Compare commits

..

35 Commits

Author SHA1 Message Date
Simon 15d609aebc chore(version): bump version to 1.5.3 2026-03-09 17:02:34 +08:00
Simon d66bf8f3cf docs: improve Contributing.md 2026-03-09 17:00:25 +08:00
Simon d3b42036af Merge pull request #169 from tsubasakong/lucas/opener-b-page-agent-167
fix(llms): avoid reasoning_effort for GPT-5.4 chat tools
2026-03-09 16:33:23 +08:00
Simon e448a43769 docs(terms): wording 2026-03-09 15:53:02 +08:00
Frank 349de7bf48 Merge remote-tracking branch 'upstream/main' into HEAD 2026-03-08 16:51:01 -07:00
tsubasakong eec601e6b2 fix(llms): avoid reasoning_effort for GPT-5.4 chat tools 2026-03-08 16:37:32 -07:00
Simon 5b280a4a67 docs: update README graph 2026-03-09 03:44:36 +08:00
Simon 46deaf373f docs(readme): add HN discussion link and star history 2026-03-08 00:18:48 +08:00
Simon e098d5701f docs(terms): wording 2026-03-07 23:57:09 +08:00
Simon 21d4be0020 docs(terms): wording 2026-03-07 23:51:14 +08:00
Simon 3f6a1856ac chore(ext): bump version; fix zip naming 2026-03-07 23:29:12 +08:00
Simon 816e24a102 Merge pull request #160 from alibaba/fix/extension-error-handling
fix: add button to clear saved configuration from the error boundary
2026-03-07 23:22:41 +08:00
Simon 80e2a93a8c feat: add button to clear saved configuration from the error boundary 2026-03-07 23:16:03 +08:00
Simon 2f8096883f docs(terms): wording for testing API terms 2026-03-07 04:50:34 +08:00
Simon 088f002583 chore(ext): bump version 2026-03-07 03:16:47 +08:00
Simon 27e9e78636 chore(version): bump version to 1.5.2 2026-03-07 03:08:33 +08:00
Simon a0c979602e feat: do not throw for webgl2 fail 2026-03-07 03:07:21 +08:00
Simon 3dc9edb8b5 fix(ext): ts types 2026-03-06 17:39:09 +08:00
Simon 32b68ab7c8 fix(docs): broken demo video 2026-03-06 16:07:22 +08:00
Simon 75a61c05c1 docs(terms): wording
Clarify the note regarding data processing location for the demo.
2026-03-06 04:33:03 +08:00
Simon bdfa98358b fix: requestIdleCallback on safari 2026-03-06 02:35:01 +08:00
Simon dc8b38ccb9 chore(ext): bump extension version to 0.1.11 2026-03-05 20:48:00 +08:00
Simon e1c288aaeb docs(changelog): 1.5.1 2026-03-05 20:44:26 +08:00
Simon 7a97de2a37 feat(ext): expose more config 2026-03-05 20:34:55 +08:00
Simon 19b03b83ea chore(version): bump version to 1.5.1 2026-03-05 19:28:19 +08:00
Simon 598b144d06 feat: change maxSteps to 40 2026-03-05 19:26:56 +08:00
Simon 1cd8a8de60 Merge pull request #158 from alibaba/fix/zod-v3
feat: import zod properly
2026-03-05 19:23:47 +08:00
Simon 9beffca985 docs: update doc for Zod v4 support 2026-03-05 19:15:03 +08:00
Simon 53db2069ce feat: zod support v3/4 2026-03-05 19:13:18 +08:00
Simon 121104e13d feat: truncate llms.txt results 2026-03-05 16:59:08 +08:00
Simon 0dacbda9da chore: improve logging 2026-03-05 16:54:41 +08:00
Simon 8bc27414a4 chore(version): bump version to 1.4.4 2026-03-05 16:25:16 +08:00
Simon 76509d93f0 feat: replace data-browser-use-ignore with data-page-agent-ignore 2026-03-05 16:24:50 +08:00
Simon ff31b0c03e chore: adjust website structure 2026-03-05 16:21:58 +08:00
Simon 6b2ab73d65 docs: model recommendation 2026-03-05 16:10:03 +08:00
42 changed files with 428 additions and 201 deletions
+27 -22
View File
@@ -1,6 +1,6 @@
# Contributing to Page-Agent
# Contributing to PageAgent
Thank you for your interest in contributing to Page-Agent! We welcome contributions from everyone.
Thank you for your interest in contributing to PageAgent! We welcome contributions from everyone.
## 🚀 Quick Start
@@ -27,11 +27,11 @@ This is a **monorepo** with npm workspaces containing **4 main packages**:
- **Extension** (`packages/extension/`) - Chrome extension for multi-page tasks and browser-level automation
- **Website** (`packages/website/`) - React documentation and landing page. Also as demo and test page for the core lib. private package `@page-agent/website`
We use a simplified monorepo solution with `native npm-workspace + ts reference + vite alias`. No fancy tooling. Hoisting is required.
- When developing. Use alias so that we don't have to pre-build.
- When bundling. Use external and disable ts `paths` alias to leave deps out.
- When bundling `IIFE` and `Website`. Bundle everything including local packages.
> We use a simplified monorepo solution with `native npm-workspace + ts reference + vite alias`. No fancy tooling. Hoisting is required.
>
> - When developing. Use alias so that we don't have to pre-build.
> - When bundling. Use external and disable ts `paths` alias to leave deps out.
> - When bundling `IIFE` and `Website`. Bundle everything including local packages.
## 🤝 How to Contribute
@@ -90,14 +90,17 @@ We use a simplified monorepo solution with `native npm-workspace + ts reference
- Keep functions small and focused
- Add JSDoc for public APIs
### Vibe coding with AI
### Vibe Coding with AI
- It's **recommended** to heavily rely on AI (aka "vibe coding") when maintaining **demo pages and tests**.
- Be very careful if AI ever touched the core lib!!!
> [Vibe coding](https://en.wikipedia.org/wiki/Vibe_coding) = describe what you want in natural language, let AI write the code, and you review the result.
- Vibe coding is **RECOMMENDED** when maintaining **the demo, the website, the UI and tests**.
- We have a [website/AGENTS.md](packages/website/AGENTS.md) for that.
- Vibe coding is **NOT** allowed for the core lib!!!
- NEVER try to vibe coding the MV3 extension!!! It is HELL.
- Review anything AI wrote before make a commit. You are the author of anything you commit. NOT AI.
- Update the [AI instructions](AGENTS.md) when structure changed.
