPageInfo()
const viewportExpansion = await this.pageController.getViewportExpansion()
await this.pageController.updateTree()
let simplifiedHTML = await this.pageController.getSimplifiedHTML()
const state = await this.pageController.getBrowserState()
let content = state.content
if (this.config.transformPageContent) {
simplifiedHTML = await this.config.transformPageContent(simplifiedHTML)
content = await this.config.transformPageContent(content)
}
let prompt = trimLines(`<browser_state>
Current Page: [${pageTitle}](${pageUrl})
return trimLines(`<browser_state>
Current Page: [${state.title}](${state.url})
Page info: ${pi.viewport_width}x${pi.viewport_height}px viewport, ${pi.page_width}x${pi.page_height}px total page size, ${pi.pages_above.toFixed(1)} pages above, ${pi.pages_below.toFixed(1)} pages below, ${pi.total_pages.toFixed(1)} total pages, at ${(pi.current_page_position * 100).toFixed(0)}% of page
${viewportExpansion === -1 ? 'Interactive elements from top layer of the current page (full page):' : 'Interactive elements from top layer of the current page inside the viewport:'}
${state.header}
${content}
${state.footer}
</browser_state>
`)
// Page header info
const has_content_above = pi.pixels_above > 4
if (has_content_above && viewportExpansion !== -1) {
prompt += `... ${pi.pixels_above} pixels above (${pi.pages_above.toFixed(1)} pages) - scroll to see more ...\n`
} else {
prompt += `[Start of page]\n`
}
// Current viewport info
prompt += simplifiedHTML
prompt += `\n`
// Page footer info
const has_content_below = pi.pixels_below > 4
if (has_content_below && viewportExpansion !== -1) {
prompt += `... ${pi.pixels_below} pixels below (${pi.pages_below.toFixed(1)} pages) - scroll to see more ...\n`
} else {
prompt += `[End of page]\n`
}
prompt += `</browser_state>\n`
return prompt
}
dispose(reason?: string) {
+2 -2
View File
@@ -2,7 +2,7 @@ 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 { ExecutionResult, HistoryEvent, PageAgent } from '../PageAgent'
import type { PageAgentTool } from '../tools'
export type { LLMConfig }
@@ -65,7 +65,7 @@ export interface AgentConfig {
// @todo: remove `this` binding, pass agent as explicit parameter instead
onBeforeStep?: (this: PageAgent, stepCnt: number) => Promise<void> | void
onAfterStep?: (this: PageAgent, stepCnt: number, history: AgentHistory[]) => Promise<void> | void
onAfterStep?: (this: PageAgent, stepCnt: number, history: HistoryEvent[]) => Promise<void> | void
onBeforeTask?: (this: PageAgent) => Promise<void> | void
onAfterTask?: (this: PageAgent, result: ExecutionResult) => Promise<void> | void
+9
View File
@@ -57,6 +57,15 @@ tools.set(
const actualWaitTime = Math.max(0, input.seconds - (Date.now() - lastTimeUpdate) / 1000)
console.log(`actualWaitTime: ${actualWaitTime} seconds`)
await waitFor(actualWaitTime)
this.states.totalWaitTime += input.seconds
if (this.states.totalWaitTime >= 3) {
this.pushObservation(
`You have waited ${this.states.totalWaitTime} seconds accumulatively. Do NOT wait any longer unless you have a good reason.`
)
}
return `✅ Waited for ${input.seconds} seconds.`
},
})
+6 -1
View File
@@ -35,7 +35,12 @@ setTimeout(() => {
window.pageAgent = new PageAgent(config)
} else {
console.log('🚀 page-agent.js no current script detected, using default demo config')
window.pageAgent = new PageAgent()
const config: PageAgentConfig = {
model: DEMO_MODEL,
baseURL: DEMO_BASE_URL,
apiKey: DEMO_API_KEY,
}
window.pageAgent = new PageAgent(config)
}
console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/page-controller",
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"main": "./dist/lib/page-controller.js",
"module": "./dist/lib/page-controller.js",
+50 -39
View File
@@ -32,6 +32,20 @@ export interface PageControllerConfig extends dom.DomConfig {
enableMask?: boolean
}
/**
* Structured browser state for LLM consumption
*/
export interface BrowserState {
url: string
title: string
/** Page info + scroll position hint (e.g. "Page info: 1920x1080px...\n[Start of page]") */
header: string
/** Simplified HTML of interactive elements */
content: string
/** Page footer hint (e.g. "... 300 pixels below ..." or "[End of page]") */
footer: string
}
interface ActionResult {
success: boolean
message: string
@@ -93,42 +107,6 @@ export class PageController extends EventTarget {
return window.location.href
}
/**
* Get current page title
*/
async getPageTitle(): Promise<string> {
return document.title
}
/**
* Get page scroll and size info
*/
async getPageInfo() {
return getPageInfo()
}
/**
* Get the simplified HTML representation of the page.
