chore(version): bump version to 1.10.0

feat: remove instructions about nav back

.agents/skills/git-cleanup/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: git-cleanup
+description: Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.
+---
+
+# Git Cleanup
+
+Clean local branches (except `main` and current branch) and non-origin remotes.
+Useful after reviewing multiple PRs that leave behind tracking branches and contributor remotes.
+
+## Workflow
+
+### 1. Survey
+
+Run these in parallel:
+
+```bash
+git branch
+git remote
+git status --short
+git stash list
+```
+
+Present a summary of how many branches and remotes will be removed.
+
+### 2. Safety Checks — Ask Before Proceeding
+
+**Stop and ask for confirmation if any of these are true:**
+
+- Current branch is NOT `main`
+- Working tree has uncommitted changes or stashes
+- Any branch is ahead of its upstream
+
+List unmerged branches separately and let the user decide.
+
+### 3. Delete Branches
+
+```bash
+# Safe delete first (fails on unmerged branches)
+git branch | grep -v '^\*' | grep -v '^\s*main$' | xargs git branch -d 2>&1
+
+# Force-delete only with explicit user approval
+git branch -D <branch>
+```
+
+### 4. Remove Remotes
+
+```bash
+git remote | grep -v '^origin$' | xargs -I{} git remote remove {}
+```
+
+### 5. Confirm
+
+```bash
+git branch && echo "---" && git remote
+```
+
+Report what was cleaned up.
+
+## Key Rules
+
+- **NEVER** delete `main` or the current checked-out branch
+- **NEVER** force-delete unmerged branches without user confirmation
+- If in doubt, ask

.agents/skills/pre-impl-discussion/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: pre-impl-discussion
+description: "Conduct a thorough pre-implementation discussion before making significant changes. Use when the user wants to discuss, plan, or evaluate a change before implementing it — especially when they say words like 'discuss', 'evaluate', 'plan', or 'let's talk about'."
+argument-hint: 'Describe the change to evaluate'
+---
+
+# Pre-Implementation Discussion
+
+Facilitate a structured, collaborative discussion to evaluate a proposed change **before any implementation begins**.
+
+## Golden Rule
+
+**Do NOT implement anything until the user explicitly confirms the final plan and says to proceed.** Not even "let me try on a branch" — that's implementation. The user will tell you when discussion is over.
+
+## Interaction Style
+
+- **Concise during discussion.** Each intermediate response should be short and focused on the current question. Do NOT repeat the full plan in every response.
+- **Complete when finalizing.** Once the plan is mature and the user asks for it, present a single comprehensive (but terse) summary for final review.
+- **Ask, don't assume.** When uncertain about project context, constraints, or preferences — ask. The user prefers collaborative discussion over receiving a pre-baked answer.
+- **Challenge the premise.** Question whether the proposed change is the right one. Suggest simpler alternatives if they exist.
+- **Match the user's language.** Reply in the same language the user writes in.
+
+## Procedure
+
+### 1. Understand the Current State
+
+Before forming any opinion:
+
+- **Read the relevant source files** — configs, code, docs that relate to the change
+- **Understand the project structure** — what's published vs private, what environments things target, existing constraints
+- **Map the impact surface** — which files, packages, or systems would be affected
+- **Estimate implementation cost** — how many files to touch, how much config to rewrite, what could break
+
+Do NOT skip this step. Do NOT rely on assumptions about what "most projects" do.
+
+### 2. Research Thoroughly
+
+- **Consult official sources** — docs, changelogs, migration guides, GitHub issues
+- **Verify every claim with evidence.** Don't say "X supports Y" without a source. If unsure, say so.
+- **Search in parallel** to save time — batch independent queries
+
+Common pitfalls:
+
+- Assuming compatibility without checking actual version constraints
+- Confusing roadmap/aspirations with actual released state
+- Missing transitive constraints (a dependency of a dependency)
+
+### 3. Present Findings (Concise)
+
+Share a **brief** assessment. Tables work well for comparisons. Highlight **blockers** and **unknowns** prominently — don't bury them in paragraphs.
+
+### 4. Identify Key Decisions
+
+Surface the decisions the user needs to make. Present them as clear choices with trade-offs, not as a recommendation monologue.
+
+For each decision point:
+
+- What are the options? (2-3 max)
+- What does each option cost or give up?
+- What's your lean and why? (one sentence)
+
+### 5. Iterate
+
+The user will ask follow-up questions, raise concerns, or challenge assumptions. For each round:
+
+- **Research if needed** — don't answer from instinct when facts are available
+- **Answer only what was asked** — don't re-present the entire plan
+- **Update your mental model** based on user feedback
+
+Common mistakes in this phase:
+
+- Repeating the full plan after every small clarification
+- Answering a narrow question with a broad redesign
+- Treating user questions as confirmation to proceed
+
+### 6. Finalize the Plan
+
+When the user signals the discussion is converging, present the **complete plan once**:
+
+- **What changes** — concrete list of actions (table or bullet points)
+- **Impact surface** — what files/systems are affected, estimated effort
+- **What does NOT change** — explicitly state scope boundaries
+- **Risks or open items** — anything that needs testing or further verification
+
+Keep it terse. Tables over paragraphs. No explanations the user already heard during discussion.
+
+### 7. Wait for Confirmation
+
+After presenting the final plan, **stop and wait**. The user will either:
+
+- Confirm → then (and only then) proceed to implementation
+- Ask more questions → go back to step 5
+- Modify scope → update the plan and re-present
+
+## Anti-Patterns
+
+| Don't                                               | Do Instead                               |
+| --------------------------------------------------- | ---------------------------------------- |
+| Start implementation "to test" without confirmation | Present findings and wait                |
+| Repeat the full plan in every response              | Answer the specific question asked       |
+| Say "X should work" without checking                | Say "I need to verify X" and research it |
+| Assume project structure or constraints             | Read the actual files                    |
+| Present one recommendation as the only option       | Present 2-3 options with trade-offs      |
+| Write long paragraphs explaining trade-offs         | Use tables and bullet points             |

.agents/skills/submit-pr-from-current-changes/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: submit-pr-from-current-changes
+description: 'Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR.'
+argument-hint: 'Short summary of the current changes to submit'
+user-invocable: true
+---
+
+# Submit PR From Current Changes
+
+Turn a working tree diff into a clean branch, commit, and pull request.
+
+## Hard Rules
+
+1. **Follow the PR template exactly.** The template is at `.github/PULL_REQUEST_TEMPLATE.md`. Read it and copy its full structure into the PR body. Do NOT remove, reorder, or skip any section or checkbox.
+2. **Never check "Requirements / 要求" checkboxes.** These are human-only declarations — the Code of Conduct acknowledgment and the AI authorship declaration can only be truthfully made by the human submitter. They MUST remain unchecked (`- [ ]`) in the PR body you generate. No exceptions, no workarounds, even if the user explicitly asks you to check them. The user goes to GitHub and checks them in person after verifying each statement is true.
+3. **Never check "Testing" checkboxes.** The template Testing checkboxes (browser tested, no console errors, types/doc added) require manual browser verification that only a human can perform. They MUST remain unchecked. You MAY add a supplementary note below the Testing section listing what automated validation you actually ran and the results.
+4. **Never fabricate information.** Do not claim tests passed, commands ran, or checks succeeded unless you actually executed them and observed the output in this session. If you did not run it, do not mention it.
+5. **PR output must be concise.** PR title: one line. "What" section: 1–2 sentences max. No walls of text, no redundant explanations. Let the diff speak.
+
+## Prerequisites
+
+Before attempting to push or open a PR, verify that the necessary tools are available:
+
+- Check that `gh` CLI is installed and authenticated (`gh auth status`). If not available, stop and ask the user to install and authenticate GitHub CLI first.
+- If the workflow uses MCP tools for GitHub operations, verify the MCP server is accessible.
+
+## Procedure
+
+1. **Read contribution rules.** Read `CONTRIBUTING.md` and any package-level instructions (e.g. `packages/*/AGENTS.md`) relevant to the changed files.
+2. **Inspect the diff.** Review changed files, scope, and impact. Understand what the change does before writing anything.
+3. **Inspect repo conventions.** Check recent branch names (`git branch -r --sort=-committerdate | head -20`), recent commit messages (`git log --oneline -20`), and the PR template.
+4. **Pre-submission health checks** (run all before creating the PR):
+    - **Unified theme**: All changes should serve one purpose. If unrelated changes are mixed in, ask the user to split or confirm.
+    - **Commit hygiene**: Every new commit must follow the repo's conventional commit style. Squash or reword if needed.
+    - **Author identity**: Verify `git config user.name` and `git config user.email` are set and the email looks real (not empty, not `noreply` unless intentional). Warn the user if not.
+    - **No leftover artifacts**: Check for debug logs, `.only` in tests, conflict markers, or temp files in the diff.
+    - **Lint and build**: Run lint/build for the affected area. Record results honestly.
+5. **Warn if the PR looks too hasty.** If any of these are true, pause and warn the user before proceeding:
+    - Large diff with no description of intent provided
+    - Changes touch core lib or extension (where vibe coding is prohibited per `CONTRIBUTING.md`)
+    - Multiple unrelated concerns in one diff
+    - No validation has been run at all
+    - Remind the user: _"This project does not accept low-quality or AI-generated PRs without meaningful human review. Please review your changes carefully."_
+6. **Branch.** Check the current branch first:
+    - If already on a non-main feature branch with a valid name (matching `type/topic` convention), reuse it.
+    - If the branch name does not follow repo conventions (e.g. missing prefix, unclear topic), ask the user whether to rename or create a new one.
+    - If on `main` or a default branch, create a new branch from it with a short kebab-case name: prefix (`fix/`, `feat/`, `docs/`, `refactor/`, `chore/`) + concrete topic words.
+7. **Stage and commit.** Stage only the intended files. Use `type(scope): subject` format. Keep the subject specific and compact.
+8. **Push.** Push with `-u origin HEAD`.
+9. **Open PR.** Use `gh pr create` with the full PR template structure. Fill in "What" and "Type" sections based on the actual diff. Leave all "Testing" and "Requirements" checkboxes unchecked.
+10. **Report results.** Tell the user: branch name, commit hash, PR link, and what validation actually ran (with pass/fail).
+
+## Post-Submission Reminder
+
+After successfully opening the PR, ALWAYS give a brief reminder in the user's language. Keep it concise and natural, but make sure it clearly tells the user:
+
+1. They need to test the changes themselves in the browser.
+2. They need to go to the PR page and check the Testing and Requirements checkboxes only after verifying each item.
+3. The PR will not enter review until those checkboxes are checked.
+4. The project does not accept autonomously AI-generated PRs, so they should only check the AI declaration if it is truthful.
+
+## Branch Naming
+
+- Prefer short kebab-case names with a repo-consistent prefix such as `fix/`, `feat/`, `docs/`, `refactor/`, or `chore/`.
+- Match the change type first, then the smallest useful topic.
+- Prefer concrete topic words over issue text dumps.
+
+## Commit Style
+
+- Use the repository's prevailing commit style (conventional commits).
+- Use `type(scope): subject` when scope is clear from the changed area.
+- Keep the subject specific and compact.
+- If multiple commits exist on the branch, each one must independently follow conventions.
+
+## Validation Strategy
+
+- Default to enough validation to defend the PR, not the absolute minimum.
+- Run `npm run ci` to run all build and lint checks.
+- Escalate to broader validation when the diff crosses packages, changes shared code, or affects release behavior.
+- Never claim checks that did not actually run.
+- You MAY note what you ran and the results below the Testing section in the PR body, but do NOT check the template checkboxes.
+
+## Decision Points
+
+- No local changes → stop, say so.
+- `gh` CLI not available → stop, ask user to install it.
+- Unrelated files mixed → stage only the intended subset or ask whether the work should be split.
+- If the repo has area-specific instructions, read them before naming the branch or writing the PR.
+- Change is small but high-risk → prefer broader validation.
+- Change is narrowly scoped and low-risk → run the most relevant checks, not arbitrary unrelated ones.
+- Template has declarations you cannot truthfully check → leave unchecked, tell the user why.
+
+## Completion Checks
+
+- The branch exists remotely and tracks upstream.
+- The commit message(s) match repo style.
+- All commit authors have proper name and email configured.
+- The PR title matches the commit intent.
+- The PR body follows the template structure completely.
+- All "Requirements" and "Testing" checkboxes are unchecked (`- [ ]`) in the PR body. Double-check: if any `- [x]` appears in these sections, it is a violation — fix it before submitting.
+- The reported validation is accurate — nothing fabricated.
+- The post-submission reminder was delivered in the user's language, concisely and accurately.

.agents/skills/update-changelog/SKILL.md

@@ -0,0 +1,109 @@
+---
+name: update-changelog
+description: 'Update docs/CHANGELOG.md from git history, GitHub releases, and code diffs. Use when: writing release notes, syncing the latest changelog entry, summarizing a new tag, or keeping changelog wording concise and consistent.'
+argument-hint: 'Describe the target, for example: latest version only'
+---
+
+# Update Changelog
+
+Update `docs/CHANGELOG.md` from repository evidence instead of guesswork.
+
+## When to Use
+
+- Add the newest release entry to `docs/CHANGELOG.md`
+- Sync changelog text with GitHub Releases
+- Summarize the latest tag from git history or code diffs
+
+## Defaults
+
+- Keep the wording brief
+- Only add the latest missing version unless the user explicitly asks to backfill older releases
+- Prefer GitHub sources first, especially Releases and tag metadata
+- Skip `Features` / `Improvements` / `Bug Fixes` headings when the release only has a few clear items
+
+## Procedure
+
+### 1. Read the local style
+
+- Open `docs/CHANGELOG.md`
+- Match the existing tone, bullet style, section ordering, and date format
+
+### 2. Determine the target release
+
+- Read the root `package.json` version and compare it with the top changelog entry
+- Find the previous tag for the target version
+- If the latest version is already documented, stop and report that no changelog update is needed
+
+### 3. Gather evidence
+
+Prefer these sources in order:
+
+1. GitHub release notes
+
+```bash
+GH_PAGER=cat gh release view v<version> --repo <owner>/<repo> --json tagName,name,publishedAt,body
+```
+
+2. Tag date
+
+```bash
+git log -1 --format=%cs v<version>
+```
+
+3. Commit history between tags
+
+```bash
+git --no-pager log --format='%h %s' --no-merges v<previous>..v<version>
+```
+
+4. Diff scope when commit subjects are vague
+
+```bash
+git --no-pager diff --name-only v<previous>..v<version>
+git --no-pager diff --stat v<previous>..v<version>
+```
+
+5. Read touched files directly only when the user-visible change is still unclear
+
+### 4. Distill what belongs in the changelog
+
+Include:
+
+- User-visible features
+- Important behavior changes
+- Bug fixes that improve reliability, compatibility, or developer experience
+- Small docs updates only when they materially change supported setups or onboarding
+
+Exclude unless explicitly requested:
+
+- Pure version bumps
+- Routine dependency updates
+- Internal refactors with no visible impact
+- Mechanical formatting noise
+
+### 5. Choose the structure
+
+- If the release has 1 to 3 clear points, write flat bullets directly under the version heading
+- If the release has several distinct items, use short headings such as `### Features`, `### Improvements`, and `### Bug Fixes`
+- Do not force categories when they make the entry longer or noisier
+
+### 6. Write the entry
+
+- Add or update only the requested release entry
+- Keep bullets short and concrete
+- Reuse project terminology from nearby entries
+- Avoid marketing language
+- Do not copy noisy GitHub release text verbatim
+
+### 7. Verify
+
+- Check dates, version numbers, and tag boundaries
+- Ensure Markdown structure matches nearby entries
+- Confirm no intermediate versions were added unless requested
+
+## Completion Checks
+
+- The newest requested version is documented
+- The wording is concise and consistent with the surrounding changelog
+- The entry is backed by GitHub releases, git history, or code diff evidence
+- Low-signal internal changes were left out

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,61 +1,59 @@
 name: Bug Report
 description: Report a bug
 title: '[Bug] '
-labels: ['bug']
+type: Bug
 body:
   - type: markdown
     attributes:
       value: |
-        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。
+        Thanks for your interest in improving the project! Before submitting, please search for existing issues.
+        感谢参与我们的社区！请先搜索现有 Issue，避免重复提交。
 
         - [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)
 
+        > 为了让更多人参与讨论，请尽量使用英文提交 Issue，感谢理解 🙏
+
   - type: textarea
     id: description
     attributes:
-      label: What happened?
-      placeholder: Describe the bug and expected behavior
+      label: What happened? / 问题描述
+      description: Describe what you expected vs what actually happened.
+      placeholder: 'A clear description of the bug.'
     validations:
       required: true
 
   - type: textarea
-    id: code
+    id: reproduction
     attributes:
-      label: Code
-      render: typescript
-      placeholder: Minimal reproduction code
+      label: How to reproduce / 如何复现
+      description: Provide steps, URL, config or code snippet to reproduce the bug.
+      placeholder: '1. Open URL: https://...'
     validations:
-      required: false
+      required: true
+
+  - type: input
+    id: version
+    attributes:
+      label: Version
+      placeholder: '0.0.0'
 
   - type: input
     id: browser
     attributes:
       label: Browser
-      placeholder: 'Chrome 120, Firefox 119, etc.'
-    validations:
-      required: false
-
-  - type: input
-    id: version
-    attributes:
-      label: version
-      placeholder: '0.0.0'
-    validations:
-      required: false
+      placeholder: 'e.g. Chrome 130'
 
   - type: checkboxes
-    id: community
+    id: checklist
     attributes:
-      label: Community Communication / 社区沟通
-      description: Confirm you will communicate respectfully and constructively / 确认将以礼貌、建设性的方式沟通
+      label: Before submitting
       options:
         - label: I will be polite and respectful. / 我会保持礼貌与尊重。
           required: true
-        - label: I will share constructive, actionable suggestions. / 我会提供建设性、可行动的建议。
-          required: true
         - label: I have read the Code of Conduct. / 我已阅读行为准则。
           required: true
+        - label: I have searched existing issues and this is not a duplicate.
+          required: true
     validations:
       required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -1,11 +1,5 @@
 blank_issues_enabled: false
 contact_links:
-  - name: Questions & Ideas / 问题与想法（Discussions）
-    url: https://github.com/alibaba/page-agent/discussions
-    about: Use Discussions for Q&A and ideation. 使用 Discussions 进行问答与想法交流。
-  - name: Security Report / 安全问题报告
-    url: https://github.com/alibaba/page-agent/security/policy
-    about: Report security vulnerabilities responsibly. 通过安全页面报告漏洞。
   - name: Contributing Guide / 贡献指南
     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。

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -1,32 +1,28 @@
 name: Feature Request
 description: Suggest a feature
 title: '[Feature] '
-labels: ['enhancement']
+type: Feature
 body:
   - type: markdown
     attributes:
       value: |
-        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。
+        Thanks for your interest in improving the project! Before submitting, please search for existing issues.
+        感谢参与我们的社区！请先搜索现有 Issue，避免重复提交。
 
         - [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)
 
+        > 为了让更多人参与讨论，请尽量使用英文提交 Issue，感谢理解 🙏
+
   - type: textarea
     id: description
     attributes:
       label: Feature Description / 功能描述
-      description: Describe the problem, solution, and any API changes. / 描述问题、解决方案以及 API 变更。
+      description: Describe the problem, solution, and any API changes.
       placeholder: |
         **Problem**:
-        What problem does this solve?
-
         **Solution**:
-        How should this work?
-
         **Proposed API**:
-        ```typescript
-        // code here
         ```
     validations:
       required: true
@@ -34,14 +30,13 @@ body:
   - type: checkboxes
     id: community
     attributes:
-      label: Community Communication / 社区沟通
-      description: Confirm you will communicate respectfully and constructively / 确认将以礼貌、建设性的方式沟通
+      label: Before submitting
       options:
         - label: I will be polite and respectful. / 我会保持礼貌与尊重。
           required: true
-        - label: I will share constructive, actionable suggestions. / 我会提供建设性、可行动的建议。
-          required: true
         - label: I have read the CODE_OF_CONDUCT.md and CONTRIBUTING.md. / 我已阅读行为准则。
           required: true
+        - label: I have searched existing issues and this is not a duplicate.
+          required: true
     validations:
       required: true

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,15 +2,15 @@
 
 Brief description of changes.
 
+Closes #(issue)
+
 ## Type
 
+- [ ] Breaking change
 - [ ] Bug fix
 - [ ] Feature / Improvement
-- [ ] Refactor
-- [ ] Documentation
-- [ ] Website
-- [ ] Demo / Testing
-- [ ] Breaking change
+- [ ] Refactor / Chores
+- [ ] Documentation / Website / Demo / Testing
 
 ## Testing
 
@@ -18,8 +18,6 @@ Brief description of changes.
 - [ ] No console errors
 - [ ] Types/doc added
 
-Closes #(issue)
-
 ## Requirements / 要求
 
 - [ ] 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。

.github/dependabot.yml

@@ -4,28 +4,35 @@ updates:
     directory: '/'
     schedule:
       interval: 'weekly'
+    labels:
+      - 'dependencies'
     groups:
-      # 生产依赖 - 小版本更新
       production-dependencies:
         dependency-type: 'production'
         update-types:
           - 'minor'
           - 'patch'
 
-      # 开发依赖 - 小版本更新
       development-dependencies:
         dependency-type: 'development'
         update-types:
           - 'minor'
           - 'patch'
 
-      # Major 更新单独处理（不分组，需要人工审查）
-      # 安全更新也不分组，Dependabot 会自动优先创建独立 PR
+      development-major:
+        dependency-type: 'development'
+        update-types:
+          - 'major'
+
+      # Production major updates are intentionally ungrouped for individual review.
+      # Security updates are also ungrouped — Dependabot prioritizes them automatically.
 
   - package-ecosystem: 'github-actions'
     directory: '/'
     schedule:
       interval: 'weekly'
+    labels:
+      - 'dependencies'
     groups:
       github-actions:
         patterns:

.github/workflows/ci.yml

@@ -1,6 +1,6 @@
+name: CI
 permissions:
   contents: read
-name: CI
 
 on:
   push:
@@ -17,6 +17,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
 
       - name: Setup Node.js ${{ matrix.node-version }}
         uses: actions/setup-node@v6
@@ -24,18 +26,8 @@ jobs:
           node-version: ${{ matrix.node-version }}
           cache: 'npm'
 
-      # test on default version of npm
-      # - 9.6~10.8 on node@20
-      # - 11.3~11.6 on node@24
-
-      - name: Node and NPM version
-        run: node --version && npm --version
-
       - name: Install dependencies
-        run: npm install
+        run: npm ci
 
-      - name: Lint
-        run: npx eslint . && npx prettier --check **/*.ts
-
-      - name: Build
-        run: npm run build
+      - name: CI checks
+        run: node scripts/ci.js

.github/workflows/deploy-demo.yml

@@ -31,7 +31,7 @@ jobs:
         uses: actions/configure-pages@v6
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@v4
+        uses: actions/upload-pages-artifact@v5
         with:
           path: './packages/website/dist'
 

.gitignore

@@ -25,6 +25,9 @@ dist-ssr
 *.sw?
 .qoder
 
+# publish backup
+package.json.bak
+
 # env files
 .env
 .env.*
@@ -34,8 +37,7 @@ dist-ssr
 .wxt
 
 # AI
-.agent
 .claude
 .cursor
 .gemini
-CLAUDE.md
+.codex

.prettierignore

@@ -0,0 +1,8 @@
+# Prompt templates (formatted manually for LLM readability)
+*prompt.md
+
+# Generated
+packages/extension/.wxt
+
+# Vendored
+**/components/ui

.vscode/settings.json

@@ -1,5 +1,6 @@
 {
     "cSpell.words": [
+        "agentic",
         "contenteditable",
         "deepseek",
         "historychange",
@@ -22,7 +23,7 @@
         "packages/*/node_modules": true
     },
     "markdownlint.config": {
-        // "comment": "Relaxed rules",
+        // Relaxed rules
         "default": true,
         "whitespace": false,
         "line_length": false,
@@ -35,5 +36,9 @@
         "blanks-around-lists": false,
         "ol-prefix": false,
         "no-duplicate-heading": false
-    }
+    },
+    "editor.defaultFormatter": "esbenp.prettier-vscode",
+    "js/ts.tsdk.path": "node_modules/typescript/lib",
+    "typescript.tsdk": "node_modules/typescript/lib",
+    "typescript.enablePromptUseWorkspaceTsdk": true
 }

AGENTS.md

@@ -5,7 +5,7 @@
 This is a **monorepo** with npm workspaces:
 
 - **Page Agent** (`packages/page-agent/`) - Main entry with built-in UI Panel, published as `page-agent` on npm
-- **Extension** (`packages/extension/`) - Browser extension (WXT + React) 🚧 WIP
+- **Extension** (`packages/extension/`) - Browser extension (WXT + React)
 - **Website** (`packages/website/`) - React docs and landing page. **When working on website, follow `packages/website/AGENTS.md`**
 
 Internal packages:
@@ -18,18 +18,20 @@ Internal packages:
 ## Development Commands
 
 ```bash
-npm start                    # Start website dev server
-npm run build                # Build all packages
-npm run build:libs           # Build all libraries
-npm run lint                 # ESLint with TypeScript strict rules
-npm run zip -w @page-agent/ext # Zip the extension package
+npm start                      # Start website dev server
+npm run build                  # Build all packages
+npm run build:libs             # Build all libraries
+npm run build:ext              # Build and zip the extension package
+npm run typecheck              # Typecheck all packages
+npm run test                   # Run unit tests across all workspaces
+npm run lint                   # ESLint
 ```
 
 ## Architecture
 
 ### Monorepo Structure
 
-Simple monorepo solution: TypeScript references + Vite aliases. Update tsconfig and vite config when adding/removing packages.
+Source-first monorepo: library `package.json` exports point to `src/*.ts` during development. At publish time, `scripts/pre-publish.js` promotes `publishConfig` fields to top-level (swapping to `dist/`), and `scripts/post-publish.js` restores the originals.
 
