Compare commits

..

73 Commits

Author SHA1 Message Date
Simon 27e9e78636 chore(version): bump version to 1.5.2 2026-03-07 03:08:33 +08:00
Simon a0c979602e feat: do not throw for webgl2 fail 2026-03-07 03:07:21 +08:00
Simon 3dc9edb8b5 fix(ext): ts types 2026-03-06 17:39:09 +08:00
Simon 32b68ab7c8 fix(docs): broken demo video 2026-03-06 16:07:22 +08:00
Simon 75a61c05c1 docs(terms): wording
Clarify the note regarding data processing location for the demo.
2026-03-06 04:33:03 +08:00
Simon bdfa98358b fix: requestIdleCallback on safari 2026-03-06 02:35:01 +08:00
Simon dc8b38ccb9 chore(ext): bump extension version to 0.1.11 2026-03-05 20:48:00 +08:00
Simon e1c288aaeb docs(changelog): 1.5.1 2026-03-05 20:44:26 +08:00
Simon 7a97de2a37 feat(ext): expose more config 2026-03-05 20:34:55 +08:00
Simon 19b03b83ea chore(version): bump version to 1.5.1 2026-03-05 19:28:19 +08:00
Simon 598b144d06 feat: change maxSteps to 40 2026-03-05 19:26:56 +08:00
Simon 1cd8a8de60 Merge pull request #158 from alibaba/fix/zod-v3
feat: import zod properly
2026-03-05 19:23:47 +08:00
Simon 9beffca985 docs: update doc for Zod v4 support 2026-03-05 19:15:03 +08:00
Simon 53db2069ce feat: zod support v3/4 2026-03-05 19:13:18 +08:00
Simon 121104e13d feat: truncate llms.txt results 2026-03-05 16:59:08 +08:00
Simon 0dacbda9da chore: improve logging 2026-03-05 16:54:41 +08:00
Simon 8bc27414a4 chore(version): bump version to 1.4.4 2026-03-05 16:25:16 +08:00
Simon 76509d93f0 feat: replace data-browser-use-ignore with data-page-agent-ignore 2026-03-05 16:24:50 +08:00
Simon ff31b0c03e chore: adjust website structure 2026-03-05 16:21:58 +08:00
Simon 6b2ab73d65 docs: model recommendation 2026-03-05 16:10:03 +08:00
Simon 2754023a80 chore(version): bump version to 1.4.3 2026-03-04 21:18:51 +08:00
Simon fa5c65db53 docs: update custom-tool docs 2026-03-04 21:17:32 +08:00
Simon 53c2c19d69 docs: update advanced docs; rm best-practice 2026-03-04 21:13:10 +08:00
Simon e5437b445a fix(core): Core and PageAgent use different config types; improve code structure 2026-03-04 20:05:48 +08:00
Simon 09bdf9ddaf feat(core): experimental support for llms.txt (#157)
* feat(core): experimental support for llms.txt

* docs: experimentalLlmsTxt
2026-03-04 18:53:24 +08:00
Simon b58d2a09ef Merge pull request #152 from alibaba/dependabot/npm_and_yarn/development-dependencies-7e2b43fd30
chore(deps-dev): bump the development-dependencies group with 7 updates
2026-03-03 22:04:35 +08:00
Simon ce442742ba Merge pull request #153 from alibaba/dependabot/npm_and_yarn/vite-plugin-css-injected-by-js-4.0.1
chore(deps-dev): bump vite-plugin-css-injected-by-js from 3.5.2 to 4.0.1
2026-03-03 22:04:17 +08:00
Simon 632f22962e docs: add recommended startup parameters for Ollama 2026-03-03 21:59:02 +08:00
dependabot[bot] 72c3b12fb4 chore(deps-dev): bump the development-dependencies group with 7 updates
Bumps the development-dependencies group with 7 updates:

| Package | From | To |
| --- | --- | --- |
| [@microsoft/api-extractor](https://github.com/microsoft/rushstack/tree/HEAD/apps/api-extractor) | `7.57.3` | `7.57.6` |
| [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) | `25.3.0` | `25.3.3` |
| [globals](https://github.com/sindresorhus/globals) | `17.3.0` | `17.4.0` |
| [lint-staged](https://github.com/lint-staged/lint-staged) | `16.2.7` | `16.3.1` |
| [lucide-react](https://github.com/lucide-icons/lucide/tree/HEAD/packages/lucide-react) | `0.575.0` | `0.576.0` |
| [motion](https://github.com/motiondivision/motion) | `12.34.3` | `12.34.4` |
| [simple-icons](https://github.com/simple-icons/simple-icons) | `16.9.0` | `16.10.0` |


Updates `@microsoft/api-extractor` from 7.57.3 to 7.57.6
- [Changelog](https://github.com/microsoft/rushstack/blob/main/apps/api-extractor/CHANGELOG.md)
- [Commits](https://github.com/microsoft/rushstack/commits/@microsoft/api-extractor_v7.57.6/apps/api-extractor)

Updates `@types/node` from 25.3.0 to 25.3.3
- [Release notes](https://github.com/DefinitelyTyped/DefinitelyTyped/releases)
- [Commits](https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/node)

Updates `globals` from 17.3.0 to 17.4.0
- [Release notes](https://github.com/sindresorhus/globals/releases)
- [Commits](https://github.com/sindresorhus/globals/compare/v17.3.0...v17.4.0)

Updates `lint-staged` from 16.2.7 to 16.3.1
- [Release notes](https://github.com/lint-staged/lint-staged/releases)
- [Changelog](https://github.com/lint-staged/lint-staged/blob/main/CHANGELOG.md)
- [Commits](https://github.com/lint-staged/lint-staged/compare/v16.2.7...v16.3.1)

Updates `lucide-react` from 0.575.0 to 0.576.0
- [Release notes](https://github.com/lucide-icons/lucide/releases)
- [Commits](https://github.com/lucide-icons/lucide/commits/0.576.0/packages/lucide-react)

Updates `motion` from 12.34.3 to 12.34.4
- [Changelog](https://github.com/motiondivision/motion/blob/main/CHANGELOG.md)
- [Commits](https://github.com/motiondivision/motion/compare/v12.34.3...v12.34.4)

Updates `simple-icons` from 16.9.0 to 16.10.0
- [Release notes](https://github.com/simple-icons/simple-icons/releases)
- [Commits](https://github.com/simple-icons/simple-icons/compare/16.9.0...16.10.0)

---
updated-dependencies:
- dependency-name: "@microsoft/api-extractor"
  dependency-version: 7.57.6
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: "@types/node"
  dependency-version: 25.3.3
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: globals
  dependency-version: 17.4.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: lint-staged
  dependency-version: 16.3.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: lucide-react
  dependency-version: 0.576.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
- dependency-name: motion
  dependency-version: 12.34.4
  dependency-type: direct:development
  update-type: version-update:semver-patch
  dependency-group: development-dependencies
- dependency-name: simple-icons
  dependency-version: 16.10.0
  dependency-type: direct:development
  update-type: version-update:semver-minor
  dependency-group: development-dependencies
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-03-03 13:58:04 +00:00
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
dependabot[bot] 5fec6846b0 chore(deps-dev): bump vite-plugin-css-injected-by-js from 3.5.2 to 4.0.1
Bumps [vite-plugin-css-injected-by-js](https://github.com/marco-prontera/vite-plugin-css-injected-by-js) from 3.5.2 to 4.0.1.
- [Release notes](https://github.com/marco-prontera/vite-plugin-css-injected-by-js/releases)
- [Commits](https://github.com/marco-prontera/vite-plugin-css-injected-by-js/compare/v3.5.2...v4.0.1)

---
updated-dependencies:
- dependency-name: vite-plugin-css-injected-by-js
  dependency-version: 4.0.1
  dependency-type: direct:development
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-03-02 21:00:45 +00:00
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
91 changed files with 3437 additions and 2292 deletions
+1 -1
View File
@@ -9,7 +9,7 @@ body:
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。
- [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)
- type: textarea
+1 -1
View File
@@ -10,5 +10,5 @@ contact_links:
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。
- 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。
+1 -1
View File
@@ -9,7 +9,7 @@ body:
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。
- [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)
- type: textarea
+1 -1
View File
@@ -22,4 +22,4 @@ Closes #(issue)
## 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
strategy:
matrix:
node-version: [20, 24, 25]
node-version: [24]
steps:
- uses: actions/checkout@v6
-5
View File
@@ -29,11 +29,6 @@ dist-ssr
.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
.output
.wxt
+24 -32
View File
@@ -9,26 +9,33 @@
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/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2" controls crossorigin muted></video>
---
## ✨ Features
- **🎯 Easy integration**
- No need for `browser extension` / `python` / `headless browser`.
- Just in-page javascript. Everything happens in your web page.
- The best tool for your agent to control web pages.
- **🎯 Easy integration**
- No need for `browser extension` / `python` / `headless browser`.
- Just in-page javascript. Everything happens in your web page.
- The best tool for your agent to control web pages.
- **📖 Text-based DOM manipulation**
- No screenshots. No OCR or multi-modal LLMs needed.
- No special permissions required.
- No screenshots. No OCR or multi-modal LLMs needed.
- No special permissions required.
- **🧠 Bring your own LLMs**
- **🎨 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
@@ -42,10 +49,10 @@ Fastest way to try PageAgent with our free Demo LLM:
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.3.0/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.3.0/files/dist/iife/page-agent.demo.js |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.2/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.2/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
@@ -57,8 +64,8 @@ npm install page-agent
import { PageAgent } from 'page-agent'
const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
model: 'qwen3.5-plus',
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'YOUR_API_KEY',
language: 'en-US',
})
@@ -66,28 +73,13 @@ const agent = new PageAgent({
await agent.execute('Click the login button')
```
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
```
For more programmatic usage, see [📖 Documentations](https://alibaba.github.io/page-agent/docs/introduction/overview).
## 🤝 Contributing
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
+60 -2
View File
@@ -5,6 +5,63 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [1.5.1] - 2026-03-05
### Breaking Changes
- **`data-browser-use-ignore``data-page-agent-ignore`** - DOM ignore attribute renamed to match the project identity
- **Config types restructured** - `PageAgentConfig` split into `AgentConfig` + `PageAgentCoreConfig`; config definitions moved from `config/index.ts` to `types.ts`
- **Zod v3/v4 dual support** - Libraries now accept both `zod@^3.25` and `zod@^4.0` as peer dependencies
### Features
- **Experimental `llms.txt` support** - Agent can fetch and include a site's `llms.txt` in context. Enable via `experimentalLlmsTxt: true`
### Improvements
- Default `maxSteps` changed from 20 to 40 for better for complex tasks out of the box
- Added 400ms wait between agent steps for page reactions
- Increased click wait time (100ms → 200ms) for more reliable interactions
- Removed debug `console.log` statements from scroll actions
- Reset observations on new task start
- Improved logging across packages
### Extension v0.1.9
> PageAgent 1.5.1
- **Advanced config panel** - New collapsible section exposing Max Steps, System Instruction, and experimental `llms.txt` toggle
- Streamlined User Auth Token description
- Moved testing API notice below auth token section
---
## [1.4.0] - 2026-02-27
### Features
- 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
### Breaking Changes
@@ -96,9 +153,10 @@ PageAgent is now ready for production use. The API is stable and breaking change
- **Ask User Tool** - Agent can ask users for clarification
- **i18n Support** - English and Chinese localization
### Configuration
### Configuration
```typescript
// Version 1.0.0
interface PageAgentConfig {
// LLM Configuration (required)
baseURL: string
@@ -146,7 +204,7 @@ interface PageAgentConfig {
- Single-page application only (cannot navigate across pages)
- No visual recognition (relies on DOM structure)
- 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
+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。
🌐 [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/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2" controls crossorigin muted></video>
---
## ✨ Features
- **🎯 轻松集成**
- 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。
- The best tool for your agent to control web pages.
- **🎯 轻松集成**
- 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。
- The best tool for your agent to control web pages.
- **📖 基于文本的 DOM 操作**
- 无需截图,无需 OCR 或多模态模型。
- 无需特殊权限。
- 无需截图,无需 OCR 或多模态模型。
- 无需特殊权限。
- **🧠 用你自己的 LLM**
- **🎨 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
@@ -42,10 +49,10 @@
| Mirrors | URL |
| ------- | ---------------------------------------------------------------------------------- |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.3.0/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.3.0/files/dist/iife/page-agent.demo.js |
| Global | https://cdn.jsdelivr.net/npm/page-agent@1.5.2/dist/iife/page-agent.demo.js |
| China | https://registry.npmmirror.com/page-agent/1.5.2/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
@@ -57,8 +64,8 @@ npm install page-agent
import { PageAgent } from 'page-agent'
const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
model: 'qwen3.5-plus',
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'YOUR_API_KEY',
language: 'zh-CN',
})
@@ -66,26 +73,11 @@ const agent = new PageAgent({
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)。
## 🏗️ 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
```
更多编程用法,请参阅 [📖 文档](https://alibaba.github.io/page-agent/docs/introduction/overview)。
## 🤝 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)。
@@ -114,7 +106,7 @@ file and in the node_modules directory after installation.
## 📄 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 testing LLM api processes data via servers located in Mainland China. If you are located in a region with strict data localization laws (such as the EU/EEA), please do not use this 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
+576 -509
View File
File diff suppressed because it is too large Load Diff
+14 -14
View File
@@ -1,7 +1,7 @@
{
"name": "root",
"private": true,
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"workspaces": [
"packages/page-controller",
@@ -35,32 +35,32 @@
"prepare": "husky"
},
"devDependencies": {
"@commitlint/cli": "^20.3.1",
"@commitlint/config-conventional": "^20.3.1",
"@commitlint/cli": "^20.4.2",
"@commitlint/config-conventional": "^20.4.2",
"@eslint/js": "^9.39.2",
"@microsoft/api-extractor": "^7.56.3",
"@tailwindcss/vite": "^4.1.18",
"@microsoft/api-extractor": "^7.57.6",
"@tailwindcss/vite": "^4.2.1",
"@trivago/prettier-plugin-sort-imports": "^6.0.2",
"@types/node": "^25.2.2",
"@types/node": "^25.3.3",
"@vitejs/plugin-react-swc": "^4.1.0",
"chalk": "^5.6.2",
"concurrently": "^9.2.1",
"dotenv": "^17.2.4",
"dotenv": "^17.3.1",
"eslint": "^9.39.2",
"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-refresh": "^0.5.0",
"eslint-plugin-react-x": "^2.12.2",
"globals": "^17.0.0",
"eslint-plugin-react-refresh": "^0.5.2",
"eslint-plugin-react-x": "^2.13.0",
"globals": "^17.4.0",
"husky": "^9.1.7",
"lint-staged": "^16.2.4",
"lint-staged": "^16.3.1",
"prettier": "^3.8.0",
"typescript": "^5.9.3",
"typescript-eslint": "^8.55.0",
"typescript-eslint": "^8.56.1",
"unplugin-dts": "^1.0.0-beta.6",
"vite": "^7.3.1",
"vite-plugin-css-injected-by-js": "^3.5.2",
"vite-plugin-css-injected-by-js": "^4.0.1",
"vite-bundle-analyzer": "^1.3.6"
},
"overrides": {
+9 -4
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/core",
"private": false,
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"main": "./dist/esm/page-agent-core.js",
"module": "./dist/esm/page-agent-core.js",
@@ -44,8 +44,13 @@
},
"dependencies": {
"chalk": "^5.6.2",
"zod": "^4.3.5",
"@page-agent/llms": "1.3.0",
"@page-agent/page-controller": "1.3.0"
"@page-agent/llms": "1.5.2",
"@page-agent/page-controller": "1.5.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
},
"devDependencies": {
"zod": "^4.3.5"
}
}
+33 -27
View File
@@ -5,14 +5,13 @@
import { InvokeError, LLM, type Tool } from '@page-agent/llms'
import type { BrowserState, PageController } from '@page-agent/page-controller'
import chalk from 'chalk'
import * as zod from 'zod'
import * as z from 'zod/v4'
import { type PageAgentConfig, type SupportedLanguage } from './config'
import { DEFAULT_MAX_STEPS } from './config/constants'
import SYSTEM_PROMPT from './prompts/system_prompt.md?raw'
import { tools } from './tools'
import type {
AgentActivity,
AgentConfig,
AgentReflection,
AgentStatus,
AgentStepEvent,
@@ -21,13 +20,13 @@ import type {
MacroToolInput,
MacroToolResult,
} from './types'
import { assert, normalizeResponse, uid, waitFor } from './utils'
import { assert, fetchLlmsTxt, normalizeResponse, uid, waitFor } from './utils'
export { type PageAgentConfig }
export type { SupportedLanguage }
export { tool, type PageAgentTool } from './tools'
export type * from './types'
export type PageAgentCoreConfig = AgentConfig & { pageController: PageController }
/**
* AI agent for browser automation.