If your lame AI assistant does not support [AGENTS.md](https://agents.md/). Add an alias for it:
If your AI assistant does not support [AGENTS.md](https://agents.md/). Add an alias for it:
- claude-code (`CLAUDE.md`)
@@ -135,10 +138,10 @@ If your lame AI assistant does not support [AGENTS.md](https://agents.md/). Add
LLM_MODEL_NAME="qwen3:14b"
```
> ⚠️ Add `*` to `OLLAMA_ORIGINS` (403). Models < 10B unlikely strong enough. Requires tool_call support. Set context length > 15k (default 4k will NOT work): `$env:OLLAMA_CONTEXT_LENGTH=64000; ollama serve`
> @see https://alibaba.github.io/page-agent/docs/features/models#ollama for configuration
- Restart the dev server to load new env vars
- If not provided, the demo will the free testing proxy by default
- **Restart the dev server** to load new env vars
- If not provided, the demo will use the free testing proxy by default. By using it, you agree to its [terms](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md).
### Website Development
@@ -149,12 +152,13 @@ npm start
### Extension Development
```bash
# make sure you ran `npm run build:libs` first
# and every time you changed the core libs
npm run dev -w @page-agent/ext
npm run zip -w @page-agent/ext
```
- Load extension in Chrome via `chrome://extensions` -> **Load unpacked**
- Use `packages/extension/docs/extension_api.md` (EN) or `packages/extension/docs/extension_api_zh.md` (ZH) for API integration details
- Update `packages/extension/docs/extension_api.md` for API integration details
### Testing on Other Websites
@@ -172,7 +176,7 @@ npm run zip -w @page-agent/ext
- Click the bookmark on any page to load Page-Agent
> Warning: AK in your local `.env` will be inlined in the iife script.
> Warning: AK in your local `.env` will be inlined in the iife script. Be very careful when you distribute the script.
### Adding Documentation
@@ -193,16 +197,17 @@ We especially welcome contributions in:
## 🚫 What We Don't Accept
- Changes that break existing API compatibility (Discuss first)
- Heavy dependencies to core library
- Breaking changes and large PRs without prior discussion
- Heavy dependencies to core libs
- Contributions without proper testing
- Code that doesn't follow project conventions
- Dependencies or code with licenses incompatible with MIT
## 📄 Legal
By contributing to this project, you agree that your contributions will be licensed under the MIT License.
> You may need to sign a github CLA before you create a PR.
> You need to sign a github CLA when you create a PR.
## 💬 Questions?
@@ -210,4 +215,4 @@ By contributing to this project, you agree that your contributions will be licen
- Check existing documentation and issues first
- Be respectful and constructive in discussions
Thank you for helping make Page-Agent better! 🎉
Thank you for helping make PageAgent better! 🎉
+12 -4
View File
@@ -11,9 +11,9 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua
🌐 **English** | [中文](./docs/README-zh.md)
👉 <a href="https://alibaba.github.io/page-agent/" target="_blank"><b>🚀 Demo</b></a> | <a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank"><b>📖 Documentation</b></a>
👉 <a href="https://alibaba.github.io/page-agent/" target="_blank"><b>🚀 Demo</b></a> | <a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank"><b>📖 Documentation</b></a> | <a href="https://news.ycombinator.com/item?id=47264138" target="_blank">📢 Join HN Discussion</a>
<video id="demo-video" src="https://github.com/user-attachments/assets/11aed429-b69c-49d5-8982-fa99b4a0e9a8" controls crossorigin muted></video>
<video id="demo-video" src="https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2" controls crossorigin muted></video>
---
@@ -49,8 +49,8 @@ Fastest way to try PageAgent with our free Demo LLM:
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.4.3/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.4.3/files/dist/iife/page-agent.demo.js |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.3/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.3/files/dist/iife/page-agent.demo.js |
> **⚠️ For technical evaluation only.** This demo CDN uses our free [testing LLM API](https://alibaba.github.io/page-agent/docs/features/models#free-testing-api). By using it, you agree to its [terms](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md).
@@ -111,3 +111,11 @@ file and in the node_modules directory after installation.
---
**⭐ Star this repo if you find PageAgent helpful!**
<a href="https://www.star-history.com/?repos=alibaba%2Fpage-agent&type=date">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/image?repos=alibaba/page-agent&type=date&theme=dark" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/image?repos=alibaba/page-agent&type=date" />
<img alt="Star History Chart" src="https://api.star-history.com/image?repos=alibaba/page-agent&type=date" />
</picture>
</a>
+31
View File
@@ -5,6 +5,37 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [1.5.1] - 2026-03-05
### Breaking Changes
- **`data-browser-use-ignore``data-page-agent-ignore`** - DOM ignore attribute renamed to match the project identity
- **Config types restructured** - `PageAgentConfig` split into `AgentConfig` + `PageAgentCoreConfig`; config definitions moved from `config/index.ts` to `types.ts`
- **Zod v3/v4 dual support** - Libraries now accept both `zod@^3.25` and `zod@^4.0` as peer dependencies
### Features
- **Experimental `llms.txt` support** - Agent can fetch and include a site's `llms.txt` in context. Enable via `experimentalLlmsTxt: true`
### Improvements
- Default `maxSteps` changed from 20 to 40 for better for complex tasks out of the box
- Added 400ms wait between agent steps for page reactions
- Increased click wait time (100ms → 200ms) for more reliable interactions
- Removed debug `console.log` statements from scroll actions
- Reset observations on new task start
- Improved logging across packages
### Extension v0.1.9
> PageAgent 1.5.1
- **Advanced config panel** - New collapsible section exposing Max Steps, System Instruction, and experimental `llms.txt` toggle
- Streamlined User Auth Token description
- Moved testing API notice below auth token section
---
## [1.4.0] - 2026-02-27
### Features
+3 -3
View File
@@ -13,7 +13,7 @@
👉 <a href="https://alibaba.github.io/page-agent/" target="_blank"><b>🚀 Demo</b></a> | <a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank"><b>📖 Documentation</b></a>
<video id="demo-video" src="https://github.com/user-attachments/assets/11aed429-b69c-49d5-8982-fa99b4a0e9a8" controls crossorigin muted></video>
<video id="demo-video" src="https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2" controls crossorigin muted></video>
---
@@ -49,8 +49,8 @@
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.4.3/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.4.3/files/dist/iife/page-agent.demo.js |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.3/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.3/files/dist/iife/page-agent.demo.js |
> **⚠️ 仅用于技术评估。** 该 Demo CDN 使用了免费的[测试 LLM API](https://alibaba.github.io/page-agent/docs/features/models#free-testing-api),使用即表示您同意其[条款](https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md)。
+19 -17
View File
@@ -1,20 +1,20 @@
# Terms of Use & Privacy
**Last updated:** February 2026
**Last updated:** March 2026
"We" in this document refers to the maintainers of the open-source Page Agent project (https://github.com/alibaba/page-agent). This document covers the Page Agent software itself and the testing services we provide — **not** any third-party product or service built with it.