 ```
 packages/
@@ -37,7 +39,7 @@ packages/
 ├── page-agent/              # npm: "page-agent" entry class (with UI + controller + demo builds)
 ├── website/                 # @page-agent/website (private)
 ├── llms/                    # @page-agent/llms
-├── extension/               # Browser extension (WXT + React)
+├── extension/               # Browser extension
 ├── page-controller/         # @page-agent/page-controller
 └── ui/                      # @page-agent/ui
 ```
@@ -124,6 +126,20 @@ const pageInfo = await this.pageController.getPageInfo()
 2. Expose via async method in `PageController.ts`
 3. Export from `packages/page-controller/src/index.ts`
 
+## Testing
+
+- **Framework**: Vitest (unit tests only for now; future E2E goes to `packages/e2e/` with Playwright)
+- **Location**: co-located, `src/foo.test.ts` next to `src/foo.ts`
+- **Coverage today**: `packages/llms` only — other packages will follow incrementally
+- **Adding tests to a new package**: create `vitest.config.ts` in the package and add a `"test": "vitest run"` script. Root `npm test` and `node scripts/ci.js` pick it up through npm workspaces.
+- **Template**: See @page-agent/llms
+
+```bash
+npm test                            # all packages with a test script
+npm test -w @page-agent/llms        # single package
+cd packages/llms && npx vitest      # watch mode in one package
+```
+
 ## Code Standards
 
 - Explicit typing for exported/public APIs

CLAUDE.md

@@ -0,0 +1 @@
+@AGENTS.md

README.md

@@ -13,7 +13,9 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua
 
 <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>📖 Docs</b></a> | <a href="https://news.ycombinator.com/item?id=47264138" target="_blank"><b>📢 HN Discussion</b></a> | <a href="https://x.com/simonluvramen" target="_blank"><b>𝕏 Follow on X</b></a>
 
-<video id="demo-video" src="https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2" controls crossorigin muted></video>
+<!-- demo video -->
+
+https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2
 
 ---
 
@@ -50,8 +52,10 @@ Fastest way to try PageAgent with our free Demo LLM:
 
 | Mirrors | URL                                                                                |
 | ------- | ---------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.7.1/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.7.1/files/dist/iife/page-agent.demo.js |
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.10.0/dist/iife/page-agent.demo.js         |
+| China   | https://registry.npmmirror.com/page-agent/1.10.0/files/dist/iife/page-agent.demo.js |
+
+Add `?autoInit=false` to load the script without creating the demo agent automatically. You can then instantiate it with `new window.PageAgent(...)`.
 
 ### NPM Installation
 

docs/CHANGELOG.md

@@ -5,6 +5,149 @@ 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).
 
+## [1.10.0] - 2026-06-15
+
+### Breaking Changes
+
+- **Agent run lifecycle rework** - `stop()` is now async and resolves only after the run fully settles. Run status is decoupled from task outcome: a new `stopped` state was added, and LLM self-reported failures now end as `completed`. Lifecycle hooks re-throw instead of folding errors into the result, agent errors are recorded in history, and `agent.lastResult` was added.
+
+### Features
+
+- **Abortable JavaScript execution** - `execute_javascript` now honors the `AbortSignal`.
+- **Leaner agent prompts** - Simplified the waiting-response flow and removed navigation-back instructions to reduce LLM cognitive load.
+- **MultiPageAgent safety** - Disabled `ScriptExecutionTool` for `MultiPageAgent`.
+
+### Improvements
+
+- **Dark mode detection** - Refined detection heuristics and made `isMainContentDark` less aggressive by checking `html` and `body` data attributes independently.
+- **Extension lifecycle robustness** - Drove heartbeat and running state from status changes, cleared stale activity on any non-running status, handled the stopped lifecycle state, and cleared `currentTabId` on `TabsController.init`.
+
+### Bug Fixes
+
+- **Accurate wait reporting** - Wait steps now report the actual wait duration.
+- **Scroll predicates** - Scroll predicates now return booleans.
+- **Docs** - Fixed the broken demo video on GitHub.
+
+## [1.9.0] - 2026-06-08
+
+### Features
+
+- **Robust abort handling** - Rewrote the aborting system; sync tools, loop execution, and LLM clients now correctly respect task abort signals (`ctx.signal`). Also decoupled `AbortError` from `InvokeError` in `@page-agent/llms`.
+- **Claude Opus 4.8 support** - Added support for Claude Opus 4.8 model.
+
+### Improvements
+
+- **Concurrency guard** - Prevented concurrent `execute()` calls on a single PageAgent/Core instance to avoid race conditions.
+- **Model recommendations refresh** - Updated default and tested model list recommendations.
+- **Test coverage** - Added comprehensive Vitest unit tests for the `@page-agent/llms` package.
+- **Improved documentation** - Added website documentation for the `ctx.signal` abort contract and `execute()` concurrency rules.
+
+### Bug Fixes
+
+- **DTS bundle fix** - Fixed a packaging bug where global type declarations were incorrectly bundled into `.d.ts` outputs.
+- **Website sidebar fix** - Normalized trailing slashes in the website's sidebar location comparison.
+
+## [1.8.2] - 2026-05-11
+
+### Features
+
+- **IIFE demo control** - Added `showPanel` and `autoInit` switches to the IIFE CDN script to control whether the UI panel automatically displays or initializes on load.
+
+### Improvements
+
+- **Build toolchain modernization** - Upgraded build infrastructure to Vite 8.
+
+### Bug Fixes
+
+- **TypeScript `InvokeErrorType` fix** - Separated the value and type space for `InvokeErrorType` to resolve TypeScript compilation issues.
+- **Website chunking fix** - Restored working code-splitting with `manualChunks` for the documentation website.
+
+## [1.8.1] - 2026-04-27
+
+### Features
+
+- **GPT-5.4 & Qwen 3.6 support** - Added support for `gpt-5.4` and `qwen3.6-max/flash` in the recommended LLM list.
+- **Custom LLM request hook** - Added a `transformRequestBody` hook to allow custom modification of payloads before sending requests to LLM providers.
+
+### Improvements
+
+- **Accessibility (a11y) enhancements** - Added descriptive accessible labels to `ConfigPanel` input fields and icon buttons in compliance with WCAG 4.1.2.
+- **UI polish** - Improved `HistoryList` loading and empty states, and added helpful tooltips for actions.
+- **Prompt caching guidance** - Added website documentation for prompt caching optimization.
+- **Build speedups** - Added parallel build scripts to accelerate local development compilation.
+
+### Bug Fixes
+
+- **DeepSeek tool choice fix** - Disabled explicit `tool_choice` for DeepSeek models to avoid API compatibility errors.
+- **MCP version advertising** - MCP server now correctly advertises its package version.
+
+## [1.8.0] - 2026-04-15
+
+### Breaking Changes
+
+- **TypeScript 6 & ESLint 10 upgrade** - Major toolchain modernization. Upgraded the entire monorepo to TypeScript 6 and ESLint 10 with source-first monorepo resolution (library exports resolve to source files directly during local development).
+
+### Improvements
+
+- **MCP security hardening** - Bound the MCP HTTP + WebSocket server to `localhost` only.
+- **Extension UI refinement** - Made the history panel height responsive to the viewport and improved the result card readability by increasing font size.
+
+### Bug Fixes
+
+- **SimulatorMask memory leak** - Fixed a memory leak by ensuring the `requestAnimationFrame` loop is cancelled when disposing the SimulatorMask.
+- **Autofixer format fix** - Corrected the fallback action format for `autoFixer` when waiting.
+- **IIFE scope protection** - Fixed a name collision in IIFE builds by preventing global helper function re-declarations.
+
+## [1.7.1] - 2026-04-04
+
+### Features
+
+- **Optional `keepSemanticTags`** - Added an experimental `keepSemanticTags` config to preserve semantic structure in PageController output
+- **Per-task extension system instructions** - Extension `ExecuteConfig` now supports `systemInstruction`
+
+### Improvements
+
+- **Smarter scroll handling** - Scroll container detection and scroll direction handling are more reliable
+- **Better accessibility-aware element detection** - Interactive candidates with supported ARIA attributes and `role="listitem"` are recognized more accurately
+
+### Bug Fixes
+
+- Fixed iframe-origin filtering for extension `postMessage` listeners
+- Avoided a `currentScript` null pointer during deferred initialization
+
+## [1.7.0] - 2026-03-31
+
+- **More reliable click actions** - Click handling now reuses pointer coordinates, verifies targets with `elementFromPoint`, and behaves better on layered layouts
+- **Better mask event handling** - `SimulatorMask` now supports passthrough events when automation should not fully swallow input
+- Fixed a `SimulatorMask` memory leak
+
+## [1.6.3] - 2026-03-30
+
+### Features
+
+- **Experimental all-tabs control** - Extension can include and control all browser tabs via `experimentalIncludeAllTabs`
+
+### Improvements
+
+- **Calmer empty state motion** - Disabled the EmptyState auto-start animation in the extension UI
+- **Cleaner extension docs** - Simplified setup and tab-control documentation across the README and developer guide
+
+### Bug Fixes
+
+- Fixed new-tab detection from content scripts
+- Fixed tab deduplication and multi-window handling in the extension
+
+## [1.6.2] - 2026-03-25
+
+- **Longer task input** - The UI task input now accepts up to 1000 characters
+- **Contributor docs refresh** - Added a maintainer note and refreshed contributor-facing documentation
+- Fixed lint issues in the release pipeline
+
+## [1.6.1] - 2026-03-22
+
+- **Internal PageController action exports** - PageController actions are now exposed as internal methods for easier reuse across packages
+- **Expanded docs** - Added MCP docs and clarified project limitations and homepage details
+
 ## [1.6.0] - 2026-03-21
 
 ### Features

docs/CODE_OF_CONDUCT.md

@@ -16,22 +16,22 @@ appearance, race, religion, or sexual identity and orientation.
 Examples of behavior that contributes to creating a positive environment
 include:
 
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
 
 Examples of unacceptable behavior by participants include:
 
-* The use of sexualized language or imagery and unwelcome sexual attention or
- advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
- address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
- professional setting
+- The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+- Trolling, insulting/derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
 
 ## Our Responsibilities
 
@@ -85,19 +85,19 @@ available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.ht
 
 有助于创造正面环境的行为包括但不限于：
 
-* 使用友好和包容性语言
-* 尊重不同的观点和经历
-* 耐心地接受建设性批评
-* 关注对社区最有利的事情
-* 友善对待其他社区成员
+- 使用友好和包容性语言
+- 尊重不同的观点和经历
+- 耐心地接受建设性批评
+- 关注对社区最有利的事情
+- 友善对待其他社区成员
 
 身为参与者不能接受的行为包括但不限于：
 
-* 使用与性有关的言语或是图像，以及不受欢迎的性骚扰
-* 捣乱/煽动/造谣的行为或进行侮辱/贬损的评论，人身攻击及政治攻击
-* 公开或私下的骚扰
-* 未经许可地发布他人的个人资料，例如住址或是电子地址
-* 其他可以被合理地认定为不恰当或者违反职业操守的行为
+- 使用与性有关的言语或是图像，以及不受欢迎的性骚扰
+- 捣乱/煽动/造谣的行为或进行侮辱/贬损的评论，人身攻击及政治攻击
+- 公开或私下的骚扰
+- 未经许可地发布他人的个人资料，例如住址或是电子地址
+- 其他可以被合理地认定为不恰当或者违反职业操守的行为
 
 ## 我们的责任
 

docs/README-zh.md

@@ -13,7 +13,9 @@
 
 <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>📖 Docs</b></a> | <a href="https://news.ycombinator.com/item?id=47264138" target="_blank"><b>📢 HN Discussion</b></a> | <a href="https://x.com/simonluvramen" target="_blank"><b>𝕏 Follow on X</b></a>
 
-<video id="demo-video" src="https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2" controls crossorigin muted></video>
+<!-- demo video -->
+
+https://github.com/user-attachments/assets/a1f2eae2-13fb-4aae-98cf-a3fc1620a6c2
 
 ---
 
@@ -49,8 +51,10 @@
 
 | Mirrors | URL                                                                                |
 | ------- | ---------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.7.1/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.7.1/files/dist/iife/page-agent.demo.js |
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.10.0/dist/iife/page-agent.demo.js         |
+| China   | https://registry.npmmirror.com/page-agent/1.10.0/files/dist/iife/page-agent.demo.js |
+
+在 URL 后添加 `?autoInit=false` 可只加载脚本，不自动创建 Demo Agent；之后可通过 `new window.PageAgent(...)` 手动初始化。
 
 ### NPM 安装
 
@@ -106,4 +110,3 @@ this project possible.
 ---
 
 **⭐ 如果觉得 PageAgent 有用或有趣，请给项目点个星！**
-

docs/developer-guide.md

@@ -10,52 +10,41 @@ For contribution rules and expectations, see [../CONTRIBUTING.md](../CONTRIBUTIN
 
 1. **Prerequisites**
     - `macOS` / `Linux` / `WSL`
-    - `node.js >= 20` with `npm >= 10`
+    - `node.js ^22.13 || >=24` with `npm >= 11`
     - An editor that supports `ts/eslint/prettier`
     - Make sure `eslint`, `prettier` and `commitlint` work well. Un-linted code won't pass the CI.
 
 2. **Setup**
 
     ```bash
-    npm i
-    npm start          # Start demo and documentation site
-    npm run build      # Build libs and website
+    npm i            # Or `npm ci` if you don't want to change the lockfile
+    npm start        # Start website dev server
+    npm run build    # Build everything
     ```
 
 ## 📦 Project Structure
 
-This is a **monorepo** with npm workspaces containing **4 main packages**:
+This is a **monorepo** with npm workspaces.
 
-- **Page Agent** (`packages/page-agent/`) - Main entry with built-in UI Panel, published as `page-agent` on npm
+Published packages:
+
+- **Page Agent** (`packages/page-agent/`) - Main entry with built-in UI Panel (npm: `page-agent`)
+- **MCP** (`packages/mcp/`) - MCP server for browser control via Page Agent extension (npm: `@page-agent/mcp`)
 - **Core** (`packages/core/`) - Core agent logic without UI (npm: `@page-agent/core`)
-- **Extension** (`packages/extension/`) - Chrome extension for multi-page tasks and browser-level automation
-- **Website** (`packages/website/`) - React documentation and landing page. Also as demo and test page for the core lib. private package `@page-agent/website`
+- **LLMs** (`packages/llms/`) - LLM client with reflection-before-action mental model
+- **Page Controller** (`packages/page-controller/`) - DOM operations and visual feedback, independent of LLM
+- **UI** (`packages/ui/`) - Panel and i18n, decoupled from PageAgent
 
-> We use a simplified monorepo solution with `native npm-workspace + ts reference + vite alias`. No fancy tooling. Hoisting is required.
->
-> - When developing. Use alias so that we don't have to pre-build.
-> - When bundling. Use external and disable ts `paths` alias.
-> - When bundling `IIFE` and `Website`. Bundle everything together.
+Applications:
+
+- **Extension** (`packages/extension/`) - Browser extension (WXT + React)
+- **Website** (`packages/website/`) - React docs, landing page, and dev playground (private)
+
+> Source-first monorepo with `npm workspaces + ts references + vite alias`. Library `package.json` exports point to `src/*.ts` during development, and point to `dist/*.js` when published. `workspaces` in root `package.json` must be in topological order.
 
 ## 🤖 AGENTS.md Alias
 
-If your AI assistant does not support [AGENTS.md](https://agents.md/). Add an alias for it:
-
-- claude-code (`CLAUDE.md`)
-
-    ```markdown
-    @AGENTS.md
-    ```
-
-- antigravity (`.agent/rules/alias.md`)
-
-    ```markdown
-    ---
-    trigger: always_on
-    ---
-
-    @../../AGENTS.md
-    ```
+If your AI assistant does not support [AGENTS.md](https://agents.md/). Add an alias for it.
 
 ## 🔧 Development Workflows
 
@@ -85,9 +74,8 @@ If your AI assistant does not support [AGENTS.md](https://agents.md/). Add an al
 ### Extension Development
 