*
@@ -60,7 +59,7 @@ export type * from './types'
*/
export class PageAgentCore extends EventTarget {
readonly id = uid()
readonly config: PageAgentConfig & { maxSteps: number }
readonly config: PageAgentCoreConfig & { maxSteps: number }
readonly tools: typeof tools
/** PageController for DOM operations */
readonly pageController: PageController
@@ -94,10 +93,10 @@ export class PageAgentCore extends EventTarget {
browserState: null as BrowserState | null,
}
constructor(config: PageAgentConfig & { pageController: PageController }) {
constructor(config: PageAgentCoreConfig) {
super()
this.config = { ...config, maxSteps: config.maxSteps || DEFAULT_MAX_STEPS }
this.config = { ...config, maxSteps: config.maxSteps ?? 40 }
this.#llm = new LLM(this.config)
this.tools = new Map(tools)
@@ -222,6 +221,7 @@ export class PageAgentCore extends EventTarget {
this.history = []
this.#setStatus('running')
this.#emitHistoryChange()
this.#observations = []
// Reset internal states
this.#states = { totalWaitTime: 0, lastURL: '', browserState: null }
@@ -248,16 +248,16 @@ export class PageAgentCore extends EventTarget {
{ role: 'user' as const, content: await this.#assembleUserPrompt() },
]
const tools = { AgentOutput: this.#packMacroTool() }
const macroTool = { AgentOutput: this.#packMacroTool() }
// invoke LLM
console.log(chalk.blue.bold('🧠 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',
normalizeResponse,
normalizeResponse: (res) => normalizeResponse(res, this.tools),
})
// assemble history
@@ -342,6 +342,8 @@ export class PageAgentCore extends EventTarget {
await onAfterTask?.(this, result)
return result
}
await waitFor(0.4) // @TODO: configurable
}
}
@@ -358,24 +360,22 @@ export class PageAgentCore extends EventTarget {
const tools = this.tools
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(
actionSchemas as unknown as [zod.ZodType, zod.ZodType, ...zod.ZodType[]]
)
const actionSchema = z.union(actionSchemas as unknown as [z.ZodType, z.ZodType, ...z.ZodType[]])
const macroToolSchema = zod.object({
// thinking: zod.string().optional(),
evaluation_previous_goal: zod.string().optional(),
memory: zod.string().optional(),
next_goal: zod.string().optional(),
const macroToolSchema = z.object({
// thinking: z.string().optional(),
evaluation_previous_goal: z.string().optional(),
memory: z.string().optional(),
next_goal: z.string().optional(),
action: actionSchema,
})
return {
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> => {
// abort
if (this.#abortController.signal.aborted) throw new Error('AbortError')
@@ -462,14 +462,13 @@ export class PageAgentCore extends EventTarget {
* Get instructions from config
*/
async #getInstructions(): Promise<string> {
const { instructions } = this.config
if (!instructions) return ''
const { instructions, experimentalLlmsTxt } = this.config
const systemInstructions = instructions.system?.trim()
const systemInstructions = instructions?.system?.trim()
let pageInstructions: string | undefined
const url = this.#states.browserState?.url || ''
if (instructions.getPageInstructions && url) {
if (instructions?.getPageInstructions && url) {
try {
pageInstructions = instructions.getPageInstructions(url)?.trim()
} catch (error) {
@@ -479,7 +478,10 @@ export class PageAgentCore extends EventTarget {
)
}
}
if (!systemInstructions && !pageInstructions) return ''
const llmsTxt = experimentalLlmsTxt && url ? await fetchLlmsTxt(url) : undefined
if (!systemInstructions && !pageInstructions && !llmsTxt) return ''
let result = '<instructions>\n'
@@ -491,6 +493,10 @@ export class PageAgentCore extends EventTarget {
result += `<page_instructions>\n${pageInstructions}\n</page_instructions>\n`
}
if (llmsTxt) {
result += `<llms_txt>\n${llmsTxt}\n</llms_txt>\n`
}
result += '</instructions>\n\n'
return result
-1
View File
@@ -1 +0,0 @@
export const DEFAULT_MAX_STEPS = 20
-152
View File
@@ -1,152 +0,0 @@
import type { LLMConfig } from '@page-agent/llms'
import type { PageControllerConfig } from '@page-agent/page-controller'
import type { PageAgentCore } from '../PageAgentCore'
import type { PageAgentTool } from '../tools'
import type { ExecutionResult, HistoricalEvent } from '../types'
export type { LLMConfig }
/** Supported UI languages */
export type SupportedLanguage = 'en-US' | 'zh-CN'
export interface AgentConfig {
// theme?: 'light' | 'dark'
language?: SupportedLanguage
/**
* Maximum number of steps the agent can take per task.
* @default 20
*/
maxSteps?: number
/**
* Custom tools to extend PageAgent capabilities
* @experimental
* @note You can also override or remove internal tools by using the same name.
* @see PageAgentTool
*
* @example
* // override internal tool
* import { tool } from 'page-agent'
* const customTools = {
* ask_user: tool({
* description:
* 'Ask the user or parent model a question and wait for their answer. Use this if you need more information or clarification.',
* inputSchema: zod.object({
* question: zod.string(),
* }),
* execute: async function (this: PageAgent, input) {
* const answer = await do_some_thing(input.question)
* return "✅ Received user answer: " + answer
* },
* })
* }
*
* @example
* // remove internal tool
* const customTools = {
* ask_user: null // never ask user questions
* }
*/
customTools?: Record<string, PageAgentTool | null>
/**
* Instructions to guide the agent's behavior
*/
instructions?: {
/**
* Global system-level instructions, applied to all tasks
*/
system?: string
/**
* Dynamic page-level instructions callback
* Called before each step to get instructions for the current page
* @param url - Current page URL (window.location.href)
* @returns Instructions string, or undefined/null to skip
*/
getPageInstructions?: (url: string) => string | undefined | null
}
/**
* Lifecycle hooks for task execution.
* @experimental API may change in future versions.
*
* All hooks receive the agent instance as first parameter.
*/
/**
* Called before each step execution.
* @experimental
* @param agent - The PageAgentCore instance
* @param stepCount - Current step number (0-indexed)
*/
onBeforeStep?: (agent: PageAgentCore, stepCount: number) => Promise<void> | void
/**
* Called after each step execution.
* @experimental
* @param agent - The PageAgentCore instance
* @param history - Current history of events
*/
onAfterStep?: (agent: PageAgentCore, history: HistoricalEvent[]) => Promise<void> | void
/**
* Called before task execution starts.
* @experimental
* @param agent - The PageAgentCore instance
*/
onBeforeTask?: (agent: PageAgentCore) => Promise<void> | void
/**
* Called after task execution completes (success or failure).
* @experimental
* @param agent - The PageAgentCore instance
* @param result - The execution result
*/
onAfterTask?: (agent: PageAgentCore, result: ExecutionResult) => Promise<void> | void
/**
* Called when the agent is disposed.
* @experimental
* @note This hook can block the disposal process if it's async.
* @param agent - The PageAgentCore instance
* @param reason - Optional reason for disposal
*/
onDispose?: (agent: PageAgentCore, reason?: string) => void
// page behavior hooks
/**
* @experimental
* Enable the experimental script execution tool that allows executing generated JavaScript code on the page.
* @note Can cause unpredictable side effects.
* @note May bypass some safe guards and data-masking mechanisms.
*/
experimentalScriptExecutionTool?: boolean
/**
* Transform page content before sending to LLM.
* Called after DOM extraction and simplification, before LLM invocation.
* Use cases: inspect extraction results, modify page info, mask sensitive data.
*
* @param content - Simplified page content that will be sent to LLM
* @returns Transformed content
*
* @example
* // Mask phone numbers
* transformPageContent: async (content) => {
* return content.replace(/1[3-9]\d{9}/g, '***********')
* }
*/
transformPageContent?: (content: string) => Promise<string> | string
/**
* Completely override the default system prompt.
* @experimental Use with caution - incorrect prompts may break agent behavior.
*/
customSystemPrompt?: string
}
export type PageAgentConfig = LLMConfig & AgentConfig & PageControllerConfig
+28 -28
View File
@@ -2,7 +2,7 @@
* Internal tools for PageAgent.
* @note Adapted from browser-use
*/
import * as zod from 'zod'
import * as z from 'zod/v4'
import type { PageAgentCore } from '../PageAgentCore'
import { waitFor } from '../utils'
@@ -13,7 +13,7 @@ import { waitFor } from '../utils'
export interface PageAgentTool<TParams = any> {
// name: string
description: string
inputSchema: zod.ZodType<TParams>
inputSchema: z.ZodType<TParams>
execute: (this: PageAgentCore, args: TParams) => Promise<string>
}
@@ -32,9 +32,9 @@ tools.set(
tool({
description:
'Complete task. Text is your final response to the user — keep it concise unless the user explicitly asks for detail.',
inputSchema: zod.object({
text: zod.string(),
success: zod.boolean().default(true),
inputSchema: z.object({
text: z.string(),
success: z.boolean().default(true),
}),
execute: async function (this: PageAgentCore, input) {
// @note main loop will handle this one
@@ -47,8 +47,8 @@ tools.set(
'wait',
tool({
description: 'Wait for x seconds. Can be used to wait until the page or data is fully loaded.',
inputSchema: zod.object({
seconds: zod.number().min(1).max(10).default(1),
inputSchema: z.object({
seconds: z.number().min(1).max(10).default(1),
}),
execute: async function (this: PageAgentCore, input) {
// try to subtract LLM calling time from the actual wait time
@@ -67,8 +67,8 @@ tools.set(
tool({
description:
'Ask the user a question and wait for their answer. Use this if you need more information or clarification.',
inputSchema: zod.object({
question: zod.string(),
inputSchema: z.object({
question: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
if (!this.onAskUser) {
@@ -84,8 +84,8 @@ tools.set(
'click_element_by_index',
tool({
description: 'Click element by index',
inputSchema: zod.object({
index: zod.int().min(0),
inputSchema: z.object({
index: z.int().min(0),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.clickElement(input.index)
@@ -98,9 +98,9 @@ tools.set(
'input_text',
tool({
description: 'Click and type text into an interactive input element',
inputSchema: zod.object({
index: zod.int().min(0),
text: zod.string(),
inputSchema: z.object({
index: z.int().min(0),
text: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.inputText(input.index, input.text)
@@ -114,9 +114,9 @@ tools.set(
tool({
description:
'Select dropdown option for interactive element index by the text of the option you want to select',
inputSchema: zod.object({
index: zod.int().min(0),
text: zod.string(),
inputSchema: z.object({
index: z.int().min(0),
text: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.selectOption(input.index, input.text)
@@ -132,11 +132,11 @@ tools.set(
'scroll',
tool({
description: 'Scroll the page vertically. Use index for scroll elements (dropdowns/custom UI).',
inputSchema: zod.object({
down: zod.boolean().default(true),
num_pages: zod.number().min(0).max(10).optional().default(0.1),
pixels: zod.number().int().min(0).optional(),
index: zod.number().int().min(0).optional(),
inputSchema: z.object({
down: z.boolean().default(true),
num_pages: z.number().min(0).max(10).optional().default(0.1),
pixels: z.number().int().min(0).optional(),
index: z.number().int().min(0).optional(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.scroll({
@@ -156,10 +156,10 @@ tools.set(
tool({
description:
'Scroll the page horizontally, or within a specific element by index. Useful for wide tables.',
inputSchema: zod.object({
right: zod.boolean().default(true),
pixels: zod.number().int().min(0),
index: zod.number().int().min(0).optional(),
inputSchema: z.object({
right: z.boolean().default(true),
pixels: z.number().int().min(0),
index: z.number().int().min(0).optional(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.scrollHorizontally(input)
@@ -173,8 +173,8 @@ tools.set(
tool({
description:
'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution!',
inputSchema: zod.object({
script: zod.string(),
inputSchema: z.object({
script: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.executeJavascript(input.script)
+156
View File
@@ -1,3 +1,159 @@
import type { LLMConfig } from '@page-agent/llms'
// @note circular dependency but okay
import type { PageAgentCore } from './PageAgentCore'
import type { PageAgentTool } from './tools'
/** Supported UI languages */
export type SupportedLanguage = 'en-US' | 'zh-CN'
export interface AgentConfig extends LLMConfig {
language?: SupportedLanguage
/**
* Maximum number of steps the agent can take per task.
* @default 40
*/
maxSteps?: number
/**
* Custom tools to extend PageAgent capabilities
* @experimental
* @note You can also override or remove internal tools by using the same name.
* @see PageAgentTool
*
* @example
* // override internal tool
* import { z } from 'zod/v4'
* import { tool } from 'page-agent'
* const customTools = {
* ask_user: tool({
* description:
* 'Ask the user or parent model a question and wait for their answer. Use this if you need more information or clarification.',
* inputSchema: z.object({
* question: z.string(),
* }),
* execute: async function (this: PageAgent, input) {
* const answer = await do_some_thing(input.question)
* return "✅ Received user answer: " + answer
* },
* })
* }
*
* @example
* // remove internal tool
* const customTools = {
* ask_user: null // never ask user questions
* }
*/
customTools?: Record<string, PageAgentTool | null>
/**
* Instructions to guide the agent's behavior
*/
instructions?: {
/**
* Global system-level instructions, applied to all tasks
*/
system?: string
/**
* Dynamic page-level instructions callback
* Called before each step to get instructions for the current page
* @param url - Current page URL (window.location.href)
* @returns Instructions string, or undefined/null to skip
*/
getPageInstructions?: (url: string) => string | undefined | null
}
/**
* Lifecycle hooks for task execution.
* @experimental API may change in future versions.
*
* All hooks receive the agent instance as first parameter.
*/
/**
* Called before each step execution.
* @experimental
* @param agent - The PageAgentCore instance
* @param stepCount - Current step number (0-indexed)
*/
onBeforeStep?: (agent: PageAgentCore, stepCount: number) => Promise<void> | void
/**
* Called after each step execution.
* @experimental
* @param agent - The PageAgentCore instance
* @param history - Current history of events
*/
onAfterStep?: (agent: PageAgentCore, history: HistoricalEvent[]) => Promise<void> | void
/**
* Called before task execution starts.
* @experimental
* @param agent - The PageAgentCore instance
*/
onBeforeTask?: (agent: PageAgentCore) => Promise<void> | void
/**
* Called after task execution completes (success or failure).
* @experimental
* @param agent - The PageAgentCore instance
* @param result - The execution result
*/
onAfterTask?: (agent: PageAgentCore, result: ExecutionResult) => Promise<void> | void
/**
* Called when the agent is disposed.
* @experimental
* @note This hook can block the disposal process if it's async.
* @param agent - The PageAgentCore instance
* @param reason - Optional reason for disposal
*/
onDispose?: (agent: PageAgentCore, reason?: string) => void
// page behavior hooks
/**
* @experimental
* Enable the experimental script execution tool that allows executing generated JavaScript code on the page.
* @note Can cause unpredictable side effects.
* @note May bypass some safe guards and data-masking mechanisms.
*/
experimentalScriptExecutionTool?: boolean
/**
* @experimental
* Fetch /llms.txt from current site origin and include as context.
* Only fetched once per origin per task.
* @default false
*/
experimentalLlmsTxt?: boolean
/**
* Transform page content before sending to LLM.
* Called after DOM extraction and simplification, before LLM invocation.
* Use cases: inspect extraction results, modify page info, mask sensitive data.
*
* @param content - Simplified page content that will be sent to LLM
* @returns Transformed content
*
* @example
* // Mask phone numbers
* transformPageContent: async (content) => {
* return content.replace(/1[3-9]\d{9}/g, '***********')
* }
*/
transformPageContent?: (content: string) => Promise<string> | string
/**
* Completely override the default system prompt.
* @experimental Use with caution - incorrect prompts may break agent behavior.
*/
customSystemPrompt?: string
}
/**
* Agent reflection state - the reflection-before-action model
*
+65 -6
View File
@@ -1,4 +1,10 @@
import { InvokeError, InvokeErrorType } from '@page-agent/llms'
import chalk from 'chalk'
import * as z from 'zod/v4'
import type { PageAgentTool } from '../tools'
const log = console.log.bind(console, chalk.yellow('[autoFixer]'))
/**
* Normalize LLM response and fix common format issues.
@@ -9,9 +15,10 @@ import chalk from 'chalk'
* - Arguments wrapped as double JSON string
* - Nested function call format
* - Missing action field (fallback to wait)
* - Primitive action input for single-field tools (e.g. `{"click_element_by_index": 2}`)
* - etc.