"We" in this document refers to the maintainers of the open-source Page Agent project (https://github.com/alibaba/page-agent). "The software" refers to PageAgent.js (the JavaScript library) and Page Agent Ext (the browser extension). This document covers the software itself and the testing API we provide — **not** any third-party product or service built with it.
---
## 1. Open Source Software Privacy
Page Agent (PageAgent.js and Page Agent Extension) is a **client-side only** tool with a "Bring Your Own Key" (BYOK) architecture. The software itself does **not** include any backend service. The software does **not** collect or transmit any user data on its own, and the maintainers do **not** have access to your browsing activity, page content, or task instructions through the software.
The software is a **client-side only** tool with a "Bring Your Own Key" (BYOK) architecture. The software itself does **not** include any backend service. The software does **not** collect or transmit any user data on its own, and we do **not** have access to your browsing activity, page content, or task instructions through the software.
All data transmission occurs **only** between your browser and the LLM provider you configure. You are in full control of which provider receives your data.
- You choose which LLM provider to use
- You may configure your own API endpoint at any time
- The project is open source and can be audited: https://github.com/alibaba/page-agent
- The project is open source under the [MIT License](https://github.com/alibaba/page-agent/blob/main/LICENSE) and can be audited at: https://github.com/alibaba/page-agent
---
@@ -22,21 +22,23 @@ All data transmission occurs **only** between your browser and the LLM provider
To facilitate easy testing and technical evaluation, we provide a free testing LLM API. This API is used in the project homepage's live demo, the pre-built demo CDN bundles, and the browser extension's default configuration. Users may also use it independently for their own technical evaluation of page-agent.
This free testing API is provided **strictly for technical evaluation and R&D purposes only**. It must not be used in any production environment. By using this service, you agree to the following terms:
This free testing API is provided **strictly for technical evaluation and R&D purposes only**. It must not be used in any production environment. By using this API, you agree to the following terms:
**No Sensitive Data**: You are strictly prohibited from inputting any Personal Identifiable Information (PII), confidential business data, financial/medical records, or using this agent on web pages containing such sensitive information.
- **No Sensitive Data**: You are strictly prohibited from inputting any Personal Identifiable Information (PII), confidential business data, financial/medical records, or using this agent on web pages containing such sensitive information.
**Zero Data Retention**: We do not store, log, or use your prompts or webpage data (DOM) for model training. All data is processed in-transit and immediately discarded. However, we do temporarily process necessary, identity-agnostic network data (such as IP addresses) solely for rate-limiting and anti-abuse purposes.
- **Data Processing**: We do not store or log your prompts, webpage data (HTML), or any submitted content, nor do we use such data for model training. All data is processed in-transit and immediately discarded. We perform in-memory request validation to prevent abuse of the testing API, and temporarily process IP addresses for rate-limiting purposes. No data from these processes is retained. Data is processed through Alibaba Cloud infrastructure, which is subject to its own privacy policy.
**Independent Infrastructure**: The `page-agent` open-source software is completely frontend-based with a "Bring Your Own Key" (BYOK) architecture and no built-in backend. To facilitate easy testing, the maintainers have independently purchased public cloud services from Alibaba Cloud China ([aliyun.com](https://www.aliyun.com) FC and BaiLian Qwen models). This project is not affiliated with, nor endorsed by, Alibaba Cloud.
- **Independent Infrastructure**: The software is completely frontend-based with a "Bring Your Own Key" (BYOK) architecture and **no built-in backend**. To facilitate easy testing, the maintainers have purchased public cloud services from Alibaba Cloud China ([aliyun.com](https://www.aliyun.com) Function Compute and BaiLian Qwen models). This project is not a product of, nor endorsed by, Alibaba Cloud.
**No Guaranteed Availability**: This testing API may be rate-limited, degraded, or discontinued at any time without prior notice.
- **No Guaranteed Availability**: This testing API may be rate-limited, degraded, or discontinued at any time without prior notice.
**"AS IS" & Limitation of Liability**: This service is provided strictly on an "AS IS" and "AS AVAILABLE" basis, without any warranties. The maintainers bear no liability for any data loss, service interruption, or legal consequences arising from your use of this demo.
- **"AS IS" & Limitation of Liability**: This service is provided strictly on an "AS IS" and "AS AVAILABLE" basis, without any warranties. The maintainers bear no liability for any data loss, service interruption, or legal consequences arising from your use of this service.
**Recommendation for Real Usage**: For secure and continuous usage, we strongly advise using the default BYOK mode with your own legally compliant commercial LLM API keys, or connecting to local, offline models (e.g., Ollama).
- **Recommendation for Real Usage**: For secure and continuous usage, we strongly advise using the BYOK mode with your own legally compliant commercial LLM API keys, or connecting to local, offline models (e.g., Ollama).
**Note**: This service processes data via servers located in Mainland China. If you are located in a region with strict data localization laws (such as the EU/EEA), please do not use this demo.
**Note**: This free testing LLM API processes data via servers located in Mainland China. If you are located in a region with strict data localization laws (such as the EU/EEA), please do not use this API.
**Age Requirement**: The software and testing API are not intended for use by individuals under the age of 13 (or the minimum age of digital consent in your jurisdiction).
---
@@ -49,19 +51,19 @@ The extension performs DOM analysis and automation actions **locally in your bro
Data is transmitted to external servers **only when you initiate an automation task**. When this occurs:
- Your task instructions (natural language commands)
- Simplified page structure (cleaned DOM) of all pages under the extension's control
- Simplified page structure (cleaned HTML) of all pages under the extension's control
are sent to the LLM API endpoint configured in **your settings**.
> **Note:** The DOM cleaning process simplifies page structure for AI readability but **does not guarantee removal of sensitive information** (e.g., visible text, form values, or personal data on the page). Please be mindful of the page content when initiating tasks.
> **Note:** The HTML cleaning process simplifies page structure for AI readability but **does not guarantee removal of sensitive information** (e.g., visible text, form values, or personal data on the page). Please be mindful of the page content when initiating tasks.
**If you configure a third-party LLM provider** (e.g., OpenAI, Anthropic, or others), data is sent directly to that provider. Their privacy policies apply.
**If you use the built-in testing API**, the terms in [Section 2](#2-testing-api-and-demo-disclaimer--terms-of-use) apply. By using the extension with the default testing API, you agree to those terms.
**If you use the testing API**, the terms in [Section 2](#2-testing-api-and-demo-disclaimer--terms-of-use) apply. By using the extension with the default testing API, you agree to those terms.