 ```bash
-# make sure you ran `npm run build:libs` first and every time you changed the core libs
-npm run dev -w @page-agent/ext
-npm run zip -w @page-agent/ext
+npm run dev:ext
+npm run build:ext
 ```
 
 - Update `packages/extension/docs/extension_api.md` for API integration details

eslint.config.js

@@ -1,8 +1,5 @@
+import eslintReact from '@eslint-react/eslint-plugin'
 import js from '@eslint/js'
-import reactDom from 'eslint-plugin-react-dom'
-import reactHooks from 'eslint-plugin-react-hooks'
-import reactRefresh from 'eslint-plugin-react-refresh'
-import reactX from 'eslint-plugin-react-x'
 import { defineConfig, globalIgnores } from 'eslint/config'
 import globals from 'globals'
 import tseslint from 'typescript-eslint'
@@ -15,44 +12,24 @@ export default defineConfig([
 		'**/.wxt',
 		'**/.output',
 	]),
-	{
-		plugins: {
-			'react-hooks': reactHooks,
-		},
-		rules: reactHooks.configs.recommended.rules,
-	},
 	{
 		files: ['**/*.{ts,tsx}'],
 		extends: [
 			js.configs.recommended,
 			tseslint.configs.recommended,
-			// reactHooks.configs['recommended-latest'],
-			reactRefresh.configs.vite,
-
-			// Remove tseslint.configs.recommended and replace with this
 			...tseslint.configs.recommendedTypeChecked,
-			// Alternatively, use this for stricter rules
 			...tseslint.configs.strictTypeChecked,
-			// Optionally, add this for stylistic rules
 			...tseslint.configs.stylisticTypeChecked,
-
-			// Enable lint rules for React
-			reactX.configs['recommended-typescript'],
-			// Enable lint rules for React DOM
-			reactDom.configs.recommended,
+			eslintReact.configs['recommended-typescript'],
 		],
 		languageOptions: {
 			parserOptions: {
-				// project: ['./tsconfig.json'],
-				// project: ['./packages/*/tsconfig.json'],
-				// tsconfigRootDir: import.meta.dirname,
 				projectService: true,
 			},
 			ecmaVersion: 2020,
 			globals: globals.browser,
 		},
 		rules: {
-			// Add any additional rules here
 			'@typescript-eslint/no-non-null-assertion': 'off',
 			'@typescript-eslint/no-unsafe-assignment': 'off',
 			'@typescript-eslint/no-unsafe-member-access': 'off',
@@ -72,14 +49,14 @@ export default defineConfig([
 			'@typescript-eslint/no-unsafe-argument': 'off',
 			'@typescript-eslint/no-unsafe-return': 'off',
 			'@typescript-eslint/restrict-plus-operands': 'off',
-			'react-dom/no-missing-button-type': 'off',
-			'react-x/no-nested-component-definitions': 'off',
 			'@typescript-eslint/prefer-optional-chain': 'off',
 			'@typescript-eslint/use-unknown-in-catch-callback-variable': 'off',
 			'@typescript-eslint/no-unnecessary-type-parameters': 'off',
-
-			// 'require-await': 'off',
 			'@typescript-eslint/require-await': 'off',
+			'@eslint-react/dom-no-missing-button-type': 'off',
+			'@eslint-react/no-nested-component-definitions': 'off',
+			'@eslint-react/no-array-index-key': 'off',
+			'@eslint-react/dom-no-dangerously-set-innerhtml': 'off',
 		},
 	},
 ])

package.json

@@ -1,7 +1,7 @@
 {
     "name": "root",
     "private": true,
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
     "workspaces": [
         "packages/page-controller",
@@ -22,52 +22,59 @@
     },
     "homepage": "https://alibaba.github.io/page-agent/",
     "engines": {
-        "node": "^20.19.0 || ^22.13.0 || >=24"
+        "node": "^22.22.1 || >=24",
+        "npm": "^11.6.3"
     },
     "scripts": {
         "start": "npm run dev --workspace=@page-agent/website",
         "dev:ext": "npm run dev -w @page-agent/ext",
         "dev:demo": "npm run dev:demo --workspace=page-agent",
-        "build": "npm run build:libs && npm run build:website",
-        "build:libs": "npm run build --workspaces --if-present",
+        "build": "node scripts/build.js",
+        "build:libs": "node scripts/build-libs.js",
         "build:website": "npm run build:website --workspace=@page-agent/website",
-        "build:ext": "npm run build:libs && npm run zip -w @page-agent/ext",
+        "build:ext": "npm run zip -w @page-agent/ext",
         "version": "node scripts/sync-version.js",
+        "postpublish": "npm run postpublish --workspaces --if-present",
+        "typecheck": "tsc --noEmit -p tsconfig.typecheck.json && tsc --noEmit -p packages/extension/tsconfig.json",
+        "test": "npm test --workspaces --if-present",
         "lint": "eslint .",
-        "cleanup": "rm -rf packages/*/dist",
-        "prepare": "husky"
+        "ci": "node scripts/ci.js",
+        "cleanup": "rm -rf packages/*/dist && rm -rf packages/*/.output",
+        "prepare": "husky || true"
     },
     "devDependencies": {
-        "@commitlint/cli": "^20.5.0",
-        "@commitlint/config-conventional": "^20.5.0",
-        "@eslint/js": "^9.39.2",
-        "@microsoft/api-extractor": "^7.57.7",
-        "@tailwindcss/vite": "^4.2.2",
+        "@commitlint/cli": "^21.0.1",
+        "@commitlint/config-conventional": "^21.0.1",
+        "@eslint-react/eslint-plugin": "^5.8.16",
+        "@eslint/js": "^10.0.1",
+        "@microsoft/api-extractor": "^7.58.8",
+        "@tailwindcss/vite": "^4.3.0",
         "@trivago/prettier-plugin-sort-imports": "^6.0.2",
-        "@types/node": "^25.5.0",
-        "@vitejs/plugin-react-swc": "^4.3.0",
+        "@types/node": "^25.9.2",
+        "@vitejs/plugin-react": "^6.0.2",
         "chalk": "^5.6.2",
-        "concurrently": "^9.2.1",
-        "dotenv": "^17.3.1",
-        "eslint": "^9.39.2",
-        "eslint-config-prettier": "^10.1.8",
-        "eslint-plugin-react-dom": "^2.13.0",
-        "eslint-plugin-react-hooks": "^7.0.1",
-        "eslint-plugin-react-refresh": "^0.5.2",
-        "eslint-plugin-react-x": "^2.13.0",
-        "globals": "^17.4.0",
+        "concurrently": "^10.0.3",
+        "dotenv": "^17.4.2",
+        "eslint": "^10.4.0",
+        "globals": "^17.6.0",
         "husky": "^9.1.7",
-        "lint-staged": "^16.4.0",
-        "prettier": "^3.8.0",
-        "typescript": "^5.9.3",
-        "typescript-eslint": "^8.58.0",
-        "unplugin-dts": "^1.0.0-beta.6",
-        "vite": "^7.3.1",
-        "vite-plugin-css-injected-by-js": "^4.0.1",
-        "vite-bundle-analyzer": "^1.3.6"
+        "lint-staged": "^17.0.5",
+        "prettier": "^3.8.3",
+        "typescript": "^6.0.3",
+        "typescript-eslint": "^8.61.0",
+        "unplugin-dts": "^1.0.1",
+        "vite": "^8.0.14",
+        "vite-plugin-css-injected-by-js": "^5.0.1",
+        "vitest": "^4.1.8"
     },
     "overrides": {
-        "typescript": "^5.9.3"
+        "typescript": "^6.0.3",
+        "node-notifier": {
+            "uuid": "11.1.1"
+        },
+        "web-ext-run": {
+            "tmp": "0.2.7"
+        }
     },
     "lint-staged": {
         "*.{js,ts,cjs,cts,mjs,mts}": [

packages/core/package.json

@@ -1,16 +1,26 @@
 {
     "name": "@page-agent/core",
     "private": false,
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
-    "main": "./dist/esm/page-agent-core.js",
-    "module": "./dist/esm/page-agent-core.js",
-    "types": "./dist/esm/PageAgentCore.d.ts",
+    "main": "./src/PageAgentCore.ts",
+    "types": "./src/PageAgentCore.ts",
     "exports": {
         ".": {
-            "types": "./dist/esm/PageAgentCore.d.ts",
-            "import": "./dist/esm/page-agent-core.js",
-            "default": "./dist/esm/page-agent-core.js"
+            "types": "./src/PageAgentCore.ts",
+            "default": "./src/PageAgentCore.ts"
+        }
+    },
+    "publishConfig": {
+        "main": "./dist/esm/page-agent-core.js",
+        "module": "./dist/esm/page-agent-core.js",
+        "types": "./dist/esm/PageAgentCore.d.ts",
+        "exports": {
+            ".": {
+                "types": "./dist/esm/PageAgentCore.d.ts",
+                "import": "./dist/esm/page-agent-core.js",
+                "default": "./dist/esm/page-agent-core.js"
+            }
         }
     },
     "files": [
@@ -38,19 +48,20 @@
     "homepage": "https://alibaba.github.io/page-agent/",
     "scripts": {
         "build": "vite build",
+        "test": "vitest run",
         "dev:iife": "concurrently \"vite build --config vite.iife.config.js --watch\" \"npx serve dist/iife -p 5174\"",
-        "prepublishOnly": "node -e \"const fs=require('fs');['README.md','LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
-        "postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+        "prepublishOnly": "node ../../scripts/pre-publish.js",
+        "postpublish": "node ../../scripts/post-publish.js"
     },
     "dependencies": {
         "chalk": "^5.6.2",
-        "@page-agent/llms": "1.7.1",
-        "@page-agent/page-controller": "1.7.1"
+        "@page-agent/llms": "1.10.0",
+        "@page-agent/page-controller": "1.10.0"
     },
     "peerDependencies": {
         "zod": "^3.25.0 || ^4.0.0"
     },
     "devDependencies": {
-        "zod": "^4.3.5"
+        "zod": "^4.4.3"
     }
 }

packages/core/src/PageAgentCore.test.ts

@@ -0,0 +1,365 @@
+import type { BrowserState, PageController } from '@page-agent/page-controller'
+import { describe, expect, it, vi } from 'vitest'
+import * as z from 'zod/v4'
+
+import { PageAgentCore, tool } from './PageAgentCore'
+import type { ExecutionResult } from './types'
+
+type TestFetch = (...args: Parameters<typeof globalThis.fetch>) => Promise<Response>
+
+function agentResponse(args: unknown): Response {
+	return new Response(
+		JSON.stringify({
+			choices: [
+				{
+					finish_reason: 'tool_calls',
+					message: {
+						tool_calls: [
+							{
+								function: {
+									name: 'AgentOutput',
+									arguments: JSON.stringify(args),
+								},
+							},
+						],
+					},
+				},
+			],
+			usage: {},
+		})
+	)
+}
+
+function createPageController(): PageController {
+	const browserState: BrowserState = {
+		url: 'https://example.test/',
+		title: 'Test page',
+		header: '',
+		content: '',
+		footer: '',
+	}
+
+	return {
+		showMask: vi.fn(async () => {}),
+		hideMask: vi.fn(),
+		cleanUpHighlights: vi.fn(),
+		getLastUpdateTime: vi.fn(() => Date.now()),
+		getBrowserState: vi.fn(async () => browserState),
+		dispose: vi.fn(),
+	} as unknown as PageController
+}
+
+function createAgent(
+	customFetch: TestFetch,
+	options: Partial<ConstructorParameters<typeof PageAgentCore>[0]> = {}
+): PageAgentCore {
+	return new PageAgentCore({
+		baseURL: 'https://llm.test',
+		model: 'test-model',
+		maxRetries: 0,
+		stepDelay: 0,
+		customFetch,
+		customSystemPrompt: 'test',
+		pageController: createPageController(),
+		...options,
+	})
+}
+
+function createFetchMock() {
+	return vi.fn<TestFetch>()
+}
+
+function onceActivity(
+	agent: PageAgentCore,
+	predicate: (detail: unknown) => boolean
+): Promise<void> {
+	return new Promise((resolve) => {
+		const onActivity = (event: Event) => {
+			if (!predicate((event as CustomEvent).detail)) return
+			agent.removeEventListener('activity', onActivity)
+			resolve()
+		}
+
+		agent.addEventListener('activity', onActivity)
+	})
+}
+
+function isExecutingTool(detail: unknown, toolName: string): boolean {
+	return (
+		typeof detail === 'object' &&
+		detail !== null &&
+		'type' in detail &&
+		'tool' in detail &&
+		detail.type === 'executing' &&
+		detail.tool === toolName
+	)
+}
+
+function doneResponse(text: string, success = true): Response {
+	return agentResponse({ action: { done: { text, success } } })
+}
+
+function waitResponse(seconds = 10): Response {
+	return agentResponse({ action: { wait: { seconds } } })
+}
+
+/**
+ * Start a task that blocks on `wait`, returning once the tool is executing.
+ * The running promise is wrapped so awaiting this helper does not await the task.
+ */
+async function startBlockedTask(
+	agent: PageAgentCore,
+	task = 'first'
+): Promise<{ result: Promise<ExecutionResult> }> {
+	const waitStarted = onceActivity(agent, (detail) => isExecutingTool(detail, 'wait'))
+	const result = agent.execute(task)
+	await waitStarted
+	return { result }
+}
+
+describe.concurrent('PageAgentCore lifecycle', () => {
+	describe('normal execution', () => {
+		it('runs a task to natural completion', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(doneResponse('all done'))
+			const agent = createAgent(fetchMock)
+
+			const result = await agent.execute('do something')
+
+			expect(result).toMatchObject({ success: true, data: 'all done' })
+			expect(agent.status).toBe('completed')
+			expect(fetchMock).toHaveBeenCalledTimes(1)
+		})
+
+		it('completes (not errors) when the LLM reports task failure', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(doneResponse('gave up', false))
+			const agent = createAgent(fetchMock)
+
+			const result = await agent.execute('do something')
+
+			expect(result).toMatchObject({ success: false, data: 'gave up' })
+			expect(agent.status).toBe('completed')
+		})
+
+		it('throws when a task is already running', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(waitResponse())
+			const agent = createAgent(fetchMock)
+			const { result } = await startBlockedTask(agent)
+
+			await expect(agent.execute('second')).rejects.toThrow('A task is already running.')
+
+			await agent.stop()
+			await result
+		})
+	})
+
+	describe('stop', () => {
+		it('aborts the running task and keeps the agent reusable', async () => {
+			const fetchMock = createFetchMock()
+				.mockResolvedValueOnce(waitResponse())
+				.mockResolvedValueOnce(doneResponse('second task'))
+			const agent = createAgent(fetchMock)
+			const { result: firstTask } = await startBlockedTask(agent)
+
+			await agent.stop()
+			expect(agent.status).toBe('stopped')
+			await expect(firstTask).resolves.toMatchObject({ success: false, data: 'Task aborted' })
+
+			const secondTask = await agent.execute('second')
+			expect(secondTask).toMatchObject({ success: true, data: 'second task' })
+			expect(agent.status).toBe('completed')
+		})
+
+		it('resolves only after the run has fully settled', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(waitResponse())
+			const agent = createAgent(fetchMock)
+			const { result } = await startBlockedTask(agent)
+
+			await agent.stop()
+			expect(agent.status).toBe('stopped')
+			await expect(result).resolves.toMatchObject({ success: false })
+		})
+
+		it('is a no-op when no task is running', async () => {
+			const agent = createAgent(createFetchMock())
+
+			await expect(agent.stop()).resolves.toBeUndefined()
+			await expect(agent.stop()).resolves.toBeUndefined()
+			expect(agent.status).toBe('idle')
+		})
+	})
+
+	describe('dispose', () => {
+		it('aborts the running task and blocks further execution', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(waitResponse())
+			const agent = createAgent(fetchMock)
+			const { result: task } = await startBlockedTask(agent)
+
+			agent.dispose()
+			await expect(task).resolves.toMatchObject({ success: false, data: 'Task aborted' })
+
+			expect(agent.disposed).toBe(true)
+			await expect(agent.execute('again')).rejects.toThrow('has been disposed')
+		})
+
+		it('is idempotent', () => {
+			const agent = createAgent(createFetchMock())
+
+			expect(() => {
+				agent.dispose()
+				agent.dispose()
+			}).not.toThrow()
+			expect(agent.disposed).toBe(true)
+		})
+	})
+
+	describe('error handling', () => {
+		it('fails the task when the network request rejects', async () => {
+			const fetchMock = createFetchMock().mockRejectedValue(new Error('network down'))
+			const agent = createAgent(fetchMock)
+
+			const result = await agent.execute('do something')
+
+			expect(result.success).toBe(false)
+			expect(agent.status).toBe('error')
+		})
+
+		it('fails the task when a tool throws', async () => {
+			const fetchMock = createFetchMock().mockResolvedValue(agentResponse({ action: { boom: {} } }))
+			const agent = createAgent(fetchMock, {
+				customTools: {
+					boom: tool({
+						description: 'Always throws.',
+						inputSchema: z.object({}),
+						execute: async () => {
+							throw new Error('tool exploded')
+						},
+					}),
+				},
+			})
+
+			const result = await agent.execute('trigger tool error')
+
+			expect(result.success).toBe(false)
+			expect(agent.status).toBe('error')
+		})
+
+		it('re-throws and sets error status when onBeforeTask throws', async () => {
+			const agent = createAgent(createFetchMock(), {
+				onBeforeTask: async () => {
+					throw new Error('setup failed')
+				},
+			})
+
+			await expect(agent.execute('do something')).rejects.toThrow('setup failed')
+			expect(agent.status).toBe('error')
+			expect(agent.history.some((e) => e.type === 'error')).toBe(false)
+		})
+
+		it('re-throws and sets error status when onAfterTask throws', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(doneResponse('all done'))
+			const agent = createAgent(fetchMock, {
+				onAfterTask: async () => {
+					throw new Error('teardown failed')
+				},
+			})
+
+			await expect(agent.execute('do something')).rejects.toThrow('teardown failed')
+			expect(agent.status).toBe('error')
+		})
+
+		it('stays reusable after onBeforeTask throws', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(doneResponse('second'))
+			let failOnce = true
+			const agent = createAgent(fetchMock, {
+				onBeforeTask: async () => {
+					if (failOnce) {
+						failOnce = false
+						throw new Error('setup failed')
+					}
+				},
+			})
+
+			await expect(agent.execute('first')).rejects.toThrow('setup failed')
+			const result = await agent.execute('second')
+			expect(result).toMatchObject({ success: true, data: 'second' })
+		})
+
+		it('re-throws and sets error status when onBeforeStep throws', async () => {
+			const agent = createAgent(createFetchMock(), {
+				onBeforeStep: async () => {
+					throw new Error('before step failed')
+				},
+			})
+
+			await expect(agent.execute('do something')).rejects.toThrow('before step failed')
+			expect(agent.status).toBe('error')
+			expect(agent.history.some((e) => e.type === 'error')).toBe(false)
+		})
+
+		it('re-throws and sets error status when onAfterStep throws', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(doneResponse('all done'))
+			const agent = createAgent(fetchMock, {
+				onAfterStep: async () => {
+					throw new Error('after step failed')
+				},
+			})
+
+			await expect(agent.execute('do something')).rejects.toThrow('after step failed')
+			expect(agent.status).toBe('error')
+			expect(agent.history.some((e) => e.type === 'error')).toBe(false)
+		})
+	})
+
+	describe('cancellation edge cases', () => {
+		it('rejects a new task while a stop is still settling', async () => {
+			const fetchMock = createFetchMock().mockResolvedValueOnce(waitResponse())
+			const agent = createAgent(fetchMock)
+			const { result: firstTask } = await startBlockedTask(agent)
+
+			const stopped = agent.stop()
+
+			await expect(agent.execute('too early')).rejects.toThrow('A task is already running.')
+
+			await stopped
+			await expect(firstTask).resolves.toMatchObject({ success: false, data: 'Task aborted' })
+			expect(fetchMock).toHaveBeenCalledTimes(1)
+		})
+
+		it('discards a custom tool result that resolves after stop', async () => {
+			let resolveTool!: () => void
+			let notifyToolStarted!: () => void
+			const toolFinished = new Promise<void>((resolve) => {
+				resolveTool = resolve
+			})
+			const toolStarted = new Promise<void>((resolve) => {
+				notifyToolStarted = resolve
+			})
+			const fetchMock = createFetchMock().mockResolvedValue(
+				agentResponse({ action: { slow_tool: {} } })
+			)
+			const agent = createAgent(fetchMock, {
+				customTools: {
+					slow_tool: tool({
+						description: 'A tool that deliberately ignores cancellation.',
+						inputSchema: z.object({}),
+						execute: async () => {
+							notifyToolStarted()
+							await toolFinished
+							return 'ignored stop'
+						},
+					}),
+				},
+			})
+
+			const task = agent.execute('run slow tool')
+			await toolStarted
+
+			const stopped = agent.stop()
+			resolveTool()
+			await stopped
+
+			await expect(task).resolves.toMatchObject({ success: false, data: 'Task aborted' })
+			expect(agent.status).toBe('stopped')
+		})
+	})
+})

packages/core/src/PageAgentCore.ts

@@ -21,7 +21,7 @@ import type {
 	MacroToolInput,
 	MacroToolResult,
 } from './types'
-import { assert, fetchLlmsTxt, normalizeResponse, uid, waitFor } from './utils'
+import { assert, fetchLlmsTxt, normalizeResponse, suppress, uid, waitFor } from './utils'
 
 export { tool, type PageAgentTool } from './tools'
 export type * from './types'
@@ -42,7 +42,7 @@ export type PageAgentCoreConfig = AgentConfig & { pageController: PageController
  * - loop
  *
  * ## Event System
- * - `statuschange` - Agent status transitions (idle → running → completed/error)
+ * - `statuschange` - Agent status transitions (idle → running → completed/error/stopped)
  * - `historychange` - History events updated (persistent, part of agent memory)
  * - `activity` - Real-time activity feedback (transient, for UI only)
  * - `dispose` - Agent cleanup triggered
@@ -73,17 +73,28 @@ export class PageAgentCore extends EventTarget {
 	disposed = false
 
 	/**
-	 * Callback for when agent needs user input (ask_user tool)
-	 * If not set, ask_user tool will be disabled
+	 * Called when the agent needs to ask the user questions.
+	 * If unset, the `ask_user` tool will be disabled.
+	 * Implementations should reject the promise when `signal` aborts.
 	 * @example onAskUser: (q) => window.prompt(q) || ''
 	 */
-	onAskUser?: (question: string) => Promise<string>
+	onAskUser?: (question: string, options?: { signal: AbortSignal }) => Promise<string>
 
 	#status: AgentStatus = 'idle'
 	#llm: LLM
+	/**
+	 * Task cancellation primitive: its signal reaches the LLM fetch, tools
+	 * (via `ctx.signal`) and async callbacks. Aborted only by `stop`/`dispose`
+	 * (during a task) or task setup, always WITHOUT a reason so `signal.reason`
+	 * stays a standard `AbortError`.
+	 */
 	#abortController = new AbortController()
 	#observations: string[] = []
 
+	/** Resolves when the current run has fully settled. Awaited by `stop()`. */
+	#running: Promise<void> = Promise.resolve()
+	#lastResult: ExecutionResult | null = null
+
 	/** internal states during a single task execution */
 	#states = {
 		/** Accumulated wait time in seconds */
@@ -103,11 +114,14 @@ export class PageAgentCore extends EventTarget {
 		this.tools = new Map(tools)
 		this.pageController = config.pageController
 
-		// Listen to LLM retry events
 		this.#llm.addEventListener('retry', (e) => {
-			const { attempt, maxAttempts } = (e as CustomEvent).detail
+			const { attempt, maxAttempts, lastError } = (e as CustomEvent).detail
 			this.#emitActivity({ type: 'retrying', attempt, maxAttempts })
-			// Also push to history for panel rendering
+			this.history.push({
+				type: 'error',
+				message: String(lastError),
+				rawResponse: (lastError as InvokeError).rawResponse,
+			})
 			this.history.push({
 				type: 'retry',
 				message: `LLM retry attempt ${attempt} of ${maxAttempts}`,
@@ -116,19 +130,6 @@ export class PageAgentCore extends EventTarget {
 			})
 			this.#emitHistoryChange()
 		})
-		this.#llm.addEventListener('error', (e) => {
-			const error = (e as CustomEvent).detail.error as Error | InvokeError
-			if ((error as any)?.rawError?.name === 'AbortError') return
-			const message = String(error)
-			this.#emitActivity({ type: 'error', message })
-			// Also push to history for panel rendering
-			this.history.push({
-				type: 'error',
-				message,
-				rawResponse: (error as InvokeError).rawResponse,
-			})
-			this.#emitHistoryChange()
-		})
 
 		if (this.config.customTools) {
 			for (const [name, tool] of Object.entries(this.config.customTools)) {
@@ -150,13 +151,19 @@ export class PageAgentCore extends EventTarget {
 		return this.#status
 	}
 
+	/** Result of the most recent run, or `null` before the first run completes. */
+	get lastResult(): ExecutionResult | null {
+		return this.#lastResult
+	}
+
 	/** Emit statuschange event */
 	#emitStatusChange(): void {
 		this.dispatchEvent(new Event('statuschange'))
 	}
 
 	/** Emit historychange event */
-	#emitHistoryChange(): void {
+	#emitHistoryChange(pushHistoricalEvent?: HistoricalEvent): void {
+		if (pushHistoricalEvent) this.history.push(pushHistoricalEvent)
 		this.dispatchEvent(new Event('historychange'))
 	}
 
@@ -186,165 +193,184 @@ export class PageAgentCore extends EventTarget {
 		this.#observations.push(content)
 	}
 
-	/** Stop the current task. Agent remains reusable. */
-	stop() {
-		this.pageController.cleanUpHighlights()
-		this.pageController.hideMask()
+	/**
+	 * Stop the current task and wait until the run has fully settled (including lifecycle hooks).
+	 * @note never await .stop() in a lifecycle hook.
+	 */
+	async stop(): Promise<void> {
+		if (this.#status !== 'running') return
 		this.#abortController.abort()
+		await this.#running
 	}
 
+	/**
+	 * external errors (pre-checks/config/hooks) will threw;
+	 * agent errors will be caught and added to history, and return a failed result
+	 */
 	async execute(task: string): Promise<ExecutionResult> {
+		// pre-checks
 		if (this.disposed) throw new Error('PageAgent has been disposed. Create a new instance.')
+		if (this.#status === 'running') throw new Error('A task is already running.')
 		if (!task) throw new Error('Task is required')
+
 		this.task = task
 		this.taskId = uid()
 
+		this.history = []
+		this.#observations = []
+		this.#states = { totalWaitTime: 0, lastURL: '', browserState: null }
+		this.#abortController = new AbortController()
+		const signal = this.#abortController.signal
+
+		let resolveRunning!: () => void
+		this.#running = new Promise<void>((r) => (resolveRunning = r))
+
+		this.#setStatus('running')
+		this.#emitHistoryChange()
+
 		// Disable ask_user tool if onAskUser is not set
-		if (!this.onAskUser) {
-			this.tools.delete('ask_user')
-		}
+		if (!this.onAskUser) this.tools.delete('ask_user')
 
 		const onBeforeStep = this.config.onBeforeStep
 		const onAfterStep = this.config.onAfterStep
 		const onBeforeTask = this.config.onBeforeTask
 		const onAfterTask = this.config.onAfterTask
-
-		await onBeforeTask?.(this)
-
-		// Show mask
-		await this.pageController.showMask()
-
-		if (this.#abortController) {
-			this.#abortController.abort()
-			this.#abortController = new AbortController()
-		}
-
-		this.history = []
-		this.#setStatus('running')
-		this.#emitHistoryChange()
-		this.#observations = []
-
-		// Reset internal states
-		this.#states = { totalWaitTime: 0, lastURL: '', browserState: null }
+		const stepDelay = this.config.stepDelay ?? 0.4
+		const maxSteps = this.config.maxSteps
 
 		let step = 0
+		let taskResult: ExecutionResult
+		let finalStatus: AgentStatus = 'error'
 
-		while (true) {
-			try {
-				console.group(`step: ${step}`)
+		await suppress(() => this.pageController.showMask())
 
+		// graceful exit
+		try {
+			await onBeforeTask?.(this)
+
+			while (true) {
 				await onBeforeStep?.(this, step)
 
-				// observe
+				// handle internal agent errors
+				try {
+					console.group(`step: ${step}`)
 
-				console.log(chalk.blue.bold('👀 Observing...'))
+					// @note It's convenient to treat stepDelay as part of the next step.
+					// Maybe move it to a dedicated try block for better semantics?
+					if (step > 0) await waitFor(stepDelay, signal)
 
-				this.#states.browserState = await this.pageController.getBrowserState()
-				await this.#handleObservations(step)
+					signal.throwIfAborted()
 
-				// assemble prompts
+					// observe
 
-				const messages = [
-					{ role: 'system' as const, content: this.#getSystemPrompt() },
-					{ role: 'user' as const, content: await this.#assembleUserPrompt() },
-				]
+					console.log(chalk.blue.bold('👀 Observing...'))
 
-				const macroTool = { AgentOutput: this.#packMacroTool() }
+					this.#states.browserState = await this.pageController.getBrowserState()
+					await this.#handleObservations(step)
 
-				// invoke LLM
+					// assemble prompts
 
-				console.log(chalk.blue.bold('🧠 Thinking...'))
-				this.#emitActivity({ type: 'thinking' })
+					const messages = [
+						{ role: 'system' as const, content: this.#getSystemPrompt() },
+						{ role: 'user' as const, content: await this.#assembleUserPrompt() },
+					]
 
-				const result = await this.#llm.invoke(messages, macroTool, this.#abortController.signal, {
-					toolChoiceName: 'AgentOutput',
-					normalizeResponse: (res) => normalizeResponse(res, this.tools),
-				})
+					const macroTool = { AgentOutput: this.#packMacroTool() }
 
-				// assemble history
+					// invoke LLM
 
-				const macroResult = result.toolResult as MacroToolResult
-				const input = macroResult.input
-				const output = macroResult.output
-				const reflection: Partial<AgentReflection> = {
-					evaluation_previous_goal: input.evaluation_previous_goal,
-					memory: input.memory,
-					next_goal: input.next_goal,
-				}
-				const actionName = Object.keys(input.action)[0]
-				const action: AgentStepEvent['action'] = {
-					name: actionName,
-					input: input.action[actionName],
-					output: output,
-				}
+					console.log(chalk.blue.bold('🧠 Thinking...'))
+					this.#emitActivity({ type: 'thinking' })
 
-				this.history.push({
-					type: 'step',
-					stepIndex: step,
-					reflection,
-					action,
-					usage: result.usage,
-					rawResponse: result.rawResponse,
-					rawRequest: result.rawRequest,
-				} as AgentStepEvent)
-				this.#emitHistoryChange()
+					const result = await this.#llm.invoke(messages, macroTool, signal, {
+						toolChoiceName: 'AgentOutput',
+						normalizeResponse: (res) => normalizeResponse(res, this.tools),
+					})
 
-				//
+					// assemble history
 
-				await onAfterStep?.(this, this.history)
-
-				console.groupEnd()
-
-				// finish task if done
-
-				if (actionName === 'done') {
-					const success = action.input?.success ?? false
-					const text = action.input?.text || 'no text provided'
-					console.log(chalk.green.bold('Task completed'), success, text)
-					this.#onDone(success)
-					const result: ExecutionResult = {
-						success,
-						data: text,
-						history: this.history,
+					const macroResult = result.toolResult as MacroToolResult
+					const input = macroResult.input
+					const output = macroResult.output
+					const reflection: Partial<AgentReflection> = {
+						evaluation_previous_goal: input.evaluation_previous_goal,
+						memory: input.memory,
+						next_goal: input.next_goal,
+					}
+					const actionName = Object.keys(input.action)[0]
+					const action: AgentStepEvent['action'] = {
+						name: actionName,
+						input: input.action[actionName],
+						output: output,
 					}
-					await onAfterTask?.(this, result)
-					return result
-				}
-			} catch (error: unknown) {
-				console.groupEnd() // to prevent nested groups
-				const isAbortError = (error as any)?.rawError?.name === 'AbortError'
 
-				console.error('Task failed', error)
-				const errorMessage = isAbortError ? 'Task stopped' : String(error)
-				this.#emitActivity({ type: 'error', message: errorMessage })
-				this.history.push({ type: 'error', message: errorMessage, rawResponse: error })
-				this.#emitHistoryChange()
-				this.#onDone(false)
-				const result: ExecutionResult = {
-					success: false,
-					data: errorMessage,
-					history: this.history,
-				}
-				await onAfterTask?.(this, result)
-				return result
-			}
+					this.#emitHistoryChange({
+						type: 'step',
+						stepIndex: step,
+						reflection,
+						action,
+						usage: result.usage,
+						rawResponse: result.rawResponse,
+						rawRequest: result.rawRequest,
+					})
 
-			step++
-			if (step > this.config.maxSteps) {
-				const errorMessage = 'Step count exceeded maximum limit'
-				this.history.push({ type: 'error', message: errorMessage })
-				this.#emitHistoryChange()
-				this.#onDone(false)
-				const result: ExecutionResult = {
-					success: false,
-					data: errorMessage,
-					history: this.history,
-				}
-				await onAfterTask?.(this, result)
-				return result
-			}
+					if (actionName === 'done') {
+						const success = action.input?.success ?? false
+						const data = action.input?.text || 'no text provided'
+						console.log(chalk.green.bold('Task completed'), success, data)
+						taskResult = { success, data, history: this.history }
+						this.#lastResult = taskResult
+						finalStatus = 'completed'
+						break
+					}
+				} catch (error: unknown) {
+					// catch block must not throw error. otherwise the error may be overridden if finally block also throws error.
 
-			await waitFor(this.config.stepDelay ?? 0.4)
+					const isAbortError = (error as any)?.name === 'AbortError'
+					if (!isAbortError) console.error('Task failed', error)
+					const message = isAbortError ? 'Task aborted' : String(error)
+					this.#emitActivity({ type: 'error', message: message })
+					this.#emitHistoryChange({ type: 'error', message: message, rawResponse: error })
+					taskResult = { success: false, data: message, history: this.history }
+					this.#lastResult = taskResult
+					finalStatus = isAbortError ? 'stopped' : 'error'
+					break
+				} finally {
+					// finally block runs before the break above.
+
+					console.groupEnd()
+					// @note hook may throw error.
+					// which will override the `break` above and be handled as an external error.
+					// as expected.
+					await onAfterStep?.(this, this.history)
+				}
+
+				step++
+				if (step > maxSteps) {
+					const message = 'Step count exceeded maximum limit'
+					console.error(message)
+					this.#emitActivity({ type: 'error', message: message })
+					this.#emitHistoryChange({ type: 'error', message: message })
+					taskResult = { success: false, data: message, history: this.history }
+					this.#lastResult = taskResult
+					finalStatus = 'error'
+					break
+				}
+			} // while
+
+			await onAfterTask?.(this, taskResult)
+
+			return taskResult
+		} catch (error) {
+			this.#emitActivity({ type: 'error', message: String(error) })
+			finalStatus = 'error'
+			throw error
+		} finally {
+			await suppress(() => this.pageController.cleanUpHighlights())
+			await suppress(() => this.pageController.hideMask())
+			this.#abortController.abort()
+			resolveRunning()
+			this.#setStatus(finalStatus)
 		}
 	}
 
@@ -378,8 +404,8 @@ export class PageAgentCore extends EventTarget {
 			description: 'You MUST call this tool every step!',
 			inputSchema: macroToolSchema as z.ZodType<MacroToolInput>,
 			execute: async (input: MacroToolInput): Promise<MacroToolResult> => {
-				// abort
-				if (this.#abortController.signal.aborted) throw new Error('AbortError')
+				const signal = this.#abortController.signal
+				signal.throwIfAborted()
 
 				console.log(chalk.blue.bold('MacroTool input'), input)
 				const action = input.action
@@ -411,8 +437,9 @@ export class PageAgentCore extends EventTarget {
 
 				const startTime = Date.now()
 
-				// Execute tool, bind `this` to PageAgent
-				const result = await tool.execute.bind(this)(toolInput)
+				const result = await tool.execute.bind(this)(toolInput, { signal })
+				// Enforce abort even if the tool ignored the signal and resolved normally.
+				signal.throwIfAborted()
 
 				const duration = Date.now() - startTime
 				console.log(chalk.green.bold(`Tool (${toolName}) executed for ${duration}ms`), result)
@@ -619,13 +646,6 @@ export class PageAgentCore extends EventTarget {
 		return prompt
 	}
 
-	#onDone(success = true) {
-		this.pageController.cleanUpHighlights()
-		this.pageController.hideMask() // No await - fire and forget
-		this.#setStatus(success ? 'completed' : 'error')
-		this.#abortController.abort()
-	}
-
 	dispose() {
 		console.log('Disposing PageAgent...')
 		this.disposed = true

packages/core/src/prompts/.prettierignore

@@ -1 +0,0 @@
-system_prompt.md

packages/core/src/prompts/system_prompt.md

@@ -70,7 +70,6 @@ Strictly follow these rules while using the browser and navigating the web:
 - You can scroll by a specific number of pages using the num_pages parameter (e.g., 0.5 for half page, 2.0 for two pages).
 - All the elements that are scrollable are marked with `data-scrollable` attribute. Including the scrollable distance in every directions. You can scroll *the element* in case some area are overflowed.
 - If a captcha appears, tell user you can not solve captcha. Finish the task and ask user to solve it.
-- If expected elements are missing, try scrolling, or navigating back.
 - If the page is not fully loaded, use the `wait` action.
 - Do not repeat one action for more than 3 times unless some conditions changed.
 - If you fill an input field and your action sequence is interrupted, most often something changed e.g. suggestions popped up under the field.

packages/core/src/tools/index.ts

@@ -7,6 +7,14 @@ import * as z from 'zod/v4'
 import type { PageAgentCore } from '../PageAgentCore'
 import { waitFor } from '../utils'
 
+/**
+ * Per-invocation context passed to every tool execution.
+ * Tools MUST honor `signal` to support cooperative cancellation.
+ */
+export interface ToolContext {
+	signal: AbortSignal
+}
+
 /**
  * Internal tool definition that has access to PageAgent `this` context
  */
@@ -14,7 +22,7 @@ export interface PageAgentTool<TParams = any> {
 	// name: string
 	description: string
 	inputSchema: z.ZodType<TParams>
-	execute: (this: PageAgentCore, args: TParams) => Promise<string>
+	execute: (this: PageAgentCore, args: TParams, ctx: ToolContext) => Promise<string>
 }
 
 export function tool<TParams>(options: PageAgentTool<TParams>): PageAgentTool<TParams> {
@@ -50,14 +58,16 @@ tools.set(
 		inputSchema: z.object({
 			seconds: z.number().min(1).max(10).default(1),
 		}),
-		execute: async function (this: PageAgentCore, input) {
+		execute: async function (this: PageAgentCore, input, { signal }) {
 			// try to subtract LLM calling time from the actual wait time
 			const lastTimeUpdate = await this.pageController.getLastUpdateTime()
-			const actualWaitTime = Math.max(0, input.seconds - (Date.now() - lastTimeUpdate) / 1000)
+			const secondsSinceLastUpdate = (Date.now() - lastTimeUpdate) / 1000
+			const actualWaitTime = Math.max(0, input.seconds - secondsSinceLastUpdate)
 			console.log(`actualWaitTime: ${actualWaitTime} seconds`)
-			await waitFor(actualWaitTime)
+			await waitFor(actualWaitTime, signal)
 
-			return `✅ Waited for ${input.seconds} seconds.`
+			const waitedSeconds = (secondsSinceLastUpdate + actualWaitTime).toFixed(2)
+			return `✅ Waited for ${waitedSeconds} seconds.`
 		},
 	})
 )
@@ -70,11 +80,11 @@ tools.set(
 		inputSchema: z.object({
 			question: z.string(),
 		}),
-		execute: async function (this: PageAgentCore, input) {
+		execute: async function (this: PageAgentCore, input, { signal }) {
 			if (!this.onAskUser) {
 				throw new Error('ask_user tool requires onAskUser callback to be set')
 			}
-			const answer = await this.onAskUser(input.question)
+			const answer = await this.onAskUser(input.question, { signal })
 			return `User answered: ${answer}`
 		},
 	})
@@ -173,12 +183,15 @@ tools.set(
 	'execute_javascript',
 	tool({
 		description:
-			'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution!',
+			'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution! ' +
+			'An `AbortSignal` named `signal` is available in scope: long-running async code MUST honor it ' +
+			'(e.g. `await fetch(url, { signal })`, or `signal.throwIfAborted()` in loops)',
 		inputSchema: z.object({
 			script: z.string(),
 		}),
-		execute: async function (this: PageAgentCore, input) {
-			const result = await this.pageController.executeJavascript(input.script)
+		execute: async function (this: PageAgentCore, input, { signal }) {
+			const result = await this.pageController.executeJavascript(input.script, signal)
+			signal.throwIfAborted()
 			return result.message
 		},
 	})
@@ -186,5 +199,4 @@ tools.set(
 
 // @todo send_keys
 // @todo upload_file
-// @todo go_back
 // @todo extract_structured_data

packages/core/src/types.ts

@@ -262,9 +262,9 @@ export type HistoricalEvent =
 	| AgentErrorEvent
 
 /**
- * Agent execution status
+ * Agent lifecycle status.
  */
-export type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
+export type AgentStatus = 'idle' | 'running' | 'completed' | 'error' | 'stopped'
 
 /**
  * Agent activity - transient state for immediate UI feedback.

packages/core/src/utils/autoFixer.ts

@@ -1,4 +1,4 @@
-import { InvokeError, InvokeErrorType } from '@page-agent/llms'
+import { InvokeError, InvokeErrorTypes } from '@page-agent/llms'
 import chalk from 'chalk'
 import * as z from 'zod/v4'
 
@@ -19,7 +19,7 @@ const log = console.log.bind(console, chalk.yellow('[autoFixer]'))
  * - etc.
  */
 export function normalizeResponse(response: any, tools?: Map<string, PageAgentTool>): any {
-	let resolvedArguments = null as any
+	let resolvedArguments: any
 
 	const choice = (response as { choices?: Choice[] }).choices?.[0]
 	if (!choice) throw new Error('No choices in response')
@@ -93,7 +93,7 @@ export function normalizeResponse(response: any, tools?: Map<string, PageAgentTo
 	// fix incomplete formats
 	if (!resolvedArguments.action) {
 		log(`#5: fixing tool_call`)
-		resolvedArguments.action = { name: 'wait', input: { seconds: 1 } }
+		resolvedArguments.action = { wait: { seconds: 1 } }
 	}
 
 	// pack back to standard format
@@ -137,7 +137,7 @@ function validateAction(action: any, tools: Map<string, PageAgentTool>): any {
 	if (!tool) {
 		const available = Array.from(tools.keys()).join(', ')
 		throw new InvokeError(
-			InvokeErrorType.INVALID_TOOL_ARGS,
+			InvokeErrorTypes.INVALID_TOOL_ARGS,
 			`Unknown action "${toolName}". Available: ${available}`
 		)
 	}
@@ -159,7 +159,7 @@ function validateAction(action: any, tools: Map<string, PageAgentTool>): any {
 	const result = schema.safeParse(value)
 	if (!result.success) {
 		throw new InvokeError(
-			InvokeErrorType.INVALID_TOOL_ARGS,
+			InvokeErrorTypes.INVALID_TOOL_ARGS,
 			`Invalid input for action "${toolName}": ${z.prettifyError(result.error)}`
 		)
 	}

packages/core/src/utils/index.ts

@@ -2,8 +2,28 @@ import chalk from 'chalk'
 
 export * from './autoFixer'
 
-export async function waitFor(seconds: number): Promise<void> {
-	await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
+/**
+ * Wait for `seconds`. If a `signal` is provided, the wait is cancellable:
+ * aborting rejects with the signal's reason (an `AbortError`).
+ */
+export async function waitFor(seconds: number, signal?: AbortSignal): Promise<void> {
+	if (!signal) {
+		await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
+		return
+	}
+	signal.throwIfAborted()
+	await new Promise<void>((resolve, reject) => {
+		const timer = setTimeout(() => {
+			signal.removeEventListener('abort', onAbort)
+			resolve()
+		}, seconds * 1000)
+		const onAbort = () => {
+			clearTimeout(timer)
+			// reason is a DOMException AbortError.
+			reject(signal.reason as DOMException)
+		}
+		signal.addEventListener('abort', onAbort, { once: true })
+	})
 }
 
 //
@@ -109,3 +129,15 @@ export function assert(condition: unknown, message?: string, silent?: boolean):
 		throw new Error(errorMessage)
 	}
 }
+
+/**
+ * Suppress errors from a function.
+ */
+export async function suppress<T>(fn: () => T | Promise<T>): Promise<Awaited<T> | undefined> {
+	try {
+		return await fn()
+	} catch (error) {
+		console.error(error)
+		return undefined
+	}
+}

packages/core/tsconfig.dts.json

@@ -1,9 +0,0 @@
-{
-    "extends": "./tsconfig.json",
-    "compilerOptions": {
-        // @workaround DTS bug
-        // dts do not work with monorepo path mapping
-        // disable path mapping for it
-        "paths": {}
-    }
-}

packages/core/tsconfig.json

@@ -1,22 +1,8 @@
 {
     "extends": "../../tsconfig.base.json",
     "compilerOptions": {
-        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
-        "noEmit": false,
-        "allowImportingTsExtensions": false,
-        "baseUrl": ".",
-        "outDir": "dist",
-        "paths": {
-            //
-            "@page-agent/llms": ["../llms/src/index.ts"],
-            "@page-agent/page-controller": ["../page-controller/src/PageController.ts"]
-        }
+        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo"
     },
-    "include": ["**/*.ts"],
-    "exclude": ["dist", "node_modules"],
-    "references": [
-        //
-        { "path": "../llms" },
-        { "path": "../page-controller" }
-    ]
+    "include": ["src/**/*.ts"],
+    "exclude": ["dist", "node_modules"]
 }

packages/core/vite.config.js

@@ -11,13 +11,20 @@ const __dirname = dirname(fileURLToPath(import.meta.url))
 export default defineConfig({
 	clearScreen: false,
 	plugins: [
-		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
+		dts({
+			include: ['src/**/*.ts'],
+			exclude: ['src/**/*.test.ts'],
+			bundleTypes: true,
+			compilerOptions: {
+				composite: true,
+				noEmit: false,
+				emitDeclarationOnly: true,
+				declaration: true,
+			},
+		}),
 		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
 	],
 	publicDir: false,
-	esbuild: {
-		keepNames: true,
-	},
 	build: {
 		lib: {
 			entry: resolve(__dirname, 'src/PageAgentCore.ts'),

packages/core/vitest.config.js

@@ -0,0 +1,9 @@
+import { defineConfig } from 'vitest/config'
+
+export default defineConfig({
+	test: {
+		name: 'core',
+		include: ['src/**/*.test.ts'],
+		silent: 'passed-only',
+	},
+})

packages/extension/.prettierignore

@@ -1,2 +0,0 @@
-.wxt
-src/components/ui

packages/extension/docs/extension_api.md

@@ -42,33 +42,28 @@ localStorage.setItem('PageAgentExtUserAuthToken', 'your-token')
 ## Quick Start
 
