Add initial chunk emission for agent response processing

- Emit `ChunkType.LLM_RESPONSE_CREATED` event to mirror assistant behavior
- Ensure UI reflects pending state immediately during response processing
- Maintain consistency with existing stream processing callback structure

.github/CODEOWNERS

@@ -0,0 +1,4 @@
+/src/renderer/src/store/ @0xfullex
+/src/main/services/ConfigManager.ts @0xfullex
+/packages/shared/IpcChannel.ts @0xfullex
+/src/main/ipc.ts @0xfullex

.github/ISSUE_TEMPLATE/#0_bug_report.yml

@@ -1,94 +0,0 @@
-name: 🐛 错误报告 (中文)
-description: 创建一个报告以帮助我们改进
-title: '[错误]: '
-labels: ['BUG']
-body:
-  - type: markdown
-    attributes:
-      value: |
-        感谢您花时间填写此错误报告！
-        在提交此问题之前，请确保您已经了解了[常见问题](https://docs.cherry-ai.com/question-contact/questions)和[知识科普](https://docs.cherry-ai.com/question-contact/knowledge)
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: 提交前检查
-      description: |
-        在提交 Issue 前请确保您已经完成了以下所有步骤
-      options:
-        - label: 我理解 Issue 是用于反馈和解决问题的，而非吐槽评论区，将尽可能提供更多信息帮助问题解决。
-          required: true
-        - label: 我的问题不是 [常见问题](https://github.com/CherryHQ/cherry-studio/issues/3881) 中的内容。
-          required: true
-        - label: 我已经查看了 **置顶 Issue** 并搜索了现有的 [开放Issue](https://github.com/CherryHQ/cherry-studio/issues)和[已关闭Issue](https://github.com/CherryHQ/cherry-studio/issues?q=is%3Aissue%20state%3Aclosed%20)，没有找到类似的问题。
-          required: true
-        - label: 我填写了简短且清晰明确的标题，以便开发者在翻阅 Issue 列表时能快速确定大致问题。而不是“一个建议”、“卡住了”等。
-          required: true
-        - label: 我确认我正在使用最新版本的 Cherry Studio。
-          required: true
-
-  - type: dropdown
-    id: platform
-    attributes:
-      label: 平台
-      description: 您正在使用哪个平台？
-      options:
-        - Windows
-        - macOS
-        - Linux
-    validations:
-      required: true
-
-  - type: input
-    id: version
-    attributes:
-      label: 版本
-      description: 您正在运行的 Cherry Studio 版本是什么？
-      placeholder: 例如 v1.0.0
-    validations:
-      required: true
-
-  - type: textarea
-    id: description
-    attributes:
-      label: 错误描述
-      description: 描述问题时请尽可能详细。请尽可能提供截图或屏幕录制，以帮助我们更好地理解问题。
-      placeholder: 告诉我们发生了什么...(记得附上截图/录屏，如果适用)
-    validations:
-      required: true
-
-  - type: textarea
-    id: reproduction
-    attributes:
-      label: 重现步骤
-      description: 提供详细的重现步骤，以便于我们的开发人员可以准确地重现问题。请尽可能为每个步骤提供截图或屏幕录制。
-      placeholder: |
-        1. 转到 '...'
-        2. 点击 '....'
-        3. 向下滚动到 '....'
-        4. 看到错误
-
-        记得尽可能为每个步骤附上截图/录屏！
-    validations:
-      required: true
-
-  - type: textarea
-    id: expected
-    attributes:
-      label: 预期行为
-      description: 清晰简洁地描述您期望发生的事情
-    validations:
-      required: true
-
-  - type: textarea
-    id: logs
-    attributes:
-      label: 相关日志输出
-      description: 请复制并粘贴任何相关的日志输出
-      render: shell
-
-  - type: textarea
-    id: additional
-    attributes:
-      label: 附加信息
-      description: 任何能让我们对你所遇到的问题有更多了解的东西

.github/ISSUE_TEMPLATE/#1_feature_request.yml

@@ -1,76 +0,0 @@
-name: 💡 功能建议 (中文)
-description: 为项目提出新的想法
-title: '[功能]: '
-labels: ['feature']
-body:
-  - type: markdown
-    attributes:
-      value: |
-        感谢您花时间提出新的功能建议!
-        在提交此问题之前，请确保您已经了解了[项目规划](https://docs.cherry-ai.com/cherrystudio/planning)和[功能介绍](https://docs.cherry-ai.com/cherrystudio/preview)
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: 提交前检查
-      description: |
-        在提交 Issue 前请确保您已经完成了以下所有步骤
-      options:
-        - label: 我理解 Issue 是用于反馈和解决问题的，而非吐槽评论区，将尽可能提供更多信息帮助问题解决。
-          required: true
-        - label: 我已经查看了置顶 Issue 并搜索了现有的 [开放Issue](https://github.com/CherryHQ/cherry-studio/issues)和[已关闭Issue](https://github.com/CherryHQ/cherry-studio/issues?q=is%3Aissue%20state%3Aclosed%20)，没有找到类似的建议。
-          required: true
-        - label: 我填写了简短且清晰明确的标题，以便开发者在翻阅 Issue 列表时能快速确定大致问题。而不是“一个建议”、“卡住了”等。
-          required: true
-        - label: 最新的 Cherry Studio 版本没有实现我所提出的功能。
-          required: true
-
-  - type: dropdown
-    id: platform
-    attributes:
-      label: 平台
-      description: 您正在使用哪个平台？
-      options:
-        - Windows
-        - macOS
-        - Linux
-    validations:
-      required: true
-
-  - type: input
-    id: version
-    attributes:
-      label: 版本
-      description: 您正在运行的 Cherry Studio 版本是什么？
-      placeholder: 例如 v1.0.0
-    validations:
-      required: true
-
-  - type: textarea
-    id: problem
-    attributes:
-      label: 您的功能建议是否与某个问题/issue相关?
-      description: 请简明扼要地描述您遇到的问题
-      placeholder: 我总是感到沮丧,因为...
-    validations:
-      required: true
-
-  - type: textarea
-    id: solution
-    attributes:
-      label: 请描述您希望实现的解决方案
-      description: 请简明扼要地描述您希望发生的情况
-    validations:
-      required: true
-
-  - type: textarea
-    id: alternatives
-    attributes:
-      label: 请描述您考虑过的其他方案
-      description: 请简明扼要地描述您考虑过的任何其他解决方案或功能
-
-  - type: textarea
-    id: additional
-    attributes:
-      label: 其他补充信息
-      description: 在此添加任何其他与功能建议相关的上下文或截图

.github/ISSUE_TEMPLATE/#2_question.yml

@@ -1,77 +0,0 @@
-name: ❓ 提问 & 讨论 (中文)
-description: 寻求帮助、讨论问题、提出疑问等...
-title: '[讨论]: '
-labels: ['discussion', 'help wanted']
-body:
-  - type: markdown
-    attributes:
-      value: |
-        感谢您的提问！请尽可能详细地描述您的问题，这样我们才能更好地帮助您。
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: Issue 检查清单
-      description: |
-        在提交 Issue 前请确保您已经完成了以下所有步骤
-      options:
-        - label: 我理解 Issue 是用于反馈和解决问题的，而非吐槽评论区，将尽可能提供更多信息帮助问题解决。
-          required: true
-        - label: 我确认自己需要的是提出问题并且讨论问题，而不是 Bug 反馈或需求建议。
-          required: true
-
-  - type: dropdown
-    id: platform
-    attributes:
-      label: 平台
-      description: 您正在使用哪个平台？
-      options:
-        - Windows
-        - macOS
-        - Linux
-    validations:
-      required: true
-
-  - type: input
-    id: version
-    attributes:
-      label: 版本
-      description: 您正在运行的 Cherry Studio 版本是什么？
-      placeholder: 例如 v1.0.0
-    validations:
-      required: true
-
-  - type: textarea
-    id: question
-    attributes:
-      label: 您的问题
-      description: 请详细描述您的问题
-      placeholder: 请尽可能清楚地说明您的问题...
-    validations:
-      required: true
-
-  - type: textarea
-    id: context
-    attributes:
-      label: 相关背景
-      description: 请提供一些背景信息，帮助我们更好地理解您的问题
-      placeholder: 例如：使用场景、已尝试的解决方案等
-
-  - type: textarea
-    id: additional
-    attributes:
-      label: 补充信息
-      description: 任何其他相关的信息、截图或代码示例
-      render: shell
-
-  - type: dropdown
-    id: priority
-    attributes:
-      label: 优先级
-      description: 这个问题对您来说有多紧急？
-      options:
-        - 低 (有空再看)
-        - 中 (希望尽快得到答复)
-        - 高 (阻碍工作进行)
-    validations:
-      required: true