### Data Storage
- **Local storage only**: Your configuration (API endpoint, API key, model selection) is stored in your browser via `chrome.storage.local`
- **Local storage only**: Your configuration (API endpoint, API key, model selection) is stored in your browser via `chrome.storage.local` (or equivalent browser storage APIs)
- **No cloud sync**: Configuration is not synced to any external server
- **No analytics**: The extension does not include any analytics or tracking code
@@ -76,7 +78,7 @@ are sent to the LLM API endpoint configured in **your settings**.
## Changes
We may update these terms as the project evolves.
We may update these terms at our discretion.
## Contact
+41 -24
View File
@@ -1,12 +1,12 @@
{
"name": "root",
"version": "1.4.3",
"version": "1.5.3",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "root",
"version": "1.4.3",
"version": "1.5.3",
"license": "MIT",
"workspaces": [
"packages/page-controller",
@@ -11113,27 +11113,31 @@
},
"packages/core": {
"name": "@page-agent/core",
"version": "1.4.3",
"version": "1.5.3",
"license": "MIT",
"dependencies": {
"@page-agent/llms": "1.4.3",
"@page-agent/page-controller": "1.4.3",
"chalk": "^5.6.2",
"@page-agent/llms": "1.5.3",
"@page-agent/page-controller": "1.5.3",
"chalk": "^5.6.2"
},
"devDependencies": {
"zod": "^4.3.5"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
}
},
"packages/extension": {
"name": "@page-agent/ext",
"version": "0.1.8",
"version": "0.1.15",
"hasInstallScript": true,
"dependencies": {
"@page-agent/core": "1.4.3",
"@page-agent/llms": "1.4.3",
"@page-agent/page-controller": "1.4.3",
"@page-agent/ui": "1.4.3",
"@page-agent/core": "1.5.3",
"@page-agent/llms": "1.5.3",
"@page-agent/page-controller": "1.5.3",
"@page-agent/ui": "1.5.3",
"ai-motion": "^0.4.8",
"chalk": "^5.6.2",
"zod": "^4.3.5"
"chalk": "^5.6.2"
},
"devDependencies": {
"@radix-ui/react-hover-card": "^1.1.15",
@@ -11162,32 +11166,45 @@
"tailwindcss": "^4.1.14",
"tw-animate-css": "^1.4.0",
"wxt": "^0.20.18"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
}
},
"packages/llms": {
"name": "@page-agent/llms",
"version": "1.4.3",
"version": "1.5.3",
"license": "MIT",
"dependencies": {
"chalk": "^5.6.2",
"chalk": "^5.6.2"
},
"devDependencies": {
"zod": "^4.3.5"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
}
},
"packages/page-agent": {
"version": "1.4.3",
"version": "1.5.3",
"license": "MIT",
"dependencies": {
"@page-agent/core": "1.4.3",
"@page-agent/llms": "1.4.3",
"@page-agent/page-controller": "1.4.3",
"@page-agent/ui": "1.4.3",
"chalk": "^5.6.2",
"@page-agent/core": "1.5.3",
"@page-agent/llms": "1.5.3",
"@page-agent/page-controller": "1.5.3",
"@page-agent/ui": "1.5.3",
"chalk": "^5.6.2"
},
"devDependencies": {
"zod": "^4.3.5"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
}
},
"packages/page-controller": {
"name": "@page-agent/page-controller",
"version": "1.4.3",
"version": "1.5.3",
"license": "MIT",
"dependencies": {
"ai-motion": "^0.4.8"
@@ -11195,12 +11212,12 @@
},
"packages/ui": {
"name": "@page-agent/ui",
"version": "1.4.3",
"version": "1.5.3",
"license": "MIT"
},
"packages/website": {
"name": "@page-agent/website",
"version": "1.4.3",
"version": "1.5.3",
"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": "1.4.3",
"version": "1.5.3",
"type": "module",
"workspaces": [
"packages/page-controller",
+9 -4
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/core",
"private": false,
"version": "1.4.3",
"version": "1.5.3",
"type": "module",
"main": "./dist/esm/page-agent-core.js",
"module": "./dist/esm/page-agent-core.js",
@@ -44,8 +44,13 @@
},
"dependencies": {
"chalk": "^5.6.2",
"zod": "^4.3.5",
"@page-agent/llms": "1.4.3",
"@page-agent/page-controller": "1.4.3"
"@page-agent/llms": "1.5.3",
"@page-agent/page-controller": "1.5.3"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
},
"devDependencies": {
"zod": "^4.3.5"
}
}
+2 -2
View File
@@ -5,7 +5,7 @@
import { InvokeError, LLM, type Tool } from '@page-agent/llms'
import type { BrowserState, PageController } from '@page-agent/page-controller'
import chalk from 'chalk'
import * as z from 'zod'
import * as z from 'zod/v4'
import SYSTEM_PROMPT from './prompts/system_prompt.md?raw'
import { tools } from './tools'
@@ -96,7 +96,7 @@ export class PageAgentCore extends EventTarget {
constructor(config: PageAgentCoreConfig) {
super()
this.config = { ...config, maxSteps: config.maxSteps || 20 }
this.config = { ...config, maxSteps: config.maxSteps ?? 40 }
this.#llm = new LLM(this.config)
this.tools = new Map(tools)
+1 -1
View File
@@ -2,7 +2,7 @@
* Internal tools for PageAgent.
* @note Adapted from browser-use
*/
import * as z from 'zod'
import * as z from 'zod/v4'
import type { PageAgentCore } from '../PageAgentCore'
import { waitFor } from '../utils'
+4 -3
View File
@@ -12,7 +12,7 @@ export interface AgentConfig extends LLMConfig {
/**
* Maximum number of steps the agent can take per task.
* @default 20
* @default 40
*/
maxSteps?: number
@@ -24,13 +24,14 @@ export interface AgentConfig extends LLMConfig {
*
* @example
* // override internal tool
* import { z } from 'zod/v4'
* import { tool } from 'page-agent'
* const customTools = {
* ask_user: tool({
* description:
* 'Ask the user or parent model a question and wait for their answer. Use this if you need more information or clarification.',
* inputSchema: zod.object({
* question: zod.string(),
* inputSchema: z.object({
* question: z.string(),
* }),
* execute: async function (this: PageAgent, input) {
* const answer = await do_some_thing(input.question)
+9 -9
View File
@@ -1,9 +1,11 @@
import { InvokeError, InvokeErrorType } from '@page-agent/llms'
import chalk from 'chalk'
import * as z from 'zod'
import * as z from 'zod/v4'
import type { PageAgentTool } from '../tools'
const log = console.log.bind(console, chalk.yellow('[autoFixer]'))
/**
* Normalize LLM response and fix common format issues.
