Compare commits

..

48 Commits

Author SHA1 Message Date
Simon b6691b4732 chore(version): bump version to 1.6.0 2026-03-21 02:24:42 +08:00
Simon a557a85d28 Merge pull request #325 from alibaba/fix/action-into-iframes
fix(PageController): same-origin iframe actions
2026-03-21 02:20:13 +08:00
Simon eeb5b6a5af fix(clickElement): reorder iframe scroll and click actions 2026-03-21 02:18:42 +08:00
Simon ad31e2b750 chore: clarify current type handling in isHTMLElement 2026-03-21 02:16:51 +08:00
Simon e98d80b6a0 fix(PageController): same-origin iframe actions 2026-03-21 01:46:09 +08:00
Simon 93b1e52376 Merge pull request #322 from alibaba/feat/optional-toolchoice 2026-03-20 17:43:44 +08:00
Simon 66a85c0dd3 feat: option to disable named tool choice 2026-03-20 17:40:16 +08:00
Simon 50ce56a4f6 Merge pull request #321 from alibaba:chore/ext-rm-keydown
chore(ext): rm keydown event on history
2026-03-20 17:14:38 +08:00
Simon 5aeb40abac chore(ext): rm keydown event on history 2026-03-20 17:13:42 +08:00
Simon 8c06cdc898 Merge pull request #313 from Adonis0123/feature/239-history-export
feat(extension): export history sessions as json
2026-03-20 17:01:59 +08:00
Simon dfde89aa70 Merge branch 'main' into pr/Adonis0123/313 2026-03-20 16:58:13 +08:00
Simon 49b3316a5f Merge pull request #314 from Adonis0123/feat/issue-304-rerun-history-task
feat(ext): rerun tasks from history
2026-03-20 16:39:09 +08:00
Simon c35f367b39 feat(ext): style adjust; rm rerunDisabled 2026-03-20 16:36:23 +08:00
Simon 3459836a14 fix(PageController): lint error 2026-03-20 16:10:43 +08:00
Simon b7b5b6db30 Merge pull request #319 from alibaba/fix/missing-pointerout
fix(PageController): add `mouseleave` event
2026-03-20 16:05:37 +08:00
Simon 05d16313c7 fix(PageController): add mouseleave event 2026-03-20 15:54:36 +08:00
Simon a3a96d85d5 Merge pull request #210 from voidborne-d/fix/contenteditable-fallback
fix: add execCommand fallback for contenteditable input
2026-03-20 15:38:06 +08:00
Simon c89042f142 chore: wording 2026-03-20 15:36:10 +08:00
voidborne-d 2e18bd862d refactor: use const for planASucceeded, clarify LinkedIn comment 2026-03-20 07:08:45 +00:00
adonis 0bc47a997d feat(ext): rerun tasks from history 2026-03-19 23:54:08 +08:00
adonis bcc7dfea2d feat(extension): export history sessions as json 2026-03-19 23:46:58 +08:00
Simon ba242d3a1b Merge pull request #311 from alibaba/feat/llms-ak-always-optional
feat: optional AK
2026-03-19 20:08:15 +08:00
Simon fe82b11285 feat: AK optional 2026-03-19 19:50:05 +08:00
Simon bdf79b7c10 chore(version): bump version to 1.5.11 2026-03-18 20:45:19 +08:00
Simon 24eefdef23 chore(version): bump version to 1.5.10 2026-03-18 20:36:29 +08:00
Simon 252f550c04 style(ext): fix ai-motion overflow; wording; launcher info 2026-03-18 20:25:54 +08:00
Simon 628c249d45 fix(ext): init without initialTab throws error 2026-03-18 19:36:02 +08:00
Simon 61d598142d feat(ext): ask user approval for MCP task 2026-03-18 19:14:44 +08:00
Simon c0510b2235 Merge pull request #294 from octo-patch/feature/upgrade-minimax-m27
feat: upgrade MiniMax default model to M2.7
2026-03-18 15:21:19 +08:00
Octopus ca0005c825 feat: upgrade MiniMax default model to M2.7
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model in code example
- Keep all previous models as alternatives
2026-03-18 02:12:58 -05:00
Simon 17e92b6200 chore(version): bump version to 1.5.9 2026-03-18 03:45:56 +08:00
Simon 2e0cbef034 Merge pull request #283 from alibaba/feat/mcp
feat: mcp (WIP)
2026-03-18 03:42:44 +08:00
Simon 95b6785f05 feat(mcp): mark MCP package as private 2026-03-18 03:37:02 +08:00
Simon 2917941b13 feat(mcp): add TODO for version checking 2026-03-18 03:31:38 +08:00
Simon 31c496cc65 docs(mcp): add development instructions for mcp 2026-03-18 03:15:02 +08:00
Simon cef39d5090 feat(mcp): MCP connector 2026-03-18 03:12:20 +08:00
Simon 3063b2a06d feat(ext): hub protocol 2026-03-18 02:59:28 +08:00
Simon d66a390516 chore(ext): add pub key to fix extension ID 2026-03-18 01:56:56 +08:00
Simon aae6c93f11 fix(ext): useAgent execute return result 2026-03-18 01:55:09 +08:00
Simon 2f5476b76c refactor(ext): mv ui components for later reuse 2026-03-17 19:11:13 +08:00
Simon 88ea2c6708 Merge pull request #221 from octo-patch/feature/add-minimax-provider
feat: add MiniMax model support with temperature clamping
2026-03-17 14:16:59 +08:00
Simon 37760a97df Merge pull request #274 from alibaba/dependabot/npm_and_yarn/development-dependencies-8ef9c9264a
chore(deps-dev): bump the development-dependencies group with 10 updates
2026-03-17 14:09:18 +08:00
dependabot[bot] de76d97303 chore(deps-dev): bump the development-dependencies group with 10 updates
Bumps the development-dependencies group with 10 updates:

| Package | From | To |
| --- | --- | --- |
| [@commitlint/cli](https://github.com/conventional-changelog/commitlint/tree/HEAD/@commitlint/cli) | `20.4.3` | `20.5.0` |
| [@commitlint/config-conventional](https://github.com/conventional-changelog/commitlint/tree/HEAD/@commitlint/config-conventional) | `20.4.3` | `20.5.0` |
| [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) | `25.4.0` | `25.5.0` |
| [@vitejs/plugin-react-swc](https://github.com/vitejs/vite-plugin-react/tree/HEAD/packages/plugin-react-swc) | `4.2.3` | `4.3.0` |
| [lint-staged](https://github.com/lint-staged/lint-staged) | `16.3.2` | `16.4.0` |
| [typescript-eslint](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/typescript-eslint) | `8.57.0` | `8.57.1` |
| [@wxt-dev/module-react](https://github.com/wxt-dev/wxt/tree/HEAD/packages/module-react) | `1.2.1` | `1.2.2` |
| [motion](https://github.com/motiondivision/motion) | `12.35.2` | `12.37.0` |
| [simple-icons](https://github.com/simple-icons/simple-icons) | `16.11.0` | `16.12.0` |
| [wxt](https://github.com/wxt-dev/wxt) | `0.20.18` | `0.20.19` |


Updates `@commitlint/cli` from 20.4.3 to 20.5.0
- [Release notes](https://github.com/conventional-changelog/commitlint/releases)
- [Changelog](https://github.com/conventional-changelog/commitlint/blob/master/@commitlint/cli/CHANGELOG.md)
- [Commits](https://github.com/conventional-changelog/commitlint/commits/v20.5.0/@commitlint/cli)

Updates `@commitlint/config-conventional` from 20.4.3 to 20.5.0
- [Release notes](https://github.com/conventional-changelog/commitlint/releases)
- [Changelog](https://github.com/conventional-changelog/commitlint/blob/master/@commitlint/config-conventional/CHANGELOG.md)
- [Commits](https://github.com/conventional-changelog/commitlint/commits/v20.5.0/@commitlint/config-conventional)

Updates `@types/node` from 25.4.0 to 25.5.0
- [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases)
- [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/node)

Updates `@vitejs/plugin-react-swc` from 4.2.3 to 4.3.0
- [Release notes](https://github.com/vitejs/vite-plugin-react/releases)
- [Changelog](https://github.com/vitejs/vite-plugin-react/blob/main/packages/plugin-react-swc/CHANGELOG.md)
- [Commits](https://github.com/vitejs/vite-plugin-react/commits/v4.3.0/packages/plugin-react-swc)

Updates `lint-staged` from 16.3.2 to 16.4.0
- [Release notes](https://github.com/lint-staged/lint-staged/releases)
- [Changelog](https://github.com/lint-staged/lint-staged/blob/main/CHANGELOG.md)
- [Commits](https://github.com/lint-staged/lint-staged/compare/v16.3.2...v16.4.0)

Updates `typescript-eslint` from 8.57.0 to 8.57.1
- [Release notes](https://github.com/typescript-eslint/typescript-eslint/releases)
- [Changelog](https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/typescript-eslint/CHANGELOG.md)
- [Commits](https://github.com/typescript-eslint/typescript-eslint/commits/v8.57.1/packages/typescript-eslint)

Updates `@wxt-dev/module-react` from 1.2.1 to 1.2.2
- [Release notes](https://github.com/wxt-dev/wxt/releases)
- [Changelog](https://github.com/wxt-dev/wxt/blob/main/packages/module-react/CHANGELOG.md)
- [Commits](https://github.com/wxt-dev/wxt/commits/storage-v1.2.2/packages/module-react)

Updates `motion` from 12.35.2 to 12.37.0
- [Changelog](https://github.com/motiondivision/motion/blob/main/CHANGELOG.md)
- [Commits](https://github.com/motiondivision/motion/compare/v12.35.2...v12.37.0)

Updates `simple-icons` from 16.11.0 to 16.12.0
- [Release notes](https://github.com/simple-icons/simple-icons/releases)
- [Commits](https://github.com/simple-icons/simple-icons/compare/16.11.0...16.12.0)

Updates `wxt` from 0.20.18 to 0.20.19
- [Release notes](https://github.com/wxt-dev/wxt/releases)
- [Commits](https://github.com/wxt-dev/wxt/compare/wxt-v0.20.18...wxt-v0.20.19)

---
updated-dependencies:
- dependency-name: "@commitlint/cli"
  dependency-version: 20.5.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: "@commitlint/config-conventional"
  dependency-version: 20.5.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: "@types/node"
  dependency-version: 25.5.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: "@vitejs/plugin-react-swc"
  dependency-version: 4.3.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: lint-staged
  dependency-version: 16.4.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: typescript-eslint
  dependency-version: 8.57.1
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: "@wxt-dev/module-react"
  dependency-version: 1.2.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: motion
  dependency-version: 12.37.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: simple-icons
  dependency-version: 16.12.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: wxt
  dependency-version: 0.20.19
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-03-16 19:36:05 +00:00
Simon 92196ac793 chore(website): tailwind important; footer 2026-03-17 00:29:13 +08:00
Simon 80dda37f8c fix: improve button cursor styles in UI components 2026-03-16 23:23:27 +08:00
Simon 5e7fe18463 docs(website): clean up 2026-03-16 23:14:48 +08:00
octo-patch 8ad4d19232 feat: add MiniMax model support with temperature clamping
Add MiniMax (M2.5 / M2.5-highspeed) as a tested model provider:

- Add model-specific patch in utils.ts: clamp temperature to (0, 1]
  since MiniMax API rejects temperature=0, and remove unsupported
  parallel_tool_calls parameter
- Add MiniMax to the tested models list on the Models documentation page
- Add MiniMax configuration example alongside existing providers
2026-03-15 23:42:30 +00:00
d 🔹 2f92a9cb32 fix: add execCommand fallback for contenteditable input (#168)
When typing into contenteditable elements (e.g. LinkedIn post editor),
the synthetic event approach (Plan A) may fail silently — the events
fire but the editor's internal state doesn't update, leaving the
element empty.

This adds an automatic fallback: after Plan A, we verify the text was
actually inserted by checking element.innerText. If it wasn't, we
fall back to execCommand('insertText') which integrates natively with
most rich-text editors including LinkedIn, Quill, and Slate.js.

The fallback uses proper Selection/Range API to select-all before
replacing, and preserves the undo stack since execCommand is handled
by the browser natively.