.github/ISSUE_TEMPLATE/#3_others.yml

@@ -1,76 +0,0 @@
-name: 🤔 其他问题 (中文)
-description: 提交不属于错误报告或功能需求的问题
-title: '[其他]: '
-body:
-  - type: markdown
-    attributes:
-      value: |
-        感谢您花时间提出问题！
-        在提交此问题之前，请确保您已经了解了[常见问题](https://docs.cherry-ai.com/question-contact/questions)和[知识科普](https://docs.cherry-ai.com/question-contact/knowledge)
-
-  - type: checkboxes
-    id: checklist
-    attributes:
-      label: 提交前检查
-      description: |
-        在提交 Issue 前请确保您已经完成了以下所有步骤
-      options:
-        - label: 我理解 Issue 是用于反馈和解决问题的，而非吐槽评论区，将尽可能提供更多信息帮助问题解决。
-          required: true
-        - label: 我已经查看了置顶 Issue 并搜索了现有的 [开放Issue](https://github.com/CherryHQ/cherry-studio/issues)和[已关闭Issue](https://github.com/CherryHQ/cherry-studio/issues?q=is%3Aissue%20state%3Aclosed%20)，没有找到类似的问题。
-          required: true
-        - label: 我填写了简短且清晰明确的标题，以便开发者在翻阅 Issue 列表时能快速确定大致问题。而不是"一个问题"、"求助"等。
-          required: true
-        - label: 我的问题不属于错误报告或功能需求类别。
-          required: true
-
-  - type: dropdown
-    id: platform
-    attributes:
-      label: 平台
-      description: 您正在使用哪个平台？
-      options:
-        - Windows
-        - macOS
-        - Linux
-    validations:
-      required: true
-
-  - type: input
-    id: version
-    attributes:
-      label: 版本
-      description: 您正在运行的 Cherry Studio 版本是什么？
-      placeholder: 例如 v1.0.0
-    validations:
-      required: true
-
-  - type: textarea
-    id: question
-    attributes:
-      label: 问题描述
-      description: 请详细描述您的问题或疑问
-      placeholder: 我想了解有关...的更多信息
-    validations:
-      required: true
-
-  - type: textarea
-    id: context
-    attributes:
-      label: 相关背景
-      description: 请提供与您的问题相关的任何背景信息或上下文
-      placeholder: 我尝试实现...时遇到了疑问
-    validations:
-      required: true
-
-  - type: textarea
-    id: attempts
-    attributes:
-      label: 您已尝试的方法
-      description: 请描述您为解决问题已经尝试过的方法（如果有）
-
-  - type: textarea
-    id: additional
-    attributes:
-      label: 附加信息
-      description: 任何能让我们对您的问题有更多了解的信息，包括截图或相关链接

.github/workflows/auto-i18n.yml

@@ -0,0 +1,66 @@
+name: Auto I18N
+
+env:
+  API_KEY: ${{ secrets.TRANSLATE_API_KEY }}
+  MODEL: ${{ vars.MODEL || 'deepseek/deepseek-v3.1'}}
+  BASE_URL: ${{ vars.BASE_URL || 'https://api.ppinfra.com/openai'}}
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+  workflow_dispatch:
+
+jobs:
+  auto-i18n:
+    runs-on: ubuntu-latest
+    if: github.event.pull_request.head.repo.full_name == 'CherryHQ/cherry-studio'
+    name: Auto I18N
+    permissions:
+      contents: write
+      pull-requests: write
+
+    steps:
+      - name: 🐈‍⬛ Checkout
+        uses: actions/checkout@v5
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+
+      - name: 📦 Setting Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: 📦 Install dependencies in isolated directory
+        run: |
+          # 在临时目录安装依赖
+          mkdir -p /tmp/translation-deps
+          cd /tmp/translation-deps
+          echo '{"dependencies": {"openai": "^5.12.2", "cli-progress": "^3.12.0", "tsx": "^4.20.3", "@biomejs/biome": "2.2.4"}}' > package.json
+          npm install --no-package-lock
+
+          # 设置 NODE_PATH 让项目能找到这些依赖
+          echo "NODE_PATH=/tmp/translation-deps/node_modules" >> $GITHUB_ENV
+
+      - name: 🏃‍♀️ Translate
+        run: npx tsx scripts/auto-translate-i18n.ts
+
+      - name: 🔍 Format
+        run: cd /tmp/translation-deps && npx biome format --config-path /home/runner/work/cherry-studio/cherry-studio/biome.jsonc --write /home/runner/work/cherry-studio/cherry-studio/src/renderer/src/i18n/
+
+      - name: 🔄 Commit changes
+        run: |
+          git config --local user.email "action@github.com"
+          git config --local user.name "GitHub Action"
+          git add .
+          git reset -- package.json yarn.lock  # 不提交 package.json 和 yarn.lock 的更改
+          if git diff --cached --quiet; then
+            echo "No changes to commit"
+          else
+            git commit -m "fix(i18n): Auto update translations for PR #${{ github.event.pull_request.number }}"
+          fi
+
+      - name: 🚀 Push changes
+        uses: ad-m/github-push-action@master
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          branch: ${{ github.event.pull_request.head.ref }}

.github/workflows/claude-code-review.yml

@@ -0,0 +1,56 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened]
+    # Optional: Only run on specific file changes
+    # paths:
+    #   - "src/**/*.ts"
+    #   - "src/**/*.tsx"
+    #   - "src/**/*.js"
+    #   - "src/**/*.jsx"
+
+jobs:
+  claude-review:
+    # Only trigger code review for PRs from the main repository due to upstream OIDC issues
+    # https://github.com/anthropics/claude-code-action/issues/542
+    if: |
+      (github.event.pull_request.head.repo.full_name == github.repository) &&
+      (github.event.pull_request.draft == false)
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: read
+      id-token: write
+      actions: read
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          prompt: |
+            Please review this pull request and provide feedback on:
+            - Code quality and best practices
+            - Potential bugs or issues
+            - Performance considerations
+            - Security concerns
+            - Test coverage
+
+            PR number: ${{ github.event.number }}
+            Repo: ${{ github.repository }}
+
+            Use the repository's CLAUDE.md for guidance on style and conventions. Be constructive and helpful in your feedback.
+
+            Use `gh pr comment` with your Bash tool to leave your review as a comment on the PR.
+
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://docs.anthropic.com/en/docs/claude-code/sdk#command-line for available options
+          claude_args: '--allowed-tools "Bash(gh issue view:*),Bash(gh search:*),Bash(gh issue list:*),Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*),Bash(gh pr list:*)"'

.github/workflows/claude-translator.yml

@@ -0,0 +1,107 @@
+name: Claude Translator
+concurrency:
+  group: translator-${{ github.event.comment.id || github.event.issue.number || github.event.review.id }}
+  cancel-in-progress: false
+
+on:
+  issues:
+    types: [opened]
+  issue_comment:
+    types: [created, edited]
+  pull_request_review:
+    types: [submitted, edited]
+  pull_request_review_comment:
+    types: [created, edited]
+
+jobs:
+  translate:
+    if: |
+      (github.event_name == 'issues') ||
+      (github.event_name == 'issue_comment' && github.event.sender.type != 'Bot') ||
+      (github.event_name == 'pull_request_review' && github.event.sender.type != 'Bot') ||
+      (github.event_name == 'pull_request_review_comment' && github.event.sender.type != 'Bot')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      issues: write # 编辑issues/comments
+      pull-requests: write
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude for translation
+        uses: anthropics/claude-code-action@main
+        id: claude
+        with:
+          # Warning: Permissions should have been controlled by workflow permission.
+          # Now `contents: read` is safe for files, but we could make a fine-grained token to control it.
+          # See: https://github.com/anthropics/claude-code-action/blob/main/docs/security.md
+          github_token: ${{ secrets.TOKEN_GITHUB_WRITE }}
+          allowed_non_write_users: "*"
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          claude_args: "--allowed-tools Bash(gh issue:*),Bash(gh api:repos/*/issues:*),Bash(gh api:repos/*/pulls/*/reviews/*),Bash(gh api:repos/*/pulls/comments/*)"
+          prompt: |
+            你是一个多语言翻译助手。你需要响应 GitHub Webhooks 中的以下四种事件：
+
+            - issues
+            - issue_comment
+            - pull_request_review
+            - pull_request_review_comment
+
+            请完成以下任务：
+
+            1. 获取当前事件的完整信息。
+
+               - 如果当前事件是 issues，就获取该 issues 的信息。
+               - 如果当前事件是 issue_comment，就获取该 comment 的信息。
+               - 如果当前事件是 pull_request_review，就获取该 review 的信息。
+               - 如果当前事件是 pull_request_review_comment，就获取该 comment 的信息。
+
+            2. 智能检测内容。
+
+                - 如果获取到的信息是已经遵循格式要求翻译过的内容，则检查翻译内容和原始内容是否匹配。若不匹配，则重新翻译一次令其匹配，并遵循格式要求；
+                - 如果获取到的信息是未翻译过的内容，检查其内容语言。若不是英文，则翻译成英文；
+                - 如果获取到的信息是部分翻译为英文的内容，则将其翻译为英文；
+                - 如果获取到的信息包含了对已翻译内容的引用，则将引用内容清理为仅含英文的内容。引用的内容不能够包含"This xxx was translated by Claude"和"Original Content`等内容。
+                - 如果获取到的信息包含了其他类型的引用，即对非 Claude 翻译的内容的引用，则直接照原样引用，不进行翻译。
+                - 如果获取到的信息是通过邮件回复的内容，则在翻译时应当将邮件内容的引用放到最后。在原始内容和翻译内容中只需要回复的内容本身，不要包含对邮件内容的引用。
+                - 如果获取到的信息本身不需要任何处理，则跳过任务。
+
+            3. 格式要求：
+
+               - 标题：英文翻译（如果非英文）
+               - 内容格式：
+                 > [!NOTE]
+                 > This issue/comment/review was translated by Claude.
+
+                 [翻译内容]
+
+                 ---
+                 <details>
+                 <summary>Original Content</summary>
+                 [原始内容]
+                 </details>
+
+            4. 使用gh工具更新：
+
+               - 根据环境信息中的Event类型选择正确的命令：
+                 - 如果 Event 是 'issues': gh issue edit [ISSUE_NUMBER] --title "[英文标题]" --body "[翻译内容 + 原始内容]"
+                 - 如果 Event 是 'issue_comment': gh api -X PATCH /repos/${{ github.repository }}/issues/comments/${{ github.event.comment.id }} -f body="[翻译内容 + 原始内容]"
+                 - 如果 Event 是 'pull_request_review': gh api -X PUT /repos/${{ github.repository }}/pulls/${{ github.event.pull_request.number }}/reviews/${{ github.event.review.id }} -f body="[翻译内容]"
+                 - 如果 Event 是 'pull_request_review_comment': gh api -X PATCH /repos/${{ github.repository }}/pulls/comments/${{ github.event.comment.id }} -f body="[翻译内容 + 原始内容]"
+
+            环境信息：
+            - Event: ${{ github.event_name }}
+            - Issue Number: ${{ github.event.issue.number }}
+            - Repository: ${{ github.repository }}
+            - (Review) Comment ID: ${{ github.event.comment.id || 'N/A' }}
+            - Pull Request Number: ${{ github.event.pull_request.number || 'N/A' }}
+            - Review ID: ${{ github.event.review.id || 'N/A' }}
+
+
+            使用以下命令获取完整信息：
+            gh issue view ${{ github.event.issue.number }} --json title,body,comments