*
@@ -34,7 +36,7 @@ export function normalizeResponse(response: any, tools?: Map<string, PageAgentTo
// case: sometimes the model only returns the action level
if (toolCall.function.name && toolCall.function.name !== 'AgentOutput') {
console.log(chalk.yellow(`[normalizeResponse] #1: fixing tool_call`))
log(`#1: fixing tool_call`)
resolvedArguments = { action: safeJsonParse(resolvedArguments) }
}
} else {
@@ -47,13 +49,13 @@ export function normalizeResponse(response: any, tools?: Map<string, PageAgentTo
// case: sometimes the content json includes upper level wrapper
if (resolvedArguments?.name === 'AgentOutput') {
console.log(chalk.yellow(`[normalizeResponse] #2: fixing tool_call`))
log(`#2: fixing tool_call`)
resolvedArguments = safeJsonParse(resolvedArguments.arguments)
}
// case: sometimes even 2-levels of wrapping
if (resolvedArguments?.type === 'function') {
console.log(chalk.yellow(`[normalizeResponse] #3: fixing tool_call`))
log(`#3: fixing tool_call`)
resolvedArguments = safeJsonParse(resolvedArguments.function.arguments)
}
@@ -66,7 +68,7 @@ export function normalizeResponse(response: any, tools?: Map<string, PageAgentTo
!resolvedArguments?.next_goal &&
!resolvedArguments?.thinking
) {
console.log(chalk.yellow(`[normalizeResponse] #4: fixing tool_call`))
log(`#4: fixing tool_call`)
resolvedArguments = { action: safeJsonParse(resolvedArguments) }
}
} else {
@@ -90,7 +92,7 @@ export function normalizeResponse(response: any, tools?: Map<string, PageAgentTo
// fix incomplete formats
if (!resolvedArguments.action) {
console.log(chalk.yellow(`[normalizeResponse] #5: fixing tool_call`))
log(`#5: fixing tool_call`)
resolvedArguments.action = { name: 'wait', input: { seconds: 1 } }
}
@@ -149,9 +151,7 @@ function validateAction(action: any, tools: Map<string, PageAgentTool>): any {
(k) => !(schema.shape as Record<string, z.ZodType>)[k].safeParse(undefined).success
)
if (requiredKey) {
console.log(
chalk.yellow(`[normalizeResponse] coercing primitive action input for "${toolName}"`)
)
log(`coercing primitive action input for "${toolName}"`)
value = { [requiredKey]: value }
}
}
+7 -3
View File
@@ -1,6 +1,6 @@
import chalk from 'chalk'
export { normalizeResponse } from './autoFixer'
export * from './autoFixer'
export async function waitFor(seconds: number): Promise<void> {
await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
@@ -72,11 +72,15 @@ export async function fetchLlmsTxt(url: string): Promise<string | null> {
if (res.ok) {
result = await res.text()
console.log(chalk.green(`[llms.txt] Found (${result.length} chars)`))
if (result.length > 1000) {
console.log(chalk.yellow(`[llms.txt] Truncating to 1000 chars`))
result = truncate(result, 1000)
}
} else {
console.log(chalk.gray(`[llms.txt] ${res.status} for ${endpoint}`))
console.debug(chalk.gray(`[llms.txt] ${res.status} for ${endpoint}`))
}
} catch (e) {
console.log(chalk.gray(`[llms.txt] Failed for ${endpoint}`), e)
console.debug(chalk.gray(`[llms.txt] not found for ${endpoint}`), e)
}
llmsTxtCache.set(origin, result)
return result
+1
View File
@@ -30,6 +30,7 @@ export default defineConfig({
external: [
'chalk',
'zod',
'zod/v4',
// all the internal packages
/^@page-agent\//,
],
+9 -7
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/ext",
"private": true,
"version": "0.1.8",
"version": "0.1.15",
"type": "module",
"scripts": {
"dev": "wxt",
@@ -38,12 +38,14 @@
"wxt": "^0.20.18"
},
"dependencies": {
"@page-agent/core": "1.4.3",
"@page-agent/llms": "1.4.3",
"@page-agent/page-controller": "1.4.3",
"@page-agent/ui": "1.4.3",
"@page-agent/core": "1.5.3",
"@page-agent/llms": "1.5.3",
"@page-agent/page-controller": "1.5.3",
"@page-agent/ui": "1.5.3",
"ai-motion": "^0.4.8",
"chalk": "^5.6.2",
"zod": "^4.3.5"
"chalk": "^5.6.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
}
}
@@ -1,4 +1,4 @@
import { type PageAgentConfig, PageAgentCore } from '@page-agent/core'
import { type AgentConfig, PageAgentCore } from '@page-agent/core'
import { RemotePageController } from './RemotePageController'
import { TabsController } from './TabsController'
@@ -17,7 +17,7 @@ function detectLanguage(): 'en-US' | 'zh-CN' {
* - can be used from a side panel or a content script
*/
export class MultiPageAgent extends PageAgentCore {
constructor(config: Omit<PageAgentConfig, 'pageController'> & { includeInitialTab?: boolean }) {
constructor(config: AgentConfig & { includeInitialTab?: boolean }) {
// multi page controller
const tabsController = new TabsController()
const pageController = new RemotePageController(tabsController)
+1 -1
View File
@@ -6,7 +6,7 @@
* - switch_to_tab: Switch to an existing tab
* - close_tab: Close a tab (optionally switch to another)
*/
import * as z from 'zod'
import * as z from 'zod/v4'
import type { TabsController } from './TabsController'
+35 -13
View File
@@ -16,7 +16,13 @@ import { DEMO_CONFIG, migrateLegacyEndpoint } from './constants'
/** Language preference: undefined means follow system */
export type LanguagePreference = SupportedLanguage | undefined
export interface ExtConfig extends LLMConfig {
export interface AdvancedConfig {
maxSteps?: number
systemInstruction?: string
experimentalLlmsTxt?: boolean
}
export interface ExtConfig extends LLMConfig, AdvancedConfig {
language?: LanguagePreference
}
@@ -40,9 +46,10 @@ export function useAgent(): UseAgentResult {
const [config, setConfig] = useState<ExtConfig | null>(null)
useEffect(() => {
chrome.storage.local.get(['llmConfig', 'language']).then((result) => {
chrome.storage.local.get(['llmConfig', 'language', 'advancedConfig']).then((result) => {
let llmConfig = (result.llmConfig as LLMConfig) ?? DEMO_CONFIG
const language = (result.language as SupportedLanguage) || undefined
const advancedConfig = (result.advancedConfig as AdvancedConfig) ?? {}