* This is used by LLM to understand the page structure.
*/
async getSimplifiedHTML(): Promise<string> {
return this.simplifiedHTML
}
/**
* Get text description for an element by index
*/
async getElementText(index: number): Promise<string | undefined> {
return this.elementTextMap.get(index)
}
/**
* Get total number of indexed interactive elements
*/
async getElementCount(): Promise<number> {
return this.selectorMap.size
}
/**
* Get last tree update timestamp
*/
@@ -137,10 +115,43 @@ export class PageController extends EventTarget {
}
/**
* Get the viewport expansion setting
* Get structured browser state for LLM consumption.
* Automatically calls updateTree() to refresh the DOM state.
*/
async getViewportExpansion(): Promise<number> {
return this.config.viewportExpansion ?? VIEWPORT_EXPANSION
async getBrowserState(): Promise<BrowserState> {
const url = window.location.href
const title = document.title
const pi = getPageInfo()
const viewportExpansion = this.config.viewportExpansion ?? VIEWPORT_EXPANSION
await this.updateTree()
const content = this.simplifiedHTML
// Build header: page info + scroll position hint
const pageInfoLine = `Page info: ${pi.viewport_width}x${pi.viewport_height}px viewport, ${pi.page_width}x${pi.page_height}px total page size, ${pi.pages_above.toFixed(1)} pages above, ${pi.pages_below.toFixed(1)} pages below, ${pi.total_pages.toFixed(1)} total pages, at ${(pi.current_page_position * 100).toFixed(0)}% of page`
const elementsLabel =
viewportExpansion === -1
? 'Interactive elements from top layer of the current page (full page):'
: 'Interactive elements from top layer of the current page inside the viewport:'
const hasContentAbove = pi.pixels_above > 4
const scrollHintAbove =
hasContentAbove && viewportExpansion !== -1
? `... ${pi.pixels_above} pixels above (${pi.pages_above.toFixed(1)} pages) - scroll to see more ...`
: '[Start of page]'
const header = `${pageInfoLine}\n\n${elementsLabel}\n\n${scrollHintAbove}`
// Build footer: scroll position hint
const hasContentBelow = pi.pixels_below > 4
const footer =
hasContentBelow && viewportExpansion !== -1
? `... ${pi.pixels_below} pixels below (${pi.pages_below.toFixed(1)} pages) - scroll to see more ...`
: '[End of page]'
return { url, title, header, content, footer }
}
// ======= DOM Tree Operations =======
@@ -16,6 +16,7 @@
* @edit scrollable element detection
* @edit add `data-browser-use-ignore` attribute
* @edit improve `sampleRect`, filter out rects with 0 area
* @edit exclude aria-hidden elements
*/
export default (
@@ -1446,7 +1447,14 @@ export default (
* @edit add `data-browser-use-ignore` attribute
*/
if (node.dataset?.browserUseIgnore === 'true') {
return true // Skip this node and its children
return null // Skip this node and its children
}
/**
* @edit exclude aria-hidden elements
*/
if (node.getAttribute && node.getAttribute('aria-hidden') === 'true') {
return null // Skip this node and its children
}
// Special handling for root node (body)
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/ui",
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"main": "./dist/lib/page-agent-ui.js",
"module": "./dist/lib/page-agent-ui.js",
+2 -5
View File
@@ -1,6 +1,6 @@
import { type Step, UIState } from './UIState'
import { I18n, type SupportedLanguage } from './i18n'
import { truncate } from './utils'
import { escapeHtml, truncate } from './utils'
import styles from './Panel.module.css'
@@ -590,10 +590,7 @@ export class Panel {
#updateHistory(): void {
const steps = this.#state.getAllSteps()
this.#historySection.innerHTML = steps.map((step) => this.#createHistoryItem(step)).join('')