.github/workflows/claude.yml

@@ -0,0 +1,60 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment'
+        && contains(github.event.comment.body, '@claude')
+        && contains(fromJSON('["COLLABORATOR","MEMBER","OWNER"]'), github.event.comment.author_association))
+      ||
+      (github.event_name == 'pull_request_review_comment'
+        && contains(github.event.comment.body, '@claude')
+        && contains(fromJSON('["COLLABORATOR","MEMBER","OWNER"]'), github.event.comment.author_association))
+      ||
+      (github.event_name == 'pull_request_review'
+        && contains(github.event.review.body, '@claude')
+        && contains(fromJSON('["COLLABORATOR","MEMBER","OWNER"]'), github.event.review.author_association))
+      ||
+      (github.event_name == 'issues'
+        && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude'))
+        && contains(fromJSON('["COLLABORATOR","MEMBER","OWNER"]'), github.event.issue.author_association))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+      actions: read # Required for Claude to read CI results on PRs
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+
+          # Optional: Give a custom prompt to Claude. If this is not specified, Claude will perform the instructions specified in the comment that tagged it.
+          # prompt: 'Update the pull request description to include a summary of changes.'
+
+          # Optional: Add claude_args to customize behavior and configuration
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://docs.anthropic.com/en/docs/claude-code/sdk#command-line for available options
+          # claude_args: '--model claude-opus-4-1-20250805 --allowed-tools Bash(gh pr:*)'

.github/workflows/pr-ci.yml

@@ -9,6 +9,7 @@ on:
     branches:
       - main
       - develop
+      - v2
 
 jobs:
   build:
@@ -48,6 +49,9 @@ jobs:
       - name: Lint Check
         run: yarn test:lint
 
+      - name: Format Check
+        run: yarn format:check
+
       - name: Type Check
         run: yarn typecheck
 

.gitignore

@@ -37,6 +37,7 @@ dist
 out
 mcp_server
 stats.html
+.eslintcache
 
 # ENV
 .env
@@ -68,3 +69,5 @@ playwright-report
 test-results
 
 YOUR_MEMORY_FILE_PATH
+
+.sessions/

.oxlintrc.json

@@ -0,0 +1,215 @@
+{
+  "$schema": "./node_modules/oxlint/configuration_schema.json",
+  "categories": {},
+  "env": {
+    "es2022": true
+  },
+  "globals": {},
+  "ignorePatterns": [
+    "node_modules/**",
+    "build/**",
+    "dist/**",
+    "out/**",
+    "local/**",
+    ".yarn/**",
+    ".gitignore",
+    "scripts/cloudflare-worker.js",
+    "src/main/integration/nutstore/sso/lib/**",
+    "src/main/integration/cherryin/index.js",
+    "src/main/integration/nutstore/sso/lib/**",
+    "src/renderer/src/ui/**",
+    "packages/**/dist",
+    "eslint.config.mjs"
+  ],
+  "overrides": [
+    // set different env
+    {
+      "env": {
+        "node": true
+      },
+      "files": ["src/main/**", "resources/scripts/**", "scripts/**", "playwright.config.ts", "electron.vite.config.ts"]
+    },
+    {
+      "env": {
+        "browser": true
+      },
+      "files": [
+        "src/renderer/**/*.{ts,tsx}",
+        "packages/aiCore/**",
+        "packages/extension-table-plus/**",
+        "resources/js/**"
+      ]
+    },
+    {
+      "env": {
+        "node": true,
+        "vitest": true
+      },
+      "files": ["**/__tests__/*.test.{ts,tsx}", "tests/**"]
+    },
+    {
+      "env": {
+        "browser": true,
+        "node": true
+      },
+      "files": ["src/preload/**"]
+    }
+  ],
+  // We don't use the React plugin here because its behavior differs slightly from that of ESLint's React plugin.
+  "plugins": ["unicorn", "typescript", "oxc", "import"],
+  "rules": {
+    "constructor-super": "error",
+    "for-direction": "error",
+    "getter-return": "error",
+    "no-array-constructor": "off",
+    // "import/no-cycle": "error", // tons of error, bro
+    "no-async-promise-executor": "error",
+    "no-caller": "warn",
+    "no-case-declarations": "error",
+    "no-class-assign": "error",
+    "no-compare-neg-zero": "error",
+    "no-cond-assign": "error",
+    "no-const-assign": "error",
+    "no-constant-binary-expression": "error",
+    "no-constant-condition": "error",
+    "no-control-regex": "error",
+    "no-debugger": "error",
+    "no-delete-var": "error",
+    "no-dupe-args": "error",
+    "no-dupe-class-members": "error",
+    "no-dupe-else-if": "error",
+    "no-dupe-keys": "error",
+    "no-duplicate-case": "error",
+    "no-empty": "error",
+    "no-empty-character-class": "error",
+    "no-empty-pattern": "error",
+    "no-empty-static-block": "error",
+    "no-eval": "warn",
+    "no-ex-assign": "error",
+    "no-extra-boolean-cast": "error",
+    "no-fallthrough": "warn",
+    "no-func-assign": "error",
+    "no-global-assign": "error",
+    "no-import-assign": "error",
+    "no-invalid-regexp": "error",
+    "no-irregular-whitespace": "error",
+    "no-loss-of-precision": "error",
+    "no-misleading-character-class": "error",
+    "no-new-native-nonconstructor": "error",
+    "no-nonoctal-decimal-escape": "error",
+    "no-obj-calls": "error",
+    "no-octal": "error",
+    "no-prototype-builtins": "error",
+    "no-redeclare": "error",
+    "no-regex-spaces": "error",
+    "no-self-assign": "error",
+    "no-setter-return": "error",
+    "no-shadow-restricted-names": "error",
+    "no-sparse-arrays": "error",
+    "no-this-before-super": "error",
+    "no-unassigned-vars": "warn",
+    "no-undef": "error",
+    "no-unexpected-multiline": "error",
+    "no-unreachable": "error",
+    "no-unsafe-finally": "error",
+    "no-unsafe-negation": "error",
+    "no-unsafe-optional-chaining": "error",
+    "no-unused-expressions": "off", // this rule disallow us to use expression to call function, like `condition && fn()`
+    "no-unused-labels": "error",
+    "no-unused-private-class-members": "error",
+    "no-unused-vars": ["error", { "caughtErrors": "none" }],
+    "no-useless-backreference": "error",
+    "no-useless-catch": "error",
+    "no-useless-escape": "error",
+    "no-useless-rename": "warn",
+    "no-with": "error",
+    "oxc/bad-array-method-on-arguments": "warn",
+    "oxc/bad-char-at-comparison": "warn",
+    "oxc/bad-comparison-sequence": "warn",
+    "oxc/bad-min-max-func": "warn",
+    "oxc/bad-object-literal-comparison": "warn",
+    "oxc/bad-replace-all-arg": "warn",
+    "oxc/const-comparisons": "warn",
+    "oxc/double-comparisons": "warn",
+    "oxc/erasing-op": "warn",
+    "oxc/missing-throw": "warn",
+    "oxc/number-arg-out-of-range": "warn",
+    "oxc/only-used-in-recursion": "off", // manually off bacause of existing warning. may turn it on in the future
+    "oxc/uninvoked-array-callback": "warn",
+    "require-yield": "error",
+    "typescript/await-thenable": "warn",
+    // "typescript/ban-ts-comment": "error",
+    "typescript/no-array-constructor": "error",
+    // "typescript/consistent-type-imports": "error",
+    "typescript/no-array-delete": "warn",
+    "typescript/no-base-to-string": "warn",
+    "typescript/no-duplicate-enum-values": "error",
+    "typescript/no-duplicate-type-constituents": "warn",
+    "typescript/no-empty-object-type": "off",
+    "typescript/no-explicit-any": "off", // not safe but too many errors
+    "typescript/no-extra-non-null-assertion": "error",
+    "typescript/no-floating-promises": "warn",
+    "typescript/no-for-in-array": "warn",
+    "typescript/no-implied-eval": "warn",
+    "typescript/no-meaningless-void-operator": "warn",
+    "typescript/no-misused-new": "error",
+    "typescript/no-misused-spread": "warn",
+    "typescript/no-namespace": "error",
+    "typescript/no-non-null-asserted-optional-chain": "off", // it's off now. but may turn it on.
+    "typescript/no-redundant-type-constituents": "warn",
+    "typescript/no-require-imports": "off",
+    "typescript/no-this-alias": "error",
+    "typescript/no-unnecessary-parameter-property-assignment": "warn",
+    "typescript/no-unnecessary-type-constraint": "error",
+    "typescript/no-unsafe-declaration-merging": "error",
+    "typescript/no-unsafe-function-type": "error",
+    "typescript/no-unsafe-unary-minus": "warn",
+    "typescript/no-useless-empty-export": "warn",
+    "typescript/no-wrapper-object-types": "error",
+    "typescript/prefer-as-const": "error",
+    "typescript/prefer-namespace-keyword": "error",
+    "typescript/require-array-sort-compare": "warn",
+    "typescript/restrict-template-expressions": "warn",
+    "typescript/triple-slash-reference": "error",
+    "typescript/unbound-method": "warn",
+    "unicorn/no-await-in-promise-methods": "warn",
+    "unicorn/no-empty-file": "off", // manually off bacause of existing warning. may turn it on in the future
+    "unicorn/no-invalid-fetch-options": "warn",
+    "unicorn/no-invalid-remove-event-listener": "warn",
+    "unicorn/no-new-array": "off", // manually off bacause of existing warning. may turn it on in the future
+    "unicorn/no-single-promise-in-promise-methods": "warn",
+    "unicorn/no-thenable": "off", // manually off bacause of existing warning. may turn it on in the future
+    "unicorn/no-unnecessary-await": "warn",
+    "unicorn/no-useless-fallback-in-spread": "warn",
+    "unicorn/no-useless-length-check": "warn",
+    "unicorn/no-useless-spread": "off", // manually off bacause of existing warning. may turn it on in the future
+    "unicorn/prefer-set-size": "warn",
+    "unicorn/prefer-string-starts-ends-with": "warn",
+    "use-isnan": "error",
+    "valid-typeof": "error"
+  },
+  "settings": {
+    "jsdoc": {
+      "augmentsExtendsReplacesDocs": false,
+      "exemptDestructuredRootsFromChecks": false,
+      "ignoreInternal": false,
+      "ignorePrivate": false,
+      "ignoreReplacesDocs": true,
+      "implementsReplacesDocs": false,
+      "overrideReplacesDocs": true,
+      "tagNamePreference": {}
+    },
+    "jsx-a11y": {
+      "attributes": {},
+      "components": {},
+      "polymorphicPropName": null
+    },
+    "next": {
+      "rootDir": []
+    },
+    "react": {
+      "formComponents": [],
+      "linkComponents": []
+    }
+  }
+}