*/
export function normalizeResponse(response: any): any {
export function normalizeResponse(response: any, tools?: Map<string, PageAgentTool>): any {
let resolvedArguments = null as any
const choice = (response as { choices?: Choice[] }).choices?.[0]
@@ -29,7 +36,7 @@ export function normalizeResponse(response: any): any {
// case: sometimes the model only returns the action level
if (toolCall.function.name && toolCall.function.name !== 'AgentOutput') {
console.log(chalk.yellow(`[normalizeResponse] #1: fixing tool_call`))
log(`#1: fixing tool_call`)
resolvedArguments = { action: safeJsonParse(resolvedArguments) }
}
} else {
@@ -42,13 +49,13 @@ export function normalizeResponse(response: any): any {
// case: sometimes the content json includes upper level wrapper
if (resolvedArguments?.name === 'AgentOutput') {
console.log(chalk.yellow(`[normalizeResponse] #2: fixing tool_call`))
log(`#2: fixing tool_call`)
resolvedArguments = safeJsonParse(resolvedArguments.arguments)
}
// case: sometimes even 2-levels of wrapping
if (resolvedArguments?.type === 'function') {
console.log(chalk.yellow(`[normalizeResponse] #3: fixing tool_call`))
log(`#3: fixing tool_call`)
resolvedArguments = safeJsonParse(resolvedArguments.function.arguments)
}
@@ -61,7 +68,7 @@ export function normalizeResponse(response: any): any {
!resolvedArguments?.next_goal &&
!resolvedArguments?.thinking
) {
console.log(chalk.yellow(`[normalizeResponse] #4: fixing tool_call`))
log(`#4: fixing tool_call`)
resolvedArguments = { action: safeJsonParse(resolvedArguments) }
}
} else {
@@ -78,9 +85,14 @@ export function normalizeResponse(response: any): any {
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
if (!resolvedArguments.action) {
console.log(chalk.yellow(`[normalizeResponse] #5: fixing tool_call`))
log(`#5: fixing tool_call`)
resolvedArguments.action = { name: 'wait', input: { seconds: 1 } }
}
@@ -108,6 +120,53 @@ 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: ${available}`
)
}
let value = action[toolName]
const schema = tool.inputSchema
// coerce primitive input for single-field tools
if (schema instanceof z.ZodObject && value !== null && typeof value !== 'object') {
const requiredKey = Object.keys(schema.shape).find(
(k) => !(schema.shape as Record<string, z.ZodType>)[k].safeParse(undefined).success
)
if (requiredKey) {
log(`coercing primitive action input for "${toolName}"`)
value = { [requiredKey]: value }
}
}
const result = schema.safeParse(value)
if (!result.success) {
throw new InvokeError(
InvokeErrorType.INVALID_TOOL_ARGS,
`Invalid input for action "${toolName}": ${z.prettifyError(result.error)}`
)
}
return { [toolName]: result.data }
}
/**
* Safely parse JSON, return original input if not json.
*/
+30 -1
View File
@@ -1,6 +1,6 @@
import chalk from 'chalk'
export { normalizeResponse } from './autoFixer'
export * from './autoFixer'
export async function waitFor(seconds: number): Promise<void> {
await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
@@ -57,6 +57,35 @@ export function uid() {
return id
}
const llmsTxtCache = new Map<string, string | null>()
/** Fetch /llms.txt for a URL's origin. Cached per origin, `null` = tried and not found. */
export async function fetchLlmsTxt(url: string): Promise<string | null> {
const origin = new URL(url).origin
if (llmsTxtCache.has(origin)) return llmsTxtCache.get(origin)!
const endpoint = `${origin}/llms.txt`
let result: string | null = null
try {
console.log(chalk.gray(`[llms.txt] Fetching ${endpoint}`))
const res = await fetch(endpoint, { signal: AbortSignal.timeout(3000) })
if (res.ok) {
result = await res.text()
console.log(chalk.green(`[llms.txt] Found (${result.length} chars)`))
if (result.length > 1000) {
console.log(chalk.yellow(`[llms.txt] Truncating to 1000 chars`))
result = truncate(result, 1000)
}
} else {
console.debug(chalk.gray(`[llms.txt] ${res.status} for ${endpoint}`))
}
} catch (e) {
console.debug(chalk.gray(`[llms.txt] not found for ${endpoint}`), e)
}
llmsTxtCache.set(origin, result)
return result
}
/**
* Simple assertion function that throws an error if the condition is falsy
* @param condition - The condition to assert
+1
View File
@@ -30,6 +30,7 @@ export default defineConfig({
external: [
'chalk',
'zod',
'zod/v4',
// all the internal packages
/^@page-agent\//,
],
+2 -57
View File
@@ -1,60 +1,5 @@
# Privacy Policy for Page Agent Extension
**Last updated:** February 2026
This document has moved. Please see our full **[Terms of Use & Privacy](../../docs/terms-and-privacy.md)**.
## Overview
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 developer.
### Data Transmission
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 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
- The free model and their service providers may change at any time without prior notice
- We do **not** store your task content, page content, or visited URLs
- Minimal logging (timestamps, request metadata, IP addresses) may be collected 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
Online: https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md
-30
View File
@@ -1,30 +0,0 @@
AI-powered browser automation. Control web pages with natural language.
Page Agent Ext — AI-Powered Browser Automation
🌟 What is Page Agent Ext?
Page Agent Ext brings AI-powered automation to your browser. Built on the open-source Page Agent framework, it lets you control web pages across multiple tabs using natural language — no scripting required.
🌟 Key Features:
- Natural Language Control — Command your browser in plain language, no code needed
- Cross-Tab Automation — Seamlessly operate across multiple tabs and pages
- Smart HTML Cleaning — Intelligently extracts and simplifies page structure for accurate AI understanding
- Bring Your Own LLM — Use OpenAI, Anthropic, or any compatible API with full data control
- Privacy-First — Zero data collection; all data flows directly to your chosen LLM provider
- Open Source — MIT licensed, built on the Page Agent framework with full transparency
🌟 How It Works & Privacy:
Page Agent Ext performs DOM analysis locally in your browser. When you initiate a task, sanitized page structure is sent to the LLM API you configure. Your data is never collected or stored by us.
- Your API Key — Configure your own LLM API (OpenAI, Anthropic, etc.). Data goes directly to your provider
- Test API — A free test endpoint is available for evaluation; we recommend your own key for regular use
Privacy policy: https://github.com/alibaba/page-agent/blob/main/packages/extension/PRIVACY.md
🌟 Open Source:
This project is MIT licensed. Review the code, verify privacy claims, or extend it for your needs:
https://github.com/alibaba/page-agent
@@ -1,30 +0,0 @@
AI 驱动的浏览器自动化助手,用自然语言控制网页。
Page Agent Ext — AI 驱动的浏览器自动化助手
🌟 什么是 Page Agent Ext
Page Agent Ext 为浏览器带来 AI 自动化能力。基于开源的 Page Agent 框架,你可以用自然语言跨标签页控制网页,无需编写任何脚本。
🌟 核心特性:
- 自然语言控制 — 用日常语言指挥浏览器,无需编程
- 跨标签页操作 — 在多个标签页之间无缝切换和操控
- HTML 智能清洗 — 智能提取和精简页面结构,让 AI 准确理解网页内容
- 使用你自己的模型 — 支持 OpenAI、Anthropic 或任何兼容 API,数据完全自主可控
- 隐私优先 — 零数据收集,所有数据直接发送到你配置的 LLM 服务商
- 开源透明 — MIT 协议,基于 Page Agent 开源框架,代码完全公开
🌟 工作原理与隐私:
Page Agent Ext 在浏览器本地进行 DOM 分析。当你发起任务时,经清洗的页面结构会发送到你配置的 LLM API。我们不会收集或存储你的任何数据。
- 你的 API Key — 配置你自己的 LLM APIOpenAI、Anthropic 等),数据直接发送到你的服务商
- 测试 API — 提供免费测试端点供体验,日常使用建议配置自己的 Key
隐私政策:https://github.com/alibaba/page-agent/blob/main/packages/extension/PRIVACY.md
🌟 开源项目:
MIT 协议开源。查看源码、验证隐私承诺,或按需扩展:
https://github.com/alibaba/page-agent
+16 -14
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/ext",
"private": true,
"version": "0.1.7",
"version": "0.1.11",
"type": "module",
"scripts": {
"dev": "wxt",
@@ -17,33 +17,35 @@
"@radix-ui/react-slot": "^1.2.4",
"@radix-ui/react-switch": "^1.2.6",
"@radix-ui/react-tooltip": "^1.2.8",
"@types/chrome": "^0.1.34",
"@types/react": "^19.2.13",
"@types/chrome": "^0.1.37",
"@types/react": "^19.2.14",
"@types/react-dom": "^19.2.1",
"@wxt-dev/module-react": "^1.1.5",
"class-variance-authority": "^0.7.1",
"clsx": "^2.1.1",
"idb": "^8.0.3",
"lucide-react": "^0.563.0",
"motion": "^12.34.0",
"lucide-react": "^0.576.0",
"motion": "^12.34.5",
"next-themes": "^0.4.6",
"react": "^19.2.4",
"react-dom": "^19.2.4",
"rough-notation": "^0.5.1",
"simple-icons": "^16.8.0",
"simple-icons": "^16.10.0",
"sonner": "^2.0.7",
"tailwind-merge": "^3.4.0",
"tailwind-merge": "^3.5.0",
"tailwindcss": "^4.1.14",
"tw-animate-css": "^1.4.0",
"wxt": "^0.20.14"
"wxt": "^0.20.18"
},
"dependencies": {
"@page-agent/core": "1.3.0",
"@page-agent/llms": "1.3.0",
"@page-agent/page-controller": "1.3.0",
"@page-agent/ui": "1.3.0",
"@page-agent/core": "1.5.2",
"@page-agent/llms": "1.5.2",
"@page-agent/page-controller": "1.5.2",
"@page-agent/ui": "1.5.2",
"ai-motion": "^0.4.8",
"chalk": "^5.6.2",
"zod": "^4.3.5"
"chalk": "^5.6.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
}
}
@@ -1,4 +1,4 @@
import { type PageAgentConfig, PageAgentCore } from '@page-agent/core'
import { type AgentConfig, PageAgentCore } from '@page-agent/core'
import { RemotePageController } from './RemotePageController'
import { TabsController } from './TabsController'
@@ -17,7 +17,7 @@ function detectLanguage(): 'en-US' | 'zh-CN' {
* - can be used from a side panel or a content script
*/
export class MultiPageAgent extends PageAgentCore {
constructor(config: Omit<PageAgentConfig, 'pageController'> & { includeInitialTab?: boolean }) {
constructor(config: AgentConfig & { includeInitialTab?: boolean }) {
// multi page controller
const tabsController = new TabsController()
const pageController = new RemotePageController(tabsController)
+21 -4
View File
@@ -1,13 +1,30 @@
import type { LLMConfig } from '@page-agent/llms'
// Demo LLM for testing
export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
export const DEMO_BASE_URL =
'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
export const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
export const DEMO_MODEL = 'qwen3.5-plus'
export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
export const DEMO_API_KEY = 'NA'
export const DEMO_CONFIG: LLMConfig = {
apiKey: DEMO_API_KEY,
baseURL: DEMO_BASE_URL,
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
* - close_tab: Close a tab (optionally switch to another)
*/
import * as zod from 'zod'
import * as z from 'zod/v4'
import type { TabsController } from './TabsController'
/** Tool definition compatible with PageAgentCore customTools */
interface TabTool {
description: string
inputSchema: zod.ZodType
inputSchema: z.ZodType
execute: (input: unknown) => Promise<string>
}
@@ -26,8 +26,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
open_new_tab: {
description:
'Open a new browser tab with the specified URL. The new tab becomes the current tab for all subsequent page operations.',
inputSchema: zod.object({
url: zod.string().describe('The URL to open in the new tab'),
inputSchema: z.object({
url: z.string().describe('The URL to open in the new tab'),
}),
execute: async (input: unknown) => {
const { url } = input as { url: string }
@@ -42,8 +42,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
switch_to_tab: {
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.',
inputSchema: zod.object({
tab_id: zod.number().int().describe('The tab ID to switch to'),
inputSchema: z.object({
tab_id: z.number().int().describe('The tab ID to switch to'),
}),
execute: async (input: unknown) => {
const { tab_id } = input as { tab_id: number }
@@ -58,8 +58,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
close_tab: {
description:
'Close a tab by its ID. Cannot close the initial tab. Optionally specify which tab to switch to after closing.',
inputSchema: zod.object({
tab_id: zod.number().int().describe('The tab ID to close'),
inputSchema: z.object({
tab_id: z.number().int().describe('The tab ID to close'),
}),
execute: async (input: unknown) => {
const { tab_id } = input as { tab_id: number }
+45 -17
View File
@@ -11,12 +11,18 @@ import type { LLMConfig } from '@page-agent/llms'
import { useCallback, useEffect, useRef, useState } from 'react'
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 {
export interface AdvancedConfig {
maxSteps?: number
systemInstruction?: string
experimentalLlmsTxt?: boolean
}
export interface ExtConfig extends LLMConfig, AdvancedConfig {
language?: LanguagePreference
}
@@ -40,21 +46,32 @@ export function useAgent(): UseAgentResult {
const [config, setConfig] = useState<ExtConfig | null>(null)
useEffect(() => {
chrome.storage.local.get(['llmConfig', 'language']).then((result) => {
const llmConfig = (result.llmConfig as LLMConfig) ?? DEMO_CONFIG
chrome.storage.local.get(['llmConfig', 'language', 'advancedConfig']).then((result) => {
let llmConfig = (result.llmConfig as LLMConfig) ?? DEMO_CONFIG
const language = (result.language as SupportedLanguage) || undefined
const full = { ...llmConfig, language }
if (!result.llmConfig) {
const advancedConfig = (result.advancedConfig as AdvancedConfig) ?? {}
// 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 })
}
setConfig(full)
setConfig({ ...llmConfig, ...advancedConfig, language })
})
}, [])
useEffect(() => {
if (!config) return
const agent = new MultiPageAgent(config)
const { systemInstruction, ...agentConfig } = config
const agent = new MultiPageAgent({
...agentConfig,
instructions: systemInstruction ? { system: systemInstruction } : undefined,
})
agentRef.current = agent
const handleStatusChange = (e: Event) => {
@@ -100,15 +117,26 @@ export function useAgent(): UseAgentResult {
agentRef.current?.stop()
}, [])
const configure = useCallback(async ({ language, ...llmConfig }: ExtConfig) => {
await chrome.storage.local.set({ llmConfig })
if (language) {
await chrome.storage.local.set({ language })
} else {
await chrome.storage.local.remove('language')
}
setConfig({ ...llmConfig, language })
}, [])
const configure = useCallback(
async ({
language,
maxSteps,
systemInstruction,
experimentalLlmsTxt,
...llmConfig
}: ExtConfig) => {
await chrome.storage.local.set({ llmConfig })
if (language) {
await chrome.storage.local.set({ language })
} else {
await chrome.storage.local.remove('language')
}
const advancedConfig: AdvancedConfig = { maxSteps, systemInstruction, experimentalLlmsTxt }
await chrome.storage.local.set({ advancedConfig })
setConfig({ ...llmConfig, ...advancedConfig, language })
},
[]
)
return {
status,
@@ -1,11 +1,22 @@
import { Copy, CornerUpLeft, Eye, EyeOff, HatGlasses, Home, Loader2, Scale } from 'lucide-react'
import {
ChevronDown,
Copy,
CornerUpLeft,
Eye,
EyeOff,
HatGlasses,
Home,
Loader2,
Scale,
} from 'lucide-react'
import { useEffect, useState } from 'react'
import { siGithub } from 'simple-icons'
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 { Input } from '@/components/ui/input'
import { Switch } from '@/components/ui/switch'
interface ConfigPanelProps {
config: ExtConfig | null
@@ -18,18 +29,26 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const [baseURL, setBaseURL] = useState(config?.baseURL || DEMO_BASE_URL)
const [model, setModel] = useState(config?.model || DEMO_MODEL)
const [language, setLanguage] = useState<LanguagePreference>(config?.language)
const [maxSteps, setMaxSteps] = useState<number | undefined>(config?.maxSteps)
const [systemInstruction, setSystemInstruction] = useState(config?.systemInstruction ?? '')
const [experimentalLlmsTxt, setExperimentalLlmsTxt] = useState(
config?.experimentalLlmsTxt ?? false
)
const [advancedOpen, setAdvancedOpen] = useState(false)
const [saving, setSaving] = useState(false)
const [userAuthToken, setUserAuthToken] = useState<string>('')
const [copied, setCopied] = useState(false)
const [showToken, setShowToken] = useState(false)
const [showApiKey, setShowApiKey] = useState(false)
// Update local state when config prop changes
useEffect(() => {
setApiKey(config?.apiKey || DEMO_API_KEY)
setBaseURL(config?.baseURL || DEMO_BASE_URL)
setModel(config?.model || DEMO_MODEL)
setLanguage(config?.language)
setMaxSteps(config?.maxSteps)
setSystemInstruction(config?.systemInstruction ?? '')
setExperimentalLlmsTxt(config?.experimentalLlmsTxt ?? false)
}, [config])
// Poll for user auth token every second until found
@@ -67,7 +86,15 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
const handleSave = async () => {
setSaving(true)
try {
await onSave({ apiKey, baseURL, model, language })
await onSave({
apiKey,
baseURL,
model,
language,
maxSteps: maxSteps || undefined,
systemInstruction: systemInstruction || undefined,
experimentalLlmsTxt,
})
} finally {
setSaving(false)
}
@@ -91,7 +118,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
<div className="flex flex-col gap-1.5 p-3 bg-muted/50 rounded-md border">
<label className="text-xs font-medium text-muted-foreground">User Auth Token</label>
<p className="text-[10px] text-muted-foreground mb-1">
Add this token to a website's localStorage to give it authorization to call this extension
Give a website the ability to call this extension.