// Auto-migrate legacy testing endpoints
const migrated = migrateLegacyEndpoint(llmConfig)
@@ -53,14 +60,18 @@ export function useAgent(): UseAgentResult {
chrome.storage.local.set({ llmConfig: DEMO_CONFIG })
}
setConfig({ ...llmConfig, language })
setConfig({ ...llmConfig, ...advancedConfig, language })
})
}, [])
useEffect(() => {
if (!config) return
const agent = new MultiPageAgent(config)
const { systemInstruction, ...agentConfig } = config
const agent = new MultiPageAgent({
...agentConfig,
instructions: systemInstruction ? { system: systemInstruction } : undefined,
})
agentRef.current = agent
const handleStatusChange = (e: Event) => {
@@ -106,15 +117,26 @@ export function useAgent(): UseAgentResult {
agentRef.current?.stop()
}, [])
const configure = useCallback(async ({ language, ...llmConfig }: ExtConfig) => {
await chrome.storage.local.set({ llmConfig })
if (language) {
await chrome.storage.local.set({ language })
} else {
await chrome.storage.local.remove('language')
}
setConfig({ ...llmConfig, language })
}, [])
const configure = useCallback(
async ({
language,
maxSteps,
systemInstruction,
experimentalLlmsTxt,
...llmConfig
}: ExtConfig) => {
await chrome.storage.local.set({ llmConfig })
if (language) {
await chrome.storage.local.set({ language })
} else {
await chrome.storage.local.remove('language')
}
const advancedConfig: AdvancedConfig = { maxSteps, systemInstruction, experimentalLlmsTxt }
await chrome.storage.local.set({ advancedConfig })
setConfig({ ...llmConfig, ...advancedConfig, language })
},
[]
)
return {
status,
@@ -1,4 +1,14 @@
import { Copy, CornerUpLeft, Eye, EyeOff, HatGlasses, Home, Loader2, Scale } from 'lucide-react'
import {
ChevronDown,
Copy,
CornerUpLeft,
Eye,
EyeOff,
HatGlasses,
Home,
Loader2,
Scale,
} from 'lucide-react'
import { useEffect, useState } from 'react'
import { siGithub } from 'simple-icons'
@@ -6,6 +16,7 @@ import { DEMO_API_KEY, DEMO_BASE_URL, DEMO_MODEL, isTestingEndpoint } from '@/ag
import type { ExtConfig, LanguagePreference } from '@/agent/useAgent'
import { Button } from '@/components/ui/button'
import { Input } from '@/components/ui/input'
import { Switch } from '@/components/ui/switch'
interface ConfigPanelProps {
config: ExtConfig | null
@@ -18,18 +29,26 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const [baseURL, setBaseURL] = useState(config?.baseURL || DEMO_BASE_URL)
const [model, setModel] = useState(config?.model || DEMO_MODEL)
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 [advancedOpen, setAdvancedOpen] = useState(false)
const [saving, setSaving] = useState(false)
const [userAuthToken, setUserAuthToken] = useState<string>('')
const [copied, setCopied] = useState(false)
const [showToken, setShowToken] = useState(false)
const [showApiKey, setShowApiKey] = useState(false)
// Update local state when config prop changes
useEffect(() => {
setApiKey(config?.apiKey || DEMO_API_KEY)
setBaseURL(config?.baseURL || DEMO_BASE_URL)
setModel(config?.model || DEMO_MODEL)
setLanguage(config?.language)
setMaxSteps(config?.maxSteps)
setSystemInstruction(config?.systemInstruction ?? '')
setExperimentalLlmsTxt(config?.experimentalLlmsTxt ?? false)
}, [config])
// Poll for user auth token every second until found
@@ -67,7 +86,15 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const handleSave = async () => {
setSaving(true)
try {
await onSave({ apiKey, baseURL, model, language })
await onSave({
apiKey,
baseURL,
model,
language,
maxSteps: maxSteps || undefined,
systemInstruction: systemInstruction || undefined,
experimentalLlmsTxt,
})
} finally {
setSaving(false)
}
@@ -87,28 +114,11 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</Button>
</div>
{/* Testing API notice */}
{isTestingEndpoint(baseURL) && (
<div className="p-2.5 rounded-md border border-amber-500/30 bg-amber-500/5 text-[10px] 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{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank"
rel="noopener noreferrer"
className="underline hover:text-foreground"
>
Terms of Use & Privacy Policy
</a>
. No sensitive data. No guaranteed availability.
</div>
)}
{/* User Auth Token Section */}
<div className="flex flex-col gap-1.5 p-3 bg-muted/50 rounded-md border">
<label className="text-xs font-medium text-muted-foreground">User Auth Token</label>
<p className="text-[10px] text-muted-foreground mb-1">
Add this token to a website's localStorage to give it authorization to call this extension
Give a website the ability to call this extension.
</p>
<div className="flex gap-2 items-center">
<Input
@@ -153,6 +163,23 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
/>
</div>
{/* Testing API notice */}
{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{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank"
rel="noopener noreferrer"
className="underline hover:text-foreground"
>
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
@@ -197,6 +224,52 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</select>
</div>
{/* Advanced Config */}
<button
type="button"
onClick={() => setAdvancedOpen(!advancedOpen)}
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)' }}
/>
</button>
{advancedOpen && (
<>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Max Steps</label>
<Input
type="number"
placeholder="40"
min={1}
max={200}
value={maxSteps ?? ''}
onChange={(e) => setMaxSteps(e.target.value ? Number(e.target.value) : undefined)}
className="text-xs h-8 [&::-webkit-inner-spin-button]:appearance-none [&::-webkit-outer-spin-button]:appearance-none [-moz-appearance:textfield]"
/>
</div>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">System Instruction</label>
<textarea
placeholder="Additional instructions for the agent..."