 ```typescript
-import type {
-  AgentActivity,
-  AgentStatus,
-  ExecutionResult,
-  HistoricalEvent,
-} from '@page-agent/core'
+import type { AgentActivity, AgentStatus, ExecutionResult, HistoricalEvent } from '@page-agent/core'
 
 // Wait for extension injection (up to 1 second)
 async function waitForExtension(timeout = 1000): Promise<boolean> {
-  const start = Date.now()
-  while (Date.now() - start < timeout) {
-    if (window.PAGE_AGENT_EXT) return true
-    await new Promise((r) => setTimeout(r, 100))
-  }
-  return false
+    const start = Date.now()
+    while (Date.now() - start < timeout) {
+        if (window.PAGE_AGENT_EXT) return true
+        await new Promise((r) => setTimeout(r, 100))
+    }
+    return false
 }
 
 // Usage
 if (await waitForExtension()) {
-  const result = await window.PAGE_AGENT_EXT!.execute('Click the login button', {
-    baseURL: 'https://api.openai.com/v1',
-    apiKey: 'your-api-key',
-    model: 'gpt-5.2',
-    onStatusChange: (status) => console.log('Status:', status),
-    onActivity: (activity) => console.log('Activity:', activity),
-  })
-  console.log('Result:', result)
+    const result = await window.PAGE_AGENT_EXT!.execute('Click the login button', {
+        baseURL: 'https://api.openai.com/v1',
+        apiKey: 'your-api-key',
+        model: 'gpt-5.2',
+        onStatusChange: (status) => console.log('Status:', status),
+        onActivity: (activity) => console.log('Activity:', activity),
+    })
+    console.log('Result:', result)
 }
 ```
 
@@ -90,10 +85,10 @@ Execute one agent task.
 
 Parameters:
 
-| Name | Type | Required | Description |
-| ---- | ---- | -------- | ----------- |
-| `task` | `string` | Yes | Task description |
-| `config` | `ExecuteConfig` | Yes | LLM settings, options, and callbacks |
+| Name     | Type            | Required | Description                          |
+| -------- | --------------- | -------- | ------------------------------------ |
+| `task`   | `string`        | Yes      | Task description                     |
+| `config` | `ExecuteConfig` | Yes      | LLM settings, options, and callbacks |
 
 Returns: `Promise<ExecutionResult>`
 
@@ -106,33 +101,28 @@ Stop the current task.
 Install `@page-agent/core` for complete types:
 
 ```typescript
-import type {
-  AgentActivity,
-  AgentStatus,
-  ExecutionResult,
-  HistoricalEvent,
-} from '@page-agent/core'
+import type { AgentActivity, AgentStatus, ExecutionResult, HistoricalEvent } from '@page-agent/core'
 
 export interface ExecuteConfig {
-  baseURL: string
-  model: string
-  apiKey?: string
+    baseURL: string
+    model: string
+    apiKey?: string
 
-  // Global system-level instructions for the agent.
-  // Equivalent to AgentConfig.instructions.system.
-  systemInstruction?: string
+    // Global system-level instructions for the agent.
+    // Equivalent to AgentConfig.instructions.system.
+    systemInstruction?: string
 
-  // Include the initial tab where page JS starts. Default: true.
-  includeInitialTab?: boolean
+    // Include the initial tab where page JS starts. Default: true.
+    includeInitialTab?: boolean
 
-  // Control all unpinned tabs in the window instead of only the tab group.
-  // When enabled, agent sees and can switch to every non-pinned tab.
-  // Default: false. Experimental.
-  experimentalIncludeAllTabs?: boolean
+    // Control all unpinned tabs in the window instead of only the tab group.
+    // When enabled, agent sees and can switch to every non-pinned tab.
+    // Default: false. Experimental.
+    experimentalIncludeAllTabs?: boolean
 
-  onStatusChange?: (status: AgentStatus) => void
-  onActivity?: (activity: AgentActivity) => void
-  onHistoryUpdate?: (history: HistoricalEvent[]) => void
+    onStatusChange?: (status: AgentStatus) => void
+    onActivity?: (activity: AgentActivity) => void
+    onHistoryUpdate?: (history: HistoricalEvent[]) => void
 }
 
 export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
@@ -141,38 +131,38 @@ export type Execute = (task: string, config: ExecuteConfig) => Promise<Execution
 `AgentStatus`
 
 ```typescript
-type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
+type AgentStatus = 'idle' | 'running' | 'completed' | 'error' | 'stopped'
 ```
 
 `AgentActivity`
 
 ```typescript
 type AgentActivity =
-  | { type: 'thinking' }
-  | { type: 'executing'; tool: string; input: unknown }
-  | { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
-  | { type: 'retrying'; attempt: number; maxAttempts: number }
-  | { type: 'error'; message: string }
+    | { type: 'thinking' }
+    | { type: 'executing'; tool: string; input: unknown }
+    | { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
+    | { type: 'retrying'; attempt: number; maxAttempts: number }
+    | { type: 'error'; message: string }
 ```
 
 `HistoricalEvent`
 
 ```typescript
 type HistoricalEvent =
-  | { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
-  | { type: 'observation'; content: string }
-  | { type: 'user_takeover' }
-  | { type: 'retry'; message: string; attempt: number; maxAttempts: number }
-  | { type: 'error'; message: string; rawResponse?: unknown }
+    | { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
+    | { type: 'observation'; content: string }
+    | { type: 'user_takeover' }
+    | { type: 'retry'; message: string; attempt: number; maxAttempts: number }
+    | { type: 'error'; message: string; rawResponse?: unknown }
 ```
 
 `ExecutionResult`
 
 ```typescript
 interface ExecutionResult {
-  success: boolean
-  data: string
-  history: HistoricalEvent[]
+    success: boolean
+    data: string
+    history: HistoricalEvent[]
 }
 ```
 
@@ -182,15 +172,15 @@ interface ExecutionResult {
 
 ```typescript
 const result = await window.PAGE_AGENT_EXT!.execute(
-  'Fill in the email field with test@example.com and click Submit',
-  {
-    baseURL: 'https://api.openai.com/v1',
-    apiKey: process.env.OPENAI_API_KEY!,
-    model: 'gpt-5.2',
-    includeInitialTab: false, // Optional: exclude current tab
-    onStatusChange: (status) => console.log(status),
-    onActivity: (activity) => console.log(activity),
-  }
+    'Fill in the email field with test@example.com and click Submit',
+    {
+        baseURL: 'https://api.openai.com/v1',
+        apiKey: process.env.OPENAI_API_KEY!,
+        model: 'gpt-5.2',
+        includeInitialTab: false, // Optional: exclude current tab
+        onStatusChange: (status) => console.log(status),
+        onActivity: (activity) => console.log(activity),
+    }
 )
 ```
 
@@ -205,35 +195,30 @@ window.PAGE_AGENT_EXT!.stop()
 If you are not importing `@page-agent/core`, add:
 
 ```typescript
-import type {
-  AgentActivity,
-  AgentStatus,
-  ExecutionResult,
-  HistoricalEvent,
-} from '@page-agent/core'
+import type { AgentActivity, AgentStatus, ExecutionResult, HistoricalEvent } from '@page-agent/core'
 
 interface ExecuteConfig {
-  baseURL: string
-  model: string
-  apiKey?: string
+    baseURL: string
+    model: string
+    apiKey?: string
 
-  systemInstruction?: string
+    systemInstruction?: string
 
-  includeInitialTab?: boolean
-  experimentalIncludeAllTabs?: boolean
-  onStatusChange?: (status: AgentStatus) => void
-  onActivity?: (activity: AgentActivity) => void
-  onHistoryUpdate?: (history: HistoricalEvent[]) => void
+    includeInitialTab?: boolean
+    experimentalIncludeAllTabs?: boolean
+    onStatusChange?: (status: AgentStatus) => void
+    onActivity?: (activity: AgentActivity) => void
+    onHistoryUpdate?: (history: HistoricalEvent[]) => void
 }
 
 declare global {
-  interface Window {
-    PAGE_AGENT_EXT_VERSION?: string
-    PAGE_AGENT_EXT?: {
-      version: string
-      execute: Execute
-      stop: () => void
+    interface Window {
+        PAGE_AGENT_EXT_VERSION?: string
+        PAGE_AGENT_EXT?: {
+            version: string
+            execute: Execute
+            stop: () => void
+        }
     }
-  }
 }
 ```

packages/extension/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/ext",
     "private": true,
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
     "scripts": {
         "dev": "wxt",
@@ -10,37 +10,38 @@
         "postinstall": "wxt prepare"
     },
     "devDependencies": {
-        "@radix-ui/react-hover-card": "^1.1.15",
+        "@radix-ui/react-hover-card": "^1.1.16",
         "@radix-ui/react-icons": "^1.3.2",
-        "@radix-ui/react-label": "^2.1.8",
-        "@radix-ui/react-separator": "^1.1.8",
+        "@radix-ui/react-label": "^2.1.9",
+        "@radix-ui/react-separator": "^1.1.9",
         "@radix-ui/react-slot": "^1.2.4",
-        "@radix-ui/react-switch": "^1.2.6",
-        "@types/chrome": "^0.1.38",
-        "@types/react": "^19.2.14",
-        "@types/react-dom": "^19.2.1",
+        "@radix-ui/react-switch": "^1.3.0",
+        "@tailwindcss/vite": "^4.3.0",
+        "@types/chrome": "^0.1.43",
+        "@types/react": "^19.2.17",
+        "@types/react-dom": "^19.2.3",
         "@wxt-dev/module-react": "^1.2.2",
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
         "idb": "^8.0.3",
-        "lucide-react": "^1.7.0",
-        "motion": "^12.38.0",
+        "lucide-react": "^1.16.0",
+        "motion": "^12.40.0",
         "next-themes": "^0.4.6",
-        "react": "^19.2.4",
-        "react-dom": "^19.2.4",
+        "react": "^19.2.6",
+        "react-dom": "^19.2.6",
         "rough-notation": "^0.5.1",
-        "simple-icons": "^16.14.0",
+        "simple-icons": "^16.23.0",
         "sonner": "^2.0.7",
-        "tailwind-merge": "^3.5.0",
-        "tailwindcss": "^4.1.14",
+        "tailwind-merge": "^3.6.0",
+        "tailwindcss": "^4.3.0",
         "tw-animate-css": "^1.4.0",
-        "wxt": "^0.20.20"
+        "wxt": "^0.20.26"
     },
     "dependencies": {
-        "@page-agent/core": "1.7.1",
-        "@page-agent/llms": "1.7.1",
-        "@page-agent/page-controller": "1.7.1",
-        "@page-agent/ui": "1.7.1",
+        "@page-agent/core": "1.10.0",
+        "@page-agent/llms": "1.10.0",
+        "@page-agent/page-controller": "1.10.0",
+        "@page-agent/ui": "1.10.0",
         "ai-motion": "^0.4.8",
         "chalk": "^5.6.2"
     },

packages/extension/public/_locales/en/messages.json

@@ -1,11 +1,11 @@
 {
-	"extName": {
-		"message": "Page Agent Ext"
-	},
-	"extDescription": {
-		"message": "AI-powered browser automation assistant. Control web pages with natural language."
-	},
-	"extActionTitle": {
-		"message": "Open Page Agent"
-	}
+    "extName": {
+        "message": "Page Agent Ext"
+    },
+    "extDescription": {
+        "message": "AI-powered browser automation assistant. Control web pages with natural language."
+    },
+    "extActionTitle": {
+        "message": "Open Page Agent"
+    }
 }

packages/extension/public/_locales/zh_CN/messages.json

@@ -1,11 +1,11 @@
 {
-	"extName": {
-		"message": "Page Agent Ext"
-	},
-	"extDescription": {
-		"message": "AI 驱动的浏览器自动化助手，用自然语言控制网页。"
-	},
-	"extActionTitle": {
-		"message": "打开 Page Agent"
-	}
+    "extName": {
+        "message": "Page Agent Ext"
+    },
+    "extDescription": {
+        "message": "AI 驱动的浏览器自动化助手，用自然语言控制网页。"
+    },
+    "extActionTitle": {
+        "message": "打开 Page Agent"
+    }
 }

packages/extension/src/agent/.prettierignore

@@ -1 +0,0 @@
-system_prompt.md

packages/extension/src/agent/MultiPageAgent.ts

@@ -40,43 +40,27 @@ export class MultiPageAgent extends PageAgentCore {
 		const experimentalIncludeAllTabs = config.experimentalIncludeAllTabs ?? false
 
 		/**
+		 * Project agent status into chrome.storage. The content script polls
+		 * `isAgentRunning` + `agentHeartbeat` (eventually consistent by design).
+		 *
 		 * When the agent is in side-panel and user closed the side-panel.
 		 * There is no chance for isAgentRunning to be set false.
 		 * (unload event doesn't work well in side panel.)
 		 * (I'm trying not to use long-lived connection because the lifecycle of a sw is hard to predict.)
 		 * This heartbeat mechanism acts as a backup.
 		 */
-		let heartBeatInterval: null | number = null
+		let heartBeatInterval: number | null = null
 
 		super({
 			...config,
+			// Disabled: AbortSignal cannot cross contexts
+			experimentalScriptExecutionTool: false,
 			pageController: pageController as any,
 			customTools: customTools,
 			customSystemPrompt: systemPrompt,
 
 			onBeforeTask: async (agent) => {
 				await tabsController.init(agent.task, { includeInitialTab, experimentalIncludeAllTabs })
-
-				heartBeatInterval = window.setInterval(() => {
-					chrome.storage.local.set({
-						agentHeartbeat: Date.now(),
-					})
-				}, 1_000)
-
-				await chrome.storage.local.set({
-					isAgentRunning: true,
-				})
-			},
-
-			onAfterTask: async () => {
-				if (heartBeatInterval) {
-					window.clearInterval(heartBeatInterval)
-					heartBeatInterval = null
-				}
-
-				await chrome.storage.local.set({
-					isAgentRunning: false,
-				})
 			},
 
 			onBeforeStep: async (agent) => {
@@ -87,16 +71,28 @@ export class MultiPageAgent extends PageAgentCore {
 
 			onDispose: () => {
 				if (heartBeatInterval) {
-					window.clearInterval(heartBeatInterval)
+					clearInterval(heartBeatInterval)
 					heartBeatInterval = null
 				}
-
-				chrome.storage.local.set({
-					isAgentRunning: false,
-				})
+				chrome.storage.local.set({ isAgentRunning: false }).catch(console.error)
 
 				tabsController.dispose()
 			},
 		})
+
+		this.addEventListener('statuschange', () => {
+			const running = this.status === 'running'
+
+			if (running && !heartBeatInterval) {
+				heartBeatInterval = window.setInterval(() => {
+					void chrome.storage.local.set({ agentHeartbeat: Date.now() })
+				}, 1_000)
+			} else if (!running && heartBeatInterval) {
+				clearInterval(heartBeatInterval)
+				heartBeatInterval = null
+			}
+
+			chrome.storage.local.set({ isAgentRunning: running }).catch(console.error)
+		})
 	}
 }

packages/extension/src/agent/RemotePageController.ts

@@ -56,7 +56,7 @@ export class RemotePageController {
 	}
 
 	async getBrowserState(): Promise<BrowserState> {
-		let browserState = {} as BrowserState
+		let browserState: BrowserState
 		debug('getBrowserState', this.currentTabId)
 
 		const currentUrl = await this.getCurrentUrl()
@@ -133,9 +133,7 @@ export class RemotePageController {
 		return this.remoteCallDomAction('scroll_horizontally', args)
 	}
 