Fixes #168
2026-03-11 17:07:22 +00:00
61 changed files with 2900 additions and 823 deletions
+2 -2
View File
@@ -49,8 +49,8 @@ Fastest way to try PageAgent with our free Demo LLM:
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.8/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.8/files/dist/iife/page-agent.demo.js |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.6.0/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.6.0/files/dist/iife/page-agent.demo.js |
### NPM Installation
-36
View File
@@ -153,42 +153,6 @@ PageAgent is now ready for production use. The API is stable and breaking change
- **Ask User Tool** - Agent can ask users for clarification
- **i18n Support** - English and Chinese localization
### Configuration
```typescript
// Version 1.0.0
interface PageAgentConfig {
// LLM Configuration (required)
baseURL: string
apiKey: string
model: string
temperature?: number
maxRetries?: number
customFetch?: typeof fetch
// Agent Configuration
language?: 'en-US' | 'zh-CN'
maxSteps?: number // default: 20
customTools?: Record<string, PageAgentTool> // experimental
instructions?: InstructionsConfig
transformPageContent?: (content: string) => string | Promise<string>
experimentalScriptExecutionTool?: boolean // default: false
// Lifecycle Hooks (experimental)
onBeforeTask?: (agent, result) => void
onAfterTask?: (agent, result) => void
onBeforeStep?: (agent, stepCount) => void
onAfterStep?: (agent, history) => void
onDispose?: (agent, reason?) => void
// Page Controller Configuration
enableMask?: boolean // default: true
viewportExpansion?: number
interactiveBlacklist?: Element[]
interactiveWhitelist?: Element[]
}
```
### Packages
| Package | Description |
+2 -2
View File
@@ -49,8 +49,8 @@
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.8/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.8/files/dist/iife/page-agent.demo.js |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.6.0/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.6.0/files/dist/iife/page-agent.demo.js |
### NPM 安装
+1269 -545
View File
File diff suppressed because it is too large Load Diff
+8 -7
View File
@@ -1,7 +1,7 @@
{
"name": "root",
"private": true,
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"workspaces": [
"packages/page-controller",
@@ -9,6 +9,7 @@
"packages/llms",
"packages/core",
"packages/page-agent",
"packages/mcp",
"packages/extension",
"packages/website"
],
@@ -37,14 +38,14 @@
"prepare": "husky"
},
"devDependencies": {
"@commitlint/cli": "^20.4.3",
"@commitlint/config-conventional": "^20.4.3",
"@commitlint/cli": "^20.5.0",
"@commitlint/config-conventional": "^20.5.0",
"@eslint/js": "^9.39.2",
"@microsoft/api-extractor": "^7.57.7",
"@tailwindcss/vite": "^4.2.1",
"@trivago/prettier-plugin-sort-imports": "^6.0.2",
"@types/node": "^25.4.0",
"@vitejs/plugin-react-swc": "^4.1.0",
"@types/node": "^25.5.0",
"@vitejs/plugin-react-swc": "^4.3.0",
"chalk": "^5.6.2",
"concurrently": "^9.2.1",
"dotenv": "^17.3.1",
@@ -56,10 +57,10 @@
"eslint-plugin-react-x": "^2.13.0",
"globals": "^17.4.0",
"husky": "^9.1.7",
"lint-staged": "^16.3.2",
"lint-staged": "^16.4.0",
"prettier": "^3.8.0",
"typescript": "^5.9.3",
"typescript-eslint": "^8.57.0",
"typescript-eslint": "^8.57.1",
"unplugin-dts": "^1.0.0-beta.6",
"vite": "^7.3.1",
"vite-plugin-css-injected-by-js": "^4.0.1",
+3 -3
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/core",
"private": false,
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"main": "./dist/esm/page-agent-core.js",
"module": "./dist/esm/page-agent-core.js",
@@ -44,8 +44,8 @@
},
"dependencies": {
"chalk": "^5.6.2",
"@page-agent/llms": "1.5.8",
"@page-agent/page-controller": "1.5.8"
"@page-agent/llms": "1.6.0",
"@page-agent/page-controller": "1.6.0"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
+2 -2
View File
@@ -115,8 +115,8 @@ import type {
export interface ExecuteConfig {
baseURL: string
apiKey: string
model: string
apiKey?: string
// Include the initial tab where page JS starts. Default: true.
includeInitialTab?: boolean
@@ -205,8 +205,8 @@ import type {
interface ExecuteConfig {
baseURL: string
apiKey: string
model: string
apiKey?: string
includeInitialTab?: boolean
onStatusChange?: (status: AgentStatus) => void
onActivity?: (activity: AgentActivity) => void
+9 -10
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/ext",
"private": true,
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"scripts": {
"dev": "wxt",
@@ -16,32 +16,31 @@
"@radix-ui/react-separator": "^1.1.8",
"@radix-ui/react-slot": "^1.2.4",
"@radix-ui/react-switch": "^1.2.6",
"@radix-ui/react-tooltip": "^1.2.8",
"@types/chrome": "^0.1.37",
"@types/react": "^19.2.14",
"@types/react-dom": "^19.2.1",
"@wxt-dev/module-react": "^1.2.1",
"@wxt-dev/module-react": "^1.2.2",
"class-variance-authority": "^0.7.1",
"clsx": "^2.1.1",
"idb": "^8.0.3",
"lucide-react": "^0.577.0",
"motion": "^12.35.2",
"motion": "^12.37.0",
"next-themes": "^0.4.6",
"react": "^19.2.4",
"react-dom": "^19.2.4",
"rough-notation": "^0.5.1",
"simple-icons": "^16.11.0",
"simple-icons": "^16.12.0",
"sonner": "^2.0.7",
"tailwind-merge": "^3.5.0",
"tailwindcss": "^4.1.14",
"tw-animate-css": "^1.4.0",
"wxt": "^0.20.18"
"wxt": "^0.20.19"
},
"dependencies": {
"@page-agent/core": "1.5.8",
"@page-agent/llms": "1.5.8",
"@page-agent/page-controller": "1.5.8",
"@page-agent/ui": "1.5.8",
"@page-agent/core": "1.6.0",
"@page-agent/llms": "1.6.0",
"@page-agent/page-controller": "1.6.0",
"@page-agent/ui": "1.6.0",
"ai-motion": "^0.4.8",
"chalk": "^5.6.2"
},
@@ -75,6 +75,7 @@ export class MultiPageAgent extends PageAgentCore {
},
onBeforeStep: async (agent) => {
if (!tabsController.currentTabId) return
// make sure the current tab is loaded before the step starts
await tabsController.waitUntilTabLoaded(tabsController.currentTabId!)
},
@@ -58,8 +58,6 @@ export class RemotePageController {
}
async getBrowserState(): Promise<BrowserState> {
if (!this.currentTabId) throw new Error('tabsController not initialized.')
let browserState = {} as BrowserState
debug('getBrowserState', this.currentTabId)
@@ -178,7 +176,7 @@ interface DomActionReturn {
/**
* Check if a URL can run content scripts.
*/
function isContentScriptAllowed(url: string | undefined): boolean {
export function isContentScriptAllowed(url: string | undefined): boolean {
if (!url) return false
const restrictedPatterns = [
+14 -10
View File
@@ -1,3 +1,5 @@
import { isContentScriptAllowed } from './RemotePageController'
const PREFIX = '[TabsController]'
function debug(...messages: any[]) {
@@ -49,23 +51,25 @@ export class TabsController extends EventTarget {
}
if (includeInitialTab) {
this.currentTabId = this.initialTabId
const info = await sendMessage({
type: 'TAB_CONTROL',
action: 'get_tab_info',
payload: { tabId: this.initialTabId },
})
this.tabs.push({
id: result.tabId,
isInitial: true,
url: info.url,
title: info.title,
status: info.status,
})
if (isContentScriptAllowed(info.url)) {
this.currentTabId = this.initialTabId
await this.createTabGroup([this.initialTabId])
this.tabs.push({
id: result.tabId,
isInitial: true,
url: info.url,
title: info.title,
status: info.status,
})
await this.createTabGroup([this.initialTabId])
}
}
await this.updateCurrentTabId(this.currentTabId)
+2 -2
View File
@@ -3,12 +3,12 @@ import type { LLMConfig } from '@page-agent/llms'
// Demo LLM for testing
export const DEMO_MODEL = 'qwen3.5-plus'
export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
export const DEMO_API_KEY = 'NA'
// export const DEMO_API_KEY = 'NA'
export const DEMO_CONFIG: LLMConfig = {
apiKey: DEMO_API_KEY,
baseURL: DEMO_BASE_URL,
model: DEMO_MODEL,
// apiKey: DEMO_API_KEY,
}
/** Legacy testing endpoints that should be auto-migrated to DEMO_BASE_URL */
+11 -3
View File
@@ -4,6 +4,7 @@
import type {
AgentActivity,
AgentStatus,
ExecutionResult,
HistoricalEvent,
SupportedLanguage,
} from '@page-agent/core'
@@ -20,6 +21,7 @@ export interface AdvancedConfig {
maxSteps?: number
systemInstruction?: string
experimentalLlmsTxt?: boolean
disableNamedToolChoice?: boolean
}
export interface ExtConfig extends LLMConfig, AdvancedConfig {
@@ -32,7 +34,7 @@ export interface UseAgentResult {
activity: AgentActivity | null
currentTask: string
config: ExtConfig | null
execute: (task: string) => Promise<void>
execute: (task: string) => Promise<ExecutionResult>
stop: () => void
configure: (config: ExtConfig) => Promise<void>
}
@@ -110,7 +112,7 @@ export function useAgent(): UseAgentResult {
setCurrentTask(task)
setHistory([])
await agent.execute(task)
return agent.execute(task)
}, [])
const stop = useCallback(() => {
@@ -123,6 +125,7 @@ export function useAgent(): UseAgentResult {
maxSteps,
systemInstruction,
experimentalLlmsTxt,
disableNamedToolChoice,
...llmConfig
}: ExtConfig) => {
await chrome.storage.local.set({ llmConfig })
@@ -131,7 +134,12 @@ export function useAgent(): UseAgentResult {
} else {
await chrome.storage.local.remove('language')
}
const advancedConfig: AdvancedConfig = { maxSteps, systemInstruction, experimentalLlmsTxt }
const advancedConfig: AdvancedConfig = {
maxSteps,
systemInstruction,
experimentalLlmsTxt,
disableNamedToolChoice,
}
await chrome.storage.local.set({ advancedConfig })
setConfig({ ...llmConfig, ...advancedConfig, language })
},
@@ -1,18 +1,20 @@
import {
ChevronDown,
Copy,
CornerUpLeft,
ExternalLink,
Eye,
EyeOff,
FoldVertical,
HatGlasses,
Home,
Loader2,
Scale,
UnfoldVertical,
} from 'lucide-react'
import { useEffect, useState } from 'react'
import { siGithub } from 'simple-icons'
import { DEMO_API_KEY, DEMO_BASE_URL, DEMO_MODEL, isTestingEndpoint } from '@/agent/constants'
import { DEMO_BASE_URL, DEMO_MODEL, isTestingEndpoint } from '@/agent/constants'
import type { ExtConfig, LanguagePreference } from '@/agent/useAgent'
import { Button } from '@/components/ui/button'
import { Input } from '@/components/ui/input'
@@ -25,15 +27,18 @@ interface ConfigPanelProps {
}
export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const [apiKey, setApiKey] = useState(config?.apiKey || DEMO_API_KEY)
const [baseURL, setBaseURL] = useState(config?.baseURL || DEMO_BASE_URL)
const [model, setModel] = useState(config?.model || DEMO_MODEL)
const [apiKey, setApiKey] = useState(config?.apiKey)
const [language, setLanguage] = useState<LanguagePreference>(config?.language)
const [maxSteps, setMaxSteps] = useState<number | undefined>(config?.maxSteps)
const [systemInstruction, setSystemInstruction] = useState(config?.systemInstruction ?? '')
const [experimentalLlmsTxt, setExperimentalLlmsTxt] = useState(
config?.experimentalLlmsTxt ?? false
)
const [disableNamedToolChoice, setDisableNamedToolChoice] = useState(
config?.disableNamedToolChoice ?? false
)
const [advancedOpen, setAdvancedOpen] = useState(false)
const [saving, setSaving] = useState(false)
const [userAuthToken, setUserAuthToken] = useState<string>('')
@@ -42,13 +47,14 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const [showApiKey, setShowApiKey] = useState(false)
useEffect(() => {
setApiKey(config?.apiKey || DEMO_API_KEY)
setBaseURL(config?.baseURL || DEMO_BASE_URL)
setModel(config?.model || DEMO_MODEL)
setApiKey(config?.apiKey)
setLanguage(config?.language)
setMaxSteps(config?.maxSteps)
setSystemInstruction(config?.systemInstruction ?? '')