// Scroll to bottom to show latest records
this.#scrollToBottom()
}
@@ -660,7 +657,7 @@ export class Panel {
<div class="${styles.historyItem} ${typeClass}">
<div class="${styles.historyContent}">
<span class="${styles.statusIcon}">${statusIcon}</span>
<span>${step.displayText}</span>
<span>${escapeHtml(step.displayText)}</span>
</div>
<div class="${styles.historyMeta}">
${stepLabel}
+12
View File
@@ -4,3 +4,15 @@ export function truncate(text: string, maxLength: number): string {
}
return text
}
/**
* Escape HTML special characters to prevent XSS and rendering issues
*/
export function escapeHtml(text: string): string {
return text
.replace(/&/g, '&amp;')
.replace(/</g, '&lt;')
.replace(/>/g, '&gt;')
.replace(/"/g, '&quot;')
.replace(/'/g, '&#039;')
}
+2 -2
View File
@@ -1,10 +1,10 @@
{
"name": "@page-agent/website",
"private": true,
"version": "0.0.22",
"version": "0.2.0",
"type": "module",
"scripts": {
"dev": "vite",
"dev": "vite --host 0.0.0.0",
"build:website": "vite build",
"preview": "vite preview",
"typecheck": "tsc --noEmit"
@@ -41,6 +41,7 @@ export default function Header() {
className="hidden sm:block text-xs text-gray-600 dark:text-gray-300 py-0 font-normal overflow-visible"
duration={600}
animateOnHover={true}
aria-hidden="true"
>
{t('header.slogan')}
</HyperText>
@@ -84,6 +85,9 @@ export default function Header() {
role="navigation"
aria-label={t('header.nav_docs')}
>
<span className="text-xs font-mono text-gray-400 dark:text-gray-500 tabular-nums before:content-['v']">
{import.meta.env.VERSION}
</span>
<Link
href="/docs/introduction/overview"
className="flex items-center gap-1.5 text-gray-600 dark:text-gray-300 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
+15 -3
View File
@@ -1,3 +1,15 @@
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'
// Demo build (auto-init with demo LLM, for quick testing)
export const CDN_DEMO_URL = 'https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.demo.js'
export const CDN_DEMO_CN_URL =
'https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.demo.js'
// Full build (exports PageAgent class, usage identical to npm)
export const CDN_FULL_URL = 'https://cdn.jsdelivr.net/npm/@page-agent/cdn/dist/page-agent.js'
export const CDN_FULL_CN_URL =
'https://registry.npmmirror.com/@page-agent/cdn/latest/files/dist/page-agent.js'
// Demo LLM for website testing
export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
export const DEMO_BASE_URL =
'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
export const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
+4
View File
@@ -1,5 +1,9 @@
/// <reference types="vite/client" />
interface ImportMetaEnv {
readonly VERSION: string
}
declare module '*.module.css' {
const classes: Record<string, string>
export default classes
+24 -10
View File
@@ -12,10 +12,16 @@ import { Highlighter } from '../components/ui/highlighter'
import { NeonGradientCard } from '../components/ui/neon-gradient-card'
import { Particles } from '../components/ui/particles'
import { SparklesText } from '../components/ui/sparkles-text'
import { CDN_CN_URL, CDN_URL } from '../constants'
import {
CDN_DEMO_CN_URL,
CDN_DEMO_URL,
DEMO_API_KEY,
DEMO_BASE_URL,
DEMO_MODEL,
} from '../constants'
function getInjection(useCN?: boolean) {
const cdn = useCN ? CDN_CN_URL : CDN_URL
const cdn = useCN ? CDN_DEMO_CN_URL : CDN_DEMO_URL
const injection = encodeURI(
`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);})();`
@@ -73,13 +79,18 @@ export default function HomePage() {
},
},
// experimentalScriptExecutionTool: true,
// testing server
// @note: rate limit. prompt limit.
