Compare commits

...

50 Commits

Author SHA1 Message Date
Simon 4807d550a3 chore(version): bump version to 1.4.2 2026-03-03 21:54:41 +08:00
Simon f9722f0619 Merge branch 'main' of https://github.com/alibaba/page-agent 2026-03-03 21:53:35 +08:00
Simon e1557a5d2e Merge pull request #156 from hobostay/main
fix(actions): remove debug console.log statements
2026-03-03 21:53:05 +08:00
Simon 06280c2ba5 chore(core): add wait time between steps for the page to react 2026-03-03 21:51:10 +08:00
Simon 645a7ceb52 feat(website): loading time optimize 2026-03-03 21:38:29 +08:00
hobostay a47c72ce84 fix(actions): remove debug console.log statements
Remove [SCROLL DEBUG] console.log statements that were left over
from development in scrollVertically and scrollHorizontally
functions. These debug statements should not be in production code.
2026-03-03 21:36:59 +08:00
Simon dcc6cd1cf3 feat(website): reduce white screen time 2026-03-03 21:05:16 +08:00
Simon b4b9f6ce2d chore(version): bump version to 1.4.1 2026-03-03 20:56:24 +08:00
Simon 14e31e6ec4 Merge pull request #155 from alibaba/fix/panel-time
fix(panel): remove timestamp (not well defined)
2026-03-03 20:55:26 +08:00
Simon 69f2478fd7 fix(panel): remove timestamp (not well defined) 2026-03-03 20:52:55 +08:00
Simon fe792f1ceb chore(docs): remove description files 2026-03-02 17:36:10 +08:00
Simon d1d27a76de style: homepage misc 2026-02-27 22:24:55 +08:00
Simon 3e7e99420a docs: changelog 2026-02-27 22:05:55 +08:00
Simon 0ffd221a61 chore(version): bump version to 1.4.0 2026-02-27 21:59:00 +08:00
Simon ee208b9779 Merge pull request #148 from alibaba/feat/drop-hash-router
feat(website): drop hash route; upgrade styling
2026-02-27 21:33:30 +08:00
Simon 6ad20c8f45 feat(website): styling 2026-02-27 21:30:21 +08:00
Simon ff4caaec22 docs(website): update AGENTS.md 2026-02-27 20:45:36 +08:00
Simon 91ae86f56e style(website): fix height; clean up code 2026-02-27 20:42:24 +08:00
Simon c2daf13ead feat(website): simplify heading api 2026-02-27 20:36:00 +08:00
Simon ce2258fe16 feat(website): implement SPA route handling and remove 404.html 2026-02-27 20:07:46 +08:00
Simon 68d68182e2 feat(website): drop hash-based router 2026-02-27 19:46:44 +08:00
Simon 5f74f98a97 feat: update Qwen model list and add new model versions 2026-02-27 18:47:02 +08:00
Simon 07b4dc32f7 feat: add legacy endpoint migration and testing endpoint notice 2026-02-27 17:50:10 +08:00
Simon 9d5c8b2302 chore: update CI configuration 2026-02-27 17:23:41 +08:00
Simon 0c61ead38f chore: remove mention of release notes 2026-02-27 17:23:25 +08:00
Simon d92ad8f959 Merge pull request #145 from alibaba/feat/free-qwen-by-default
feat: update testing LLM endpoint and terms of use
2026-02-27 17:15:47 +08:00
Simon a51772e191 style(website): fix layout 2026-02-27 17:12:02 +08:00
Simon 89c83f454d feat: update terms and default llm endpoint 2026-02-27 17:09:54 +08:00
Simon 7f67463a24 Merge branch 'main' into feat/free-qwen-by-default 2026-02-27 15:51:19 +08:00
Simon 2311c1918a Merge pull request #146 from alibaba/dependabot/npm_and_yarn/development-dependencies-10a0d14ef2 2026-02-25 17:50:11 +08:00
Simon b45a2af9bf Merge pull request #147 from alibaba/feat/robust-llm-toolcall 2026-02-25 17:25:05 +08:00
Simon b4377ed152 chore: remove unused env.d.ts file 2026-02-25 17:19:09 +08:00
Simon b7be29d792 feat(core): enhance tollcall validation with better error reporting 2026-02-25 17:17:35 +08:00
Simon cbe223dac5 fix(core): auto-wrap primitive action input in normalizeResponse
Small models sometimes output single-field tool args as primitives
(e.g. {"click_element_by_index": 2} instead of {"index": 2}).
normalizeResponse now accepts an optional tools map and wraps
such values using the tool schema. Renamed invoke tools to macroTool.
2026-02-25 17:01:45 +08:00
Simon 22fe448d95 refactor: unify zod imports 2026-02-25 16:18:56 +08:00
Simon 49bdc70c78 chore: improve error logging 2026-02-25 16:13:39 +08:00
dependabot[bot] d6bd6a7170 chore(deps-dev): bump the development-dependencies group across 1 directory with 18 updates
Bumps the development-dependencies group with 17 updates in the / directory:

| Package | From | To |
| --- | --- | --- |
| [@commitlint/cli](https://github.com/conventional-changelog/commitlint/tree/HEAD/@commitlint/cli) | `20.4.1` | `20.4.2` |
| [@commitlint/config-conventional](https://github.com/conventional-changelog/commitlint/tree/HEAD/@commitlint/config-conventional) | `20.4.1` | `20.4.2` |
| [@microsoft/api-extractor](https://github.com/microsoft/rushstack/tree/HEAD/apps/api-extractor) | `7.56.3` | `7.57.3` |
| [@tailwindcss/vite](https://github.com/tailwindlabs/tailwindcss/tree/HEAD/packages/@tailwindcss-vite) | `4.1.18` | `4.2.1` |
| [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) | `25.2.2` | `25.3.0` |
| [dotenv](https://github.com/motdotla/dotenv) | `17.2.4` | `17.3.1` |
| [eslint-plugin-react-dom](https://github.com/Rel1cx/eslint-react/tree/HEAD/packages/plugins/eslint-plugin-react-dom) | `2.12.2` | `2.13.0` |
| [eslint-plugin-react-refresh](https://github.com/ArnaudBarre/eslint-plugin-react-refresh) | `0.5.0` | `0.5.2` |
| [eslint-plugin-react-x](https://github.com/Rel1cx/eslint-react/tree/HEAD/packages/plugins/eslint-plugin-react-x) | `2.12.2` | `2.13.0` |
| [typescript-eslint](https://github.com/typescript-eslint/typescript-eslint/tree/HEAD/packages/typescript-eslint) | `8.55.0` | `8.56.1` |
| [@types/chrome](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/chrome) | `0.1.36` | `0.1.37` |
| [@types/react](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/react) | `19.2.13` | `19.2.14` |
| [lucide-react](https://github.com/lucide-icons/lucide/tree/HEAD/packages/lucide-react) | `0.563.0` | `0.575.0` |
| [motion](https://github.com/motiondivision/motion) | `12.34.0` | `12.34.3` |
| [simple-icons](https://github.com/simple-icons/simple-icons) | `16.8.0` | `16.9.0` |
| [tailwind-merge](https://github.com/dcastil/tailwind-merge) | `3.4.0` | `3.5.0` |
| [wxt](https://github.com/wxt-dev/wxt) | `0.20.14` | `0.20.18` |



Updates `@commitlint/cli` from 20.4.1 to 20.4.2
- [Release notes](https://github.com/conventional-changelog/commitlint/releases)
- [Changelog](https://github.com/conventional-changelog/commitlint/blob/master/@commitlint/cli/CHANGELOG.md)
- [Commits](https://github.com/conventional-changelog/commitlint/commits/v20.4.2/@commitlint/cli)

Updates `@commitlint/config-conventional` from 20.4.1 to 20.4.2
- [Release notes](https://github.com/conventional-changelog/commitlint/releases)
- [Changelog](https://github.com/conventional-changelog/commitlint/blob/master/@commitlint/config-conventional/CHANGELOG.md)
- [Commits](https://github.com/conventional-changelog/commitlint/commits/v20.4.2/@commitlint/config-conventional)

Updates `@microsoft/api-extractor` from 7.56.3 to 7.57.3
- [Changelog](https://github.com/microsoft/rushstack/blob/main/apps/api-extractor/CHANGELOG.md)
- [Commits](https://github.com/microsoft/rushstack/commits/@microsoft/api-extractor_v7.57.3/apps/api-extractor)

Updates `@tailwindcss/vite` from 4.1.18 to 4.2.1
- [Release notes](https://github.com/tailwindlabs/tailwindcss/releases)
- [Changelog](https://github.com/tailwindlabs/tailwindcss/blob/main/CHANGELOG.md)
- [Commits](https://github.com/tailwindlabs/tailwindcss/commits/v4.2.1/packages/@tailwindcss-vite)

Updates `@types/node` from 25.2.2 to 25.3.0
- [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases)
- [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/node)

Updates `dotenv` from 17.2.4 to 17.3.1
- [Changelog](https://github.com/motdotla/dotenv/blob/master/CHANGELOG.md)
- [Commits](https://github.com/motdotla/dotenv/compare/v17.2.4...v17.3.1)

Updates `eslint-plugin-react-dom` from 2.12.2 to 2.13.0
- [Release notes](https://github.com/Rel1cx/eslint-react/releases)
- [Changelog](https://github.com/Rel1cx/eslint-react/blob/main/CHANGELOG.md)
- [Commits](https://github.com/Rel1cx/eslint-react/commits/v2.13.0/packages/plugins/eslint-plugin-react-dom)

Updates `eslint-plugin-react-refresh` from 0.5.0 to 0.5.2
- [Release notes](https://github.com/ArnaudBarre/eslint-plugin-react-refresh/releases)
- [Changelog](https://github.com/ArnaudBarre/eslint-plugin-react-refresh/blob/main/CHANGELOG.md)
- [Commits](https://github.com/ArnaudBarre/eslint-plugin-react-refresh/compare/v0.5.0...v0.5.2)

Updates `eslint-plugin-react-x` from 2.12.2 to 2.13.0
- [Release notes](https://github.com/Rel1cx/eslint-react/releases)
- [Changelog](https://github.com/Rel1cx/eslint-react/blob/main/CHANGELOG.md)
- [Commits](https://github.com/Rel1cx/eslint-react/commits/v2.13.0/packages/plugins/eslint-plugin-react-x)

Updates `typescript-eslint` from 8.55.0 to 8.56.1
- [Release notes](https://github.com/typescript-eslint/typescript-eslint/releases)
- [Changelog](https://github.com/typescript-eslint/typescript-eslint/blob/main/packages/typescript-eslint/CHANGELOG.md)
- [Commits](https://github.com/typescript-eslint/typescript-eslint/commits/v8.56.1/packages/typescript-eslint)

Updates `@types/chrome` from 0.1.36 to 0.1.37
- [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases)
- [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/chrome)

Updates `@types/react` from 19.2.13 to 19.2.14
- [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases)
- [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/react)

Updates `lucide-react` from 0.563.0 to 0.575.0
- [Release notes](https://github.com/lucide-icons/lucide/releases)
- [Commits](https://github.com/lucide-icons/lucide/commits/0.575.0/packages/lucide-react)

Updates `motion` from 12.34.0 to 12.34.3
- [Changelog](https://github.com/motiondivision/motion/blob/main/CHANGELOG.md)
- [Commits](https://github.com/motiondivision/motion/compare/v12.34.0...v12.34.3)

Updates `simple-icons` from 16.8.0 to 16.9.0
- [Release notes](https://github.com/simple-icons/simple-icons/releases)
- [Commits](https://github.com/simple-icons/simple-icons/compare/16.8.0...16.9.0)

Updates `tailwind-merge` from 3.4.0 to 3.5.0
- [Release notes](https://github.com/dcastil/tailwind-merge/releases)
- [Commits](https://github.com/dcastil/tailwind-merge/compare/v3.4.0...v3.5.0)

Updates `tailwindcss` from 4.1.18 to 4.2.1
- [Release notes](https://github.com/tailwindlabs/tailwindcss/releases)
- [Changelog](https://github.com/tailwindlabs/tailwindcss/blob/main/CHANGELOG.md)
- [Commits](https://github.com/tailwindlabs/tailwindcss/commits/v4.2.1/packages/tailwindcss)

Updates `wxt` from 0.20.14 to 0.20.18
- [Release notes](https://github.com/wxt-dev/wxt/releases)
- [Commits](https://github.com/wxt-dev/wxt/compare/wxt-v0.20.14...wxt-v0.20.18)