setExperimentalLlmsTxt(config?.experimentalLlmsTxt ?? false)
setDisableNamedToolChoice(config?.disableNamedToolChoice ?? false)
}, [config])
// Poll for user auth token every second until found
@@ -94,6 +100,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
maxSteps: maxSteps || undefined,
systemInstruction: systemInstruction || undefined,
experimentalLlmsTxt,
disableNamedToolChoice,
})
} finally {
setSaving(false)
@@ -153,6 +160,16 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</div>
</div>
{/* Hub link */}
<a
href="/hub.html"
target="_blank"
className="flex items-center justify-between p-3 rounded-md border bg-muted/50 text-xs font-medium text-muted-foreground hover:text-foreground hover:border-foreground/20 transition-colors"
>
Manage Page Agent Hub
<ExternalLink className="size-3" />
</a>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Base URL</label>
<Input
@@ -167,7 +184,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
{isTestingEndpoint(baseURL) && (
<div className="p-2.5 rounded-md border border-amber-500/30 bg-amber-500/5 text-[11px] text-muted-foreground leading-relaxed">
<Scale className="size-3 inline-block mr-1 -mt-0.5 text-amber-600" />
You are using the free testing API. By using this service you agree to the{' '}
You are using our testing API. By using this you agree to the{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank"
@@ -176,14 +193,13 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
>
Terms of Use & Privacy Policy
</a>
. No sensitive data. No guaranteed availability.
</div>
)}
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Model</label>
<Input
placeholder="gpt-5.2"
placeholder="gpt-5.1"
value={model}
onChange={(e) => setModel(e.target.value)}
className="text-xs h-8"
@@ -195,7 +211,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
<div className="flex gap-2 items-center">
<Input
type={showApiKey ? 'text' : 'password'}
placeholder="sk-..."
// placeholder="sk-..."
value={apiKey}
onChange={(e) => setApiKey(e.target.value)}
className="text-xs h-8"
@@ -212,7 +228,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</div>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Language</label>
<label className="text-xs text-muted-foreground">Response Language</label>
<select
value={language ?? ''}
onChange={(e) => setLanguage((e.target.value || undefined) as LanguagePreference)}
@@ -231,10 +247,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
className="flex items-center gap-1 text-xs text-muted-foreground hover:text-foreground cursor-pointer mt-1 font-bold"
>
Advanced
<ChevronDown
className="size-3 transition-transform"
style={{ transform: advancedOpen ? 'rotate(0deg)' : 'rotate(90deg)' }}
/>
{advancedOpen ? <FoldVertical className="size-3" /> : <UnfoldVertical className="size-3" />}
</button>
{advancedOpen && (
@@ -263,6 +276,11 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
/>
</div>
<label className="flex items-center justify-between cursor-pointer">
<span className="text-xs text-muted-foreground">Disable named tool_choice</span>
<Switch checked={disableNamedToolChoice} onCheckedChange={setDisableNamedToolChoice} />
</label>
<label className="flex items-center justify-between cursor-pointer">
<span className="text-xs text-muted-foreground">Experimental llms.txt support</span>
<Switch checked={experimentalLlmsTxt} onCheckedChange={setExperimentalLlmsTxt} />
@@ -1,12 +1,20 @@
import { ArrowLeft } from 'lucide-react'
import { ArrowLeft, RotateCcw, Trash2 } from 'lucide-react'
import { useEffect, useState } from 'react'
import { Button } from '@/components/ui/button'
import { type SessionRecord, getSession } from '@/lib/db'
import { type SessionRecord, deleteSession, getSession } from '@/lib/db'
import { EventCard } from './cards'
export function HistoryDetail({ sessionId, onBack }: { sessionId: string; onBack: () => void }) {
export function HistoryDetail({
sessionId,
onBack,
onRerun,
}: {
sessionId: string
onBack: () => void
onRerun: (task: string) => void
}) {
const [session, setSession] = useState<SessionRecord | null>(null)
useEffect(() => {
@@ -37,6 +45,27 @@ export function HistoryDetail({ sessionId, onBack }: { sessionId: string; onBack
<div className="text-xs font-medium" title={session.task}>
{session.task}
</div>
<div className="mt-2 flex items-center gap-2">
<button
type="button"
onClick={() => onRerun(session.task)}
className="flex items-center gap-1 text-[10px] text-muted-foreground hover:text-foreground transition-colors cursor-pointer disabled:opacity-50 disabled:cursor-not-allowed"
>
<RotateCcw className="size-3" />
Run again
</button>
<button
type="button"
onClick={async () => {
await deleteSession(sessionId)
onBack()
}}
className="flex items-center gap-1 text-[10px] text-muted-foreground hover:text-destructive transition-colors cursor-pointer"
>
<Trash2 className="size-3" />
Delete
</button>
</div>
</div>
{/* Events (read-only) */}
@@ -1,8 +1,9 @@
import { ArrowLeft, CheckCircle, Trash2, XCircle } from 'lucide-react'
import { ArrowDownToLine, ArrowLeft, CheckCircle, RotateCcw, Trash2, XCircle } from 'lucide-react'
import { useCallback, useEffect, useState } from 'react'
import { Button } from '@/components/ui/button'
import { type SessionRecord, clearSessions, deleteSession, listSessions } from '@/lib/db'
import { downloadHistoryExport } from '@/lib/history-export'
function timeAgo(ts: number): string {
const seconds = Math.floor((Date.now() - ts) / 1000)
@@ -18,9 +19,11 @@ function timeAgo(ts: number): string {
export function HistoryList({
onSelect,
onBack,
onRerun,
}: {
onSelect: (id: string) => void
onBack: () => void
onRerun: (task: string) => void
}) {
const [sessions, setSessions] = useState<SessionRecord[]>([])
const [loading, setLoading] = useState(true)
@@ -41,6 +44,16 @@ export function HistoryList({
setSessions((prev) => prev.filter((s) => s.id !== id))
}
const handleExport = (e: React.MouseEvent, session: SessionRecord) => {
e.stopPropagation()
downloadHistoryExport(session.task, session.createdAt, session.history)
}
const handleRerun = (e: React.MouseEvent, task: string) => {
e.stopPropagation()
onRerun(task)
}
return (
<div className="flex flex-col h-screen bg-background">
{/* Header */}
@@ -85,7 +98,6 @@ export function HistoryList({
role="button"
tabIndex={0}
onClick={() => onSelect(session.id)}
onKeyDown={(e) => e.key === 'Enter' && onSelect(session.id)}
className="w-full text-left px-3 py-2.5 border-b hover:bg-muted/50 transition-colors cursor-pointer flex items-start gap-2 group"
>
{/* Status icon */}
@@ -98,19 +110,41 @@ export function HistoryList({
{/* Content */}
<div className="flex-1 min-w-0">
<p className="text-xs font-medium truncate">{session.task}</p>
<p className="text-[10px] text-muted-foreground mt-0.5">
{timeAgo(session.createdAt)} · {session.history.length} steps
</p>
<div className="flex items-center mt-0.5">
<p className="text-[10px] text-muted-foreground">
{timeAgo(session.createdAt)} · {session.history.length} steps
</p>
<div className="flex items-center gap-0.5 ml-auto opacity-0 group-hover:opacity-100 transition-opacity">
<button
type="button"
onClick={(e) => handleRerun(e, session.task)}
className="p-0.5 text-muted-foreground hover:text-foreground transition-colors cursor-pointer"
title="Run task again"
aria-label={`Run history task again: ${session.task}`}
>
<RotateCcw className="size-3" />
</button>
<button
type="button"
onClick={(e) => handleExport(e, session)}
className="p-1 text-muted-foreground hover:text-foreground transition-colors cursor-pointer"
title="Export history JSON"
aria-label={`Export history for ${session.task}`}
>
<ArrowDownToLine className="size-3" />
</button>
<button
type="button"
onClick={(e) => handleDelete(e, session.id)}
className="p-0.5 text-muted-foreground hover:text-destructive transition-colors cursor-pointer"
title="Delete history"
aria-label={`Delete history for ${session.task}`}
>
<Trash2 className="size-3" />
</button>
</div>
</div>
</div>
{/* Delete */}
<button
type="button"
onClick={(e) => handleDelete(e, session.id)}
className="opacity-0 group-hover:opacity-100 transition-opacity p-1 hover:text-destructive cursor-pointer shrink-0"
>
<Trash2 className="size-3" />
</button>
</div>
))}
</div>
@@ -84,7 +84,7 @@ export function MotionOverlay({ active }: { active: boolean }) {
return (
<div
ref={containerRef}
className="pointer-events-none absolute inset-0 z-10 opacity-60"
className="pointer-events-none absolute inset-0 z-10 opacity-60 overflow-hidden"
style={{ display: active ? undefined : 'none' }}
/>
)
@@ -8,7 +8,7 @@ function Switch({ className, ...props }: React.ComponentProps<typeof SwitchPrimi
<SwitchPrimitive.Root
data-slot="switch"
className={cn(
'peer data-[state=checked]:bg-primary data-[state=unchecked]:bg-input focus-visible:border-ring focus-visible:ring-ring/50 dark:data-[state=unchecked]:bg-input/80 inline-flex h-[1.15rem] w-8 shrink-0 items-center rounded-full border border-transparent shadow-xs transition-all outline-none focus-visible:ring-[3px] disabled:cursor-not-allowed disabled:opacity-50',
'peer data-[state=checked]:bg-primary data-[state=unchecked]:bg-input focus-visible:border-ring focus-visible:ring-ring/50 dark:data-[state=unchecked]:bg-input/80 inline-flex h-[1.15rem] w-8 shrink-0 cursor-pointer items-center rounded-full border border-transparent shadow-xs transition-all outline-none focus-visible:ring-[3px] disabled:cursor-not-allowed disabled:opacity-50',
className
)}
{...props}
@@ -30,7 +30,34 @@ export default defineBackground(() => {
}
})
// external messages (from localhost launcher page via externally_connectable)
chrome.runtime.onMessageExternal.addListener((message, sender, sendResponse) => {
if (message.type === 'OPEN_HUB') {
openOrFocusHubTab(message.wsPort).then(() => {
if (sender.tab?.id) chrome.tabs.remove(sender.tab.id)
sendResponse({ ok: true })
})
return true
}
})
// setup
chrome.sidePanel.setPanelBehavior({ openPanelOnActionClick: true }).catch(() => {})
})
async function openOrFocusHubTab(wsPort: number) {
const hubUrl = chrome.runtime.getURL('hub.html')
const existing = await chrome.tabs.query({ url: `${hubUrl}*` })
if (existing.length > 0 && existing[0].id) {
await chrome.tabs.update(existing[0].id, {
active: true,
url: `${hubUrl}?ws=${wsPort}`,
})
return
}
await chrome.tabs.create({ url: `${hubUrl}?ws=${wsPort}`, pinned: true })
}
@@ -0,0 +1,251 @@
import { FoldVertical, Plug, PlugZap, Square, UnfoldVertical, Unplug } from 'lucide-react'
import { useEffect, useRef, useState } from 'react'
import { useAgent } from '@/agent/useAgent'
import { ActivityCard, EventCard } from '@/components/cards'
import { Logo, MotionOverlay, StatusDot } from '@/components/misc'
import { Button } from '@/components/ui/button'
import { Switch } from '@/components/ui/switch'
import { useHubWs } from './hub-ws'
export default function App() {
const { status, history, activity, currentTask, config, execute, stop, configure } = useAgent()
const { wsState } = useHubWs(execute, stop, configure, config)
const historyRef = useRef<HTMLDivElement>(null)
useEffect(() => {
if (historyRef.current) {
historyRef.current.scrollTop = historyRef.current.scrollHeight
}
}, [history, activity])
const isRunning = status === 'running'
const WsIcon = wsState === 'connected' ? PlugZap : wsState === 'connecting' ? Plug : Unplug