-	async executeJavascript(...args: any[]): Promise<DomActionReturn> {
-		return this.remoteCallDomAction('execute_javascript', args)
-	}
+	// `execute_javascript` is intentionally not implemented: AbortSignal cannot cross context
 
 	/** @note Managed by content script via storage polling. */
 	async showMask(): Promise<void> {}

packages/extension/src/agent/TabsController.ts

@@ -24,7 +24,7 @@ export class TabsController {
 	currentTabId: number | null = null
 
 	private disposed = false
-	private port: chrome.runtime.Port | null = null
+	private port?: chrome.runtime.Port
 	private portRetries = 0
 
 	private windowId: number | null = null
@@ -42,9 +42,9 @@ export class TabsController {
 			throw new Error('TabsController already disposed')
 		}
 
-		this.currentTabId = null
+		await this.updateCurrentTabId(null)
 		this.disposed = false
-		this.port = null
+		this.port = undefined
 		this.portRetries = 0
 
 		this.windowId = null
@@ -338,7 +338,7 @@ export class TabsController {
 		})
 
 		this.port.onDisconnect.addListener(() => {
-			this.port = null
+			this.port = undefined
 			if (this.disposed) return
 			if (this.portRetries >= 7) {
 				console.error(PREFIX, 'tab events port failed after 7 retries, giving up')
@@ -354,7 +354,7 @@ export class TabsController {
 		debug('dispose')
 		this.disposed = true
 		this.port?.disconnect()
-		this.port = null
+		this.port = undefined
 	}
 }
 

packages/extension/src/agent/system_prompt.md

@@ -72,7 +72,6 @@ Strictly follow these rules while using the browser and navigating the web:
 - You can scroll by a specific number of pages using the num_pages parameter (e.g., 0.5 for half page, 2.0 for two pages).
 - All the elements that are scrollable are marked with `data-scrollable` attribute. Including the scrollable distance in every directions. You can scroll *the element* in case some area are overflowed.
 - If a captcha appears, tell user you can not solve captcha. Finish the task and ask user to solve it.
-- If expected elements are missing, try scrolling, or navigating back.
 - If the page is not fully loaded, use the `wait` action.
 - Do not repeat one action for more than 3 times unless some conditions changed.
 - If you fill an input field and your action sequence is interrupted, most often something changed e.g. suggestions popped up under the field.

packages/extension/src/agent/useAgent.ts

@@ -80,7 +80,7 @@ export function useAgent(): UseAgentResult {
 		const handleStatusChange = (e: Event) => {
 			const newStatus = agent.status as AgentStatus
 			setStatus(newStatus)
-			if (newStatus === 'idle' || newStatus === 'completed' || newStatus === 'error') {
+			if (newStatus !== 'running') {
 				setActivity(null)
 			}
 		}
@@ -108,7 +108,6 @@ export function useAgent(): UseAgentResult {
 
 	const execute = useCallback(async (task: string) => {
 		const agent = agentRef.current
-		console.log('🚀 [useAgent] start executing task:', task)
 		if (!agent) throw new Error('Agent not initialized')
 
 		setCurrentTask(task)

packages/extension/src/components/ConfigPanel.tsx

@@ -49,7 +49,9 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 	const [showToken, setShowToken] = useState(false)
 	const [showApiKey, setShowApiKey] = useState(false)
 
-	useEffect(() => {
+	const [prevConfig, setPrevConfig] = useState(config)
+	if (prevConfig !== config) {
+		setPrevConfig(config)
 		setBaseURL(config?.baseURL || DEMO_BASE_URL)
 		setModel(config?.model || DEMO_MODEL)
 		setApiKey(config?.apiKey)
@@ -59,7 +61,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 		setExperimentalLlmsTxt(config?.experimentalLlmsTxt ?? false)
 		setExperimentalIncludeAllTabs(config?.experimentalIncludeAllTabs ?? false)
 		setDisableNamedToolChoice(config?.disableNamedToolChoice ?? false)
-	}, [config])
+	}
 
 	// Poll for user auth token every second until found
 	useEffect(() => {
@@ -121,6 +123,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 					size="icon-sm"
 					onClick={onClose}
 					className="absolute top-2 right-3 cursor-pointer"
+					aria-label="Back"
 				>
 					<CornerUpLeft className="size-3.5" />
 				</Button>
@@ -128,12 +131,15 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 
 			{/* User Auth Token Section */}
 			<div className="flex flex-col gap-1.5 p-3 bg-muted/50 rounded-md border">
-				<label className="text-xs font-medium text-muted-foreground">User Auth Token</label>
+				<label htmlFor="user-auth-token" className="text-xs font-medium text-muted-foreground">
+					User Auth Token
+				</label>
 				<p className="text-[10px] text-muted-foreground mb-1">
 					Give a website the ability to call this extension.
 				</p>
 				<div className="flex gap-2 items-center">
 					<Input
+						id="user-auth-token"
 						readOnly
 						value={
 							userAuthToken
@@ -150,6 +156,8 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 						className="h-8 w-8 shrink-0 cursor-pointer"
 						onClick={() => setShowToken(!showToken)}
 						disabled={!userAuthToken}
+						aria-label={showToken ? 'Hide token' : 'Show token'}
+						aria-pressed={showToken}
 					>
 						{showToken ? <EyeOff className="size-3" /> : <Eye className="size-3" />}
 					</Button>
@@ -159,9 +167,13 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 						className="h-8 w-8 shrink-0 cursor-pointer"
 						onClick={handleCopyToken}
 						disabled={!userAuthToken}
+						aria-label="Copy token"
 					>
 						{copied ? <span className="">✓</span> : <Copy className="size-3" />}
 					</Button>
+					<span role="status" aria-live="polite" aria-atomic="true" className="sr-only">
+						{copied ? 'Token copied' : ''}
+					</span>
 				</div>
 			</div>
 
@@ -169,6 +181,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			<a
 				href="/hub.html"
 				target="_blank"
+				rel="noopener noreferrer"
 				className="flex items-center justify-between p-3 rounded-md border bg-muted/50 text-xs font-medium text-muted-foreground hover:text-foreground hover:border-foreground/20 transition-colors"
 			>
 				Manage Page Agent Hub
@@ -176,8 +189,11 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			</a>
 
 			<div className="flex flex-col gap-1.5">
-				<label className="text-xs text-muted-foreground">Base URL</label>
+				<label htmlFor="base-url" className="text-xs text-muted-foreground">
+					Base URL
+				</label>
 				<Input
+					id="base-url"
 					placeholder="https://api.openai.com/v1"
 					value={baseURL}
 					onChange={(e) => setBaseURL(e.target.value)}
@@ -202,8 +218,11 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			)}
 
 			<div className="flex flex-col gap-1.5">
-				<label className="text-xs text-muted-foreground">Model</label>
+				<label htmlFor="model" className="text-xs text-muted-foreground">
+					Model
+				</label>
 				<Input
+					id="model"
 					placeholder="gpt-5.1"
 					value={model}
 					onChange={(e) => setModel(e.target.value)}
@@ -212,9 +231,12 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			</div>
 
 			<div className="flex flex-col gap-1.5">
-				<label className="text-xs text-muted-foreground">API Key</label>
+				<label htmlFor="api-key" className="text-xs text-muted-foreground">
+					API Key
+				</label>
 				<div className="flex gap-2 items-center">
 					<Input
+						id="api-key"
 						type={showApiKey ? 'text' : 'password'}
 						// placeholder="sk-..."
 						value={apiKey}
@@ -226,6 +248,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 						size="icon"
 						className="h-8 w-8 shrink-0 cursor-pointer"
 						onClick={() => setShowApiKey(!showApiKey)}
+						aria-label={showApiKey ? 'Hide API key' : 'Show API key'}
 					>
 						{showApiKey ? <EyeOff className="size-3" /> : <Eye className="size-3" />}
 					</Button>
@@ -258,8 +281,11 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			{advancedOpen && (
 				<>
 					<div className="flex flex-col gap-1.5">
-						<label className="text-xs text-muted-foreground">Max Steps</label>
+						<label htmlFor="max-steps" className="text-xs text-muted-foreground">
+							Max Steps
+						</label>
 						<Input
+							id="max-steps"
 							type="number"
 							placeholder="40"
 							min={1}

packages/extension/src/components/HistoryDetail.tsx

@@ -71,7 +71,6 @@ export function HistoryDetail({
 			{/* Events (read-only) */}
 			<div className="flex-1 overflow-y-auto p-3 space-y-2">
 				{session.history.map((event, index) => (
-					// eslint-disable-next-line react-x/no-array-index-key
 					<EventCard key={index} event={event} />
 				))}
 			</div>

packages/extension/src/components/HistoryList.tsx

@@ -1,4 +1,12 @@
-import { ArrowDownToLine, ArrowLeft, CheckCircle, RotateCcw, Trash2, XCircle } from 'lucide-react'
+import {
+	ArrowDownToLine,
+	ArrowLeft,
+	CheckCircle,
+	History,
+	RotateCcw,
+	Trash2,
+	XCircle,
+} from 'lucide-react'
 import { useCallback, useEffect, useState } from 'react'
 
 import { Button } from '@/components/ui/button'
@@ -29,12 +37,16 @@ export function HistoryList({
 	const [loading, setLoading] = useState(true)
 
 	const load = useCallback(async () => {
-		setSessions(await listSessions())
-		setLoading(false)
+		try {
+			setSessions(await listSessions())
+		} catch (err) {
+			console.error('[HistoryList] Failed to load sessions:', err)
+		} finally {
+			setLoading(false)
+		}
 	}, [])
 
 	useEffect(() => {
-		// eslint-disable-next-line react-hooks/set-state-in-effect
 		load()
 	}, [load])
 
@@ -58,7 +70,14 @@ export function HistoryList({
 		<div className="flex flex-col h-screen bg-background">
 			{/* Header */}
 			<header className="flex items-center gap-2 border-b px-3 py-2">
-				<Button variant="ghost" size="icon-sm" onClick={onBack} className="cursor-pointer">
+				<Button
+					variant="ghost"
+					size="icon-sm"
+					onClick={onBack}
+					className="cursor-pointer"
+					aria-label="Back"
+					title="Back"
+				>
 					<ArrowLeft className="size-3.5" />
 				</Button>
 				<span className="text-sm font-medium flex-1">History</span>
@@ -81,14 +100,23 @@ export function HistoryList({
 			{/* List */}
 			<div className="flex-1 overflow-y-auto">
 				{loading && (
-					<div className="flex items-center justify-center h-32 text-xs text-muted-foreground">
-						Loading...
+					<div className="flex flex-col" aria-label="Loading history" aria-busy="true">
+						{[...Array(4)].map((_, i) => (
+							<div key={i} className="flex items-start gap-2 px-3 py-2.5 border-b">
+								<div className="size-3.5 mt-0.5 rounded-full bg-muted animate-pulse shrink-0" />
+								<div className="flex-1 space-y-1.5">
+									<div className="h-2.5 bg-muted animate-pulse rounded w-3/4" />
+									<div className="h-2 bg-muted animate-pulse rounded w-1/3" />
+								</div>
+							</div>
+						))}
 					</div>
 				)}
 
 				{!loading && sessions.length === 0 && (
-					<div className="flex items-center justify-center h-32 text-xs text-muted-foreground">
-						No history yet
+					<div className="flex flex-col items-center justify-center h-40 gap-2 text-muted-foreground">
+						<History className="size-8 opacity-30" />
+						<p className="text-xs">No history yet</p>
 					</div>
 				)}
 

packages/extension/src/components/cards.tsx

@@ -54,7 +54,7 @@ function ResultCard({
 					Result: {success ? 'Success' : 'Failed'}
 				</span>
 			</div>
-			<p className="text-xs text-[11px] text-muted-foreground pl-5 whitespace-pre-wrap">{text}</p>
+			<p className="text-[12px] text-foreground pl-5 whitespace-pre-wrap">{text}</p>
 			{children}
 		</div>
 	)
@@ -146,6 +146,7 @@ function CopyButton({ text, label }: { text: string; label: string }) {
 function extractPrompt(rawRequest: unknown, role: 'system' | 'user'): string | null {
 	const messages = (rawRequest as { messages?: { role: string; content?: unknown }[] })?.messages
 	if (!messages) return null
+	if (!Array.isArray(messages)) return null
 	const msg =
 		role === 'system'
 			? messages.find((m) => m.role === role)

packages/extension/src/components/misc.tsx

@@ -14,6 +14,7 @@ export function StatusDot({ status }: { status: AgentStatus }) {
 		running: 'bg-blue-500',
 		completed: 'bg-green-500',
 		error: 'bg-destructive',
+		stopped: 'bg-muted-foreground',
 	}[status]
 
 	const label = {
@@ -21,6 +22,7 @@ export function StatusDot({ status }: { status: AgentStatus }) {
 		running: 'Running',
 		completed: 'Done',
 		error: 'Error',
+		stopped: 'Stopped',
 	}[status]
 
 	return (

packages/extension/src/entrypoints/hub/App.tsx

@@ -133,7 +133,6 @@ export default function App() {
 					)}
 
 					{history.map((event, index) => (
-						// eslint-disable-next-line react-x/no-array-index-key
 						<EventCard key={index} event={event} />
 					))}
 

packages/extension/src/entrypoints/hub/hub-ws.ts

@@ -206,9 +206,9 @@ export function useHubWs(
 	const [wsState, setWsState] = useState<HubWsState>(() => (wsPort ? 'connecting' : 'disconnected'))
 	const hubWsRef = useRef<HubWs | null>(null)
 
-	const latest = useRef({ execute, stop, configure, config })
+	const latestRef = useRef({ execute, stop, configure, config })
 	useEffect(() => {
-		latest.current = { execute, stop, configure, config }
+		latestRef.current = { execute, stop, configure, config }
 	})
 
 	useEffect(() => {
@@ -218,14 +218,14 @@ export function useHubWs(
 			Number(wsPort),
 			{
 				onExecute: async (task, incomingConfig) => {
-					const { execute, configure, config } = latest.current
+					const { execute, configure, config } = latestRef.current
 					if (incomingConfig) {
 						await configure({ ...config, ...incomingConfig } as ExtConfig)
 					}
 					const result = await execute(task)
 					return { success: result.success, data: result.data }
 				},
-				onStop: () => latest.current.stop(),
+				onStop: () => latestRef.current.stop(),
 			},
 			setWsState
 		)

packages/extension/src/entrypoints/sidepanel/App.tsx

@@ -39,7 +39,7 @@ export default function App() {
 
 		if (
 			prev === 'running' &&
-			(status === 'completed' || status === 'error') &&
+			(status === 'completed' || status === 'error' || status === 'stopped') &&
 			history.length > 0 &&
 			currentTask
 		) {
@@ -147,6 +147,8 @@ export default function App() {
 						size="icon-sm"
 						onClick={() => setView({ name: 'history' })}
 						className="cursor-pointer"
+						aria-label="History"
+						title="History"
 					>
 						<History className="size-3.5" />
 					</Button>
@@ -155,6 +157,8 @@ export default function App() {
 						size="icon-sm"
 						onClick={() => setView({ name: 'config' })}
 						className="cursor-pointer"
+						aria-label="Settings"
+						title="Settings"
 					>
 						<Settings className="size-3.5" />
 					</Button>
@@ -178,7 +182,6 @@ export default function App() {
 					{showEmptyState && <EmptyState />}
 
 					{history.map((event, index) => (
-						// eslint-disable-next-line react-x/no-array-index-key
 						<EventCard key={index} event={event} />
 					))}
 
@@ -206,6 +209,8 @@ export default function App() {
 								variant="destructive"
 								onClick={handleStop}
 								className="size-7"
+								aria-label="Stop task"
+								title="Stop task"
 							>
 								<Square className="size-3" />
 							</InputGroupButton>
@@ -216,6 +221,8 @@ export default function App() {
 								onClick={() => handleSubmit()}
 								disabled={!inputValue.trim()}
 								className="size-7 cursor-pointer"
+								aria-label="Send"
+								title="Send"
 							>
 								<Send className="size-3" />
 							</InputGroupButton>

packages/extension/src/lib/db.ts

@@ -8,7 +8,7 @@ export interface SessionRecord {
 	id: string
 	task: string
 	history: HistoricalEvent[]
-	status: 'completed' | 'error'
+	status: 'completed' | 'error' | 'stopped'
 	createdAt: number
 }
 

packages/extension/tsconfig.json

@@ -3,26 +3,11 @@
     "compilerOptions": {
         "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
         "useDefineForClassFields": true,
-        "noEmit": false,
-        "allowImportingTsExtensions": false,
         "strictNullChecks": true,
         "jsx": "react-jsx",
-        "baseUrl": ".",
+        "types": ["node", "chrome"],
         "paths": {
-            // Self root
-            "@/*": ["src/*"],
-
-            "@page-agent/llms": ["../llms/src/index.ts"],
-            "@page-agent/page-controller": ["../page-controller/src/PageController.ts"],
-            "@page-agent/core": ["../core/src/PageAgentCore.ts"],
-            "@page-agent/ui": ["../ui/src/index.ts"]
+            "@/*": ["./src/*"]
         }
-    },
-    "references": [
-        //
-        { "path": "../llms" },
-        { "path": "../page-controller" },
-        { "path": "../core" },
-        { "path": "../ui" }
-    ]
+    }
 }

packages/llms/package.json

@@ -1,15 +1,25 @@
 {
     "name": "@page-agent/llms",
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
-    "main": "./dist/lib/page-agent-llms.js",
-    "module": "./dist/lib/page-agent-llms.js",
-    "types": "./dist/lib/index.d.ts",
+    "main": "./src/index.ts",
+    "types": "./src/index.ts",
     "exports": {
         ".": {
-            "types": "./dist/lib/index.d.ts",
-            "import": "./dist/lib/page-agent-llms.js",
-            "default": "./dist/lib/page-agent-llms.js"
+            "types": "./src/index.ts",
+            "default": "./src/index.ts"
+        }
+    },
+    "publishConfig": {
+        "main": "./dist/lib/page-agent-llms.js",
+        "module": "./dist/lib/page-agent-llms.js",
+        "types": "./dist/lib/index.d.ts",
+        "exports": {
+            ".": {
+                "types": "./dist/lib/index.d.ts",
+                "import": "./dist/lib/page-agent-llms.js",
+                "default": "./dist/lib/page-agent-llms.js"
+            }
         }
     },
     "files": [
@@ -33,8 +43,9 @@
     "homepage": "https://alibaba.github.io/page-agent/",
     "scripts": {
         "build": "vite build",
-        "prepublishOnly": "node -e \"const fs=require('fs');['LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
-        "postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+        "test": "vitest run",
+        "prepublishOnly": "node ../../scripts/pre-publish.js",
+        "postpublish": "node ../../scripts/post-publish.js"
     },
     "dependencies": {
         "chalk": "^5.6.2"
@@ -43,6 +54,6 @@
         "zod": "^3.25.0 || ^4.0.0"
     },
     "devDependencies": {
-        "zod": "^4.3.5"
+        "zod": "^4.4.3"
     }
 }

packages/llms/src/OpenAIClient.test.ts

@@ -0,0 +1,369 @@
+import { beforeEach, describe, expect, it, vi } from 'vitest'
+import * as z from 'zod/v4'
+
+import { OpenAIClient } from './OpenAIClient'
+import { InvokeError, InvokeErrorTypes } from './errors'
+import { parseLLMConfig } from './index'
+import type { LLMConfig, Tool } from './types'
+
+// ---------- Fixtures ----------
+
+function makeClient(overrides: Partial<LLMConfig> = {}) {
+	const fetchMock = vi.fn<typeof fetch>()
+	const config = parseLLMConfig({
+		baseURL: 'http://test.local/v1',
+		model: 'test-model',
+		apiKey: 'sk-test',
+		customFetch: fetchMock,
+		...overrides,
+	})
+	const client = new OpenAIClient(config)
+	return { client, fetchMock }
+}
+
+function makeTool(): Tool<{ name: string }, string> {
+	return {
+		description: 'greet',
+		inputSchema: z.object({ name: z.string() }),
+		execute: vi.fn(async (args) => `hello ${args.name}`),
+	}
+}
+
+function jsonResponse(body: unknown, status = 200): Response {
+	return new Response(JSON.stringify(body), {
+		status,
+		headers: { 'Content-Type': 'application/json' },
+	})
+}
+
+function toolCallBody(toolName: string, args: unknown, finishReason = 'tool_calls') {
+	return {
+		choices: [
+			{
+				finish_reason: finishReason,
+				message: {
+					tool_calls: [
+						{
+							id: 'call_1',
+							type: 'function',
+							function: {
+								name: toolName,
+								arguments: typeof args === 'string' ? args : JSON.stringify(args),
+							},
+						},
+					],
+				},
+			},
+		],
+		usage: { prompt_tokens: 10, completion_tokens: 5, total_tokens: 15 },
+	}
+}
+
+function abortError(message = 'aborted'): Error {
+	const err = new Error(message)
+	err.name = 'AbortError'
+	return err
+}
+
+function getSentBody(fetchMock: ReturnType<typeof vi.fn>): Record<string, unknown> {
+	const init = fetchMock.mock.calls[0][1] as RequestInit
+	return JSON.parse(init.body as string)
+}
+
+const signal = new AbortController().signal
+
+// ---------- Request construction ----------
+
+describe('OpenAIClient.invoke — request construction', () => {
+	let setup: ReturnType<typeof makeClient>
+	const tools = { greet: makeTool() }
+
+	beforeEach(() => {
+		setup = makeClient()
+		setup.fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'world' })))
+	})
+
+	it('defaults tool_choice to "required" when no toolChoiceName is given', async () => {
+		await setup.client.invoke([], tools, signal)
+		expect(getSentBody(setup.fetchMock).tool_choice).toBe('required')
+	})
+
+	it('uses named tool_choice when toolChoiceName is given', async () => {
+		await setup.client.invoke([], tools, signal, { toolChoiceName: 'greet' })
+		expect(getSentBody(setup.fetchMock).tool_choice).toEqual({
+			type: 'function',
+			function: { name: 'greet' },
+		})
+	})
+
+	it('falls back to "required" when disableNamedToolChoice is true', async () => {
+		const { client, fetchMock } = makeClient({ disableNamedToolChoice: true })
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'world' })))
+		await client.invoke([], tools, signal, { toolChoiceName: 'greet' })
+		expect(getSentBody(fetchMock).tool_choice).toBe('required')
+	})
+
+	it('sends Authorization header when apiKey is set', async () => {
+		await setup.client.invoke([], tools, signal)
+		const init = setup.fetchMock.mock.calls[0][1]!
+		expect((init.headers as Record<string, string>).Authorization).toBe('Bearer sk-test')
+	})
+
+	it('omits Authorization header when apiKey is empty', async () => {
+		const { client, fetchMock } = makeClient({ apiKey: '' })
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'world' })))
+		await client.invoke([], tools, signal)
+		const init = fetchMock.mock.calls[0][1]!
+		expect((init.headers as Record<string, string>).Authorization).toBeUndefined()
+	})
+
+	it('applies transformRequestBody (in-place form, returns undefined)', async () => {
+		const { client, fetchMock } = makeClient({
+			transformRequestBody: (body) => {
+				body.custom_flag = 42
+				return undefined
+			},
+		})
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'world' })))
+		await client.invoke([], tools, signal)
+		expect(getSentBody(fetchMock).custom_flag).toBe(42)
+	})
+
+	it('applies transformRequestBody (returning a new object)', async () => {
+		const { client, fetchMock } = makeClient({
+			transformRequestBody: () => ({ replaced: true }),
+		})
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'world' })))
+		await client.invoke([], tools, signal)
+		expect(getSentBody(fetchMock)).toEqual({ replaced: true })
+	})
+
+	it('wraps transformRequestBody throws as CONFIG_ERROR', async () => {
+		const { client } = makeClient({
+			transformRequestBody: () => {
+				throw new Error('bad transform')
+			},
+		})
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			name: 'InvokeError',
+			type: InvokeErrorTypes.CONFIG_ERROR,
+		})
+	})
+})
+
+// ---------- Success path ----------
+
+describe('OpenAIClient.invoke — success', () => {
+	it('returns toolCall, toolResult and usage', async () => {
+		const { client, fetchMock } = makeClient()
+		const tool = makeTool()
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'Alice' })))
+
+		const result = await client.invoke([], { greet: tool }, signal)
+
+		expect(result.toolCall).toEqual({ name: 'greet', args: { name: 'Alice' } })
+		expect(result.toolResult).toBe('hello Alice')
+		expect(result.usage).toEqual({
+			promptTokens: 10,
+			completionTokens: 5,
+			totalTokens: 15,
+			cachedTokens: undefined,
+			reasoningTokens: undefined,
+		})
+		expect(tool.execute).toHaveBeenCalledWith({ name: 'Alice' })
+	})
+
+	it('accepts finish_reason="stop" with tool calls', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'Bob' }, 'stop')))
+		const result = await client.invoke([], { greet: makeTool() }, signal)
+		expect(result.toolResult).toBe('hello Bob')
+	})
+})
+
+// ---------- HTTP errors ----------
+
+describe('OpenAIClient.invoke — HTTP errors', () => {
+	const tools = { greet: makeTool() }
+
+	it.each([
+		[401, InvokeErrorTypes.AUTH_ERROR],
+		[403, InvokeErrorTypes.AUTH_ERROR],
+		[429, InvokeErrorTypes.RATE_LIMIT],
+		[500, InvokeErrorTypes.SERVER_ERROR],
+		[502, InvokeErrorTypes.SERVER_ERROR],
+		[418, InvokeErrorTypes.UNKNOWN],
+	])('maps status %i to %s', async (status, type) => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(jsonResponse({ error: { message: 'nope' } }, status))
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			name: 'InvokeError',
+			type,
+		})
+	})
+
+	it('falls back to statusText when body has no error.message', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(
+			new Response('not json', { status: 500, statusText: 'Internal Boom' })
+		)
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.SERVER_ERROR,
+			message: expect.stringContaining('Internal Boom'),
+		})
+	})
+})
+
+// ---------- Response anomalies ----------
+
+describe('OpenAIClient.invoke — response anomalies', () => {
+	const tools = { greet: makeTool() }
+
+	it('throws CONTEXT_LENGTH on finish_reason="length"', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(
+			jsonResponse({ choices: [{ finish_reason: 'length', message: {} }] })
+		)
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.CONTEXT_LENGTH,
+		})
+	})
+
+	it('throws CONTENT_FILTER on finish_reason="content_filter"', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(
+			jsonResponse({ choices: [{ finish_reason: 'content_filter', message: {} }] })
+		)
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.CONTENT_FILTER,
+		})
+	})
+
+	it('throws INVALID_SCHEMA when there are no choices', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(jsonResponse({}))
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.INVALID_SCHEMA,
+		})
+	})
+
+	it('throws NO_TOOL_CALL when message has no tool_calls', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(
+			jsonResponse({ choices: [{ finish_reason: 'tool_calls', message: {} }] })
+		)
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.NO_TOOL_CALL,
+		})
+	})
+
+	it('throws INVALID_TOOL_ARGS when arguments are not valid JSON', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', 'not-json{')))
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.INVALID_TOOL_ARGS,
+			message: expect.stringContaining('JSON'),
+		})
+	})
+
+	it('throws INVALID_TOOL_ARGS when args fail Zod validation', async () => {
+		const { client, fetchMock } = makeClient()
+		// tool expects { name: string }, send { name: 123 }
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 123 })))
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.INVALID_TOOL_ARGS,
+		})
+	})
+
+	it('throws UNKNOWN when model calls a tool that does not exist', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('mystery', { name: 'x' })))
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.UNKNOWN,
+			message: expect.stringContaining('mystery'),
+		})
+	})
+
+	it('wraps tool.execute failures as TOOL_EXECUTION_ERROR', async () => {
+		const { client, fetchMock } = makeClient()
+		const tool: Tool<{ name: string }, string> = {
+			inputSchema: z.object({ name: z.string() }),
+			execute: vi.fn(async () => {
+				throw new Error('downstream blew up')
+			}),
+		}
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'x' })))
+		await expect(client.invoke([], { greet: tool }, signal)).rejects.toMatchObject({
+			type: InvokeErrorTypes.TOOL_EXECUTION_ERROR,
+			message: expect.stringContaining('downstream blew up'),
+		})
+	})
+})
+
+// ---------- Abort handling (the important part) ----------
+
+describe('OpenAIClient.invoke — abort', () => {
+	const tools = { greet: makeTool() }
+
+	it('throws AbortError immediately when signal is already aborted', async () => {
+		const { client, fetchMock } = makeClient()
+		const controller = new AbortController()
+		controller.abort()
+
+		await expect(client.invoke([], tools, controller.signal)).rejects.toMatchObject({
+			name: 'AbortError',
+		})
+		expect(fetchMock).not.toHaveBeenCalled()
+	})
+
+	it('propagates AbortError thrown by fetch (does NOT wrap as NETWORK_ERROR)', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockRejectedValue(abortError())
+
+		const err = await client.invoke([], tools, signal).catch((e) => e)
+		expect(err).toBeInstanceOf(Error)
+		expect(err).not.toBeInstanceOf(InvokeError)
+		expect(err.name).toBe('AbortError')
+	})
+
+	it('propagates AbortError thrown by response.json() (does NOT wrap as INVALID_RESPONSE)', async () => {
+		const { client, fetchMock } = makeClient()
+		// Fake Response whose .json() rejects with AbortError mid-read
+		const fakeResponse = {
+			ok: true,
+			status: 200,
+			statusText: 'OK',
+			json: () => Promise.reject(abortError()),
+		} as unknown as Response
+		fetchMock.mockResolvedValue(fakeResponse)
+
+		const err = await client.invoke([], tools, signal).catch((e) => e)
+		expect(err).not.toBeInstanceOf(InvokeError)
+		expect(err.name).toBe('AbortError')
+	})
+
+	it('propagates AbortError thrown by tool.execute (does NOT wrap as TOOL_EXECUTION_ERROR)', async () => {
+		const { client, fetchMock } = makeClient()
+		const tool: Tool<{ name: string }, string> = {
+			inputSchema: z.object({ name: z.string() }),
+			execute: vi.fn(async () => {
+				throw abortError()
+			}),
+		}
+		fetchMock.mockResolvedValue(jsonResponse(toolCallBody('greet', { name: 'x' })))
+
+		const err = await client.invoke([], { greet: tool }, signal).catch((e) => e)
+		expect(err).not.toBeInstanceOf(InvokeError)
+		expect(err.name).toBe('AbortError')
+	})
+
+	// Sanity check: the wrappers we deliberately bypass for AbortError still work for normal errors
+	it('still wraps non-Abort fetch errors as NETWORK_ERROR', async () => {
+		const { client, fetchMock } = makeClient()
+		fetchMock.mockRejectedValue(new TypeError('ECONNREFUSED'))
+		await expect(client.invoke([], tools, signal)).rejects.toMatchObject({
+			name: 'InvokeError',
+			type: InvokeErrorTypes.NETWORK_ERROR,
+		})
+	})
+})