---
updated-dependencies:
- dependency-name: "@commitlint/cli"
  dependency-version: 20.4.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: "@commitlint/config-conventional"
  dependency-version: 20.4.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: "@microsoft/api-extractor"
  dependency-version: 7.57.3
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: "@tailwindcss/vite"
  dependency-version: 4.2.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: "@types/node"
  dependency-version: 25.3.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: dotenv
  dependency-version: 17.3.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: eslint-plugin-react-dom
  dependency-version: 2.13.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: eslint-plugin-react-refresh
  dependency-version: 0.5.2
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: eslint-plugin-react-x
  dependency-version: 2.13.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: typescript-eslint
  dependency-version: 8.56.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: "@types/chrome"
  dependency-version: 0.1.37
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: "@types/react"
  dependency-version: 19.2.14
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: lucide-react
  dependency-version: 0.575.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: motion
  dependency-version: 12.34.3
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: simple-icons
  dependency-version: 16.9.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: tailwind-merge
  dependency-version: 3.5.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: tailwindcss
  dependency-version: 4.2.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: wxt
  dependency-version: 0.20.18
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-02-23 20:54:10 +00:00
Simon 2b99620de3 feat: add qwen3.5-plus for testing and make it default 2026-02-24 00:59:42 +08:00
Simon d913dd7bd0 chore(docs): move docs 2026-02-24 00:13:36 +08:00
Simon 8cb57befb3 feat(model): disable thinking for Qwen model patch 2026-02-23 17:30:35 +08:00
Simon b1be05309b feat(website): wording and style 2026-02-14 18:54:43 +08:00
Simon e5cf60df1b feat(website): loading speed; model list 2026-02-14 17:41:14 +08:00
Simon 58a3d5fbc6 feat(website): add "One More Thing" section; auto scroll 2026-02-14 17:30:00 +08:00
Simon 6abe75f199 docs(ext): clarify data handling and privacy in PRIVACY.md 2026-02-14 17:03:41 +08:00
Simon e27ebda960 chore(ext): docs and locales 2026-02-14 16:51:37 +08:00
Simon 9b603d90ba docs: update limitations page 2026-02-14 16:23:34 +08:00
Simon b89228693d feat(ext): add lang setting 2026-02-14 16:10:46 +08:00
Simon 66cc9e0a3c style: pretty up; fix extension shadcn 2026-02-14 15:12:45 +08:00
Simon 53144a8021 chore(ext): rm zh doc 2026-02-14 15:12:03 +08:00
Simon 43b7c1b136 style(ext): make over 2026-02-13 19:09:46 +08:00
81 changed files with 2906 additions and 1934 deletions
+1 -1
View File
@@ -9,7 +9,7 @@ body:
Thanks for your interest in improving the project! Before submitting, please read our guidelines. Thanks for your interest in improving the project! Before submitting, please read our guidelines.
感谢您对改进项目的兴趣!提交前请阅读我们的指南。 感谢您对改进项目的兴趣!提交前请阅读我们的指南。
- [Code of Conduct](https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT.md) - [Code of Conduct](https://github.com/alibaba/page-agent/blob/main/docs/CODE_OF_CONDUCT.md)
- [Contributing Guide](https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md) - [Contributing Guide](https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md)
- type: textarea - type: textarea
+1 -1
View File
@@ -10,5 +10,5 @@ contact_links:
url: https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md url: https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md
about: How to contribute code and ideas. 如何进行贡献与提交代码。 about: How to contribute code and ideas. 如何进行贡献与提交代码。
- name: Code of Conduct / 行为准则 - name: Code of Conduct / 行为准则
url: https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT.md url: https://github.com/alibaba/page-agent/blob/main/docs/CODE_OF_CONDUCT.md
about: Community expectations and standards. 社区行为期望与标准。 about: Community expectations and standards. 社区行为期望与标准。
+1 -1
View File
@@ -9,7 +9,7 @@ body:
Thanks for your interest in improving the project! Before submitting, please read our guidelines. Thanks for your interest in improving the project! Before submitting, please read our guidelines.
感谢您对改进项目的兴趣!提交前请阅读我们的指南。 感谢您对改进项目的兴趣!提交前请阅读我们的指南。
- [Code of Conduct](https://github.com/alibaba/page-agent/blob/main/CODE_OF_CONDUCT.md) - [Code of Conduct](https://github.com/alibaba/page-agent/blob/main/docs/CODE_OF_CONDUCT.md)
- [Contributing Guide](https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md) - [Contributing Guide](https://github.com/alibaba/page-agent/blob/main/CONTRIBUTING.md)
- type: textarea - type: textarea
+1 -1
View File
@@ -22,4 +22,4 @@ Closes #(issue)
## Requirements / 要求 ## Requirements / 要求
- [ ] I have read and follow the [Code of Conduct](CODE_OF_CONDUCT.md) and [Contributing Guide](CONTRIBUTING.md) . / 我已阅读并遵守行为准则。 - [ ] I have read and follow the [Code of Conduct](../docs/CODE_OF_CONDUCT.md) and [Contributing Guide](../CONTRIBUTING.md) . / 我已阅读并遵守行为准则。
+1 -1
View File
@@ -13,7 +13,7 @@ jobs:
runs-on: ubuntu-latest runs-on: ubuntu-latest
strategy: strategy:
matrix: matrix:
node-version: [20, 24, 25] node-version: [24]
steps: steps:
- uses: actions/checkout@v6 - uses: actions/checkout@v6
-5
View File
@@ -29,11 +29,6 @@ dist-ssr
.env .env
.env.* .env.*
# Copied files for npm publish (generated by prepublishOnly)
packages/page-agent/README.md
packages/page-agent/README-zh.md
packages/page-agent/LICENSE
# extension # extension
.output .output
.wxt .wxt
+24 -32
View File
@@ -9,26 +9,33 @@
The GUI Agent Living in Your Webpage. Control web interfaces with natural language. The GUI Agent Living in Your Webpage. Control web interfaces with natural language.
🌐 **English** | [中文](./README-zh.md) 🌐 **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>
<video id="demo-video" src="https://github.com/user-attachments/assets/34d8444d-cbfb-44a3-a24e-fd5c167bb0bf" controls crossorigin muted></video> <video id="demo-video" src="https://github.com/user-attachments/assets/11aed429-b69c-49d5-8982-fa99b4a0e9a8" controls crossorigin muted></video>
--- ---
## ✨ Features ## ✨ Features
- **🎯 Easy integration** - **🎯 Easy integration**
- No need for `browser extension` / `python` / `headless browser`. - No need for `browser extension` / `python` / `headless browser`.
- Just in-page javascript. Everything happens in your web page. - Just in-page javascript. Everything happens in your web page.
- The best tool for your agent to control web pages. - The best tool for your agent to control web pages.
- **📖 Text-based DOM manipulation** - **📖 Text-based DOM manipulation**
- No screenshots. No OCR or multi-modal LLMs needed. - No screenshots. No OCR or multi-modal LLMs needed.
- No special permissions required. - No special permissions required.
- **🧠 Bring your own LLMs** - **🧠 Bring your own LLMs**
- **🎨 Pretty UI with human-in-the-loop** - **🎨 Pretty UI with human-in-the-loop**
- **🐙 Optional [chrome extension](https://alibaba.github.io/page-agent/#/docs/features/chrome-extension) for multi-page tasks.** - **🐙 Optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension) for multi-page tasks.**
## 💡 Use Cases
- **SaaS AI Copilot** — Ship an AI copilot in your product in lines of code. No backend rewrite needed.
- **Smart Form Filling** — Turn 20-click workflows into one sentence. Perfect for ERP, CRM, and admin systems.
- **Accessibility** — Make any web app accessible through natural language. Voice commands, screen readers, zero barrier.
- **Multi-page Agent** — Extend your agent's reach across browser tabs with the optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension).
## 🚀 Quick Start ## 🚀 Quick Start
@@ -42,10 +49,10 @@ Fastest way to try PageAgent with our free Demo LLM:
| Mirrors | URL | | Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- | | ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.3.0/dist/iife/page-agent.demo.js | | Global | https://cdn.jsdelivr.net/npm/page-agent@1.4.2/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.3.0/files/dist/iife/page-agent.demo.js | | China | https://registry.npmmirror.com/page-agent/1.4.2/files/dist/iife/page-agent.demo.js |
> **⚠️ For technical evaluation only.** Demo LLM has rate limits and usage restrictions. Slow. May change without notice. > **⚠️ 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).
### NPM Installation ### NPM Installation
@@ -57,8 +64,8 @@ npm install page-agent
import { PageAgent } from 'page-agent' import { PageAgent } from 'page-agent'
const agent = new PageAgent({ const agent = new PageAgent({
model: 'deepseek-chat', model: 'qwen3.5-plus',
baseURL: 'https://api.deepseek.com', baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'YOUR_API_KEY', apiKey: 'YOUR_API_KEY',
language: 'en-US', language: 'en-US',
}) })
@@ -66,28 +73,13 @@ const agent = new PageAgent({
await agent.execute('Click the login button') await agent.execute('Click the login button')
``` ```
For more programmatic usage, see [📖 Documentations](https://alibaba.github.io/page-agent/#/docs/introduction/overview). For more programmatic usage, see [📖 Documentations](https://alibaba.github.io/page-agent/docs/introduction/overview).
## 🏗️ Structure
PageAgent adopts a simplified monorepo structure:
```
packages/
├── core/ # ** Core agent logic (npm: @page-agent/core) **
├── llms/ # LLM client (npm: @page-agent/llms)
├── page-controller/ # DOM operations (npm: @page-agent/page-controller)
├── ui/ # Panel UI (npm: @page-agent/ui)
├── page-agent/ # Entry class and iife builds(npm: page-agent)
├── extension/ # Chrome extension for multi-page tasks
└── website/ # Website & Documentation site
```
## 🤝 Contributing ## 🤝 Contributing
We welcome contributions from the community! Follow our instructions in [CONTRIBUTING.md](CONTRIBUTING.md) for environment setup and local development. We welcome contributions from the community! Follow our instructions in [CONTRIBUTING.md](CONTRIBUTING.md) for environment setup and local development.
Please read [Code of Conduct](CODE_OF_CONDUCT.md) before contributing. Please read [Code of Conduct](docs/CODE_OF_CONDUCT.md) before contributing.
## 👏 Acknowledgments ## 👏 Acknowledgments
+27 -1
View File
@@ -5,6 +5,32 @@ 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/), 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). and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [1.4.0] - 2026-02-27
### Features
- Update Terms of Use and Privacy Policy
- **Robust tool-call validation** - Action inputs are now validated against tool schemas individually, producing clear error messages (e.g. `Invalid input for action "click_element_by_index"`) instead of unreadable union parse errors
- **Primitive action input coercion** - Small models that output `{"click_element_by_index": 2}` instead of `{"click_element_by_index": {"index": 2}}` are now auto-corrected using tool schemas
- **Qwen model updates** - Added `qwen3.5-plus` as the default free testing model; disabled `enable_thinking` for Qwen models to avoid incompatible responses
- **Updated default LLM endpoint** - Migrated demo and extension to a new testing endpoint with legacy endpoint auto-migration
### Improvements
- Unified zod imports (`* as z`) across all packages for consistency
- Better Zod error formatting with `z.prettifyError()` in LLM client
- Exported `InvokeError` and `InvokeErrorType` as values (not just types) from `@page-agent/llms`
- Exported `SupportedLanguage` type from `@page-agent/core`
### Extension v0.1.8
- **Language setting** - Added language selector (System / English / 中文) in config panel
- **UI makeover** - New empty state with breathing glow and typing animation; ai-motion glow overlay while running; refined focus styles
- **Testing endpoint notice** - Shows terms of use notice when using the free testing API
- **Legacy endpoint migration** - Auto-migrates old Supabase testing endpoint to new endpoint on startup
---
## [1.3.0] - 2026-02-13 ## [1.3.0] - 2026-02-13
### Breaking Changes ### Breaking Changes
@@ -146,7 +172,7 @@ interface PageAgentConfig {
- Single-page application only (cannot navigate across pages) - Single-page application only (cannot navigate across pages)
- No visual recognition (relies on DOM structure) - No visual recognition (relies on DOM structure)
- Limited interaction support (no hover, drag-drop, canvas operations) - Limited interaction support (no hover, drag-drop, canvas operations)
- See [Limitations](https://alibaba.github.io/page-agent/#/docs/introduction/limitations) for details - See [Limitations](https://alibaba.github.io/page-agent/docs/introduction/limitations) for details
### Acknowledgments ### Acknowledgments
+25 -33
View File
@@ -9,26 +9,33 @@
纯 JS 实现的 GUI agent。使用自然语言操作你的 Web 应用。无须后端、客户端、浏览器插件。 纯 JS 实现的 GUI agent。使用自然语言操作你的 Web 应用。无须后端、客户端、浏览器插件。
🌐 [English](./README.md) | **中文** 🌐 [English](../README.md) | **中文**
👉 <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>
<video id="demo-video" src="https://github.com/user-attachments/assets/34d8444d-cbfb-44a3-a24e-fd5c167bb0bf" controls crossorigin muted></video> <video id="demo-video" src="https://github.com/user-attachments/assets/11aed429-b69c-49d5-8982-fa99b4a0e9a8" controls crossorigin muted></video>
--- ---
## ✨ Features ## ✨ Features
- **🎯 轻松集成** - **🎯 轻松集成**
- 无需 `浏览器插件` / `Python` / `无头浏览器` - 无需 `浏览器插件` / `Python` / `无头浏览器`
- 纯页面内 JavaScript,一切都在你的网页中完成。 - 纯页面内 JavaScript,一切都在你的网页中完成。
- The best tool for your agent to control web pages. - The best tool for your agent to control web pages.
- **📖 基于文本的 DOM 操作** - **📖 基于文本的 DOM 操作**
- 无需截图,无需 OCR 或多模态模型。 - 无需截图,无需 OCR 或多模态模型。
- 无需特殊权限。 - 无需特殊权限。
- **🧠 用你自己的 LLM** - **🧠 用你自己的 LLM**
- **🎨 精美 UI,支持人机协同** - **🎨 精美 UI,支持人机协同**
- **🐙 可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/#/docs/features/chrome-extension),支持跨页面任务。** - **🐙 可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension),支持跨页面任务。**
## 💡 应用场景
- **SaaS AI 副驾驶** — 几行代码为你的产品加上 AI 副驾驶,不需要重写后端。
- **智能表单填写** — 把 20 次点击变成一句话。ERP、CRM、管理后台的最佳拍档。
- **无障碍增强** — 用自然语言让任何网页无障碍。语音指令、屏幕阅读器,零门槛。
- **跨页面 Agent** — 通过可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension),让你的 Agent 跨标签页工作。
## 🚀 快速开始 ## 🚀 快速开始
@@ -42,10 +49,10 @@
| Mirrors | URL | | Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- | | ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.3.0/dist/iife/page-agent.demo.js | | Global | https://cdn.jsdelivr.net/npm/page-agent@1.4.2/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.3.0/files/dist/iife/page-agent.demo.js | | China | https://registry.npmmirror.com/page-agent/1.4.2/files/dist/iife/page-agent.demo.js |
> **⚠️ 仅用于技术评估。** Demo LLM 有速率和使用限制,速度较慢,可能随时变更 > **⚠️ 仅用于技术评估。** 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)
### NPM 安装 ### NPM 安装
@@ -57,8 +64,8 @@ npm install page-agent
import { PageAgent } from 'page-agent' import { PageAgent } from 'page-agent'
const agent = new PageAgent({ const agent = new PageAgent({
model: 'deepseek-chat', model: 'qwen3.5-plus',
baseURL: 'https://api.deepseek.com', baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'YOUR_API_KEY', apiKey: 'YOUR_API_KEY',
language: 'zh-CN', language: 'zh-CN',
}) })
@@ -66,26 +73,11 @@ const agent = new PageAgent({
await agent.execute('点击登录按钮') await agent.execute('点击登录按钮')
``` ```
更多编程用法,请参阅 [📖 文档](https://alibaba.github.io/page-agent/#/docs/introduction/overview)。 更多编程用法,请参阅 [📖 文档](https://alibaba.github.io/page-agent/docs/introduction/overview)。
## 🏗️ 架构设计
PageAgent adopts a simplified monorepo structure:
```
packages/
├── core/ # ** Core agent logic (npm: @page-agent/core) **
├── llms/ # LLM 客户端 (npm: @page-agent/llms)
├── page-controller/ # DOM 操作 (npm: @page-agent/page-controller)
├── ui/ # 面板 UI (npm: @page-agent/ui)
├── page-agent/ # 入口类 & iife 包 (npm: page-agent)
├── extension/ # Chrome 扩展,支持跨页面任务
└── website/ # 网站 & 文档站点
```
## 🤝 贡献 ## 🤝 贡献
欢迎社区贡献!请参阅 [CONTRIBUTING.md](CONTRIBUTING.md) 了解环境配置和本地开发说明。 欢迎社区贡献!请参阅 [CONTRIBUTING.md](../CONTRIBUTING.md) 了解环境配置和本地开发说明。
请在贡献前阅读[行为准则](CODE_OF_CONDUCT.md)。 请在贡献前阅读[行为准则](CODE_OF_CONDUCT.md)。
@@ -114,7 +106,7 @@ file and in the node_modules directory after installation.
## 📄 许可证 ## 📄 许可证
[MIT License](LICENSE) [MIT License](../LICENSE)
--- ---
+83
View File
@@ -0,0 +1,83 @@
# Terms of Use & Privacy
**Last updated:** February 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.
---
## 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.
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
---
## 2. Testing API and Demo Disclaimer & Terms of Use
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:
**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.
**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.
**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.
**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).
**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.
---
## 3. Browser Extension (Page Agent Ext)
### Data Processing
The extension performs DOM analysis and automation actions **locally in your browser**. Your browsing history, passwords, and form data are not accessed or collected by the extension developer.
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
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.
**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.
### Data Storage
- **Local storage only**: Your configuration (API endpoint, API key, model selection) is stored in your browser via `chrome.storage.local`
- **No cloud sync**: Configuration is not synced to any external server
- **No analytics**: The extension does not include any analytics or tracking code
### Your Control
- The extension is open source and can be audited by anyone
- You choose which LLM provider to use
- You may configure your own API endpoint at any time
- You can clear all stored data by removing the extension
---
## Changes
We may update these terms as the project evolves.
## Contact
https://github.com/alibaba/page-agent/issues
+530 -431
View File
File diff suppressed because it is too large Load Diff
+11 -11
View File
@@ -1,7 +1,7 @@
{ {
"name": "root", "name": "root",
"private": true, "private": true,
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"workspaces": [ "workspaces": [
"packages/page-controller", "packages/page-controller",
@@ -35,29 +35,29 @@
"prepare": "husky" "prepare": "husky"
}, },
"devDependencies": { "devDependencies": {
"@commitlint/cli": "^20.3.1", "@commitlint/cli": "^20.4.2",
"@commitlint/config-conventional": "^20.3.1", "@commitlint/config-conventional": "^20.4.2",
"@eslint/js": "^9.39.2", "@eslint/js": "^9.39.2",
"@microsoft/api-extractor": "^7.56.3", "@microsoft/api-extractor": "^7.57.3",
"@tailwindcss/vite": "^4.1.18", "@tailwindcss/vite": "^4.2.1",
"@trivago/prettier-plugin-sort-imports": "^6.0.2", "@trivago/prettier-plugin-sort-imports": "^6.0.2",
"@types/node": "^25.2.2", "@types/node": "^25.3.0",
"@vitejs/plugin-react-swc": "^4.1.0", "@vitejs/plugin-react-swc": "^4.1.0",
"chalk": "^5.6.2", "chalk": "^5.6.2",
"concurrently": "^9.2.1", "concurrently": "^9.2.1",
"dotenv": "^17.2.4", "dotenv": "^17.3.1",
"eslint": "^9.39.2", "eslint": "^9.39.2",
"eslint-config-prettier": "^10.1.8", "eslint-config-prettier": "^10.1.8",
"eslint-plugin-react-dom": "^2.12.2", "eslint-plugin-react-dom": "^2.13.0",
"eslint-plugin-react-hooks": "^7.0.1", "eslint-plugin-react-hooks": "^7.0.1",
"eslint-plugin-react-refresh": "^0.5.0", "eslint-plugin-react-refresh": "^0.5.2",
"eslint-plugin-react-x": "^2.12.2", "eslint-plugin-react-x": "^2.13.0",
"globals": "^17.0.0", "globals": "^17.0.0",
"husky": "^9.1.7", "husky": "^9.1.7",
"lint-staged": "^16.2.4", "lint-staged": "^16.2.4",
"prettier": "^3.8.0", "prettier": "^3.8.0",
"typescript": "^5.9.3", "typescript": "^5.9.3",
"typescript-eslint": "^8.55.0", "typescript-eslint": "^8.56.1",
"unplugin-dts": "^1.0.0-beta.6", "unplugin-dts": "^1.0.0-beta.6",
"vite": "^7.3.1", "vite": "^7.3.1",
"vite-plugin-css-injected-by-js": "^3.5.2", "vite-plugin-css-injected-by-js": "^3.5.2",
+3 -3
View File
@@ -1,7 +1,7 @@
{ {
"name": "@page-agent/core", "name": "@page-agent/core",
"private": false, "private": false,
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"main": "./dist/esm/page-agent-core.js", "main": "./dist/esm/page-agent-core.js",
"module": "./dist/esm/page-agent-core.js", "module": "./dist/esm/page-agent-core.js",
@@ -45,7 +45,7 @@
"dependencies": { "dependencies": {
"chalk": "^5.6.2", "chalk": "^5.6.2",
"zod": "^4.3.5", "zod": "^4.3.5",
"@page-agent/llms": "1.3.0", "@page-agent/llms": "1.4.2",
"@page-agent/page-controller": "1.3.0" "@page-agent/page-controller": "1.4.2"
} }
} }
+16 -15
View File
@@ -5,9 +5,9 @@
import { InvokeError, LLM, type Tool } from '@page-agent/llms' import { InvokeError, LLM, type Tool } from '@page-agent/llms'
import type { BrowserState, PageController } from '@page-agent/page-controller' import type { BrowserState, PageController } from '@page-agent/page-controller'
import chalk from 'chalk' import chalk from 'chalk'
import * as zod from 'zod' import * as z from 'zod'
import { type PageAgentConfig } from './config' import { type PageAgentConfig, type SupportedLanguage } from './config'
import { DEFAULT_MAX_STEPS } from './config/constants' import { DEFAULT_MAX_STEPS } from './config/constants'
import SYSTEM_PROMPT from './prompts/system_prompt.md?raw' import SYSTEM_PROMPT from './prompts/system_prompt.md?raw'
import { tools } from './tools' import { tools } from './tools'
@@ -24,6 +24,7 @@ import type {
import { assert, normalizeResponse, uid, waitFor } from './utils' import { assert, normalizeResponse, uid, waitFor } from './utils'
export { type PageAgentConfig } export { type PageAgentConfig }
export type { SupportedLanguage }
export { tool, type PageAgentTool } from './tools' export { tool, type PageAgentTool } from './tools'
export type * from './types' export type * from './types'
@@ -247,16 +248,16 @@ export class PageAgentCore extends EventTarget {
{ role: 'user' as const, content: await this.#assembleUserPrompt() }, { role: 'user' as const, content: await this.#assembleUserPrompt() },
] ]
const tools = { AgentOutput: this.#packMacroTool() } const macroTool = { AgentOutput: this.#packMacroTool() }
// invoke LLM // invoke LLM
console.log(chalk.blue.bold('🧠 Thinking...')) console.log(chalk.blue.bold('🧠 Thinking...'))
this.#emitActivity({ type: 'thinking' }) this.#emitActivity({ type: 'thinking' })
const result = await this.#llm.invoke(messages, tools, this.#abortController.signal, { const result = await this.#llm.invoke(messages, macroTool, this.#abortController.signal, {
toolChoiceName: 'AgentOutput', toolChoiceName: 'AgentOutput',
normalizeResponse, normalizeResponse: (res) => normalizeResponse(res, this.tools),
}) })
// assemble history // assemble history
@@ -341,6 +342,8 @@ export class PageAgentCore extends EventTarget {
await onAfterTask?.(this, result) await onAfterTask?.(this, result)
return result return result
} }
await waitFor(0.4) // @TODO: configurable
} }
} }
@@ -357,24 +360,22 @@ export class PageAgentCore extends EventTarget {
const tools = this.tools const tools = this.tools
const actionSchemas = Array.from(tools.entries()).map(([toolName, tool]) => { const actionSchemas = Array.from(tools.entries()).map(([toolName, tool]) => {
return zod.object({ [toolName]: tool.inputSchema }).describe(tool.description) return z.object({ [toolName]: tool.inputSchema }).describe(tool.description)
}) })
const actionSchema = zod.union( const actionSchema = z.union(actionSchemas as unknown as [z.ZodType, z.ZodType, ...z.ZodType[]])
actionSchemas as unknown as [zod.ZodType, zod.ZodType, ...zod.ZodType[]]
)
const macroToolSchema = zod.object({ const macroToolSchema = z.object({
// thinking: zod.string().optional(), // thinking: z.string().optional(),
evaluation_previous_goal: zod.string().optional(), evaluation_previous_goal: z.string().optional(),
memory: zod.string().optional(), memory: z.string().optional(),
next_goal: zod.string().optional(), next_goal: z.string().optional(),
action: actionSchema, action: actionSchema,
}) })
return { return {
description: 'You MUST call this tool every step!', description: 'You MUST call this tool every step!',
inputSchema: macroToolSchema as zod.ZodType<MacroToolInput>, inputSchema: macroToolSchema as z.ZodType<MacroToolInput>,
execute: async (input: MacroToolInput): Promise<MacroToolResult> => { execute: async (input: MacroToolInput): Promise<MacroToolResult> => {
// abort // abort
if (this.#abortController.signal.aborted) throw new Error('AbortError') if (this.#abortController.signal.aborted) throw new Error('AbortError')
+28 -28
View File
@@ -2,7 +2,7 @@
* Internal tools for PageAgent. * Internal tools for PageAgent.
* @note Adapted from browser-use * @note Adapted from browser-use
*/ */
import * as zod from 'zod' import * as z from 'zod'
import type { PageAgentCore } from '../PageAgentCore' import type { PageAgentCore } from '../PageAgentCore'
import { waitFor } from '../utils' import { waitFor } from '../utils'
@@ -13,7 +13,7 @@ import { waitFor } from '../utils'
export interface PageAgentTool<TParams = any> { export interface PageAgentTool<TParams = any> {
// name: string // name: string
description: string description: string
inputSchema: zod.ZodType<TParams> inputSchema: z.ZodType<TParams>
execute: (this: PageAgentCore, args: TParams) => Promise<string> execute: (this: PageAgentCore, args: TParams) => Promise<string>
} }
@@ -32,9 +32,9 @@ tools.set(
tool({ tool({
description: description:
'Complete task. Text is your final response to the user — keep it concise unless the user explicitly asks for detail.', 'Complete task. Text is your final response to the user — keep it concise unless the user explicitly asks for detail.',
inputSchema: zod.object({ inputSchema: z.object({
text: zod.string(), text: z.string(),
success: zod.boolean().default(true), success: z.boolean().default(true),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
// @note main loop will handle this one // @note main loop will handle this one
@@ -47,8 +47,8 @@ tools.set(
'wait', 'wait',
tool({ tool({
description: 'Wait for x seconds. Can be used to wait until the page or data is fully loaded.', description: 'Wait for x seconds. Can be used to wait until the page or data is fully loaded.',
inputSchema: zod.object({ inputSchema: z.object({
seconds: zod.number().min(1).max(10).default(1), seconds: z.number().min(1).max(10).default(1),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
// try to subtract LLM calling time from the actual wait time // try to subtract LLM calling time from the actual wait time
@@ -67,8 +67,8 @@ tools.set(
tool({ tool({
description: description:
'Ask the user a question and wait for their answer. Use this if you need more information or clarification.', 'Ask the user a question and wait for their answer. Use this if you need more information or clarification.',
inputSchema: zod.object({ inputSchema: z.object({
question: zod.string(), question: z.string(),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
if (!this.onAskUser) { if (!this.onAskUser) {
@@ -84,8 +84,8 @@ tools.set(
'click_element_by_index', 'click_element_by_index',
tool({ tool({
description: 'Click element by index', description: 'Click element by index',
inputSchema: zod.object({ inputSchema: z.object({
index: zod.int().min(0), index: z.int().min(0),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.clickElement(input.index) const result = await this.pageController.clickElement(input.index)
@@ -98,9 +98,9 @@ tools.set(
'input_text', 'input_text',
tool({ tool({
description: 'Click and type text into an interactive input element', description: 'Click and type text into an interactive input element',
inputSchema: zod.object({ inputSchema: z.object({
index: zod.int().min(0), index: z.int().min(0),
text: zod.string(), text: z.string(),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.inputText(input.index, input.text) const result = await this.pageController.inputText(input.index, input.text)
@@ -114,9 +114,9 @@ tools.set(
tool({ tool({
description: description:
'Select dropdown option for interactive element index by the text of the option you want to select', 'Select dropdown option for interactive element index by the text of the option you want to select',
inputSchema: zod.object({ inputSchema: z.object({
index: zod.int().min(0), index: z.int().min(0),
text: zod.string(), text: z.string(),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.selectOption(input.index, input.text) const result = await this.pageController.selectOption(input.index, input.text)
@@ -132,11 +132,11 @@ tools.set(
'scroll', 'scroll',
tool({ tool({