const wsLabel = {
connected: 'Connected',
connecting: 'Connecting…',
disconnected: new URLSearchParams(location.search).get('ws') ? 'Disconnected' : 'No connection',
}[wsState]
return (
<div className="flex h-screen bg-background">
{/* Left — Protocol docs */}
<aside className="w-80 shrink-0 border-r flex flex-col bg-muted/20">
<a
href="https://alibaba.github.io/page-agent/"
target="_blank"
rel="noopener noreferrer"
className="flex items-center gap-2 px-5 h-12 border-b hover:bg-muted/30 transition-colors"
>
<Logo className="size-5" />
<span className="text-sm font-semibold tracking-tight">Page Agent Hub</span>
<span className="text-[9px] font-medium uppercase tracking-wider text-amber-600 bg-amber-500/10 border border-amber-500/30 rounded px-1.5 py-0.5">
Beta
</span>
</a>
<div className="flex-1 overflow-y-auto px-5 py-4 space-y-6">
<div className="text-xs text-muted-foreground leading-relaxed space-y-2">
<p>
Page Agent Hub lets local apps (e.g. MCP servers) control the Page Agent extension via
WebSocket.
</p>
<p>
Check out the official{' '}
<a
href="https://github.com/alibaba/page-agent/tree/main/packages/mcp"
target="_blank"
rel="noopener noreferrer"
className="underline hover:text-foreground"
>
MCP server package
</a>
.
</p>
</div>
<HubConfig />
<ProtocolDocsCollapsible />
</div>
<div className="border-t px-5 py-3 text-[10px] text-muted-foreground/60 flex items-center justify-between">
<span className="font-mono">v{__VERSION__}</span>
<span>
Built with by{' '}
<a
href="https://github.com/gaomeng1900"
target="_blank"
rel="noopener noreferrer"
className="underline hover:text-foreground"
>
@Simon
</a>
</span>
</div>
</aside>
{/* Right — Live session */}
<main className="flex-1 flex flex-col min-w-0 relative">
<MotionOverlay active={isRunning} />
<header className="flex items-center justify-between border-b px-5 h-12">
<div className="flex items-center gap-2 text-xs text-muted-foreground">
<WsIcon className="size-3.5" />
<span>{wsLabel}</span>
</div>
<div className="flex items-center gap-3">
<StatusDot status={status} />
{isRunning && (
<Button variant="destructive" size="sm" onClick={stop} className="h-7 text-xs">
<Square className="size-3 mr-1" />
Stop
</Button>
)}
</div>
</header>
{/* Task banner */}
{currentTask && (
<div className="border-b px-5 py-2 bg-muted/30">
<div className="text-[10px] text-muted-foreground uppercase tracking-wide">
Current Task
</div>
<div className="text-sm font-medium truncate" title={currentTask}>
{currentTask}
</div>
</div>
)}
{/* Event stream */}
<div ref={historyRef} className="flex-1 overflow-y-auto p-5 space-y-2">
{!currentTask && history.length === 0 && !isRunning && (
<div className="flex flex-col items-center justify-center h-full text-muted-foreground gap-3">
<WsIcon className="size-10 opacity-30" />
<p className="text-sm">
{wsState === 'connected'
? 'Waiting for task from external caller…'
: 'No active session'}
</p>
</div>
)}
{history.map((event, index) => (
// eslint-disable-next-line react-x/no-array-index-key
<EventCard key={index} event={event} />
))}
{activity && <ActivityCard activity={activity} />}
</div>
</main>
</div>
)
}
function HubConfig() {
const [allowAll, setAllowAll] = useState(false)
useEffect(() => {
chrome.storage.local.get('allowAllHubConnection').then((r) => {
setAllowAll(r.allowAllHubConnection === true)
})
}, [])
const toggle = (checked: boolean) => {
setAllowAll(checked)
chrome.storage.local.set({ allowAllHubConnection: checked })
}
return (
<div>
<h3 className="text-[11px] font-semibold text-foreground/80 uppercase tracking-wider mb-2">
Config
</h3>
<div className="group/hub relative">
<label
className={`flex items-center justify-between p-3 rounded-md border cursor-pointer text-xs ${allowAll ? 'bg-amber-500/10 border-amber-500/30 text-amber-600' : 'bg-muted/50 text-muted-foreground'}`}
>
Auto-approve connections
<Switch
checked={allowAll}
onCheckedChange={toggle}
className={allowAll ? 'data-[state=checked]:bg-amber-500' : ''}
/>
</label>
{/* hide with invisible absolute opacity-0*/}
<div className="group-hover/hub:visible group-hover/hub:opacity-100 transition-opacity duration-150 left-0 right-0 top-full z-10 pt-2">
<div className="relative p-2.5 rounded-md border border-border bg-background/60 backdrop-blur-md shadow-2xl text-muted-foreground text-xs leading-relaxed">
<div className="absolute -top-1.5 left-5 size-3 rotate-45 rounded-[1px] border-l border-t border-border bg-background/60 backdrop-blur-md" />
By default, each connection requires your approval before running tasks. <br />
Enable this to skip per-session approval.
<br />
<span className="font-semibold">* Use with caution!</span>
</div>
</div>
</div>
</div>
)
}
function ProtocolDocsCollapsible() {
const [open, setOpen] = useState(false)
return (
<div>
<button
type="button"
onClick={() => setOpen(!open)}
className="flex items-center gap-1 text-[11px] font-semibold text-foreground/80 uppercase tracking-wider cursor-pointer"
>
Docs
{open ? <FoldVertical className="size-3" /> : <UnfoldVertical className="size-3" />}
</button>
{open && (
<div className="mt-3 space-y-4 text-xs text-muted-foreground">
<p className="text-[10px]">
Connect via <code className="text-[10px]">hub.html?ws=PORT</code>
</p>
<section>
<h4 className="text-[11px] font-medium text-foreground/60 mb-1.5">Flow</h4>
<ol className="list-decimal list-inside space-y-1 text-[11px] leading-relaxed">
<li>Hub opens WS to caller's server</li>
<li>
Sends <code className="text-[10px]">ready</code>
</li>
<li>
Caller sends <code className="text-[10px]">execute</code> with task
</li>
<li>Hub runs agent, streams events</li>
<li>
Hub sends <code className="text-[10px]">result</code> or{' '}
<code className="text-[10px]">error</code>
</li>
</ol>
</section>
<section>
<h4 className="text-[11px] font-medium text-foreground/60 mb-1.5">Caller Hub</h4>
<pre className="bg-muted/50 rounded-md p-3 font-mono text-[10px] leading-relaxed whitespace-pre-wrap">
{`{ type: "execute", task: string, config?: object }
{ type: "stop" }`}
</pre>
</section>
<section>
<h4 className="text-[11px] font-medium text-foreground/60 mb-1.5">Hub Caller</h4>
<pre className="bg-muted/50 rounded-md p-3 font-mono text-[10px] leading-relaxed whitespace-pre-wrap">
{`{ type: "ready" }
{ type: "result", success: boolean, data: string }
{ type: "error", message: string }`}
</pre>
</section>
</div>
)}
</div>
)
}
@@ -0,0 +1,243 @@
/**
* Hub WebSocket Protocol
*
* Hub connects as WS client to `ws://localhost:{port}`.
* All messages are JSON. One task at a time.
*
* Inbound (Caller → Hub):
* { type: "execute", task: string, config?: object }
* { type: "stop" }
*
* Outbound (Hub → Caller):
* { type: "ready" }
* { type: "result", success: boolean, data: string }
* { type: "error", message: string }
*/
import type { ExecutionResult } from '@page-agent/core'
import { useEffect, useRef, useState } from 'react'
import type { ExtConfig } from '@/agent/useAgent'
// --- Protocol types ---
interface ExecuteMessage {
type: 'execute'
task: string
config?: Record<string, unknown>
}
interface StopMessage {
type: 'stop'
}
type InboundMessage = ExecuteMessage | StopMessage
interface ReadyMessage {
type: 'ready'
}
interface ResultMessage {
type: 'result'
success: boolean
data: string
}
interface ErrorMessage {
type: 'error'
message: string
}
type OutboundMessage = ReadyMessage | ResultMessage | ErrorMessage
export type HubWsState = 'connecting' | 'connected' | 'disconnected'
// --- HubWs class ---
export interface HubWsHandlers {
onExecute: (
task: string,
config?: Record<string, unknown>
) => Promise<{ success: boolean; data: string }>
onStop: () => void
}
/**
* Framework-agnostic WebSocket client for Hub.
* Connects to an external WS server, receives tasks, dispatches to handlers,
* and sends results back. No React, no DOM.
*/
export class HubWs {
#ws: WebSocket | null = null
#state: HubWsState = 'disconnected'
#busy = false
#approved = false
#handlers: HubWsHandlers
#port: number
#onStateChange: (state: HubWsState) => void
constructor(port: number, handlers: HubWsHandlers, onStateChange: (state: HubWsState) => void) {
this.#port = port
this.#handlers = handlers
this.#onStateChange = onStateChange
}
get state() {
return this.#state
}
get busy() {
return this.#busy
}
connect() {
if (this.#ws) return
this.#setState('connecting')
const ws = new WebSocket(`ws://localhost:${this.#port}`)
this.#ws = ws
ws.addEventListener('open', () => {
this.#setState('connected')
this.#send({ type: 'ready' })
})
ws.addEventListener('close', () => {
this.#ws = null
this.#busy = false
this.#approved = false
this.#setState('disconnected')
})
ws.addEventListener('message', (event) => {
this.#handleMessage(event.data as string)
})
}
disconnect() {
this.#ws?.close()
this.#ws = null
this.#busy = false
this.#approved = false
this.#setState('disconnected')
}
#setState(state: HubWsState) {
if (this.#state === state) return
this.#state = state
this.#onStateChange(state)
}
#send(msg: OutboundMessage) {
if (this.#ws?.readyState === WebSocket.OPEN) {
this.#ws.send(JSON.stringify(msg))
}
}
async #handleMessage(raw: string) {
let msg: InboundMessage
try {
msg = JSON.parse(raw)
} catch {
return
}
if (!(await this.#checkApproval())) {
this.#send({ type: 'error', message: 'User denied the connection request.' })
return
}
switch (msg.type) {
case 'execute':
this.#handleExecute(msg)
break
case 'stop':
this.#handlers.onStop()
break
}
}
async #checkApproval(): Promise<boolean> {
if (this.#approved) return true
const { allowAllHubConnection } = await chrome.storage.local.get('allowAllHubConnection')
if (allowAllHubConnection === true) {
this.#approved = true
return true
}
const ok = window.confirm(
'An external application is requesting to control your browser via Page Agent Ext.\nAllow this session?'
)
if (ok) this.#approved = true
return ok
}
async #handleExecute(msg: ExecuteMessage) {
if (this.#busy) {
this.#send({ type: 'error', message: 'Hub is busy with another task' })
return
}
this.#busy = true
try {
const result = await this.#handlers.onExecute(msg.task, msg.config)
this.#send({ type: 'result', success: result.success, data: result.data })
} catch (err) {
this.#send({ type: 'error', message: err instanceof Error ? err.message : String(err) })
} finally {
this.#busy = false
}
}
}
// --- React hook ---
/**
* React hook that bridges HubWs to the agent's execute/stop/configure.
* Handles the config-before-execute dance internally.
*/
export function useHubWs(
execute: (task: string) => Promise<ExecutionResult>,
stop: () => void,
configure: (config: ExtConfig) => Promise<void>,
config: ExtConfig | null
): { wsState: HubWsState } {
const wsPort = new URLSearchParams(location.search).get('ws')
const [wsState, setWsState] = useState<HubWsState>(() => (wsPort ? 'connecting' : 'disconnected'))
const hubWsRef = useRef<HubWs | null>(null)
const latest = useRef({ execute, stop, configure, config })
useEffect(() => {
latest.current = { execute, stop, configure, config }
})
useEffect(() => {
if (!wsPort) return
const hubWs = new HubWs(
Number(wsPort),
{
onExecute: async (task, incomingConfig) => {
const { execute, configure, config } = latest.current
if (incomingConfig) {
await configure({ ...config, ...incomingConfig } as ExtConfig)