.prettierignore

@@ -1,11 +0,0 @@
-out
-dist
-pnpm-lock.yaml
-LICENSE.md
-tsconfig.json
-tsconfig.*.json
-CHANGELOG*.md
-agents.json
-src/renderer/src/integration/nutstore/sso/lib
-AGENT.md
-src/main/integration/cherryin/index.js

.prettierrc

@@ -1,11 +0,0 @@
-{
-  "bracketSameLine": true,
-  "endOfLine": "lf",
-  "jsonRecursiveSort": true,
-  "jsonSortOrder": "{\"*\": \"lexical\"}",
-  "plugins": ["prettier-plugin-sort-json"],
-  "printWidth": 120,
-  "semi": false,
-  "singleQuote": true,
-  "trailingComma": "none"
-}

.vscode/extensions.json

@@ -1,8 +1,11 @@
 {
   "recommendations": [
     "dbaeumer.vscode-eslint",
-    "esbenp.prettier-vscode",
     "editorconfig.editorconfig",
-    "lokalise.i18n-ally"
+    "lokalise.i18n-ally",
+    "bradlc.vscode-tailwindcss",
+    "vitest.explorer",
+    "oxc.oxc-vscode",
+    "biomejs.biome"
   ]
 }

.vscode/settings.json

@@ -1,38 +1,43 @@
 {
   "[css]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "[javascript]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "[json]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "[jsonc]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "[markdown]": {
     "files.trimTrailingWhitespace": false
   },
   "[scss]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "[typescript]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "[typescriptreact]": {
-    "editor.defaultFormatter": "esbenp.prettier-vscode"
+    "editor.defaultFormatter": "biomejs.biome"
   },
   "editor.codeActionsOnSave": {
+    "source.fixAll.biome": "explicit",
     "source.fixAll.eslint": "explicit",
+    "source.fixAll.oxc": "explicit",
     "source.organizeImports": "never"
   },
   "editor.formatOnSave": true,
+  "files.associations": {
+    "*.css": "tailwindcss"
+  },
   "files.eol": "\n",
-  "i18n-ally.displayLanguage": "zh-cn",
+  // "i18n-ally.displayLanguage": "zh-cn", // 界面显示语言
   "i18n-ally.enabledFrameworks": ["react-i18next", "i18next"],
   "i18n-ally.enabledParsers": ["ts", "js", "json"], // 解析语言
-  "i18n-ally.fullReloadOnChanged": true, // 界面显示语言
+  "i18n-ally.fullReloadOnChanged": true,
   "i18n-ally.keystyle": "nested", // 翻译路径格式
   "i18n-ally.localesPaths": ["src/renderer/src/i18n/locales"],
   // "i18n-ally.namespace": true, // 开启命名空间

.yarn/patches/@anthropic-ai-claude-code-npm-1.0.118-bbf4e9e59f.patch

@@ -0,0 +1,18 @@
+diff --git a/sdk.mjs b/sdk.mjs
+index e2dbafb4e2faa1bf2b6b02f0009a2b9bbf57c757..3f07a1d5c2949a246fe5414e69ab45942fa605a2 100644
+--- a/sdk.mjs
++++ b/sdk.mjs
+@@ -6355,11 +6355,11 @@ class ProcessTransport {
+         prompt,
+         additionalDirectories = [],
+         cwd,
+-        executable = isRunningWithBun() ? "bun" : "node",
++        executable = process.execPath,
+         executableArgs = [],
+         extraArgs = {},
+         pathToClaudeCodeExecutable,
+-        env = { ...process.env },
++        env = { ...process.env, ELECTRON_RUN_AS_NODE: '1' },
+         stderr,
+         customSystemPrompt,
+         appendSystemPrompt,

.yarnrc.yml

@@ -5,3 +5,5 @@ httpTimeout: 300000
 nodeLinker: node-modules
 
 yarnPath: .yarn/releases/yarn-4.9.1.cjs
+npmRegistryServer: https://registry.npmjs.org
+npmPublishRegistry: https://registry.npmjs.org

AGENTS.md

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

CLAUDE.md

@@ -1,120 +1,52 @@
-# CLAUDE.md
+# AI Assistant Guide
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+This file provides guidance to AI coding assistants when working with code in this repository. Adherence to these guidelines is crucial for maintaining code quality and consistency.
+
+## Guiding Principles
+
+- **Clarity and Simplicity**: Write code that is easy to understand and maintain.
+- **Consistency**: Follow existing patterns and conventions in the codebase.
+- **Correctness**: Ensure code is correct, well-tested, and robust.
+- **Efficiency**: Write performant code and use resources judiciously.
+
+## MUST Follow Rules
+
+1.  **Code Search**: Use `ast-grep` for semantic code pattern searches when available. Fallback to `rg` (ripgrep) or `grep` for text-based searches.
+2.  **UI Framework**: Exclusively use **HeroUI** for all new UI components. The use of `antd` or `styled-components` is strictly **PROHIBITED**.
+3.  **Quality Assurance**: **Always** run `yarn build:check` before finalizing your work or making any commits. This ensures code quality (linting, testing, and type checking).
+4.  **Centralized Logging**: Use the `loggerService` exclusively for all application logging (info, warn, error levels) with proper context. Do not use `console.log`.
+5.  **External Research**: Leverage `subagent` for gathering external information, including latest documentation, API references, news, or web-based research. This keeps the main conversation focused on the task at hand.
+6.  **Code Reviews**: Always seek a code review from a human developer before merging significant changes. This ensures adherence to project standards and catches potential issues.
+7.  **Documentation**: Update or create documentation for any new features, modules, or significant changes to existing functionality.
 
 ## Development Commands
 
-### Environment Setup
+- **Install**: `yarn install`
+- **Development**: `yarn dev` - Runs Electron app in development mode
+- **Debug**: `yarn debug` - Starts with debugging enabled, use chrome://inspect
+- **Build Check**: `yarn build:check` - REQUIRED before commits (lint + test + typecheck)
+- **Test**: `yarn test` - Run all tests (Vitest)
+- **Single Test**: `yarn test:main` or `yarn test:renderer`
+- **Lint**: `yarn lint` - Fix linting issues and run typecheck
 
-- **Prerequisites**: Node.js v22.x.x or higher, Yarn 4.9.1
-- **Setup Yarn**: `corepack enable && corepack prepare yarn@4.9.1 --activate`
-- **Install Dependencies**: `yarn install`
+## Project Architecture
 
-### Development
+### Electron Structure
+- **Main Process** (`src/main/`): Node.js backend with services (MCP, Knowledge, Storage, etc.)
+- **Renderer Process** (`src/renderer/`): React UI with Redux state management
+- **Preload Scripts** (`src/preload/`): Secure IPC bridge
 