// model: DEMO_MODEL,
// baseURL: DEMO_BASE_URL,
// apiKey: DEMO_API_KEY,
model:
import.meta.env.DEV && import.meta.env.LLM_MODEL_NAME
? import.meta.env.LLM_MODEL_NAME
: DEMO_MODEL,
baseURL:
import.meta.env.DEV && import.meta.env.LLM_BASE_URL
? import.meta.env.LLM_BASE_URL
: DEMO_BASE_URL,
apiKey:
import.meta.env.DEV && import.meta.env.LLM_API_KEY
? import.meta.env.LLM_API_KEY
: DEMO_API_KEY,
})
win.pageAgent = pageAgent
}
@@ -95,7 +106,10 @@ export default function HomePage() {
{/* Hero Section */}
<main id="main-content">
<section className="relative px-6 py-22 lg:py-28" aria-labelledby="hero-heading">
<section
className="relative px-6 py-22 lg:py-28 overflow-hidden"
aria-labelledby="hero-heading"
>
<div className="max-w-7xl mx-auto text-center">
{/* Background Pattern + Particles */}
<div className="absolute inset-0 opacity-30" aria-hidden="true">
+1 -1
View File
@@ -43,7 +43,7 @@ export default function DocsLayout({ children }: DocsLayoutProps) {
items: [
{ title: t('nav.configuration'), path: '/docs/integration/configuration' },
{ title: t('nav.third_party_agent'), path: '/docs/integration/third-party-agent' },
{ title: '🚧 ' + t('nav.cdn_setup'), path: '/docs/integration/cdn-setup' },
{ title: t('nav.cdn_setup'), path: '/docs/integration/cdn-setup' },
{
title: '🚧 ' + t('nav.security_permissions'),
path: '/docs/integration/security-permissions',
@@ -1,81 +1,124 @@
import { useTranslation } from 'react-i18next'
import BetaNotice from '@/components/BetaNotice'
import CodeEditor from '@/components/CodeEditor'
import { CDN_CN_URL, CDN_URL } from '@/constants'
import { CDN_DEMO_CN_URL, CDN_DEMO_URL, CDN_FULL_CN_URL, CDN_FULL_URL } from '@/constants'
export default function CdnSetup() {
const { i18n } = useTranslation()
const isZh = i18n.language === 'zh-CN'
return (
<div>
<BetaNotice />
<div className="space-y-10">
<header>
<h1 className="text-4xl font-bold mb-4">{isZh ? 'CDN 引入' : 'CDN Setup'}</h1>
<p className="text-lg text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? 'CDN 提供两种构建版本:Demo 版用于快速体验,标准版用法与 NPM 一致。'
: 'CDN provides two builds: Demo for quick testing, standard build with usage identical to NPM.'}
</p>
</header>
<h1 className="text-4xl font-bold mb-6">{isZh ? 'CDN 引入' : 'CDN Setup'}</h1>
{/* Demo Build Section */}
<section>
<h2 className="text-2xl font-bold mb-3">{isZh ? '🚀 快速体验' : '🚀 Quick Try'}</h2>
<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
{isZh
? '通过 CDN 快速集成 page-agent,无需复杂的构建配置。默认使用演示模型。'
: 'Fastest way to integrate page-agent via CDN. No complex build setup needed. Demo model will be used by default.'}
</p>
<section className="mb-8">
<h2 className="text-2xl font-bold mb-4">{isZh ? 'CDN 地址' : 'CDN URLs'}</h2>
<div className="overflow-x-auto mb-6">
<table className="w-full border-collapse text-sm">
<thead>
<tr className="border-b border-gray-200 dark:border-gray-700">