packages/llms/src/OpenAIClient.ts

@@ -3,7 +3,7 @@
  */
 import * as z from 'zod/v4'
 
-import { InvokeError, InvokeErrorType } from './errors'
+import { InvokeError, InvokeErrorTypes } from './errors'
 import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
 import { modelPatch, zodToOpenAITool } from './utils'
 
@@ -25,6 +25,8 @@ export class OpenAIClient implements LLMClient {
 		abortSignal?: AbortSignal,
 		options?: InvokeOptions
 	): Promise<InvokeResult> {
+		abortSignal?.throwIfAborted()
+
 		// 1. Convert tools to OpenAI format
 		const openaiTools = Object.entries(tools).map(([name, t]) => zodToOpenAITool(name, t))
 
@@ -45,6 +47,17 @@ export class OpenAIClient implements LLMClient {
 		}
 
 		modelPatch(requestBody)
+		let transformedBody: Record<string, unknown> | undefined
+		try {
+			transformedBody = this.config.transformRequestBody(requestBody)
+		} catch (error) {
+			throw new InvokeError(
+				InvokeErrorTypes.CONFIG_ERROR,
+				`transformRequestBody failed: ${(error as Error).message}`,
+				error
+			)
+		}
+		const finalRequestBody = transformedBody ?? requestBody
 
 		// 2. Call API
 		let response: Response
@@ -55,56 +68,69 @@ export class OpenAIClient implements LLMClient {
 					'Content-Type': 'application/json',
 					...(this.config.apiKey && { Authorization: `Bearer ${this.config.apiKey}` }),
 				},
-				body: JSON.stringify(requestBody),
+				body: JSON.stringify(finalRequestBody),
 				signal: abortSignal,
 			})
 		} catch (error: unknown) {
-			const isAbortError = (error as any)?.name === 'AbortError'
-			const errorMessage = isAbortError ? 'Network request aborted' : 'Network request failed'
-			if (!isAbortError) console.error(error)
-			throw new InvokeError(InvokeErrorType.NETWORK_ERROR, errorMessage, error)
+			if ((error as any)?.name === 'AbortError') throw error
+			console.error(error)
+			throw new InvokeError(InvokeErrorTypes.NETWORK_ERROR, 'Network request failed', error)
 		}
 
 		// 3. Handle HTTP errors
 		if (!response.ok) {
-			const errorData = await response.json().catch()
-			const errorMessage =
-				(errorData as { error?: { message?: string } }).error?.message || response.statusText
+			let errorData: any
+			try {
+				errorData = await response.json()
+			} catch (error) {
+				if ((error as any)?.name === 'AbortError') throw error
+			}
+			const errorMessage = errorData?.error?.message || response.statusText
 
 			if (response.status === 401 || response.status === 403) {
 				throw new InvokeError(
-					InvokeErrorType.AUTH_ERROR,
+					InvokeErrorTypes.AUTH_ERROR,
 					`Authentication failed: ${errorMessage}`,
 					errorData
 				)
 			}
 			if (response.status === 429) {
 				throw new InvokeError(
-					InvokeErrorType.RATE_LIMIT,
+					InvokeErrorTypes.RATE_LIMIT,
 					`Rate limit exceeded: ${errorMessage}`,
 					errorData
 				)
 			}
 			if (response.status >= 500) {
 				throw new InvokeError(
-					InvokeErrorType.SERVER_ERROR,
+					InvokeErrorTypes.SERVER_ERROR,
 					`Server error: ${errorMessage}`,
 					errorData
 				)
 			}
 			throw new InvokeError(
-				InvokeErrorType.UNKNOWN,
+				InvokeErrorTypes.UNKNOWN,
 				`HTTP ${response.status}: ${errorMessage}`,
 				errorData
 			)
 		}
 
 		// 4. Parse and validate response
-		const data = await response.json()
+		let data: any
+		try {
+			data = await response.json()
+		} catch (error) {
+			if ((error as any)?.name === 'AbortError') throw error
+			throw new InvokeError(
+				InvokeErrorTypes.INVALID_RESPONSE,
+				'Response body is not valid JSON',
+				error
+			)
+		}
 
 		const choice = data.choices?.[0]
 		if (!choice) {
-			throw new InvokeError(InvokeErrorType.UNKNOWN, 'No choices in response', data)
+			throw new InvokeError(InvokeErrorTypes.INVALID_SCHEMA, 'No choices in response', data)
 		}
 
 		// Check finish_reason
@@ -115,21 +141,21 @@ export class OpenAIClient implements LLMClient {
 				break
 			case 'length':
 				throw new InvokeError(
-					InvokeErrorType.CONTEXT_LENGTH,
+					InvokeErrorTypes.CONTEXT_LENGTH,
 					'Response truncated: max tokens reached',
 					undefined,
 					data
 				)
 			case 'content_filter':
 				throw new InvokeError(
-					InvokeErrorType.CONTENT_FILTER,
+					InvokeErrorTypes.CONTENT_FILTER,
 					'Content filtered by safety system',
 					undefined,
 					data
 				)
 			default:
 				throw new InvokeError(
-					InvokeErrorType.UNKNOWN,
+					InvokeErrorTypes.INVALID_SCHEMA,
 					`Unexpected finish_reason: ${choice.finish_reason}`,
 					undefined,
 					data
@@ -144,7 +170,7 @@ export class OpenAIClient implements LLMClient {
 		const toolCallName = normalizedChoice?.message?.tool_calls?.[0]?.function?.name
 		if (!toolCallName) {
 			throw new InvokeError(
-				InvokeErrorType.NO_TOOL_CALL,
+				InvokeErrorTypes.NO_TOOL_CALL,
 				'No tool call found in response',
 				undefined,
 				data
@@ -154,7 +180,7 @@ export class OpenAIClient implements LLMClient {
 		const tool = tools[toolCallName]
 		if (!tool) {
 			throw new InvokeError(
-				InvokeErrorType.UNKNOWN,
+				InvokeErrorTypes.UNKNOWN,
 				`Tool "${toolCallName}" not found in tools`,
 				undefined,
 				data
@@ -165,7 +191,7 @@ export class OpenAIClient implements LLMClient {
 		const argString = normalizedChoice.message?.tool_calls?.[0]?.function?.arguments
 		if (!argString) {
 			throw new InvokeError(
-				InvokeErrorType.INVALID_TOOL_ARGS,
+				InvokeErrorTypes.INVALID_TOOL_ARGS,
 				'No tool call arguments found',
 				undefined,
 				data
@@ -177,7 +203,7 @@ export class OpenAIClient implements LLMClient {
 			parsedArgs = JSON.parse(argString)
 		} catch (error) {
 			throw new InvokeError(
-				InvokeErrorType.INVALID_TOOL_ARGS,
+				InvokeErrorTypes.INVALID_TOOL_ARGS,
 				'Failed to parse tool arguments as JSON',
 				error,
 				data
@@ -189,7 +215,7 @@ export class OpenAIClient implements LLMClient {
 		if (!validation.success) {
 			console.error(z.prettifyError(validation.error))
 			throw new InvokeError(
-				InvokeErrorType.INVALID_TOOL_ARGS,
+				InvokeErrorTypes.INVALID_TOOL_ARGS,
 				'Tool arguments validation failed',
 				validation.error,
 				data
@@ -201,11 +227,12 @@ export class OpenAIClient implements LLMClient {
 		let toolResult: unknown
 		try {
 			toolResult = await tool.execute(toolInput)
-		} catch (e) {
+		} catch (error: unknown) {
+			if ((error as any)?.name === 'AbortError') throw error
 			throw new InvokeError(
-				InvokeErrorType.TOOL_EXECUTION_ERROR,
-				`Tool execution failed: ${(e as Error).message}`,
-				e,
+				InvokeErrorTypes.TOOL_EXECUTION_ERROR,
+				`Tool execution failed: ${(error as Error)?.message}`,
+				error,
 				data
 			)
 		}
@@ -225,7 +252,7 @@ export class OpenAIClient implements LLMClient {
 				reasoningTokens: data.usage?.completion_tokens_details?.reasoning_tokens,
 			},
 			rawResponse: data,
-			rawRequest: requestBody,
+			rawRequest: finalRequestBody,
 		}
 	}
 }

packages/llms/src/errors.ts

@@ -1,8 +1,8 @@
 /**
- * Error types and error handling for LLM invocations
+ * Error types and error handling for LLM invocations.
  */
 
-export const InvokeErrorType = {
+export const InvokeErrorTypes = {
 	// Retryable
 	NETWORK_ERROR: 'network_error', // Network error, retry
 	RATE_LIMIT: 'rate_limit', // Rate limit, retry
@@ -10,16 +10,31 @@ export const InvokeErrorType = {
 	NO_TOOL_CALL: 'no_tool_call', // Model did not call tool
 	INVALID_TOOL_ARGS: 'invalid_tool_args', // Tool args don't match schema
 	TOOL_EXECUTION_ERROR: 'tool_execution_error', // Tool execution error
+	INVALID_RESPONSE: 'invalid_response', // Response body is not valid JSON
+	INVALID_SCHEMA: 'invalid_schema', // Response is valid JSON but doesn't match expected shape
 
 	UNKNOWN: 'unknown',
 
 	// Non-retryable
+	CONFIG_ERROR: 'config_error', // Invalid local configuration or hook
 	AUTH_ERROR: 'auth_error', // Authentication failed
 	CONTEXT_LENGTH: 'context_length', // Prompt too long
 	CONTENT_FILTER: 'content_filter', // Content filtered
 } as const
 
-export type InvokeErrorType = (typeof InvokeErrorType)[keyof typeof InvokeErrorType]
+type InvokeErrorType = (typeof InvokeErrorTypes)[keyof typeof InvokeErrorTypes]
+
+const RETRYABLE_TYPES: readonly InvokeErrorType[] = [
+	InvokeErrorTypes.NETWORK_ERROR,
+	InvokeErrorTypes.RATE_LIMIT,
+	InvokeErrorTypes.SERVER_ERROR,
+	InvokeErrorTypes.NO_TOOL_CALL,
+	InvokeErrorTypes.INVALID_TOOL_ARGS,
+	InvokeErrorTypes.TOOL_EXECUTION_ERROR,
+	InvokeErrorTypes.INVALID_RESPONSE,
+	InvokeErrorTypes.INVALID_SCHEMA,
+	InvokeErrorTypes.UNKNOWN,
+]
 
 export class InvokeError extends Error {
 	type: InvokeErrorType
@@ -34,24 +49,8 @@ export class InvokeError extends Error {
 		super(message)
 		this.name = 'InvokeError'
 		this.type = type
-		this.retryable = this.isRetryable(type, rawError)
+		this.retryable = RETRYABLE_TYPES.includes(type)
 		this.rawError = rawError
 		this.rawResponse = rawResponse
 	}
-
-	private isRetryable(type: InvokeErrorType, rawError?: unknown): boolean {
-		const isAbortError = (rawError as any)?.name === 'AbortError'
-		if (isAbortError) return false
-
-		const retryableTypes: InvokeErrorType[] = [
-			InvokeErrorType.NETWORK_ERROR,
-			InvokeErrorType.RATE_LIMIT,
-			InvokeErrorType.SERVER_ERROR,
-			InvokeErrorType.NO_TOOL_CALL,
-			InvokeErrorType.INVALID_TOOL_ARGS,
-			InvokeErrorType.TOOL_EXECUTION_ERROR,
-			InvokeErrorType.UNKNOWN,
-		]
-		return retryableTypes.includes(type)
-	}
 }

packages/llms/src/index.test.ts

@@ -0,0 +1,114 @@
+import { beforeEach, describe, expect, it, vi } from 'vitest'
+
+import { InvokeError, InvokeErrorTypes, LLM } from './index'
+import type { LLMClient } from './types'
+
+function makeLLM(maxRetries = 2): LLM {
+	return new LLM({
+		baseURL: 'http://test.local/v1',
+		model: 'gpt-5',
+		maxRetries,
+	})
+}
+
+function abortError(): Error {
+	const err = new Error('aborted')
+	err.name = 'AbortError'
+	return err
+}
+
+describe('LLM.invoke retry behavior', () => {
+	let llm: LLM
+	let client: { invoke: ReturnType<typeof vi.fn> }
+	const signal = new AbortController().signal
+
+	beforeEach(() => {
+		llm = makeLLM(2)
+		client = { invoke: vi.fn() }
+		llm.client = client as unknown as LLMClient
+	})
+
+	it('returns immediately on first success', async () => {
+		client.invoke.mockResolvedValueOnce('ok')
+		const retryListener = vi.fn()
+		llm.addEventListener('retry', retryListener)
+
+		await expect(llm.invoke([], {}, signal)).resolves.toBe('ok')
+		expect(client.invoke).toHaveBeenCalledOnce()
+		expect(retryListener).not.toHaveBeenCalled()
+	})
+
+	it('retries up to maxRetries on retryable errors, then throws last error', async () => {
+		const retryable = new InvokeError(InvokeErrorTypes.NETWORK_ERROR, 'boom')
+		client.invoke
+			.mockRejectedValueOnce(retryable)
+			.mockRejectedValueOnce(retryable)
+			.mockRejectedValueOnce(retryable)
+
+		await expect(llm.invoke([], {}, signal)).rejects.toBe(retryable)
+		// 1 initial + 2 retries = 3 attempts total
+		expect(client.invoke).toHaveBeenCalledTimes(3)
+	})
+
+	it('succeeds on retry after transient failure', async () => {
+		const retryable = new InvokeError(InvokeErrorTypes.RATE_LIMIT, 'slow down')
+		client.invoke.mockRejectedValueOnce(retryable).mockResolvedValueOnce('ok')
+
+		await expect(llm.invoke([], {}, signal)).resolves.toBe('ok')
+		expect(client.invoke).toHaveBeenCalledTimes(2)
+	})
+
+	it('emits "retry" events with attempt count and lastError', async () => {
+		const err1 = new InvokeError(InvokeErrorTypes.NETWORK_ERROR, 'first')
+		const err2 = new InvokeError(InvokeErrorTypes.NETWORK_ERROR, 'second')
+		client.invoke
+			.mockRejectedValueOnce(err1)
+			.mockRejectedValueOnce(err2)
+			.mockResolvedValueOnce('ok')
+
+		const events: { attempt: number; maxAttempts: number; lastError: Error }[] = []
+		llm.addEventListener('retry', (e) => {
+			events.push((e as CustomEvent).detail)
+		})
+
+		await llm.invoke([], {}, signal)
+
+		expect(events).toEqual([
+			{ attempt: 1, maxAttempts: 2, lastError: err1 },
+			{ attempt: 2, maxAttempts: 2, lastError: err2 },
+		])
+	})
+
+	it('does not retry on AbortError, throws immediately', async () => {
+		const err = abortError()
+		client.invoke.mockRejectedValueOnce(err)
+
+		await expect(llm.invoke([], {}, signal)).rejects.toBe(err)
+		expect(client.invoke).toHaveBeenCalledOnce()
+	})
+
+	it('does not retry on non-retryable InvokeError (AUTH_ERROR)', async () => {
+		const err = new InvokeError(InvokeErrorTypes.AUTH_ERROR, 'bad token')
+		client.invoke.mockRejectedValueOnce(err)
+
+		await expect(llm.invoke([], {}, signal)).rejects.toBe(err)
+		expect(client.invoke).toHaveBeenCalledOnce()
+	})
+
+	it('does not retry on non-retryable InvokeError (CONFIG_ERROR)', async () => {
+		const err = new InvokeError(InvokeErrorTypes.CONFIG_ERROR, 'bad config')
+		client.invoke.mockRejectedValueOnce(err)
+
+		await expect(llm.invoke([], {}, signal)).rejects.toBe(err)
+		expect(client.invoke).toHaveBeenCalledOnce()
+	})
+
+	it('retries plain (non-InvokeError) errors as unknown failures', async () => {
+		// Plain errors are treated as retryable by withRetry (only InvokeError carries retryable flag)
+		const plain = new TypeError('weird')
+		client.invoke.mockRejectedValueOnce(plain).mockResolvedValueOnce('ok')
+
+		await expect(llm.invoke([], {}, signal)).resolves.toBe('ok')
+		expect(client.invoke).toHaveBeenCalledTimes(2)
+	})
+})

packages/llms/src/index.ts

@@ -1,9 +1,9 @@
 import { OpenAIClient } from './OpenAIClient'
 import { DEFAULT_TEMPERATURE, LLM_MAX_RETRIES } from './constants'
-import { InvokeError, InvokeErrorType } from './errors'
+import { InvokeError, InvokeErrorTypes } from './errors'
 import type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool } from './types'
 
-export { InvokeError, InvokeErrorType }
+export { InvokeError, InvokeErrorTypes }
 export type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool }
 
 export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
@@ -21,6 +21,7 @@ export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
 		apiKey: config.apiKey || '',
 		temperature: config.temperature ?? DEFAULT_TEMPERATURE,
 		maxRetries: config.maxRetries ?? LLM_MAX_RETRIES,
+		transformRequestBody: config.transformRequestBody ?? ((requestBody) => requestBody),
 		disableNamedToolChoice: config.disableNamedToolChoice ?? false,
 		customFetch: (config.customFetch ?? fetch).bind(globalThis), // fetch will be illegal unless bound
 	}
@@ -49,65 +50,43 @@ export class LLM extends EventTarget {
 		abortSignal: AbortSignal,
 		options?: InvokeOptions
 	): Promise<InvokeResult> {
-		return await withRetry(
-			async () => {
-				// in case user aborted before invoking
-				if (abortSignal.aborted) throw new Error('AbortError')
-
-				const result = await this.client.invoke(messages, tools, abortSignal, options)
-
-				return result
+		return await withRetry(async () => this.client.invoke(messages, tools, abortSignal, options), {
+			maxRetries: this.config.maxRetries,
+			onRetry: (attempt, lastError) => {
+				this.dispatchEvent(
+					new CustomEvent('retry', {
+						detail: { attempt, maxAttempts: this.config.maxRetries, lastError },
+					})
+				)
 			},
-			// retry settings
-			{
-				maxRetries: this.config.maxRetries,
-				onRetry: (attempt: number) => {
-					this.dispatchEvent(
-						new CustomEvent('retry', { detail: { attempt, maxAttempts: this.config.maxRetries } })
-					)
-				},
-				onError: (error: Error) => {
-					this.dispatchEvent(new CustomEvent('error', { detail: { error } }))
-				},
-			}
-		)
+		})
 	}
 }
 
+/**
+ * Retry a function until it succeeds or reaches the maximum number of retries.
+ */
 async function withRetry<T>(
 	fn: () => Promise<T>,
 	settings: {
 		maxRetries: number
-		onRetry: (attempt: number) => void
-		onError: (error: Error) => void
+		onRetry: (attempt: number, lastError: Error) => void
 	}
 ): Promise<T> {
 	let attempt = 0
-	let lastError: Error | null = null
-	while (attempt <= settings.maxRetries) {
-		if (attempt > 0) {
-			settings.onRetry(attempt)
-			await new Promise((resolve) => setTimeout(resolve, 100))
-		}
-
+	while (true) {
 		try {
 			return await fn()
 		} catch (error: unknown) {
-			// do not retry if aborted by user
-			if ((error as any)?.rawError?.name === 'AbortError') throw error
-
-			console.error(error)
-			settings.onError(error as Error)
-
-			// do not retry if error is not retryable (InvokeError)
+			if ((error as any)?.name === 'AbortError') throw error
 			if (error instanceof InvokeError && !error.retryable) throw error
-
-			lastError = error as Error
 			attempt++
+			if (attempt > settings.maxRetries) throw error
+
+			console.debug('[LLM] retryable failure, will retry:', error)
+			settings.onRetry(attempt, error as Error)
 
 			await new Promise((resolve) => setTimeout(resolve, 100))
 		}
 	}
-
-	throw lastError!
 }

packages/llms/src/types.ts

@@ -95,6 +95,16 @@ export interface LLMConfig {
 	temperature?: number
 	maxRetries?: number
 
+	/**
+	 * Transform the final request body before sending it to the provider.
+	 * Use this to implement provider-specific request tweaks such as caching hints or custom flags.
+	 *
+	 * Return a new object, or mutate the input object and return undefined.
+	 */
+	transformRequestBody?: (
+		requestBody: Record<string, unknown>
+	) => Record<string, unknown> | undefined
+
 	/**
 	 * remove the tool_choice field from the request.
 	 * @note fix "Invalid tool_choice type: 'object'" for some LLMs.