-- **Start Development**: `yarn dev` - Runs Electron app in development mode
-- **Debug Mode**: `yarn debug` - Starts with debugging enabled, use chrome://inspect
-
-### Testing & Quality
-
-- **Run Tests**: `yarn test` - Runs all tests (Vitest)
-- **Run E2E Tests**: `yarn test:e2e` - Playwright end-to-end tests
-- **Type Check**: `yarn typecheck` - Checks TypeScript for both node and web
-- **Lint**: `yarn lint` - ESLint with auto-fix
-- **Format**: `yarn format` - Prettier formatting
-
-### Build & Release
-
-- **Build**: `yarn build` - Builds for production (includes typecheck)
-- **Platform-specific builds**:
-  - Windows: `yarn build:win`
-  - macOS: `yarn build:mac`
-  - Linux: `yarn build:linux`
-
-## Architecture Overview
-
-### Electron Multi-Process Architecture
-
-- **Main Process** (`src/main/`): Node.js backend handling system integration, file operations, and services
-- **Renderer Process** (`src/renderer/`): React-based UI running in Chromium
-- **Preload Scripts** (`src/preload/`): Secure bridge between main and renderer processes
-
-### Key Architectural Components
-
-#### Main Process Services (`src/main/services/`)
-
-- **MCPService**: Model Context Protocol server management
-- **KnowledgeService**: Document processing and knowledge base management
-- **FileStorage/S3Storage/WebDav**: Multiple storage backends
-- **WindowService**: Multi-window management (main, mini, selection windows)
-- **ProxyManager**: Network proxy handling
-- **SearchService**: Full-text search capabilities
-
-#### AI Core (`src/renderer/src/aiCore/`)
-
-- **Middleware System**: Composable pipeline for AI request processing
-- **Client Factory**: Supports multiple AI providers (OpenAI, Anthropic, Gemini, etc.)
-- **Stream Processing**: Real-time response handling
-
-#### State Management (`src/renderer/src/store/`)
-
-- **Redux Toolkit**: Centralized state management
-- **Persistent Storage**: Redux-persist for data persistence
-- **Thunks**: Async actions for complex operations
-
-#### Knowledge Management
-
-- **Embeddings**: Vector search with multiple providers (OpenAI, Voyage, etc.)
-- **OCR**: Document text extraction (system OCR, Doc2x, Mineru)
-- **Preprocessing**: Document preparation pipeline
-- **Loaders**: Support for various file formats (PDF, DOCX, EPUB, etc.)
-
-### Build System
-
-- **Electron-Vite**: Development and build tooling (v4.0.0)
-- **Rolldown-Vite**: Using experimental rolldown-vite instead of standard vite
-- **Workspaces**: Monorepo structure with `packages/` directory
-- **Multiple Entry Points**: Main app, mini window, selection toolbar
-- **Styled Components**: CSS-in-JS styling with SWC optimization
-
-### Testing Strategy
-
-- **Vitest**: Unit and integration testing
-- **Playwright**: End-to-end testing
-- **Component Testing**: React Testing Library
-- **Coverage**: Available via `yarn test:coverage`
-
-### Key Patterns
-
-- **IPC Communication**: Secure main-renderer communication via preload scripts
-- **Service Layer**: Clear separation between UI and business logic
-- **Plugin Architecture**: Extensible via MCP servers and middleware
-- **Multi-language Support**: i18n with dynamic loading
-- **Theme System**: Light/dark themes with custom CSS variables
-
-## Logging Standards
-
-### Usage
+### Key Components
+- **AI Core** (`src/renderer/src/aiCore/`): Middleware pipeline for multiple AI providers.
+- **Services** (`src/main/services/`): MCPService, KnowledgeService, WindowService, etc.
+- **Build System**: Electron-Vite with experimental rolldown-vite, yarn workspaces.
+- **State Management**: Redux Toolkit (`src/renderer/src/store/`) for predictable state.
+- **UI Components**: HeroUI (`@heroui/*`) for all new UI elements.
 
+### Logging
 ```typescript
-// Main process
 import { loggerService } from '@logger'
 const logger = loggerService.withContext('moduleName')
-
-// Renderer process (set window source first)
-loggerService.initWindowSource('windowName')
-const logger = loggerService.withContext('moduleName')
-
-// Logging
+// Renderer: loggerService.initWindowSource('windowName') first
 logger.info('message', CONTEXT)
-logger.error('message', new Error('error'), CONTEXT)
 ```
-
-### Log Levels (highest to lowest)
-
-- `error` - Critical errors causing crash/unusable functionality
-- `warn` - Potential issues that don't affect core functionality
-- `info` - Application lifecycle and key user actions
-- `verbose` - Detailed flow information for feature tracing
-- `debug` - Development diagnostic info (not for production)
-- `silly` - Extreme debugging, low-level information

LICENSE

@@ -1,48 +1,3 @@
-**许可协议 (Licensing)**
-
-本项目采用**区分用户的双重许可 (User-Segmented Dual Licensing)** 模式。
-
-**核心原则：**
-
-* **个人用户 和 10人及以下企业/组织:** 默认适用 **GNU Affero 通用公共许可证 v3.0 (AGPLv3)**。  
-* **超过10人的企业/组织:** **必须** 获取 **商业许可证 (Commercial License)**。
-
-定义：“10人及以下”  
-指在您的组织（包括公司、非营利组织、政府机构、教育机构等任何实体）中，能够访问、使用或以任何方式直接或间接受益于本软件（Cherry Studio）功能的个人总数不超过10人。这包括但不限于开发者、测试人员、运营人员、最终用户、通过集成系统间接使用者等。
-
----
-
-**1. 开源许可证 (Open Source License): AGPLv3 - 适用于个人及10人及以下组织**
-
-* 如果您是个人用户，或者您的组织满足上述“10人及以下”的定义，您可以在 **AGPLv3** 的条款下自由使用、修改和分发 Cherry Studio。AGPLv3 的完整文本可以访问 [https://www.gnu.org/licenses/agpl-3.0.html](https://www.gnu.org/licenses/agpl-3.0.html) 获取。  
-* **核心义务：** AGPLv3 的一个关键要求是，如果您修改了 Cherry Studio 并通过网络提供服务，或者分发了修改后的版本，您必须以 AGPLv3 许可证向接收者提供相应的**完整源代码**。即使您符合“10人及以下”的标准，如果您希望避免此源代码公开义务，您也需要考虑获取商业许可证（见下文）。  
-* 使用前请务必仔细阅读并理解 AGPLv3 的所有条款。
-
-**2. 商业许可证 (Commercial License) - 适用于超过10人的组织，或希望规避 AGPLv3 义务的用户**
-
-* **强制要求：** 如果您的组织**不**满足上述“10人及以下”的定义（即有11人或更多人可以访问、使用或受益于本软件），您**必须**联系我们获取并签署一份商业许可证才能使用 Cherry Studio。  
-* **自愿选择：** 即使您的组织满足“10人及以下”的条件，但如果您的使用场景**无法满足 AGPLv3 的条款要求**（特别是关于**源代码公开**的义务），或者您需要 AGPLv3 **未提供**的特定商业条款（如保证、赔偿、无 Copyleft 限制等），您也**必须**联系我们获取并签署一份商业许可证。  
-* **需要商业许可证的常见情况包括（但不限于）：**  
-  * 您的组织规模超过10人。  
-  * （无论组织规模）您希望分发修改过的 Cherry Studio 版本，但**不希望**根据 AGPLv3 公开您修改部分的源代码。  
-  * （无论组织规模）您希望基于修改过的 Cherry Studio 提供网络服务（SaaS），但**不希望**根据 AGPLv3 向服务使用者提供修改后的源代码。  
-  * （无论组织规模）您的公司政策、客户合同或项目要求不允许使用 AGPLv3 许可的软件，或要求闭源分发及保密。  
-* 商业许可证将为您提供豁免 AGPLv3 义务（如源代码公开）的权利，并可能包含额外的商业保障条款。  
-* **获取商业许可：** 请通过邮箱 **bd@cherry-ai.com** 联系 Cherry Studio 开发团队洽谈商业授权事宜。
-
-**3. 贡献 (Contributions)**
-
-* 我们欢迎社区对 Cherry Studio 的贡献。所有向本项目提交的贡献都将被视为在 **AGPLv3** 许可证下提供。  
-* 通过向本项目提交贡献（例如通过 Pull Request），即表示您同意您的代码以 AGPLv3 许可证授权给本项目及所有后续使用者（无论这些使用者最终遵循 AGPLv3 还是商业许可）。  
-* 您也理解并同意，您的贡献可能会被包含在根据商业许可证分发的 Cherry Studio 版本中。
-
-**4. 其他条款 (Other Terms)**
-
-* 关于商业许可证的具体条款和条件，以双方签署的正式商业许可协议为准。  
-* 项目维护者保留根据需要更新本许可政策（包括用户规模定义和阈值）的权利。相关更新将通过项目官方渠道（如代码仓库、官方网站）进行通知。
-
----
-
 **Licensing**
 
 This project employs a **User-Segmented Dual Licensing** model.