value={systemInstruction}
onChange={(e) => setSystemInstruction(e.target.value)}
rows={3}
className="text-xs rounded-md border border-input bg-background px-3 py-2 resize-y min-h-[60px]"
/>
</div>
<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} />
</label>
</>
)}
<div className="flex gap-2 mt-2">
<Button variant="outline" onClick={onClose} className="flex-1 h-8 text-xs cursor-pointer">
Cancel
@@ -1,4 +1,4 @@
import { AlertTriangle, RotateCcw } from 'lucide-react'
import { AlertTriangle, Eraser, RotateCcw } from 'lucide-react'
import { Component, type ErrorInfo, type ReactNode } from 'react'
import { Button } from '@/components/ui/button'
@@ -27,6 +27,11 @@ export class ErrorBoundary extends Component<Props, State> {
window.location.reload()
}
handleResetConfig = async () => {
await chrome.storage.local.remove(['llmConfig', 'language', 'advancedConfig'])
window.location.reload()
}
render() {
if (!this.state.hasError) {
return this.props.children
@@ -39,10 +44,16 @@ export class ErrorBoundary extends Component<Props, State> {
<p className="text-sm text-muted-foreground mb-4 max-w-xs">
{this.state.error?.message || 'An unexpected error occurred'}
</p>
<Button variant="outline" size="sm" onClick={this.handleReload}>
<RotateCcw className="size-3.5 mr-2" />
Reload Panel
</Button>
<div className="flex gap-2">
<Button variant="outline" size="sm" onClick={this.handleResetConfig}>
<Eraser className="size-3.5 mr-2" />
Reset Config
</Button>
<Button variant="outline" size="sm" onClick={this.handleReload}>
<RotateCcw className="size-3.5 mr-2" />
Reload Panel
</Button>
</div>
</div>
)
}
@@ -43,20 +43,24 @@ export function MotionOverlay({ active }: { active: boolean }) {
const motionRef = useRef<Motion | null>(null)
useEffect(() => {
const mode = document.documentElement.classList.contains('dark') ? 'dark' : 'light'
const motion = new Motion({
mode,
borderWidth: 4,
borderRadius: 14,
glowWidth: mode === 'dark' ? 120 : 60,
styles: { position: 'absolute', inset: '0' },
})
motionRef.current = motion
containerRef.current!.appendChild(motion.element)
motion.autoResize(containerRef.current!)
try {
const mode = document.documentElement.classList.contains('dark') ? 'dark' : 'light'
const motion = new Motion({
mode,
borderWidth: 4,
borderRadius: 14,
glowWidth: mode === 'dark' ? 120 : 60,
styles: { position: 'absolute', inset: '0' },
})
motionRef.current = motion
containerRef.current!.appendChild(motion.element)
motion.autoResize(containerRef.current!)
} catch (e) {
console.warn('[MotionOverlay] Motion unavailable:', e)
}
return () => {
motion.dispose()
motionRef.current?.dispose()
motionRef.current = null
}
}, [])
+3
View File
@@ -37,6 +37,9 @@ export default defineConfig({
},
},
}),
zip: {
artifactTemplate: 'page-agent-ext-{{version}}-{{browser}}.zip',
},
manifest: {
default_locale: 'en',
name: '__MSG_extName__',
+7 -2
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/llms",
"version": "1.4.3",
"version": "1.5.3",
"type": "module",
"main": "./dist/lib/page-agent-llms.js",
"module": "./dist/lib/page-agent-llms.js",
@@ -37,7 +37,12 @@
"postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
},
"dependencies": {
"chalk": "^5.6.2",
"chalk": "^5.6.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
},
"devDependencies": {
"zod": "^4.3.5"
}
}
+1 -1
View File
@@ -1,7 +1,7 @@
/**
* OpenAI Client implementation
*/
import * as z from 'zod'
import * as z from 'zod/v4'
import { InvokeError, InvokeErrorType } from './errors'
import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
+1 -1
View File
@@ -1,7 +1,7 @@
/**
* Core types for LLM integration
*/
import type * as z from 'zod'
import type * as z from 'zod/v4'
/**
* Message format - OpenAI standard (industry standard)
+7 -4
View File
@@ -2,13 +2,11 @@
* Utility functions for LLM integration
*/
import chalk from 'chalk'
import * as z from 'zod'
import * as z from 'zod/v4'
import type { Tool } from './types'
function debug(message: string) {
console.debug(chalk.gray('[LLM]'), message)
}
const debug = console.debug.bind(console, chalk.gray('[LLM]'))
/**
* Convert Zod schema to OpenAI tool format
@@ -75,6 +73,11 @@ export function modelPatch(body: Record<string, any>) {
} else if (modelName.startsWith('gpt-51')) {
debug('Applying GPT-51 patch: disable reasoning')
body.reasoning_effort = 'none'
} else if (modelName.startsWith('gpt-54')) {
debug(
'Applying GPT-5.4 patch: skip reasoning_effort because chat/completions rejects it with function tools'
)
delete body.reasoning_effort
} else if (modelName.startsWith('gpt-5-mini')) {
debug('Applying GPT-5-mini patch: set reasoning effort to low, temperature to 1')
body.reasoning_effort = 'low'
+1 -1
View File
@@ -25,7 +25,7 @@ export default defineConfig({
},
outDir: resolve(__dirname, 'dist', 'lib'),
rollupOptions: {
external: ['chalk', 'zod'],
external: ['chalk', 'zod', 'zod/v4'],
},
minify: false,
sourcemap: true,
+11 -6
View File
@@ -1,7 +1,7 @@
{
"name": "page-agent",
"private": false,
"version": "1.4.3",
"version": "1.5.3",
"type": "module",
"main": "./dist/esm/page-agent.js",
"module": "./dist/esm/page-agent.js",
@@ -44,11 +44,16 @@
"postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
},
"dependencies": {
"@page-agent/core": "1.4.3",
"@page-agent/llms": "1.4.3",
"@page-agent/page-controller": "1.4.3",
"@page-agent/ui": "1.4.3",
"chalk": "^5.6.2",
"@page-agent/core": "1.5.3",
"@page-agent/llms": "1.5.3",
"@page-agent/page-controller": "1.5.3",
"@page-agent/ui": "1.5.3",
"chalk": "^5.6.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
},
"devDependencies": {
"zod": "^4.3.5"
}
}
+1
View File
@@ -30,6 +30,7 @@ export default defineConfig({
external: [
'chalk',
'zod',
'zod/v4',
// all the internal packages
/^@page-agent\//,
],
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/page-controller",
"version": "1.4.3",
"version": "1.5.3",
"type": "module",
"main": "./dist/lib/page-controller.js",
"module": "./dist/lib/page-controller.js",
@@ -1446,7 +1446,7 @@ export default (
/**
* @edit add `data-browser-use-ignore` attribute
*/
if (node.dataset?.browserUseIgnore === 'true') {
if (node.dataset?.browserUseIgnore === 'true' || node.dataset?.pageAgentIgnore === 'true') {
return null // Skip this node and its children
}
@@ -8,13 +8,7 @@ import cursorStyles from './cursor.module.css'