</p>
<div className="flex gap-2 items-center">
<Input
@@ -136,6 +163,23 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
/>
</div>
{/* Testing API notice */}
{isTestingEndpoint(baseURL) && (
<div className="p-2.5 rounded-md border border-amber-500/30 bg-amber-500/5 text-[11px] text-muted-foreground leading-relaxed">
<Scale className="size-3 inline-block mr-1 -mt-0.5 text-amber-600" />
You are using the free testing API. By using this service you agree to the{' '}
<a
href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
target="_blank"
rel="noopener noreferrer"
className="underline hover:text-foreground"
>
Terms of Use & Privacy Policy
</a>
. No sensitive data. No guaranteed availability.
</div>
)}
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Model</label>
<Input
@@ -180,6 +224,52 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</select>
</div>
{/* Advanced Config */}
<button
type="button"
onClick={() => setAdvancedOpen(!advancedOpen)}
className="flex items-center gap-1 text-xs text-muted-foreground hover:text-foreground cursor-pointer mt-1 font-bold"
>
Advanced
<ChevronDown
className="size-3 transition-transform"
style={{ transform: advancedOpen ? 'rotate(0deg)' : 'rotate(90deg)' }}
/>
</button>
{advancedOpen && (
<>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">Max Steps</label>
<Input
type="number"
placeholder="40"
min={1}
max={200}
value={maxSteps ?? ''}
onChange={(e) => setMaxSteps(e.target.value ? Number(e.target.value) : undefined)}
className="text-xs h-8 [&::-webkit-inner-spin-button]:appearance-none [&::-webkit-outer-spin-button]:appearance-none [-moz-appearance:textfield]"
/>
</div>
<div className="flex flex-col gap-1.5">
<label className="text-xs text-muted-foreground">System Instruction</label>
<textarea
placeholder="Additional instructions for the agent..."
value={systemInstruction}
onChange={(e) => setSystemInstruction(e.target.value)}
rows={3}
className="text-xs rounded-md border border-input bg-background px-3 py-2 resize-y min-h-[60px]"
/>
</div>
<label className="flex items-center justify-between cursor-pointer">
<span className="text-xs text-muted-foreground">Experimental llms.txt support</span>
<Switch checked={experimentalLlmsTxt} onCheckedChange={setExperimentalLlmsTxt} />
</label>
</>
)}
<div className="flex gap-2 mt-2">
<Button variant="outline" onClick={onClose} className="flex-1 h-8 text-xs cursor-pointer">
Cancel
@@ -219,7 +309,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
</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"
rel="noopener noreferrer"
className="flex items-center gap-1 hover:text-foreground"
@@ -43,20 +43,24 @@ export function MotionOverlay({ active }: { active: boolean }) {
const motionRef = useRef<Motion | null>(null)
useEffect(() => {
const mode = document.documentElement.classList.contains('dark') ? 'dark' : 'light'
const motion = new Motion({
mode,
borderWidth: 4,
borderRadius: 14,
glowWidth: mode === 'dark' ? 120 : 60,
styles: { position: 'absolute', inset: '0' },
})
motionRef.current = motion
containerRef.current!.appendChild(motion.element)
motion.autoResize(containerRef.current!)
try {
const mode = document.documentElement.classList.contains('dark') ? 'dark' : 'light'
const motion = new Motion({
mode,
borderWidth: 4,
borderRadius: 14,
glowWidth: mode === 'dark' ? 120 : 60,
styles: { position: 'absolute', inset: '0' },
})
motionRef.current = motion
containerRef.current!.appendChild(motion.element)
motion.autoResize(containerRef.current!)
} catch (e) {
console.warn('[MotionOverlay] Motion unavailable:', e)
}
return () => {
motion.dispose()
motionRef.current?.dispose()
motionRef.current = null
}
}, [])
@@ -125,7 +129,7 @@ export function EmptyState() {
</svg>
</a>
<a
href="https://alibaba.github.io/page-agent/#/docs/features/chrome-extension"
href="https://alibaba.github.io/page-agent/docs/features/chrome-extension"
target="_blank"
rel="noopener noreferrer"
className="hover:text-foreground transition-colors"
+7 -2
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/llms",
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"main": "./dist/lib/page-agent-llms.js",
"module": "./dist/lib/page-agent-llms.js",
@@ -37,7 +37,12 @@
"postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
},
"dependencies": {
"chalk": "^5.6.2",
"chalk": "^5.6.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
},
"devDependencies": {
"zod": "^4.3.5"
}
}
+3 -1
View File
@@ -1,6 +1,8 @@
/**
* OpenAI Client implementation
*/
import * as z from 'zod/v4'
import { InvokeError, InvokeErrorType } from './errors'
import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
import { modelPatch, zodToOpenAITool } from './utils'
@@ -182,7 +184,7 @@ export class OpenAIClient implements LLMClient {
// Validate with schema
const validation = tool.inputSchema.safeParse(parsedArgs)
if (!validation.success) {
console.error(validation.error)
console.error(z.prettifyError(validation.error))
throw new InvokeError(
InvokeErrorType.INVALID_TOOL_ARGS,
'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 { 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'
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> {
// Runtime validation as defensive programming (types already guarantee these)
if (!config.baseURL || !config.apiKey || !config.model) {
throw new Error(
'[PageAgent] LLM configuration required. Please provide: baseURL, apiKey, model. ' +
'See: https://alibaba.github.io/page-agent/#/docs/features/models'
'See: https://alibaba.github.io/page-agent/docs/features/models'
)
}
+1 -1
View File
@@ -1,7 +1,7 @@
/**
* Core types for LLM integration
*/
import type { z } from 'zod'
import type * as z from 'zod/v4'
/**
* Message format - OpenAI standard (industry standard)
+3 -4
View File
@@ -2,13 +2,11 @@
* Utility functions for LLM integration
*/
import chalk from 'chalk'
import * as z from 'zod'
import * as z from 'zod/v4'
import type { Tool } from './types'
function debug(message: string) {
console.debug(chalk.gray('[LLM]'), message)
}
const debug = console.debug.bind(console, chalk.gray('[LLM]'))
/**
* Convert Zod schema to OpenAI tool format
@@ -38,6 +36,7 @@ export function modelPatch(body: Record<string, any>) {
if (modelName.startsWith('qwen')) {
debug('Applying Qwen patch: use higher temperature for auto fixing')
body.temperature = Math.max(body.temperature || 0, 1.0)
body.enable_thinking = false
}
if (modelName.startsWith('claude')) {
+1 -1
View File
@@ -25,7 +25,7 @@ export default defineConfig({
},
outDir: resolve(__dirname, 'dist', 'lib'),
rollupOptions: {
external: ['chalk', 'zod'],
external: ['chalk', 'zod', 'zod/v4'],
},
minify: false,
sourcemap: true,
+11 -6
View File
@@ -1,7 +1,7 @@
{
"name": "page-agent",
"private": false,
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"main": "./dist/esm/page-agent.js",
"module": "./dist/esm/page-agent.js",
@@ -44,11 +44,16 @@
"postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
},
"dependencies": {
"@page-agent/core": "1.3.0",
"@page-agent/llms": "1.3.0",
"@page-agent/page-controller": "1.3.0",
"@page-agent/ui": "1.3.0",
"chalk": "^5.6.2",
"@page-agent/core": "1.5.2",
"@page-agent/llms": "1.5.2",
"@page-agent/page-controller": "1.5.2",
"@page-agent/ui": "1.5.2",
"chalk": "^5.6.2"
},
"peerDependencies": {
"zod": "^3.25.0 || ^4.0.0"
},
"devDependencies": {
"zod": "^4.3.5"
}
}
+5 -4
View File
@@ -2,12 +2,13 @@
* Copyright (C) 2025 Alibaba Group Holding Limited
* All rights reserved.
*/
import { type PageAgentConfig, PageAgentCore, type PageAgentTool, tool } from '@page-agent/core'
import { PageController } from '@page-agent/page-controller'
import { type AgentConfig, PageAgentCore } from '@page-agent/core'
import { PageController, type PageControllerConfig } from '@page-agent/page-controller'
import { Panel } from '@page-agent/ui'
export type { PageAgentConfig, PageAgentTool }
export { tool }
export * from '@page-agent/core'
export type PageAgentConfig = AgentConfig & PageControllerConfig
export class PageAgent extends PageAgentCore {
panel: Panel
+3 -3
View File
@@ -13,9 +13,9 @@ window.PageAgent = PageAgent
console.log('🚀 page-agent.js loaded!')
const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
const DEMO_BASE_URL = 'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
const DEMO_MODEL = 'qwen3.5-plus'
const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
const DEMO_API_KEY = 'NA'
// in case document.x is not ready yet
setTimeout(() => {
+1
View File
@@ -30,6 +30,7 @@ export default defineConfig({
external: [
'chalk',
'zod',
'zod/v4',
// all the internal packages
/^@page-agent\//,
],
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/page-controller",
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"main": "./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
// 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
@@ -181,11 +181,6 @@ export async function scrollVertically(
// Element-specific scrolling if element is provided
if (element) {
const targetElement = element
console.log(
'[SCROLL DEBUG] Starting direct container scroll for element:',
targetElement.tagName
)
let currentElement = targetElement as HTMLElement | null
let scrollSuccess = false
let scrolledElement: HTMLElement | null = null
@@ -198,19 +193,6 @@ export async function scrollVertically(
const hasScrollableY = /(auto|scroll|overlay)/.test(computedStyle.overflowY)
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) {
const beforeScroll = currentElement.scrollTop
const maxScroll = currentElement.scrollHeight - currentElement.clientHeight
@@ -228,27 +210,10 @@ export async function scrollVertically(
const afterScroll = currentElement.scrollTop
const actualScrollDelta = afterScroll - beforeScroll
console.log(
'[SCROLL DEBUG] Scroll attempt:',
currentElement.tagName,
'before:',
beforeScroll,
'after:',
afterScroll,
'delta:',
actualScrollDelta
)
if (Math.abs(actualScrollDelta) > 0.5) {
scrollSuccess = true
scrolledElement = currentElement
scrollDelta = actualScrollDelta
console.log(
'[SCROLL DEBUG] Successfully scrolled container:',
currentElement.tagName,
'delta:',
actualScrollDelta
)
break
}
}
@@ -344,11 +309,6 @@ export async function scrollHorizontally(
// Element-specific scrolling if element is provided
if (element) {
const targetElement = element
console.log(
'[SCROLL DEBUG] Starting direct container scroll for element:',
targetElement.tagName
)
let currentElement = targetElement as HTMLElement | null
let scrollSuccess = false
let scrolledElement: HTMLElement | null = null
@@ -361,19 +321,6 @@ export async function scrollHorizontally(
const hasScrollableX = /(auto|scroll|overlay)/.test(computedStyle.overflowX)
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) {
const beforeScroll = currentElement.scrollLeft
const maxScroll = currentElement.scrollWidth - currentElement.clientWidth
@@ -391,27 +338,10 @@ export async function scrollHorizontally(
const afterScroll = currentElement.scrollLeft
const actualScrollDelta = afterScroll - beforeScroll
console.log(
'[SCROLL DEBUG] Scroll attempt:',
currentElement.tagName,
'before:',
beforeScroll,
'after:',
afterScroll,
'delta:',
actualScrollDelta
)
if (Math.abs(actualScrollDelta) > 0.5) {
scrollSuccess = true
scrolledElement = currentElement
scrollDelta = actualScrollDelta
console.log(
'[SCROLL DEBUG] Successfully scrolled container:',
currentElement.tagName,
'delta:',
actualScrollDelta
)
break
}
}
@@ -1446,7 +1446,7 @@ export default (
/**
* @edit add `data-browser-use-ignore` attribute
*/
if (node.dataset?.browserUseIgnore === 'true') {
if (node.dataset?.browserUseIgnore === 'true' || node.dataset?.pageAgentIgnore === 'true') {
return null // Skip this node and its children
}
@@ -8,13 +8,7 @@ import cursorStyles from './cursor.module.css'
export class SimulatorMask {
shown: boolean = false
wrapper = document.createElement('div')
motion = new Motion({
mode: isPageDark() ? 'dark' : 'light',
styles: {
position: 'absolute',
inset: '0',
},
})
motion: Motion | null = null
#cursor = document.createElement('div')
@@ -28,9 +22,19 @@ export class SimulatorMask {
this.wrapper.id = 'page-agent-runtime_simulator-mask'
this.wrapper.className = styles.wrapper
this.wrapper.setAttribute('data-browser-use-ignore', 'true')
this.wrapper.setAttribute('data-page-agent-ignore', 'true')
this.wrapper.appendChild(this.motion.element)
this.motion.autoResize(this.wrapper)
try {
const motion = new Motion({
mode: isPageDark() ? 'dark' : 'light',
styles: { position: 'absolute', inset: '0' },
})
this.motion = motion
this.wrapper.appendChild(motion.element)
motion.autoResize(this.wrapper)
} catch (e) {
console.warn('[SimulatorMask] Motion overlay unavailable:', e)
}
// Capture all mouse, keyboard, and wheel events
this.wrapper.addEventListener('click', (e) => {
@@ -144,8 +148,8 @@ export class SimulatorMask {
if (this.shown) return
this.shown = true
this.motion.start()
this.motion.fadeIn()
this.motion?.start()
this.motion?.fadeIn()
this.wrapper.style.display = 'block'
@@ -162,8 +166,8 @@ export class SimulatorMask {
if (!this.shown) return
this.shown = false
this.motion.fadeOut()
this.motion.pause()
this.motion?.fadeOut()
this.motion?.pause()
this.#cursor.classList.remove(cursorStyles.clicking)
@@ -173,7 +177,7 @@ export class SimulatorMask {
}
dispose() {
this.motion.dispose()
this.motion?.dispose()
this.wrapper.remove()
}
}
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@page-agent/ui",
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"main": "./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',
expand: 'Expand history',
collapse: 'Collapse history',
step: 'Step {{number}} · {{time}}{{duration}}',
step: 'Step {{number}}',
},
tools: {
clicking: 'Clicking element [{{index}}]...',
@@ -63,7 +63,7 @@ const zhCN = {
close: '关闭',
expand: '展开历史',
collapse: '收起历史',
step: '步骤 {{number}} · {{time}}{{duration}}',
step: '步骤 {{number}}',
},
tools: {
clicking: '正在点击元素 [{{index}}]...',
+4 -7
View File
@@ -1,6 +1,6 @@
import { I18n, type SupportedLanguage } from '../i18n'
import { truncate } from '../utils'
import { createCard, createReflectionLines, formatTime } from './cards'
import { createCard, createReflectionLines } from './cards'
import type { AgentActivity, PanelAgentAdapter } from './types'
import styles from './Panel.module.css'
@@ -187,7 +187,6 @@ export class Panel {
tempCard.innerHTML = createCard({
icon: '❓',
content: `Question: ${question}`,
meta: formatTime(this.#config.language ?? 'en-US'),
type: 'question',
})
const cardElement = tempCard.firstElementChild as HTMLElement
@@ -374,6 +373,7 @@ export class Panel {
wrapper.id = 'page-agent-runtime_agent-panel'
wrapper.className = styles.wrapper
wrapper.setAttribute('data-browser-use-ignore', 'true')
wrapper.setAttribute('data-page-agent-ignore', 'true')
wrapper.innerHTML = `
<div class="${styles.background}"></div>
@@ -591,15 +591,12 @@ export class Panel {
/** Create cards for a history event */
#createHistoryCards(event: PanelAgentAdapter['history'][number]): string[] {
const cards: string[] = []
const time = formatTime(this.#config.language ?? 'en-US')
const meta =
event.type === 'step' && event.stepIndex !== undefined
? this.#i18n.t('ui.panel.step', {
number: (event.stepIndex + 1).toString(),
time,
duration: '',
})
: time
: undefined
if (event.type === 'step') {
// Reflection card
@@ -636,7 +633,7 @@ export class Panel {
/** Create cards for an action */
#createActionCards(
action: { name: string; input: unknown; output: string },
meta: string
meta?: string
): 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 */
export function createReflectionLines(reflection: {
evaluation_previous_goal?: string
+40 -24
View File
@@ -5,9 +5,9 @@
- **React** with TypeScript
- **Vite** for dev server and build
- **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
- **wouter** with hash routing for static hosting
- **wouter** with browser routing (`base: "/page-agent"`)
- **lucide-react** for icons
## Component Guidelines
@@ -53,58 +53,74 @@ Located in `src/components/ui/`:
### Styling Rules
1. **Prefer Tailwind classes** over custom CSS
2. Use CSS modules only for complex component-specific styles
3. Support dark mode via `dark:` classes
4. Use CSS variables from `src/index.css` for theme colors
2. Support dark mode via `dark:` classes
3. Use CSS variables from `src/index.css` for theme colors
## Project Structure
```
src/
├── pages/
│ ├── Home.tsx # Homepage
│ ├── home/
│ │ ├── index.tsx # Homepage
│ │ └── ...Section.tsx
│ └── docs/
│ ├── Layout.tsx # Documentation sidebar
│ ├── index.tsx # Docs route switch
│ ├── Layout.tsx # Sidebar navigation
│ └── [section]/[topic]/page.tsx
├── 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
│ └── Footer.tsx # Site footer
├── i18n/ # Internationalization
├── router.tsx # Central routing
├── router.tsx # Root layout + routing
└── 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
### Documentation Page
1. Create `src/pages/docs/<section>/<slug>/page.tsx`
2. Add route to `src/router.tsx` with `<Header /> + <DocsLayout>` wrapper
3. Add navigation item to `pages/docs/Layout.tsx`
## 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>
```
2. Add route in `src/pages/docs/index.tsx`
3. Add navigation item in `src/pages/docs/Layout.tsx`
4. Add path to `SPA_ROUTES` in `vite.config.js`
## Configuration Files
| File | Purpose |
| ----------------- | ----------------------- |
| `components.json` | shadcn/ui configuration |
| `vite.config.js` | Vite build settings |
| `vite.config.js` | Vite build + SPA routes |
| `tsconfig.json` | TypeScript config |
## Commands
```bash
npm start # Dev server (from root)
npm start # Dev server (from root)
npm run build:website # Build website (from root)
```
+13 -2
View File
@@ -45,13 +45,24 @@
</script>
</head>
<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>
// Dynamically update html lang attribute based on i18n detection
const updateHtmlLang = () => {
const lang = localStorage.getItem('i18nextLng') || navigator.language || 'zh-CN'
document.documentElement.lang = lang
const el = document.getElementById('sk-text')
if (el) el.textContent = lang.startsWith('zh') ? '加载中...' : 'Loading...'