}
const result = await execute(task)
return { success: result.success, data: result.data }
},
onStop: () => latest.current.stop(),
},
setWsState
)
hubWs.connect()
hubWsRef.current = hubWs
return () => {
hubWs.disconnect()
hubWsRef.current = null
}
}, [wsPort])
return { wsState }
}
@@ -0,0 +1,13 @@
<!doctype html>
<html>
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="icon" type="image/png" href="/assets/page-agent-64.png" />
<title>Page Agent Hub</title>
</head>
<body>
<div id="root"></div>
<script type="module" src="./main.tsx"></script>
</body>
</html>
@@ -0,0 +1,25 @@
import React from 'react'
import ReactDOM from 'react-dom/client'
import { ErrorBoundary } from '@/components/ErrorBoundary'
import App from './App'
import '@/assets/index.css'
const syncDarkMode = () => {
document.documentElement.classList.toggle(
'dark',
matchMedia('(prefers-color-scheme: dark)').matches
)
}
syncDarkMode()
matchMedia('(prefers-color-scheme: dark)').addEventListener('change', syncDarkMode)
ReactDOM.createRoot(document.getElementById('root')!).render(
<React.StrictMode>
<ErrorBoundary>
<App />
</ErrorBoundary>
</React.StrictMode>
)
@@ -4,8 +4,8 @@ export type Execute = (task: string, config: ExecuteConfig) => Promise<Execution
export interface ExecuteConfig {
baseURL: string
apiKey: string
model: string
apiKey?: string
/**
* Whether to include the initial tab (that holds this main world script) in the task.
@@ -30,7 +30,6 @@ export default defineUnlistedScript(() => {
if (task.trim().length === 0) throw new Error('Task cannot be empty')
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()
@@ -85,8 +84,8 @@ export default defineUnlistedScript(() => {
task,
config: {
baseURL: config.baseURL,
apiKey: config.apiKey,
model: config.model,
apiKey: config.apiKey,
includeInitialTab: config.includeInitialTab,
},
},
@@ -1,6 +1,11 @@
import { History, Send, Settings, Square } from 'lucide-react'
import { useCallback, useEffect, useRef, useState } from 'react'
import { ConfigPanel } from '@/components/ConfigPanel'
import { HistoryDetail } from '@/components/HistoryDetail'
import { HistoryList } from '@/components/HistoryList'
import { ActivityCard, EventCard } from '@/components/cards'
import { EmptyState, Logo, MotionOverlay, StatusDot } from '@/components/misc'
import { Button } from '@/components/ui/button'
import {
InputGroup,
@@ -11,11 +16,6 @@ import {
import { saveSession } from '@/lib/db'
import { useAgent } from '../../agent/useAgent'
import { ConfigPanel } from './components/ConfigPanel'
import { HistoryDetail } from './components/HistoryDetail'
import { HistoryList } from './components/HistoryList'
import { ActivityCard, EventCard } from './components/cards'
import { EmptyState, Logo, MotionOverlay, StatusDot } from './components/misc'
type View =
| { name: 'chat' }
@@ -56,19 +56,27 @@ export default function App() {
}
}, [history, activity])
const handleSubmit = useCallback(
(e?: React.SyntheticEvent) => {
e?.preventDefault()
if (!inputValue.trim() || status === 'running') return
const runTask = useCallback(
(task: string) => {
const normalizedTask = task.trim()
if (!normalizedTask || status === 'running') return
const taskToExecute = inputValue.trim()
setInputValue('')
setView({ name: 'chat' })
execute(taskToExecute).catch((error) => {
execute(normalizedTask).catch((error) => {
console.error('[SidePanel] Failed to execute task:', error)
})
},
[inputValue, status, execute]
[execute, status]
)
const handleSubmit = useCallback(
(e?: React.SyntheticEvent) => {
e?.preventDefault()
runTask(inputValue)
},
[inputValue, runTask]
)
const handleStop = useCallback(() => {
@@ -103,12 +111,19 @@ export default function App() {
<HistoryList
onSelect={(id) => setView({ name: 'history-detail', sessionId: id })}
onBack={() => setView({ name: 'chat' })}
onRerun={runTask}
/>
)
}
if (view.name === 'history-detail') {
return <HistoryDetail sessionId={view.sessionId} onBack={() => setView({ name: 'history' })} />
return (
<HistoryDetail
sessionId={view.sessionId}
onBack={() => setView({ name: 'history' })}
onRerun={runTask}
/>
)
}
// --- Chat view ---
@@ -1,8 +1,9 @@
import React from 'react'
import ReactDOM from 'react-dom/client'
import { ErrorBoundary } from '@/components/ErrorBoundary'
import App from './App'
import { ErrorBoundary } from './components/ErrorBoundary'
import '@/assets/index.css'
@@ -0,0 +1,60 @@
import type { HistoricalEvent } from '@page-agent/core'
const EXPORT_FILE_PREFIX = 'page-agent-history'
const MAX_TASK_SLUG_LENGTH = 40
export function serializeHistoryExport(history: HistoricalEvent[]): string {
return `${JSON.stringify(history, null, 2)}\n`
}
export function buildHistoryExportFilename(task: string, createdAt: number): string {
const taskSlug = sanitizeTaskForFilename(task)
const timestamp = formatTimestampForFilename(createdAt)
return taskSlug
? `${EXPORT_FILE_PREFIX}-${taskSlug}-${timestamp}.json`
: `${EXPORT_FILE_PREFIX}-${timestamp}.json`
}
export function downloadHistoryExport(
task: string,
createdAt: number,
history: HistoricalEvent[]
): void {
const filename = buildHistoryExportFilename(task, createdAt)
const content = serializeHistoryExport(history)
const blob = new Blob([content], { type: 'application/json;charset=utf-8' })
const url = URL.createObjectURL(blob)
const link = document.createElement('a')
link.href = url
link.download = filename
link.click()
URL.revokeObjectURL(url)
}
function sanitizeTaskForFilename(task: string): string {
return task
.trim()
.toLowerCase()
.replace(/[^a-z0-9]+/g, '-')
.replace(/^-+|-+$/g, '')
.slice(0, MAX_TASK_SLUG_LENGTH)
}
function formatTimestampForFilename(createdAt: number): string {
const date = new Date(createdAt)
const year = date.getFullYear()
const month = pad(date.getMonth() + 1)
const day = pad(date.getDate())
const hours = pad(date.getHours())
const minutes = pad(date.getMinutes())
const seconds = pad(date.getSeconds())
return `${year}-${month}-${day}_${hours}-${minutes}-${seconds}`
}
function pad(value: number): string {
return value.toString().padStart(2, '0')
}
+4
View File
@@ -40,6 +40,7 @@ export default defineConfig({
artifactTemplate: 'page-agent-ext-{{version}}-{{browser}}.zip',
},
manifest: {
key: 'MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAqbzT0iTYeYlnCvDJIGDnGU8oarJgZILDzSfLi/ufuSxXEPDKuMyD892GhvrMCZNVHS11Sh6NYUOc/PcUOhtaR2urHtcNkrpSJNV10zUamY7fxBdVEkOucfyLu8INVy+teis62MoRWYPaUPkfZUjrLGW8MsZ9aFzARfu9GGDEp2EAYsWDN6w6vyz9LJ82pm542EWnVT4MjmDPgvYFCWGBtaU/dfHD+GAX6URJFapsCvryVURKJ+76c/GO9/I3EX1IBfbY6dec78bLCMvVxiTmiv36KyGPwX1OpakW8IiCpXWdbAxjm+plbYlp5t5zTyyoE3sOSFeXsBH0Kg27o8GcvQIDAQAB',
default_locale: 'en',
name: '__MSG_extName__',
description: '__MSG_extDescription__',
@@ -61,5 +62,8 @@ export default defineConfig({
side_panel: {
default_path: 'sidepanel/index.html',
},
externally_connectable: {
matches: ['http://localhost/*'],
},
},
})
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/llms",
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"main": "./dist/lib/page-agent-llms.js",
"module": "./dist/lib/page-agent-llms.js",
+8 -5
View File
@@ -29,16 +29,19 @@ export class OpenAIClient implements LLMClient {
const openaiTools = Object.entries(tools).map(([name, t]) => zodToOpenAITool(name, t))
// Build request body
let toolChoice: unknown = 'required'
if (options?.toolChoiceName && !this.config.disableNamedToolChoice) {
toolChoice = { type: 'function', function: { name: options.toolChoiceName } }
}
const requestBody: Record<string, unknown> = {
model: this.config.model,
temperature: this.config.temperature,
messages,
tools: openaiTools,
parallel_tool_calls: false,
// Require tool call: specific tool if provided, otherwise any tool
tool_choice: options?.toolChoiceName
? { type: 'function', function: { name: options.toolChoiceName } }
: 'required',
tool_choice: toolChoice,
}
modelPatch(requestBody)
@@ -50,7 +53,7 @@ export class OpenAIClient implements LLMClient {
method: 'POST',
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${this.config.apiKey}`,
...(this.config.apiKey && { Authorization: `Bearer ${this.config.apiKey}` }),
},
body: JSON.stringify(requestBody),
signal: abortSignal,
+4 -3
View File
@@ -8,19 +8,20 @@ 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) {
if (!config.baseURL || !config.model) {
throw new Error(
'[PageAgent] LLM configuration required. Please provide: baseURL, apiKey, model. ' +
'[PageAgent] LLM configuration required. Please provide: baseURL, model. ' +
'See: https://alibaba.github.io/page-agent/docs/features/models'
)
}
return {
baseURL: config.baseURL,
apiKey: config.apiKey,
model: config.model,
apiKey: config.apiKey || '',
temperature: config.temperature ?? DEFAULT_TEMPERATURE,
maxRetries: config.maxRetries ?? LLM_MAX_RETRIES,
disableNamedToolChoice: config.disableNamedToolChoice ?? false,
customFetch: (config.customFetch ?? fetch).bind(globalThis), // fetch will be illegal unless bound
}
}
+7 -1
View File
@@ -89,12 +89,18 @@ export interface InvokeResult<TResult = unknown> {
*/
export interface LLMConfig {
baseURL: string
apiKey: string
model: string
apiKey?: string
temperature?: number
maxRetries?: number
/**
* remove the tool_choice field from the request.
* @note fix "Invalid tool_choice type: 'object'" for some LLMs.
*/
disableNamedToolChoice?: boolean
/**
* Custom fetch function for LLM API requests.
* Use this to customize headers, credentials, proxy, etc.
+9
View File
@@ -93,6 +93,15 @@ export function modelPatch(body: Record<string, any>) {
body.reasoning_effort = 'minimal'
}
if (modelName.startsWith('minimax')) {
debug('Applying MiniMax patch: clamp temperature to (0, 1]')
// MiniMax API rejects temperature = 0; clamp to a small positive value
body.temperature = Math.max(body.temperature || 0, 0.01)
if (body.temperature > 1) body.temperature = 1
// MiniMax does not support parallel_tool_calls
delete body.parallel_tool_calls
}
return body
}
+94
View File
@@ -0,0 +1,94 @@
# @page-agent/mcp
MCP server that lets AI agent clients (Claude Desktop, Copilot, etc.) control your browser through the [Page Agent](https://github.com/alibaba/page-agent) extension.
## Prerequisites
- Node.js >= 20
- [Page Agent Extension](https://chromewebstore.google.com/detail/page-agent-ext/akldabonmimlicnjlflnapfeklbfemhj) installed in Chrome
- An LLM API key (OpenAI-compatible)
## Installation
### Claude Desktop
Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:
```json
{
"mcpServers": {
"page-agent": {
"command": "npx",
"args": ["-y", "@page-agent/mcp"],
"env": {
"LLM_BASE_URL": "https://dashscope.aliyuncs.com/compatible-mode/v1",
"LLM_API_KEY": "sk-xxx",
"LLM_MODEL_NAME": "qwen3.5-plus"
}
}
}
}
```
### Cursor / Copilot
Same format — add the config to the MCP settings of your client.
## MCP Tools
| Tool | Input | Description |
| -------------- | ------------------ | ---------------------------------------------------- |
| `execute_task` | `{ task: string }` | Execute a browser task in natural language. Blocking. |
| `get_status` | — | Returns `{ connected, busy }` |
| `stop_task` | — | Stop the currently running task. |
## Environment Variables
| Variable | Default | Description |
| ---------------- | ------- | --------------------- |
| `LLM_BASE_URL` | — | LLM API base URL |
| `LLM_API_KEY` | — | LLM API key |
