Compare commits

...

25 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
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
34 changed files with 395 additions and 229 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@1.5.10/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.10/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@1.5.10/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.10/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
+20 -20
View File
@@ -1,12 +1,12 @@
{
"name": "root",
"version": "1.5.10",
"version": "1.6.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "root",
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT",
"workspaces": [
"packages/page-controller",
@@ -11799,11 +11799,11 @@
},
"packages/core": {
"name": "@page-agent/core",
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT",
"dependencies": {
"@page-agent/llms": "1.5.10",
"@page-agent/page-controller": "1.5.10",
"@page-agent/llms": "1.6.0",
"@page-agent/page-controller": "1.6.0",
"chalk": "^5.6.2"
},
"devDependencies": {
@@ -11815,13 +11815,13 @@
},
"packages/extension": {
"name": "@page-agent/ext",
"version": "1.5.10",
"version": "1.6.0",
"hasInstallScript": true,
"dependencies": {
"@page-agent/core": "1.5.10",
"@page-agent/llms": "1.5.10",
"@page-agent/page-controller": "1.5.10",
"@page-agent/ui": "1.5.10",
"@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"
},
@@ -11858,7 +11858,7 @@
},
"packages/llms": {
"name": "@page-agent/llms",
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT",
"dependencies": {
"chalk": "^5.6.2"
@@ -11872,7 +11872,7 @@
},
"packages/mcp": {
"name": "@page-agent/mcp",
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.27.1",
@@ -11887,13 +11887,13 @@
}
},
"packages/page-agent": {
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT",
"dependencies": {
"@page-agent/core": "1.5.10",
"@page-agent/llms": "1.5.10",
"@page-agent/page-controller": "1.5.10",
"@page-agent/ui": "1.5.10",
"@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"
},
"devDependencies": {
@@ -11905,7 +11905,7 @@
},
"packages/page-controller": {
"name": "@page-agent/page-controller",
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT",
"dependencies": {
"ai-motion": "^0.4.8"
@@ -11913,12 +11913,12 @@
},
"packages/ui": {
"name": "@page-agent/ui",
"version": "1.5.10",
"version": "1.6.0",
"license": "MIT"
},
"packages/website": {
"name": "@page-agent/website",
"version": "1.5.10",
"version": "1.6.0",
"devDependencies": {
"@radix-ui/react-icons": "^1.3.2",
"@radix-ui/react-separator": "^1.1.8",
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "root",
"private": true,
"version": "1.5.10",
"version": "1.6.0",
"type": "module",
"workspaces": [
"packages/page-controller",
+3 -3
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/core",
"private": false,
"version": "1.5.10",
"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": "1.5.10",
"@page-agent/page-controller": "1.5.10"
"@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
+5 -5
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/ext",
"private": true,
"version": "1.5.10",
"version": "1.6.0",
"type": "module",
"scripts": {
"dev": "wxt",
@@ -37,10 +37,10 @@
"wxt": "^0.20.19"
},
"dependencies": {
"@page-agent/core": "1.5.10",
"@page-agent/llms": "1.5.10",
"@page-agent/page-controller": "1.5.10",
"@page-agent/ui": "1.5.10",
"@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"
},
+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 */
+8 -1
View File
@@ -21,6 +21,7 @@ export interface AdvancedConfig {
maxSteps?: number
systemInstruction?: string
experimentalLlmsTxt?: boolean
disableNamedToolChoice?: boolean
}
export interface ExtConfig extends LLMConfig, AdvancedConfig {
@@ -124,6 +125,7 @@ export function useAgent(): UseAgentResult {
maxSteps,
systemInstruction,
experimentalLlmsTxt,
disableNamedToolChoice,
...llmConfig
}: ExtConfig) => {
await chrome.storage.local.set({ llmConfig })
@@ -132,7 +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 })
},
@@ -14,7 +14,7 @@ import {
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'
@@ -27,15 +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>('')
@@ -44,13 +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
@@ -96,6 +100,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
maxSteps: maxSteps || undefined,
systemInstruction: systemInstruction || undefined,
experimentalLlmsTxt,
disableNamedToolChoice,
})
} finally {
setSaving(false)
@@ -194,7 +199,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
<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"
@@ -206,7 +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"
@@ -271,6 +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>
@@ -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,
},
},
@@ -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 ---
@@ -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')
}
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/llms",
"version": "1.5.10",
"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.
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/mcp",
"private": false,
"version": "1.5.10",
"version": "1.6.0",
"type": "module",
"bin": {
"page-agent-mcp": "src/index.js"
+1 -1
View File
@@ -12,9 +12,9 @@ const port = parseInt(env.PORT || '38401')
/** @type {Record<string, string>} */
const llmConfig = {}
if (env.LLM_API_KEY) llmConfig.apiKey = env.LLM_API_KEY
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) ---
+5 -5
View File
@@ -1,7 +1,7 @@
{
"name": "page-agent",
"private": false,
"version": "1.5.10",
"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": "1.5.10",
"@page-agent/llms": "1.5.10",
"@page-agent/page-controller": "1.5.10",
"@page-agent/ui": "1.5.10",
"@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
@@ -1,6 +1,6 @@
{
"name": "@page-agent/page-controller",
"version": "1.5.10",
"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": "1.5.10",
"version": "1.6.0",
"type": "module",
"main": "./dist/lib/page-agent-ui.js",
"module": "./dist/lib/page-agent-ui.js",
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/website",
"private": true,
"version": "1.5.10",
"version": "1.6.0",
"type": "module",
"scripts": {
"dev": "vite --host 0.0.0.0",
+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@1.5.10/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/1.5.10/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 = ''
@@ -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"
/>
@@ -129,10 +129,9 @@ const pageAgent = new PageAgent({
model: 'MiniMax-M2.7'
});
// Self-hosted models (e.g., Ollama)
// Self-hosted models (e.g., Ollama) — no apiKey needed
const pageAgent = new PageAgent({
baseURL: 'http://localhost:11434/v1',
apiKey: 'NA',
model: 'qwen3:14b'
});
@@ -280,7 +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' }),
@@ -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,
})
}