}
updateHtmlLang()
window.addEventListener('storage', updateHtmlLang)
+6 -6
View File
@@ -1,7 +1,7 @@
{
"name": "@page-agent/website",
"private": true,
"version": "1.3.0",
"version": "1.5.2",
"type": "module",
"scripts": {
"dev": "vite --host 0.0.0.0",
@@ -15,19 +15,19 @@
"@radix-ui/react-slot": "^1.2.4",
"@radix-ui/react-switch": "^1.2.6",
"@radix-ui/react-tooltip": "^1.2.8",
"@types/react": "^19.2.13",
"@types/react": "^19.2.14",
"@types/react-dom": "^19.2.1",
"class-variance-authority": "^0.7.1",
"clsx": "^2.1.1",
"lucide-react": "^0.563.0",
"motion": "^12.34.0",
"lucide-react": "^0.576.0",
"motion": "^12.34.5",
"next-themes": "^0.4.6",
"react": "^19.2.4",
"react-dom": "^19.2.4",
"rough-notation": "^0.5.1",
"simple-icons": "^16.8.0",
"simple-icons": "^16.10.0",
"sonner": "^2.0.7",
"tailwind-merge": "^3.4.0",
"tailwind-merge": "^3.5.0",
"tailwindcss": "^4.1.14",
"tw-animate-css": "^1.4.0",
"wouter": "^3.9.0"
@@ -5,10 +5,9 @@
*/
import * as React from 'react'
import { Badge } from '@/components/ui/badge'
import { cn } from '@/lib/utils'
import { Badge } from './badge'
// ============================================================================
// Types
// ============================================================================
@@ -35,6 +34,8 @@ export interface APIReferenceProps {
description?: React.ReactNode
/** Property definitions */
properties: PropDefinition[]
/** Display variant: 'properties' for fields, 'methods' for methods */
variant?: 'properties' | 'methods'
/** Additional CSS classes */
className?: string
}
@@ -43,7 +44,14 @@ export interface APIReferenceProps {
// Component
// ============================================================================
export function APIReference({ title, description, properties, className }: APIReferenceProps) {
export function APIReference({
title,
description,
properties,
variant = 'properties',
className,
}: APIReferenceProps) {
const isMethodsVariant = variant === 'methods'
return (
<div className={cn('my-6', className)}>
{title && (
@@ -58,10 +66,10 @@ export function APIReference({ title, description, properties, className }: APIR
<thead>
<tr className="bg-gray-50 dark:bg-gray-800/50">
<th className="px-4 py-3 text-left font-medium text-gray-600 dark:text-gray-300">
Property
{isMethodsVariant ? 'Method' : 'Property'}
</th>
<th className="px-4 py-3 text-left font-medium text-gray-600 dark:text-gray-300">
Type
{isMethodsVariant ? 'Return Type' : 'Type'}
</th>
<th className="px-4 py-3 text-left font-medium text-gray-600 dark:text-gray-300 hidden md:table-cell">
Default
@@ -120,7 +128,7 @@ function PropRow({ name, type, required, defaultValue, description, status }: Pr
{/* Type */}
<td className="px-4 py-3 align-top">
<code className="font-mono text-xs text-gray-700 dark:text-gray-300 bg-gray-100 dark:bg-gray-800 px-1.5 py-0.5 rounded whitespace-nowrap">
<code className="font-mono text-xs text-gray-700 dark:text-gray-300 bg-gray-100 dark:bg-gray-800 px-1.5 py-0.5 rounded wrap-break-word">
{type}
</code>
</td>
@@ -42,7 +42,7 @@ const CodeEditor: React.FC<CodeEditorProps> = ({
return (
<div
className={`group relative ${containerClasses} rounded-xl border shadow-2xl overflow-hidden ${className}`}
className={`group relative ${containerClasses} rounded-xl border shadow-2xl my-4 overflow-hidden ${className}`}
>
{/* 编辑器顶部栏 */}
{showHeader && (
@@ -16,6 +16,14 @@ export default function Footer() {
© 2026 page-agent. All rights reserved.
</p>
<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
href="https://github.com/alibaba/page-agent"
target="_blank"
+5 -5
View File
@@ -23,7 +23,7 @@ export default function Header() {
<div className="flex items-center justify-between gap-2">
{/* Logo */}
<Link
href="~/"
href="/"
className="flex items-center gap-2 sm:gap-3 group shrink-0"
aria-label={isZh ? 'page-agent 首页' : 'page-agent home'}
onClick={() => setMobileMenuOpen(false)}
@@ -44,7 +44,7 @@ export default function Header() {
animateOnHover={true}
aria-hidden="true"
>
GUI Agent in your webpage
AI Agent In Your Webpage
</HyperText>
</div>
</Link>
@@ -56,7 +56,7 @@ export default function Header() {
aria-label="Mobile navigation"
>
<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"
aria-label={isZh ? '文档' : 'Docs'}
>
@@ -90,7 +90,7 @@ export default function Header() {
{import.meta.env.VERSION}
</span>
<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"
>
<BookOpen className="w-4 h-4" />
@@ -138,7 +138,7 @@ export default function Header() {
role="navigation"
>
<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"
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
className="pointer-events-none absolute inset-px rounded-[inherit] opacity-0 transition-opacity duration-300 group-hover:opacity-100"
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)
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@1.5.2/dist/iife/page-agent.demo.js'
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/1.5.2/files/dist/iife/page-agent.demo.js'
// Demo LLM for website testing
export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'
export const DEMO_BASE_URL =
'https://hwcxiuzfylggtcktqgij.supabase.co/functions/v1/llm-testing-proxy'
export const DEMO_API_KEY = 'PAGE-AGENT-FREE-TESTING-RANDOM'
// Demo LLM for website testing (homepage quick trial uses flash)
export const DEMO_MODEL = 'qwen3.5-flash'
export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
export const DEMO_API_KEY = 'NA'
+18
View File
@@ -377,6 +377,24 @@ td {
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 */
+8 -2
View File
@@ -1,15 +1,21 @@
import { createRoot } from 'react-dom/client'
import { Router } from 'wouter'
import { useHashLocation } from 'wouter/use-hash-location'
import { LanguageProvider } from './i18n/context'
import { default as PagesRouter } from './router'
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(
<LanguageProvider>
<Router hook={useHashLocation}>
<Router base="/page-agent">
<PagesRouter />
</Router>
</LanguageProvider>
-586
View File
@@ -1,586 +0,0 @@
/* eslint-disable react-dom/no-dangerously-set-innerhtml */
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 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 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 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 (
<div className="min-h-screen bg-linear-to-br from-blue-50 to-purple-50 dark:from-gray-900 dark:to-gray-800">
<Header />
{/* Hero Section */}
<main id="main-content">
<section
className="relative px-6 py-22 pb-18 lg:py-28 overflow-hidden"
aria-labelledby="hero-heading"
>
<div className="max-w-7xl mx-auto text-center">
{/* Background Pattern + Particles */}
<div className="absolute inset-0 opacity-30" aria-hidden="true">
<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>
</section>
{/* Features Section */}
<section
className="px-6 py-20 bg-white/50 dark:bg-gray-800/50 backdrop-blur-sm"
aria-labelledby="features-heading"
>
<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>
)
}
+3 -6
View File
@@ -34,10 +34,6 @@ export default function DocsLayout({ children }: DocsLayoutProps) {
title: isZh ? '故障排查' : 'Troubleshooting',
path: '/introduction/troubleshooting',
},
{
title: '🚧 ' + (isZh ? '最佳实践' : 'Best Practices'),
path: '/integration/best-practices',
},
],
},
{
@@ -50,7 +46,7 @@ export default function DocsLayout({ children }: DocsLayoutProps) {
{ title: isZh ? 'Chrome 扩展' : 'Chrome Extension', path: '/features/chrome-extension' },
{
title: isZh ? '接入第三方 Agent' : 'Third-party Agent',
path: '/integration/third-party-agent',
path: '/features/third-party-agent',
},
],
},
@@ -59,10 +55,11 @@ export default function DocsLayout({ children }: DocsLayoutProps) {
items: [
{ title: 'PageAgent', path: '/advanced/page-agent' },
{ title: 'PageAgentCore', path: '/advanced/page-agent-core' },
{ title: 'PageController', path: '/advanced/page-controller' },
{ title: isZh ? '自定义 UI' : 'Custom UI', path: '/advanced/custom-ui' },
{
title: '🚧 ' + (isZh ? '安全与权限' : 'Security & Permissions'),
path: '/integration/security-permissions',
path: '/advanced/security-permissions',
},
],
},
@@ -1,5 +1,6 @@
import { APIDivider, APIReference } from '@/components/APIReference'
import CodeEditor from '@/components/CodeEditor'
import { APIDivider, APIReference } from '@/components/ui/api-reference'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function CustomUIDocs() {
@@ -17,7 +18,7 @@ export default function CustomUIDocs() {
{/* Architecture */}
<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">
{isZh
? '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 */}
<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">
{isZh
? '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 */}
<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
properties={[
{
@@ -155,7 +156,7 @@ export default function CustomUIDocs() {
{/* HistoricalEvent Types */}
<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">
{isZh ? 'agent.history 数组中的事件类型:' : 'Event types in agent.history array:'}
</p>
@@ -172,7 +173,7 @@ export default function CustomUIDocs() {
{/* AgentActivity Types */}
<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">
{isZh ? 'activity 事件的 detail 类型:' : 'The detail type of activity events:'}
</p>
@@ -191,9 +192,7 @@ export default function CustomUIDocs() {
{/* React Hooks Example */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">
{isZh ? '使用 React Hooks' : 'Using React Hooks'}
</h2>
<Heading id="using-react-hooks">{isZh ? '使用 React Hooks' : 'Using React Hooks'}</Heading>
<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:'}
</p>
@@ -229,9 +228,9 @@ export default function CustomUIDocs() {
{/* Assembly Example */}
<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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '参考内置 PageAgent 的实现方式,用自定义 UI 替换 Panel'
@@ -1,5 +1,8 @@
import { Link } from 'wouter'
import { APIDivider, APIReference, TypeRef } from '@/components/APIReference'
import CodeEditor from '@/components/CodeEditor'
import { APIDivider, APIReference, TypeRef } from '@/components/ui/api-reference'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function PageAgentCoreDocs() {
@@ -17,9 +20,9 @@ export default function PageAgentCoreDocs() {
{/* When to use */}
<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'}
</h2>
</Heading>
<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 ? '在自动化测试中无头运行' : 'Running headless in automated tests'}</li>
@@ -38,7 +41,7 @@ export default function PageAgentCoreDocs() {
{/* Basic Usage */}
<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
language="typescript"
code={`import { PageAgentCore } from '@page-agent/core'
@@ -49,19 +52,13 @@ const agent = new PageAgentCore({
baseURL: 'https://api.openai.com/v1',
apiKey: 'your-api-key',
model: 'gpt-5.2',
language: 'en-US',
})
// Listen to events for UI display
agent.addEventListener('statuschange', () => {
console.log('Status:', agent.status)
})
agent.addEventListener('historychange', () => {
console.log('History:', agent.history)
})
agent.addEventListener('activity', (e) => {
const activity = (e as CustomEvent).detail
console.log('Activity:', activity.type)
@@ -74,14 +71,54 @@ const result = await agent.execute('Fill in the form with test data')`}
<APIDivider title={isZh ? '配置' : 'Configuration'} />
{/* LLM Configuration */}
{/* Configuration */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">LLMConfig</h2>
<Heading id="configuration">PageAgentCoreConfig</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '配置与大语言模型的连接参数。支持 OpenAI 兼容的 API。'
: 'Configure connection parameters for the language model. Supports OpenAI-compatible APIs.'}
? 'PageAgentCoreConfig = AgentConfig & { pageController: PageController }。AgentConfig 包含以下配置项:'
: 'PageAgentCoreConfig = AgentConfig & { pageController: PageController }. AgentConfig contains the following options:'}
</p>
{/* PageController */}
<h3 className="text-lg font-semibold mt-6 mb-3 text-gray-800 dark:text-gray-200">
PageController
</h3>
<APIReference
properties={[
{
name: 'pageController',
type: 'PageController',
required: true,
description: isZh ? (
<>
<Link
href="/advanced/page-controller"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
PageController
</Link>{' '}
DOM
</>
) : (
<>
<Link
href="/advanced/page-controller"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
PageController
</Link>{' '}
instance for DOM operations and element interaction.