<th className="text-left py-3 px-4 font-semibold">{isZh ? '位置' : 'Location'}</th>
<th className="text-left py-3 px-4 font-semibold">URL</th>
</tr>
</thead>
<tbody>
<tr className="border-b border-gray-100 dark:border-gray-800">
<td className="py-3 px-4">{isZh ? '全球' : 'Global'}</td>
<td className="py-3 px-4 font-mono text-xs break-all">{CDN_URL}</td>
</tr>
<tr className="border-b border-gray-100 dark:border-gray-800">
<td className="py-3 px-4">{isZh ? '中国镜像' : 'China Mirror'}</td>
<td className="py-3 px-4 font-mono text-xs break-all">{CDN_CN_URL}</td>
</tr>
</tbody>
</table>
</div>
</section>
<section className="mb-8">
<h2 className="text-2xl font-bold mb-4">{isZh ? '快速开始' : 'Quick Start'}</h2>
<p className="text-gray-600 dark:text-gray-300 mb-3">
{isZh
? '自动初始化并使用内置 Demo LLM,无需任何配置:'
: 'Auto-initializes with built-in demo LLM, no configuration needed:'}
</p>
<CodeEditor
className="mb-6"
code={`<script
src="${CDN_URL}"
crossorigin="true"
type="text/javascript"
></script>`}
className="mb-3"
code={`<script src="${CDN_DEMO_URL}" crossorigin="true"></script>`}
/>
<div className="bg-yellow-50 dark:bg-yellow-900/20 px-4 py-3 rounded-lg mb-4 text-sm">
<span className="text-yellow-800 dark:text-yellow-200">
{' '}
{isZh
? '仅用于技术评估,Demo 模型有速率限制。'
: 'For evaluation only. Demo model has rate limits.'}
</span>
</div>
<table className="w-full border-collapse text-sm">
<thead>
<tr className="border-b border-gray-200 dark:border-gray-700">
<th className="text-left py-2 px-3 font-semibold w-28">
{isZh ? '位置' : 'Location'}
</th>
<th className="text-left py-2 px-3 font-semibold">URL</th>
</tr>
</thead>
<tbody>
<tr className="border-b border-gray-100 dark:border-gray-800">
<td className="py-2 px-3">{isZh ? '全球' : 'Global'}</td>
<td className="py-2 px-3 font-mono text-xs break-all">{CDN_DEMO_URL}</td>
</tr>
<tr>
<td className="py-2 px-3">{isZh ? '中国' : 'China'}</td>
<td className="py-2 px-3 font-mono text-xs break-all">{CDN_DEMO_CN_URL}</td>
</tr>
</tbody>
</table>
</section>
<section className="mb-8">
<div className="bg-yellow-50 dark:bg-yellow-900/20 p-4 rounded-lg">
<h3 className="text-lg font-semibold mb-2 text-yellow-900 dark:text-yellow-300">
{isZh ? '注意事项' : 'Notes'}
</h3>
<ul className="text-gray-600 dark:text-gray-300 space-y-1">
<li>
{isZh ? '生产环境建议使用固定版本号' : 'Use fixed version number in production'}
</li>
<li> {isZh ? '确保 HTTPS 环境下使用' : 'Ensure HTTPS environment'}</li>
<li>
{' '}
{isZh
? '配置 CSP 策略允许脚本执行'
: 'Configure CSP policy to allow script execution'}
</li>
</ul>
</div>
{/* CDN Build Section */}
<section>
<h2 className="text-2xl font-bold mb-3">{isZh ? '📦 标准版' : '📦 Standard Build'}</h2>
<p className="text-gray-600 dark:text-gray-300 mb-3">
{isZh
? '将 PageAgent 类暴露到 globalThis,用法与 NPM 一致:'
: 'Exposes PageAgent class to globalThis, usage identical to NPM:'}
</p>
<CodeEditor
className="mb-4"
code={`<script src="${CDN_FULL_URL}" crossorigin="true"></script>