description: 'Scroll the page vertically. Use index for scroll elements (dropdowns/custom UI).', description: 'Scroll the page vertically. Use index for scroll elements (dropdowns/custom UI).',
inputSchema: zod.object({ inputSchema: z.object({
down: zod.boolean().default(true), down: z.boolean().default(true),
num_pages: zod.number().min(0).max(10).optional().default(0.1), num_pages: z.number().min(0).max(10).optional().default(0.1),
pixels: zod.number().int().min(0).optional(), pixels: z.number().int().min(0).optional(),
index: zod.number().int().min(0).optional(), index: z.number().int().min(0).optional(),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.scroll({ const result = await this.pageController.scroll({
@@ -156,10 +156,10 @@ tools.set(
tool({ tool({
description: description:
'Scroll the page horizontally, or within a specific element by index. Useful for wide tables.', 'Scroll the page horizontally, or within a specific element by index. Useful for wide tables.',
inputSchema: zod.object({ inputSchema: z.object({
right: zod.boolean().default(true), right: z.boolean().default(true),
pixels: zod.number().int().min(0), pixels: z.number().int().min(0),
index: zod.number().int().min(0).optional(), index: z.number().int().min(0).optional(),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.scrollHorizontally(input) const result = await this.pageController.scrollHorizontally(input)
@@ -173,8 +173,8 @@ tools.set(
tool({ tool({
description: description:
'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution!', 'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution!',
inputSchema: zod.object({ inputSchema: z.object({
script: zod.string(), script: z.string(),
}), }),
execute: async function (this: PageAgentCore, input) { execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.executeJavascript(input.script) const result = await this.pageController.executeJavascript(input.script)
+60 -1
View File
@@ -1,4 +1,8 @@
import { InvokeError, InvokeErrorType } from '@page-agent/llms'
import chalk from 'chalk' import chalk from 'chalk'
import * as z from 'zod'
import type { PageAgentTool } from '../tools'
/** /**
* Normalize LLM response and fix common format issues. * Normalize LLM response and fix common format issues.
@@ -9,9 +13,10 @@ import chalk from 'chalk'
* - Arguments wrapped as double JSON string * - Arguments wrapped as double JSON string
* - Nested function call format * - Nested function call format
* - Missing action field (fallback to wait) * - Missing action field (fallback to wait)
* - Primitive action input for single-field tools (e.g. `{"click_element_by_index": 2}`)
* - etc. * - etc.
*/ */
export function normalizeResponse(response: any): any { export function normalizeResponse(response: any, tools?: Map<string, PageAgentTool>): any {
let resolvedArguments = null as any let resolvedArguments = null as any
const choice = (response as { choices?: Choice[] }).choices?.[0] const choice = (response as { choices?: Choice[] }).choices?.[0]
@@ -78,6 +83,11 @@ export function normalizeResponse(response: any): any {
resolvedArguments.action = safeJsonParse(resolvedArguments.action) resolvedArguments.action = safeJsonParse(resolvedArguments.action)
} }
// validate and fix action input using tool schemas
if (resolvedArguments.action && tools) {
resolvedArguments.action = validateAction(resolvedArguments.action, tools)
}
// fix incomplete formats // fix incomplete formats
if (!resolvedArguments.action) { if (!resolvedArguments.action) {
console.log(chalk.yellow(`[normalizeResponse] #5: fixing tool_call`)) console.log(chalk.yellow(`[normalizeResponse] #5: fixing tool_call`))
@@ -108,6 +118,55 @@ export function normalizeResponse(response: any): any {
} }
} }
/**
* Validate action against tool schemas. Provides clear error messages
* instead of letting the union schema produce unreadable errors.
*
* Also coerces primitive inputs for single-field tools:
* e.g. `{"click_element_by_index": 2}` → `{"click_element_by_index": {"index": 2}}`
*/
function validateAction(action: any, tools: Map<string, PageAgentTool>): any {
if (typeof action !== 'object' || action === null) return action
const toolName = Object.keys(action)[0]
if (!toolName) return action
const tool = tools.get(toolName)
if (!tool) {
const available = Array.from(tools.keys()).join(', ')
throw new InvokeError(
InvokeErrorType.INVALID_TOOL_ARGS,
`Unknown action "${toolName}". Available: ${available}`
)
}
let value = action[toolName]
const schema = tool.inputSchema
// coerce primitive input for single-field tools
if (schema instanceof z.ZodObject && value !== null && typeof value !== 'object') {
const requiredKey = Object.keys(schema.shape).find(
(k) => !(schema.shape as Record<string, z.ZodType>)[k].safeParse(undefined).success
)
if (requiredKey) {
console.log(
chalk.yellow(`[normalizeResponse] coercing primitive action input for "${toolName}"`)
)
value = { [requiredKey]: value }
}
}
const result = schema.safeParse(value)
if (!result.success) {
throw new InvokeError(
InvokeErrorType.INVALID_TOOL_ARGS,
`Invalid input for action "${toolName}": ${z.prettifyError(result.error)}`
)
}
return { [toolName]: result.data }
}
/** /**
* Safely parse JSON, return original input if not json. * Safely parse JSON, return original input if not json.
*/ */
+2 -54
View File
@@ -1,57 +1,5 @@
# Privacy Policy for Page Agent Extension # Privacy Policy for Page Agent Extension
**Last updated:** January 2026 This document has moved. Please see our full **[Terms of Use & Privacy](../../docs/terms-and-privacy.md)**.
## Overview Online: https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md
Page Agent Extension is a browser automation tool that uses AI to help you interact with web pages. This policy explains what data is processed and under what circumstances.
## Data Processing
### Local Processing
The extension performs DOM analysis and automation actions **locally in your browser**. Your browsing history, passwords, and form data are not accessed or collected by the extension itself.
### Data Transmission
Data is transmitted to external servers **only when you initiate an automation task**. When this occurs:
- Your task instructions (natural language commands)
- Sanitized page structure (simplified DOM, excluding sensitive form values)
are sent to the LLM API endpoint configured in **your settings**.
**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 our testing endpoint**, your requests are proxied to [DeepSeek](https://deepseek.com) for AI processing. Regarding this test endpoint:
- This endpoint is provided for evaluation purposes only and is not recommended for production or daily use
- We do **not** store your task content, page content, or visited URLs
- Minimal logging (timestamps, request metadata, IP addresses) may occur for abuse prevention and service stability
- DeepSeek's [Privacy Policy](https://cdn.deepseek.com/policies/en-US/deepseek-privacy-policy.html) applies to their processing of your requests
## Data Storage
- **Local storage only**: Your configuration (API endpoint, API key, model selection) is stored in your browser via `chrome.storage.local`
- **No cloud sync**: Configuration is not synced to any external server
- **No analytics**: The extension does not include any analytics or tracking code
## Your Control
- The extension is open source and can be audited by anyone
- You choose which LLM provider to use
- You may configure your own API endpoint at any time
- You can clear all stored data by removing the extension
## Changes to This Policy
We may update this policy as the extension evolves. Significant changes will be noted in the extension's release notes.
## Contact
For questions about this privacy policy:
https://github.com/alibaba/page-agent/issues
---
Source code: https://github.com/alibaba/page-agent
+2 -2
View File
@@ -5,7 +5,7 @@
"tsx": true, "tsx": true,
"tailwind": { "tailwind": {
"config": "", "config": "",
"css": "src/index.css", "css": "src/assets/index.css",
"baseColor": "neutral", "baseColor": "neutral",
"cssVariables": true, "cssVariables": true,
"prefix": "" "prefix": ""
@@ -16,7 +16,7 @@
"utils": "@/lib/utils", "utils": "@/lib/utils",
"ui": "@/components/ui", "ui": "@/components/ui",
"lib": "@/lib", "lib": "@/lib",
"hooks": "@/hooks" "hooks": "@/lib/hooks"
}, },
"registries": { "registries": {
"@magicui": "https://magicui.design/r/{name}.json" "@magicui": "https://magicui.design/r/{name}.json"
-226
View File
@@ -1,226 +0,0 @@
# Page Agent 浏览器插件 API
在你的网页应用中接入 Page Agent 插件,并通过页面 JavaScript 发起多页面浏览器任务。
## 安装
### 1. 安装浏览器插件
首选渠道:
- Chrome 应用商店:https://chromewebstore.google.com/detail/page-agent-ext/akldabonmimlicnjlflnapfeklbfemhj
通常更快提供最新构建的渠道:
- GitHub Releaseshttps://github.com/alibaba/page-agent/releases
### 2. 安装类型定义(推荐)
```bash
npm install @page-agent/core --save-dev
```
### 3. 授权(Token
token 用于让页面 JS 调用扩展 API(`window.PAGE_AGENT_EXT`)并执行多页面任务。
为什么必须使用 token
- 插件具备较广的浏览器权限(页面访问、导航、多标签控制)。
- 若被滥用,可能危害用户隐私与安全。
- 用户必须主动将 token 提供给其信任的应用。
配置步骤:
1. 在扩展侧边栏中复制 auth token。
2. 在页面中设置 token
```typescript
localStorage.setItem('PageAgentExtUserAuthToken', 'your-token')
```
## 快速开始
```typescript
import type {
AgentActivity,
AgentStatus,
ExecutionResult,
HistoricalEvent,
} from '@page-agent/core'
// 等待插件注入(最多 1 秒)
async function waitForExtension(timeout = 1000): Promise<boolean> {
const start = Date.now()
while (Date.now() - start < timeout) {
if (window.PAGE_AGENT_EXT) return true
await new Promise((r) => setTimeout(r, 100))
}
return false
}
// 使用
if (await waitForExtension()) {
const result = await window.PAGE_AGENT_EXT!.execute('点击登录按钮', {
baseURL: 'https://api.openai.com/v1',
apiKey: 'your-api-key',
model: 'gpt-5.2',
onStatusChange: (status) => console.log('状态:', status),
onActivity: (activity) => console.log('活动:', activity),
})
console.log('结果:', result)
}
```
## 全局 API
token 匹配后,插件会在 `window` 上注入 API。
### `window.PAGE_AGENT_EXT_VERSION`
插件版本号字符串,可用于在访问主 API 前做能力检查。
### `window.PAGE_AGENT_EXT`
主命名空间对象。
#### `PAGE_AGENT_EXT.execute(task, config)`
执行 Agent 任务。
参数:
| 名称 | 类型 | 必填 | 说明 |
| ---- | ---- | ---- | ---- |
| `task` | `string` | 是 | 任务描述 |
| `config` | `ExecuteConfig` | 是 | LLM 设置、执行选项和回调 |
返回:`Promise<ExecutionResult>`
#### `PAGE_AGENT_EXT.stop()`
停止当前任务。
## 类型定义
安装 `@page-agent/core` 获取完整类型:
```typescript
import type {
AgentActivity,
AgentStatus,
ExecutionResult,
HistoricalEvent,
} from '@page-agent/core'
export interface ExecuteConfig {
baseURL: string
apiKey: string
model: string
// 是否包含启动脚本所在标签页。默认 true。
includeInitialTab?: boolean
onStatusChange?: (status: AgentStatus) => void
onActivity?: (activity: AgentActivity) => void
onHistoryUpdate?: (history: HistoricalEvent[]) => void
}
export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
```
`AgentStatus`
```typescript
type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
```
`AgentActivity`
```typescript
type AgentActivity =
| { type: 'thinking' }
| { type: 'executing'; tool: string; input: unknown }
| { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
| { type: 'retrying'; attempt: number; maxAttempts: number }
| { type: 'error'; message: string }
```
`HistoricalEvent`
```typescript
type HistoricalEvent =
| { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
| { type: 'observation'; content: string }
| { type: 'user_takeover' }
| { type: 'retry'; message: string; attempt: number; maxAttempts: number }
| { type: 'error'; message: string; rawResponse?: unknown }
```
`ExecutionResult`
```typescript
interface ExecutionResult {
success: boolean
data: string
history: HistoricalEvent[]
}
```
## 使用示例
### 基础执行
```typescript
const result = await window.PAGE_AGENT_EXT!.execute(
'在邮箱输入框填入 test@example.com 然后点击提交',
{
baseURL: 'https://api.openai.com/v1',
apiKey: process.env.OPENAI_API_KEY!,
model: 'gpt-5.2',
includeInitialTab: false, // 可选:排除当前标签页
onStatusChange: (status) => console.log(status),
onActivity: (activity) => console.log(activity),
}
)
```
### 停止当前任务
```typescript
window.PAGE_AGENT_EXT!.stop()
```
## Window 类型声明
如果你不直接引入 `@page-agent/core`,可添加以下声明:
```typescript
import type {
AgentActivity,
AgentStatus,
ExecutionResult,
HistoricalEvent,
} from '@page-agent/core'
interface ExecuteConfig {
baseURL: string
apiKey: string
model: string
includeInitialTab?: boolean
onStatusChange?: (status: AgentStatus) => void
onActivity?: (activity: AgentActivity) => void
onHistoryUpdate?: (history: HistoricalEvent[]) => void
}
declare global {
interface Window {
PAGE_AGENT_EXT_VERSION?: string
PAGE_AGENT_EXT?: {
version: string
execute: Execute
stop: () => void
}
}
}
```
+13 -12
View File
@@ -1,7 +1,7 @@
{ {
"name": "@page-agent/ext", "name": "@page-agent/ext",
"private": true, "private": true,
"version": "0.1.5", "version": "0.1.8",
"type": "module", "type": "module",
"scripts": { "scripts": {
"dev": "wxt", "dev": "wxt",
@@ -17,31 +17,32 @@
"@radix-ui/react-slot": "^1.2.4", "@radix-ui/react-slot": "^1.2.4",
"@radix-ui/react-switch": "^1.2.6", "@radix-ui/react-switch": "^1.2.6",
"@radix-ui/react-tooltip": "^1.2.8", "@radix-ui/react-tooltip": "^1.2.8",
"@types/chrome": "^0.1.34", "@types/chrome": "^0.1.37",
"@types/react": "^19.2.13", "@types/react": "^19.2.14",
"@types/react-dom": "^19.2.1", "@types/react-dom": "^19.2.1",
"@wxt-dev/module-react": "^1.1.5", "@wxt-dev/module-react": "^1.1.5",
"class-variance-authority": "^0.7.1", "class-variance-authority": "^0.7.1",
"clsx": "^2.1.1", "clsx": "^2.1.1",
"idb": "^8.0.3", "idb": "^8.0.3",
"lucide-react": "^0.563.0", "lucide-react": "^0.575.0",
"motion": "^12.34.0", "motion": "^12.34.3",
"next-themes": "^0.4.6", "next-themes": "^0.4.6",
"react": "^19.2.4", "react": "^19.2.4",
"react-dom": "^19.2.4", "react-dom": "^19.2.4",
"rough-notation": "^0.5.1", "rough-notation": "^0.5.1",
"simple-icons": "^16.8.0", "simple-icons": "^16.9.0",
"sonner": "^2.0.7", "sonner": "^2.0.7",
"tailwind-merge": "^3.4.0", "tailwind-merge": "^3.5.0",
"tailwindcss": "^4.1.14", "tailwindcss": "^4.1.14",
"tw-animate-css": "^1.4.0", "tw-animate-css": "^1.4.0",
"wxt": "^0.20.14" "wxt": "^0.20.18"
}, },
"dependencies": { "dependencies": {
"@page-agent/core": "1.3.0", "@page-agent/core": "1.4.2",
"@page-agent/llms": "1.3.0", "@page-agent/llms": "1.4.2",
"@page-agent/page-controller": "1.3.0", "@page-agent/page-controller": "1.4.2",
"@page-agent/ui": "1.3.0", "@page-agent/ui": "1.4.2",
"ai-motion": "^0.4.8",
"chalk": "^5.6.2", "chalk": "^5.6.2",
"zod": "^4.3.5" "zod": "^4.3.5"
} }
@@ -0,0 +1,11 @@
{
"extName": {
"message": "Page Agent Ext"
},
"extDescription": {
"message": "AI-powered browser automation assistant. Control web pages with natural language."
},
"extActionTitle": {
"message": "Open Page Agent"
}
}
@@ -0,0 +1,11 @@
{
"extName": {
"message": "Page Agent Ext"
},
"extDescription": {
"message": "AI 驱动的浏览器自动化助手,用自然语言控制网页。"
},
"extActionTitle": {
"message": "打开 Page Agent"
}
}
+21 -4
View File
@@ -1,13 +1,30 @@
import type { LLMConfig } from '@page-agent/llms' import type { LLMConfig } from '@page-agent/llms'
// Demo LLM for testing // Demo LLM for testing
export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM' export const DEMO_MODEL = 'qwen3.5-plus'
export const DEMO_BASE_URL = export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy' export const DEMO_API_KEY = 'NA'
export const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
export const DEMO_CONFIG: LLMConfig = { export const DEMO_CONFIG: LLMConfig = {
apiKey: DEMO_API_KEY, apiKey: DEMO_API_KEY,
baseURL: DEMO_BASE_URL, baseURL: DEMO_BASE_URL,
model: DEMO_MODEL, model: DEMO_MODEL,
} }
/** Legacy testing endpoints that should be auto-migrated to DEMO_BASE_URL */
export const LEGACY_TESTING_ENDPOINTS = [
'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy',
]
export function isTestingEndpoint(url: string): boolean {
const normalized = url.replace(/\/+$/, '')
return normalized === DEMO_BASE_URL || LEGACY_TESTING_ENDPOINTS.some((ep) => normalized === ep)
}
export function migrateLegacyEndpoint(config: LLMConfig): LLMConfig {
const normalized = config.baseURL.replace(/\/+$/, '')
if (LEGACY_TESTING_ENDPOINTS.some((ep) => normalized === ep)) {
return { ...DEMO_CONFIG }
}
return config
}
+8 -8
View File
@@ -6,14 +6,14 @@
* - switch_to_tab: Switch to an existing tab * - switch_to_tab: Switch to an existing tab
* - close_tab: Close a tab (optionally switch to another) * - close_tab: Close a tab (optionally switch to another)
*/ */
import * as zod from 'zod' import * as z from 'zod'
import type { TabsController } from './TabsController' import type { TabsController } from './TabsController'
/** Tool definition compatible with PageAgentCore customTools */ /** Tool definition compatible with PageAgentCore customTools */
interface TabTool { interface TabTool {
description: string description: string
inputSchema: zod.ZodType inputSchema: z.ZodType
execute: (input: unknown) => Promise<string> execute: (input: unknown) => Promise<string>
} }
@@ -26,8 +26,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
open_new_tab: { open_new_tab: {
description: description:
'Open a new browser tab with the specified URL. The new tab becomes the current tab for all subsequent page operations.', 'Open a new browser tab with the specified URL. The new tab becomes the current tab for all subsequent page operations.',
inputSchema: zod.object({ inputSchema: z.object({
url: zod.string().describe('The URL to open in the new tab'), url: z.string().describe('The URL to open in the new tab'),
}), }),
execute: async (input: unknown) => { execute: async (input: unknown) => {
const { url } = input as { url: string } const { url } = input as { url: string }
@@ -42,8 +42,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
switch_to_tab: { switch_to_tab: {
description: description:
'Switch to an existing tab by its ID. After switching, all page operations will target the new current tab. You can only switch to tabs in the tab list shown in browser state.', 'Switch to an existing tab by its ID. After switching, all page operations will target the new current tab. You can only switch to tabs in the tab list shown in browser state.',
inputSchema: zod.object({ inputSchema: z.object({
tab_id: zod.number().int().describe('The tab ID to switch to'), tab_id: z.number().int().describe('The tab ID to switch to'),
}), }),
execute: async (input: unknown) => { execute: async (input: unknown) => {
const { tab_id } = input as { tab_id: number } const { tab_id } = input as { tab_id: number }
@@ -58,8 +58,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
close_tab: { close_tab: {
description: description:
'Close a tab by its ID. Cannot close the initial tab. Optionally specify which tab to switch to after closing.', 'Close a tab by its ID. Cannot close the initial tab. Optionally specify which tab to switch to after closing.',
inputSchema: zod.object({ inputSchema: z.object({
tab_id: zod.number().int().describe('The tab ID to close'), tab_id: z.number().int().describe('The tab ID to close'),
}), }),
execute: async (input: unknown) => { execute: async (input: unknown) => {
const { tab_id } = input as { tab_id: number } const { tab_id } = input as { tab_id: number }
+37 -13
View File
@@ -1,22 +1,34 @@
/** /**
* React hook for using AgentController * React hook for using AgentController
*/ */
import type { AgentActivity, AgentStatus, HistoricalEvent } from '@page-agent/core' import type {
AgentActivity,
AgentStatus,
HistoricalEvent,
SupportedLanguage,
} from '@page-agent/core'
import type { LLMConfig } from '@page-agent/llms' import type { LLMConfig } from '@page-agent/llms'
import { useCallback, useEffect, useRef, useState } from 'react' import { useCallback, useEffect, useRef, useState } from 'react'
import { MultiPageAgent } from './MultiPageAgent' import { MultiPageAgent } from './MultiPageAgent'
import { DEMO_CONFIG } from './constants' import { DEMO_CONFIG, migrateLegacyEndpoint } from './constants'
/** Language preference: undefined means follow system */
export type LanguagePreference = SupportedLanguage | undefined
export interface ExtConfig extends LLMConfig {
language?: LanguagePreference
}
export interface UseAgentResult { export interface UseAgentResult {
status: AgentStatus status: AgentStatus
history: HistoricalEvent[] history: HistoricalEvent[]
activity: AgentActivity | null activity: AgentActivity | null
currentTask: string currentTask: string
config: LLMConfig | null config: ExtConfig | null
execute: (task: string) => Promise<void> execute: (task: string) => Promise<void>
stop: () => void stop: () => void
configure: (config: LLMConfig) => Promise<void> configure: (config: ExtConfig) => Promise<void>
} }
export function useAgent(): UseAgentResult { export function useAgent(): UseAgentResult {
@@ -25,16 +37,23 @@ export function useAgent(): UseAgentResult {
const [history, setHistory] = useState<HistoricalEvent[]>([]) const [history, setHistory] = useState<HistoricalEvent[]>([])
const [activity, setActivity] = useState<AgentActivity | null>(null) const [activity, setActivity] = useState<AgentActivity | null>(null)
const [currentTask, setCurrentTask] = useState('') const [currentTask, setCurrentTask] = useState('')
const [config, setConfig] = useState<LLMConfig | null>(null) const [config, setConfig] = useState<ExtConfig | null>(null)
useEffect(() => { useEffect(() => {
chrome.storage.local.get('llmConfig').then((result) => { chrome.storage.local.get(['llmConfig', 'language']).then((result) => {
if (result.llmConfig) { let llmConfig = (result.llmConfig as LLMConfig) ?? DEMO_CONFIG
setConfig(result.llmConfig as LLMConfig) const language = (result.language as SupportedLanguage) || undefined
} else {
// Auto-migrate legacy testing endpoints
const migrated = migrateLegacyEndpoint(llmConfig)
if (migrated !== llmConfig) {
llmConfig = migrated
chrome.storage.local.set({ llmConfig: migrated })
} else if (!result.llmConfig) {
chrome.storage.local.set({ llmConfig: DEMO_CONFIG }) chrome.storage.local.set({ llmConfig: DEMO_CONFIG })
setConfig(DEMO_CONFIG)
} }
setConfig({ ...llmConfig, language })
}) })
}, []) }, [])
@@ -87,9 +106,14 @@ export function useAgent(): UseAgentResult {
agentRef.current?.stop() agentRef.current?.stop()
}, []) }, [])
const configure = useCallback(async (newConfig: LLMConfig) => { const configure = useCallback(async ({ language, ...llmConfig }: ExtConfig) => {
await chrome.storage.local.set({ llmConfig: newConfig }) await chrome.storage.local.set({ llmConfig })
setConfig(newConfig) if (language) {
await chrome.storage.local.set({ language })
} else {
await chrome.storage.local.remove('language')
}
setConfig({ ...llmConfig, language })
}, []) }, [])
return { return {
+35
View File
@@ -111,6 +111,41 @@
--color-sidebar-accent-foreground: var(--sidebar-accent-foreground); --color-sidebar-accent-foreground: var(--sidebar-accent-foreground);
--color-sidebar-border: var(--sidebar-border); --color-sidebar-border: var(--sidebar-border);
--color-sidebar-ring: var(--sidebar-ring); --color-sidebar-ring: var(--sidebar-ring);
--animate-blink-cursor: blink-cursor 1.2s step-end infinite;
@keyframes blink-cursor {
0%,
49% {
opacity: 1;
}
50%,
100% {
opacity: 0;
}
}
}
@keyframes glow-a {
0%,
100% {
opacity: 0.45;
transform: scale(1);
}
50% {
opacity: 0;
transform: scale(1.1);
}
}
@keyframes glow-b {
0%,
100% {
opacity: 0;
transform: scale(1.1);
}
50% {
opacity: 0.45;
transform: scale(1);
}
} }
@layer base { @layer base {
@@ -21,8 +21,9 @@ function InputGroup({ className, ...props }: React.ComponentProps<'div'>) {
'has-[>[data-align=block-start]]:h-auto has-[>[data-align=block-start]]:flex-col has-[>[data-align=block-start]]:[&>input]:pb-3', 'has-[>[data-align=block-start]]:h-auto has-[>[data-align=block-start]]:flex-col has-[>[data-align=block-start]]:[&>input]:pb-3',
'has-[>[data-align=block-end]]:h-auto has-[>[data-align=block-end]]:flex-col has-[>[data-align=block-end]]:[&>input]:pt-3', 'has-[>[data-align=block-end]]:h-auto has-[>[data-align=block-end]]:flex-col has-[>[data-align=block-end]]:[&>input]:pt-3',
// Focus state. // Focus state — soft multi-color glow matching ai-motion palette
'has-[[data-slot=input-group-control]:focus-visible]:border-ring has-[[data-slot=input-group-control]:focus-visible]:ring-ring/50 has-[[data-slot=input-group-control]:focus-visible]:ring-[3px]', 'has-[[data-slot=input-group-control]:focus-visible]:border-blue-400/60',
'has-[[data-slot=input-group-control]:focus-visible]:shadow-[0_0_0_1px_rgba(57,182,255,0.2),0_0_8px_rgba(57,182,255,0.15),0_0_16px_rgba(189,69,251,0.1)]',
// Error state. // Error state.
'has-[[data-slot][aria-invalid=true]]:ring-destructive/20 has-[[data-slot][aria-invalid=true]]:border-destructive dark:has-[[data-slot][aria-invalid=true]]:ring-destructive/40', 'has-[[data-slot][aria-invalid=true]]:ring-destructive/20 has-[[data-slot][aria-invalid=true]]:border-destructive dark:has-[[data-slot][aria-invalid=true]]:ring-destructive/40',
@@ -0,0 +1,164 @@
import { MotionProps, motion, useInView } from 'motion/react'
import { useEffect, useMemo, useRef, useState } from 'react'
import { cn } from '@/lib/utils'
interface TypingAnimationProps extends MotionProps {
children?: string
words?: string[]
className?: string
duration?: number
typeSpeed?: number
deleteSpeed?: number
delay?: number
pauseDelay?: number
loop?: boolean
as?: React.ElementType
startOnView?: boolean
showCursor?: boolean
blinkCursor?: boolean
cursorStyle?: 'line' | 'block' | 'underscore'
}
export function TypingAnimation({
children,
words,
className,
duration = 100,
typeSpeed,
deleteSpeed,
delay = 0,
pauseDelay = 1000,
loop = false,
as: Component = 'span',
startOnView = true,
showCursor = true,
blinkCursor = true,
cursorStyle = 'line',
...props
}: TypingAnimationProps) {
const MotionComponent = motion.create(Component, {
forwardMotionProps: true,
})
const [displayedText, setDisplayedText] = useState<string>('')
const [currentWordIndex, setCurrentWordIndex] = useState(0)
const [currentCharIndex, setCurrentCharIndex] = useState(0)
const [phase, setPhase] = useState<'typing' | 'pause' | 'deleting'>('typing')
const elementRef = useRef<HTMLElement | null>(null)
const isInView = useInView(elementRef as React.RefObject<Element>, {
amount: 0.3,
once: true,
})
const wordsToAnimate = useMemo(() => words || (children ? [children] : []), [words, children])
const hasMultipleWords = wordsToAnimate.length > 1
const typingSpeed = typeSpeed || duration
const deletingSpeed = deleteSpeed || typingSpeed / 2
const shouldStart = startOnView ? isInView : true
useEffect(() => {
if (!shouldStart || wordsToAnimate.length === 0) return
const timeoutDelay =
delay > 0 && displayedText === ''
? delay
: phase === 'typing'
? typingSpeed
: phase === 'deleting'
? deletingSpeed
: pauseDelay
const timeout = setTimeout(() => {
const currentWord = wordsToAnimate[currentWordIndex] || ''
const graphemes = Array.from(currentWord)
switch (phase) {
case 'typing':
if (currentCharIndex < graphemes.length) {
setDisplayedText(graphemes.slice(0, currentCharIndex + 1).join(''))
setCurrentCharIndex(currentCharIndex + 1)
} else {
if (hasMultipleWords || loop) {
const isLastWord = currentWordIndex === wordsToAnimate.length - 1
if (!isLastWord || loop) {
setPhase('pause')
}
}
}
break
case 'pause':
setPhase('deleting')
break
case 'deleting':
if (currentCharIndex > 0) {
setDisplayedText(graphemes.slice(0, currentCharIndex - 1).join(''))
setCurrentCharIndex(currentCharIndex - 1)
} else {
const nextIndex = (currentWordIndex + 1) % wordsToAnimate.length
setCurrentWordIndex(nextIndex)
setPhase('typing')
}
break
}
}, timeoutDelay)
return () => clearTimeout(timeout)
}, [
shouldStart,
phase,
currentCharIndex,
currentWordIndex,
displayedText,
wordsToAnimate,
hasMultipleWords,
loop,
typingSpeed,
deletingSpeed,
pauseDelay,
delay,
])
const currentWordGraphemes = Array.from(wordsToAnimate[currentWordIndex] || '')
const isComplete =
!loop &&
currentWordIndex === wordsToAnimate.length - 1 &&
currentCharIndex >= currentWordGraphemes.length &&
phase !== 'deleting'
const shouldShowCursor =
showCursor &&
!isComplete &&
(hasMultipleWords || loop || currentCharIndex < currentWordGraphemes.length)
const getCursorChar = () => {
switch (cursorStyle) {
case 'block':
return '▌'
case 'underscore':
return '_'
case 'line':
default:
return '|'
}
}
return (
<MotionComponent
ref={elementRef}
className={cn('leading-[5rem] tracking-[-0.02em]', className)}
{...props}
>
{displayedText}
{shouldShowCursor && (
<span className={cn('inline-block', blinkCursor && 'animate-blink-cursor')}>
{getCursorChar()}
</span>
)}
</MotionComponent>
)
}
@@ -15,7 +15,7 @@ import { ConfigPanel } from './components/ConfigPanel'
import { HistoryDetail } from './components/HistoryDetail' import { HistoryDetail } from './components/HistoryDetail'
import { HistoryList } from './components/HistoryList' import { HistoryList } from './components/HistoryList'
import { ActivityCard, EventCard } from './components/cards' import { ActivityCard, EventCard } from './components/cards'