</>
),
},
]}
/>
{/* LLM Config */}
<h3 className="text-lg font-semibold mt-6 mb-3 text-gray-800 dark:text-gray-200">
{isZh ? 'LLM 配置' : 'LLM Config'}
</h3>
<APIReference
properties={[
{
@@ -109,7 +146,6 @@ const result = await agent.execute('Fill in the form with test data')`}
{
name: 'temperature',
type: 'number',
defaultValue: '0',
description: isZh
? '模型温度参数,控制输出随机性'
: 'Model temperature, controls output randomness',
@@ -129,16 +165,11 @@ const result = await agent.execute('Fill in the form with test data')`}
},
]}
/>
</section>
{/* Agent Configuration */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">AgentConfig</h2>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '配置 Agent 的行为、生命周期钩子和扩展能力。'
: 'Configure agent behavior, lifecycle hooks, and extension capabilities.'}
</p>
{/* Agent Config */}
<h3 className="text-lg font-semibold mt-6 mb-3 text-gray-800 dark:text-gray-200">
{isZh ? 'Agent 配置' : 'Agent Config'}
</h3>
<APIReference
properties={[
{
@@ -150,7 +181,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{
name: 'maxSteps',
type: 'number',
defaultValue: '20',
defaultValue: '40',
description: isZh ? '每个任务的最大步骤数' : 'Maximum number of steps per task',
},
{
@@ -165,8 +196,8 @@ const result = await agent.execute('Fill in the form with test data')`}
name: 'instructions',
type: 'InstructionsConfig',
description: isZh
? '指导 Agent 行为的指令配置'
: 'Instructions to guide agent behavior',
? '指导 Agent 行为的指令配置,见下方类型定义'
: 'Instructions to guide agent behavior, see type definition below',
},
{
name: 'transformPageContent',
@@ -176,7 +207,15 @@ const result = await agent.execute('Fill in the form with test data')`}
: 'Transform page content before sending to LLM, useful for data masking',
},
{
name: 'experimentalScriptExecutionTool',
name: 'customSystemPrompt',
type: 'string',
status: 'experimental',
description: isZh
? '完全覆盖默认系统提示词。谨慎使用。'
: 'Completely override the default system prompt. Use with caution.',
},
{
name: 'experimentalScript\nExecutionTool',
type: 'boolean',
defaultValue: 'false',
status: 'experimental',
@@ -184,134 +223,58 @@ const result = await agent.execute('Fill in the form with test data')`}
? '启用实验性 JavaScript 执行工具'
: 'Enable experimental JavaScript execution tool',
},
]}
/>
<h3 className="text-lg font-semibold mt-6 mb-3">InstructionsConfig</h3>
<APIReference
properties={[
{
name: 'system',
type: 'string',
name: 'experimentalLlmsTxt',
type: 'boolean',
defaultValue: 'false',
status: 'experimental',
description: isZh
? '全局系统级指令,应用于所有任务'
: 'Global system-level instructions, applied to all tasks',
},
{
name: 'getPageInstructions',
type: '(url: string) => string | undefined | null',
description: isZh
? '动态页面级指令回调,在每个步骤前调用'
: 'Dynamic page-level instructions callback, called before each step',
? '从当前站点根目录获取 /llms.txt 并作为上下文提供给 LLM'
: 'Fetch /llms.txt from site origin and include as LLM context',
},
]}
/>
</section>
{/* Lifecycle Hooks */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '生命周期钩子' : 'Lifecycle Hooks'}</h2>
{/* Lifecycle Hooks */}
<h3 className="text-lg font-semibold mt-6 mb-3 text-gray-800 dark:text-gray-200">
{isZh ? '生命周期钩子' : 'Lifecycle Hooks'}
<span className="ml-2 text-xs font-normal text-amber-600 dark:text-amber-400">
experimental
</span>
</h3>
<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">
<strong> {isZh ? '警告' : 'Warning'}:</strong>{' '}
{isZh
? '这些接口高度实验性,可能在未来版本中发生变化。建议优先使用事件系统(Events)来监听 Agent 状态。'
: 'These APIs are highly experimental and may change in future versions. Prefer using the Events system for monitoring agent state.'}
? '这些接口高度实验性,可能在未来版本中发生变化。'
: 'These APIs are highly experimental and may change in future versions. '}
</p>
</div>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '所有生命周期钩子都接收 agent 实例作为第一个参数,便于在回调中访问 Agent 状态和方法。'
: 'All lifecycle hooks receive the agent instance as first parameter, making it easy to access agent state and methods in callbacks.'}
</p>
<APIReference
properties={[
{
name: 'onBeforeStep',
type: '(agent: PageAgentCore, stepCount: number) => void | Promise<void>',
type: '(agent, stepCount) => void | Promise<void>',
description: isZh ? '每个步骤执行前调用' : 'Called before each step execution',
status: 'experimental',
},
{
name: 'onAfterStep',
type: '(agent: PageAgentCore, history: HistoricalEvent[]) => void | Promise<void>',
type: '(agent, history) => void | Promise<void>',
description: isZh ? '每个步骤执行后调用' : 'Called after each step execution',
status: 'experimental',
},
{
name: 'onBeforeTask',
type: '(agent: PageAgentCore) => void | Promise<void>',
type: '(agent) => void | Promise<void>',
description: isZh ? '任务开始前调用' : 'Called before task starts',
status: 'experimental',
},
{
name: 'onAfterTask',
type: '(agent: PageAgentCore, result: ExecutionResult) => void | Promise<void>',
type: '(agent, result) => void | Promise<void>',
description: isZh ? '任务结束后调用' : 'Called after task ends',
status: 'experimental',
},
{
name: 'onDispose',
type: '(agent: PageAgentCore, reason?: string) => void',
type: '(agent, reason?) => void',
description: isZh ? 'Agent 销毁时调用' : 'Called when agent is disposed',
status: 'experimental',
},
]}
/>
</section>
{/* PageController Configuration */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">PageControllerConfig</h2>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '配置 DOM 提取、元素交互和视觉反馈。'
: 'Configure DOM extraction, element interaction, and visual feedback.'}
</p>
<APIReference
properties={[
{
name: 'pageController',
type: 'PageController',
status: 'experimental',
description: isZh
? '自定义 PageController 实例。如不提供,将创建默认实例。'
: 'Custom PageController instance. If not provided, a default one will be created.',
},
{
name: 'enableMask',
type: 'boolean',
defaultValue: 'true',
description: isZh
? '启用视觉遮罩覆盖层,阻止用户在自动化期间操作'
: 'Enable visual mask overlay that blocks user interaction during automation',
},
{
name: 'viewportExpansion',
type: 'number',
defaultValue: '0',
description: isZh
? '视口扩展像素数,-1 表示提取整个页面'
: 'Viewport expansion in pixels, -1 means extract entire page',
},
{
name: 'interactiveBlacklist',
type: '(Element | (() => Element))[]',
description: isZh ? '要排除的交互元素列表' : 'Elements to exclude from interaction',
},
{
name: 'interactiveWhitelist',
type: '(Element | (() => Element))[]',
description: isZh
? '要强制包含的交互元素列表'
: 'Elements to force include for interaction',
},
{
name: 'includeAttributes',
type: 'string[]',
description: isZh
? '在 DOM 提取中包含的额外属性'
: 'Additional attributes to include in DOM extraction',
},
]}
/>
@@ -321,7 +284,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Properties */}
<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
properties={[
{
@@ -366,18 +329,26 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Methods */}
<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
variant="methods"
properties={[
{
name: 'execute(task: string)',
name: 'execute(task)',
type: 'Promise<ExecutionResult>',
description: isZh
? '执行任务并返回结果。包含 success、data 和 history 字段。'
: 'Execute a task and return result. Contains success, data, and history fields.',
},
{
name: 'dispose(reason?: string)',
name: 'stop()',
type: 'void',
description: isZh
? '停止当前任务。Agent 仍可复用。'
: 'Stop the current task. Agent remains reusable.',
},
{
name: 'dispose()',
type: 'void',
description: isZh
? '销毁 Agent 并清理资源'
@@ -389,7 +360,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* Events */}
<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">
{isZh ? (
<>
@@ -438,15 +409,12 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* ExecutionResult */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">ExecutionResult</h2>
<Heading id="executionresult">ExecutionResult</Heading>
<CodeEditor
language="typescript"
code={`interface ExecutionResult {
/** Whether the task completed successfully */
success: boolean
/** Result description from the agent */
data: string
/** Full execution history */
history: HistoricalEvent[]
}`}
/>
@@ -454,7 +422,7 @@ const result = await agent.execute('Fill in the form with test data')`}
{/* AgentActivity */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">AgentActivity</h2>
<Heading id="agentactivity">AgentActivity</Heading>
<CodeEditor
language="typescript"
code={`type AgentActivity =
@@ -466,50 +434,21 @@ const result = await agent.execute('Fill in the form with test data')`}
/>
</section>
<APIDivider title={isZh ? '无头模式' : 'Headless Mode'} />
{/* Headless Usage */}
{/* InstructionsConfig */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '无头模式' : 'Headless Mode'}</h2>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{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)。'
: 'In non-DOM environments, you must implement a custom PageController (e.g., remote page control or Puppeteer).'}
</p>
<Heading id="instructionsconfig">InstructionsConfig</Heading>
<CodeEditor
language="typescript"
code={`import { PageAgentCore } from '@page-agent/core'
import type { PageController } from '@page-agent/page-controller'
code={`interface InstructionsConfig {
/** Global system-level instructions, applied to all tasks */
system?: string
class MyRemotePageController implements PageController {
// Implement required methods for DOM extraction and interaction
}
const agent = new PageAgentCore({
pageController: new MyRemotePageController(),
baseURL: 'https://api.openai.com/v1',
apiKey: 'your-api-key',
model: 'gpt-5.2',
language: 'en-US',
})
// Listen to events for UI display
agent.addEventListener('statuschange', () => {
console.log('Status:', agent.status)
})
agent.addEventListener('historychange', () => {
console.log('History:', agent.history)
})
agent.addEventListener('activity', (e) => {
const activity = (e as CustomEvent).detail
console.log('Activity:', activity.type)
})
// Execute task
const result = await agent.execute('Fill in the form with test data')`}
/**
* Dynamic page-level instructions callback.
* Called before each step to get instructions for the current page.
*/
getPageInstructions?: (url: string) => string | undefined
}`}
/>
</section>
</div>
@@ -1,7 +1,7 @@
import { Link } from 'wouter'
import CodeEditor from '@/components/CodeEditor'
import { APIReference, TypeRef } from '@/components/ui/api-reference'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function PageAgentDocs() {
@@ -13,21 +13,26 @@ export default function PageAgentDocs() {
<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
{isZh
? 'PageAgent 是带有内置 UI 面板的完整 Agent 类。它继承自 PageAgentCore,并自动创建交互面板。'
: 'PageAgent is the complete Agent class with built-in UI panel. It extends PageAgentCore and automatically creates an interactive panel.'}
? 'PageAgent 是带有内置 UI 面板的完整 Agent 类。它继承自 PageAgentCore,并自动创建交互面板和 PageController。'
: 'PageAgent is the complete Agent class with built-in UI panel. It extends PageAgentCore and automatically creates an interactive panel and PageController.'}
</p>
{/* When to use */}
<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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{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:'
: 'In most cases, you should use PageAgent. It provides a complete out-of-the-box experience:'}
</p>
<ul className="list-disc list-inside text-gray-600 dark:text-gray-400 space-y-2 mb-6">
<li>
{isZh
? '自动创建 PageController,处理 DOM 提取和元素操作'
: 'Automatically creates PageController for DOM extraction and element actions'}
</li>
<li>
{isZh
? '内置 UI 面板,显示任务进度、Agent 思考过程和操作结果'
@@ -43,7 +48,7 @@ export default function PageAgentDocs() {
{/* Basic Usage */}
<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
language="typescript"
code={`import { PageAgent } from 'page-agent'
@@ -69,13 +74,12 @@ console.log(result.history) // Full execution history`}
{/* Class Definition */}
<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
language="typescript"
code={`class PageAgent extends PageAgentCore {
/** The UI panel instance */
panel: Panel
pageController: PageController
constructor(config: PageAgentConfig)
}`}
/>
@@ -89,7 +93,21 @@ console.log(result.history) // Full execution history`}
>
PageAgentCore
</Link>
API PageAgentCore
{' '}
<Link
href="/advanced/page-agent-core#configuration"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
AgentConfig
</Link>{' '}
{' '}
<Link
href="/advanced/page-controller#configuration"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
PageControllerConfig
</Link>
</>
) : (
<>
@@ -100,71 +118,34 @@ console.log(result.history) // Full execution history`}
>
PageAgentCore
</Link>
. All core methods and events are available. See PageAgentCore docs for detailed API
reference.
</>
)}
</p>
</section>
{/* Configuration */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? '配置' : 'Configuration'}</h2>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? 'PageAgent 使用与 PageAgentCore 相同的配置接口。'
: 'PageAgent uses the same configuration interface as PageAgentCore.'}
</p>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh ? (
<>
{' '}
. All core methods and events are available. Config merges{' '}
<Link
href="/advanced/page-agent-core"
href="/advanced/page-agent-core#configuration"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
PageAgentCore
</Link>
</>
) : (
<>
See{' '}
<Link
href="/advanced/page-agent-core"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
PageAgentCore configuration docs
AgentConfig
</Link>{' '}
for complete reference.
and{' '}
<Link
href="/advanced/page-controller#configuration"
className="text-blue-600 dark:text-blue-400 hover:underline"
>
PageControllerConfig
</Link>
.