<script>
const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
})
await agent.execute('Click the submit button')
</script>`}
/>
<table className="w-full border-collapse text-sm">
<thead>
<tr className="border-b border-gray-200 dark:border-gray-700">
<th className="text-left py-2 px-3 font-semibold w-28">
{isZh ? '位置' : 'Location'}
</th>
<th className="text-left py-2 px-3 font-semibold">URL</th>
</tr>
</thead>
<tbody>
<tr className="border-b border-gray-100 dark:border-gray-800">
<td className="py-2 px-3">{isZh ? '全球' : 'Global'}</td>
<td className="py-2 px-3 font-mono text-xs break-all">{CDN_FULL_URL}</td>
</tr>
<tr>
<td className="py-2 px-3">{isZh ? '中国' : 'China'}</td>
<td className="py-2 px-3 font-mono text-xs break-all">{CDN_FULL_CN_URL}</td>
</tr>
</tbody>
</table>
</section>
{/* Tips */}
<section className="bg-blue-50 dark:bg-blue-900/20 p-4 rounded-lg">
<h3 className="text-base font-semibold mb-2 text-blue-900 dark:text-blue-300">
💡 {isZh ? '提示' : 'Tips'}
</h3>
<ul className="text-gray-600 dark:text-gray-300 text-sm space-y-1">
<li> {isZh ? '生产环境推荐使用 NPM' : 'NPM is recommended for production'}</li>
<li> {isZh ? '生产环境建议锁定版本号' : 'Lock version number in production'}</li>
<li> {isZh ? '确保 HTTPS 环境' : 'Ensure HTTPS environment'}</li>
</ul>
</section>
</div>
)
@@ -2,10 +2,11 @@ import { useTranslation } from 'react-i18next'
import BetaNotice from '@/components/BetaNotice'
import CodeEditor from '@/components/CodeEditor'
import { CDN_CN_URL, CDN_URL } from '@/constants'
import { CDN_DEMO_CN_URL, CDN_DEMO_URL } from '@/constants'
export default function QuickStart() {
const { t } = useTranslation('docs')
const { t, i18n } = useTranslation('docs')
const isZh = i18n.language === 'zh-CN'
return (
<div>
@@ -16,64 +17,62 @@ export default function QuickStart() {
<h2 className="text-2xl font-bold mb-3">{t('quick_start.installation')}</h2>
<div className="space-y-4 mb-6">
{/* Demo CDN - One Line */}
<div className="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg">
<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">
{t('quick_start.step1_title')}
{isZh ? '🚀 快速体验(Demo CDN' : '🚀 Quick Try (Demo CDN)'}
</h3>
<div className="space-y-3">
<div>
<p className="text-sm font-medium mb-2">{t('quick_start.step1_cdn')}</p>
<CodeEditor
code={`// CDN: \t${CDN_URL}
// Mirror: \t${CDN_CN_URL}
<script src="${CDN_URL}" crossorigin="true" type="text/javascript"></script>`}
language="html"
/>
</div>
<div>
<p className="text-sm font-medium mb-2">{t('quick_start.step1_npm')}</p>
<CodeEditor
code={`// npm install page-agent
import PageAgent from 'page-agent'`}
language="bash"
/>
</div>
<div className="bg-yellow-50 dark:bg-yellow-900/20 p-2 rounded mb-3 text-sm">
<span className="text-yellow-800 dark:text-yellow-200">
{isZh ? '仅用于技术评估' : 'For evaluation only'}
</span>
</div>
<CodeEditor
code={`// Global: ${CDN_DEMO_URL}