packages/llms/src/utils.test.ts

@@ -0,0 +1,162 @@
+import { describe, expect, it } from 'vitest'
+
+import { modelPatch } from './utils'
+
+/**
+ * Baseline request body used as starting point for each provider test.
+ * Mirrors what OpenAIClient builds before calling modelPatch.
+ */
+function baseBody(model: string) {
+	return {
+		model,
+		temperature: 0.7,
+		messages: [],
+		tools: [],
+		parallel_tool_calls: false,
+		tool_choice: 'required' as unknown,
+	}
+}
+
+describe('modelPatch', () => {
+	it('returns body unchanged when model is missing', () => {
+		const body = { temperature: 0.7 }
+		expect(modelPatch(body)).toBe(body)
+		expect(body).toEqual({ temperature: 0.7 })
+	})
+
+	it('qwen: bumps temperature and disables thinking', () => {
+		const body = baseBody('qwen-max')
+		modelPatch(body)
+		expect(body.temperature).toBe(1.0)
+		expect(body).toMatchObject({ enable_thinking: false })
+	})
+
+	it('qwen: keeps higher caller-provided temperature', () => {
+		const body = baseBody('qwen-max')
+		body.temperature = 1.5
+		modelPatch(body)
+		expect(body.temperature).toBe(1.5)
+	})
+
+	it('claude: disables thinking and converts tool_choice "required" -> { type: "any" }', () => {
+		const body = baseBody('claude-3-5-sonnet')
+		modelPatch(body)
+		expect(body).toMatchObject({
+			thinking: { type: 'disabled' },
+			tool_choice: { type: 'any' },
+		})
+	})
+
+	it('claude: converts named tool_choice to { type: "tool", name }', () => {
+		const body = baseBody('claude-3-5-sonnet')
+		body.tool_choice = { type: 'function', function: { name: 'doStuff' } }
+		modelPatch(body)
+		expect(body.tool_choice).toEqual({ type: 'tool', name: 'doStuff' })
+	})
+
+	it('claude-opus-4-7: drops temperature', () => {
+		const body = baseBody('claude-opus-4-7')
+		modelPatch(body)
+		expect(body).not.toHaveProperty('temperature')
+	})
+
+	it('claude-opus-47 (alt id form): drops temperature', () => {
+		// Provider sometimes ships ids with the dot stripped; modelPatch normalizes.
+		const body = baseBody('claude-opus-47-20251029')
+		modelPatch(body)
+		expect(body).not.toHaveProperty('temperature')
+	})
+
+	it('claude-opus-4-8: drops temperature', () => {
+		const body = baseBody('claude-opus-4-8')
+		modelPatch(body)
+		expect(body).not.toHaveProperty('temperature')
+	})
+
+	it('claude-opus-48 (alt id form): drops temperature', () => {
+		const body = baseBody('claude-opus-48-20251210')
+		modelPatch(body)
+		expect(body).not.toHaveProperty('temperature')
+	})
+
+	it('grok: removes tool_choice and disables reasoning/thinking', () => {
+		const body = baseBody('grok-4')
+		modelPatch(body)
+		expect(body).not.toHaveProperty('tool_choice')
+		expect(body).toMatchObject({
+			thinking: { type: 'disabled', effort: 'minimal' },
+			reasoning: { enabled: false, effort: 'low' },
+		})
+	})
+
+	it('gpt-5: sets verbosity=low and reasoning_effort=low', () => {
+		const body = baseBody('gpt-5')
+		modelPatch(body)
+		expect(body).toMatchObject({ verbosity: 'low', reasoning_effort: 'low' })
+	})
+
+	it('gpt-5-mini: low effort, temperature=1', () => {
+		const body = baseBody('gpt-5-mini')
+		modelPatch(body)
+		expect(body).toMatchObject({
+			verbosity: 'low',
+			reasoning_effort: 'low',
+			temperature: 1,
+		})
+	})
+
+	it('gpt-5.1 (gpt-51): disables reasoning', () => {
+		const body = baseBody('gpt-5.1')
+		modelPatch(body)
+		expect(body).toMatchObject({ verbosity: 'low', reasoning_effort: 'none' })
+	})
+
+	it('gpt-5.4 (gpt-54): drops reasoning_effort', () => {
+		const body = baseBody('gpt-5.4')
+		modelPatch(body)
+		expect(body).toMatchObject({ verbosity: 'low' })
+		expect(body).not.toHaveProperty('reasoning_effort')
+	})
+
+	it('gpt-5.5 (gpt-55): drops reasoning_effort and temperature', () => {
+		const body = baseBody('gpt-5.5')
+		modelPatch(body)
+		expect(body).toMatchObject({ verbosity: 'low' })
+		expect(body).not.toHaveProperty('reasoning_effort')
+		expect(body).not.toHaveProperty('temperature')
+	})
+
+	it('gemini: sets reasoning_effort=minimal', () => {
+		const body = baseBody('gemini-2.5-pro')
+		modelPatch(body)
+		expect(body).toMatchObject({ reasoning_effort: 'minimal' })
+	})
+
+	it('deepseek: removes tool_choice', () => {
+		const body = baseBody('deepseek-chat')
+		modelPatch(body)
+		expect(body).not.toHaveProperty('tool_choice')
+	})
+
+	it('minimax: clamps temperature into (0, 1] and removes parallel_tool_calls', () => {
+		const body = baseBody('minimax-m2')
+		body.temperature = 0
+		modelPatch(body)
+		expect(body.temperature).toBeGreaterThan(0)
+		expect(body.temperature).toBeLessThanOrEqual(1)
+		expect(body).not.toHaveProperty('parallel_tool_calls')
+	})
+
+	it('minimax: caps temperature at 1', () => {
+		const body = baseBody('minimax-m2')
+		body.temperature = 2
+		modelPatch(body)
+		expect(body.temperature).toBe(1)
+	})
+
+	it('normalizes provider-prefixed model id (openai/gpt-5)', () => {
+		const body = baseBody('openai/gpt-5')
+		modelPatch(body)
+		expect(body).toMatchObject({ verbosity: 'low', reasoning_effort: 'low' })
+	})
+})

packages/llms/src/utils.ts

@@ -53,6 +53,18 @@ export function modelPatch(body: Record<string, any>) {
 			debug('Applying Claude patch: convert tool_choice format')
 			body.tool_choice = { type: 'tool', name: body.tool_choice.function.name }
 		}
+
+		// TODO: Claude naming pattern has changed
+		// needs proper handling
+		if (
+			modelName.startsWith('claude-opus-4-7') ||
+			modelName.startsWith('claude-opus-47') ||
+			modelName.startsWith('claude-opus-4-8') ||
+			modelName.startsWith('claude-opus-48')
+		) {
+			debug('Applying Claude-4.7/4.8 patch: remove temperature')
+			delete body.temperature
+		}
 	}
 
 	if (modelName.startsWith('grok')) {
@@ -74,10 +86,12 @@ export function modelPatch(body: Record<string, any>) {
 			debug('Applying GPT-51 patch: disable reasoning')
 			body.reasoning_effort = 'none'
 		} else if (modelName.startsWith('gpt-54')) {
-			debug(
-				'Applying GPT-5.4 patch: skip reasoning_effort because chat/completions rejects it with function tools'
-			)
+			debug('Applying GPT-5.4 patch: remove reasoning_effort')
 			delete body.reasoning_effort
+		} else if (modelName.startsWith('gpt-55')) {
+			debug('Applying GPT-5.4 patch: remove reasoning_effort and temperature')
+			delete body.reasoning_effort
+			delete body.temperature
 		} else if (modelName.startsWith('gpt-5-mini')) {
 			debug('Applying GPT-5-mini patch: set reasoning effort to low, temperature to 1')
 			body.reasoning_effort = 'low'
@@ -93,6 +107,11 @@ export function modelPatch(body: Record<string, any>) {
 		body.reasoning_effort = 'minimal'
 	}
 
+	if (modelName.startsWith('deepseek')) {
+		debug('Applying DeepSeek patch: remove tool_choice')
+		delete body.tool_choice
+	}
+
 	if (modelName.startsWith('minimax')) {
 		debug('Applying MiniMax patch: clamp temperature to (0, 1]')
 		// MiniMax API rejects temperature = 0; clamp to a small positive value

packages/llms/tsconfig.dts.json

@@ -1,9 +0,0 @@
-{
-    "extends": "./tsconfig.json",
-    "compilerOptions": {
-        // @workaround DTS bug
-        // dts do not work with monorepo path mapping
-        // disable path mapping for it
-        "paths": {}
-    }
-}

packages/llms/tsconfig.json

@@ -1,12 +1,8 @@
 {
     "extends": "../../tsconfig.base.json",
     "compilerOptions": {
-        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
-        "noEmit": false,
-        "allowImportingTsExtensions": false,
-        "baseUrl": ".",
-        "outDir": "dist"
+        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo"
     },
-    "include": ["**/*.ts"],
+    "include": ["src/**/*.ts"],
     "exclude": ["dist", "node_modules"]
 }

packages/llms/vite.config.js

@@ -11,11 +11,20 @@ console.log(chalk.cyan(`📦 Building @page-agent/llms`))
 
 export default defineConfig({
 	clearScreen: false,
-	plugins: [dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true })],
+	plugins: [
+		dts({
+			include: ['src/**/*.ts'],
+			exclude: ['src/**/*.test.ts'],
+			bundleTypes: true,
+			compilerOptions: {
+				composite: true,
+				noEmit: false,
+				emitDeclarationOnly: true,
+				declaration: true,
+			},
+		}),
+	],
 	publicDir: false,
-	esbuild: {
-		keepNames: true,
-	},
 	build: {
 		lib: {
 			entry: resolve(__dirname, 'src/index.ts'),

packages/llms/vitest.config.js

@@ -0,0 +1,10 @@
+import { defineConfig } from 'vitest/config'
+
+export default defineConfig({
+	test: {
+		name: 'llms',
+		include: ['src/**/*.test.ts'],
+		// Suppress console output from passing tests; failed tests still get their logs.
+		silent: 'passed-only',
+	},
+})

packages/mcp/README.md

@@ -36,11 +36,11 @@ Same format — add the config to the MCP settings of your client.
 
 ## MCP Tools
 
-| Tool           | Input              | Description                                          |
-| -------------- | ------------------ | ---------------------------------------------------- |
+| Tool           | Input              | Description                                           |
+| -------------- | ------------------ | ----------------------------------------------------- |
 | `execute_task` | `{ task: string }` | Execute a browser task in natural language. Blocking. |
-| `get_status`   | —                  | Returns `{ connected, busy }`                        |
-| `stop_task`    | —                  | Stop the currently running task.                     |
+| `get_status`   | —                  | Returns `{ connected, busy }`                         |
+| `stop_task`    | —                  | Stop the currently running task.                      |
 
 ## Environment Variables
 
@@ -88,7 +88,6 @@ src/
 ## Dev
 
 ```bash
-npm run build:libs
 npm run dev:ext
 npx @modelcontextprotocol/inspector node packages/mcp/src/index.js
 ```

packages/mcp/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/mcp",
     "private": false,
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
     "bin": {
         "page-agent-mcp": "src/index.js"
@@ -29,7 +29,7 @@
     },
     "dependencies": {
         "@modelcontextprotocol/sdk": "^1.29.0",
-        "ws": "^8.20.0",
-        "zod": "^4.3.5"
+        "ws": "^8.21.0",
+        "zod": "^4.4.3"
     }
 }

packages/mcp/src/hub-bridge.js

@@ -6,6 +6,7 @@ import { WebSocketServer } from 'ws'
 
 const EXT_ID = 'akldabonmimlicnjlflnapfeklbfemhj'
 const STORE_URL = `https://chromewebstore.google.com/detail/page-agent-ext/${EXT_ID}`
+const LOOPBACK_HOST = 'localhost'
 
 const launcherTemplate = readFileSync(
 	fileURLToPath(new URL('./launcher.html', import.meta.url)),
@@ -60,8 +61,8 @@ export class HubBridge {
 					reject(err)
 				}
 			})
-			this.#httpServer.listen(this.port, () => {
-				console.error(`[page-agent-mcp] HTTP + WS on http://localhost:${this.port}`)
+			this.#httpServer.listen(this.port, LOOPBACK_HOST, () => {
+				console.error(`[page-agent-mcp] HTTP + WS on http://${LOOPBACK_HOST}:${this.port}`)
 				resolve()
 			})
 		})

packages/mcp/src/index.js

@@ -2,6 +2,7 @@
 import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'
 import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
 import { exec } from 'node:child_process'
+import { readFileSync } from 'node:fs'
 import { platform } from 'node:os'
 import * as z from 'zod/v4'
 
@@ -9,6 +10,7 @@ import { HubBridge } from './hub-bridge.js'
 
 const env = process.env
 const port = parseInt(env.PORT || '38401')
+const { version } = JSON.parse(readFileSync(new URL('../package.json', import.meta.url), 'utf8'))
 
 /** @type {Record<string, string>} */
 const llmConfig = {}
@@ -30,7 +32,7 @@ exec(`${cmd} "${url}"`, (err) => {
 
 // --- MCP server (stdio) ---
 
-const mcpServer = new McpServer({ name: 'page-agent', version: '1.5.8' })
+const mcpServer = new McpServer({ name: 'page-agent', version })
 
 mcpServer.registerTool(
 	'execute_task',

packages/mcp/src/launcher.html

@@ -3,7 +3,10 @@
 	<head>
 		<meta charset="UTF-8" />
 		<meta name="viewport" content="width=device-width, initial-scale=1.0" />
-		<link rel="icon" href="https://img.alicdn.com/imgextra/i1/O1CN01mRGret1QrKiu7CFJI_!!6000000002029-2-tps-64-64.png" />
+		<link
+			rel="icon"
+			href="https://img.alicdn.com/imgextra/i1/O1CN01mRGret1QrKiu7CFJI_!!6000000002029-2-tps-64-64.png"
+		/>
 		<title>Page Agent MCP Launcher</title>
 		<style>
 			* {
@@ -172,16 +175,26 @@
 						If the extension is outdated, please update it to the latest version.
 					</li>
 					<li data-i18n="tip_other_browser">
-						If the extension is not installed in this browser, open this page from the
-						browser that has it installed.
+						If the extension is not installed in this browser, open this page from the browser that
+						has it installed.
 					</li>
 					<li data-i18n="tip_refresh">Refresh this page after installing or updating.</li>
 				</ul>
 			</div>
 
 			<div class="links">
-				<a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank" data-i18n="link_docs">Docs</a>
-				<a href="https://github.com/alibaba/page-agent/issues" target="_blank" data-i18n="link_issues">Report an Issue</a>
+				<a
+					href="https://alibaba.github.io/page-agent/docs/introduction/overview"
+					target="_blank"
+					data-i18n="link_docs"
+					>Docs</a
+				>
+				<a
+					href="https://github.com/alibaba/page-agent/issues"
+					target="_blank"
+					data-i18n="link_issues"
+					>Report an Issue</a
+				>
 			</div>
 		</div>
 
@@ -197,8 +210,7 @@
 					install_sub: 'Page Agent 需要安装最新版浏览器插件才能运行。',
 					install_btn: '从 Chrome 应用商店安装',
 					tip_outdated: '如果插件版本过旧，请更新到最新版本。',
-					tip_other_browser:
-						'如果该浏览器中未安装插件，请从装有插件的浏览器打开此页面。',
+					tip_other_browser: '如果该浏览器中未安装插件，请从装有插件的浏览器打开此页面。',
 					tip_refresh: '安装或更新后，请刷新此页面。',
 					link_docs: '文档',
 					link_issues: '问题反馈',
@@ -220,13 +232,9 @@
 					if (!globalThis.chrome?.runtime?.sendMessage) {
 						showInstall()
 					} else {
-						chrome.runtime.sendMessage(
-							EXT_ID,
-							{ type: 'OPEN_HUB', wsPort },
-							(response) => {
-								if (chrome.runtime.lastError || !response?.ok) showInstall()
-							}
-						)
+						chrome.runtime.sendMessage(EXT_ID, { type: 'OPEN_HUB', wsPort }, (response) => {
+							if (chrome.runtime.lastError || !response?.ok) showInstall()
+						})
 					}
 				} catch {
 					showInstall()

packages/page-agent/package.json

@@ -1,16 +1,26 @@
 {
     "name": "page-agent",
     "private": false,
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
-    "main": "./dist/esm/page-agent.js",
-    "module": "./dist/esm/page-agent.js",
-    "types": "./dist/esm/PageAgent.d.ts",
+    "main": "./src/PageAgent.ts",
+    "types": "./src/PageAgent.ts",
     "exports": {
         ".": {
-            "types": "./dist/esm/PageAgent.d.ts",
-            "import": "./dist/esm/page-agent.js",
-            "default": "./dist/esm/page-agent.js"
+            "types": "./src/PageAgent.ts",
+            "default": "./src/PageAgent.ts"
+        }
+    },
+    "publishConfig": {
+        "main": "./dist/esm/page-agent.js",
+        "module": "./dist/esm/page-agent.js",
+        "types": "./dist/esm/PageAgent.d.ts",
+        "exports": {
+            ".": {
+                "types": "./dist/esm/PageAgent.d.ts",
+                "import": "./dist/esm/page-agent.js",
+                "default": "./dist/esm/page-agent.js"
+            }
         }
     },
     "files": [
@@ -40,20 +50,20 @@
         "build": "vite build && npm run build:demo",
         "build:demo": "vite build --config vite.iife.config.js",
         "dev:demo": "concurrently \"vite build --config vite.iife.config.js --watch\" \"npx serve dist/iife -p 5174\"",
-        "prepublishOnly": "node -e \"const fs=require('fs');['README.md','LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
-        "postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+        "prepublishOnly": "node ../../scripts/pre-publish.js",
+        "postpublish": "node ../../scripts/post-publish.js"
     },
     "dependencies": {
-        "@page-agent/core": "1.7.1",
-        "@page-agent/llms": "1.7.1",
-        "@page-agent/page-controller": "1.7.1",
-        "@page-agent/ui": "1.7.1",
+        "@page-agent/core": "1.10.0",
+        "@page-agent/llms": "1.10.0",
+        "@page-agent/page-controller": "1.10.0",
+        "@page-agent/ui": "1.10.0",
         "chalk": "^5.6.2"
     },
     "peerDependencies": {
         "zod": "^3.25.0 || ^4.0.0"
     },
     "devDependencies": {
-        "zod": "^4.3.5"
+        "zod": "^4.4.3"
     }
 }

packages/page-agent/src/demo.ts

@@ -3,8 +3,12 @@
  */
 import { PageAgent, type PageAgentConfig } from './PageAgent'
 
+const currentScript = document.currentScript as HTMLScriptElement | null
+const currentScriptURL = currentScript?.src ? new URL(currentScript.src) : null
+const autoInit = currentScriptURL?.searchParams.get('autoInit') !== 'false'
+
 // Clean up existing instances to prevent multiple injections from bookmarklet
-if (window.pageAgent) {
+if (autoInit && window.pageAgent) {
 	window.pageAgent.dispose()
 }
 
@@ -17,32 +21,35 @@ const DEMO_MODEL = 'qwen3.5-plus'
 const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
 const DEMO_API_KEY = 'NA'
 
-const currentScript = document.currentScript as HTMLScriptElement | null
-
 // in case document.x is not ready yet
-setTimeout(() => {
-	let config: PageAgentConfig
+if (autoInit) {
+	setTimeout(() => {
+		let config: PageAgentConfig
+		let showPanel = true
 
-	if (currentScript) {
-		console.log('🚀 page-agent.js detected current script:', currentScript.src)
-		const url = new URL(currentScript.src)
-		const model = url.searchParams.get('model') || DEMO_MODEL
-		const baseURL = url.searchParams.get('baseURL') || DEMO_BASE_URL
-		const apiKey = url.searchParams.get('apiKey') || DEMO_API_KEY
-		const language = (url.searchParams.get('lang') as 'zh-CN' | 'en-US') || 'zh-CN'
-		config = { model, baseURL, apiKey, language }
-	} else {
-		console.log('🚀 page-agent.js no current script detected, using default demo config')
-		config = {
-			model: import.meta.env.LLM_MODEL_NAME ? import.meta.env.LLM_MODEL_NAME : DEMO_MODEL,
-			baseURL: import.meta.env.LLM_BASE_URL ? import.meta.env.LLM_BASE_URL : DEMO_BASE_URL,
-			apiKey: import.meta.env.LLM_API_KEY ? import.meta.env.LLM_API_KEY : DEMO_API_KEY,
+		if (currentScriptURL) {
+			const url = currentScriptURL
+			const model = url.searchParams.get('model') || DEMO_MODEL
+			const baseURL = url.searchParams.get('baseURL') || DEMO_BASE_URL
+			const apiKey = url.searchParams.get('apiKey') || DEMO_API_KEY
+			const language = (url.searchParams.get('lang') as 'zh-CN' | 'en-US') || 'zh-CN'
+			showPanel = ((url.searchParams.get('showPanel') as 'true' | 'false') || 'true') === 'true'
+			config = { model, baseURL, apiKey, language }
+		} else {
+			console.log('🚀 page-agent.js no current script detected, using default demo config')
+			config = {
+				model: import.meta.env.LLM_MODEL_NAME ? import.meta.env.LLM_MODEL_NAME : DEMO_MODEL,
+				baseURL: import.meta.env.LLM_BASE_URL ? import.meta.env.LLM_BASE_URL : DEMO_BASE_URL,
+				apiKey: import.meta.env.LLM_API_KEY ? import.meta.env.LLM_API_KEY : DEMO_API_KEY,
+			}
 		}
-	}
 
-	// Create agent
-	window.pageAgent = new PageAgent(config)
-	window.pageAgent.panel.show()
+		// Create agent
+		window.pageAgent = new PageAgent(config)
+		if (showPanel) {
+			window.pageAgent.panel.show()
+		}
 
-	console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
-})
+		console.log('🚀 page-agent.js initialized with config:', window.pageAgent.config)
+	})
+}

packages/page-agent/tsconfig.dts.json

@@ -1,9 +0,0 @@
-{
-    "extends": "./tsconfig.json",
-    "compilerOptions": {
-        // @workaround DTS bug
-        // dts do not work with monorepo path mapping
-        // disable path mapping for it
-        "paths": {}
-    }
-}

packages/page-agent/tsconfig.json

@@ -1,26 +1,8 @@
 {
     "extends": "../../tsconfig.base.json",
     "compilerOptions": {
-        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
-        "noEmit": false,
-        "allowImportingTsExtensions": false,
-        "baseUrl": ".",
-        "outDir": "dist",
-        "paths": {
-            //
-            "@page-agent/llms": ["../llms/src/index.ts"],
-            "@page-agent/page-controller": ["../page-controller/src/PageController.ts"],
-            "@page-agent/core": ["../core/src/PageAgentCore.ts"],
-            "@page-agent/ui": ["../ui/src/index.ts"]
-        }
+        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo"
     },
-    "include": ["**/*.ts"],
-    "exclude": ["dist", "node_modules"],
-    "references": [
-        //
-        { "path": "../llms" },
-        { "path": "../page-controller" },
-        { "path": "../core" },
-        { "path": "../ui" }
-    ]
+    "include": ["src/**/*.ts"],
+    "exclude": ["dist", "node_modules"]
 }

packages/page-agent/vite.config.js

@@ -11,13 +11,20 @@ const __dirname = dirname(fileURLToPath(import.meta.url))
 export default defineConfig({
 	clearScreen: false,
 	plugins: [
-		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
+		dts({
+			include: ['src/**/*.ts'],
+			exclude: ['src/**/*.test.ts'],
+			bundleTypes: true,
+			compilerOptions: {
+				composite: true,
+				noEmit: false,
+				emitDeclarationOnly: true,
+				declaration: true,
+			},
+		}),
 		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
 	],
 	publicDir: false,
-	esbuild: {
-		keepNames: true,
-	},
 	build: {
 		lib: {
 			entry: resolve(__dirname, 'src/PageAgent.ts'),

packages/page-agent/vite.iife.config.js

@@ -3,7 +3,6 @@ import { config as dotenvConfig } from 'dotenv'
 import { dirname, resolve } from 'path'
 import { fileURLToPath } from 'url'
 import { defineConfig } from 'vite'
-// import { analyzer } from 'vite-bundle-analyzer'
 import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
 
 const __dirname = dirname(fileURLToPath(import.meta.url))
@@ -21,17 +20,6 @@ export default defineConfig(() => ({
 		// analyzer()
 	],
 	publicDir: false,
-	esbuild: {
-		keepNames: true,
-	},
-	resolve: {
-		alias: {
-			'@page-agent/page-controller': resolve(__dirname, '../page-controller/src/PageController.ts'),
-			'@page-agent/llms': resolve(__dirname, '../llms/src/index.ts'),
-			'@page-agent/core': resolve(__dirname, '../core/src/PageAgentCore.ts'),
-			'@page-agent/ui': resolve(__dirname, '../ui/src/index.ts'),
-		},
-	},
 	build: {
 		lib: {
 			entry: resolve(__dirname, 'src/demo.ts'),

packages/page-controller/package.json

@@ -1,15 +1,25 @@
 {
     "name": "@page-agent/page-controller",
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
-    "main": "./dist/lib/page-controller.js",
-    "module": "./dist/lib/page-controller.js",
-    "types": "./dist/lib/PageController.d.ts",
+    "main": "./src/PageController.ts",
+    "types": "./src/PageController.ts",
     "exports": {
         ".": {
-            "types": "./dist/lib/PageController.d.ts",
-            "import": "./dist/lib/page-controller.js",
-            "default": "./dist/lib/page-controller.js"
+            "types": "./src/PageController.ts",
+            "default": "./src/PageController.ts"
+        }
+    },
+    "publishConfig": {
+        "main": "./dist/lib/page-controller.js",
+        "module": "./dist/lib/page-controller.js",
+        "types": "./dist/lib/PageController.d.ts",
+        "exports": {
+            ".": {
+                "types": "./dist/lib/PageController.d.ts",
+                "import": "./dist/lib/page-controller.js",
+                "default": "./dist/lib/page-controller.js"
+            }
         }
     },
     "files": [
@@ -32,10 +42,14 @@
     "homepage": "https://alibaba.github.io/page-agent/",
     "scripts": {
         "build": "vite build",
-        "prepublishOnly": "node -e \"const fs=require('fs');['LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
-        "postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+        "test": "vitest run",
+        "prepublishOnly": "node ../../scripts/pre-publish.js",
+        "postpublish": "node ../../scripts/post-publish.js"
     },
     "dependencies": {
         "ai-motion": "^0.4.8"
+    },
+    "devDependencies": {
+        "happy-dom": "^20.10.2"
     }
 }

packages/page-controller/src/PageController.test.ts

@@ -0,0 +1,40 @@
+import { describe, expect, it } from 'vitest'
+
+import { PageController } from './PageController'
+
+describe('PageController', () => {
+	it('constructs and exposes the current url', async () => {
+		const controller = new PageController()
+		expect(controller).toBeInstanceOf(PageController)
+		expect(await controller.getCurrentUrl()).toBe(window.location.href)
+	})
+
+	describe('executeJavascript', () => {
+		it('runs a script and returns its result', async () => {
+			const controller = new PageController()
+			const result = await controller.executeJavascript('return 1 + 2')
+			expect(result).toMatchObject({ success: true })
+			expect(result.message).toContain('3')
+		})
+
+		it('exposes the abort signal to the script scope', async () => {
+			const controller = new PageController()
+			const controllerSignal = new AbortController()
+			controllerSignal.abort()
+
+			const result = await controller.executeJavascript(
+				'return signal.aborted',
+				controllerSignal.signal
+			)
+			expect(result).toMatchObject({ success: true })
+			expect(result.message).toContain('true')
+		})
+
+		it('reports a syntax error as a failed result', async () => {
+			const controller = new PageController()
+			const result = await controller.executeJavascript('return (')
+			expect(result.success).toBe(false)
+			expect(result.message).toContain('❌')
+		})
+	})
+})

packages/page-controller/src/PageController.ts

@@ -185,7 +185,7 @@ export class PageController extends EventTarget {
 
 		const blacklist = [
 			...(this.config.interactiveBlacklist || []),
-			...document.querySelectorAll('[data-page-agent-not-interactive]').values(),
+			...Array.from(document.querySelectorAll('[data-page-agent-not-interactive]')),
 		]
 
 		this.flatTree = dom.getFlatTree({
@@ -376,13 +376,15 @@ export class PageController extends EventTarget {
 	}
 