</>
)}
</p>
</section>
{/* Panel Property */}
{/* Panel */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">{isZh ? 'Panel 属性' : 'Panel Property'}</h2>
<Heading id="panel">{isZh ? 'UI 面板' : 'UI Panel'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{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 automatically creates a Panel instance. You can access it via the panel property to control the UI:'}
? 'PageAgent 自动创建一个 Panel 实例。你可以通过 panel 属性控制 UI'
: 'PageAgent automatically creates a Panel instance. You can control the UI via the panel property:'}
</p>
<APIReference
properties={[
{
name: 'panel',
type: 'Panel',
required: true,
description: isZh
? '内置的 UI 面板实例,用于显示任务进度和接收用户输入。'
: 'The built-in UI panel instance for displaying task progress and receiving user input.',
},
]}
/>
<h3 className="text-lg font-semibold mt-6 mb-3">{isZh ? 'Panel 方法' : 'Panel Methods'}</h3>
<CodeEditor
language="typescript"
code={`// Show/hide the panel
@@ -185,9 +166,9 @@ agent.panel.dispose()`}
{/* Comparison with PageAgentCore */}
<section className="mb-10">
<h2 className="text-2xl font-semibold mb-4">
<Heading id="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">
<table className="w-full text-sm">
<thead>
@@ -211,16 +192,16 @@ agent.panel.dispose()`}
</tr>
<tr className="bg-white dark:bg-gray-900">
<td className="px-4 py-3 text-gray-600 dark:text-gray-400">
{isZh ? 'Headless 模式' : 'Headless Mode'}
{isZh ? '自动创建 PageController' : 'Auto-creates PageController'}
</td>
<td className="px-4 py-3 text-center text-gray-400 dark:text-gray-600">-</td>
<td className="px-4 py-3 text-center text-green-600 dark:text-green-400"></td>
<td className="px-4 py-3 text-center text-gray-400 dark:text-gray-600">-</td>
</tr>
<tr className="bg-white dark:bg-gray-900">
<td className="px-4 py-3 text-gray-600 dark:text-gray-400">
{isZh ? '自定义 PageController' : 'Custom PageController'}
{isZh ? 'Headless 模式' : 'Headless Mode'}
</td>
<td className="px-4 py-3 text-center text-green-600 dark:text-green-400"></td>
<td className="px-4 py-3 text-center text-gray-400 dark:text-gray-600">-</td>
<td className="px-4 py-3 text-center text-green-600 dark:text-green-400"></td>
</tr>
<tr className="bg-white dark:bg-gray-900">
@@ -0,0 +1,286 @@
import { Link } from 'wouter'
import { APIDivider, APIReference } from '@/components/APIReference'
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function PageControllerDocs() {
const { isZh } = useLanguage()
return (
<div>
<h1 className="text-4xl font-bold mb-6">PageController</h1>
<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
{isZh
? 'PageController 负责 DOM 提取和元素交互,独立于 LLM。它将页面状态结构化为 LLM 可消费的格式,并执行元素级操作。'
: 'PageController handles DOM extraction and element interaction, independent of LLM. It structures page state into LLM-consumable format and executes element-level actions.'}
</p>
{/* Basic Usage */}
<section className="mb-10">
<Heading id="basic-usage">{isZh ? '基本用法' : 'Basic Usage'}</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? 'PageAgent 接受 PageController 配置项:'
: 'PageAgent accepts PageController options:'}
</p>
<CodeEditor
language="typescript"
code={`import { PageAgent } from 'page-agent'
const agent = new PageAgent({
baseURL: 'https://api.openai.com/v1',
apiKey: 'your-api-key',
model: 'gpt-5.2',
// PageController options
enableMask: true,
viewportExpansion: 0,
})`}
/>
<p className="text-gray-600 dark:text-gray-400 mt-4">
{isZh
? 'PageAgentCore 接受 PageController 实例:'
: 'PageAgentCore accepts a PageController instance:'}
</p>
<CodeEditor
language="typescript"
code={`import { PageAgentCore } from '@page-agent/core'
import { PageController } from '@page-agent/page-controller'
const pageController = new PageController({
enableMask: true,
viewportExpansion: -1, // extract full page
})
const agent = new PageAgentCore({
pageController,
baseURL: 'https://api.openai.com/v1',
apiKey: 'your-api-key',
model: 'gpt-5.2',
})`}
/>
</section>
<APIDivider title={isZh ? '配置' : 'Configuration'} />
{/* Configuration */}
<section className="mb-10">
<Heading id="configuration">PageControllerConfig</Heading>
<APIReference
properties={[
{
name: 'enableMask',
type: 'boolean',
defaultValue: 'false',
description: isZh
? '启用视觉遮罩覆盖层,在自动化期间阻止用户操作页面。通过 PageAgent 创建时默认为 true。'
: 'Enable visual mask overlay that blocks user interaction during automation. Defaults to true when created via PageAgent.',
},
{
name: 'viewportExpansion',
type: 'number',
defaultValue: '0',
description: isZh
? '向视口外扩展提取的像素数。设为 -1 表示提取整个页面。'
: 'Pixels to expand extraction beyond viewport. Set to -1 to extract the entire page.',
},
{
name: 'interactiveBlacklist',
type: '(Element | (() => Element))[]',
description: isZh
? '要排除的交互元素列表。支持元素引用或返回元素的函数(延迟求值)。'
: 'Elements to exclude from interaction. Supports element references or functions returning elements (lazy evaluation).',
},
{
name: 'interactiveWhitelist',
type: '(Element | (() => Element))[]',
description: isZh
? '要强制包含的交互元素列表。支持元素引用或返回元素的函数。'
: 'Elements to force include for interaction. Supports element references or functions returning elements.',
},
{
name: 'includeAttributes',
type: 'string[]',
description: isZh
? '在 DOM 提取中包含的额外 HTML 属性(如 data-testid)。默认已包含常见属性如 role, aria-label 等。'
: 'Additional HTML attributes to include in DOM extraction (e.g. data-testid). Common attributes like role, aria-label are included by default.',
},
]}
/>
</section>
<APIDivider title={isZh ? '方法' : 'Methods'} />
{/* Methods */}
<section className="mb-10">
<Heading id="methods">{isZh ? '方法' : 'Methods'}</Heading>
<h3 className="text-lg font-semibold mt-6 mb-3">{isZh ? '状态查询' : 'State Queries'}</h3>
<APIReference
variant="methods"
properties={[
{
name: 'getBrowserState()',
type: 'Promise<BrowserState>',
description: isZh
? '获取结构化的浏览器状态(URL、标题、简化 HTML 等),自动调用 updateTree() 刷新 DOM。这是 Agent 在每步使用的主要方法。'
: 'Get structured browser state (URL, title, simplified HTML, etc.), automatically calls updateTree() to refresh DOM. This is the primary method the agent uses each step.',
},
{
name: 'updateTree()',
type: 'Promise<string>',
description: isZh
? '刷新 DOM 树并返回简化 HTML。通常不需要手动调用 —— getBrowserState() 会自动调用。'
: 'Refresh DOM tree and return simplified HTML. Usually not needed manually — getBrowserState() calls it automatically.',
},
{
name: 'getCurrentUrl()',
type: 'Promise<string>',
description: isZh ? '获取当前页面 URL。' : 'Get current page URL.',
},
]}
/>
<h3 className="text-lg font-semibold mt-6 mb-3">{isZh ? '元素操作' : 'Element Actions'}</h3>
<APIReference
variant="methods"
properties={[
{
name: 'clickElement(index)',
type: 'Promise<ActionResult>',
description: isZh
? '按索引点击元素。索引来自简化 HTML 中的 [N] 标记。'
: 'Click element by index. Index comes from [N] markers in simplified HTML.',
},
{
name: 'inputText(index, text)',
type: 'Promise<ActionResult>',
description: isZh ? '向输入框元素填入文本。' : 'Input text into a form element.',
},
{
name: 'selectOption(index, optionText)',
type: 'Promise<ActionResult>',
description: isZh ? '在下拉框中选择选项。' : 'Select option in a dropdown element.',
},
{
name: 'scroll(options)',
type: 'Promise<ActionResult>',
description: isZh
? '垂直滚动页面或指定元素。'
: 'Scroll page or specific element vertically.',
},
{
name: 'scrollHorizontally(options)',
type: 'Promise<ActionResult>',
description: isZh
? '水平滚动页面或指定元素。'
: 'Scroll page or specific element horizontally.',
},
]}
/>
<h3 className="text-lg font-semibold mt-6 mb-3">{isZh ? '遮罩控制' : 'Mask Control'}</h3>
<APIReference
variant="methods"
properties={[
{
name: 'showMask()',
type: 'Promise<void>',
description: isZh
? '显示视觉遮罩。需要 enableMask: true。'
: 'Show visual mask overlay. Requires enableMask: true.',
},
{
name: 'hideMask()',
type: 'Promise<void>',
description: isZh ? '隐藏视觉遮罩。' : 'Hide visual mask overlay.',
},
]}
/>
<h3 className="text-lg font-semibold mt-6 mb-3">{isZh ? '生命周期' : 'Lifecycle'}</h3>
<APIReference
variant="methods"
properties={[
{
name: 'dispose()',
type: 'void',
description: isZh
? '清理所有资源(DOM 高亮、遮罩等)。Agent 销毁时自动调用。'
: 'Clean up all resources (DOM highlights, mask, etc.). Called automatically when agent disposes.',
},
]}
/>
</section>
<APIDivider title={isZh ? '类型定义' : 'Type Definitions'} />
{/* BrowserState */}
<section className="mb-10">
<Heading id="browser-state">BrowserState</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? 'getBrowserState() 返回的结构化浏览器状态,直接用于构建 LLM prompt。'
: 'Structured browser state returned by getBrowserState(), used directly to build LLM prompts.'}
</p>
<CodeEditor
language="typescript"
code={`interface BrowserState {
url: string
title: string
header: string // page info + scroll position
content: string // simplified HTML of interactive elements
footer: string // scroll hint
}`}
/>
</section>
{/* ActionResult */}
<section className="mb-10">
<Heading id="action-result">ActionResult</Heading>
<CodeEditor
language="typescript"
code={`interface ActionResult {
success: boolean
message: string
}`}
/>
</section>
{/* Custom PageController */}
<section className="mb-10">
<Heading id="custom-implementation">
{isZh ? '自定义实现' : 'Custom Implementation'}
</Heading>
<p className="text-gray-600 dark:text-gray-400 mb-4">
{isZh
? '在非浏览器环境(如 Puppeteer、Playwright),你可以实现自定义 PageController。需要实现 Agent 使用的核心方法:'
: 'In non-browser environments (e.g. Puppeteer, Playwright), you can implement a custom PageController. Implement the core methods used by the agent:'}
</p>
<CodeEditor
language="typescript"
code={`import { PageAgentCore } from '@page-agent/core'
import type { PageController } from '@page-agent/page-controller'
class PuppeteerPageController implements PageController {
async getBrowserState() { /* ... */ }
async clickElement(index: number) { /* ... */ }
async inputText(index: number, text: string) { /* ... */ }
async scroll(options: { down: boolean; numPages: number }) { /* ... */ }
// ... other methods
}
const agent = new PageAgentCore({
pageController: new PuppeteerPageController(),
baseURL: 'https://api.openai.com/v1',
apiKey: 'your-api-key',
model: 'gpt-5.2',
})`}
/>
</section>
</div>
)
}
@@ -1,4 +1,5 @@
import BetaNotice from '@/components/BetaNotice'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function SecurityPermissions() {
@@ -18,9 +19,9 @@ export default function SecurityPermissions() {
<div className="space-y-6">
<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'}
</h2>
</Heading>
<div className="space-y-3">
<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">
@@ -46,9 +47,9 @@ export default function SecurityPermissions() {
</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'}
</h2>
</Heading>
<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">
{isZh ? '高危操作控制' : 'High-Risk Operation Control'}
@@ -1,6 +1,7 @@
import { siChromewebstore, siGithub } from 'simple-icons'
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function ChromeExtension() {
@@ -22,7 +23,9 @@ export default function ChromeExtension() {
<div className="space-y-8 mt-8">
{/* Features */}
<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="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>
@@ -57,7 +60,9 @@ export default function ChromeExtension() {
{/* Install */}
<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">
<a
href={chromeWebStoreUrl}
@@ -86,9 +91,9 @@ export default function ChromeExtension() {
{/* Relationship with PageAgent.js */}
<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'}
</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">
<p>
{isZh
@@ -105,9 +110,9 @@ export default function ChromeExtension() {
{/* Third-party Integration */}
<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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{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。'
@@ -145,7 +150,9 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
{/* API Reference */}
<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 */}
<section className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
@@ -170,9 +177,9 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
</section>
{/* 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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
? '推荐把 `execute` 的类型声明加入你的项目,获得完整类型提示。'
@@ -304,11 +311,14 @@ window.PAGE_AGENT_EXT.stop()`
{/* Integration Guide */}
<section>
<h2 className="text-2xl font-bold mb-4">
<Heading
id="integrate-multipageagent-into-your-extension"
className="text-2xl font-bold mb-4"
>
{isZh
? '将 MultiPageAgent 集成你自己的插件'
: 'Integrate MultiPageAgent into Your Extension'}
</h2>
</Heading>
<p>@TODO</p>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function Instructions() {
@@ -16,9 +17,9 @@ export default function Instructions() {
{/* System Instructions */}
<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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-6">
{isZh
@@ -46,9 +47,9 @@ Guidelines:
{/* Page Instructions */}
<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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-6">
{isZh
@@ -90,7 +91,9 @@ This is the product listing page.
{/* How It Works */}
<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">
{isZh
@@ -1,5 +1,5 @@
import BetaNotice from '@/components/BetaNotice'
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function CustomTools() {
@@ -11,109 +11,100 @@ export default function CustomTools() {
<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
{isZh
? '通过注册自定义工具,扩展 AI Agent 的能力边界。使用 Zod 定义严格的输入接口,让 AI 安全调用你的业务逻辑。'
: 'Extend AI Agent capabilities by registering custom tools. Use Zod to define strict input schemas for safe business logic calls.'}
? '通过注册自定义工具,扩展 AI Agent 的能力边界。使用 Zod 定义输入接口,让 AI 安全调用你的业务逻辑。'
: 'Extend AI Agent capabilities by registering custom tools. Define input schemas with Zod for safe business logic invocation.'}
</p>
<div className="space-y-8">
<section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '工具注册' : 'Tool Registration'}</h2>
<Heading id="zod-version" className="text-2xl font-bold mb-4">
{isZh ? 'Zod 版本' : 'Zod Version'}
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
? '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。'
: 'Each custom tool requires four core properties: name, description, input schema, and execute function.'}
? 'Page Agent 使用 Zod 定义工具的输入 schema。支持 Zod 3 (>=3.25.0) 和 Zod 4,请从 zod/v4 子路径导入。不支持 Zod Mini。'
: 'Page Agent uses Zod for tool input schemas. Both Zod 3 (>=3.25.0) and Zod 4 are supported. Always import from the zod/v4 subpath. Zod Mini is not supported.'}
</p>
<CodeEditor
code={`import * as zod from 'zod'
import { PageAgent, tool } from 'page-agent'
// override internal tool
const customTools = {
ask_user: tool({
description:
'Ask the user or parent model a question and wait for their answer. Use this if you need more information or clarification.',
inputSchema: zod.object({
question: zod.string(),
}),
execute: async function (this: PageAgent, input) {
const answer = await do_some_thing(input.question)
return "✅ Received user answer: " + answer
},
})
}
// remove internal tool
const customTools = {
scroll: null, // never scroll
}
const pageAgent = new PageAgent({customTools})
`}
code={`// Zod 3 (>=3.25.0) or Zod 4
import { z } from 'zod/v4'`}
language="javascript"
/>
</section>
<section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '页面过滤器' : 'Page Filter'}</h2>
<BetaNotice />
<Heading id="define-tools" className="text-2xl font-bold mb-4">
{isZh ? '定义工具' : 'Define Tools'}
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
? '通过 pageFilter 属性控制工具在哪些页面可见,提升安全性和用户体验。'
: 'Control tool visibility on specific pages via the pageFilter property to enhance security and UX.'}
? '使用 tool() 辅助函数定义自定义工具,每个工具包含 description、inputSchema 和 execute 三个属性。'
: 'Use the tool() helper to define custom tools with description, inputSchema, and execute.'}
</p>
<CodeEditor
code={`pageAgent.registerTool({
name: 'approveOrder',
description: '审批订单',
input: z.object({
orderId: z.string(),
approved: z.boolean()
}),
execute: async (params) => {
// 审批逻辑
code={`import { z } from 'zod/v4'
import { PageAgent, tool } from 'page-agent'
const pageAgent = new PageAgent({
customTools: {
//
add_to_cart: tool({
description: 'Add a product to the shopping cart by its product ID.',
inputSchema: z.object({
productId: z.string(),
quantity: z.number().min(1).default(1),
}),
execute: async function (input) {
await fetch('/api/cart', {
method: 'POST',
body: JSON.stringify(input),
})
return \`Added \${input.quantity}x \${input.productId} to cart.\`
},
}),
//
search_knowledge_base: tool({
description: 'Search the internal knowledge base and return relevant articles.',
inputSchema: z.object({
query: z.string(),
limit: z.number().max(10).default(3),
}),
execute: async function (input) {
const res = await fetch(
\`/api/kb?q=\${encodeURIComponent(input.query)}&limit=\${input.limit}\`
)
const articles = await res.json()
return JSON.stringify(articles)
},
}),
},
// 可选:页面过滤器
pageFilter: {
// 只在订单管理页面显示
include: ['/admin/orders', '/admin/orders/*'],
// 排除特定页面
exclude: ['/admin/orders/archived']
}
})`}
language="javascript"
/>
</section>
<section>
<h2 className="text-2xl font-bold mb-4">{isZh ? '最佳实践' : 'Best Practices'}</h2>
<div className="space-y-4">
<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">
{isZh ? '⚡ 性能优化' : '⚡ Performance Optimization'}
</h3>
<ul className="text-gray-600 dark:text-gray-300 space-y-1 text-sm">
<li>
{isZh
? '• 使用 pageFilter 减少不必要的工具加载'
: '• Use pageFilter to reduce unnecessary tool loading'}
</li>
<li>
{isZh
? '• 在 execute 函数中实现适当的缓存机制'
: '• Implement appropriate caching in execute functions'}
</li>
<li>
{isZh
? '• 避免在工具中执行耗时的同步操作'
: '• Avoid long-running sync operations in tools'}
</li>
</ul>
</div>
</div>
<Heading id="override-remove" className="text-2xl font-bold mb-4">
{isZh ? '覆盖与移除内置工具' : 'Override & Remove Built-in Tools'}
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
? '使用相同的名称可以覆盖内置工具的行为,设置为 null 则完全移除该工具。'