// China: ${CDN_DEMO_CN_URL}
<script src="${isZh ? CDN_DEMO_CN_URL : CDN_DEMO_URL}" crossorigin="true"></script>`}
language="html"
/>
</div>
{/* NPM - Recommended */}
<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
<h3 className="text-lg font-semibold mb-2 text-green-900 dark:text-green-300">
{t('quick_start.step2_title')}
{isZh ? '📦 NPM 安装(推荐)' : '📦 NPM Install (Recommended)'}
</h3>
<CodeEditor
code={`// 仅供测试使用,生产环境需要配置 LLM 接入点,本工具不提供 LLM 服务
// 测试接口
// @note: 限流,限制 prompt 内容,限制来源,随时变更,请替换成你自己的
// @note: 使用 DeepSeek-chat(3.2) 官方版本,使用协议和隐私策略见 DeepSeek 网站
const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
const DEMO_BASE_URL = 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
code={`npm install page-agent
const agent = new PageAgent({
model: DEMO_MODEL,
baseURL: DEMO_BASE_URL,
apiKey: DEMO_API_KEY,
language: 'zh-CN'
})`}
language="javascript"
import { PageAgent } from 'page-agent'`}
language="bash"
/>
</div>
<div className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
<h3 className="text-lg font-semibold mb-2 text-purple-900 dark:text-purple-300">
{t('quick_start.step2_title')}
</h3>
<CodeEditor
code={`const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
apiKey: 'YOUR_API_KEY',
language: '${isZh ? 'zh-CN' : 'en-US'}'
})`}
language="javascript"
/>
</div>
<div className="p-4 bg-orange-50 dark:bg-orange-900/20 rounded-lg">
<h3 className="text-lg font-semibold mb-2 text-orange-900 dark:text-orange-300">
{t('quick_start.step3_title')}
</h3>
<CodeEditor
code={`// 程序化执行自然语言指令
await pageAgent.execute('点击提交按钮,然后填写用户名为张三');
code={`// ${isZh ? '程序化执行自然语言指令' : 'Execute natural language instructions programmatically'}
await agent.execute('${isZh ? '' : 'Click submit button, then fill username as John'}');
// 或者显示对话框让用户输入指令
pageAgent.panel.show()
// ${isZh ? '或者显示对话框让用户输入指令' : 'Or show panel for user to input instructions'}
agent.panel.show()
`}
language="javascript"
/>
+5
View File
@@ -1,12 +1,16 @@
import tailwindcss from '@tailwindcss/vite'
import react from '@vitejs/plugin-react-swc'
import { config as dotenvConfig } from 'dotenv'
import { readFileSync } from 'node:fs'
import process from 'node:process'
import { dirname, resolve } from 'path'
import { fileURLToPath } from 'url'
import { defineConfig } from 'vite'
const __dirname = dirname(fileURLToPath(import.meta.url))
const pageAgentPkg = JSON.parse(
readFileSync(resolve(__dirname, '../page-agent/package.json'), 'utf-8')
)
// Load .env from repo root
dotenvConfig({ path: resolve(__dirname, '../../.env') })
@@ -32,5 +36,6 @@ export default defineConfig({
'import.meta.env.LLM_MODEL_NAME': JSON.stringify(process.env.LLM_MODEL_NAME),
'import.meta.env.LLM_API_KEY': JSON.stringify(process.env.LLM_API_KEY),
'import.meta.env.LLM_BASE_URL': JSON.stringify(process.env.LLM_BASE_URL),
'import.meta.env.VERSION': JSON.stringify(pageAgentPkg.version),
},
})