README.md

@@ -82,7 +82,7 @@ Cherry Studio is a desktop client that supports multiple LLM providers, availabl
 1. **Diverse LLM Provider Support**:
 
 - ☁️ Major LLM Cloud Services: OpenAI, Gemini, Anthropic, and more
-- 🔗 AI Web Service Integration: Claude, Peplexity, Poe, and others
+- 🔗 AI Web Service Integration: Claude, Perplexity, Poe, and others
 - 💻 Local Model Support with Ollama, LM Studio
 
 2. **AI Assistants & Conversations**:

biome.jsonc

@@ -0,0 +1,97 @@
+{
+  "$schema": "https://biomejs.dev/schemas/2.2.4/schema.json",
+  "assist": {
+    // to sort json
+    "actions": {
+      "source": {
+        "organizeImports": "on",
+        "useSortedKeys": {
+          "level": "on",
+          "options": {
+            "sortOrder": "lexicographic"
+          }
+        }
+      }
+    },
+    "enabled": true,
+    "includes": ["**/*.json", "!*.json", "!**/package.json"]
+  },
+  "css": {
+    "formatter": {
+      "quoteStyle": "single"
+    }
+  },
+  "files": { "ignoreUnknown": false },
+  "formatter": {
+    "attributePosition": "auto",
+    "bracketSameLine": false,
+    "bracketSpacing": true,
+    "enabled": true,
+    "expand": "auto",
+    "formatWithErrors": true,
+    "includes": [
+      "**",
+      "!out/**",
+      "!**/dist/**",
+      "!build/**",
+      "!.yarn/**",
+      "!.github/**",
+      "!.husky/**",
+      "!.vscode/**",
+      "!*.yaml",
+      "!*.yml",
+      "!*.mjs",
+      "!*.cjs",
+      "!*.md",
+      "!*.json",
+      "!src/main/integration/**",
+      "!**/tailwind.css",
+      "!**/package.json"
+    ],
+    "indentStyle": "space",
+    "indentWidth": 2,
+    "lineEnding": "lf",
+    "lineWidth": 120,
+    "useEditorconfig": true
+  },
+  "html": { "formatter": { "selfCloseVoidElements": "always" } },
+  "javascript": {
+    "formatter": {
+      "arrowParentheses": "always",
+      "attributePosition": "auto",
+      // To minimize changes in this PR as much as possible, it's set to true. However, setting it to false would make it more convenient to add attributes at the end.
+      "bracketSameLine": true,
+      "bracketSpacing": true,
+      "jsxQuoteStyle": "double",
+      "quoteProperties": "asNeeded",
+      "quoteStyle": "single",
+      "semicolons": "asNeeded",
+      "trailingCommas": "none"
+    }
+  },
+  "json": {
+    "parser": {
+      "allowComments": true
+    }
+  },
+  "linter": {
+    "enabled": true,
+    "includes": ["!**/tailwind.css", "src/renderer/**/*.{tsx,ts}"],
+    // only enable sorted tailwind css rule. used as formatter instead of linter
+    "rules": {
+      "nursery": {
+        // to sort tailwind css classes
+        "useSortedClasses": {
+          "fix": "safe",
+          "level": "warn",
+          "options": {
+            "functions": ["cn"]
+          }
+        }
+      },
+      "recommended": false,
+      "suspicious": "off"
+    }
+  },
+  "vcs": { "clientKind": "git", "enabled": false, "useIgnoreFile": false }
+}

components.json

@@ -0,0 +1,21 @@
+{
+  "$schema": "https://ui.shadcn.com/schema.json",
+  "aliases": {
+    "components": "@renderer/ui/third-party",
+    "hooks": "@renderer/hooks",
+    "lib": "@renderer/lib",
+    "ui": "@renderer/ui",
+    "utils": "@renderer/utils"
+  },
+  "iconLibrary": "lucide",
+  "rsc": false,
+  "style": "new-york",
+  "tailwind": {
+    "baseColor": "zinc",
+    "config": "",
+    "css": "src/renderer/src/assets/styles/tailwind.css",
+    "cssVariables": true,
+    "prefix": ""
+  },
+  "tsx": true
+}

docs/README.zh.md

@@ -13,7 +13,7 @@
         <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=fr">Français</a></p>
         <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=de">Deutsch</a></p>
         <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=es">Español</a></p>
-        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=it">Itapano</a></p>
+        <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=it">Italiano</a></p>
         <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=ru">Русский</a></p>
         <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=pt">Português</a></p>
         <p><a href="https://openaitx.github.io/view.html?user=CherryHQ&project=cherry-studio&lang=nl">Nederlands</a></p>
@@ -89,7 +89,7 @@ https://docs.cherry-ai.com
 1. **多样化 LLM 服务支持**：
 
 - ☁️ 支持主流 LLM 云服务：OpenAI、Gemini、Anthropic、硅基流动等
-- 🔗 集成流行 AI Web 服务：Claude、Peplexity、Poe、腾讯元宝、知乎直答等
+- 🔗 集成流行 AI Web 服务：Claude、Perplexity、Poe、腾讯元宝、知乎直答等
 - 💻 支持 Ollama、LM Studio 本地模型部署
 
 2. **智能助手与对话**：

docs/dev.md

@@ -2,7 +2,9 @@
 
 ## IDE Setup
 
-[Cursor](https://www.cursor.com/) + [ESLint](https://marketplace.visualstudio.com/items?itemName=dbaeumer.vscode-eslint) + [Prettier](https://marketplace.visualstudio.com/items?itemName=esbenp.prettier-vscode)
+- Editor: [Cursor](https://www.cursor.com/), etc. Any VS Code compatible editor.
+- Linter: [ESLint](https://marketplace.visualstudio.com/items?itemName=dbaeumer.vscode-eslint)
+- Formatter: [Biome](https://marketplace.visualstudio.com/items?itemName=biomejs.biome)
 
 ## Project Setup
 

docs/technical/db.translate_languages.md

@@ -8,9 +8,9 @@
 
 | 字段名     | 类型   | 是否主键 | 索引 | 说明                                                                     |
 | ---------- | ------ | -------- | ---- | ------------------------------------------------------------------------ |
-| `id`       | string | ✅ 是     | ✅    | 唯一标识符，主键                                                         |
-| `langCode` | string | ❌ 否     | ✅    | 语言代码（如：`zh-cn`, `en-us`, `ja-jp` 等，均为小写），支持普通索引查询 |
-| `value`    | string | ❌ 否     | ❌    | 语言的名称，用户输入                                                     |
-| `emoji`    | string | ❌ 否     | ❌    | 语言的emoji，用户输入                                                    |
+| `id`       | string | ✅ 是    | ✅   | 唯一标识符，主键                                                         |
+| `langCode` | string | ❌ 否    | ✅   | 语言代码（如：`zh-cn`, `en-us`, `ja-jp` 等，均为小写），支持普通索引查询 |
+| `value`    | string | ❌ 否    | ❌   | 语言的名称，用户输入                                                     |
+| `emoji`    | string | ❌ 否    | ❌   | 语言的emoji，用户输入                                                    |
 