: 'Use the same name to override a built-in tool, or set it to null to remove it entirely.'}
</p>
<CodeEditor
code={`const pageAgent = new PageAgent({
customTools: {
scroll: null, // remove scroll tool
execute_javascript: null, // remove script execution
},
})`}
language="javascript"
/>
</section>
</div>
</div>
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function DataMasking() {
@@ -15,7 +16,9 @@ export default function DataMasking() {
</p>
<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
className="mb-6"
@@ -30,9 +33,9 @@ export default function DataMasking() {
</section>
<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'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-6">
{isZh
@@ -1,6 +1,7 @@
import { Fragment } from 'react'
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
const BASELINE = new Set([
@@ -8,15 +9,23 @@ const BASELINE = new Set([
'claude-haiku-4.5',
'gemini-3-flash',
'deepseek-3.2',
'qwen3-coder-next',
'qwen3.5-plus',
'qwen3.5-flash',
])
// Models grouped by brand, newest first
const MODEL_GROUPS: Record<string, string[]> = {
Qwen: [
'qwen3.5-plus',
'qwen3.5-flash',
'qwen3-coder-next',
'qwen-3-max',
'qwen-3-plus',
'qwen3:14b (ollama)',
],
OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'],
Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'],
Qwen: ['qwen3-coder-next', 'qwen-3-max', 'qwen-3-plus', 'qwen3:14b (ollama)'],
DeepSeek: ['deepseek-3.2'],
Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'],
Anthropic: [
'claude-opus-4.6',
'claude-opus-4.5',
@@ -26,7 +35,7 @@ const MODEL_GROUPS: Record<string, string[]> = {
],
xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
MoonshotAI: ['kimi-k2.5'],
'Z.AI': ['glm-4.7'],
'Z.AI': ['glm-5', 'glm-4.7'],
}
const ModelBadge = ({ model, baseline }: { model: string; baseline?: boolean }) => (
@@ -56,7 +65,9 @@ export default function Models() {
{/* Models Section */}
<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">
{isZh
? '推荐使用 ToolCall 能力强的轻量级模型。'
@@ -134,13 +145,13 @@ export default function Models() {
{/* Configuration Section */}
<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
code={`// OpenAI-compatible services (e.g., Alibaba Bailian)
const pageAgent = new PageAgent({
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'your-api-key',
model: 'qwen-plus'
model: 'qwen3.5-plus'
});
// Self-hosted models (e.g., Ollama)
@@ -150,19 +161,63 @@ const pageAgent = new PageAgent({
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>
{/* 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 */}
<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">
{isZh
? '已在 Ollama 0.15 + qwen3:14b (RTX3090 24GB) 上测试通过。'
@@ -193,16 +248,34 @@ LLM_MODEL_NAME="qwen3:14b"`}
{isZh
? '确保上下文长度大于输入 token 数,否则 Ollama 会静默截断 prompt。普通页面约需 15k token,随步骤增加。默认 4k 上下文长度无法正常工作'
: 'Ensure context length exceeds input tokens, or Ollama will silently truncate prompts. ~15k tokens for a typical page, increases with steps. Default 4k context length will NOT work'}
<ul className="text-sm text-gray-700 dark:text-gray-300 space-y-2 list-disc pl-5">
<li>
<code className="text-xs bg-gray-200 dark:bg-gray-700 px-1 rounded">
$env:OLLAMA_CONTEXT_LENGTH=64000; ollama serve
</code>
</li>
</ul>
</li>
</ul>
</div>
<div className="mt-4">
<h3 className="font-semibold text-gray-900 dark:text-gray-100 mb-3">
{isZh ? '建议启动参数' : 'Recommended Startup'}
</h3>
<p className="text-sm text-gray-600 dark:text-gray-400 mb-3">
{isZh
? '启动 Ollama 时建议配置以下环境变量:扩大上下文窗口、允许跨域访问、监听所有网络接口。'
: 'Start Ollama with these environment variables: larger context window, allow cross-origin access, and listen on all interfaces.'}
</p>
<div className="space-y-2">
<p className="text-xs font-medium text-gray-500 dark:text-gray-400">macOS / Linux</p>
<CodeEditor
code={`OLLAMA_CONTEXT_LENGTH=64000 OLLAMA_HOST=0.0.0.0:11434 OLLAMA_ORIGINS="*" ollama serve`}
/>
<p className="text-xs font-medium text-gray-500 dark:text-gray-400 pt-2">
Windows (PowerShell)
</p>
<CodeEditor
code={`$env:OLLAMA_CONTEXT_LENGTH=64000; $env:OLLAMA_HOST="0.0.0.0:11434"; $env:OLLAMA_ORIGINS="*"; ollama serve`}
/>
</div>
</div>
</section>
</div>
)
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function ThirdPartyAgentPage() {
@@ -26,7 +27,9 @@ export default function ThirdPartyAgentPage() {
</p>
</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="p-4 bg-green-50 dark:bg-green-900/20 rounded-lg">
@@ -57,7 +60,9 @@ const pageAgentTool = {
</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="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">
@@ -100,27 +105,6 @@ const pageAgentTool = {
</p>
</div>
</div>
<div className="bg-yellow-50 dark:bg-yellow-900/20 border border-yellow-200 dark:border-yellow-800 rounded-lg p-4 mb-6">
<h3 className="text-lg font-semibold text-yellow-900 dark:text-yellow-100 mb-2">
{isZh ? '⚠️ 注意事项' : '⚠️ Notes'}
</h3>
<ul className="text-yellow-800 dark:text-yellow-200 space-y-1 text-sm">
<li>
{' '}
{isZh
? '确保目标网站允许自动化操作'
: 'Ensure target website allows automated operations'}
</li>
<li> {isZh ? '实现适当的频率限制' : 'Implement appropriate rate limiting'}</li>
<li>
{' '}
{isZh
? '敏感操作建议要求人工确认'
: 'Recommend human confirmation for sensitive operations'}
</li>
</ul>
</div>
</div>
)
}
+17 -21
View File
@@ -1,21 +1,20 @@
import { Suspense } from 'react'
import { Route, Switch } from 'wouter'
import Header from '../../components/Header'
import DocsLayout from './Layout'
import CustomUIDocs from './advanced/custom-ui/page'
import PageAgentCoreDocs from './advanced/page-agent-core/page'
// Advanced
import PageAgentDocs from './advanced/page-agent/page'
import PageControllerDocs from './advanced/page-controller/page'
import SecurityPermissions from './advanced/security-permissions/page'
// Features
import ChromeExtension from './features/chrome-extension/page'
import Instructions from './features/custom-instructions/page'
import CustomTools from './features/custom-tools/page'
import DataMasking from './features/data-masking/page'
import Models from './features/models/page'
import BestPractices from './integration/best-practices/page'
import SecurityPermissions from './integration/security-permissions/page'
import ThirdPartyAgent from './integration/third-party-agent/page'
import ThirdPartyAgent from './features/third-party-agent/page'
import Limitations from './introduction/limitations/page'
// Introduction
import Overview from './introduction/overview/page'
@@ -24,12 +23,9 @@ import Troubleshooting from './introduction/troubleshooting/page'
function DocsPage({ children }: { children: React.ReactNode }) {
return (
<div className="min-h-screen bg-white dark:bg-gray-900">
<Header />
<DocsLayout>
<Suspense>{children}</Suspense>
</DocsLayout>
</div>
<DocsLayout>
<Suspense>{children}</Suspense>
</DocsLayout>
)
}
@@ -84,6 +80,11 @@ export default function DocsRouter() {
<ChromeExtension />
</DocsPage>
</Route>
<Route path="/features/third-party-agent">
<DocsPage>
<ThirdPartyAgent />
</DocsPage>
</Route>
{/* Advanced */}
<Route path="/advanced/page-agent">
@@ -96,26 +97,21 @@ export default function DocsRouter() {
<PageAgentCoreDocs />
</DocsPage>
</Route>
<Route path="/advanced/page-controller">
<DocsPage>
<PageControllerDocs />
</DocsPage>
</Route>
<Route path="/advanced/custom-ui">
<DocsPage>
<CustomUIDocs />
</DocsPage>
</Route>
<Route path="/integration/security-permissions">
<Route path="/advanced/security-permissions">
<DocsPage>
<SecurityPermissions />
</DocsPage>
</Route>
<Route path="/integration/best-practices">
<DocsPage>
<BestPractices />
</DocsPage>
</Route>
<Route path="/integration/third-party-agent">
<DocsPage>
<ThirdPartyAgent />
</DocsPage>
</Route>
{/* Default redirect or 404 */}
<Route path="/docs">
@@ -1,20 +0,0 @@
import BetaNotice from '@/components/BetaNotice'
import CodeEditor from '@/components/CodeEditor'
import { useLanguage } from '@/i18n/context'
export default function BestPractices() {
const { isZh } = useLanguage()
return (
<div>
<h1 className="text-4xl font-bold mb-6">{isZh ? '最佳实践' : 'Best Practices'}</h1>
<BetaNotice />
<p className="text-xl text-gray-600 dark:text-gray-300 mb-6 leading-relaxed">
{isZh
? '使用 page-agent 的最佳实践和常见问题解决方案。'
: 'Best practices and common solutions for using page-agent.'}
</p>
<CodeEditor code={`// TODO`} />
</div>
)
}
@@ -1,5 +1,6 @@
import { Link } from 'wouter'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function LimitationsPage() {
@@ -20,9 +21,9 @@ export default function LimitationsPage() {
<div className="prose prose-lg dark:prose-invert max-w-none">
{/* PageAgent.js vs PageAgentExt */}
<h2 className="text-2xl font-bold mb-3">
<Heading id="pageagent-js-vs-pageagentext" className="text-2xl font-bold mb-3">
{isZh ? 'PageAgent.js vs PageAgentExt' : 'PageAgent.js vs PageAgentExt'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-4">
{isZh
? '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。'
@@ -37,7 +38,7 @@ export default function LimitationsPage() {
<th className="text-left py-3 pl-4 font-semibold">
PageAgentExt{' '}
<Link
href="/docs/features/chrome-extension"
href="/features/chrome-extension"
className="text-xs font-normal text-blue-600 dark:text-blue-400 hover:underline"
>
{isZh ? '了解更多' : 'learn more'}
@@ -82,9 +83,9 @@ export default function LimitationsPage() {
</div>
{/* Interaction Limitations */}
<h2 className="text-2xl font-bold mb-3">
<Heading id="interaction-capabilities" className="text-2xl font-bold mb-3 mt-6">
{isZh ? '交互能力' : 'Interaction Capabilities'}
</h2>
</Heading>
<div className="bg-gray-50 dark:bg-gray-800 rounded-lg p-6 mb-6">
<div className="grid md:grid-cols-2 gap-6">
<div>
@@ -127,31 +128,25 @@ export default function LimitationsPage() {
</div>
{/* Understanding Limitations */}
<h2 className="text-2xl font-bold mb-3">{isZh ? '理解能力' : 'Understanding'}</h2>
<div className="bg-amber-50 dark:bg-amber-900/20 border-l-4 border-amber-400 p-4 mb-6">
<p className="text-amber-800 dark:text-amber-200 mb-2 font-medium">
{isZh
? '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。'
: 'Page Agent does not use multimodal models, does not take screenshots, and has no visual capability. It reads pages through DOM structure only.'}
</p>
<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>
<Heading id="understanding" className="text-2xl font-bold mb-3 mt-6">
{isZh ? '理解能力' : 'Understanding'}
</Heading>
{/* Website Quality */}
<h2 className="text-2xl font-bold mb-3">
{isZh ? '网页质量影响' : 'Page Quality Matters'}
</h2>
<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>
<p className="mb-2 font-medium">
{isZh
? '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。'
: 'Page Agent does not use multimodal models, does not take screenshots, and has no visual capability. It reads pages through DOM structure only.'}
</p>
<p className="mb-2 font-medium">
{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>
<p className="mb-2 font-medium">
{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>
)
@@ -1,3 +1,4 @@
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
export default function Overview() {
@@ -48,9 +49,9 @@ export default function Overview() {
</div>
<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?'}
</h2>
</Heading>
<p className="text-gray-600 dark:text-gray-300 mb-8 leading-relaxed ">
{isZh
@@ -60,7 +61,9 @@ export default function Overview() {
</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="p-4 bg-blue-50 dark:bg-blue-900/20 rounded-lg">
@@ -108,9 +111,9 @@ export default function Overview() {
</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'}
</h2>
</Heading>
<div className="overflow-x-auto mb-8">
<table className="w-full border-collapse border border-gray-300 dark:border-gray-600">
@@ -174,7 +177,9 @@ export default function Overview() {
</table>
</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">
<li className="flex items-start space-x-3">
@@ -1,4 +1,5 @@
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { CDN_DEMO_CN_URL, CDN_DEMO_URL } from '@/constants'
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.'}
</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">
{/* Demo CDN - One Line */}
@@ -23,7 +26,32 @@ export default function QuickStart() {
</h3>
<div className="bg-yellow-50 dark:bg-yellow-900/20 p-2 rounded mb-3 text-sm">
<span className="text-yellow-800 dark:text-yellow-200">
{isZh ? '仅用于技术评估' : 'For evaluation only'}
{' '}
{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>
</div>
<CodeEditor
@@ -71,8 +99,8 @@ import { PageAgent } from 'page-agent'`}
</h3>
<CodeEditor
code={`const agent = new PageAgent({
model: 'deepseek-chat',
baseURL: 'https://api.deepseek.com',
model: 'qwen3.5-plus',
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
apiKey: 'YOUR_API_KEY',
language: '${isZh ? 'zh-CN' : 'en-US'}'
})`}
@@ -2,6 +2,7 @@ import { useEffect, useRef, useState } from 'react'
import { Link } from 'wouter'
import CodeEditor from '@/components/CodeEditor'
import { Heading } from '@/components/Heading'
import { useLanguage } from '@/i18n/context'
// ---------------------------------------------------------------------------
@@ -369,10 +370,13 @@ export default function TroubleshootingPage() {
{/* Main content */}
<div className="flex-1 min-w-0 space-y-12">
{SECTIONS.map((section) => (
<section key={section.id} id={section.id} className="scroll-mt-24">
<h2 className="text-2xl font-bold mb-4 text-gray-900 dark:text-white">
<section key={section.id} className="scroll-mt-24">
<Heading
id={section.id}
className="text-2xl font-bold mb-4 text-gray-900 dark:text-white"
>
{isZh ? section.title.zh : section.title.en}
</h2>
</Heading>
{/* Symptom callout */}
<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>
)
}
+27
View File
@@ -0,0 +1,27 @@
import { Suspense, lazy } from 'react'
import HeroSection from './HeroSection'
const FeaturesSection = lazy(() => import('./FeaturesSection'))
const ScenariosSection = lazy(() => import('./ScenariosSection'))
const OneMoreThingSection = lazy(() => import('./OneMoreThingSection'))
export default function HomePage() {
return (
<>
<HeroSection />
<Suspense
fallback={
<div className="flex items-center justify-center gap-3 py-20 text-gray-400">
<div className="w-4 h-4 border-2 border-blue-500 border-t-transparent rounded-full animate-spin" />
Loading...
</div>
}
>
<FeaturesSection />
<ScenariosSection />
<OneMoreThingSection />
</Suspense>
</>
)
}
+61 -26
View File
@@ -1,35 +1,70 @@
import { Suspense, lazy } from 'react'
import { Route, Switch } from 'wouter'
import { Suspense, lazy, useEffect, useLayoutEffect } from 'react'
import { Route, Switch, useLocation } from 'wouter'
import HomePage from './pages/Home'
import DocsPages from './pages/docs/index'
import Footer from './components/Footer'
import Header from './components/Header'
import HomePage from './pages/home'
// const DocsPages = lazy(() => import('./pages/docs/index'))
const docsImport = () => import('./pages/docs')
const DocsPages = lazy(docsImport)
function ScrollToTop() {
const [pathname] = useLocation()
useLayoutEffect(() => {
window.scrollTo(0, 0)
}, [pathname])
return null
}
export default function Router() {
useEffect(() => {
const schedule = globalThis.requestIdleCallback ?? ((cb: () => void) => setTimeout(cb, 1))
const cancel = globalThis.cancelIdleCallback ?? clearTimeout
const id = schedule(() => docsImport())
return () => cancel(id)
}, [])
return (
<Suspense>
<Switch>
{/* Home page */}
<Route path="/">
<HomePage />
</Route>
<div className="flex min-h-screen flex-col">
<Header />
<Suspense>
<ScrollToTop />
<Switch>
<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>
<DocsPages />
</Route>
{/* 404 */}
<Route>
<div className="min-h-screen 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"></p>
<Route path="/docs" nest>
<div className="flex-1 bg-white dark:bg-gray-900">
<Suspense
fallback={
<div className="flex items-center justify-center gap-3 py-20 text-gray-400">
<div className="w-4 h-4 border-2 border-blue-500 border-t-transparent rounded-full animate-spin" />
Loading...
</div>
}
>
<DocsPages />
</Suspense>
</div>
</div>
</Route>
</Switch>
</Suspense>
</Route>
<Route>
<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 react from '@vitejs/plugin-react-swc'
import { config as dotenvConfig } from 'dotenv'
import { readFileSync } from 'node:fs'
import { copyFileSync, mkdirSync, readFileSync } from 'node:fs'
import process from 'node:process'
import { dirname, resolve } from 'path'
import { dirname, join, resolve } from 'path'
import { fileURLToPath } from 'url'
import { defineConfig } from 'vite'
@@ -15,11 +15,47 @@ const pageAgentPkg = JSON.parse(
// Load .env from repo root
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/features/third-party-agent',
'docs/advanced/page-agent',
'docs/advanced/page-agent-core',
'docs/advanced/page-controller',
'docs/advanced/custom-ui',
'docs/advanced/security-permissions',
]
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 ${SPA_ROUTES.length} SPA routes`)
},
}
}
// Website Config (React Documentation Site)
export default defineConfig(({ mode }) => ({
base: './',
base: '/page-agent/',
clearScreen: false,
plugins: [react(), tailwindcss()],
plugins: [react(), tailwindcss(), spaRoutes()],
build: {
chunkSizeWarningLimit: 2000,
cssCodeSplit: true,
@@ -28,6 +64,11 @@ export default defineConfig(({ mode }) => ({
if (message.code === 'EVAL') return
handler(message)
},
output: {
manualChunks: {
vendor: ['react', 'react-dom', 'wouter'],
},
},
},
},
resolve: {
+1 -1
View File
@@ -111,7 +111,7 @@ const CDN_DEMO_URL_NEW = `https://cdn.jsdelivr.net/npm/page-agent@${newVersion}/
const CDN_DEMO_CN_URL_OLD = `https://registry.npmmirror.com/page-agent/${oldVersion}/files/dist/iife/page-agent.demo.js`
const CDN_DEMO_CN_URL_NEW = `https://registry.npmmirror.com/page-agent/${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) {
const filePath = join(rootDir, relPath)