import { EmptyState, Logo, StatusDot } from './components/misc' import { EmptyState, Logo, MotionOverlay, StatusDot } from './components/misc'
type View = type View =
| { name: 'chat' } | { name: 'chat' }
@@ -117,14 +117,15 @@ export default function App() {
const showEmptyState = !currentTask && history.length === 0 && !isRunning const showEmptyState = !currentTask && history.length === 0 && !isRunning
return ( return (
<div className="flex flex-col h-screen bg-background"> <div className="relative flex flex-col h-screen bg-background">
<MotionOverlay active={isRunning} />
{/* Header */} {/* Header */}
<header className="flex items-center justify-between border-b px-3 py-2"> <header className="flex items-center justify-between border-b px-3 py-2">
<div className="flex items-center gap-2"> <div className="flex items-center gap-2">
<Logo className="size-5" /> <Logo className="size-5" />
<span className="text-sm font-medium">Page Agent Ext</span> <span className="text-sm font-medium">Page Agent Ext</span>
</div> </div>
<div className="flex items-center gap-3"> <div className="flex items-center gap-1">
<StatusDot status={status} /> <StatusDot status={status} />
<Button <Button
variant="ghost" variant="ghost"
@@ -1,15 +1,15 @@
import type { LLMConfig } from '@page-agent/llms'
import { Copy, CornerUpLeft, Eye, EyeOff, HatGlasses, Home, Loader2, Scale } from 'lucide-react' import { Copy, CornerUpLeft, Eye, EyeOff, HatGlasses, Home, Loader2, Scale } from 'lucide-react'
import { useEffect, useState } from 'react' import { useEffect, useState } from 'react'
import { siGithub } from 'simple-icons' import { siGithub } from 'simple-icons'
import { DEMO_API_KEY, DEMO_BASE_URL, DEMO_MODEL } from '@/agent/constants' import { DEMO_API_KEY, DEMO_BASE_URL, DEMO_MODEL, isTestingEndpoint } from '@/agent/constants'
import type { ExtConfig, LanguagePreference } from '@/agent/useAgent'
import { Button } from '@/components/ui/button' import { Button } from '@/components/ui/button'
import { Input } from '@/components/ui/input' import { Input } from '@/components/ui/input'
interface ConfigPanelProps { interface ConfigPanelProps {
config: LLMConfig | null config: ExtConfig | null
onSave: (config: LLMConfig) => Promise<void> onSave: (config: ExtConfig) => Promise<void>
onClose: () => void onClose: () => void
} }
@@ -17,6 +17,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const [apiKey, setApiKey] = useState(config?.apiKey || DEMO_API_KEY) const [apiKey, setApiKey] = useState(config?.apiKey || DEMO_API_KEY)
const [baseURL, setBaseURL] = useState(config?.baseURL || DEMO_BASE_URL) const [baseURL, setBaseURL] = useState(config?.baseURL || DEMO_BASE_URL)
const [model, setModel] = useState(config?.model || DEMO_MODEL) const [model, setModel] = useState(config?.model || DEMO_MODEL)
const [language, setLanguage] = useState<LanguagePreference>(config?.language)
const [saving, setSaving] = useState(false) const [saving, setSaving] = useState(false)
const [userAuthToken, setUserAuthToken] = useState<string>('') const [userAuthToken, setUserAuthToken] = useState<string>('')
const [copied, setCopied] = useState(false) const [copied, setCopied] = useState(false)
@@ -28,6 +29,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
setApiKey(config?.apiKey || DEMO_API_KEY) setApiKey(config?.apiKey || DEMO_API_KEY)
setBaseURL(config?.baseURL || DEMO_BASE_URL) setBaseURL(config?.baseURL || DEMO_BASE_URL)
setModel(config?.model || DEMO_MODEL) setModel(config?.model || DEMO_MODEL)
setLanguage(config?.language)
}, [config]) }, [config])
// Poll for user auth token every second until found // Poll for user auth token every second until found
@@ -65,7 +67,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const handleSave = async () => { const handleSave = async () => {
setSaving(true) setSaving(true)
try { try {
await onSave({ apiKey, baseURL, model }) await onSave({ apiKey, baseURL, model, language })
} finally { } finally {
setSaving(false) setSaving(false)
} }
@@ -85,6 +87,23 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</Button> </Button>
</div> </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 */} {/* User Auth Token Section */}
<div className="flex flex-col gap-1.5 p-3 bg-muted/50 rounded-md border"> <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> <label className="text-xs font-medium text-muted-foreground">User Auth Token</label>
@@ -165,6 +184,19 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</div> </div>
</div> </div>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Language</label>
<select
value={language ?? ''}
onChange={(e) => setLanguage((e.target.value || undefined) as LanguagePreference)}
className="h-8 text-xs rounded-md border border-input bg-background px-2 cursor-pointer"
>
<option value="">System</option>
<option value="en-US">English</option>
<option value="zh-CN">中文</option>
</select>
</div>
<div className="flex gap-2 mt-2"> <div className="flex gap-2 mt-2">
<Button variant="outline" onClick={onClose} className="flex-1 h-8 text-xs cursor-pointer"> <Button variant="outline" onClick={onClose} className="flex-1 h-8 text-xs cursor-pointer">
Cancel Cancel
@@ -204,7 +236,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</a> </a>
<a <a
href="https://github.com/alibaba/page-agent/blob/main/packages/extension/PRIVACY.md" href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank" target="_blank"
rel="noopener noreferrer" rel="noopener noreferrer"
className="flex items-center gap-1 hover:text-foreground" className="flex items-center gap-1 hover:text-foreground"
@@ -1,5 +1,10 @@
import type { AgentStatus } from '@page-agent/core' import type { AgentStatus } from '@page-agent/core'
import { Motion } from 'ai-motion'
import { BookOpen, Globe } from 'lucide-react'
import { useEffect, useRef } from 'react'
import { siGithub } from 'simple-icons'
import { TypingAnimation } from '@/components/ui/typing-animation'
import { cn } from '@/lib/utils' import { cn } from '@/lib/utils'
// Status dot indicator // Status dot indicator
@@ -19,7 +24,7 @@ export function StatusDot({ status }: { status: AgentStatus }) {
}[status] }[status]
return ( return (
<div className="flex items-center gap-1.5"> <div className="flex items-center gap-1.5 mr-2">
<span <span
className={cn('size-2 rounded-full', colorClass, status === 'running' && 'animate-pulse')} className={cn('size-2 rounded-full', colorClass, status === 'running' && 'animate-pulse')}
/> />
@@ -32,14 +37,111 @@ export function Logo({ className }: { className?: string }) {
return <img src="/assets/page-agent-256.webp" alt="Page Agent" className={cn('', className)} /> return <img src="/assets/page-agent-256.webp" alt="Page Agent" className={cn('', className)} />
} }
// Empty state with logo // Full-screen ai-motion glow overlay, shown only while running
export function MotionOverlay({ active }: { active: boolean }) {
const containerRef = useRef<HTMLDivElement>(null)
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!)
return () => {
motion.dispose()
motionRef.current = null
}
}, [])
useEffect(() => {
const motion = motionRef.current
if (!motion) return
let disposed = false
if (active) {
motion.start()
motion.fadeIn()
} else {
motion.fadeOut().then(() => !disposed && motion.pause())
}
return () => {
disposed = true
}
}, [active])
return (
<div
ref={containerRef}
className="pointer-events-none absolute inset-0 z-10 opacity-60"
style={{ display: active ? undefined : 'none' }}
/>
)
}
// Empty state with logo and breathing glow
export function EmptyState() { export function EmptyState() {
return ( return (
<div className="flex flex-col items-center justify-center h-full gap-3 text-center px-6"> <div className="flex flex-col items-center justify-center h-full gap-4 text-center px-6">
<Logo className="size-20 opacity-80" /> <div className="relative select-none pointer-events-none">
<div className="absolute inset-0 -m-6 rounded-full bg-[conic-gradient(from_180deg,oklch(0.55_0.2_280),oklch(0.5_0.15_230),oklch(0.6_0.18_310),oklch(0.55_0.2_280))] blur-2xl animate-[glow-a_5s_ease-in-out_infinite]" />
<div className="absolute inset-0 -m-6 rounded-full bg-[conic-gradient(from_0deg,oklch(0.55_0.18_160),oklch(0.5_0.2_200),oklch(0.6_0.15_120),oklch(0.55_0.18_160))] blur-2xl animate-[glow-b_5s_ease-in-out_infinite]" />
<Logo className="relative size-20 opacity-80" />
</div>
<div> <div>
<h2 className="text-sm font-medium text-foreground">Page Agent Ext</h2> <h2 className="text-base font-medium text-foreground mb-1">Page Agent Ext</h2>
<p className="text-xs text-muted-foreground mt-1">Enter a task to automate this page</p> <TypingAnimation
className="text-sm text-muted-foreground"
words={[
'Enter a task to automate this page',
'Execute multi-page tasks',
'Call this extension from your web page',
'Use this extension in your own agents',
]}
cursorStyle="underscore"
loop
typeSpeed={20}
deleteSpeed={10}
pauseDelay={3000}
/>
</div>
<div className="flex items-center gap-3 mt-1 text-muted-foreground">
<a
href="https://github.com/alibaba/page-agent"
target="_blank"
rel="noopener noreferrer"
className="hover:text-foreground transition-colors"
title="GitHub"
>
<svg role="img" viewBox="0 0 24 24" className="size-4 fill-current">
<path d={siGithub.path} />
</svg>
</a>
<a
href="https://alibaba.github.io/page-agent/docs/features/chrome-extension"
target="_blank"
rel="noopener noreferrer"
className="hover:text-foreground transition-colors"
title="Documentation"
>
<BookOpen className="size-4" />
</a>
<a
href="https://alibaba.github.io/page-agent"
target="_blank"
rel="noopener noreferrer"
className="hover:text-foreground transition-colors"
title="Website"
>
<Globe className="size-4" />
</a>
</div> </div>
</div> </div>
) )
+4 -4
View File
@@ -38,9 +38,9 @@ export default defineConfig({
}, },
}), }),
manifest: { manifest: {
name: 'Page Agent Ext', default_locale: 'en',
description: name: '__MSG_extName__',
'AI-powered browser automation assistant. Control web pages with natural language.', description: '__MSG_extDescription__',
homepage_url: 'https://alibaba.github.io/page-agent/', homepage_url: 'https://alibaba.github.io/page-agent/',
permissions: ['tabs', 'tabGroups', 'sidePanel', 'storage'], permissions: ['tabs', 'tabGroups', 'sidePanel', 'storage'],
host_permissions: ['<all_urls>'], host_permissions: ['<all_urls>'],
@@ -48,7 +48,7 @@ export default defineConfig({
64: 'assets/page-agent-64.png', 64: 'assets/page-agent-64.png',
}, },
action: { action: {
default_title: 'Open Page Agent', default_title: '__MSG_extActionTitle__',
}, },
web_accessible_resources: [ web_accessible_resources: [
{ {
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "@page-agent/llms", "name": "@page-agent/llms",
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"main": "./dist/lib/page-agent-llms.js", "main": "./dist/lib/page-agent-llms.js",
"module": "./dist/lib/page-agent-llms.js", "module": "./dist/lib/page-agent-llms.js",
+3 -1
View File
@@ -1,6 +1,8 @@
/** /**
* OpenAI Client implementation * OpenAI Client implementation
*/ */
import * as z from 'zod'
import { InvokeError, InvokeErrorType } from './errors' import { InvokeError, InvokeErrorType } from './errors'
import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types' import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
import { modelPatch, zodToOpenAITool } from './utils' import { modelPatch, zodToOpenAITool } from './utils'
@@ -182,7 +184,7 @@ export class OpenAIClient implements LLMClient {
// Validate with schema // Validate with schema
const validation = tool.inputSchema.safeParse(parsedArgs) const validation = tool.inputSchema.safeParse(parsedArgs)
if (!validation.success) { if (!validation.success) {
console.error(validation.error) console.error(z.prettifyError(validation.error))
throw new InvokeError( throw new InvokeError(
InvokeErrorType.INVALID_TOOL_ARGS, InvokeErrorType.INVALID_TOOL_ARGS,
'Tool arguments validation failed', 'Tool arguments validation failed',
-1
View File
@@ -1 +0,0 @@
/// <reference types="vite/client" />
+4 -3
View File
@@ -1,16 +1,17 @@
import { OpenAIClient } from './OpenAIClient' import { OpenAIClient } from './OpenAIClient'
import { DEFAULT_TEMPERATURE, LLM_MAX_RETRIES } from './constants' import { DEFAULT_TEMPERATURE, LLM_MAX_RETRIES } from './constants'
import { InvokeError } from './errors' import { InvokeError, InvokeErrorType } from './errors'
import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types' import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
export type { InvokeError, InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } export { InvokeError, InvokeErrorType }
export type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool }
export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> { export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
// Runtime validation as defensive programming (types already guarantee these) // Runtime validation as defensive programming (types already guarantee these)
if (!config.baseURL || !config.apiKey || !config.model) { if (!config.baseURL || !config.apiKey || !config.model) {
throw new Error( throw new Error(
'[PageAgent] LLM configuration required. Please provide: baseURL, apiKey, model. ' + '[PageAgent] LLM configuration required. Please provide: baseURL, apiKey, model. ' +
'See: https://alibaba.github.io/page-agent/#/docs/features/models' 'See: https://alibaba.github.io/page-agent/docs/features/models'
) )
} }
+1 -1
View File
@@ -1,7 +1,7 @@
/** /**
* Core types for LLM integration * Core types for LLM integration
*/ */
import type { z } from 'zod' import type * as z from 'zod'
/** /**
* Message format - OpenAI standard (industry standard) * Message format - OpenAI standard (industry standard)
+1
View File
@@ -38,6 +38,7 @@ export function modelPatch(body: Record<string, any>) {
if (modelName.startsWith('qwen')) { if (modelName.startsWith('qwen')) {
debug('Applying Qwen patch: use higher temperature for auto fixing') debug('Applying Qwen patch: use higher temperature for auto fixing')
body.temperature = Math.max(body.temperature || 0, 1.0) body.temperature = Math.max(body.temperature || 0, 1.0)
body.enable_thinking = false
} }
if (modelName.startsWith('claude')) { if (modelName.startsWith('claude')) {
+5 -5
View File
@@ -1,7 +1,7 @@
{ {
"name": "page-agent", "name": "page-agent",
"private": false, "private": false,
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"main": "./dist/esm/page-agent.js", "main": "./dist/esm/page-agent.js",
"module": "./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{}})\"" "postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
}, },
"dependencies": { "dependencies": {
"@page-agent/core": "1.3.0", "@page-agent/core": "1.4.2",
"@page-agent/llms": "1.3.0", "@page-agent/llms": "1.4.2",
"@page-agent/page-controller": "1.3.0", "@page-agent/page-controller": "1.4.2",
"@page-agent/ui": "1.3.0", "@page-agent/ui": "1.4.2",
"chalk": "^5.6.2", "chalk": "^5.6.2",
"zod": "^4.3.5" "zod": "^4.3.5"
} }
+3 -3
View File
@@ -13,9 +13,9 @@ window.PageAgent = PageAgent
console.log('🚀 page-agent.js loaded!') console.log('🚀 page-agent.js loaded!')
const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM' const DEMO_MODEL = 'qwen3.5-plus'
const DEMO_BASE_URL = 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy' const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM' const DEMO_API_KEY = 'NA'
// in case document.x is not ready yet // in case document.x is not ready yet
setTimeout(() => { setTimeout(() => {
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "@page-agent/page-controller", "name": "@page-agent/page-controller",
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"main": "./dist/lib/page-controller.js", "main": "./dist/lib/page-controller.js",
"module": "./dist/lib/page-controller.js", "module": "./dist/lib/page-controller.js",
+1 -71
View File
@@ -86,7 +86,7 @@ export async function clickElement(element: HTMLElement) {
// dispatch a click event // dispatch a click event
// element.click() // element.click()
await waitFor(0.1) // Wait to ensure click event processing completes await waitFor(0.2) // Wait to ensure click event processing completes
} }
// eslint-disable-next-line @typescript-eslint/unbound-method // eslint-disable-next-line @typescript-eslint/unbound-method
@@ -181,11 +181,6 @@ export async function scrollVertically(
// Element-specific scrolling if element is provided // Element-specific scrolling if element is provided
if (element) { if (element) {
const targetElement = element const targetElement = element
console.log(
'[SCROLL DEBUG] Starting direct container scroll for element:',
targetElement.tagName
)
let currentElement = targetElement as HTMLElement | null let currentElement = targetElement as HTMLElement | null
let scrollSuccess = false let scrollSuccess = false
let scrolledElement: HTMLElement | null = null let scrolledElement: HTMLElement | null = null
@@ -198,19 +193,6 @@ export async function scrollVertically(
const hasScrollableY = /(auto|scroll|overlay)/.test(computedStyle.overflowY) const hasScrollableY = /(auto|scroll|overlay)/.test(computedStyle.overflowY)
const canScrollVertically = currentElement.scrollHeight > currentElement.clientHeight const canScrollVertically = currentElement.scrollHeight > currentElement.clientHeight
console.log(
'[SCROLL DEBUG] Checking element:',
currentElement.tagName,
'hasScrollableY:',
hasScrollableY,
'canScrollVertically:',
canScrollVertically,
'scrollHeight:',
currentElement.scrollHeight,
'clientHeight:',
currentElement.clientHeight
)
if (hasScrollableY && canScrollVertically) { if (hasScrollableY && canScrollVertically) {
const beforeScroll = currentElement.scrollTop const beforeScroll = currentElement.scrollTop
const maxScroll = currentElement.scrollHeight - currentElement.clientHeight const maxScroll = currentElement.scrollHeight - currentElement.clientHeight
@@ -228,27 +210,10 @@ export async function scrollVertically(
const afterScroll = currentElement.scrollTop const afterScroll = currentElement.scrollTop
const actualScrollDelta = afterScroll - beforeScroll const actualScrollDelta = afterScroll - beforeScroll
console.log(
'[SCROLL DEBUG] Scroll attempt:',
currentElement.tagName,
'before:',
beforeScroll,
'after:',
afterScroll,
'delta:',
actualScrollDelta
)
if (Math.abs(actualScrollDelta) > 0.5) { if (Math.abs(actualScrollDelta) > 0.5) {
scrollSuccess = true scrollSuccess = true
scrolledElement = currentElement scrolledElement = currentElement
scrollDelta = actualScrollDelta scrollDelta = actualScrollDelta
console.log(
'[SCROLL DEBUG] Successfully scrolled container:',
currentElement.tagName,
'delta:',
actualScrollDelta
)
break break
} }
} }
@@ -344,11 +309,6 @@ export async function scrollHorizontally(
// Element-specific scrolling if element is provided // Element-specific scrolling if element is provided
if (element) { if (element) {
const targetElement = element const targetElement = element
console.log(
'[SCROLL DEBUG] Starting direct container scroll for element:',
targetElement.tagName
)
let currentElement = targetElement as HTMLElement | null let currentElement = targetElement as HTMLElement | null
let scrollSuccess = false let scrollSuccess = false
let scrolledElement: HTMLElement | null = null let scrolledElement: HTMLElement | null = null
@@ -361,19 +321,6 @@ export async function scrollHorizontally(
const hasScrollableX = /(auto|scroll|overlay)/.test(computedStyle.overflowX) const hasScrollableX = /(auto|scroll|overlay)/.test(computedStyle.overflowX)
const canScrollHorizontally = currentElement.scrollWidth > currentElement.clientWidth const canScrollHorizontally = currentElement.scrollWidth > currentElement.clientWidth
console.log(
'[SCROLL DEBUG] Checking element:',
currentElement.tagName,
'hasScrollableX:',
hasScrollableX,
'canScrollHorizontally:',
canScrollHorizontally,
'scrollWidth:',
currentElement.scrollWidth,
'clientWidth:',
currentElement.clientWidth
)
if (hasScrollableX && canScrollHorizontally) { if (hasScrollableX && canScrollHorizontally) {
const beforeScroll = currentElement.scrollLeft const beforeScroll = currentElement.scrollLeft
const maxScroll = currentElement.scrollWidth - currentElement.clientWidth const maxScroll = currentElement.scrollWidth - currentElement.clientWidth
@@ -391,27 +338,10 @@ export async function scrollHorizontally(
const afterScroll = currentElement.scrollLeft const afterScroll = currentElement.scrollLeft
const actualScrollDelta = afterScroll - beforeScroll const actualScrollDelta = afterScroll - beforeScroll
console.log(
'[SCROLL DEBUG] Scroll attempt:',
currentElement.tagName,
'before:',
beforeScroll,
'after:',
afterScroll,
'delta:',
actualScrollDelta
)
if (Math.abs(actualScrollDelta) > 0.5) { if (Math.abs(actualScrollDelta) > 0.5) {
scrollSuccess = true scrollSuccess = true
scrolledElement = currentElement scrolledElement = currentElement
scrollDelta = actualScrollDelta scrollDelta = actualScrollDelta
console.log(
'[SCROLL DEBUG] Successfully scrolled container:',
currentElement.tagName,
'delta:',
actualScrollDelta
)
break break
} }
} }
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "@page-agent/ui", "name": "@page-agent/ui",
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"main": "./dist/lib/page-agent-ui.js", "main": "./dist/lib/page-agent-ui.js",
"module": "./dist/lib/page-agent-ui.js", "module": "./dist/lib/page-agent-ui.js",
+2 -2
View File
@@ -15,7 +15,7 @@ const enUS = {
close: 'Close', close: 'Close',
expand: 'Expand history', expand: 'Expand history',
collapse: 'Collapse history', collapse: 'Collapse history',
step: 'Step {{number}} · {{time}}{{duration}}', step: 'Step {{number}}',
}, },
tools: { tools: {
clicking: 'Clicking element [{{index}}]...', clicking: 'Clicking element [{{index}}]...',
@@ -63,7 +63,7 @@ const zhCN = {
close: '关闭', close: '关闭',
expand: '展开历史', expand: '展开历史',
collapse: '收起历史', collapse: '收起历史',
step: '步骤 {{number}} · {{time}}{{duration}}', step: '步骤 {{number}}',
}, },
tools: { tools: {
clicking: '正在点击元素 [{{index}}]...', clicking: '正在点击元素 [{{index}}]...',
+3 -7
View File
@@ -1,6 +1,6 @@
import { I18n, type SupportedLanguage } from '../i18n' import { I18n, type SupportedLanguage } from '../i18n'
import { truncate } from '../utils' import { truncate } from '../utils'
import { createCard, createReflectionLines, formatTime } from './cards' import { createCard, createReflectionLines } from './cards'
import type { AgentActivity, PanelAgentAdapter } from './types' import type { AgentActivity, PanelAgentAdapter } from './types'
import styles from './Panel.module.css' import styles from './Panel.module.css'
@@ -187,7 +187,6 @@ export class Panel {
tempCard.innerHTML = createCard({ tempCard.innerHTML = createCard({
icon: '❓', icon: '❓',
content: `Question: ${question}`, content: `Question: ${question}`,
meta: formatTime(this.#config.language ?? 'en-US'),
type: 'question', type: 'question',
}) })
const cardElement = tempCard.firstElementChild as HTMLElement const cardElement = tempCard.firstElementChild as HTMLElement
@@ -591,15 +590,12 @@ export class Panel {
/** Create cards for a history event */ /** Create cards for a history event */
#createHistoryCards(event: PanelAgentAdapter['history'][number]): string[] { #createHistoryCards(event: PanelAgentAdapter['history'][number]): string[] {
const cards: string[] = [] const cards: string[] = []
const time = formatTime(this.#config.language ?? 'en-US')
const meta = const meta =
event.type === 'step' && event.stepIndex !== undefined event.type === 'step' && event.stepIndex !== undefined
? this.#i18n.t('ui.panel.step', { ? this.#i18n.t('ui.panel.step', {
number: (event.stepIndex + 1).toString(), number: (event.stepIndex + 1).toString(),
time,
duration: '',
}) })
: time : undefined
if (event.type === 'step') { if (event.type === 'step') {
// Reflection card // Reflection card
@@ -636,7 +632,7 @@ export class Panel {
/** Create cards for an action */ /** Create cards for an action */
#createActionCards( #createActionCards(
action: { name: string; input: unknown; output: string }, action: { name: string; input: unknown; output: string },
meta: string meta?: string
): string[] { ): string[] {
const cards: string[] = [] const cards: string[] = []
-10
View File
@@ -32,16 +32,6 @@ export function createCard({ icon, content, meta, type }: CardOptions): string {
` `
} }
/** Format timestamp for cards */
export function formatTime(locale: string = 'en-US'): string {
return new Date().toLocaleTimeString(locale, {
hour12: false,
hour: '2-digit',
minute: '2-digit',
second: '2-digit',
})
}
/** Create reflection lines from reflection object */ /** Create reflection lines from reflection object */
export function createReflectionLines(reflection: { export function createReflectionLines(reflection: {
evaluation_previous_goal?: string evaluation_previous_goal?: string
+40 -24
View File
@@ -5,9 +5,9 @@
- **React** with TypeScript - **React** with TypeScript
- **Vite** for dev server and build - **Vite** for dev server and build
- **Tailwind CSS** for styling - **Tailwind CSS** for styling
- **shadcn/ui** (new-york style) for UI components - **shadcn/ui** (new-york style) for UI components**do NOT hand-edit `src/components/ui/` files**
- **Magic UI** for animations and effects - **Magic UI** for animations and effects
- **wouter** with hash routing for static hosting - **wouter** with browser routing (`base: "/page-agent"`)
- **lucide-react** for icons - **lucide-react** for icons
## Component Guidelines ## Component Guidelines
@@ -53,58 +53,74 @@ Located in `src/components/ui/`:
### Styling Rules ### Styling Rules
1. **Prefer Tailwind classes** over custom CSS 1. **Prefer Tailwind classes** over custom CSS
2. Use CSS modules only for complex component-specific styles 2. Support dark mode via `dark:` classes
3. Support dark mode via `dark:` classes 3. Use CSS variables from `src/index.css` for theme colors
4. Use CSS variables from `src/index.css` for theme colors
## Project Structure ## Project Structure
``` ```
src/ src/
├── pages/ ├── pages/
│ ├── Home.tsx # Homepage │ ├── home/
│ │ ├── HomeContent.tsx # Homepage sections
│ │ └── ...Section.tsx
│ └── docs/ │ └── docs/
│ ├── Layout.tsx # Documentation sidebar │ ├── index.tsx # Docs route switch
│ ├── Layout.tsx # Sidebar navigation
│ └── [section]/[topic]/page.tsx │ └── [section]/[topic]/page.tsx
├── components/ ├── components/
│ ├── ui/ # shadcn/ui + Magic UI components │ ├── ui/ # shadcn/ui + Magic UI (DO NOT hand-edit)
│ ├── Heading.tsx # Anchor heading for doc pages
│ ├── Header.tsx # Site header │ ├── Header.tsx # Site header
│ └── Footer.tsx # Site footer │ └── Footer.tsx # Site footer
├── i18n/ # Internationalization ├── i18n/ # Internationalization
├── router.tsx # Central routing ├── router.tsx # Root layout + routing
└── main.tsx # App entry └── main.tsx # App entry
``` ```
## Routing
Uses wouter browser routing with base path for GitHub Pages deployment at `https://alibaba.github.io/page-agent/`.
```tsx
// main.tsx
<Router base="/page-agent">
<PagesRouter />
</Router>
```
**Key rules:**
- Header and Footer live in `router.tsx` **outside** `<Switch>`, so they always see the root router context (`base="/page-agent"`)
- Docs pages are nested via `<Route path="/docs" nest>`, which creates a child context (`base="/page-agent/docs"`)
- Inside the docs nest, Link hrefs are relative to `/docs` (e.g. `href="/features/models"`, NOT `href="/docs/features/models"`)
- **Never use `~` prefix** in Link hrefs — it bypasses the base path entirely
- Doc page headings use `<Heading id="slug" level={2}>` for anchor links
### SPA on GitHub Pages
Instead of `404.html` redirects, the build copies `index.html` into every route directory. Add new routes to the `SPA_ROUTES` array in `vite.config.js`.
## Adding New Pages ## Adding New Pages
### Documentation Page ### Documentation Page
1. Create `src/pages/docs/<section>/<slug>/page.tsx` 1. Create `src/pages/docs/<section>/<slug>/page.tsx`
2. Add route to `src/router.tsx` with `<Header /> + <DocsLayout>` wrapper 2. Add route in `src/pages/docs/index.tsx`
3. Add navigation item to `pages/docs/Layout.tsx` 3. Add navigation item in `src/pages/docs/Layout.tsx`
4. Add path to `SPA_ROUTES` in `vite.config.js`
## Routing
Uses hash-based routing for static hosting:
```tsx
import { Router } from 'wouter'
import { useHashLocation } from 'wouter/use-hash-location'
;<Router hook={useHashLocation}>{/* routes */}</Router>
```
## Configuration Files ## Configuration Files
| File | Purpose | | File | Purpose |
| ----------------- | ----------------------- | | ----------------- | ----------------------- |
| `components.json` | shadcn/ui configuration | | `components.json` | shadcn/ui configuration |
| `vite.config.js` | Vite build settings | | `vite.config.js` | Vite build + SPA routes |
| `tsconfig.json` | TypeScript config | | `tsconfig.json` | TypeScript config |
## Commands ## Commands
```bash ```bash