 > `langCode` 虽非主键，但在业务层应当避免重复插入相同语言代码。

electron-builder.yml

@@ -17,52 +17,52 @@ protocols:
     schemes:
       - cherrystudio
 files:
-  - '**/*'
-  - '!**/{.vscode,.yarn,.yarn-lock,.github,.cursorrules,.prettierrc}'
-  - '!electron.vite.config.{js,ts,mjs,cjs}}'
-  - '!**/{.eslintignore,.eslintrc.js,.eslintrc.json,.eslintcache,root.eslint.config.js,eslint.config.js,.eslintrc.cjs,.prettierignore,.prettierrc.yaml,eslint.config.mjs,dev-app-update.yml,CHANGELOG.md,README.md}'
-  - '!**/{.env,.env.*,.npmrc,pnpm-lock.yaml}'
-  - '!**/{tsconfig.json,tsconfig.tsbuildinfo,tsconfig.node.json,tsconfig.web.json}'
-  - '!**/{.editorconfig,.jekyll-metadata}'
-  - '!src'
-  - '!scripts'
-  - '!local'
-  - '!docs'
-  - '!packages'
-  - '!.swc'
-  - '!.bin'
-  - '!._*'
-  - '!*.log'
-  - '!stats.html'
-  - '!*.md'
-  - '!**/*.{iml,o,hprof,orig,pyc,pyo,rbc,swp,csproj,sln,xproj}'
-  - '!**/*.{map,ts,tsx,jsx,less,scss,sass,css.d.ts,d.cts,d.mts,md,markdown,yaml,yml}'
-  - '!**/{test,tests,__tests__,powered-test,coverage}/**'
-  - '!**/{example,examples}/**'
-  - '!**/*.{spec,test}.{js,jsx,ts,tsx}'
-  - '!**/*.min.*.map'
-  - '!**/*.d.ts'
-  - '!**/dist/es6/**'
-  - '!**/dist/demo/**'
-  - '!**/amd/**'
-  - '!**/{.DS_Store,Thumbs.db,thumbs.db,__pycache__}'
-  - '!**/{LICENSE,license,LICENSE.*,*.LICENSE.txt,NOTICE.txt,README.md,readme.md,CHANGELOG.md}'
-  - '!node_modules/rollup-plugin-visualizer'
-  - '!node_modules/js-tiktoken'
-  - '!node_modules/@tavily/core/node_modules/js-tiktoken'
-  - '!node_modules/pdf-parse/lib/pdf.js/{v1.9.426,v1.10.88,v2.0.550}'
-  - '!node_modules/mammoth/{mammoth.browser.js,mammoth.browser.min.js}'
-  - '!node_modules/selection-hook/prebuilds/**/*' # we rebuild .node, don't use prebuilds
-  - '!node_modules/selection-hook/node_modules' # we don't need what in the node_modules dir
-  - '!node_modules/selection-hook/src' # we don't need source files
-  - '!node_modules/tesseract.js-core/{tesseract-core.js,tesseract-core.wasm,tesseract-core.wasm.js}' # we don't need source files
-  - '!node_modules/tesseract.js-core/{tesseract-core-lstm.js,tesseract-core-lstm.wasm,tesseract-core-lstm.wasm.js}' # we don't need source files
-  - '!node_modules/tesseract.js-core/{tesseract-core-simd-lstm.js,tesseract-core-simd-lstm.wasm,tesseract-core-simd-lstm.wasm.js}' # we don't need source files
-  - '!**/*.{h,iobj,ipdb,tlog,recipe,vcxproj,vcxproj.filters,Makefile,*.Makefile}' # filter .node build files
+  - "**/*"
+  - "!**/{.vscode,.yarn,.yarn-lock,.github,.cursorrules,.prettierrc}"
+  - "!electron.vite.config.{js,ts,mjs,cjs}}"
+  - "!**/{.eslintignore,.eslintrc.js,.eslintrc.json,.eslintcache,root.eslint.config.js,eslint.config.js,.eslintrc.cjs,.prettierignore,.prettierrc.yaml,eslint.config.mjs,dev-app-update.yml,CHANGELOG.md,README.md,biome.jsonc}"
+  - "!**/{.env,.env.*,.npmrc,pnpm-lock.yaml}"
+  - "!**/{tsconfig.json,tsconfig.tsbuildinfo,tsconfig.node.json,tsconfig.web.json}"
+  - "!**/{.editorconfig,.jekyll-metadata}"
+  - "!src"
+  - "!scripts"
+  - "!local"
+  - "!docs"
+  - "!packages"
+  - "!.swc"
+  - "!.bin"
+  - "!._*"
+  - "!*.log"
+  - "!stats.html"
+  - "!*.md"
+  - "!**/*.{iml,o,hprof,orig,pyc,pyo,rbc,swp,csproj,sln,xproj}"
+  - "!**/*.{map,ts,tsx,jsx,less,scss,sass,css.d.ts,d.cts,d.mts,md,markdown,yaml,yml}"
+  - "!**/{test,tests,__tests__,powered-test,coverage}/**"
+  - "!**/{example,examples}/**"
+  - "!**/*.{spec,test}.{js,jsx,ts,tsx}"
+  - "!**/*.min.*.map"
+  - "!**/*.d.ts"
+  - "!**/dist/es6/**"
+  - "!**/dist/demo/**"
+  - "!**/amd/**"
+  - "!**/{.DS_Store,Thumbs.db,thumbs.db,__pycache__}"
+  - "!**/{LICENSE,license,LICENSE.*,*.LICENSE.txt,NOTICE.txt,README.md,readme.md,CHANGELOG.md}"
+  - "!node_modules/rollup-plugin-visualizer"
+  - "!node_modules/js-tiktoken"
+  - "!node_modules/@tavily/core/node_modules/js-tiktoken"
+  - "!node_modules/pdf-parse/lib/pdf.js/{v1.9.426,v1.10.88,v2.0.550}"
+  - "!node_modules/mammoth/{mammoth.browser.js,mammoth.browser.min.js}"
+  - "!node_modules/selection-hook/prebuilds/**/*" # we rebuild .node, don't use prebuilds
+  - "!node_modules/selection-hook/node_modules" # we don't need what in the node_modules dir
+  - "!node_modules/selection-hook/src" # we don't need source files
+  - "!node_modules/tesseract.js-core/{tesseract-core.js,tesseract-core.wasm,tesseract-core.wasm.js}" # we don't need source files
+  - "!node_modules/tesseract.js-core/{tesseract-core-lstm.js,tesseract-core-lstm.wasm,tesseract-core-lstm.wasm.js}" # we don't need source files
+  - "!node_modules/tesseract.js-core/{tesseract-core-simd-lstm.js,tesseract-core-simd-lstm.wasm,tesseract-core-simd-lstm.wasm.js}" # we don't need source files
+  - "!**/*.{h,iobj,ipdb,tlog,recipe,vcxproj,vcxproj.filters,Makefile,*.Makefile}" # filter .node build files
 asarUnpack:
   - resources/**
-  - '**/*.{metal,exp,lib}'
-  - 'node_modules/@img/sharp-libvips-*/**'
+  - "**/*.{metal,exp,lib}"
+  - "node_modules/@img/sharp-libvips-*/**"
 win:
   executableName: Cherry Studio
   artifactName: ${productName}-${version}-${arch}-setup.${ext}
@@ -88,7 +88,7 @@ mac:
   entitlementsInherit: build/entitlements.mac.plist
   notarize: false
   artifactName: ${productName}-${version}-${arch}.${ext}
-  minimumSystemVersion: '20.1.0' # 最低支持 macOS 11.0
+  minimumSystemVersion: "20.1.0" # 最低支持 macOS 11.0
   extendInfo:
     - NSCameraUsageDescription: Application requests access to the device's camera.
     - NSMicrophoneUsageDescription: Application requests access to the device's microphone.
@@ -110,6 +110,10 @@ linux:
       StartupWMClass: CherryStudio
   mimeTypes:
     - x-scheme-handler/cherrystudio
+rpm:
+  # Workaround for electron build issue on rpm package:
+  # https://github.com/electron/forge/issues/3594
+  fpm: ["--rpm-rpmbuild-define=_build_id_links none"]
 publish:
   provider: generic
   url: https://releases.cherry-ai.com
@@ -121,12 +125,16 @@ afterSign: scripts/notarize.js
 artifactBuildCompleted: scripts/artifact-build-completed.js
 releaseInfo:
   releaseNotes: |
-    🔧 性能优化：
-    - 优化AI服务连接方式，提升响应速度和稳定性
-    - 改进模型列表获取功能，减少不必要的网络请求
-    - 增强各AI服务商的兼容性和连接可靠性
-
     🐛 问题修复：
-    - 修复部分AI服务商连接失败的问题
-    - 修复模型配置加载时的潜在错误
-    - 提升应用整体稳定性和容错能力
+    - 修复 Anthropic API URL 处理，移除尾部斜杠并添加端点路径处理
+    - 修复 MessageEditor 缺少 QuickPanelProvider 包装的问题
+    - 修复 MiniWindow 高度问题
+
+    🚀 性能优化：
+    - 优化输入栏提及模型状态缓存，在渲染间保持状态
+    - 重构网络搜索参数支持模型内置搜索，新增 OpenAI Chat 和 OpenRouter 支持
+
+    🔧 重构改进：
+    - 更新 HeroUIProvider 导入路径，改善上下文管理
+    - 更新依赖项和 VSCode 开发环境配置
+    - 升级 @cherrystudio/ai-core 到 v1.0.0-alpha.17

electron.vite.config.ts

@@ -4,7 +4,9 @@ import { defineConfig, externalizeDepsPlugin } from 'electron-vite'
 import { resolve } from 'path'
 import { visualizer } from 'rollup-plugin-visualizer'
 
-import pkg from './package.json' assert { type: 'json' }
+// assert not supported by biome
+// import pkg from './package.json' assert { type: 'json' }
+import pkg from './package.json'
 
 const visualizerPlugin = (type: 'renderer' | 'main') => {
   return process.env[`VISUALIZER_${type.toUpperCase()}`] ? [visualizer({ open: true })] : []
@@ -23,10 +25,7 @@ export default defineConfig({
         '@shared': resolve('packages/shared'),
         '@logger': resolve('src/main/services/LoggerService'),
         '@mcp-trace/trace-core': resolve('packages/mcp-trace/trace-core'),
-        '@mcp-trace/trace-node': resolve('packages/mcp-trace/trace-node'),
-        '@cherrystudio/ai-core/provider': resolve('packages/aiCore/src/core/providers'),
-        '@cherrystudio/ai-core/built-in/plugins': resolve('packages/aiCore/src/core/plugins/built-in'),
-        '@cherrystudio/ai-core': resolve('packages/aiCore/src')
+        '@mcp-trace/trace-node': resolve('packages/mcp-trace/trace-node')
       }
     },
     build: {
@@ -63,6 +62,7 @@ export default defineConfig({
   },
   renderer: {
     plugins: [
+      (async () => (await import('@tailwindcss/vite')).default())(),
       react({
         tsDecorators: true,
         plugins: [
@@ -84,6 +84,7 @@ export default defineConfig({
       alias: {
         '@renderer': resolve('src/renderer/src'),
         '@shared': resolve('packages/shared'),
+        '@types': resolve('src/renderer/src/types'),
         '@logger': resolve('src/renderer/src/services/LoggerService'),
         '@mcp-trace/trace-core': resolve('packages/mcp-trace/trace-core'),
         '@mcp-trace/trace-web': resolve('packages/mcp-trace/trace-web'),

eslint.config.mjs

@@ -1,8 +1,8 @@
-import electronConfigPrettier from '@electron-toolkit/eslint-config-prettier'
 import tseslint from '@electron-toolkit/eslint-config-ts'
 import eslint from '@eslint/js'
 import eslintReact from '@eslint-react/eslint-plugin'
 import { defineConfig } from 'eslint/config'
+import oxlint from 'eslint-plugin-oxlint'
 import reactHooks from 'eslint-plugin-react-hooks'
 import simpleImportSort from 'eslint-plugin-simple-import-sort'
 import unusedImports from 'eslint-plugin-unused-imports'
@@ -10,7 +10,6 @@ import unusedImports from 'eslint-plugin-unused-imports'
 export default defineConfig([
   eslint.configs.recommended,
   tseslint.configs.recommended,
-  electronConfigPrettier,
   eslintReact.configs['recommended-typescript'],
   reactHooks.configs['recommended-latest'],
   {
@@ -26,7 +25,6 @@ export default defineConfig([
       'simple-import-sort/exports': 'error',
       'unused-imports/no-unused-imports': 'error',
       '@eslint-react/no-prop-types': 'error',
-      'prettier/prettier': ['error']
     }
   },
   // Configuration for ensuring compatibility with the original ESLint(8.x) rules
@@ -53,7 +51,7 @@ export default defineConfig([
   {
     // LoggerService Custom Rules - only apply to src directory
     files: ['src/**/*.{ts,tsx,js,jsx}'],
-    ignores: ['src/**/__tests__/**', 'src/**/__mocks__/**', 'src/**/*.test.*'],
+    ignores: ['src/**/__tests__/**', 'src/**/__mocks__/**', 'src/**/*.test.*', 'src/preload/**'],
     rules: {
       'no-restricted-syntax': [
         process.env.PRCI ? 'error' : 'warn',
@@ -123,7 +121,14 @@ export default defineConfig([
       '.gitignore',
       'scripts/cloudflare-worker.js',
       'src/main/integration/nutstore/sso/lib/**',
-      'src/main/integration/cherryin/index.js'
+      'src/main/integration/cherryin/index.js',
+      'src/main/integration/nutstore/sso/lib/**',
+      'src/renderer/src/ui/**',
+      'packages/**/dist'
     ]
-  }
+  },
+  // turn off oxlint supported rules.
+  ...oxlint.configs['flat/eslint'],
+  ...oxlint.configs['flat/typescript'],
+  ...oxlint.configs['flat/unicorn']
 ])