| `LLM_MODEL_NAME` | — | Model name |
| `PORT` | `38401` | HTTP + WebSocket port |
## How It Works
```
┌──────────────┐ stdio ┌──────────────────┐ WebSocket ┌──────────────┐
│ Claude / │◄────────►│ @page-agent/mcp │◄────────────►│ Hub tab │
│ Copilot │ (MCP) │ (Node.js) │ (localhost) │ (extension) │
└──────────────┘ └──────────────────┘ └──────┬───────┘
│ │
│ HTTP │ useAgent
▼ ▼
┌──────────────────┐ ┌──────────────┐
│ Launcher page │ │ MultiPage │
│ (localhost:PORT) │ │ Agent │
└──────────────────┘ └──────────────┘
```
1. Agent client starts the MCP server via stdio (`npx @page-agent/mcp`).
2. Server starts HTTP + WS on `localhost:PORT`, opens the launcher page in browser.
3. Launcher page triggers the extension to open a **hub tab** (`hub.html?ws=PORT`).
4. Hub connects to the WS server. MCP tools now proxy tasks to the hub.
The hub tab speaks a generic WebSocket protocol (defined in `hub-ws.ts` in the extension package) and has no knowledge of MCP. See the hub's protocol docs for message format details.
## Architecture
Pure JS ESM, no build step. Source files are the published artifacts.
```
src/
├── index.js # CLI entry: MCP server (stdio) + opens launcher
├── hub-bridge.js # HTTP server + WebSocket bridge to hub tab
└── launcher.html # Bootstrap page: detects extension, triggers hub open
```
## Dev
```bash
npm run build:libs
npm run dev:ext
npx @modelcontextprotocol/inspector node packages/mcp/src/index.js
```
+35
View File
@@ -0,0 +1,35 @@
{
"name": "@page-agent/mcp",
"private": false,
"version": "1.6.0",
"type": "module",
"bin": {
"page-agent-mcp": "src/index.js"
},
"files": [
"src/"
],
"description": "MCP server for controlling the browser via Page Agent extension",
"keywords": [
"page-agent",
"mcp",
"browser-automation",
"chrome-extension"
],
"author": "Simon<gaomeng1900>",
"license": "MIT",
"repository": {
"type": "git",
"url": "https://github.com/alibaba/page-agent.git",
"directory": "packages/mcp"
},
"homepage": "https://alibaba.github.io/page-agent/",
"engines": {
"node": ">=20"
},
"dependencies": {
"@modelcontextprotocol/sdk": "^1.27.1",
"ws": "^8.19.0",
"zod": "^4.3.5"
}
}
+138
View File
@@ -0,0 +1,138 @@
#!/usr/bin/env node
import { readFileSync } from 'node:fs'
import http from 'node:http'
import { fileURLToPath } from 'node:url'
import { WebSocketServer } from 'ws'
const EXT_ID = 'akldabonmimlicnjlflnapfeklbfemhj'
const STORE_URL = `https://chromewebstore.google.com/detail/page-agent-ext/${EXT_ID}`
const launcherTemplate = readFileSync(
fileURLToPath(new URL('./launcher.html', import.meta.url)),
'utf-8'
)
/**
* HTTP + WebSocket bridge to the hub.html extension tab.
* - HTTP serves the launcher page (triggers extension to open hub)
* - WS carries execute/stop commands and result/error responses
*/
export class HubBridge {
/** @type {number} */
port
/** @type {http.Server} */
#httpServer
/** @type {WebSocketServer} */
#wss
/** @type {import('ws').WebSocket | null} */
#hub = null
/** @type {{ resolve: (r: {success: boolean, data: string}) => void, reject: (e: Error) => void } | null} */
#pendingTask = null
/** @param {number} port */
constructor(port) {
this.port = port
this.#httpServer = http.createServer((_req, res) => {
const html = launcherTemplate
.replaceAll('__EXT_ID__', EXT_ID)
.replaceAll('__STORE_URL__', STORE_URL)
.replaceAll('__WS_PORT__', String(port))
res.writeHead(200, { 'Content-Type': 'text/html; charset=utf-8' })
res.end(html)
})
this.#wss = new WebSocketServer({ server: this.#httpServer })
this.#wss.on('connection', (ws) => this.#onConnection(ws))
}
/** @returns {Promise<void>} */
async start() {
return new Promise((resolve, reject) => {
this.#httpServer.on('error', (/** @type {NodeJS.ErrnoException} */ err) => {
if (err.code === 'EADDRINUSE') {
reject(
new Error(`Port ${this.port} is in use. Another Page Agent MCP server may be running.`)
)
} else {
reject(err)
}
})
this.#httpServer.listen(this.port, () => {
console.error(`[page-agent-mcp] HTTP + WS on http://localhost:${this.port}`)
resolve()
})
})
}
get connected() {
return this.#hub?.readyState === 1
}
get busy() {
return this.#pendingTask !== null
}
/**
* @param {string} task
* @param {Record<string, unknown>} [config]
* @returns {Promise<{success: boolean, data: string}>}
*/
async executeTask(task, config) {
if (!this.connected) throw new Error('Hub is not connected. Is the extension running?')
if (this.#pendingTask) throw new Error('Agent is already running a task.')
return new Promise((resolve, reject) => {
this.#pendingTask = { resolve, reject }
this.#hub.send(JSON.stringify({ type: 'execute', task, config }))
})
}
stopTask() {
if (this.connected) {
this.#hub.send(JSON.stringify({ type: 'stop' }))
}
}
// TODO: Add version checking
/** @param {import('ws').WebSocket} ws */
#onConnection(ws) {
if (this.#hub && this.#hub.readyState === 1) {
ws.close(4000, 'Another hub is already connected')
return
}
this.#hub = ws
console.error('[page-agent-mcp] Hub connected')
ws.on('message', (/** @type {Buffer} */ rawData) => {
/** @type {{ type: string, success?: boolean, data?: string, message?: string }} */
let msg
try {
msg = JSON.parse(rawData.toString('utf-8'))
} catch {
return
}
if (msg.type === 'result') {
this.#pendingTask?.resolve({ success: msg.success ?? false, data: msg.data ?? '' })
this.#pendingTask = null
} else if (msg.type === 'error') {
this.#pendingTask?.reject(new Error(msg.message ?? 'Unknown error from hub'))
this.#pendingTask = null
}
})
ws.on('close', () => {
console.error('[page-agent-mcp] Hub disconnected')
if (this.#hub === ws) this.#hub = null
if (this.#pendingTask) {
this.#pendingTask.reject(new Error('Hub disconnected while task was running'))
this.#pendingTask = null
}
})
}
}
+95
View File
@@ -0,0 +1,95 @@
#!/usr/bin/env node
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
import { exec } from 'node:child_process'
import { platform } from 'node:os'
import * as z from 'zod/v4'
import { HubBridge } from './hub-bridge.js'
const env = process.env
const port = parseInt(env.PORT || '38401')
/** @type {Record<string, string>} */
const llmConfig = {}
if (env.LLM_BASE_URL) llmConfig.baseURL = env.LLM_BASE_URL
if (env.LLM_MODEL_NAME) llmConfig.model = env.LLM_MODEL_NAME
if (env.LLM_API_KEY) llmConfig.apiKey = env.LLM_API_KEY
// --- Hub bridge (HTTP + WebSocket) ---
const hub = new HubBridge(port)
await hub.start()
// Open launcher in default browser
const url = `http://localhost:${port}`
const cmd = platform() === 'darwin' ? 'open' : platform() === 'win32' ? 'start ""' : 'xdg-open'
exec(`${cmd} "${url}"`, (err) => {
if (err) console.error(`[page-agent-mcp] Could not open browser: ${err.message}`)
})
// --- MCP server (stdio) ---
const mcpServer = new McpServer({ name: 'page-agent', version: '1.5.8' })
mcpServer.registerTool(
'execute_task',
{
description:
'Execute a browser automation task described in natural language. ' +
'The Page Agent extension will control the browser to complete the task. ' +
'Blocks until the task is complete.',
inputSchema: { task: z.string().describe('Task description in natural language') },
},
async ({ task }) => {
try {
const config = Object.keys(llmConfig).length > 0 ? llmConfig : undefined
const result = await hub.executeTask(task, config)
return {
content: [
{
type: 'text',
text: result.success
? `Task completed successfully.\n\n${result.data}`
: `Task failed.\n\n${result.data}`,
},
],
}
} catch (err) {
return {
content: [{ type: 'text', text: `Error: ${err.message}` }],
isError: true,
}
}
}
)
mcpServer.registerTool(
'get_status',
{
description: 'Check the current status of the Page Agent hub connection and agent.',
},
async () => ({
content: [
{
type: 'text',
text: JSON.stringify({ connected: hub.connected, busy: hub.busy }, null, 2),
},
],
})
)
mcpServer.registerTool(
'stop_task',
{
description: 'Stop the currently running browser automation task.',
},
async () => {
hub.stopTask()
return { content: [{ type: 'text', text: 'Stop signal sent.' }] }
}
)
const transport = new StdioServerTransport()
await mcpServer.connect(transport)
console.error('[page-agent-mcp] MCP server ready (stdio)')
+237
View File
@@ -0,0 +1,237 @@
<!doctype html>
<html>
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="icon" href="https://img.alicdn.com/imgextra/i1/O1CN01mRGret1QrKiu7CFJI_!!6000000002029-2-tps-64-64.png" />
<title>Page Agent MCP Launcher</title>
<style>
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family:
system-ui,
-apple-system,
sans-serif;
background: #09090b;
color: #e5e5e5;
display: flex;
align-items: center;
justify-content: center;
min-height: 100vh;
}
.card {
text-align: center;
max-width: 480px;
padding: 3rem 2rem;
}
.logo {
width: 72px;
height: 72px;
border-radius: 18px;
margin-bottom: 1rem;
}
.badge {
font-size: 0.6875rem;
font-weight: 500;
color: #52525b;
letter-spacing: 0.05em;
text-transform: uppercase;
margin-bottom: 1.5rem;
}
h1 {
font-size: 1.35rem;
font-weight: 600;
margin-bottom: 0.5rem;
}
.sub {
font-size: 0.875rem;
color: #a1a1aa;
line-height: 1.7;
}
.spinner {
width: 32px;
height: 32px;
border: 3px solid #27272a;
border-top-color: #fff;
border-radius: 50%;
animation: spin 0.8s linear infinite;
margin: 0 auto 1.5rem;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
a {
color: #60a5fa;
text-decoration: none;
}
a:hover {
text-decoration: underline;
}
.install {
display: none;
}
.install.show {
display: block;
}
.tips {
margin-top: 1.75rem;
text-align: left;
background: #18181b;
border: 1px solid #27272a;
border-radius: 12px;
padding: 1.25rem 1.5rem;
}
.tips li {
font-size: 0.8125rem;
color: #a1a1aa;
line-height: 1.7;
margin-left: 1rem;
}
.tips li + li {
margin-top: 0.35rem;
}
.store-btn {
display: inline-flex;
align-items: center;
gap: 0.625rem;
margin-top: 1.5rem;
padding: 0.625rem 1.5rem;
background: #2563eb;
color: #fff;
border-radius: 10px;
font-size: 0.875rem;
font-weight: 500;
transition: background 0.15s;
}
.store-btn:hover {
background: #1d4ed8;
text-decoration: none;
}
.store-btn img {
width: 20px;
height: 20px;
}
.links {
margin-top: 1.75rem;
display: flex;
justify-content: center;
gap: 1.5rem;
font-size: 0.8125rem;
}
.links a {
color: #71717a;
transition: color 0.15s;
}
.links a:hover {
color: #a1a1aa;
text-decoration: none;
}
</style>
</head>
<body>
<div class="card">
<img
class="logo"
src="https://img.alicdn.com/imgextra/i3/O1CN01JPT4Fj1FJTfmHfNxO_!!6000000000466-49-tps-512-512.webp"
alt="Page Agent"
/>
<div class="badge">Page Agent MCP Launcher</div>
<div id="connecting">
<div class="spinner"></div>
<h1 data-i18n="connecting_title">Connecting to Page Agent</h1>
<p class="sub" data-i18n="connecting_sub">Opening the hub in your browser…</p>
</div>
<div id="install" class="install">
<h1 data-i18n="install_title">Extension Required</h1>
<p class="sub" data-i18n="install_sub">
Page Agent requires the latest browser extension to work.
</p>
<a class="store-btn" href="__STORE_URL__" target="_blank">
<img
src="https://img.alicdn.com/imgextra/i3/O1CN01JpW0Vo1sR3FpiZKFM_!!6000000005762-55-tps-192-192.svg"
alt=""
/>
<span data-i18n="install_btn">Install from Chrome Web Store</span>
</a>
<ul class="tips">
<li data-i18n="tip_outdated">
If the extension is outdated, please update it to the latest version.
</li>
<li data-i18n="tip_other_browser">