npm start # Dev server (from root) npm start # Dev server (from root)
npm run build:website # Build website (from root) npm run build:website # Build website (from root)
``` ```
+13 -2
View File
@@ -45,13 +45,24 @@
</script> </script>
</head> </head>
<body> <body>
<div id="root"></div> <div id="root">
<div id="sk">
<p class="sk-text" id="sk-text">Loading...</p>
<style>
#sk{display:flex;align-items:center;justify-content:center;min-height:100vh;background:linear-gradient(135deg,#eff6ff,#f5f3ff)}
@media(prefers-color-scheme:dark){#sk{background:linear-gradient(135deg,#111827,#1f2937)}}
.sk-text{font:400 14px/1 system-ui,sans-serif;color:#94a3b8;animation:skf 2s ease-in-out infinite}
@keyframes skf{0%,100%{opacity:.6}50%{opacity:.3}}
</style>
</div>
</div>
<script type="module" src="./src/main.tsx"></script> <script type="module" src="./src/main.tsx"></script>
<script> <script>
// Dynamically update html lang attribute based on i18n detection
const updateHtmlLang = () => { const updateHtmlLang = () => {
const lang = localStorage.getItem('i18nextLng') || navigator.language || 'zh-CN' const lang = localStorage.getItem('i18nextLng') || navigator.language || 'zh-CN'
document.documentElement.lang = lang document.documentElement.lang = lang
const el = document.getElementById('sk-text')
if (el) el.textContent = lang.startsWith('zh') ? '加载中...' : 'Loading...'
} }
updateHtmlLang() updateHtmlLang()
window.addEventListener('storage', updateHtmlLang) window.addEventListener('storage', updateHtmlLang)
+6 -6
View File
@@ -1,7 +1,7 @@
{ {
"name": "@page-agent/website", "name": "@page-agent/website",
"private": true, "private": true,
"version": "1.3.0", "version": "1.4.2",
"type": "module", "type": "module",
"scripts": { "scripts": {
"dev": "vite --host 0.0.0.0", "dev": "vite --host 0.0.0.0",
@@ -15,19 +15,19 @@
"@radix-ui/react-slot": "^1.2.4", "@radix-ui/react-slot": "^1.2.4",
"@radix-ui/react-switch": "^1.2.6", "@radix-ui/react-switch": "^1.2.6",
"@radix-ui/react-tooltip": "^1.2.8", "@radix-ui/react-tooltip": "^1.2.8",
"@types/react": "^19.2.13", "@types/react": "^19.2.14",
"@types/react-dom": "^19.2.1", "@types/react-dom": "^19.2.1",
"class-variance-authority": "^0.7.1", "class-variance-authority": "^0.7.1",
"clsx": "^2.1.1", "clsx": "^2.1.1",
"lucide-react": "^0.563.0", "lucide-react": "^0.575.0",
"motion": "^12.34.0", "motion": "^12.34.3",
"next-themes": "^0.4.6", "next-themes": "^0.4.6",
"react": "^19.2.4", "react": "^19.2.4",
"react-dom": "^19.2.4", "react-dom": "^19.2.4",
"rough-notation": "^0.5.1", "rough-notation": "^0.5.1",
"simple-icons": "^16.8.0", "simple-icons": "^16.9.0",
"sonner": "^2.0.7", "sonner": "^2.0.7",
"tailwind-merge": "^3.4.0", "tailwind-merge": "^3.5.0",
"tailwindcss": "^4.1.14", "tailwindcss": "^4.1.14",
"tw-animate-css": "^1.4.0", "tw-animate-css": "^1.4.0",
"wouter": "^3.9.0" "wouter": "^3.9.0"
@@ -16,6 +16,14 @@ export default function Footer() {
© 2026 page-agent. All rights reserved. © 2026 page-agent. All rights reserved.
</p> </p>
<div className="flex items-center space-x-6"> <div className="flex items-center space-x-6">
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank"
rel="noopener noreferrer"
className="text-gray-600 dark:text-gray-300 hover:text-gray-900 dark:hover:text-white transition-colors duration-200 text-sm"
>
{isZh ? '使用条款与隐私' : 'Terms & Privacy'}
</a>
<a <a
href="https://github.com/alibaba/page-agent" href="https://github.com/alibaba/page-agent"
target="_blank" target="_blank"
+5 -5
View File
@@ -23,7 +23,7 @@ export default function Header() {
<div className="flex items-center justify-between gap-2"> <div className="flex items-center justify-between gap-2">
{/* Logo */} {/* Logo */}
<Link <Link
href="~/" href="/"
className="flex items-center gap-2 sm:gap-3 group shrink-0" className="flex items-center gap-2 sm:gap-3 group shrink-0"
aria-label={isZh ? 'page-agent 首页' : 'page-agent home'} aria-label={isZh ? 'page-agent 首页' : 'page-agent home'}
onClick={() => setMobileMenuOpen(false)} onClick={() => setMobileMenuOpen(false)}
@@ -44,7 +44,7 @@ export default function Header() {
animateOnHover={true} animateOnHover={true}
aria-hidden="true" aria-hidden="true"
> >
GUI Agent in your webpage AI Agent In Your Webpage
</HyperText> </HyperText>
</div> </div>
</Link> </Link>
@@ -56,7 +56,7 @@ export default function Header() {
aria-label="Mobile navigation" aria-label="Mobile navigation"
> >
<Link <Link
href="~/docs/introduction/overview" href="/docs/introduction/overview"
className="p-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200 shrink-0" className="p-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200 shrink-0"
aria-label={isZh ? '文档' : 'Docs'} aria-label={isZh ? '文档' : 'Docs'}
> >
@@ -90,7 +90,7 @@ export default function Header() {
{import.meta.env.VERSION} {import.meta.env.VERSION}
</span> </span>
<Link <Link
href="~/docs/introduction/overview" href="/docs/introduction/overview"
className="flex items-center gap-1.5 text-gray-600 dark:text-gray-300 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200" className="flex items-center gap-1.5 text-gray-600 dark:text-gray-300 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
> >
<BookOpen className="w-4 h-4" /> <BookOpen className="w-4 h-4" />
@@ -138,7 +138,7 @@ export default function Header() {
role="navigation" role="navigation"
> >
<Link <Link
href="~/docs/introduction/overview" href="/docs/introduction/overview"
className="flex items-center gap-2 px-3 py-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200" className="flex items-center gap-2 px-3 py-2 rounded-lg text-gray-600 dark:text-gray-300 hover:bg-gray-100 dark:hover:bg-gray-800 hover:text-blue-600 dark:hover:text-blue-400 transition-colors duration-200"
onClick={() => setMobileMenuOpen(false)} onClick={() => setMobileMenuOpen(false)}
> >
@@ -0,0 +1,45 @@
import { ComponentPropsWithoutRef, useEffect, useRef } from 'react'
import { cn } from '@/lib/utils'
type Level = 2 | 3
interface HeadingProps extends Omit<ComponentPropsWithoutRef<'h2'>, 'children'> {
id: string
level?: Level
children: React.ReactNode
}
const levelStyles = {
2: { tag: 'h2', className: 'text-2xl font-semibold mb-4' },
3: { tag: 'h3', className: 'text-xl font-semibold mb-3' },
} as const
export function Heading({ id, level = 2, className, children, ...props }: HeadingProps) {
const ref = useRef<HTMLHeadingElement>(null)
const { tag: Tag, className: defaultClassName } = levelStyles[level]
useEffect(() => {
if (window.location.hash === `#${id}`) {
ref.current?.scrollIntoView({ behavior: 'smooth' })
}
}, [id])
return (
<Tag
ref={ref}
id={id}
className={cn('group relative scroll-mt-20', defaultClassName, className)}
{...props}
>
<a
href={`#${id}`}
className="absolute -left-5 top-1/2 -translate-y-1/2 opacity-0 group-hover:opacity-100 text-gray-400 hover:text-blue-500 transition-opacity no-underline"
aria-label={`Link to ${id}`}
>
#
</a>
{children}
</Tag>
)
}
@@ -85,7 +85,7 @@ export function MagicCard({
`, `,
}} }}
/> />
<div className="bg-background absolute inset-px rounded-[inherit]" /> <div className="absolute inset-px rounded-[inherit] bg-white dark:bg-neutral-900" />
<motion.div <motion.div
className="pointer-events-none absolute inset-px rounded-[inherit] opacity-0 transition-opacity duration-300 group-hover:opacity-100" className="pointer-events-none absolute inset-px rounded-[inherit] opacity-0 transition-opacity duration-300 group-hover:opacity-100"
style={{ style={{
@@ -0,0 +1,74 @@
import { ComponentPropsWithoutRef } from 'react'
import { cn } from '@/lib/utils'
interface MarqueeProps extends ComponentPropsWithoutRef<'div'> {
/**
* Optional CSS class name to apply custom styles
*/
className?: string
/**
* Whether to reverse the animation direction
* @default false
*/
reverse?: boolean
/**
* Whether to pause the animation on hover
* @default false
*/
pauseOnHover?: boolean
/**
* Content to be displayed in the marquee
*/
children: React.ReactNode
/**
* Whether to animate vertically instead of horizontally
* @default false
*/
vertical?: boolean
/**
* Number of times to repeat the content
* @default 4
*/
repeat?: number
}
export function Marquee({
className,
reverse = false,
pauseOnHover = false,
children,
vertical = false,
repeat = 4,
...props
}: MarqueeProps) {
return (
<div
{...props}
className={cn(
'group flex [gap:var(--gap)] overflow-hidden p-2 [--duration:40s] [--gap:1rem]',
{
'flex-row': !vertical,
'flex-col': vertical,
},
className
)}
>
{Array(repeat)
.fill(0)
.map((_, i) => (
<div
key={i}
className={cn('flex shrink-0 justify-around [gap:var(--gap)]', {
'animate-marquee flex-row': !vertical,
'animate-marquee-vertical flex-col': vertical,
'group-hover:[animation-play-state:paused]': pauseOnHover,
'[animation-direction:reverse]': reverse,
})}
>
{children}
</div>
))}
</div>
)
}
+6 -7
View File
@@ -1,11 +1,10 @@
// Demo build (auto-init with demo LLM, for quick testing) // Demo build (auto-init with demo LLM, for quick testing)
export const CDN_DEMO_URL = export const CDN_DEMO_URL =
'https://cdn.jsdelivr.net/npm/page-agent@1.3.0/dist/iife/page-agent.demo.js' 'https://cdn.jsdelivr.net/npm/page-agent@1.4.2/dist/iife/page-agent.demo.js'
export const CDN_DEMO_CN_URL = export const CDN_DEMO_CN_URL =
'https://registry.npmmirror.com/page-agent/1.3.0/files/dist/iife/page-agent.demo.js' 'https://registry.npmmirror.com/page-agent/1.4.2/files/dist/iife/page-agent.demo.js'
// Demo LLM for website testing // Demo LLM for website testing (homepage quick trial uses flash)
export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM' export const DEMO_MODEL = 'qwen3.5-flash'
export const DEMO_BASE_URL = export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy' export const DEMO_API_KEY = 'NA'
export const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
+18
View File
@@ -377,6 +377,24 @@ td {
background-position: bottom center; background-position: bottom center;
} }
} }
--animate-marquee: marquee var(--duration) infinite linear;
--animate-marquee-vertical: marquee-vertical var(--duration) linear infinite;
@keyframes marquee {
from {
transform: translateX(0);
}
to {
transform: translateX(calc(-100% - var(--gap)));
}
}
@keyframes marquee-vertical {
from {
transform: translateY(0);
}
to {
transform: translateY(calc(-100% - var(--gap)));
}
}
} }
/* shadcn dark mode */ /* shadcn dark mode */
+8 -2
View File
@@ -1,15 +1,21 @@
import { createRoot } from 'react-dom/client' import { createRoot } from 'react-dom/client'
import { Router } from 'wouter' import { Router } from 'wouter'
import { useHashLocation } from 'wouter/use-hash-location'
import { LanguageProvider } from './i18n/context' import { LanguageProvider } from './i18n/context'
import { default as PagesRouter } from './router' import { default as PagesRouter } from './router'
import './index.css' import './index.css'
// Redirect legacy hash routes (e.g. /#/docs/foo) to clean paths
const { hash } = window.location
if (hash.length > 1 && hash.includes('/')) {
const path = hash.replace(/^#\/?/, '/')
history.replaceState(null, '', '/page-agent' + path)
}
createRoot(document.getElementById('root')!).render( createRoot(document.getElementById('root')!).render(
<LanguageProvider> <LanguageProvider>
<Router hook={useHashLocation}> <Router base="/page-agent">
<PagesRouter /> <PagesRouter />
</Router> </Router>
</LanguageProvider> </LanguageProvider>
+19 -578
View File
@@ -1,586 +1,27 @@
/* eslint-disable react-dom/no-dangerously-set-innerhtml */ import { Suspense, lazy } from 'react'
import { Bot, Box, MessageSquare, PlayCircle, Shield, Sparkles, Users, Zap } from 'lucide-react'
import { useEffect, useState } from 'react'
import { Link, useSearchParams } from 'wouter'
import Footer from '../components/Footer' import HeroSection from './home/HeroSection'
import Header from '../components/Header'
import { AnimatedGradientText } from '../components/ui/animated-gradient-text'
import { Highlighter } from '../components/ui/highlighter'
import { NeonGradientCard } from '../components/ui/neon-gradient-card'
import { Particles } from '../components/ui/particles'
import { SparklesText } from '../components/ui/sparkles-text'
import {
CDN_DEMO_CN_URL,
CDN_DEMO_URL,
DEMO_API_KEY,
DEMO_BASE_URL,
DEMO_MODEL,
} from '../constants'
import { useLanguage } from '../i18n/context'
function getInjection(useCN?: boolean) { const FeaturesSection = lazy(() => import('./home/FeaturesSection'))
const cdn = useCN ? CDN_DEMO_CN_URL : CDN_DEMO_URL const ScenariosSection = lazy(() => import('./home/ScenariosSection'))
const OneMoreThingSection = lazy(() => import('./home/OneMoreThingSection'))
const injection = encodeURI(
`javascript:(function(){var s=document.createElement('script');s.src=\`${cdn}?t=\${Math.random()}\`;s.setAttribute('crossorigin', true);s.type="text/javascript";s.onload=()=>console.log('PageAgent script loaded!');document.body.appendChild(s);})();`
)
return `
<a
href=${injection}
class="inline-flex items-center text-xs px-3 py-2 bg-blue-500 text-white font-medium rounded-lg hover:shadow-md transform hover:scale-105 transition-all duration-200 cursor-move border-2 border-dashed border-green-300"
draggable="true"
onclick="return false;"
title="Drag me to your bookmarks bar!"
>
✨PageAgent
</a>
`
}
export default function HomePage() { export default function HomePage() {
const { language, isZh } = useLanguage()
const defaultTask = isZh
? '从导航栏中进入文档页,打开"快速开始"相关的文档,帮我总结成 markdown'
: 'Goto docs in navigation bar, find Quick-Start section, and summarize in markdown'
const [task, setTask] = useState(() => defaultTask)
// Update task when language changes
useEffect(() => {
setTask(defaultTask)
}, [defaultTask])
const [params, setParams] = useSearchParams()
const isOther = params.has('try_other')
const [activeTab, setActiveTab] = useState<'try' | 'other'>(isOther ? 'other' : 'try')
const [cdnSource, setCdnSource] = useState<'international' | 'china'>('international')
const handleExecute = async () => {
if (!task.trim()) return
const win = window as any
// Lazy load PageAgent only when user clicks execute
if (!win.pageAgent || win.pageAgent.disposed) {
const { PageAgent } = await import('page-agent')
win.pageAgent = new PageAgent({
// 把 react 根元素排除掉,挂了很多冒泡时间导致假阳
interactiveBlacklist: [document.getElementById('root')!],
language: language,
instructions: {
system: 'You are a helpful assistant on PageAgent website.',
getPageInstructions: (url) => {
const hint = url.includes('page-agent') ? 'This is PageAgent demo page.' : undefined
console.log('[instructions] getPageInstructions:', url, '->', hint)
return hint
},
},
model:
import.meta.env.DEV && import.meta.env.LLM_MODEL_NAME
? import.meta.env.LLM_MODEL_NAME
: DEMO_MODEL,
baseURL:
import.meta.env.DEV && import.meta.env.LLM_BASE_URL
? import.meta.env.LLM_BASE_URL
: DEMO_BASE_URL,
apiKey:
import.meta.env.DEV && import.meta.env.LLM_API_KEY
? import.meta.env.LLM_API_KEY
: DEMO_API_KEY,
// enableAskUser: false,
// promptForNextTask: false,
// enablePanel: false,
})
}
const result = await win.pageAgent.execute(task)
console.log(result)
}
return ( return (
<div className="min-h-screen bg-linear-to-br from-blue-50 to-purple-50 dark:from-gray-900 dark:to-gray-800"> <>
<Header /> <HeroSection />
<Suspense
{/* Hero Section */} fallback={
<main id="main-content"> <div className="flex items-center justify-center gap-3 py-20 text-gray-400">
<section <div className="w-4 h-4 border-2 border-blue-500 border-t-transparent rounded-full animate-spin" />
className="relative px-6 py-22 pb-18 lg:py-28 overflow-hidden" Loading...
aria-labelledby="hero-heading"
>
<div className="max-w-7xl mx-auto text-center">
{/* Background Pattern + Particles */}
<div className="absolute inset-0 opacity-30" aria-hidden="true">
<div className="absolute inset-0 bg-linear-to-r from-blue-400/20 to-purple-400/20 rounded-3xl transform rotate-1"></div>
<div className="absolute inset-0 bg-linear-to-l from-purple-400/20 to-blue-400/20 rounded-3xl transform -rotate-1"></div>
</div>
<Particles
className="absolute inset-0"
quantity={80}
staticity={30}
ease={80}
color="#6366f1"
/>
<div className="relative z-10">
<div className="inline-flex items-center px-4 py-2 mb-8 text-sm font-medium bg-white/90 dark:bg-gray-800/90 rounded-full shadow-lg border border-gray-200 dark:border-gray-700">
<span
className="w-2 h-2 bg-blue-500 rounded-full mr-2 animate-pulse"
aria-hidden="true"
></span>
<AnimatedGradientText colorFrom="#3b82f6" colorTo="#8b5cf6">
GUI Agent in your webpage
</AnimatedGradientText>
</div>
<h1
id="hero-heading"
className="text-5xl lg:text-7xl font-bold mb-8 bg-linear-to-r from-blue-600 to-purple-600 bg-clip-text text-transparent pb-1"
>
{isZh ? '让你的 Web 应用' : 'The AI Operator'}
<br />
{isZh ? '拥有 AI 操作员' : 'Living in Your Web App'}
</h1>
<p className="text-xl lg:text-2xl text-gray-600 dark:text-gray-300 mb-12 max-w-4xl mx-auto leading-relaxed">
<Highlighter action="underline" color="#8b5cf6" strokeWidth={2}>
<span className="bg-linear-to-r from-blue-500 to-purple-500 bg-clip-text text-transparent font-bold">
{isZh ? '🪄一行代码' : '🪄One line of code'}
</span>
</Highlighter>
{isZh
? ',为你的网站添加 GUI Agent。'
: ' adds intelligent GUI Agents to your website.'}
<br />
{isZh
? '用户/答疑机器人给出文字指示,AI 帮你操作页面。'
: 'Users give natural language commands, AI handles the rest.'}
</p>
{/* Try It Now Section - Tab Card */}
<div className="mb-12">
<div className="max-w-3xl mx-auto">
<NeonGradientCard
borderSize={2}
borderRadius={20}
neonColors={{ firstColor: '#ff00aa', secondColor: '#00FFF1' }}
>
{/* Tab Headers */}
<div className="flex border-b border-gray-200 dark:border-gray-700">
<button
onClick={() => setActiveTab('try')}
className={`flex-1 px-4 py-4 text-lg font-medium transition-colors duration-200 rounded-tl-2xl ${
activeTab === 'try'
? 'bg-linear-to-r from-blue-50 to-purple-50 dark:from-blue-900/30 dark:to-purple-900/30 text-blue-700 dark:text-blue-300 border-b-2 border-blue-500'
: 'text-gray-600 dark:text-gray-400 hover:text-gray-900 dark:hover:text-white hover:bg-gray-50 dark:hover:bg-gray-700'
}`}
>
{isZh ? '🚀 立即尝试' : '🚀 Try It Now'}
</button>
<button
onClick={() => setActiveTab('other')}
className={`flex-1 px-4 py-4 text-lg font-medium transition-colors duration-200 rounded-tr-2xl ${
activeTab === 'other'
? 'bg-linear-to-r from-green-50 to-blue-50 dark:from-green-900/30 dark:to-blue-900/30 text-green-700 dark:text-green-300 border-b-2 border-green-500'
: 'text-gray-600 dark:text-gray-400 hover:text-gray-900 dark:hover:text-white hover:bg-gray-50 dark:hover:bg-gray-700'
}`}
>
{isZh ? '🌐 其他网页尝试' : '🌐 Try on Other Sites'}
</button>
</div>
{/* Tab Content */}
<div className="p-4">
{activeTab === 'try' && (
<div className="space-y-4">
<div className="relative">
<input
value={task}
onChange={(e) => setTask(e.target.value)}
placeholder={
isZh
? '输入您想要 AI 执行的任务...'
: 'Describe what you want AI to do...'
}
className="w-full px-4 py-3 pr-20 border border-gray-300 dark:border-gray-600 rounded-lg bg-white dark:bg-gray-700 text-gray-900 dark:text-white placeholder-gray-500 dark:placeholder-gray-400 focus:ring-2 focus:ring-blue-500 focus:border-transparent resize-none text-sm mb-0"
data-page-agent-not-interactive
/>
<button
onClick={handleExecute}
// disabled
// disabled={!task.trim()}
className="absolute right-2 top-2 px-5 py-1.5 bg-linear-to-r from-blue-600 to-purple-600 text-white font-medium rounded-md hover:shadow-md transform hover:scale-105 transition-all duration-200 disabled:opacity-50 disabled:cursor-not-allowed disabled:transform-none text-sm"
data-page-agent-not-interactive
>
{isZh ? '执行' : 'Run'}
</button>
</div>
</div>
)}
{activeTab === 'other' && (
<div className="grid md:grid-cols-2 gap-6">
{/* 左侧:操作步骤 */}
<div className="space-y-4">
{/* Keyboard Shortcut Hint */}
<div className="bg-blue-50 dark:bg-gray-700 p-4 rounded-lg">
<p className="text-gray-700 dark:text-gray-300 text-sm mb-3">
<span className="font-semibold">
{isZh ? '步骤 1:' : 'Step 1:'}
</span>{' '}
{isZh ? '显示收藏夹栏' : 'Show your bookmarks bar'}
</p>
<div className="flex items-center justify-center gap-2">
<kbd className="px-2 py-1 bg-white dark:bg-gray-600 border border-gray-300 dark:border-gray-500 rounded text-xs font-mono">
Ctrl + Shift + B
</kbd>
<span className="text-gray-500 dark:text-gray-400">
{isZh ? '或' : 'or'}
</span>
<kbd className="px-2 py-1 bg-white dark:bg-gray-600 border border-gray-300 dark:border-gray-500 rounded text-xs font-mono">
+ Shift + B
</kbd>
</div>
</div>
{/* Draggable Bookmarklet */}
<div className="bg-green-50 dark:bg-gray-700 p-4 rounded-lg">
<p className="text-gray-700 dark:text-gray-300 text-sm mb-3">
<span className="font-semibold">
{isZh ? '步骤 2:' : 'Step 2:'}
</span>{' '}
{isZh
? '拖拽下面按钮到收藏夹栏'
: 'Drag this button to your bookmarks'}
</p>
<div className="flex items-center justify-center gap-3">
<select
value={cdnSource}
onChange={(e) =>
setCdnSource(e.target.value as 'international' | 'china')
}
className="px-2 py-1.5 text-xs border border-gray-300 dark:border-gray-500 rounded bg-white dark:bg-gray-600 text-gray-700 dark:text-gray-200"
>
<option value="international">
{isZh ? '国际' : 'International'}
</option>
<option value="china">
{isZh ? '国内镜像' : 'China Mirror'}
</option>
</select>
<div
dangerouslySetInnerHTML={{
__html: getInjection(cdnSource === 'china'),
}}
></div>
</div>
</div>
{/* Usage Instructions */}
<div className="bg-purple-50 dark:bg-gray-700 p-4 rounded-lg">
<p className="text-gray-700 dark:text-gray-300 text-sm">
<span className="font-semibold">
{isZh ? '步骤 3:' : 'Step 3:'}
</span>{' '}
{isZh
? '在其他网站点击收藏夹中的按钮即可使用'
: 'Click the bookmark on any site to activate'}
</p>
</div>
</div>
{/* 右侧:注意事项 */}
<div className="bg-yellow-50 dark:bg-gray-700 p-4 rounded-lg">
<h4 className="font-semibold text-gray-900 dark:text-white mb-3 text-sm">
{isZh ? '⚠️ 注意' : '⚠️ Heads Up'}
</h4>
<ul className="space-y-2 text-sm text-gray-700 dark:text-gray-300">
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '仅做技术评估,链接定期失效'
: 'Demo only—link may expire without notice'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '使用 DeepSeek 模型,参考 DeepSeek 用户协议和隐私政策'
: 'This free demo uses DeepSeek API (see their terms and privacy policy)'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '部分网站屏蔽了链接嵌入,将无反应'
: 'Some sites block script injection (CSP policies)'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '仅支持单页应用,页面跳转后需要重新注入'
: 'Works on single-page apps only—reload required after navigation'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '仅识别文本,不识别图像,不支持拖拽等复杂交互'
: 'Text-only understanding—no image recognition or drag-and-drop'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh ? '详细使用限制参照' : 'Full limitations in'}{' '}
<Link
href="/docs/introduction/limitations"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
{isZh ? '《文档》' : 'Docs'}
</Link>
</li>
</ul>
</div>
</div>
)}
</div>
</NeonGradientCard>
</div>
</div>
<ul
className="flex flex-wrap justify-center gap-6 text-sm text-gray-500 dark:text-gray-400"
role="list"
>
<li className="flex items-center">
<span
className="w-2 h-2 bg-green-500 rounded-full mr-2"
aria-hidden="true"
></span>
{isZh ? '纯前端方案' : 'Pure Front-end Solution'}
</li>
<li className="flex items-center">
<span
className="w-2 h-2 bg-green-500 rounded-full mr-2"
aria-hidden="true"
></span>
{isZh ? '支持私有模型' : 'Your Own Models'}
</li>
<li className="flex items-center">
<span
className="w-2 h-2 bg-green-500 rounded-full mr-2"
aria-hidden="true"
></span>
{isZh ? '无痛脱敏' : 'Built-in Privacy'}
</li>
<li className="flex items-center">
<span
className="w-2 h-2 bg-green-500 rounded-full mr-2"
aria-hidden="true"
></span>
{isZh ? 'MIT 开源' : 'MIT Open Source'}
</li>
</ul>
</div>
</div> </div>
</section> }
>
{/* Features Section */} <FeaturesSection />
<section <ScenariosSection />
className="px-6 py-20 bg-white/50 dark:bg-gray-800/50 backdrop-blur-sm" <OneMoreThingSection />
aria-labelledby="features-heading" </Suspense>
> </>
<div className="max-w-7xl mx-auto">
<div className="grid md:grid-cols-2 lg:grid-cols-4 gap-8" role="list">
{/* Feature 1 */}
<article
className="group p-8 bg-linear-to-br from-blue-100 to-purple-100 dark:from-gray-700 dark:to-gray-800 rounded-2xl shadow-lg hover:shadow-xl transition-all duration-300 border border-gray-100 dark:border-gray-700"
role="listitem"
>
<div
className="w-14 h-14 bg-linear-to-br from-blue-500 to-blue-600 rounded-xl flex items-center justify-center mb-6 group-hover:scale-110 group-hover:rotate-3 transition-all duration-300 shadow-lg"
aria-hidden="true"
>
<Box className="w-7 h-7 text-white" strokeWidth={2.5} />
</div>
<h3 className="text-xl font-bold mb-4 text-gray-900 dark:text-white">
{isZh ? '纯页面内方案' : 'In-page Solution'}
</h3>
<p className="text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '完全运行在你的页面内。不需要浏览器插件、不需要无头浏览器,不需要后端。'
: 'Runs entirely within your page. No browser extensions, no headless browsers, and no backend required.'}
</p>
</article>
{/* Feature 2 */}
<article
className="group p-8 bg-linear-to-br from-purple-100 to-pink-100 dark:from-gray-700 dark:to-gray-800 rounded-2xl shadow-lg hover:shadow-xl transition-all duration-300 border border-gray-100 dark:border-gray-700"
role="listitem"
>
<div
className="w-14 h-14 bg-linear-to-br from-green-500 to-green-600 rounded-xl flex items-center justify-center mb-6 group-hover:scale-110 group-hover:rotate-3 transition-all duration-300 shadow-lg"
aria-hidden="true"
>
<Zap className="w-7 h-7 text-white fill-white" strokeWidth={2.5} />
</div>
<h3 className="text-xl font-bold mb-4 text-gray-900 dark:text-white">
{isZh ? '零后端部署' : 'Zero Backend Setup'}
</h3>
<p className="text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '前端脚本引入,自定义 LLM 接入点。从 OpenAI 到 qwen3,完全由你掌控。'
: 'Just drop in a script. Works with any LLM provider—OpenAI, Anthropic, or your own models.'}
</p>
</article>
{/* Feature 3 */}
<article
className="group p-8 bg-linear-to-br from-orange-100 to-red-100 dark:from-gray-700 dark:to-gray-800 rounded-2xl shadow-lg hover:shadow-xl transition-all duration-300 border border-gray-100 dark:border-gray-700"
role="listitem"
>
<div
className="w-14 h-14 bg-linear-to-br from-purple-500 to-purple-600 rounded-xl flex items-center justify-center mb-6 group-hover:scale-110 group-hover:rotate-3 transition-all duration-300 shadow-lg"
aria-hidden="true"
>
<MessageSquare className="w-7 h-7 text-white" strokeWidth={2.5} />
</div>
<h3 className="text-xl font-bold mb-4 text-gray-900 dark:text-white">
{isZh ? '普惠智能交互' : 'Natural Language UI'}
</h3>
<p className="text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '为复杂 B端系统、管理后台提供自然语言入口。让每个用户都能轻松上手。'
: 'Transform complex admin panels into chat interfaces. Make powerful tools accessible to everyone, not just experts.'}
</p>
</article>
{/* Feature 4 */}
<article
className="group p-8 bg-linear-to-br from-green-100 to-blue-100 dark:from-gray-700 dark:to-gray-800 rounded-2xl shadow-lg hover:shadow-xl transition-all duration-300 border border-gray-100 dark:border-gray-700"
role="listitem"
>
<div
className="w-14 h-14 bg-linear-to-br from-orange-500 to-orange-600 rounded-xl flex items-center justify-center mb-6 group-hover:scale-110 group-hover:rotate-3 transition-all duration-300 shadow-lg"
aria-hidden="true"
>
<Shield className="w-7 h-7 text-white" strokeWidth={2.5} />
</div>
<h3 className="text-xl font-bold mb-4 text-gray-900 dark:text-white">
{isZh ? '安全可控集成' : 'Secure by Design'}
</h3>
<p className="text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '支持操作黑白名单、数据脱敏保护。注入自定义知识库,让 AI 按你的规则工作。'
: 'Control what AI can access with allowlists, data masking, and custom knowledge injection. Your rules, your data.'}
</p>
</article>
</div>
</div>
</section>
{/* Use Cases Section */}
<section className="px-6 py-20" aria-labelledby="use-cases-heading">
<div className="max-w-7xl mx-auto">
<div className="text-center mb-16">
<SparklesText
className="text-4xl lg:text-5xl mb-6"
colors={{ first: '#3b82f6', second: '#8b5cf6' }}
>
{isZh ? '应用场景' : 'Where It Shines'}
</SparklesText>
<p className="text-xl text-gray-600 dark:text-gray-300 max-w-3xl mx-auto">
{isZh
? '从简单的表单填写到复杂的业务流程,AI 都能理解并执行'
: 'From simple forms to complex workflows, AI understands and executes'}
</p>
</div>
<div className="grid lg:grid-cols-2 gap-12" role="list">
{/* Use Case 1 */}
<div className="group bg-linear-to-br from-blue-100 to-purple-100 dark:from-gray-700 dark:to-gray-800 p-8 rounded-2xl hover:shadow-xl transition-all duration-300">
<div className="flex items-start space-x-4">
<div className="w-12 h-12 bg-linear-to-br from-blue-500 to-purple-500 rounded-xl flex items-center justify-center shrink-0 group-hover:scale-110 transition-transform duration-300 shadow-md">
<Bot className="w-6 h-6 text-white" strokeWidth={2.5} />
</div>
<div>
<h3 className="text-xl font-bold mb-2 text-gray-900 dark:text-white">
{isZh ? '对接答疑机器人' : 'Supercharge Support Bots'}
</h3>
<p className="text-gray-600 dark:text-gray-300">
{isZh
? '把你的答疑助手变成全能Agent。客服机器人不再只说「请先点击设置按钮然后点击...」,而是直接帮用户现场操作。'
: 'Stop telling users where to click—let AI do it for them. Turn your chatbot from a guide into an operator that actually completes tasks.'}