 	/**
-	 * Execute arbitrary JavaScript on the page
+	 * Execute arbitrary JavaScript on the page.
+	 * The optional `signal` is exposed to the script scope so cooperative code
+	 * can abort promptly when the task is stopped.
 	 */
-	async executeJavascript(script: string): Promise<ActionResult> {
+	async executeJavascript(script: string, signal?: AbortSignal): Promise<ActionResult> {
 		try {
-			// Wrap script in async function to support await
-			const asyncFunction = eval(`(async () => { ${script} })`)
-			const result = await asyncFunction()
+			// Wrap script in async function to support await, exposing `signal`.
+			const asyncFunction = eval(`(async (signal) => { ${script} })`)
+			const result = await asyncFunction(signal)
 			return {
 				success: true,
 				message: `✅ Executed JavaScript. Result: ${result}`,

packages/page-controller/src/actions.ts

@@ -336,11 +336,13 @@ export async function scrollVertically(scroll_amount: number, element?: HTMLElem
 
 	const dy = scroll_amount
 	const bigEnough = (el: HTMLElement) => el.clientHeight >= window.innerHeight * 0.5
-	const canScroll = (el: HTMLElement | null) =>
-		el &&
-		/(auto|scroll|overlay)/.test(getComputedStyle(el).overflowY) &&
-		el.scrollHeight > el.clientHeight &&
-		bigEnough(el)
+	const canScroll = (el: HTMLElement | null): boolean =>
+		Boolean(
+			el &&
+			/(auto|scroll|overlay)/.test(getComputedStyle(el).overflowY) &&
+			el.scrollHeight > el.clientHeight &&
+			bigEnough(el)
+		)
 
 	// @deprecated Heuristic container search.
 	// Unreliable in multi-panel layouts. Should guide LLMs to use indexed scroll for consistency.
@@ -479,11 +481,13 @@ export async function scrollHorizontally(scroll_amount: number, element?: HTMLEl
 	const dx = scroll_amount
 
 	const bigEnough = (el: HTMLElement) => el.clientWidth >= window.innerWidth * 0.5
-	const canScroll = (el: HTMLElement | null) =>
-		el &&
-		/(auto|scroll|overlay)/.test(getComputedStyle(el).overflowX) &&
-		el.scrollWidth > el.clientWidth &&
-		bigEnough(el)
+	const canScroll = (el: HTMLElement | null): boolean =>
+		Boolean(
+			el &&
+			/(auto|scroll|overlay)/.test(getComputedStyle(el).overflowX) &&
+			el.scrollWidth > el.clientWidth &&
+			bigEnough(el)
+		)
 
 	// @deprecated Same heuristic container search as scrollVertically.
 	// TODO: Remove once LLMs reliably use indexed scrolling via data-scrollable.

packages/page-controller/src/dom/dom_tree/index.d.ts

@@ -0,0 +1,16 @@
+import type { FlatDomTree } from './type'
+
+interface DomTreeArgs {
+	doHighlightElements?: boolean
+	focusHighlightIndex?: number
+	viewportExpansion?: number
+	debugMode?: boolean
+	interactiveBlacklist?: Element[]
+	interactiveWhitelist?: Element[]
+	highlightOpacity?: number
+	highlightLabelOpacity?: number
+}
+
+declare const domTree: (args?: DomTreeArgs) => FlatDomTree
+
+export default domTree

packages/page-controller/src/dom/dom_tree/index.js

@@ -552,8 +552,6 @@ export default (
 			scrollData: scrollData,
 		})
 
-		console.log('scrollData!!!', scrollData)
-
 		return scrollData
 	}
 

packages/page-controller/src/mask/SimulatorMask.ts

@@ -10,6 +10,8 @@ export class SimulatorMask extends EventTarget {
 	wrapper = document.createElement('div')
 	motion: Motion | null = null
 
+	#disposed = false
+
 	#cursor = document.createElement('div')
 
 	#currentCursorX = 0
@@ -129,6 +131,8 @@ export class SimulatorMask extends EventTarget {
 	}
 
 	#moveCursorToTarget() {
+		if (this.#disposed) return
+
 		const newX = this.#currentCursorX + (this.#targetCursorX - this.#currentCursorX) * 0.2
 		const newY = this.#currentCursorY + (this.#targetCursorY - this.#currentCursorY) * 0.2
 
@@ -156,11 +160,15 @@ export class SimulatorMask extends EventTarget {
 	}
 
 	setCursorPosition(x: number, y: number) {
+		if (this.#disposed) return
+
 		this.#targetCursorX = x
 		this.#targetCursorY = y
 	}
 
 	triggerClickAnimation() {
+		if (this.#disposed) return
+
 		this.#cursor.classList.remove(cursorStyles.clicking)
 		// Force reflow to restart animation
 		void this.#cursor.offsetHeight
@@ -168,7 +176,7 @@ export class SimulatorMask extends EventTarget {
 	}
 
 	show() {
-		if (this.shown) return
+		if (this.shown || this.#disposed) return
 
 		this.shown = true
 		this.motion?.start()
@@ -186,7 +194,7 @@ export class SimulatorMask extends EventTarget {
 	}
 
 	hide() {
-		if (!this.shown) return
+		if (!this.shown || this.#disposed) return
 
 		this.shown = false
 		this.motion?.fadeOut()
@@ -200,7 +208,7 @@ export class SimulatorMask extends EventTarget {
 	}
 
 	dispose() {
-		console.log('dispose SimulatorMask')
+		this.#disposed = true
 		this.motion?.dispose()
 		this.wrapper.remove()
 		this.dispatchEvent(new Event('dispose'))

packages/page-controller/src/mask/checkDarkMode.ts

@@ -1,6 +1,25 @@
+/**
+ * A comprehensive function to determine if the page is currently in a dark theme.
+ * Heuristic check. Only work for common patterns. Return false by default.
+ */
+export function isPageDark() {
+	try {
+		if (hasDarkModeClass()) return true
+		if (hasDarkModeDataAttribute()) return true
+		if (isColorSchemeDark()) return true
+		if (isBackgroundDark()) return true
+		if (isMainContentBackgroundDark()) return true
+		if (isTextColorLight()) return true
+
+		return false
+	} catch (error) {
+		console.warn('Error determining if page is dark:', error)
+		return false
+	}
+}
+
 /**
  * Checks for common dark mode CSS classes on the html or body elements.
- * @returns {boolean} - True if a common dark mode class is found.
  */
 function hasDarkModeClass() {
 	const DEFAULT_DARK_MODE_CLASSES = ['dark', 'dark-mode', 'theme-dark', 'night', 'night-mode']
@@ -15,57 +34,47 @@ function hasDarkModeClass() {
 		}
 	}
 
-	// Some sites use data attributes
-	const darkThemeAttribute = htmlElement.getAttribute('data-theme')
-	if (darkThemeAttribute?.toLowerCase().includes('dark')) {
-		return true
+	return false
+}
+
+/**
+ * Some UI frameworks use data attributes to indicate theme
+ */
+function hasDarkModeDataAttribute() {
+	const htmlElement = document.documentElement
+	const bodyElement = document.body || document.documentElement // can be null in some cases
+
+	const dataAttrs = ['data-theme', 'data-color-mode', 'data-bs-theme', 'data-mui-color-scheme']
+	for (const attr of dataAttrs) {
+		const bodyValue = bodyElement?.getAttribute(attr)
+		const htmlValue = htmlElement.getAttribute(attr)
+
+		if (bodyValue?.toLowerCase() === 'dark' || htmlValue?.toLowerCase() === 'dark') {
+			return true
+		}
 	}
 
 	return false
 }
 
 /**
- * Parses an RGB or RGBA color string and returns an object with r, g, b properties.
- * @param {string} colorString - e.g., "rgb(34, 34, 34)" or "rgba(0, 0, 0, 0.5)"
- * @returns {{r: number, g: number, b: number}|null}
+ * Checks the CSS `color-scheme` property and `<meta name="color-scheme">` tag.
+ * Only "dark"/"only dark" counts as dark; "light dark" is ambiguous and ignored.
  */
-function parseRgbColor(colorString: string) {
-	const rgbMatch = /rgba?\((\d+),\s*(\d+),\s*(\d+)/.exec(colorString)
-	if (!rgbMatch) {
-		return null // Not a valid rgb/rgba string
-	}
-	return {
-		r: parseInt(rgbMatch[1]),
-		g: parseInt(rgbMatch[2]),
-		b: parseInt(rgbMatch[3]),
-	}
-}
+function isColorSchemeDark() {
+	// Check <meta name="color-scheme" content="dark">
+	const meta = document.querySelector<HTMLMetaElement>('meta[name="color-scheme"]')
+	const metaContent = meta?.content.toLowerCase()
+	if (metaContent === 'dark' || metaContent === 'only dark') return true
 
-/**
- * Determines if a color is "dark" based on its calculated luminance.
- * @param {string} colorString - The CSS color string (e.g., "rgb(50, 50, 50)").
- * @param {number} threshold - A value between 0 and 255. Colors with luminance below this will be considered dark. Default is 128.
- * @returns {boolean} - True if the color is considered dark.
- */
-function isColorDark(colorString: string, threshold = 128) {
-	if (!colorString || colorString === 'transparent' || colorString.startsWith('rgba(0, 0, 0, 0)')) {
-		return false // Transparent is not dark
-	}
-
-	const rgb = parseRgbColor(colorString)
-	if (!rgb) {
-		return false // Could not parse color
-	}
-
-	// Calculate perceived luminance using the standard formula
-	const luminance = 0.299 * rgb.r + 0.587 * rgb.g + 0.114 * rgb.b
-
-	return luminance < threshold
+	// Check the computed color-scheme CSS property on :root
+	const rootStyle = window.getComputedStyle(document.documentElement)
+	const colorScheme = rootStyle.getPropertyValue('color-scheme').trim().toLowerCase()
+	return colorScheme === 'dark' || colorScheme === 'only dark'
 }
 
 /**
  * Checks the background color of the body element to determine if the page is dark.
- * @returns {boolean}
  */
 function isBackgroundDark() {
 	// We check both <html> and <body> because some pages set the color on <html>
@@ -88,28 +97,85 @@ function isBackgroundDark() {
 }
 
 /**
- * A comprehensive function to determine if the page is currently in a dark theme.
- * It combines class checking and background color analysis.
- * @returns {boolean} - True if the page is likely dark.
+ * Checks if the text color on the body is light, which implies a dark background.
  */
-export function isPageDark() {
-	try {
-		// Strategy 1: Check for common dark mode classes
-		if (hasDarkModeClass()) {
-			return true
-		}
+function isTextColorLight() {
+	/** Luminance (0-255) above which body text is considered light */
+	const LIGHT_TEXT_LUMINANCE = 200
 
-		// Strategy 2: Analyze the computed background color
-		if (isBackgroundDark()) {
-			return true
-		}
+	const bodyStyle = window.getComputedStyle(document.body || document.documentElement)
+	const luminance = getLuminance(bodyStyle.color)
 
-		// @TODO add more checks here, e.g., analyzing text color,
-		// or checking the background of major layout elements like <main> or #app.
+	// Light text has high luminance (e.g. white text on dark bg)
+	return luminance !== null && luminance > LIGHT_TEXT_LUMINANCE
+}
 
-		return false
-	} catch (error) {
-		console.warn('Error determining if page is dark:', error)
-		return false
+/**
+ * Checks the background color of major layout elements (#app, #root, etc.).
+ * Many SPAs render into a container that may have its own dark background while
+ * <body> remains transparent.
+ */
+function isMainContentBackgroundDark() {
+	const { innerWidth: vw, innerHeight: vh } = window
+	const minArea = vw * vh * 0.5
+
+	const selectors = ['#app', '#root', '#__next']
+	for (const selector of selectors) {
+		const el = document.querySelector(selector)
+		if (!el) continue
+
+		const rect = el.getBoundingClientRect()
+		if (rect.width * rect.height < minArea) continue
+
+		if (isColorDark(window.getComputedStyle(el).backgroundColor)) return true
+	}
+	return false
+}
+
+// --- utils ---
+
+/**
+ * Parses an RGB or RGBA color string and returns an object with r, g, b properties.
+ * @param {string} colorString - e.g., "rgb(34, 34, 34)" or "rgba(0, 0, 0, 0.5)"
+ * @returns {{r: number, g: number, b: number}|null}
+ */
+function parseRgbColor(colorString: string) {
+	const rgbMatch = /rgba?\((\d+),\s*(\d+),\s*(\d+)/.exec(colorString)
+	if (!rgbMatch) {
+		return null // Not a valid rgb/rgba string
+	}
+	return {
+		r: parseInt(rgbMatch[1]),
+		g: parseInt(rgbMatch[2]),
+		b: parseInt(rgbMatch[3]),
 	}
 }
+
+/**
+ * Calculates the perceived luminance (0-255) of a CSS color string.
+ * @param {string} colorString - e.g., "rgb(50, 50, 50)" or "rgba(0, 0, 0, 0.5)"
+ * @returns {number|null} - The luminance, or null if the color is transparent or unparseable.
+ */
+function getLuminance(colorString: string): number | null {
+	if (!colorString || colorString === 'transparent' || colorString.startsWith('rgba(0, 0, 0, 0)')) {
+		return null // Transparent has no meaningful luminance
+	}
+
+	const rgb = parseRgbColor(colorString)
+	if (!rgb) {
+		return null // Could not parse color
+	}
+
+	// Standard perceived luminance formula
+	return 0.299 * rgb.r + 0.587 * rgb.g + 0.114 * rgb.b
+}
+
+/**
+ * Determines if a color is "dark" based on its calculated luminance.
+ * @param {string} colorString - The CSS color string (e.g., "rgb(50, 50, 50)").
+ * @param {number} threshold - A value between 0 and 255. Colors with luminance below this will be considered dark. Default is 128.
+ */
+function isColorDark(colorString: string, threshold = 128) {
+	const luminance = getLuminance(colorString)
+	return luminance !== null && luminance < threshold
+}

packages/page-controller/tsconfig.dts.json

@@ -1,9 +0,0 @@
-{
-    "extends": "./tsconfig.json",
-    "compilerOptions": {
-        // @workaround DTS bug
-        // dts do not work with monorepo path mapping
-        // disable path mapping for it
-        "paths": {}
-    }
-}

packages/page-controller/tsconfig.json

@@ -1,11 +1,7 @@
 {
     "extends": "../../tsconfig.base.json",
     "compilerOptions": {
-        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
-        "noEmit": false,
-        "allowImportingTsExtensions": false,
-        "baseUrl": ".",
-        "outDir": "dist"
+        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo"
     },
     "include": ["**/*.ts", "**/*.js"],
     "exclude": ["dist", "node_modules"]

packages/page-controller/vite.config.js

@@ -13,13 +13,20 @@ console.log(chalk.cyan(`📦 Building @page-agent/page-controller`))
 export default defineConfig({
 	clearScreen: false,
 	plugins: [
-		dts({ tsconfigPath: './tsconfig.dts.json', bundleTypes: true }),
+		dts({
+			include: ['src/**/*.ts'],
+			exclude: ['src/**/*.test.ts'],
+			bundleTypes: true,
+			compilerOptions: {
+				composite: true,
+				noEmit: false,
+				emitDeclarationOnly: true,
+				declaration: true,
+			},
+		}),
 		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
 	],
 	publicDir: false,
-	esbuild: {
-		keepNames: true,
-	},
 	build: {
 		lib: {
 			entry: resolve(__dirname, 'src/PageController.ts'),

packages/page-controller/vitest.config.js

@@ -0,0 +1,10 @@
+import { defineConfig } from 'vitest/config'
+
+export default defineConfig({
+	test: {
+		name: 'page-controller',
+		environment: 'happy-dom',
+		include: ['src/**/*.test.ts'],
+		silent: 'passed-only',
+	},
+})

packages/ui/package.json

@@ -1,15 +1,25 @@
 {
     "name": "@page-agent/ui",
-    "version": "1.7.1",
+    "version": "1.10.0",
     "type": "module",
-    "main": "./dist/lib/page-agent-ui.js",
-    "module": "./dist/lib/page-agent-ui.js",
-    "types": "./dist/lib/index.d.ts",
+    "main": "./src/index.ts",
+    "types": "./src/index.ts",
     "exports": {
         ".": {
-            "types": "./dist/lib/index.d.ts",
-            "import": "./dist/lib/page-agent-ui.js",
-            "default": "./dist/lib/page-agent-ui.js"
+            "types": "./src/index.ts",
+            "default": "./src/index.ts"
+        }
+    },
+    "publishConfig": {
+        "main": "./dist/lib/page-agent-ui.js",
+        "module": "./dist/lib/page-agent-ui.js",
+        "types": "./dist/lib/index.d.ts",
+        "exports": {
+            ".": {
+                "types": "./dist/lib/index.d.ts",
+                "import": "./dist/lib/page-agent-ui.js",
+                "default": "./dist/lib/page-agent-ui.js"
+            }
         }
     },
     "files": [
@@ -32,7 +42,7 @@
     "homepage": "https://alibaba.github.io/page-agent/",
     "scripts": {
         "build": "vite build",
-        "prepublishOnly": "node -e \"const fs=require('fs');['LICENSE'].forEach(f=>fs.copyFileSync('../../'+f,f))\"",
-        "postpublish": "node -e \"['LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
+        "prepublishOnly": "node ../../scripts/pre-publish.js",
+        "postpublish": "node ../../scripts/post-publish.js"
     }
 }

packages/ui/src/panel/Panel.module.css

@@ -291,7 +291,7 @@
 		transition: max-height 0.2s;
 
 		.expanded & {
-			max-height: 400px;
+			max-height: min(500px, calc(100vh - 200px - var(--height)));
 		}
 
 		.historyItem {

packages/ui/src/panel/Panel.ts

@@ -68,7 +68,7 @@ export class Panel {
 		this.#i18n = new I18n(config.language ?? 'en-US')
 
 		// Set up askUser callback on agent
-		this.#agent.onAskUser = (question) => this.#askUser(question)
+		this.#agent.onAskUser = (question, options) => this.#askUser(question, options?.signal)
 
 		// Create UI elements
 		this.#wrapper = this.#createWrapper()
@@ -100,10 +100,10 @@ export class Panel {
 	#handleStatusChange(): void {
 		const status = this.#agent.status
 
-		// Map agent status to UI indicator type
-		const indicatorType =
-			status === 'running' ? 'thinking' : status === 'idle' ? 'thinking' : status
-		this.#updateStatusIndicator(indicatorType)
+		// Map agent status to UI indicator. A `completed` run whose result reports
+		// failure shows as error; other statuses map to their own indicator.
+		const failed = status === 'completed' && this.#agent.lastResult?.success === false
+		this.#updateStatusIndicator(failed ? 'error' : status)
 
 		// Morph action button: running = stop (■), not running = close (X)
 		if (status === 'running') {
@@ -121,7 +121,7 @@ export class Panel {
 		}
 
 		// Handle completion
-		if (status === 'completed' || status === 'error') {
+		if (status === 'completed' || status === 'error' || status === 'stopped') {
 			if (!this.#isExpanded) {
 				this.#expand()
 			}
@@ -169,10 +169,12 @@ export class Panel {
 	}
 
 	/**
-	 * Ask for user input (internal, called by agent via onAskUser)
+	 * Ask for user input (internal, called by agent via onAskUser).
+	 * Rejects when `signal` aborts (task stopped or disposed), cleaning up the
+	 * question card and pending state so the agent loop can settle.
 	 */
-	#askUser(question: string): Promise<string> {
-		return new Promise((resolve) => {
+	#askUser(question: string, signal?: AbortSignal): Promise<string> {
+		return new Promise((resolve, reject) => {
 			// Set `waiting for user answer` state
 			this.#isWaitingForUserAnswer = true
 			this.#userAnswerResolver = resolve
@@ -195,6 +197,27 @@ export class Panel {
 			this.#scrollToBottom()
 
 			this.#showInputArea(this.#i18n.t('ui.panel.userAnswerPrompt'))
+
+			signal?.addEventListener(
+				'abort',
+				() => {
+					this.#removeTempCards()
+					this.#isWaitingForUserAnswer = false
+					this.#userAnswerResolver = null
+					// reason is a DOMException AbortError (abort() takes no args).
+					reject(signal.reason as DOMException)
+				},
+				{ once: true }
+			)
+		})
+	}
+
+	/** Remove temporary question cards (only direct children for safety) */
+	#removeTempCards(): void {
+		Array.from(this.#historySection.children).forEach((child) => {
+			if (child.getAttribute('data-temp-card') === 'true') {
+				child.remove()
+			}
 		})
 	}
 
@@ -307,12 +330,7 @@ export class Panel {
 	 * Handle user answer
 	 */
 	#handleUserAnswer(input: string): void {
-		// Remove temporary question cards (only direct children for safety)
-		Array.from(this.#historySection.children).forEach((child) => {
-			if (child.getAttribute('data-temp-card') === 'true') {
-				child.remove()
-			}
-		})
+		this.#removeTempCards()
 
 		// Reset state
 		this.#isWaitingForUserAnswer = false
@@ -358,7 +376,7 @@ export class Panel {
 		}
 
 		const status = this.#agent.status
-		const isTaskEnded = status === 'completed' || status === 'error'
+		const isTaskEnded = status === 'completed' || status === 'error' || status === 'stopped'
 
 		// Only show input area after task completion if configured to do so
 		if (isTaskEnded) {
@@ -541,13 +559,23 @@ export class Panel {
 	}
 
 	#updateStatusIndicator(
-		type: 'thinking' | 'executing' | 'executed' | 'retrying' | 'completed' | 'error'
+		type:
+			| 'idle'
+			| 'running'
+			| 'thinking'
+			| 'executing'
+			| 'executed'
+			| 'retrying'
+			| 'completed'
+			| 'error'
+			| 'stopped'
 	): void {
-		// Clear all status classes
+		// `running` animates like thinking; `idle`/`stopped` use the neutral base.
+		const variant = type === 'running' ? 'thinking' : type
 		this.#indicator.className = styles.indicator
-
-		// Add corresponding status class
-		this.#indicator.classList.add(styles[type])
+		if (variant !== 'idle' && variant !== 'stopped') {
+			this.#indicator.classList.add(styles[variant])
+		}
 	}
 
 	#scrollToBottom(): void {

packages/ui/src/panel/types.ts

@@ -22,14 +22,17 @@ export type AgentActivity =
  * This enables decoupling and allows any agent implementation to work with Panel.
  *
  * Events:
- * - 'statuschange': Agent status changed (idle/running/completed/error)
+ * - 'statuschange': Agent status changed
  * - 'historychange': Historical events updated (persisted)
  * - 'activity': Transient activity for immediate UI feedback (thinking/executing/etc)
  * - 'dispose': Agent is being disposed
  */
 export interface PanelAgentAdapter extends EventTarget {
 	/** Current agent status */
-	readonly status: 'idle' | 'running' | 'completed' | 'error'
+	readonly status: 'idle' | 'running' | 'completed' | 'error' | 'stopped'
+
+	/** Result of the most recent run, or `null` before the first run completes */
+	readonly lastResult: { success: boolean } | null
 
 	/** History of agent events */
 	readonly history: readonly {
@@ -60,16 +63,18 @@ export interface PanelAgentAdapter extends EventTarget {
 	readonly task: string
 
 	/**
-	 * Callback for when agent needs user input.
+	 * Called when the agent needs to ask the user questions.
+	 * If unset, the `ask_user` tool will be disabled.
 	 * Panel will set this to handle user questions via its UI.
+	 * The optional `signal` aborts when the task is stopped or disposed.
 	 */
-	onAskUser?: (question: string) => Promise<string>
+	onAskUser?: (question: string, options?: { signal: AbortSignal }) => Promise<string>
 
 	/** Execute a task */
 	execute(task: string): Promise<unknown>
 
 	/** Stop the current task (agent remains reusable) */
-	stop(): void
+	stop(): Promise<void>
 
 	/** Dispose the agent (terminal, cannot be reused) */
 	dispose(): void

packages/ui/tsconfig.dts.json

@@ -1,9 +0,0 @@
-{
-    "extends": "./tsconfig.json",
-    "compilerOptions": {
-        // @workaround DTS bug
-        // dts do not work with monorepo path mapping
-        // disable path mapping for it
-        "paths": {}
-    }
-}

packages/ui/tsconfig.json

@@ -1,11 +1,7 @@
 {
     "extends": "../../tsconfig.base.json",
     "compilerOptions": {
-        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
-        "noEmit": false,
-        "allowImportingTsExtensions": false,
-        "baseUrl": ".",
-        "outDir": "dist"
+        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo"
     },
     "include": ["**/*.ts", "**/*.js"],
     "exclude": ["dist", "node_modules"]