If the extension is not installed in this browser, open this page from the
browser that has it installed.
</li>
<li data-i18n="tip_refresh">Refresh this page after installing or updating.</li>
</ul>
</div>
<div class="links">
<a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank" data-i18n="link_docs">Docs</a>
<a href="https://github.com/alibaba/page-agent/issues" target="_blank" data-i18n="link_issues">Report an Issue</a>
</div>
</div>
<script>
{
const EXT_ID = '__EXT_ID__'
const wsPort = __WS_PORT__
const zh = {
connecting_title: '正在连接 Page Agent',
connecting_sub: '正在浏览器中打开 Hub…',
install_title: '需要安装浏览器插件',
install_sub: 'Page Agent 需要安装最新版浏览器插件才能运行。',
install_btn: '从 Chrome 应用商店安装',
tip_outdated: '如果插件版本过旧,请更新到最新版本。',
tip_other_browser:
'如果该浏览器中未安装插件,请从装有插件的浏览器打开此页面。',
tip_refresh: '安装或更新后,请刷新此页面。',
link_docs: '文档',
link_issues: '问题反馈',
}
if (/^zh\b/i.test(navigator.language)) {
document.querySelectorAll('[data-i18n]').forEach((el) => {
const key = el.getAttribute('data-i18n')
if (zh[key]) el.textContent = zh[key]
})
}
const showInstall = () => {
document.getElementById('connecting').style.display = 'none'
document.getElementById('install').classList.add('show')
}
try {
if (!globalThis.chrome?.runtime?.sendMessage) {
showInstall()
} else {
chrome.runtime.sendMessage(
EXT_ID,
{ type: 'OPEN_HUB', wsPort },
(response) => {
if (chrome.runtime.lastError || !response?.ok) showInstall()
}
)
}
} catch {
showInstall()
}
}
</script>
</body>
</html>
+5 -5
View File
@@ -1,7 +1,7 @@
{
"name": "page-agent",
"private": false,
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"main": "./dist/esm/page-agent.js",
"module": "./dist/esm/page-agent.js",
@@ -44,10 +44,10 @@
"postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
},
"dependencies": {
"@page-agent/core": "1.5.8",
"@page-agent/llms": "1.5.8",
"@page-agent/page-controller": "1.5.8",
"@page-agent/ui": "1.5.8",
"@page-agent/core": "1.6.0",
"@page-agent/llms": "1.6.0",
"@page-agent/page-controller": "1.6.0",
"@page-agent/ui": "1.6.0",
"chalk": "^5.6.2"
},
"peerDependencies": {
+1 -1
View File
@@ -9,7 +9,7 @@ import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
const __dirname = dirname(fileURLToPath(import.meta.url))
// Load .env from repo root
dotenvConfig({ path: resolve(__dirname, '../../.env') })
dotenvConfig({ path: resolve(__dirname, '../../.env'), quiet: true })
// UMD Bundle for CDN
// - alias all local packages so that they can be build in
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/page-controller",
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"main": "./dist/lib/page-controller.js",
"module": "./dist/lib/page-controller.js",
@@ -18,6 +18,7 @@ import * as dom from './dom'
import type { FlatDomTree, InteractiveElementDomNode } from './dom/dom_tree/type'
import { getPageInfo } from './dom/getPageInfo'
import { patchReact } from './patches/react'
import { isAnchorElement } from './utils'
/**
* Configuration for PageController
@@ -243,7 +244,7 @@ export class PageController extends EventTarget {
await clickElement(element)
// Handle links that open in new tabs
if (element instanceof HTMLAnchorElement && element.target === '_blank') {
if (isAnchorElement(element) && element.target === '_blank') {
return {
success: true,
message: `✅ Clicked element (${elemText ?? index}). ⚠️ Link opened in a new tab.`,
+53 -51
View File
@@ -3,24 +3,15 @@
* All rights reserved.
*/
import type { InteractiveElementDomNode } from './dom/dom_tree/type'
// ======= general utils =======
async function waitFor(seconds: number): Promise<void> {
await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
}
// ======= dom utils =======
export async function movePointerToElement(element: HTMLElement) {
const rect = element.getBoundingClientRect()
const x = rect.left + rect.width / 2
const y = rect.top + rect.height / 2
window.dispatchEvent(new CustomEvent('PageAgent::MovePointerTo', { detail: { x, y } }))
await waitFor(0.3)
}
import {
getNativeValueSetter,
isHTMLElement,
isInputElement,
isSelectElement,
isTextAreaElement,
movePointerToElement,
waitFor,
} from './utils'
/**
* Get the HTMLElement by index from a selectorMap.
@@ -39,7 +30,7 @@ export function getElementByIndex(
throw new Error(`Element at index ${index} does not have a reference`)
}
if (!(element instanceof HTMLElement)) {
if (!isHTMLElement(element)) {
throw new Error(`Element at index ${index} is not an HTMLElement`)
}
@@ -54,6 +45,9 @@ function blurLastClickedElement() {
lastClickedElement.dispatchEvent(
new MouseEvent('mouseout', { bubbles: true, cancelable: true })
)
lastClickedElement.dispatchEvent(
new MouseEvent('mouseleave', { bubbles: false, cancelable: true })
)
lastClickedElement = null
}
}
@@ -65,9 +59,15 @@ export async function clickElement(element: HTMLElement) {
blurLastClickedElement()
lastClickedElement = element
await scrollIntoViewIfNeeded(element)
// Scroll the iframe element itself into view if needed
const frame = element.ownerDocument.defaultView?.frameElement
if (frame) await scrollIntoViewIfNeeded(frame)
await movePointerToElement(element)
window.dispatchEvent(new CustomEvent('PageAgent::ClickPointer'))
await waitFor(0.1)
// hover it
@@ -89,25 +89,9 @@ export async function clickElement(element: HTMLElement) {
await waitFor(0.2) // Wait to ensure click event processing completes
}
// eslint-disable-next-line @typescript-eslint/unbound-method
const nativeInputValueSetter = Object.getOwnPropertyDescriptor(
window.HTMLInputElement.prototype,
'value'
)!.set!
// eslint-disable-next-line @typescript-eslint/unbound-method
const nativeTextAreaValueSetter = Object.getOwnPropertyDescriptor(
window.HTMLTextAreaElement.prototype,
'value'
)!.set!
export async function inputTextElement(element: HTMLElement, text: string) {
const isContentEditable = element.isContentEditable
if (
!(element instanceof HTMLInputElement) &&
!(element instanceof HTMLTextAreaElement) &&
!isContentEditable
) {
if (!isInputElement(element) && !isTextAreaElement(element) && !isContentEditable) {
throw new Error('Element is not an input, textarea, or contenteditable')
}
@@ -119,9 +103,12 @@ export async function inputTextElement(element: HTMLElement, text: string) {
// - Monaco/CodeMirror: Require direct JS instance access. No universal way to obtain.
// - Draft.js: Not responsive to synthetic/execCommand/Range/DataTransfer. Unmaintained.
//
// Strategy: Try Plan A (synthetic events) first, then verify and fall back
// to Plan B (execCommand) if the text wasn't actually inserted.
//
// Plan A: Dispatch synthetic events
// Works: LinkedIn, React contenteditable, Quill.
// Fails: Slate.js
// Works: React contenteditable, Quill.
// Fails: Slate.js, some contenteditable editors that ignore synthetic events.
// Sequence: beforeinput -> mutation -> input -> change -> blur
// Dispatch beforeinput + mutation + input for clearing
@@ -164,22 +151,37 @@ export async function inputTextElement(element: HTMLElement, text: string) {
)
}
// Verify Plan A worked by checking if the text was actually inserted
const planASucceeded = element.innerText.trim() === text.trim()
if (!planASucceeded) {
// Plan B: execCommand fallback (deprecated but widely supported)
// Works: Quill, Slate.js, react contenteditable components.
// This approach integrates with the browser's undo stack and is handled
// natively by most rich-text editors.
element.focus()
// Select all existing content and delete it
const doc = element.ownerDocument
const selection = (doc.defaultView || window).getSelection()
const range = doc.createRange()
range.selectNodeContents(element)
selection?.removeAllRanges()
selection?.addRange(range)
// eslint-disable-next-line @typescript-eslint/no-deprecated
doc.execCommand('delete', false)
// eslint-disable-next-line @typescript-eslint/no-deprecated
doc.execCommand('insertText', false, text)
}
// Dispatch change event (for good measure)
element.dispatchEvent(new Event('change', { bubbles: true }))
// Trigger blur for validation
element.blur()
// Plan B: execCommand (deprecated but works better for some editors)
// Works: LinkedIn, Quill, Slate.js, react contenteditable components
//
// document.execCommand('selectAll')
// document.execCommand('delete')
// document.execCommand('insertText', false, text)
} else if (element instanceof HTMLTextAreaElement) {
nativeTextAreaValueSetter.call(element, text)
} else {
nativeInputValueSetter.call(element, text)
getNativeValueSetter(element as HTMLInputElement | HTMLTextAreaElement).call(element, text)
}
// Only dispatch shared input event for non-contenteditable (contenteditable has its own)
@@ -196,7 +198,7 @@ export async function inputTextElement(element: HTMLElement, text: string) {
* @todo browser-use version is very complex and supports menu tags, need to follow up
*/
export async function selectOptionElement(selectElement: HTMLSelectElement, optionText: string) {
if (!(selectElement instanceof HTMLSelectElement)) {
if (!isSelectElement(selectElement)) {
throw new Error('Element is not a select element')
}
@@ -213,11 +215,11 @@ export async function selectOptionElement(selectElement: HTMLSelectElement, opti
await waitFor(0.1) // Wait to ensure change event processing completes
}
interface ScrollableElement extends HTMLElement {
interface ScrollableElement extends Element {
scrollIntoViewIfNeeded?: (centerIfNeeded?: boolean) => void
}
export async function scrollIntoViewIfNeeded(element: HTMLElement) {
export async function scrollIntoViewIfNeeded(element: Element) {
const el = element as ScrollableElement
if (typeof el.scrollIntoViewIfNeeded === 'function') {
el.scrollIntoViewIfNeeded()
@@ -0,0 +1,62 @@
// ======= type guards =======
// @note instanceof fails for elements inside iframes
export function isHTMLElement(el: unknown): el is HTMLElement {
// @todo either specify to HTMLElement or allow Element here.
return !!el && (el as Node).nodeType === 1
}
export function isInputElement(el: Element): el is HTMLInputElement {
return el?.nodeType === 1 && el.tagName === 'INPUT'
}
export function isTextAreaElement(el: Element): el is HTMLTextAreaElement {
return el?.nodeType === 1 && el.tagName === 'TEXTAREA'
}
export function isSelectElement(el: Element): el is HTMLSelectElement {
return el?.nodeType === 1 && el.tagName === 'SELECT'
}
export function isAnchorElement(el: Element): el is HTMLAnchorElement {
return el?.nodeType === 1 && el.tagName === 'A'
}
// ======= iframe helpers =======
/** Iframe offset for translating element coordinates to top-frame viewport. */
export function getIframeOffset(element: HTMLElement): { x: number; y: number } {
const frame = element.ownerDocument.defaultView?.frameElement as HTMLElement | null
if (!frame) return { x: 0, y: 0 }
const rect = frame.getBoundingClientRect()
return { x: rect.left, y: rect.top }
}
/**
* Get native value setter from the element's own prototype (iframe-safe).
* @note for React
*/
export function getNativeValueSetter(element: HTMLInputElement | HTMLTextAreaElement) {
// eslint-disable-next-line @typescript-eslint/unbound-method
return Object.getOwnPropertyDescriptor(Object.getPrototypeOf(element) as object, 'value')!
.set as (v: string) => void
}
// ======= general utils =======
export async function waitFor(seconds: number): Promise<void> {