</p>
</div>
</div>
</div>
{/* Use Case 2 */}
<div className="group bg-linear-to-br from-green-100 to-blue-100 dark:from-gray-700 dark:to-gray-800 p-8 rounded-2xl hover:shadow-xl transition-all duration-300">
<div className="flex items-start space-x-4">
<div className="w-12 h-12 bg-linear-to-br from-green-500 to-blue-500 rounded-xl flex items-center justify-center shrink-0 group-hover:scale-110 transition-transform duration-300 shadow-md">
<Sparkles className="w-6 h-6 text-white" strokeWidth={2.5} />
</div>
<div>
<h3 className="text-xl font-bold mb-2 text-gray-900 dark:text-white">
{isZh ? '交互升级/智能化改造' : 'Modernize Legacy Apps'}
</h3>
<p className="text-gray-600 dark:text-gray-300">
{isZh
? '一行代码,老应用变身Agent,产品专家帮用户操作复杂 B 端软件。降低人工支持成本,提高用户满意度。'
: 'Add AI superpowers to old software without rebuilding. One script tag transforms complex enterprise tools into chat-driven interfaces.'}
</p>
</div>
</div>
</div>
{/* Use Case 3 */}
<div className="group bg-linear-to-br from-purple-100 to-pink-100 dark:from-gray-700 dark:to-gray-800 p-8 rounded-2xl hover:shadow-xl transition-all duration-300">
<div className="flex items-start space-x-4">
<div className="w-12 h-12 bg-linear-to-br from-purple-500 to-pink-500 rounded-xl flex items-center justify-center shrink-0 group-hover:scale-110 transition-transform duration-300 shadow-md">
<PlayCircle className="w-6 h-6 text-white fill-white/30" strokeWidth={2.5} />
</div>
<div>
<h3 className="text-xl font-bold mb-2 text-gray-900 dark:text-white">
{isZh ? '产品教学' : 'Interactive Walkthroughs'}
</h3>
<p className="text-gray-600 dark:text-gray-300">
{isZh
? '向用户演示交互过程,边做边教。例如让AI演示「如何提交报销申请」的完整操作流程。'
: "Show, don't tell. Let AI demonstrate workflows in real-time—perfect for onboarding or training new users on complex systems."}
</p>
</div>
</div>
</div>
{/* Use Case 4 */}
<div className="group bg-linear-to-br from-orange-100 to-red-100 dark:from-gray-700 dark:to-gray-800 p-8 rounded-2xl hover:shadow-xl transition-all duration-300">
<div className="flex items-start space-x-4">
<div className="w-12 h-12 bg-linear-to-br from-orange-500 to-red-500 rounded-xl flex items-center justify-center shrink-0 group-hover:scale-110 transition-transform duration-300 shadow-md">
<Users className="w-6 h-6 text-white" strokeWidth={2.5} />
</div>
<div>
<h3 className="text-xl font-bold mb-2 text-gray-900 dark:text-white">
{isZh ? '无障碍支持' : 'Accessibility First'}
</h3>
<p className="text-gray-600 dark:text-gray-300">
{isZh
? '为视障用户、老年用户提供自然语言交互,对接屏幕阅读器或语音助理,让软件人人可用。'
: 'Make web apps accessible through natural language. Perfect for screen readers, voice control, or users who find traditional interfaces challenging.'}
</p>
</div>
</div>
</div>
</div>
</div>
</section>
</main>
<Footer />
</div>
) )
} }
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { APIDivider, APIReference } from '@/components/ui/api-reference' import { APIDivider, APIReference } from '@/components/ui/api-reference'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
@@ -17,7 +18,7 @@ export default function CustomUIDocs() {
{/* Architecture */} {/* Architecture */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '架构' : 'Architecture'}</h2> <Heading id="architecture">{isZh ? '架构' : 'Architecture'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? 'PageAgent 由三个独立模块组成,可自由组合:' ? 'PageAgent 由三个独立模块组成,可自由组合:'
@@ -45,7 +46,7 @@ export default function CustomUIDocs() {
{/* Two Event Streams */} {/* Two Event Streams */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '两个事件流' : 'Two Event Streams'}</h2> <Heading id="two-event-streams">{isZh ? '两个事件流' : 'Two Event Streams'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? 'PageAgentCore 提供两种不同性质的事件流,方便 UI 渲染:' ? 'PageAgentCore 提供两种不同性质的事件流,方便 UI 渲染:'
@@ -120,7 +121,7 @@ export default function CustomUIDocs() {
{/* All Events */} {/* All Events */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '所有事件' : 'All Events'}</h2> <Heading id="all-events">{isZh ? '所有事件' : 'All Events'}</Heading>
<APIReference <APIReference
properties={[ properties={[
{ {
@@ -155,7 +156,7 @@ export default function CustomUIDocs() {
{/* HistoricalEvent Types */} {/* HistoricalEvent Types */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">HistoricalEvent</h2> <Heading id="historicalevent">HistoricalEvent</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh ? 'agent.history 数组中的事件类型:' : 'Event types in agent.history array:'} {isZh ? 'agent.history 数组中的事件类型:' : 'Event types in agent.history array:'}
</p> </p>
@@ -172,7 +173,7 @@ export default function CustomUIDocs() {
{/* AgentActivity Types */} {/* AgentActivity Types */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">AgentActivity</h2> <Heading id="agentactivity">AgentActivity</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh ? 'activity 事件的 detail 类型:' : 'The detail type of activity events:'} {isZh ? 'activity 事件的 detail 类型:' : 'The detail type of activity events:'}
</p> </p>
@@ -191,9 +192,7 @@ export default function CustomUIDocs() {
{/* React Hooks Example */} {/* React Hooks Example */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4"> <Heading id="using-react-hooks">{isZh ? '使用 React Hooks' : 'Using React Hooks'}</Heading>
{isZh ? '使用 React Hooks' : 'Using React Hooks'}
</h2>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh ? '监听事件并更新 React 状态:' : 'Listen to events and update React state:'} {isZh ? '监听事件并更新 React 状态:' : 'Listen to events and update React state:'}
</p> </p>
@@ -229,9 +228,9 @@ export default function CustomUIDocs() {
{/* Assembly Example */} {/* Assembly Example */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4"> <Heading id="assembling-core-controller-custom-ui">
{isZh ? '组装 Core + Controller + 自定义 UI' : 'Assembling Core + Controller + Custom UI'} {isZh ? '组装 Core + Controller + 自定义 UI' : 'Assembling Core + Controller + Custom UI'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '参考内置 PageAgent 的实现方式,用自定义 UI 替换 Panel' ? '参考内置 PageAgent 的实现方式,用自定义 UI 替换 Panel'
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { APIDivider, APIReference, TypeRef } from '@/components/ui/api-reference' import { APIDivider, APIReference, TypeRef } from '@/components/ui/api-reference'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
@@ -17,9 +18,9 @@ export default function PageAgentCoreDocs() {
{/* When to use */} {/* When to use */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4"> <Heading id="when-to-use-pageagentcore">
{isZh ? '何时使用 PageAgentCore' : 'When to Use PageAgentCore'} {isZh ? '何时使用 PageAgentCore' : 'When to Use PageAgentCore'}
</h2> </Heading>
<ul className="list-disc list-inside text-gray-600 dark:text-gray-400 space-y-2"> <ul className="list-disc list-inside text-gray-600 dark:text-gray-400 space-y-2">
<li>{isZh ? '需要自定义 UI 界面' : 'Need a custom UI interface'}</li> <li>{isZh ? '需要自定义 UI 界面' : 'Need a custom UI interface'}</li>
<li>{isZh ? '在自动化测试中无头运行' : 'Running headless in automated tests'}</li> <li>{isZh ? '在自动化测试中无头运行' : 'Running headless in automated tests'}</li>
@@ -38,7 +39,7 @@ export default function PageAgentCoreDocs() {
{/* Basic Usage */} {/* Basic Usage */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '基本用法' : 'Basic Usage'}</h2> <Heading id="basic-usage">{isZh ? '基本用法' : 'Basic Usage'}</Heading>
<CodeEditor <CodeEditor
language="typescript" language="typescript"
code={`import { PageAgentCore } from '@page-agent/core' code={`import { PageAgentCore } from '@page-agent/core'
@@ -76,7 +77,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* LLM Configuration */} {/* LLM Configuration */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">LLMConfig</h2> <Heading id="llmconfig">LLMConfig</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '配置与大语言模型的连接参数。支持 OpenAI 兼容的 API。' ? '配置与大语言模型的连接参数。支持 OpenAI 兼容的 API。'
@@ -133,7 +134,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Agent Configuration */} {/* Agent Configuration */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">AgentConfig</h2> <Heading id="agentconfig">AgentConfig</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '配置 Agent 的行为、生命周期钩子和扩展能力。' ? '配置 Agent 的行为、生命周期钩子和扩展能力。'
@@ -210,7 +211,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Lifecycle Hooks */} {/* Lifecycle Hooks */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '生命周期钩子' : 'Lifecycle Hooks'}</h2> <Heading id="lifecycle-hooks">{isZh ? '生命周期钩子' : 'Lifecycle Hooks'}</Heading>
<div className="bg-amber-50 dark:bg-amber-900/20 border border-amber-200 dark:border-amber-800 rounded-lg p-4 mb-4"> <div className="bg-amber-50 dark:bg-amber-900/20 border border-amber-200 dark:border-amber-800 rounded-lg p-4 mb-4">
<p className="text-amber-800 dark:text-amber-200 text-sm"> <p className="text-amber-800 dark:text-amber-200 text-sm">
<strong> {isZh ? '警告' : 'Warning'}:</strong>{' '} <strong> {isZh ? '警告' : 'Warning'}:</strong>{' '}
@@ -262,7 +263,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* PageController Configuration */} {/* PageController Configuration */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">PageControllerConfig</h2> <Heading id="pagecontrollerconfig">PageControllerConfig</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '配置 DOM 提取、元素交互和视觉反馈。' ? '配置 DOM 提取、元素交互和视觉反馈。'
@@ -321,7 +322,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Properties */} {/* Properties */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '属性' : 'Properties'}</h2> <Heading id="properties">{isZh ? '属性' : 'Properties'}</Heading>
<APIReference <APIReference
properties={[ properties={[
{ {
@@ -366,7 +367,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Methods */} {/* Methods */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '方法' : 'Methods'}</h2> <Heading id="methods">{isZh ? '方法' : 'Methods'}</Heading>
<APIReference <APIReference
properties={[ properties={[
{ {
@@ -389,7 +390,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Events */} {/* Events */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '事件' : 'Events'}</h2> <Heading id="events">{isZh ? '事件' : 'Events'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh ? ( {isZh ? (
<> <>
@@ -438,7 +439,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* ExecutionResult */} {/* ExecutionResult */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">ExecutionResult</h2> <Heading id="executionresult">ExecutionResult</Heading>
<CodeEditor <CodeEditor
language="typescript" language="typescript"
code={`interface ExecutionResult { code={`interface ExecutionResult {
@@ -454,7 +455,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* AgentActivity */} {/* AgentActivity */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">AgentActivity</h2> <Heading id="agentactivity">AgentActivity</Heading>
<CodeEditor <CodeEditor
language="typescript" language="typescript"
code={`type AgentActivity = code={`type AgentActivity =
@@ -470,7 +471,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Headless Usage */} {/* Headless Usage */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '无头模式' : 'Headless Mode'}</h2> <Heading id="headless-mode">{isZh ? '无头模式' : 'Headless Mode'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '在非 DOM 环境中,你必须实现自定义的 PageController(例如远程操作页面或 Puppeteer)。' ? '在非 DOM 环境中,你必须实现自定义的 PageController(例如远程操作页面或 Puppeteer)。'
@@ -1,6 +1,7 @@
import { Link } from 'wouter' import { Link } from 'wouter'
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { APIReference, TypeRef } from '@/components/ui/api-reference' import { APIReference, TypeRef } from '@/components/ui/api-reference'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
@@ -19,9 +20,9 @@ export default function PageAgentDocs() {
{/* When to use */} {/* When to use */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4"> <Heading id="when-to-use-pageagent">
{isZh ? '何时使用 PageAgent' : 'When to Use PageAgent'} {isZh ? '何时使用 PageAgent' : 'When to Use PageAgent'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '在大多数场景下,你应该使用 PageAgent。它提供了开箱即用的完整体验:' ? '在大多数场景下,你应该使用 PageAgent。它提供了开箱即用的完整体验:'
@@ -43,7 +44,7 @@ export default function PageAgentDocs() {
{/* Basic Usage */} {/* Basic Usage */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '基本用法' : 'Basic Usage'}</h2> <Heading id="basic-usage">{isZh ? '基本用法' : 'Basic Usage'}</Heading>
<CodeEditor <CodeEditor
language="typescript" language="typescript"
code={`import { PageAgent } from 'page-agent' code={`import { PageAgent } from 'page-agent'
@@ -69,7 +70,7 @@ console.log(result.history) // Full execution history`}
{/* Class Definition */} {/* Class Definition */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '类定义' : 'Class Definition'}</h2> <Heading id="class-definition">{isZh ? '类定义' : 'Class Definition'}</Heading>
<CodeEditor <CodeEditor
language="typescript" language="typescript"
code={`class PageAgent extends PageAgentCore { code={`class PageAgent extends PageAgentCore {
@@ -109,7 +110,7 @@ console.log(result.history) // Full execution history`}
{/* Configuration */} {/* Configuration */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '配置' : 'Configuration'}</h2> <Heading id="configuration">{isZh ? '配置' : 'Configuration'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? 'PageAgent 使用与 PageAgentCore 相同的配置接口。' ? 'PageAgent 使用与 PageAgentCore 相同的配置接口。'
@@ -144,7 +145,7 @@ console.log(result.history) // Full execution history`}
{/* Panel Property */} {/* Panel Property */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? 'Panel 属性' : 'Panel Property'}</h2> <Heading id="panel-property">{isZh ? 'Panel 属性' : 'Panel Property'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4"> <p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? 'PageAgent 自动创建一个 Panel 实例。你可以通过 panel 属性访问它来控制 UI' ? 'PageAgent 自动创建一个 Panel 实例。你可以通过 panel 属性访问它来控制 UI'
@@ -185,9 +186,9 @@ agent.panel.dispose()`}
{/* Comparison with PageAgentCore */} {/* Comparison with PageAgentCore */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4"> <Heading id="pageagent-vs-pageagentcore">
{isZh ? 'PageAgent vs PageAgentCore' : 'PageAgent vs PageAgentCore'} {isZh ? 'PageAgent vs PageAgentCore' : 'PageAgent vs PageAgentCore'}
</h2> </Heading>
<div className="overflow-hidden rounded-lg border border-gray-200 dark:border-gray-700"> <div className="overflow-hidden rounded-lg border border-gray-200 dark:border-gray-700">
<table className="w-full text-sm"> <table className="w-full text-sm">
<thead> <thead>
@@ -1,6 +1,7 @@
import { siChromewebstore, siGithub } from 'simple-icons' import { siChromewebstore, siGithub } from 'simple-icons'
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function ChromeExtension() { export default function ChromeExtension() {
@@ -22,7 +23,9 @@ export default function ChromeExtension() {
<div className="space-y-8 mt-8"> <div className="space-y-8 mt-8">
{/* Features */} {/* Features */}
<section> <section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '核心特性' : 'Key Features'}</h2> <Heading id="key-features" className="text-2xl font-bold mb-4">
{isZh ? '核心特性' : 'Key Features'}
</Heading>
<div className="grid md:grid-cols-3 gap-4"> <div className="grid md:grid-cols-3 gap-4">
<div className="p-4 bg-gray-50 dark:bg-gray-800 rounded-lg"> <div className="p-4 bg-gray-50 dark:bg-gray-800 rounded-lg">
<h3 className="font-semibold mb-2">🔓 {isZh ? '多页任务' : 'Multi-Page Tasks'}</h3> <h3 className="font-semibold mb-2">🔓 {isZh ? '多页任务' : 'Multi-Page Tasks'}</h3>
@@ -57,13 +60,15 @@ export default function ChromeExtension() {
{/* Install */} {/* Install */}
<section> <section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '获取扩展' : 'Get the Extension'}</h2> <Heading id="get-the-extension" className="text-2xl font-bold mb-4">
{isZh ? '获取扩展' : 'Get the Extension'}
</Heading>
<div className="flex flex-wrap gap-3"> <div className="flex flex-wrap gap-3">
<a <a
href={chromeWebStoreUrl} href={chromeWebStoreUrl}
target="_blank" target="_blank"
rel="noopener noreferrer" rel="noopener noreferrer"
className="inline-flex items-center gap-2 px-6 py-3 bg-blue-600 hover:bg-blue-700 text-white font-medium rounded-lg transition-colors" className="inline-flex items-center gap-2 px-6 py-3 bg-blue-600 hover:bg-blue-700 text-white! font-medium rounded-lg transition-colors"
> >
<svg className="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"> <svg className="w-5 h-5" fill="currentColor" viewBox="0 0 24 24">
<path d={siChromewebstore.path} /> <path d={siChromewebstore.path} />
@@ -74,7 +79,7 @@ export default function ChromeExtension() {
href={githubReleasesUrl} href={githubReleasesUrl}
target="_blank" target="_blank"
rel="noopener noreferrer" rel="noopener noreferrer"
className="inline-flex items-center gap-2 px-6 py-3 bg-gray-900 hover:bg-gray-800 dark:bg-gray-700 dark:hover:bg-gray-600 text-white font-medium rounded-lg transition-colors" className="inline-flex items-center gap-2 px-6 py-3 bg-gray-900 hover:bg-gray-800 dark:bg-gray-700 dark:hover:bg-gray-600 text-white! font-medium rounded-lg transition-colors"
> >
<svg className="w-5 h-5" fill="currentColor" viewBox="0 0 24 24"> <svg className="w-5 h-5" fill="currentColor" viewBox="0 0 24 24">
<path d={siGithub.path} /> <path d={siGithub.path} />
@@ -86,9 +91,9 @@ export default function ChromeExtension() {
{/* Relationship with PageAgent.js */} {/* Relationship with PageAgent.js */}
<section> <section>
<h2 className="text-2xl font-bold mb-4"> <Heading id="how-it-relates-to-page-agent-js" className="text-2xl font-bold mb-4">
{isZh ? '与 PageAgent.js 的关系' : 'How It Relates to PageAgent.js'} {isZh ? '与 PageAgent.js 的关系' : 'How It Relates to PageAgent.js'}
</h2> </Heading>
<div className="p-5 bg-gray-50 dark:bg-gray-800 rounded-lg space-y-3 text-gray-600 dark:text-gray-300"> <div className="p-5 bg-gray-50 dark:bg-gray-800 rounded-lg space-y-3 text-gray-600 dark:text-gray-300">
<p> <p>
{isZh {isZh
@@ -105,9 +110,9 @@ export default function ChromeExtension() {
{/* Third-party Integration */} {/* Third-party Integration */}
<section> <section>
<h2 className="text-2xl font-bold mb-4"> <Heading id="third-party-integration" className="text-2xl font-bold mb-4">
{isZh ? '第三方接入' : 'Third-Party Integration'} {isZh ? '第三方接入' : 'Third-Party Integration'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4"> <p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh {isZh
? '通过页面 JavaScript 调用 `window.PAGE_AGENT_EXT`,你的应用可以发起跨页面任务并控制浏览器行为。' ? '通过页面 JavaScript 调用 `window.PAGE_AGENT_EXT`,你的应用可以发起跨页面任务并控制浏览器行为。'
@@ -145,7 +150,9 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
{/* API Reference */} {/* API Reference */}
<section> <section>
<h2 className="text-2xl font-bold mb-4">{isZh ? 'API 参考' : 'API Reference'}</h2> <Heading id="api-reference" className="text-2xl font-bold mb-4">
{isZh ? 'API 参考' : 'API Reference'}
</Heading>
{/* AI Assistant Instructions */} {/* AI Assistant Instructions */}
<section className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg"> <section className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
@@ -164,23 +171,15 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
rel="noopener noreferrer" rel="noopener noreferrer"
className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline" className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline"
> >
📄 {isZh ? '英文版 API 文档' : 'API Documentation (English)'} 📄 {isZh ? 'API 文档' : 'API Documentation'}
</a>
<a
href="https://github.com/alibaba/page-agent/blob/main/packages/extension/docs/extension_api_zh.md"
target="_blank"
rel="noopener noreferrer"
className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline"
>
📄 {isZh ? '中文版 API 文档' : 'API Documentation (Chinese)'}
</a> </a>
</div> </div>
</section> </section>
{/* TypeScript Declaration */} {/* TypeScript Declaration */}
<h2 className="text-2xl font-bold mb-4"> <Heading id="typescript-declaration" className="text-2xl font-bold mb-4">
{isZh ? 'TypeScript 类型声明' : 'TypeScript Declaration'} {isZh ? 'TypeScript 类型声明' : 'TypeScript Declaration'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4"> <p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh {isZh
? '推荐把 `execute` 的类型声明加入你的项目,获得完整类型提示。' ? '推荐把 `execute` 的类型声明加入你的项目,获得完整类型提示。'
@@ -312,11 +311,15 @@ window.PAGE_AGENT_EXT.stop()`
{/* Integration Guide */} {/* Integration Guide */}
<section> <section>
<h2 className="text-2xl font-bold mb-4"> <Heading
id="integrate-multipageagent-into-your-extension"
className="text-2xl font-bold mb-4"
>
{isZh {isZh
? '将 MultiPageAgent 集成你自己的插件' ? '将 MultiPageAgent 集成你自己的插件'
: 'Integrate MultiPageAgent into Your Extension'} : 'Integrate MultiPageAgent into Your Extension'}
</h2> </Heading>
<p>@TODO</p>
<p className="text-gray-600 dark:text-gray-300 mb-4"> <p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh {isZh
? '建议先阅读扩展 API 文档,再参考 background entry implementation。' ? '建议先阅读扩展 API 文档,再参考 background entry implementation。'
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function Instructions() { export default function Instructions() {
@@ -16,9 +17,9 @@ export default function Instructions() {
{/* System Instructions */} {/* System Instructions */}
<section className="mb-12"> <section className="mb-12">
<h2 className="text-3xl font-bold mb-6"> <Heading id="system-instructions" className="text-3xl font-bold mb-6">
{isZh ? '系统级指导 (System Instructions)' : 'System Instructions'} {isZh ? '系统级指导 (System Instructions)' : 'System Instructions'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-300 mb-6"> <p className="text-gray-600 dark:text-gray-300 mb-6">
{isZh {isZh
@@ -46,9 +47,9 @@ Guidelines:
{/* Page Instructions */} {/* Page Instructions */}
<section className="mb-12"> <section className="mb-12">
<h2 className="text-3xl font-bold mb-6"> <Heading id="page-instructions" className="text-3xl font-bold mb-6">
{isZh ? '页面级指导 (Page Instructions)' : 'Page Instructions'} {isZh ? '页面级指导 (Page Instructions)' : 'Page Instructions'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-300 mb-6"> <p className="text-gray-600 dark:text-gray-300 mb-6">
{isZh {isZh
@@ -90,7 +91,9 @@ This is the product listing page.
{/* How It Works */} {/* How It Works */}
<section className="mb-12"> <section className="mb-12">
<h2 className="text-3xl font-bold mb-6">{isZh ? '工作原理' : 'How It Works'}</h2> <Heading id="how-it-works" className="text-3xl font-bold mb-6">
{isZh ? '工作原理' : 'How It Works'}
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4"> <p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh {isZh
@@ -1,5 +1,6 @@
import BetaNotice from '@/components/BetaNotice' import BetaNotice from '@/components/BetaNotice'
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function CustomTools() { export default function CustomTools() {
@@ -17,7 +18,9 @@ export default function CustomTools() {
<div className="space-y-8"> <div className="space-y-8">
<section> <section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '工具注册' : 'Tool Registration'}</h2> <Heading id="tool-registration" className="text-2xl font-bold mb-4">
{isZh ? '工具注册' : 'Tool Registration'}
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4"> <p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh {isZh
? '每个自定义工具需要定义四个核心属性:name、description、input schema 和 execute 函数。' ? '每个自定义工具需要定义四个核心属性:name、description、input schema 和 execute 函数。'
@@ -55,7 +58,9 @@ const pageAgent = new PageAgent({customTools})
</section> </section>
<section> <section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '页面过滤器' : 'Page Filter'}</h2> <Heading id="page-filter" className="text-2xl font-bold mb-4">
{isZh ? '页面过滤器' : 'Page Filter'}
</Heading>
<BetaNotice /> <BetaNotice />
@@ -89,7 +94,9 @@ const pageAgent = new PageAgent({customTools})
</section> </section>
<section> <section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '最佳实践' : 'Best Practices'}</h2> <Heading id="best-practices" className="text-2xl font-bold mb-4">
{isZh ? '最佳实践' : 'Best Practices'}
</Heading>
<div className="space-y-4"> <div className="space-y-4">
<div className="p-4 bg-yellow-50 dark:bg-yellow-900/20 rounded-lg"> <div className="p-4 bg-yellow-50 dark:bg-yellow-900/20 rounded-lg">
<h3 className="text-lg font-semibold text-yellow-900 dark:text-yellow-300 mb-2"> <h3 className="text-lg font-semibold text-yellow-900 dark:text-yellow-300 mb-2">
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function DataMasking() { export default function DataMasking() {
@@ -15,7 +16,9 @@ export default function DataMasking() {
</p> </p>
<section className="mb-12"> <section className="mb-12">
<h2 className="text-3xl font-bold mb-6">{isZh ? '接口定义' : 'API Definition'}</h2> <Heading id="api-definition" className="text-3xl font-bold mb-6">
{isZh ? '接口定义' : 'API Definition'}
</Heading>
<CodeEditor <CodeEditor
className="mb-6" className="mb-6"
@@ -30,9 +33,9 @@ export default function DataMasking() {
</section> </section>
<section className="mb-12"> <section className="mb-12">
<h2 className="text-3xl font-bold mb-6"> <Heading id="common-masking-patterns" className="text-3xl font-bold mb-6">
{isZh ? '常用脱敏规则' : 'Common Masking Patterns'} {isZh ? '常用脱敏规则' : 'Common Masking Patterns'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-300 mb-6"> <p className="text-gray-600 dark:text-gray-300 mb-6">
{isZh {isZh
@@ -1,6 +1,7 @@
import { Fragment } from 'react' import { Fragment } from 'react'
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
const BASELINE = new Set([ const BASELINE = new Set([
@@ -8,15 +9,22 @@ const BASELINE = new Set([
'claude-haiku-4.5', 'claude-haiku-4.5',
'gemini-3-flash', 'gemini-3-flash',
'deepseek-3.2', 'deepseek-3.2',
'qwen3-coder-next', 'qwen3.5-plus',
]) ])
// Models grouped by brand, newest first // Models grouped by brand, newest first
const MODEL_GROUPS: Record<string, string[]> = { 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'], OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'],
Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'], Qwen: [
Qwen: ['qwen3-coder-next', 'qwen-3-max', 'qwen-3-plus', 'qwen3:14b (ollama)'], 'qwen3.5-plus',
'qwen3.5-flash',
'qwen3-coder-next',
'qwen-3-max',
'qwen-3-plus',
'qwen3:14b (ollama)',
],
DeepSeek: ['deepseek-3.2'], DeepSeek: ['deepseek-3.2'],
Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'],
Anthropic: [ Anthropic: [
'claude-opus-4.6', 'claude-opus-4.6',
'claude-opus-4.5', 'claude-opus-4.5',
@@ -26,7 +34,7 @@ const MODEL_GROUPS: Record<string, string[]> = {
], ],
xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'], xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
MoonshotAI: ['kimi-k2.5'], MoonshotAI: ['kimi-k2.5'],
'Z.AI': ['glm-4.7'], 'Z.AI': ['glm-5', 'glm-4.7'],
} }
const ModelBadge = ({ model, baseline }: { model: string; baseline?: boolean }) => ( const ModelBadge = ({ model, baseline }: { model: string; baseline?: boolean }) => (
@@ -56,7 +64,9 @@ export default function Models() {
{/* Models Section */} {/* Models Section */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-3">{isZh ? '已测试模型' : 'Tested Models'}</h2> <Heading id="tested-models" className="text-2xl font-semibold mb-3">
{isZh ? '已测试模型' : 'Tested Models'}
</Heading>
<p className="text-sm text-gray-600 dark:text-gray-400 mb-4"> <p className="text-sm text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '推荐使用 ToolCall 能力强的轻量级模型。' ? '推荐使用 ToolCall 能力强的轻量级模型。'
@@ -134,13 +144,13 @@ export default function Models() {
{/* Configuration Section */} {/* Configuration Section */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '配置方式' : 'Configuration'}</h2> <Heading id="configuration">{isZh ? '配置方式' : 'Configuration'}</Heading>
<CodeEditor <CodeEditor
code={`// OpenAI-compatible services (e.g., Alibaba Bailian) code={`// OpenAI-compatible services (e.g., Alibaba Bailian)
const pageAgent = new PageAgent({ const pageAgent = new PageAgent({
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1', baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'your-api-key', apiKey: 'your-api-key',
model: 'qwen-plus' model: 'qwen3.5-plus'
}); });
// Self-hosted models (e.g., Ollama) // Self-hosted models (e.g., Ollama)
@@ -150,19 +160,63 @@ const pageAgent = new PageAgent({
model: 'qwen3:14b' model: 'qwen3:14b'
}); });
// Free testing endpoint
// Note: Rate-limited, content-filtered, subject to change. Replace with your own.
// Note: Uses official DeepSeek-chat (3.2). See DeepSeek website for terms & privacy.
const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
const DEMO_BASE_URL = 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
`} `}
/> />
</section> </section>
{/* Free Testing API Section */}
<section className="mb-10">
<Heading id="free-testing-api">{isZh ? '免费测试接口' : 'Free Testing API'}</Heading>
<p className="text-sm text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '以下免费测试接口仅供 PageAgent.js 和 PageAgent Extension 的技术评估使用。有速率限制,可能随时变更。请勿用于生产环境。'