export class SimulatorMask {
shown: boolean = false
wrapper = document.createElement('div')
motion = new Motion({
mode: isPageDark() ? 'dark' : 'light',
styles: {
position: 'absolute',
inset: '0',
},
})
motion: Motion | null = null
#cursor = document.createElement('div')
@@ -28,9 +22,19 @@ export class SimulatorMask {
this.wrapper.id = 'page-agent-runtime_simulator-mask'
this.wrapper.className = styles.wrapper
this.wrapper.setAttribute('data-browser-use-ignore', 'true')
this.wrapper.setAttribute('data-page-agent-ignore', 'true')
this.wrapper.appendChild(this.motion.element)
this.motion.autoResize(this.wrapper)
try {
const motion = new Motion({
mode: isPageDark() ? 'dark' : 'light',
styles: { position: 'absolute', inset: '0' },
})
this.motion = motion
this.wrapper.appendChild(motion.element)
motion.autoResize(this.wrapper)
} catch (e) {
console.warn('[SimulatorMask] Motion overlay unavailable:', e)
}
// Capture all mouse, keyboard, and wheel events
this.wrapper.addEventListener('click', (e) => {
@@ -144,8 +148,8 @@ export class SimulatorMask {
if (this.shown) return
this.shown = true
this.motion.start()
this.motion.fadeIn()
this.motion?.start()
this.motion?.fadeIn()
this.wrapper.style.display = 'block'
@@ -162,8 +166,8 @@ export class SimulatorMask {
if (!this.shown) return
this.shown = false
this.motion.fadeOut()
this.motion.pause()
this.motion?.fadeOut()
this.motion?.pause()
this.#cursor.classList.remove(cursorStyles.clicking)
@@ -173,7 +177,7 @@ export class SimulatorMask {
}
dispose() {
this.motion.dispose()
this.motion?.dispose()
this.wrapper.remove()
}
}
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/ui",
"version": "1.4.3",
"version": "1.5.3",
"type": "module",
"main": "./dist/lib/page-agent-ui.js",
"module": "./dist/lib/page-agent-ui.js",
+1
View File
@@ -373,6 +373,7 @@ export class Panel {
wrapper.id = 'page-agent-runtime_agent-panel'
wrapper.className = styles.wrapper
wrapper.setAttribute('data-browser-use-ignore', 'true')
wrapper.setAttribute('data-page-agent-ignore', 'true')
wrapper.innerHTML = `
<div class="${styles.background}"></div>
+1 -1
View File
@@ -62,7 +62,7 @@ Located in `src/components/ui/`:
src/
├── pages/
│ ├── home/
│ │ ├── HomeContent.tsx # Homepage sections
│ │ ├── index.tsx # Homepage
│ │ └── ...Section.tsx
│ └── docs/
│ ├── index.tsx # Docs route switch
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/website",
"private": true,
"version": "1.4.3",
"version": "1.5.3",
"type": "module",
"scripts": {
"dev": "vite --host 0.0.0.0",
+2 -2
View File
@@ -1,8 +1,8 @@
// Demo build (auto-init with demo LLM, for quick testing)
export const CDN_DEMO_URL =
'https://cdn.jsdelivr.net/npm/page-agent@1.4.3/dist/iife/page-agent.demo.js'
'https://cdn.jsdelivr.net/npm/page-agent@1.5.3/dist/iife/page-agent.demo.js'
export const CDN_DEMO_CN_URL =
'https://registry.npmmirror.com/page-agent/1.4.3/files/dist/iife/page-agent.demo.js'
'https://registry.npmmirror.com/page-agent/1.5.3/files/dist/iife/page-agent.demo.js'
// Demo LLM for website testing (homepage quick trial uses flash)
export const DEMO_MODEL = 'qwen3.5-flash'
@@ -181,7 +181,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{
name: 'maxSteps',
type: 'number',
defaultValue: '20',
defaultValue: '40',
description: isZh ? '每个任务的最大步骤数' : 'Maximum number of steps per task',
},
{
@@ -16,6 +16,22 @@ export default function CustomTools() {
</p>
<div className="space-y-8">
<section>
<Heading id="zod-version" className="text-2xl font-bold mb-4">
{isZh ? 'Zod 版本' : 'Zod Version'}
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
? 'Page Agent 使用 Zod 定义工具的输入 schema。支持 Zod 3 (>=3.25.0) 和 Zod 4,请从 zod/v4 子路径导入。不支持 Zod Mini。'
: 'Page Agent uses Zod for tool input schemas. Both Zod 3 (>=3.25.0) and Zod 4 are supported. Always import from the zod/v4 subpath. Zod Mini is not supported.'}
</p>
<CodeEditor
code={`// Zod 3 (>=3.25.0) or Zod 4
import { z } from 'zod/v4'`}
language="javascript"
/>
</section>
<section>
<Heading id="define-tools" className="text-2xl font-bold mb-4">
{isZh ? '定义工具' : 'Define Tools'}
@@ -27,7 +43,7 @@ export default function CustomTools() {
</p>
<CodeEditor
code={`import { z } from 'zod'
code={`import { z } from 'zod/v4'
import { PageAgent, tool } from 'page-agent'
const pageAgent = new PageAgent({
@@ -10,11 +10,11 @@ const BASELINE = new Set([
'gemini-3-flash',
'deepseek-3.2',
'qwen3.5-plus',
'qwen3.5-flash',
])
// Models grouped by brand, newest first
const MODEL_GROUPS: Record<string, string[]> = {
OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'],
Qwen: [
'qwen3.5-plus',
'qwen3.5-flash',
@@ -23,6 +23,7 @@ const MODEL_GROUPS: Record<string, string[]> = {
'qwen-3-plus',
'qwen3:14b (ollama)',
],
OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'],
DeepSeek: ['deepseek-3.2'],
Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'],
Anthropic: [
@@ -1,10 +1,10 @@
import { Suspense, lazy } from 'react'
import HeroSection from './home/HeroSection'
import HeroSection from './HeroSection'
const FeaturesSection = lazy(() => import('./home/FeaturesSection'))
const ScenariosSection = lazy(() => import('./home/ScenariosSection'))
const OneMoreThingSection = lazy(() => import('./home/OneMoreThingSection'))
const FeaturesSection = lazy(() => import('./FeaturesSection'))
const ScenariosSection = lazy(() => import('./ScenariosSection'))
const OneMoreThingSection = lazy(() => import('./OneMoreThingSection'))
export default function HomePage() {
return (
+6 -4
View File
@@ -3,9 +3,9 @@ import { Route, Switch, useLocation } from 'wouter'
import Footer from './components/Footer'
import Header from './components/Header'
import HomePage from './pages/Home'
import HomePage from './pages/home'
const docsImport = () => import('./pages/docs/index')
const docsImport = () => import('./pages/docs')
const DocsPages = lazy(docsImport)
function ScrollToTop() {
@@ -18,8 +18,10 @@ function ScrollToTop() {
export default function Router() {
useEffect(() => {
const id = requestIdleCallback(() => docsImport())
return () => cancelIdleCallback(id)
const schedule = globalThis.requestIdleCallback ?? ((cb: () => void) => setTimeout(cb, 1))
const cancel = globalThis.cancelIdleCallback ?? clearTimeout
const id = schedule(() => docsImport())
return () => cancel(id)
}, [])
return (