await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
}
// ======= dom utils =======
export async function movePointerToElement(element: HTMLElement) {
const rect = element.getBoundingClientRect()
const offset = getIframeOffset(element)
const x = rect.left + rect.width / 2 + offset.x
const y = rect.top + rect.height / 2 + offset.y
window.dispatchEvent(new CustomEvent('PageAgent::MovePointerTo', { detail: { x, y } }))
await waitFor(0.3)
}
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/ui",
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"main": "./dist/lib/page-agent-ui.js",
"module": "./dist/lib/page-agent-ui.js",
+3 -3
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/website",
"private": true,
"version": "1.5.8",
"version": "1.6.0",
"type": "module",
"scripts": {
"dev": "vite --host 0.0.0.0",
@@ -20,12 +20,12 @@
"class-variance-authority": "^0.7.1",
"clsx": "^2.1.1",
"lucide-react": "^0.577.0",
"motion": "^12.35.2",
"motion": "^12.37.0",
"next-themes": "^0.4.6",
"react": "^19.2.4",
"react-dom": "^19.2.4",
"rough-notation": "^0.5.1",
"simple-icons": "^16.11.0",
"simple-icons": "^16.12.0",
"sonner": "^2.0.7",
"tailwind-merge": "^3.5.0",
"tailwindcss": "^4.1.14",
+8 -7
View File
@@ -13,26 +13,27 @@ export default function Footer() {
<div className="max-w-7xl mx-auto px-6 py-6">
<div className="flex flex-col md:flex-row justify-between items-center space-y-4 md:space-y-0">
<div className="text-gray-600 dark:text-gray-300 text-sm text-center md:text-left">
<p>© 2026 page-agent. All rights reserved.</p>
<p>
Built with by{' '}
<a
href="https://x.com/simonluvramen"
target="_blank"
rel="noopener noreferrer"
className="hover:text-gray-900 dark:hover:text-white transition-colors duration-200"
className="inline-block bg-[linear-gradient(60deg,#39b6ff_0%,#bd45fb_33%,#ff5733_66%,#ffd600_100%)] bg-clip-text text-xs leading-none text-transparent font-mono transition-opacity duration-200 hover:opacity-85"
>
Simon
Simon.
</a>
</p>
<p className="text-gray-600 dark:text-gray-300 text-xs mt-0.5">
© 2026 page-agent. All rights reserved.
</p>
</div>
<div className="flex items-center space-x-6">
<div className="flex items-center">
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank"
rel="noopener noreferrer"
className="text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white transition-colors duration-200 text-sm"
className="text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white transition-colors duration-200 text-sm mr-4"
>
{isZh ? '使用条款与隐私' : 'Terms & Privacy'}
</a>
@@ -40,7 +41,7 @@ export default function Footer() {
href="https://x.com/simonluvramen"
target="_blank"
rel="noopener noreferrer"
className="text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white transition-colors duration-200"
className="text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white transition-colors duration-200 mr-4"
aria-label="X (Twitter)"
>
<svg
@@ -40,7 +40,7 @@ export default function LanguageSwitcher() {
<div className="relative" ref={dropdownRef}>
<button
onClick={() => setIsOpen(!isOpen)}
className="flex items-center gap-2 px-3 py-1.5 rounded-lg bg-gray-100 dark:bg-gray-800 hover:bg-gray-200 dark:hover:bg-gray-700 transition-colors text-sm font-medium border border-gray-200 dark:border-gray-700 text-gray-700 dark:text-gray-300"
className="flex cursor-pointer items-center gap-2 rounded-lg border border-gray-200 bg-gray-100 px-3 py-1.5 text-sm font-medium text-gray-700 transition-colors hover:bg-gray-200 dark:border-gray-700 dark:bg-gray-800 dark:text-gray-300 dark:hover:bg-gray-700"
aria-label={isZh ? '切换语言' : 'Switch language'}
aria-expanded={isOpen}
aria-haspopup="true"
@@ -81,7 +81,7 @@ export default function LanguageSwitcher() {
<button
key={lang.code}
onClick={() => handleLanguageChange(lang.code)}
className={`w-full flex items-center gap-2 px-4 py-2 text-sm text-left hover:bg-gray-100 dark:hover:bg-gray-700 transition-colors ${
className={`flex w-full cursor-pointer items-center gap-2 px-4 py-2 text-left text-sm transition-colors hover:bg-gray-100 dark:hover:bg-gray-700 ${
language === lang.code
? 'bg-blue-50 dark:bg-blue-900/20 text-blue-700 dark:text-blue-300'
: 'text-gray-700 dark:text-gray-300'
@@ -52,7 +52,7 @@ export default function ThemeSwitcher() {
return (
<button
onClick={toggleTheme}
className="relative inline-flex items-center h-8 w-16 rounded-full transition-colors duration-300 ease-in-out focus:outline-none"
className="relative inline-flex h-8 w-16 cursor-pointer items-center rounded-full transition-colors duration-300 ease-in-out focus:outline-none"
style={{
backgroundColor: theme === 'dark' ? '#1e293b' : '#e0f2fe',
}}
@@ -62,10 +62,11 @@ export default function ThemeSwitcher() {
>
{/* 滑块 */}
<span
className="inline-block h-6 w-6 transform rounded-full transition-all duration-300 ease-in-out shadow-md"
className={`inline-block h-6 w-6 rounded-full transition-all duration-300 ease-in-out shadow-md ${
theme === 'dark' ? 'translate-x-9' : 'translate-x-1'
}`}
style={{
backgroundColor: theme === 'dark' ? '#475569' : '#fbbf24',
transform: theme === 'dark' ? 'translateX(2.25rem)' : 'translateX(0.25rem)',
}}
>
{/* 图标 */}
+3 -3
View File
@@ -1,10 +1,10 @@
// Demo build (auto-init with demo LLM, for quick testing)
export const CDN_DEMO_URL =
'https://cdn.jsdelivr.net/npm/page-agent@1.5.8/dist/iife/page-agent.demo.js'
'https://cdn.jsdelivr.net/npm/page-agent@1.6.0/dist/iife/page-agent.demo.js'
export const CDN_DEMO_CN_URL =
'https://registry.npmmirror.com/page-agent/1.5.8/files/dist/iife/page-agent.demo.js'
'https://registry.npmmirror.com/page-agent/1.6.0/files/dist/iife/page-agent.demo.js'
// Demo LLM for website testing (homepage quick trial uses flash)
export const DEMO_MODEL = 'qwen3.5-flash'
export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
export const DEMO_API_KEY = 'NA'
// export const DEMO_API_KEY = ''
+2 -1
View File
@@ -1,4 +1,5 @@
@import 'tailwindcss' important;
@config '../tailwind.config.js';
@import 'tailwindcss';
@import 'tw-animate-css';
@custom-variant dark (&:is(.dark *));
@@ -129,12 +129,6 @@ const result = await agent.execute('Fill in the form with test data')`}
? 'LLM API 的基础 URL(如 https://api.openai.com/v1'
: 'Base URL of the LLM API (e.g., https://api.openai.com/v1)',
},
{
name: 'apiKey',
type: 'string',
required: true,
description: isZh ? 'API 密钥' : 'API key for authentication',
},
{
name: 'model',
type: 'string',
@@ -143,6 +137,12 @@ const result = await agent.execute('Fill in the form with test data')`}
? '模型名称(如 gpt-5.2, anthropic/claude-4.5-haiku'
: 'Model name (e.g., gpt-5.2, anthropic/claude-4.5-haiku)',
},
{
name: 'apiKey',
type: 'string',
required: false,
description: 'LLM AK',
},
{
name: 'temperature',
type: 'number',
@@ -156,6 +156,14 @@ const result = await agent.execute('Fill in the form with test data')`}
defaultValue: '3',
description: isZh ? 'API 调用失败时的最大重试次数' : 'Maximum retries on API failure',
},
{
name: 'disableNamedToolChoice',
type: 'boolean',
defaultValue: 'false',
description: isZh
? '禁用命名 tool_choice,始终使用 "required" 字符串。适用于不支持 tool_choice 对象格式的 LLM 服务。'
: 'Disable named tool_choice, always use "required" string. For LLM services that don\'t support the object format of tool_choice.',
},
{
name: 'customFetch',
type: 'typeof fetch',
@@ -187,39 +187,7 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
</p>
<CodeEditor
code={
isZh
? `import type {
AgentActivity,
AgentStatus,
ExecutionResult,
HistoricalEvent
} from '@page-agent/core'
interface ExecuteConfig {
baseURL: string // LLM API 端点
apiKey: string // API 密钥
model: string // 模型名称
includeInitialTab?: boolean
onStatusChange?: (status: AgentStatus) => void
onActivity?: (activity: AgentActivity) => void
onHistoryUpdate?: (history: HistoricalEvent[]) => void
}
type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
declare global {
interface Window {
PAGE_AGENT_EXT_VERSION?: string
PAGE_AGENT_EXT?: {
version: string
execute: Execute
stop: () => void
}
}
}`
: `import type {
code={`import type {
AgentActivity,
AgentStatus,
ExecutionResult,
@@ -228,8 +196,8 @@ declare global {
interface ExecuteConfig {
baseURL: string // LLM API endpoint
apiKey: string // API key
model: string // Model name
apiKey?: string // LLM AK
includeInitialTab?: boolean
onStatusChange?: (status: AgentStatus) => void
@@ -248,8 +216,7 @@ declare global {
stop: () => void
}
}
}`
}
}`}
language="typescript"
/>
@@ -34,6 +34,7 @@ const MODEL_GROUPS: Record<string, string[]> = {
'claude-sonnet-3.5',
],
xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
MiniMax: ['MiniMax-M2.7', 'MiniMax-M2.7-highspeed', 'MiniMax-M2.5', 'MiniMax-M2.5-highspeed'],
MoonshotAI: ['kimi-k2.5'],
'Z.AI': ['glm-5', 'glm-4.7'],
}
@@ -121,10 +122,16 @@ const pageAgent = new PageAgent({
model: 'qwen3.5-plus'
});
// Self-hosted models (e.g., Ollama)
// MiniMax
const pageAgent = new PageAgent({
baseURL: 'https://api.minimax.io/v1',
apiKey: 'your-minimax-api-key',
model: 'MiniMax-M2.7'
});
// Self-hosted models (e.g., Ollama) — no apiKey needed
const pageAgent = new PageAgent({
baseURL: 'http://localhost:11434/v1',
apiKey: 'NA',
model: 'qwen3:14b'
});
@@ -272,7 +279,6 @@ LLM_MODEL_NAME="qwen3:14b"`}
<CodeEditor
code={`const agent = new PageAgent({
baseURL: '/api/llm-proxy',
apiKey: 'NA',
model: 'gpt-5.1',
customFetch: (url, init) =>
fetch(url, { ...init, credentials: 'include' }),
@@ -16,17 +16,6 @@ export default function ThirdPartyAgentPage() {
: 'Integrate pageAgent as a tool in your support assistant or Agent system, becoming the eyes and hands of your Agent.'}
</p>
<div className="bg-blue-50 dark:bg-blue-900/20 rounded-lg p-4 mb-6">
<h3 className="text-lg font-semibold mb-2 text-blue-900 dark:text-blue-300">
{isZh ? '💡 核心价值' : '💡 Core Value'}
</h3>
<p className="text-blue-800 dark:text-blue-200">
{isZh
? '让你的答疑机器人不再只是"嘴巴",而是拥有"眼睛"和"手"的完整智能体。'
: 'Transform your support bot from just a "mouth" into a complete intelligent agent with "eyes" and "hands".'}
</p>
</div>
<Heading id="integration-method" className="text-2xl font-bold mb-4">
{isZh ? '集成方式' : 'Integration Method'}
</Heading>
@@ -410,7 +410,7 @@ export default function TroubleshootingPage() {
.getElementById(section.id)
?.scrollIntoView({ behavior: 'smooth', block: 'start' })
}
className={`block text-sm py-1 text-left transition-colors ${
className={`block cursor-pointer py-1 text-left text-sm transition-colors ${
activeId === section.id
? 'text-blue-600 dark:text-blue-400 font-medium'
: 'text-gray-500 dark:text-gray-400 hover:text-gray-900 dark:hover:text-gray-200'
@@ -10,7 +10,7 @@ import { Particles } from '../../components/ui/particles'
import {
CDN_DEMO_CN_URL,
CDN_DEMO_URL,
DEMO_API_KEY,
// DEMO_API_KEY,
DEMO_BASE_URL,
DEMO_MODEL,
} from '../../constants'
@@ -94,7 +94,7 @@ export default function HeroSection() {
apiKey:
import.meta.env.DEV && import.meta.env.LLM_API_KEY
? import.meta.env.LLM_API_KEY
: DEMO_API_KEY,
: undefined,
})
}
+3
View File
@@ -0,0 +1,3 @@
export default {
important: '#root',
}
+1 -1
View File
@@ -13,7 +13,7 @@ const pageAgentPkg = JSON.parse(
)
// Load .env from repo root
dotenvConfig({ path: resolve(__dirname, '../../.env') })
dotenvConfig({ path: resolve(__dirname, '../../.env'), quiet: true })
// All SPA routes that need index.html copies for direct access on static hosts
const SPA_ROUTES = [