: 'The following free testing endpoints are provided for technical evaluation of PageAgent.js and PageAgent Extension only. Rate-limited, subject to change. Not for production use.'}
</p>
<div className="bg-gray-50 dark:bg-gray-900/30 rounded-lg p-5 border border-gray-200 dark:border-gray-800">
<h3 className="font-semibold text-gray-900 dark:text-gray-100 mb-2">
Qwen (Alibaba Cloud China)
</h3>
<p className="text-xs text-gray-500 dark:text-gray-400 mb-3">
{isZh
? '通过阿里云函数计算(中国大陆)转发至百炼 Qwen 模型'
: 'Proxied via Alibaba Cloud FC (Mainland China) to BaiLian Qwen models'}
{' · '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="text-blue-500 hover:underline"
>
{isZh ? '使用条款' : 'Terms of Use'}
</a>
</p>
<CodeEditor
code={`# qwen3.5-plus (default for demos) or qwen3.5-flash (lighter)
LLM_BASE_URL="https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run"
LLM_MODEL_NAME="qwen3.5-plus"
LLM_API_KEY="NA"`}
/>
</div>
<div className="mt-4 p-4 bg-amber-50 dark:bg-amber-950/20 rounded-lg border border-amber-200 dark:border-amber-800">
<p className="text-xs text-gray-600 dark:text-gray-400">
{isZh
? '⚠️ 仅供技术评估和研发用途,禁止用于生产环境。数据通过中国大陆服务器处理。请勿输入任何个人身份信息或敏感数据。使用即表示您同意'
: '⚠️ Strictly for technical evaluation and R&D only. Data is processed via servers in Mainland China. Do not input any PII or sensitive data. By using this API you agree to the'}{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="text-blue-500 hover:underline"
>
{isZh ? '使用条款' : 'Terms of Use'}
</a>
</p>
</div>
</section>
{/* Ollama Section */} {/* Ollama Section */}
<section className="mb-10"> <section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">Ollama</h2> <Heading id="ollama">Ollama</Heading>
<p className="text-sm text-gray-600 dark:text-gray-400 mb-4"> <p className="text-sm text-gray-600 dark:text-gray-400 mb-4">
{isZh {isZh
? '已在 Ollama 0.15 + qwen3:14b (RTX3090 24GB) 上测试通过。' ? '已在 Ollama 0.15 + qwen3:14b (RTX3090 24GB) 上测试通过。'
+3 -7
View File
@@ -1,7 +1,6 @@
import { Suspense } from 'react' import { Suspense } from 'react'
import { Route, Switch } from 'wouter' import { Route, Switch } from 'wouter'
import Header from '../../components/Header'
import DocsLayout from './Layout' import DocsLayout from './Layout'
import CustomUIDocs from './advanced/custom-ui/page' import CustomUIDocs from './advanced/custom-ui/page'
import PageAgentCoreDocs from './advanced/page-agent-core/page' import PageAgentCoreDocs from './advanced/page-agent-core/page'
@@ -24,12 +23,9 @@ import Troubleshooting from './introduction/troubleshooting/page'
function DocsPage({ children }: { children: React.ReactNode }) { function DocsPage({ children }: { children: React.ReactNode }) {
return ( return (
<div className="min-h-screen bg-white dark:bg-gray-900"> <DocsLayout>
<Header /> <Suspense>{children}</Suspense>
<DocsLayout> </DocsLayout>
<Suspense>{children}</Suspense>
</DocsLayout>
</div>
) )
} }
@@ -1,4 +1,5 @@
import BetaNotice from '@/components/BetaNotice' import BetaNotice from '@/components/BetaNotice'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function SecurityPermissions() { export default function SecurityPermissions() {
@@ -18,9 +19,9 @@ export default function SecurityPermissions() {
<div className="space-y-6"> <div className="space-y-6">
<section> <section>
<h2 className="text-2xl font-bold mb-3"> <Heading id="element-interaction-allowlist-blocklist" className="text-2xl font-bold mb-3">
{isZh ? '元素操作黑白名单' : 'Element Interaction Allowlist/Blocklist'} {isZh ? '元素操作黑白名单' : 'Element Interaction Allowlist/Blocklist'}
</h2> </Heading>
<div className="space-y-3"> <div className="space-y-3">
<div className="p-4 bg-red-50 dark:bg-red-900/20 rounded-lg"> <div className="p-4 bg-red-50 dark:bg-red-900/20 rounded-lg">
<h3 className="text-lg font-semibold text-red-900 dark:text-red-300"> <h3 className="text-lg font-semibold text-red-900 dark:text-red-300">
@@ -46,9 +47,9 @@ export default function SecurityPermissions() {
</section> </section>
<section> <section>
<h2 className="text-2xl font-bold mb-3"> <Heading id="instruction-safety-constraints" className="text-2xl font-bold mb-3">
{isZh ? 'Instruction 安全约束' : 'Instruction Safety Constraints'} {isZh ? 'Instruction 安全约束' : 'Instruction Safety Constraints'}
</h2> </Heading>
<div className="p-4 bg-yellow-50 dark:bg-yellow-900/20 rounded-lg"> <div className="p-4 bg-yellow-50 dark:bg-yellow-900/20 rounded-lg">
<h3 className="text-lg font-semibold mb-2 text-yellow-900 dark:text-yellow-300"> <h3 className="text-lg font-semibold mb-2 text-yellow-900 dark:text-yellow-300">
{isZh ? '高危操作控制' : 'High-Risk Operation Control'} {isZh ? '高危操作控制' : 'High-Risk Operation Control'}
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function ThirdPartyAgentPage() { export default function ThirdPartyAgentPage() {
@@ -26,7 +27,9 @@ export default function ThirdPartyAgentPage() {
</p> </p>
</div> </div>
<h2 className="text-2xl font-bold mb-4">{isZh ? '集成方式' : 'Integration Method'}</h2> <Heading id="integration-method" className="text-2xl font-bold mb-4">
{isZh ? '集成方式' : 'Integration Method'}
</Heading>
<div className="space-y-4 mb-6"> <div className="space-y-4 mb-6">
<div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg"> <div className="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
@@ -57,7 +60,9 @@ const pageAgentTool = {
</div> </div>
</div> </div>
<h2 className="text-2xl font-bold mb-4">{isZh ? '应用场景' : 'Use Cases'}</h2> <Heading id="use-cases" className="text-2xl font-bold mb-4">
{isZh ? '应用场景' : 'Use Cases'}
</Heading>
<div className="grid md:grid-cols-2 gap-4 mb-6"> <div className="grid md:grid-cols-2 gap-4 mb-6">
<div className="bg-linear-to-br from-blue-50 to-purple-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg"> <div className="bg-linear-to-br from-blue-50 to-purple-50 dark:from-gray-800 dark:to-gray-700 p-4 rounded-lg">
<h4 className="font-semibold mb-2 text-gray-900 dark:text-white"> <h4 className="font-semibold mb-2 text-gray-900 dark:text-white">
@@ -1,3 +1,6 @@
import { Link } from 'wouter'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function LimitationsPage() { export default function LimitationsPage() {
@@ -11,184 +14,146 @@ export default function LimitationsPage() {
</h1> </h1>
<p className="text-xl text-gray-600 dark:text-gray-300"> <p className="text-xl text-gray-600 dark:text-gray-300">
{isZh {isZh
? '了解 page-agent 当前的功能边界和技术限制' ? 'Page Agent 基于 DOM 理解网页并执行操作。这决定了它的能力边界。'
: "Understand page-agent's current capabilities and technical constraints"} : 'Page Agent understands web pages via DOM and performs actions accordingly. This defines its capability boundary.'}
</p> </p>
</div> </div>
<div className="prose prose-lg dark:prose-invert max-w-none"> <div className="prose prose-lg dark:prose-invert max-w-none">
<h2 className="text-2xl font-bold mb-3"> {/* PageAgent.js vs PageAgentExt */}
{isZh ? '页面支持限制' : 'Page Support Limitations'} <Heading id="pageagent-js-vs-pageagentext" className="text-2xl font-bold mb-3">
</h2> {isZh ? 'PageAgent.js vs PageAgentExt' : 'PageAgent.js vs PageAgentExt'}
<div className="bg-blue-50 dark:bg-blue-900/20 border-l-4 border-blue-400 p-4 mb-6"> </Heading>
<h3 className="font-semibold text-blue-800 dark:text-blue-200 mb-2"> <p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh ? '单页应用限制' : 'Single Page Application Limits'} {isZh
</h3> ? 'PageAgent.js 是核心库,运行在页面内。PageAgentExt 是可选的浏览器扩展,提供额外的浏览器级控制能力。'
<ul className="text-blue-700 dark:text-blue-300 space-y-2"> : 'PageAgent.js is the core library running inside a page. PageAgentExt is an optional browser extension that adds browser-level control.'}
<li> </p>
{isZh <div className="overflow-x-auto mb-6">
? '• 仅支持单页应用(SPA):目前只能在单个页面内进行操作' <table className="w-full text-sm border-collapse">
: '• SPA only: Currently operates within a single page'} <thead>
</li> <tr className="border-b border-gray-200 dark:border-gray-700">
<li> <th className="text-left py-3 pr-4"></th>
{isZh <th className="text-left py-3 px-4 font-semibold">PageAgent.js</th>
? '• 多页接力功能正在设计中:暂时无法跨页面执行连续任务' <th className="text-left py-3 pl-4 font-semibold">
: '• Multi-page relay in design: Cannot execute continuous tasks across pages yet'} PageAgentExt{' '}
</li> <Link
<li> href="/features/chrome-extension"
{isZh className="text-xs font-normal text-blue-600 dark:text-blue-400 hover:underline"
? '• 无法操作未接入该能力的网站:需要目标网站主动集成 page-agent' >
: '• Requires integration: Cannot operate on sites without page-agent'} {isZh ? '了解更多' : 'learn more'}
</li> </Link>
</ul> </th>
</tr>
</thead>
<tbody className="text-gray-600 dark:text-gray-300">
<tr className="border-b border-gray-100 dark:border-gray-800">
<td className="py-3 pr-4 font-medium text-gray-900 dark:text-white">
{isZh ? '接入方式' : 'Integration'}
</td>
<td className="py-3 px-4">
{isZh ? '网站开发者主动集成' : 'Site developer integrates the library'}
</td>
<td className="py-3 pl-4">
{isZh ? '用户安装浏览器扩展' : 'User installs a browser extension'}
</td>
</tr>
<tr className="border-b border-gray-100 dark:border-gray-800">
<td className="py-3 pr-4 font-medium text-gray-900 dark:text-white">
{isZh ? '可操作范围' : 'Scope'}
</td>
<td className="py-3 px-4">
{isZh ? '当前页面(为 SPA 设计)' : 'Current page (designed for SPAs)'}
</td>
<td className="py-3 pl-4">
{isZh ? '任意网页、多标签页' : 'Any web page, multi-tab'}
</td>
</tr>
<tr>
<td className="py-3 pr-4 font-medium text-gray-900 dark:text-white">
{isZh ? '额外能力' : 'Extra capabilities'}
</td>
<td className="py-3 px-4"></td>
<td className="py-3 pl-4">
{isZh ? '新建/切换/关闭标签页' : 'Open / switch / close tabs'}
</td>
</tr>
</tbody>
</table>
</div> </div>
<h2 className="text-2xl font-bold mb-3"> {/* Interaction Limitations */}
{isZh ? '交互行为限制' : 'Interaction Limitations'} <Heading id="interaction-capabilities" className="text-2xl font-bold mb-3">
</h2> {isZh ? '交互能力' : 'Interaction Capabilities'}
</Heading>
<div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6 mb-6"> <div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6 mb-6">
<h3 className="font-semibold mb-4">{isZh ? '支持的操作' : 'Supported Operations'}</h3> <div className="grid md:grid-cols-2 gap-6">
<div className="grid md:grid-cols-2 gap-4 mb-6">
<div className="space-y-2">
<div className="flex items-center text-green-600 dark:text-green-400">
<span className="mr-2"></span>
<span>{isZh ? '点击操作' : 'Click'}</span>
</div>
<div className="flex items-center text-green-600 dark:text-green-400">
<span className="mr-2"></span>
<span>{isZh ? '文本输入' : 'Text input'}</span>
</div>
<div className="flex items-center text-green-600 dark:text-green-400">
<span className="mr-2"></span>
<span>{isZh ? '页面滚动' : 'Scroll'}</span>
</div>
<div className="flex items-center text-green-600 dark:text-green-400">
<span className="mr-2"></span>
<span>{isZh ? '表单提交' : 'Form submit'}</span>
</div>
</div>
<div className="space-y-2">
<div className="flex items-center text-green-600 dark:text-green-400">
<span className="mr-2"></span>
<span>{isZh ? '选择操作' : 'Select'}</span>
</div>
<div className="flex items-center text-green-600 dark:text-green-400">
<span className="mr-2"></span>
<span>{isZh ? '焦点切换' : 'Focus'}</span>
</div>
</div>
</div>
<h3 className="font-semibold mb-4">{isZh ? '不支持的操作' : 'Unsupported Operations'}</h3>
<div className="grid md:grid-cols-2 gap-4">
<div className="space-y-2">
<div className="flex items-center text-red-600 dark:text-red-400">
<span className="mr-2"></span>
<span>{isZh ? '鼠标悬停(hover' : 'Mouse hover'}</span>
</div>
<div className="flex items-center text-red-600 dark:text-red-400">
<span className="mr-2"></span>
<span>{isZh ? '拖拽操作' : 'Drag & drop'}</span>
</div>
<div className="flex items-center text-red-600 dark:text-red-400">
<span className="mr-2"></span>
<span>{isZh ? '右键菜单' : 'Right-click menu'}</span>
</div>
</div>
<div className="space-y-2">
<div className="flex items-center text-red-600 dark:text-red-400">
<span className="mr-2"></span>
<span>{isZh ? '图形绘制' : 'Drawing'}</span>
</div>
<div className="flex items-center text-red-600 dark:text-red-400">
<span className="mr-2"></span>
<span>{isZh ? '键盘快捷键' : 'Keyboard shortcuts'}</span>
</div>
<div className="flex items-center text-red-600 dark:text-red-400">
<span className="mr-2"></span>
<span>{isZh ? '基于点击区域或鼠标位置的控制' : 'Position-based control'}</span>
</div>
</div>
</div>
</div>
<h2 className="text-2xl font-bold mb-3">
{isZh ? '网页理解限制' : 'Understanding Limitations'}
</h2>
<div className="bg-red-50 dark:bg-red-900/20 border-l-4 border-red-400 p-4 mb-6">
<h3 className="font-semibold text-red-800 dark:text-red-200 mb-2">
{isZh ? '无视觉能力' : 'No Visual Recognition'}
</h3>
<p className="text-red-700 dark:text-red-300 mb-3">
{isZh
? 'page-agent 基于 DOM 结构进行理解和操作,没有视觉识别能力,无法理解以下内容:'
: 'page-agent operates based on DOM structure with no visual recognition. Cannot understand:'}
</p>
<ul className="text-red-700 dark:text-red-300 space-y-1">
<li>
{isZh
? '• 图片内容:无法识别图片中的文字、图标或视觉元素'
: '• Image content: Cannot recognize text, icons, or visual elements in images'}
</li>
<li>
{isZh
? '• Canvas 画布:无法理解 Canvas 中绘制的图形和内容'
: '• Canvas: Cannot understand graphics drawn on Canvas'}
</li>
<li>
{isZh
? '• WebGL 3D 内容:无法操作 3D 场景中的元素'
: '• WebGL 3D: Cannot operate elements in 3D scenes'}
</li>
<li>
{isZh
? '• SVG 图形:无法理解 SVG 中的视觉内容和路径'
: '• SVG graphics: Cannot understand visual content and paths in SVG'}
</li>
</ul>
</div>
<h2 className="text-2xl font-bold mb-3">
{isZh ? '被操作网站要求' : 'Website Requirements'}
</h2>
<div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6 mb-6">
<div className="space-y-4">
<div> <div>
<h3 className="font-semibold mb-2"> <h3 className="font-semibold mb-3 text-green-700 dark:text-green-400">
{isZh ? '语义化和易用性' : 'Semantic & Usability'} {isZh ? '支持' : 'Supported'}
</h3> </h3>
<p className="text-gray-600 dark:text-gray-300"> <ul className="space-y-1.5 text-sm">
{isZh {[
? '所有操作都基于 DOM 元素的语义化标签和属性。如果页面结构不够语义化,或者没有任何 accessibility 特性,可能影响 AI 的理解准确性。' isZh ? '点击、文本输入、选择' : 'Click, text input, select',
: 'All operations rely on semantic tags and attributes. Poor semantic structure or lack of accessibility features may affect AI understanding accuracy.'} isZh ? '页面滚动(垂直 / 水平)' : 'Scroll (vertical / horizontal)',
</p> isZh ? '表单提交、焦点切换' : 'Form submit, focus',
isZh ? '执行 JavaScript(可选)' : 'Execute JavaScript (opt-in)',
].map((text) => (
<li key={text} className="flex items-center text-gray-700 dark:text-gray-300">
<span className="mr-2 text-green-600 dark:text-green-400"></span>
{text}
</li>
))}
</ul>
</div> </div>
<div> <div>
<h3 className="font-semibold mb-2">{isZh ? 'UI/UX' : 'UI/UX'}</h3> <h3 className="font-semibold mb-3 text-red-700 dark:text-red-400">
<p className="text-gray-600 dark:text-gray-300"> {isZh ? '不支持' : 'Not supported'}
{isZh </h3>
? '反常识的交互规则、基于视觉的操作提示、复杂的鼠标交互、快速出现快速消失的元素等,都会影响 AI 的理解和操作。' <ul className="space-y-1.5 text-sm">
: 'Counter-intuitive interaction rules, visual-only operation hints, complex mouse interactions, or rapidly appearing/disappearing elements can affect AI understanding and operation.'} {[
</p> isZh ? '悬停、拖拽、右键菜单' : 'Hover, drag & drop, right-click',
</div> isZh ? '键盘快捷键' : 'Keyboard shortcuts',
<div> isZh ? '坐标定位操作' : 'Position-based control',
<h3 className="font-semibold mb-2">{isZh ? '环境要求' : 'Environment'}</h3> isZh ? '绘图操作' : 'Drawing',
<p className="text-gray-600 dark:text-gray-300">modern browser</p> ].map((text) => (
<li key={text} className="flex items-center text-gray-700 dark:text-gray-300">
<span className="mr-2 text-red-600 dark:text-red-400"></span>
{text}
</li>
))}
</ul>
</div> </div>
</div> </div>
</div> </div>
<h2>{isZh ? '未来规划' : 'Future Plans'}</h2> {/* Understanding Limitations */}
<div className="bg-green-50 dark:bg-green-900/20 border-l-4 border-green-400 p-4"> <Heading id="understanding" className="text-2xl font-bold mb-3">
<h3 className="font-semibold text-green-800 dark:text-green-200 mb-2"> {isZh ? '理解能力' : 'Understanding'}
{isZh ? '即将支持' : 'Coming Soon'} </Heading>
</h3> <div className="bg-amber-50 dark:bg-amber-900/20 border-l-4 border-amber-400 p-4 mb-6">
<ul className="text-green-700 dark:text-green-300 space-y-1"> <p className="text-amber-800 dark:text-amber-200 mb-2 font-medium">
<li>{isZh ? '• 多页面接力操作能力' : '• Multi-page relay capabilities'}</li> {isZh
<li>{isZh ? '• 更丰富的鼠标交互支持' : '• Richer mouse interaction support'}</li> ? 'Page Agent 不使用多模态模型,不截图,没有视觉能力。仅通过 DOM 结构理解页面。'
<li>{isZh ? '• 基础的视觉理解能力' : '• Basic visual understanding'}</li> : 'Page Agent does not use multimodal models, does not take screenshots, and has no visual capability. It reads pages through DOM structure only.'}
<li>{isZh ? '• 更智能的错误恢复机制' : '• Smarter error recovery'}</li> </p>
</ul> <p className="text-amber-700 dark:text-amber-300 text-sm">
{isZh
? '图片、Canvas、WebGL、SVG 等视觉内容无法被识别。页面的语义化程度和可访问性直接影响 AI 的理解准确性。'
: 'Images, Canvas, WebGL, SVG and other visual content cannot be recognized. Page semantic quality and accessibility directly affect AI accuracy.'}
</p>
</div>
{/* Website Quality */}
<Heading id="page-quality-matters" className="text-2xl font-bold mb-3">
{isZh ? '网页质量影响' : 'Page Quality Matters'}
</Heading>
<div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6">
<p className="text-gray-600 dark:text-gray-300 text-sm">
{isZh
? '反常识的交互逻辑、纯视觉的操作提示、快速出现消失的元素等都会降低自动化成功率。语义化的 HTML 和良好的可访问性会显著提升效果。'
: 'Counter-intuitive interactions, visual-only cues, and rapidly appearing/disappearing elements reduce automation success. Semantic HTML and good accessibility significantly improve results.'}
</p>
</div> </div>
</div> </div>
</div> </div>
@@ -1,3 +1,4 @@
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
export default function Overview() { export default function Overview() {
@@ -48,9 +49,9 @@ export default function Overview() {
</div> </div>
<section> <section>
<h2 className="text-2xl font-bold mb-4"> <Heading id="what-is-page-agent" className="text-2xl font-bold mb-4">
{isZh ? '什么是 page-agent' : 'What is page-agent?'} {isZh ? '什么是 page-agent' : 'What is page-agent?'}
</h2> </Heading>
<p className="text-gray-600 dark:text-gray-300 mb-8 leading-relaxed "> <p className="text-gray-600 dark:text-gray-300 mb-8 leading-relaxed ">
{isZh {isZh
@@ -60,7 +61,9 @@ export default function Overview() {
</section> </section>
<section> <section>
<h2 className="text-2xl font-bold mb-3">{isZh ? '核心特性' : 'Core Features'}</h2> <Heading id="core-features" className="text-2xl font-bold mb-3">
{isZh ? '核心特性' : 'Core Features'}
</Heading>
<div className="grid md:grid-cols-2 gap-4 mb-8" role="list"> <div className="grid md:grid-cols-2 gap-4 mb-8" role="list">
<div className="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg"> <div className="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg">
@@ -108,9 +111,9 @@ export default function Overview() {
</div> </div>
</div> </div>
<h2 className="text-2xl font-bold mb-4"> <Heading id="vs-browser-use" className="text-2xl font-bold mb-4">
{isZh ? '与 browser-use 的区别' : 'vs. browser-use'} {isZh ? '与 browser-use 的区别' : 'vs. browser-use'}
</h2> </Heading>
<div className="overflow-x-auto mb-8"> <div className="overflow-x-auto mb-8">
<table className="w-full border-collapse border border-gray-300 dark:border-gray-600"> <table className="w-full border-collapse border border-gray-300 dark:border-gray-600">
@@ -174,7 +177,9 @@ export default function Overview() {
</table> </table>
</div> </div>
<h2 className="text-2xl font-bold mb-4">{isZh ? '应用场景' : 'Use Cases'}</h2> <Heading id="use-cases" className="text-2xl font-bold mb-4">
{isZh ? '应用场景' : 'Use Cases'}
</Heading>
<ul className="space-y-4 mb-8"> <ul className="space-y-4 mb-8">
<li className="flex items-start space-x-3"> <li className="flex items-start space-x-3">
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { CDN_DEMO_CN_URL, CDN_DEMO_URL } from '@/constants' import { CDN_DEMO_CN_URL, CDN_DEMO_URL } from '@/constants'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
@@ -13,7 +14,9 @@ export default function QuickStart() {
{isZh ? '几分钟内完成 page-agent 的集成。' : 'Integrate page-agent in minutes.'} {isZh ? '几分钟内完成 page-agent 的集成。' : 'Integrate page-agent in minutes.'}
</p> </p>
<h2 className="text-2xl font-bold mb-3">{isZh ? '安装步骤' : 'Installation Steps'}</h2> <Heading id="installation-steps" className="text-2xl font-bold mb-3">
{isZh ? '安装步骤' : 'Installation Steps'}
</Heading>
<div className="space-y-4 mb-6"> <div className="space-y-4 mb-6">
{/* Demo CDN - One Line */} {/* Demo CDN - One Line */}
@@ -23,7 +26,32 @@ export default function QuickStart() {
</h3> </h3>
<div className="bg-yellow-50 dark:bg-yellow-900/20 p-2 rounded mb-3 text-sm"> <div className="bg-yellow-50 dark:bg-yellow-900/20 p-2 rounded mb-3 text-sm">
<span className="text-yellow-800 dark:text-yellow-200"> <span className="text-yellow-800 dark:text-yellow-200">
{isZh ? '仅用于技术评估' : 'For evaluation only'} {' '}
{isZh ? (
<>
Demo CDN 使 LLM API使
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="underline"
>
使
</a>
</>
) : (
<>
This demo CDN uses our free testing LLM API. By using it you agree to the{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="underline"
>
Terms of Use
</a>
</>
)}
</span> </span>
</div> </div>
<CodeEditor <CodeEditor
@@ -71,8 +99,8 @@ import { PageAgent } from 'page-agent'`}
</h3> </h3>
<CodeEditor <CodeEditor
code={`const agent = new PageAgent({ code={`const agent = new PageAgent({
model: 'deepseek-chat', model: 'qwen3.5-plus',
baseURL: 'https://api.deepseek.com', baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'YOUR_API_KEY', apiKey: 'YOUR_API_KEY',
language: '${isZh ? 'zh-CN' : 'en-US'}' language: '${isZh ? 'zh-CN' : 'en-US'}'
})`} })`}
@@ -2,6 +2,7 @@ import { useEffect, useRef, useState } from 'react'
import { Link } from 'wouter' import { Link } from 'wouter'
import CodeEditor from '@/components/CodeEditor' import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context' import { useLanguage } from '@/i18n/context'
// --------------------------------------------------------------------------- // ---------------------------------------------------------------------------
@@ -369,10 +370,13 @@ export default function TroubleshootingPage() {
{/* Main content */} {/* Main content */}
<div className="flex-1 min-w-0 space-y-12"> <div className="flex-1 min-w-0 space-y-12">
{SECTIONS.map((section) => ( {SECTIONS.map((section) => (
<section key={section.id} id={section.id} className="scroll-mt-24"> <section key={section.id} className="scroll-mt-24">
<h2 className="text-2xl font-bold mb-4 text-gray-900 dark:text-white"> <Heading
id={section.id}
className="text-2xl font-bold mb-4 text-gray-900 dark:text-white"
>
{isZh ? section.title.zh : section.title.en} {isZh ? section.title.zh : section.title.en}
</h2> </Heading>
{/* Symptom callout */} {/* Symptom callout */}
<div <div
@@ -0,0 +1,232 @@
import { Bot, Box, MessageSquare, Shield, Sparkles, Users } from 'lucide-react'
import { BlurFade } from '../../components/ui/blur-fade'
import { Highlighter } from '../../components/ui/highlighter'
import { MagicCard } from '../../components/ui/magic-card'
import { Particles } from '../../components/ui/particles'
import { useLanguage } from '../../i18n/context'
// Word-cloud style: each item has a position (%), size, opacity, and color for a scattered look
const LLM_CLOUD: {
name: string
color: string
x: number
y: number
size: number
opacity: number
}[] = [
{ name: 'OpenAI', color: '#10b981', x: 18, y: 22, size: 1.5, opacity: 1 },
{ name: 'Claude', color: '#f97316', x: 62, y: 15, size: 1.35, opacity: 0.95 },
{ name: 'Qwen', color: '#8b5cf6', x: 38, y: 50, size: 1.8, opacity: 0.9 },
{ name: 'Gemini', color: '#3b82f6', x: 68, y: 48, size: 1.2, opacity: 0.85 },
{ name: 'DeepSeek', color: '#06b6d4', x: 10, y: 65, size: 1.1, opacity: 0.8 },
{ name: 'Grok', color: '#f43f5e', x: 52, y: 78, size: 1.0, opacity: 0.75 },
{ name: 'Ollama', color: '#9ca3af', x: 82, y: 25, size: 1.1, opacity: 0.8 },
{ name: 'Kimi', color: '#14b8a6', x: 30, y: 82, size: 0.85, opacity: 0.6 },
{ name: 'GLM', color: '#f59e0b', x: 70, y: 72, size: 0.85, opacity: 0.55 },
{ name: 'LLaMA', color: '#60a5fa', x: 88, y: 70, size: 0.8, opacity: 0.45 },
]
const CARD_HEIGHT = 'h-72'
export default function FeaturesSection() {
const { isZh } = useLanguage()
return (
<section className="px-6 py-14" aria-labelledby="features-heading">
<div className="max-w-6xl mx-auto">
<div className="grid grid-cols-1 md:grid-cols-3 gap-4 auto-rows-[18rem]">
{/* Row 1: Zero Infrastructure (2col) + Privacy (1col) */}
<BlurFade inView className="col-span-1 md:col-span-2">
<MagicCard
className="h-full rounded-2xl"
gradientFrom="#3b82f6"
gradientTo="#06b6d4"
gradientColor="#3b82f6"
gradientOpacity={0.15}
>
<div className={`flex ${CARD_HEIGHT} flex-col`}>
<div className="flex-1 p-7 flex flex-col justify-center">
<div className="space-y-2.5 mb-5">
{[
'pip install browser-use playwright',
'docker run -p 3000:3000 playwright-mcp',
'const browser = await chromium.launch()',
].map((cmd) => (
<div
key={cmd}
className="font-mono text-sm text-white-400 dark:text-gray-300 truncate"
>
<Highlighter
action="strike-through"
color="#ef4444aa"
strokeWidth={1.5}
// multiline={false}
// isView
>
{cmd}
</Highlighter>
</div>
))}
</div>
<div className="bg-emerald-50 dark:bg-emerald-950/30 border border-emerald-200/60 dark:border-emerald-700/40 rounded-xl px-5 py-3 font-mono text-sm text-emerald-700 dark:text-emerald-400 flex items-center gap-2.5">
<span className="text-emerald-500 text-xs shrink-0"></span>
{'<script src="page-agent.js"></script>'}
</div>
</div>
<div className="px-7 pb-5">
<div className="flex items-center gap-2.5 mb-1">
<Box className="w-5 h-5 text-blue-500" />
<h3 className="font-semibold text-lg text-gray-900 dark:text-white">
{isZh ? '零基建集成' : 'Zero Infrastructure'}
</h3>
</div>
<p className="text-sm text-gray-500 dark:text-gray-300 leading-relaxed">
{isZh
? '无需 Python、无头浏览器、服务端部署。一行 script 标签搞定。'
: "No Python. No headless browser. No server. One script tag — that's it."}
</p>
</div>
</div>
</MagicCard>
</BlurFade>
<BlurFade inView delay={0.1} className="col-span-1">
<MagicCard
className="h-full rounded-2xl"
gradientFrom="#8b5cf6"
gradientTo="#a855f7"
gradientColor="#8b5cf6"
gradientOpacity={0.12}
>
<div className={`flex ${CARD_HEIGHT} flex-col`}>
<div className="flex-1 relative overflow-hidden">
<Particles
className="absolute inset-0"
quantity={40}
staticity={50}
ease={80}
color="#8b5cf6"
/>
<div className="absolute inset-0 flex items-center justify-center">
<div className="w-16 h-16 rounded-2xl bg-purple-500/10 dark:bg-purple-500/20 backdrop-blur-sm flex items-center justify-center ring-1 ring-purple-500/20">
<Shield className="w-8 h-8 text-purple-500" strokeWidth={1.5} />
</div>
</div>
</div>
<div className="px-6 pb-5">
<h3 className="font-semibold text-lg text-gray-900 dark:text-white mb-1">
{isZh ? '隐私优先' : 'Privacy by Default'}
</h3>
<p className="text-sm text-gray-500 dark:text-gray-300 leading-relaxed">
{isZh
? '浏览器内运行,数据完全由你掌控。'
: 'Runs in the browser. You control your data, always.'}
</p>
</div>
</div>
</MagicCard>
</BlurFade>
{/* Row 2: Human-in-the-Loop (1col) + LLM (2col) */}
<BlurFade inView delay={0.15} className="col-span-1">
<MagicCard
className="h-full rounded-2xl"
gradientFrom="#3b82f6"
gradientTo="#8b5cf6"
gradientColor="#6366f1"
gradientOpacity={0.12}
>
<div className={`flex ${CARD_HEIGHT} flex-col`}>
<div className="flex-1 p-5 flex flex-col justify-center max-w-xs mx-auto w-full">
<div className="flex gap-2 mb-2.5">
<div className="shrink-0 w-6 h-6 rounded-full bg-purple-100 dark:bg-purple-900/50 flex items-center justify-center">
<Bot className="w-3.5 h-3.5 text-purple-600 dark:text-purple-400" />
</div>
<div className="bg-gray-100 dark:bg-white/10 rounded-2xl rounded-tl-md px-3.5 py-2 text-sm text-gray-700 dark:text-gray-200">
{isZh ? '找到 3 条匹配记录。选择哪一条?' : 'Found 3 matches. Which one?'}
</div>
</div>
<div className="flex gap-2 justify-end mb-2.5">
<div className="bg-blue-500 rounded-2xl rounded-tr-md px-3.5 py-2 text-sm text-white">
{isZh ? '第二条' : 'The second one.'}
</div>
<div className="shrink-0 w-6 h-6 rounded-full bg-blue-100 dark:bg-blue-900/50 flex items-center justify-center">
<Users className="w-3.5 h-3.5 text-blue-600 dark:text-blue-400" />
</div>
</div>
<div className="flex gap-2">
<div className="shrink-0 w-6 h-6 rounded-full bg-emerald-100 dark:bg-emerald-900/50 flex items-center justify-center text-emerald-600 dark:text-emerald-400 text-xs font-bold">
</div>
<div className="bg-gray-100 dark:bg-white/10 rounded-2xl rounded-tl-md px-3.5 py-2 text-sm text-gray-700 dark:text-gray-200">
{isZh ? '已选择并提交!' : 'Done! Selected and submitted.'}
</div>
</div>
</div>
<div className="px-5 pb-5">
<div className="flex items-center gap-2.5 mb-1">
<MessageSquare className="w-5 h-5 text-blue-500" />
<h3 className="font-semibold text-lg text-gray-900 dark:text-white">
{isZh ? '人机协同' : 'Human-in-the-Loop'}
</h3>
</div>
<p className="text-sm text-gray-500 dark:text-gray-300 leading-relaxed">
{isZh
? '内置协作面板,AI 操作前先确认——不是盲目自动化。'
: 'Built-in collaborative panel. Agent asks before acting — not blind automation.'}
</p>
</div>
</div>
</MagicCard>
</BlurFade>
<BlurFade inView delay={0.2} className="col-span-1 md:col-span-2">
<MagicCard
className="h-full rounded-2xl"
gradientFrom="#f59e0b"
gradientTo="#f97316"
gradientColor="#f59e0b"
gradientOpacity={0.12}
>
<div className={`flex ${CARD_HEIGHT} flex-col`}>
<div className="flex-1 overflow-hidden relative">
{LLM_CLOUD.map((item) => (
<span
key={item.name}
className="absolute font-semibold whitespace-nowrap select-none"
style={{
left: `${item.x}%`,
top: `${item.y}%`,
fontSize: `${item.size}rem`,
color: item.color,
opacity: item.opacity,
transform: 'translate(-50%, -50%)',
textShadow: `0 0 80px ${item.color}99`,
}}
>
{item.name}
</span>
))}
</div>
<div className="px-7 pb-5">
<div className="flex items-center gap-2.5 mb-1">
<Sparkles className="w-5 h-5 text-amber-500" />
<h3 className="font-semibold text-lg text-gray-900 dark:text-white">
{isZh ? '兼容多种 LLM' : 'Bring Your Own LLMs'}
</h3>
</div>
<p className="text-sm text-gray-500 dark:text-gray-300 leading-relaxed">
{isZh
? 'OpenAI、Claude、DeepSeek、Qwen 等,或通过 Ollama 完全离线。'
: 'OpenAI, Claude, DeepSeek, Qwen, and more — or fully offline via Ollama.'}
</p>
</div>
</div>
</MagicCard>
</BlurFade>
</div>
</div>
</section>
)
}
@@ -0,0 +1,423 @@
/* eslint-disable react-dom/no-dangerously-set-innerhtml */
import type { PageAgent as PageAgentType } from 'page-agent'
import { useEffect, useState } from 'react'
import { Link, useSearchParams } from 'wouter'
import { AnimatedGradientText } from '../../components/ui/animated-gradient-text'
import { Highlighter } from '../../components/ui/highlighter'
import { NeonGradientCard } from '../../components/ui/neon-gradient-card'
import { Particles } from '../../components/ui/particles'
import {
CDN_DEMO_CN_URL,
CDN_DEMO_URL,
DEMO_API_KEY,
DEMO_BASE_URL,
DEMO_MODEL,
} from '../../constants'
import { useLanguage } from '../../i18n/context'
let pageAgentModule: Promise<typeof import('page-agent')> | null = null
function getInjection(useCN?: boolean) {
const cdn = useCN ? CDN_DEMO_CN_URL : CDN_DEMO_URL
const injection = encodeURI(
`javascript:(function(){var s=document.createElement('script');s.src=\`${cdn}?t=\${Math.random()}\`;s.setAttribute('crossorigin', true);s.type="text/javascript";s.onload=()=>console.log('PageAgent script loaded!');document.body.appendChild(s);})();`
)
return `
<a
href=${injection}
class="inline-flex items-center text-xs px-3 py-2 bg-blue-500 text-white font-medium rounded-lg hover:shadow-md transform hover:scale-105 transition-all duration-200 cursor-move border-2 border-dashed border-green-300"
draggable="true"
onclick="return false;"
title="Drag me to your bookmarks bar!"
>
✨PageAgent
</a>
`
}
export default function HeroSection() {
const { language, isZh } = useLanguage()
const defaultTask = isZh
? '从导航栏中进入文档页,打开"快速开始"相关的文档,帮我总结成 markdown'
: 'Goto docs in navigation bar, find Quick-Start section, and summarize in markdown'
const [task, setTask] = useState(() => defaultTask)
useEffect(() => {
setTask(defaultTask)
}, [defaultTask])
const [params] = useSearchParams()
const isOther = params.has('try_other')
const [activeTab, setActiveTab] = useState<'try' | 'other'>(isOther ? 'other' : 'try')
const [cdnSource, setCdnSource] = useState<'international' | 'china'>('international')
const [ready, setReady] = useState(false)
useEffect(() => {
pageAgentModule ??= import('page-agent')
pageAgentModule.then(() => setReady(true))
}, [])
const handleExecute = async () => {
if (!task.trim() || !ready || !pageAgentModule) return
const { PageAgent } = await pageAgentModule
const win = window as any
if (!win.pageAgent || win.pageAgent.disposed) {
win.pageAgent = new (PageAgent as typeof PageAgentType)({
interactiveBlacklist: [document.getElementById('root')!],
language: language,
instructions: {
system: 'You are a helpful assistant on PageAgent website.',
getPageInstructions: (url: string) => {
const hint = url.includes('page-agent') ? 'This is PageAgent demo page.' : undefined
console.log('[instructions] getPageInstructions:', url, '->', hint)
return hint
},
},
model:
import.meta.env.DEV && import.meta.env.LLM_MODEL_NAME
? import.meta.env.LLM_MODEL_NAME
: DEMO_MODEL,
baseURL:
import.meta.env.DEV && import.meta.env.LLM_BASE_URL
? import.meta.env.LLM_BASE_URL
: DEMO_BASE_URL,
apiKey:
import.meta.env.DEV && import.meta.env.LLM_API_KEY
? import.meta.env.LLM_API_KEY
: DEMO_API_KEY,
})
}
const result = await win.pageAgent.execute(task)
console.log(result)
}
return (
<section
className="relative px-6 pt-24 py-20 pb-18 lg:py-22 lg:pt-28 overflow-hidden"
aria-labelledby="hero-heading"
>
<div className="max-w-7xl mx-auto text-center">
{/* Background Pattern + Particles */}
<div className="absolute inset-0 opacity-30" aria-hidden="true">
<div className="absolute inset-0 bg-linear-to-r from-blue-400/20 to-purple-400/20 rounded-3xl transform rotate-1"></div>
<div className="absolute inset-0 bg-linear-to-l from-purple-400/20 to-blue-400/20 rounded-3xl transform -rotate-1"></div>
</div>
<Particles
className="absolute inset-0"
quantity={80}
staticity={30}
ease={80}
color="#6366f1"
/>
<div className="relative z-10">
<div className="inline-flex items-center px-4 py-2 mb-8 text-sm font-medium bg-white/90 dark:bg-gray-800/90 rounded-full shadow-lg border border-gray-200 dark:border-gray-700">
<span
className="w-2 h-2 bg-blue-500 rounded-full mr-2 animate-pulse"
aria-hidden="true"
></span>
<AnimatedGradientText colorFrom="#3b82f6" colorTo="#8b5cf6">
AI Agent In Your Webpage
</AnimatedGradientText>
</div>
<h1
id="hero-heading"
className="text-5xl lg:text-7xl font-bold mb-14 mt-8 bg-linear-to-r from-blue-600 to-purple-600 bg-clip-text text-transparent pb-1"
>
{isZh ? (
<>
<span className="text-6xl lg:text-7xl"> AI </span>
<span className="block text-xl lg:text-2xl mt-5 font-medium bg-linear-to-r from-blue-400 to-purple-400 bg-clip-text text-transparent">
The AI Operator Living in Your Web Page
</span>
</>
) : (
<>
The AI Operator
<br />
Living in Your Web Page
</>
)}
</h1>
<p className="text-xl lg:text-2xl text-gray-600 dark:text-gray-300 mb-12 max-w-4xl mx-auto leading-relaxed">
<Highlighter action="underline" color="#8b5cf6" strokeWidth={2}>
<span className="bg-linear-to-r from-blue-500 to-purple-500 bg-clip-text text-transparent font-bold">
{isZh ? '🪄一行代码' : '🪄One line of code'}
</span>
</Highlighter>
{isZh
? ',让你的网站变身 AI 原生应用。'
: ', turns your website into an AI-native app.'}
<br />
{isZh
? '用户/答疑机器人给出文字指示,AI 帮你操作页面。'
: 'Users give natural language commands, AI handles the rest.'}
</p>
{/* Try It Now Section - Tab Card */}
<div className="mb-12">
<div className="max-w-3xl mx-auto">
<NeonGradientCard
borderSize={2}
borderRadius={20}
neonColors={{ firstColor: '#ff00aa', secondColor: '#00FFF1' }}
>
{/* Tab Headers */}
<div className="flex border-b border-gray-200 dark:border-gray-700">
<button
onClick={() => setActiveTab('try')}
className={`cursor-pointer flex-1 px-4 py-4 text-lg font-medium transition-colors duration-200 rounded-tl-2xl ${
activeTab === 'try'
? 'bg-linear-to-r from-blue-50 to-purple-50 dark:from-blue-900/30 dark:to-purple-900/30 text-blue-700 dark:text-blue-300 border-b-2 border-blue-500'
: 'text-gray-600 dark:text-gray-400 hover:text-gray-900 dark:hover:text-white hover:bg-gray-50 dark:hover:bg-gray-700'
}`}
>
{isZh ? '🚀 立即尝试' : '🚀 Try It Now'}
</button>
<button
onClick={() => setActiveTab('other')}
className={`cursor-pointer flex-1 px-4 py-4 text-lg font-medium transition-colors duration-200 rounded-tr-2xl ${
activeTab === 'other'
? 'bg-linear-to-r from-green-50 to-blue-50 dark:from-green-900/30 dark:to-blue-900/30 text-green-700 dark:text-green-300 border-b-2 border-green-500'
: 'text-gray-600 dark:text-gray-400 hover:text-gray-900 dark:hover:text-white hover:bg-gray-50 dark:hover:bg-gray-700'
}`}
>
{isZh ? '🌐 其他网页尝试' : '🌐 Try on Other Sites'}
</button>
</div>
{/* Tab Content */}
<div className="p-4">
{activeTab === 'try' && (
<div className="space-y-4">
<div className="relative">
<input
value={task}
onChange={(e) => setTask(e.target.value)}
placeholder={
isZh
? '输入您想要 AI 执行的任务...'
: 'Describe what you want AI to do...'
}
className="w-full px-4 py-3 pr-20 border border-gray-300 dark:border-gray-600 rounded-lg bg-white dark:bg-gray-700 text-gray-900 dark:text-white placeholder-gray-500 dark:placeholder-gray-400 focus:ring-2 focus:ring-blue-500 focus:border-transparent resize-none text-sm mb-0"
data-page-agent-not-interactive
/>
<button
onClick={handleExecute}
disabled={!ready}
className="absolute right-2 top-2 px-5 py-1.5 bg-linear-to-r from-blue-600 to-purple-600 text-white font-medium rounded-md hover:shadow-md transform hover:scale-105 transition-all duration-200 disabled:opacity-50 disabled:cursor-not-allowed disabled:transform-none text-sm"
data-page-agent-not-interactive
>
{ready ? (
isZh ? (
'执行'
) : (
'Run'
)
) : (
<span className="animate-pulse">
{isZh ? '准备中...' : 'Preparing...'}
</span>
)}
</button>
</div>
<p className="text-xs text-gray-500 dark:text-gray-400 text-left">
{isZh ? (
<>
使 LLM API
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="underline"
>
使
</a>
</>
) : (
<>
Powered by free testing LLM API. By clicking Run you agree to the{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="underline"
>
Terms of Use
</a>
</>
)}
</p>
</div>
)}
{activeTab === 'other' && (
<div className="grid md:grid-cols-2 gap-6">
{/* 左侧:操作步骤 */}
<div className="space-y-4">
<div className="bg-blue-50 dark:bg-gray-700 p-4 rounded-lg">
<p className="text-gray-700 dark:text-gray-300 text-sm mb-3">
<span className="font-semibold">{isZh ? '步骤 1:' : 'Step 1:'}</span>{' '}
{isZh ? '显示收藏夹栏' : 'Show your bookmarks bar'}
</p>
<div className="flex items-center justify-center gap-2">
<kbd className="px-2 py-1 bg-white dark:bg-gray-600 border border-gray-300 dark:border-gray-500 rounded text-xs font-mono">
Ctrl + Shift + B
</kbd>
<span className="text-gray-500 dark:text-gray-400">
{isZh ? '或' : 'or'}
</span>
<kbd className="px-2 py-1 bg-white dark:bg-gray-600 border border-gray-300 dark:border-gray-500 rounded text-xs font-mono">
+ Shift + B
</kbd>
</div>
</div>
<div className="bg-green-50 dark:bg-gray-700 p-4 rounded-lg">
<p className="text-gray-700 dark:text-gray-300 text-sm mb-3">
<span className="font-semibold">{isZh ? '步骤 2:' : 'Step 2:'}</span>{' '}
{isZh ? '拖拽下面按钮到收藏夹栏' : 'Drag this button to your bookmarks'}
</p>
<div className="flex items-center justify-center gap-3">
<select
value={cdnSource}
onChange={(e) =>
setCdnSource(e.target.value as 'international' | 'china')
}
className="px-2 py-1.5 text-xs border border-gray-300 dark:border-gray-500 rounded bg-white dark:bg-gray-600 text-gray-700 dark:text-gray-200"
>
<option value="international">jsdelivr CDN</option>
<option value="china">npmmirror CDN</option>
</select>
<div
dangerouslySetInnerHTML={{
__html: getInjection(cdnSource === 'china'),
}}
></div>
</div>
</div>
<div className="bg-purple-50 dark:bg-gray-700 p-4 rounded-lg">
<p className="text-gray-700 dark:text-gray-300 text-sm">
<span className="font-semibold">{isZh ? '步骤 3:' : 'Step 3:'}</span>{' '}
{isZh
? '在其他网站点击收藏夹中的按钮即可使用'
: 'Click the bookmark on any site to activate'}
</p>
</div>
</div>
{/* 右侧:注意事项 */}
<div className="bg-yellow-50 dark:bg-gray-700 p-4 rounded-lg">
<h4 className="font-semibold text-gray-900 dark:text-white mb-3 text-sm">
{isZh ? '⚠️ 注意' : '⚠️ Heads Up'}
</h4>
<ul className="space-y-2 text-sm text-gray-700 dark:text-gray-300">
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh ? (
<span>
使 LLM API使
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="text-yellow-700 dark:text-yellow-300 underline"
>
使
</a>
</span>
) : (
<span>
Uses free testing LLM API. By using you agree to the{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md#2-testing-api-and-demo-disclaimer--terms-of-use"
target="_blank"
rel="noopener noreferrer"
className="text-yellow-700 dark:text-yellow-300 underline"
>
Terms of Use
</a>
</span>
)}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '数据通过中国大陆服务器处理'
: 'Data processed via servers in Mainland China'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '部分网站屏蔽了链接嵌入,将无反应'
: 'Some sites block script injection (CSP policies)'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh ? '支持单页应用' : 'Works on single-page apps'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh
? '仅识别文本,不识别图像,不支持拖拽等复杂交互'
: 'Text-only understanding—no image recognition or drag-and-drop'}
</li>
<li className="flex items-start text-left">
<span className="w-1.5 h-1.5 bg-yellow-500 rounded-full mt-2 mr-2 shrink-0 "></span>
{isZh ? '详细使用限制参照' : 'Full limitations in'}
<Link
href="/docs/introduction/limitations"
className="text-blue-600 dark:text-blue-400 hover:underline pl-1"
>
{isZh ? '《文档》' : 'Docs'}
</Link>
</li>
</ul>
</div>
</div>
)}
</div>
</NeonGradientCard>
</div>
</div>
<ul
className="flex flex-wrap justify-center gap-6 text-sm text-gray-500 dark:text-gray-400"
role="list"
>
<li className="flex items-center">
<span className="w-2 h-2 bg-green-500 rounded-full mr-2" aria-hidden="true"></span>
{isZh ? '纯前端方案' : 'Pure Front-end Solution'}
</li>
<li className="flex items-center">
<span className="w-2 h-2 bg-green-500 rounded-full mr-2" aria-hidden="true"></span>
{isZh ? '支持私有模型' : 'Your Own Models'}
</li>
<li className="flex items-center">
<span className="w-2 h-2 bg-green-500 rounded-full mr-2" aria-hidden="true"></span>
{isZh ? '无痛脱敏' : 'Built-in Privacy'}
</li>
<li className="flex items-center">
<span className="w-2 h-2 bg-green-500 rounded-full mr-2" aria-hidden="true"></span>
{isZh ? 'MIT 开源' : 'MIT Open Source'}
</li>
</ul>
</div>
</div>
</section>
)
}
@@ -0,0 +1,98 @@
import { ExternalLink } from 'lucide-react'
import { siGooglechrome } from 'simple-icons'
import { Link } from 'wouter'
import { BlurFade } from '../../components/ui/blur-fade'
import { MagicCard } from '../../components/ui/magic-card'
import { useLanguage } from '../../i18n/context'
export default function OneMoreThingSection() {
const { isZh } = useLanguage()
return (
<section className="px-6 py-14" aria-labelledby="one-more-thing-heading">
<div className="max-w-4xl mx-auto text-center">
<BlurFade inView>
<h2
id="one-more-thing-heading"
className="text-4xl lg:text-5xl font-bold mb-6 bg-linear-to-r from-blue-600 to-purple-600 bg-clip-text text-transparent"
>
One More Thing
</h2>
<p className="text-xl text-gray-600 dark:text-gray-300 mb-4 max-w-2xl mx-auto">
{isZh
? '想要多页面控制?试试可选的浏览器扩展。'
: 'Need multi-page control? Try the optional browser extension.'}
</p>
<p className="text-sm text-gray-500 dark:text-gray-400 mb-12 max-w-2xl mx-auto">
{'* '}
{isZh
? 'PageAgent.js 本身无需任何扩展即可工作,扩展是额外的能力增强。'
: 'PageAgent.js works without any extension — this is a power-up, not a dependency.'}
</p>
</BlurFade>
<div className="flex flex-col sm:flex-row items-center justify-center gap-4 mb-12">
<a
href="https://chromewebstore.google.com/detail/page-agent-ext/akldabonmimlicnjlflnapfeklbfemhj"
target="_blank"
rel="noopener noreferrer"
className="group inline-flex items-center gap-3 px-8 py-4 bg-linear-to-r from-blue-600 to-blue-700 hover:from-blue-700 hover:to-blue-800 text-white font-medium rounded-2xl shadow-lg hover:shadow-xl transition-all duration-300 hover:scale-105"
>
<img
src="https://img.alicdn.com/imgextra/i3/O1CN01JpW0Vo1sR3FpiZKFM_!!6000000005762-55-tps-192-192.svg"
alt="Chrome Web Store"
className="w-7 h-7"
/>
<span>{isZh ? '从 Chrome 应用商店安装' : 'Install from Chrome Web Store'}</span>
<ExternalLink className="w-4 h-4 opacity-50 group-hover:opacity-100 transition-opacity" />
</a>
<Link
href="/docs/features/chrome-extension"
className="inline-flex items-center gap-3 px-8 py-4 bg-gray-100 dark:bg-gray-700 hover:bg-gray-200 dark:hover:bg-gray-600 text-gray-900 dark:text-white font-medium rounded-2xl transition-all duration-300 hover:scale-105"
>
<svg className="w-5 h-5" viewBox="0 0 24 24" aria-hidden="true">
<path d={siGooglechrome.path} fill="currentColor" />
</svg>
<span>{isZh ? '查看文档' : 'Read the Docs'}</span>
</Link>
</div>
<div className="grid sm:grid-cols-3 gap-5 text-left max-w-3xl mx-auto">
{[
{
title: isZh ? '多页面任务' : 'Multi-Page Tasks',
desc: isZh
? '跨多个页面和标签页连续执行任务,不再受限于单页上下文'
: 'Run tasks across multiple pages and tabs without being limited to a single page context',
},
{
title: isZh ? '页面内发起控制' : 'Control from Your Page',
desc: isZh
? '在页面 JS 中发起任务,驱动整个浏览器完成跨标签操作'
: 'Trigger tasks from page JS to drive the entire browser across tabs',
},
{
title: isZh ? '外部发起任务' : 'External Triggers',
desc: isZh
? '页面 JS、本地 Agent 或云端 Agent 均可通过扩展发起任务'
: 'Page JS, local agents, or cloud agents can trigger tasks through the extension',
},
].map((item) => (
<MagicCard
key={item.title}
className="rounded-xl"
gradientColor="#8b5cf620"
gradientOpacity={0.15}
>
<div className="p-5">
<h3 className="font-semibold text-gray-900 dark:text-white mb-1">{item.title}</h3>
<p className="text-sm text-gray-600 dark:text-gray-300">{item.desc}</p>
</div>
</MagicCard>
))}
</div>
</div>
</section>
)
}
@@ -0,0 +1,165 @@
import { Bot, Users, Zap } from 'lucide-react'
import { BlurFade } from '../../components/ui/blur-fade'
import { SparklesText } from '../../components/ui/sparkles-text'
import { useLanguage } from '../../i18n/context'
export default function ScenariosSection() {
const { isZh } = useLanguage()
return (
<section
className="px-6 py-16 bg-linear-to-b from-blue-100 to-purple-100 dark:from-blue-950/40 dark:to-gray-800"
aria-labelledby="scenarios-heading"
>
<div className="max-w-6xl mx-auto">
<BlurFade inView>
<div className="text-center mb-12">
<SparklesText
className="text-4xl lg:text-5xl mb-6"
colors={{ first: '#3b82f6', second: '#8b5cf6' }}
>
{isZh ? '应用场景' : 'Built For'}
</SparklesText>
</div>
</BlurFade>
<div className="grid grid-cols-1 md:grid-cols-3 gap-6">
{/* SaaS AI Copilot */}
<BlurFade inView delay={0.05}>
<div className="group relative overflow-hidden rounded-2xl bg-linear-to-b from-blue-50 to-white dark:from-blue-950/40 dark:to-gray-800 border border-blue-200/80 dark:border-blue-800/50 shadow-sm hover:shadow-xl hover:-translate-y-1 transition-all duration-500">
<div className="p-6 pb-4">
<div className="rounded-xl bg-gray-950 p-4 font-mono text-xs leading-6 text-gray-300 overflow-hidden shadow-inner">
<div>
<span className="text-purple-400">import</span> {'{ PageAgent }'}{' '}
<span className="text-purple-400">from</span>{' '}
<span className="text-emerald-400">&apos;page-agent&apos;</span>
</div>
<div className="mt-2">
<span className="text-purple-400">const</span>{' '}
<span className="text-blue-300">copilot</span> ={' '}
<span className="text-purple-400">new</span>{' '}
<span className="text-yellow-300">PageAgent</span>
{'({'}
</div>
<div className="pl-4">
<span className="text-blue-300">model</span>:{' '}
<span className="text-emerald-400">&apos;gpt-5.1&apos;</span>,
</div>
<div className="pl-4">
<span className="text-blue-300">apiKey</span>:{' '}
<span className="text-emerald-400">process.env.KEY</span>,
</div>
<div>{'})'}</div>
</div>
</div>
<div className="p-6 pt-2">
<div className="flex items-center gap-2 mb-2">
<Bot className="w-5 h-5 text-blue-500" />
<h3 className="font-semibold text-lg text-gray-900 dark:text-white">
{isZh ? 'SaaS AI 副驾驶' : 'SaaS AI Copilot'}
</h3>
</div>
<p className="text-sm text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '几小时内为你的产品加上 AI 副驾驶,不需要重写后端。'
: 'Ship an AI copilot in your product in hours, not months. No backend rewrite needed.'}
</p>
</div>
</div>
</BlurFade>
{/* Smart Form Filling */}
<BlurFade inView delay={0.1}>
<div className="group relative overflow-hidden rounded-2xl bg-linear-to-b from-amber-50 to-white dark:from-amber-950/40 dark:to-gray-800 border border-amber-200/80 dark:border-amber-800/50 shadow-sm hover:shadow-xl hover:-translate-y-1 transition-all duration-500">
<div className="p-6 pb-4">
<div className="rounded-xl bg-white dark:bg-gray-900 border border-gray-200 dark:border-gray-700 p-4 shadow-inner space-y-2.5">
<div className="flex items-center gap-2 text-xs text-gray-500 dark:text-gray-400 bg-amber-50 dark:bg-amber-900/30 rounded-lg px-3 py-2 border border-amber-200/50 dark:border-amber-700/40">
<span>🪄</span>
<span className="italic">
{isZh
? '"填写上周五出差的报销单"'
: '"Fill the expense report for Friday\'s trip"'}
</span>
</div>
{[
{ label: isZh ? '姓名' : 'Name', value: 'John Smith' },
{ label: isZh ? '金额' : 'Amount', value: '$342.50' },
{ label: isZh ? '类目' : 'Category', value: 'Travel' },
].map((field) => (
<div key={field.label} className="flex items-center gap-2">
<span className="text-xs text-gray-400 dark:text-gray-500 w-12 shrink-0">
{field.label}
</span>
<div className="flex-1 h-7 bg-gray-50 dark:bg-gray-800 rounded border border-gray-200 dark:border-gray-600 px-2 flex items-center text-xs text-gray-600 dark:text-gray-300">
{field.value}
</div>
<span className="text-emerald-500 text-xs"></span>
</div>
))}
</div>
</div>
<div className="p-6 pt-2">
<div className="flex items-center gap-2 mb-2">
<Zap className="w-5 h-5 text-amber-500" />
<h3 className="font-semibold text-lg text-gray-900 dark:text-white">
{isZh ? '智能表单填写' : 'Smart Form Filling'}
</h3>
</div>
<p className="text-sm text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '把 20 次点击变成一句话。ERP、CRM、管理后台的最佳拍档。'
: 'Turn 20-click workflows into one sentence. Perfect for ERP, CRM, and admin systems.'}
</p>
</div>
</div>
</BlurFade>
{/* Accessibility */}
<BlurFade inView delay={0.15}>
<div className="group relative overflow-hidden rounded-2xl bg-linear-to-b from-purple-50 to-white dark:from-purple-950/40 dark:to-gray-800 border border-purple-200/80 dark:border-purple-800/50 shadow-sm hover:shadow-xl hover:-translate-y-1 transition-all duration-500">
<div className="p-6 pb-4 flex flex-col items-center justify-center">
<div className="w-full rounded-xl bg-purple-50 dark:bg-purple-900/30 p-5 space-y-3">
<div className="flex items-center gap-3">
<div className="w-8 h-8 rounded-full bg-purple-500/10 dark:bg-purple-500/20 flex items-center justify-center text-base">
🎤
</div>
<div className="text-sm text-purple-700 dark:text-purple-300 italic">
{isZh ? '"点击提交按钮"' : '"Click the submit button"'}
</div>
</div>
<div className="flex items-center gap-3 pl-11">
<div className="flex items-center gap-1.5">
<div className="w-1.5 h-1.5 bg-purple-400 rounded-full animate-pulse"></div>
<div className="w-1.5 h-1.5 bg-purple-400 rounded-full animate-pulse [animation-delay:0.2s]"></div>
<div className="w-1.5 h-1.5 bg-purple-400 rounded-full animate-pulse [animation-delay:0.4s]"></div>
</div>
<span className="text-xs text-purple-500 dark:text-purple-400">
{isZh ? 'AI 正在执行...' : 'AI executing...'}
</span>
</div>
<div className="flex items-center gap-3 pl-11 text-sm text-emerald-600 dark:text-emerald-400">
<span></span> {isZh ? '按钮已点击' : 'Button clicked'}
</div>
</div>
</div>
<div className="p-6 pt-2">
<div className="flex items-center gap-2 mb-2">
<Users className="w-5 h-5 text-purple-500" />
<h3 className="font-semibold text-lg text-gray-900 dark:text-white">
{isZh ? '无障碍增强' : 'Accessibility'}
</h3>
</div>
<p className="text-sm text-gray-600 dark:text-gray-300 leading-relaxed">
{isZh
? '用自然语言让任何网页无障碍。语音指令、屏幕阅读器,零门槛。'
: 'Make any web app accessible through natural language. Voice, screen readers, zero barrier.'}
</p>
</div>
</div>
</BlurFade>
</div>
</div>
</section>
)
}
+58 -25
View File
@@ -1,35 +1,68 @@
import { Suspense, lazy } from 'react' import { Suspense, lazy, useEffect, useLayoutEffect } from 'react'
import { Route, Switch } from 'wouter' 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'
import DocsPages from './pages/docs/index'
// const DocsPages = lazy(() => import('./pages/docs/index')) const docsImport = () => import('./pages/docs/index')
const DocsPages = lazy(docsImport)
function ScrollToTop() {
const [pathname] = useLocation()
useLayoutEffect(() => {
window.scrollTo(0, 0)
}, [pathname])
return null
}
export default function Router() { export default function Router() {
useEffect(() => {
const id = requestIdleCallback(() => docsImport())
return () => cancelIdleCallback(id)
}, [])
return ( return (
<Suspense> <div className="flex min-h-screen flex-col">
<Switch> <Header />
{/* Home page */} <Suspense>
<Route path="/"> <ScrollToTop />
<HomePage /> <Switch>
</Route> <Route path="/">
<main
id="main-content"
className="flex-1 bg-linear-to-br from-blue-50 to-purple-50 dark:from-gray-900 dark:to-gray-800"
>
<HomePage />
</main>
</Route>
{/* All docs pages */} <Route path="/docs" nest>
<Route path="/docs" nest> <div className="flex-1 bg-white dark:bg-gray-900">
<DocsPages /> <Suspense
</Route> fallback={
<div className="flex items-center justify-center gap-3 py-20 text-gray-400">
{/* 404 */} <div className="w-4 h-4 border-2 border-blue-500 border-t-transparent rounded-full animate-spin" />
<Route> Loading...
<div className="min-h-screen bg-white dark:bg-gray-900 flex items-center justify-center"> </div>
<div className="text-center"> }
<h1 className="text-4xl font-bold mb-4 text-gray-900 dark:text-white">404</h1> >
<p className="text-xl text-gray-600 dark:text-gray-300"></p> <DocsPages />
</Suspense>
</div> </div>
</div> </Route>
</Route>
</Switch> <Route>
</Suspense> <div className="flex-1 bg-white dark:bg-gray-900 flex items-center justify-center">
<div className="text-center">
<h1 className="text-4xl font-bold mb-4 text-gray-900 dark:text-white">404</h1>
<p className="text-xl text-gray-600 dark:text-gray-300">Page not found</p>
</div>
</div>
</Route>
</Switch>
</Suspense>
<Footer />
</div>
) )
} }
+45 -4
View File
@@ -1,9 +1,9 @@
import tailwindcss from '@tailwindcss/vite' import tailwindcss from '@tailwindcss/vite'
import react from '@vitejs/plugin-react-swc' import react from '@vitejs/plugin-react-swc'
import { config as dotenvConfig } from 'dotenv' import { config as dotenvConfig } from 'dotenv'
import { readFileSync } from 'node:fs' import { copyFileSync, mkdirSync, readFileSync } from 'node:fs'
import process from 'node:process' import process from 'node:process'
import { dirname, resolve } from 'path' import { dirname, join, resolve } from 'path'
import { fileURLToPath } from 'url' import { fileURLToPath } from 'url'
import { defineConfig } from 'vite' import { defineConfig } from 'vite'
@@ -15,11 +15,47 @@ const pageAgentPkg = JSON.parse(
// Load .env from repo root // Load .env from repo root
dotenvConfig({ path: resolve(__dirname, '../../.env') }) dotenvConfig({ path: resolve(__dirname, '../../.env') })
// All SPA routes that need index.html copies for direct access on static hosts
const SPA_ROUTES = [
'docs',
'docs/introduction/overview',
'docs/introduction/quick-start',
'docs/introduction/limitations',
'docs/introduction/troubleshooting',
'docs/features/custom-tools',
'docs/features/data-masking',
'docs/features/custom-instructions',
'docs/features/models',
'docs/features/chrome-extension',
'docs/advanced/page-agent',
'docs/advanced/page-agent-core',
'docs/advanced/custom-ui',
'docs/integration/security-permissions',
'docs/integration/best-practices',
'docs/integration/third-party-agent',
]
function spaRoutes() {
return {
name: 'spa-routes',
closeBundle() {
const dist = resolve(__dirname, 'dist')
const src = join(dist, 'index.html')
for (const route of SPA_ROUTES) {
const dir = join(dist, route)
mkdirSync(dir, { recursive: true })
copyFileSync(src, join(dir, 'index.html'))
}
console.log(` ✓ Copied index.html to ${SPA_ROUTES.length} SPA routes`)
},
}
}
// Website Config (React Documentation Site) // Website Config (React Documentation Site)
export default defineConfig(({ mode }) => ({ export default defineConfig(({ mode }) => ({
base: './', base: '/page-agent/',
clearScreen: false, clearScreen: false,
plugins: [react(), tailwindcss()], plugins: [react(), tailwindcss(), spaRoutes()],
build: { build: {
chunkSizeWarningLimit: 2000, chunkSizeWarningLimit: 2000,
cssCodeSplit: true, cssCodeSplit: true,
@@ -28,6 +64,11 @@ export default defineConfig(({ mode }) => ({
if (message.code === 'EVAL') return if (message.code === 'EVAL') return
handler(message) handler(message)
}, },
output: {
manualChunks: {
vendor: ['react', 'react-dom', 'wouter'],
},
},
}, },
}, },
resolve: { resolve: {
+1 -1
View File
@@ -111,7 +111,7 @@ const CDN_DEMO_URL_NEW = `https://cdn.jsdelivr.net/npm/page-agent@${newVersion}/
const CDN_DEMO_CN_URL_OLD = `https://registry.npmmirror.com/page-agent/${oldVersion}/files/dist/iife/page-agent.demo.js` const CDN_DEMO_CN_URL_OLD = `https://registry.npmmirror.com/page-agent/${oldVersion}/files/dist/iife/page-agent.demo.js`
const CDN_DEMO_CN_URL_NEW = `https://registry.npmmirror.com/page-agent/${newVersion}/files/dist/iife/page-agent.demo.js` const CDN_DEMO_CN_URL_NEW = `https://registry.npmmirror.com/page-agent/${newVersion}/files/dist/iife/page-agent.demo.js`
const filesToUpdateCdn = ['README.md', 'README-zh.md', 'packages/website/src/constants.ts'] const filesToUpdateCdn = ['README.md', 'docs/README-zh.md', 'packages/website/src/constants.ts']
for (const relPath of filesToUpdateCdn) { for (const relPath of filesToUpdateCdn) {
const filePath = join(rootDir, relPath) const filePath = join(rootDir, relPath)