package.json

@@ -1,6 +1,6 @@
 {
   "name": "CherryStudio",
-  "version": "1.6.0-beta.6",
+  "version": "1.6.0-rc.2",
   "private": true,
   "description": "A powerful AI assistant for producer.",
   "main": "./out/main/index.js",
@@ -27,6 +27,7 @@
   "scripts": {
     "start": "electron-vite preview",
     "dev": "dotenv electron-vite dev",
+    "dev:main": "dotenv electron-vite dev --watch",
     "debug": "electron-vite -- --inspect --sourcemap --remote-debugging-port=9222",
     "build": "npm run typecheck && electron-vite build",
     "build:check": "yarn lint && yarn test",
@@ -43,15 +44,18 @@
     "release": "node scripts/version.js",
     "publish": "yarn build:check && yarn release patch push",
     "pulish:artifacts": "cd packages/artifacts && npm publish && cd -",
-    "generate:agents": "yarn workspace @cherry-studio/database agents",
+    "agents:generate": "NODE_ENV='development' drizzle-kit generate --config src/main/services/agents/drizzle.config.ts",
+    "agents:push": "NODE_ENV='development' drizzle-kit push --config src/main/services/agents/drizzle.config.ts",
+    "agents:studio": "NODE_ENV='development' drizzle-kit studio --config src/main/services/agents/drizzle.config.ts",
+    "agents:drop": "NODE_ENV='development' drizzle-kit drop --config src/main/services/agents/drizzle.config.ts",
     "generate:icons": "electron-icon-builder --input=./build/logo.png --output=build",
     "analyze:renderer": "VISUALIZER_RENDERER=true yarn build",
     "analyze:main": "VISUALIZER_MAIN=true yarn build",
     "typecheck": "concurrently -n \"node,web\" -c \"cyan,magenta\" \"npm run typecheck:node\" \"npm run typecheck:web\"",
-    "typecheck:node": "tsc --noEmit -p tsconfig.node.json --composite false",
-    "typecheck:web": "tsc --noEmit -p tsconfig.web.json --composite false",
-    "check:i18n": "tsx scripts/check-i18n.ts",
-    "sync:i18n": "tsx scripts/sync-i18n.ts",
+    "typecheck:node": "tsgo --noEmit -p tsconfig.node.json --composite false",
+    "typecheck:web": "tsgo --noEmit -p tsconfig.web.json --composite false",
+    "check:i18n": "dotenv -e .env -- tsx scripts/check-i18n.ts",
+    "sync:i18n": "dotenv -e .env -- tsx scripts/sync-i18n.ts",
     "update:i18n": "dotenv -e .env -- tsx scripts/update-i18n.ts",
     "auto:i18n": "dotenv -e .env -- tsx scripts/auto-translate-i18n.ts",
     "update:languages": "tsx scripts/update-languages.ts",
@@ -63,26 +67,37 @@
     "test:ui": "vitest --ui",
     "test:watch": "vitest",
     "test:e2e": "yarn playwright test",
-    "test:lint": "eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts",
+    "test:lint": "oxlint --deny-warnings && eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts --cache",
     "test:scripts": "vitest scripts",
-    "format": "prettier --write .",
-    "lint": "eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts --fix && yarn typecheck && yarn check:i18n",
-    "prepare": "git config blame.ignoreRevsFile .git-blame-ignore-revs && husky"
+    "lint": "oxlint --fix && eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts --fix --cache && yarn typecheck && yarn check:i18n",
+    "format": "biome format --write && biome lint --write",
+    "format:check": "biome format && biome lint",
+    "prepare": "git config blame.ignoreRevsFile .git-blame-ignore-revs && husky",
+    "claude": "dotenv -e .env -- claude",
+    "release:aicore:alpha": "yarn workspace @cherrystudio/ai-core version prerelease --immediate && yarn workspace @cherrystudio/ai-core npm publish --tag alpha --access public",
+    "release:aicore:beta": "yarn workspace @cherrystudio/ai-core version prerelease --immediate && yarn workspace @cherrystudio/ai-core npm publish --tag beta --access public",
+    "release:aicore": "yarn workspace @cherrystudio/ai-core version patch --immediate && yarn workspace @cherrystudio/ai-core npm publish --access public"
   },
   "dependencies": {
+    "@anthropic-ai/claude-code": "patch:@anthropic-ai/claude-code@npm%3A1.0.118#~/.yarn/patches/@anthropic-ai-claude-code-npm-1.0.118-bbf4e9e59f.patch",
     "@libsql/client": "0.14.0",
     "@libsql/win32-x64-msvc": "^0.4.7",
     "@napi-rs/system-ocr": "patch:@napi-rs/system-ocr@npm%3A1.0.2#~/.yarn/patches/@napi-rs-system-ocr-npm-1.0.2-59e7a78e8b.patch",
     "@strongtz/win32-arm64-msvc": "^0.4.7",
-    "ai-sdk-provider-claude-code": "^1.1.3",
+    "@types/uuid": "^10.0.0",
+    "drizzle-orm": "^0.44.5",
     "express": "^5.1.0",
+    "express-validator": "^7.2.1",
+    "font-list": "^2.0.0",
     "graceful-fs": "^4.2.11",
     "jsdom": "26.1.0",
     "node-stream-zip": "^1.15.0",
     "officeparser": "^4.2.0",
     "os-proxy-config": "^1.1.2",
-    "selection-hook": "^1.0.11",
+    "selection-hook": "^1.0.12",
     "sharp": "^0.34.3",
+    "swagger-jsdoc": "^6.2.8",
+    "swagger-ui-express": "^5.0.1",
     "tesseract.js": "patch:tesseract.js@npm%3A6.0.1#~/.yarn/patches/tesseract.js-npm-6.0.1-2562a7e46d.patch",
     "turndown": "7.2.0"
   },
@@ -90,16 +105,18 @@
     "@agentic/exa": "^7.3.3",
     "@agentic/searxng": "^7.3.3",
     "@agentic/tavily": "^7.3.3",
-    "@ai-sdk/amazon-bedrock": "^3.0.0",
-    "@ai-sdk/google-vertex": "^3.0.0",
-    "@ai-sdk/mistral": "^2.0.0",
+    "@ai-sdk/amazon-bedrock": "^3.0.21",
+    "@ai-sdk/google-vertex": "^3.0.27",
+    "@ai-sdk/mistral": "^2.0.14",
+    "@ai-sdk/perplexity": "^2.0.9",
     "@ant-design/v5-patch-for-react-19": "^1.0.3",
     "@anthropic-ai/sdk": "^0.41.0",
     "@anthropic-ai/vertex-sdk": "patch:@anthropic-ai/vertex-sdk@npm%3A0.11.4#~/.yarn/patches/@anthropic-ai-vertex-sdk-npm-0.11.4-c19cb41edb.patch",
     "@aws-sdk/client-bedrock": "^3.840.0",
     "@aws-sdk/client-bedrock-runtime": "^3.840.0",
     "@aws-sdk/client-s3": "^3.840.0",
-    "@cherrystudio/ai-core": "workspace:*",
+    "@biomejs/biome": "2.2.4",
+    "@cherrystudio/ai-core": "workspace:^1.0.0-alpha.18",
     "@cherrystudio/embedjs": "^0.1.31",
     "@cherrystudio/embedjs-libsql": "^0.1.31",
     "@cherrystudio/embedjs-loader-csv": "^0.1.31",
@@ -117,7 +134,6 @@
     "@dnd-kit/modifiers": "^9.0.0",
     "@dnd-kit/sortable": "^10.0.0",
     "@dnd-kit/utilities": "^3.2.2",
-    "@electron-toolkit/eslint-config-prettier": "^3.0.0",
     "@electron-toolkit/eslint-config-ts": "^3.0.0",
     "@electron-toolkit/preload": "^3.0.0",
     "@electron-toolkit/tsconfig": "^1.0.1",
@@ -128,11 +144,11 @@
     "@eslint/js": "^9.22.0",
     "@google/genai": "patch:@google/genai@npm%3A1.0.1#~/.yarn/patches/@google-genai-npm-1.0.1-e26f0f9af7.patch",
     "@hello-pangea/dnd": "^18.0.1",
+    "@heroui/react": "^2.8.3",
     "@kangfenmao/keyv-storage": "^0.1.0",
-    "@langchain/community": "^0.3.36",
-    "@langchain/ollama": "^0.2.1",
+    "@langchain/community": "^0.3.50",
     "@mistralai/mistralai": "^1.7.5",
-    "@modelcontextprotocol/sdk": "^1.17.0",
+    "@modelcontextprotocol/sdk": "^1.17.5",
     "@mozilla/readability": "^0.6.0",
     "@notionhq/client": "^2.2.15",
     "@openrouter/ai-sdk-provider": "^1.1.2",
@@ -143,9 +159,11 @@
     "@opentelemetry/sdk-trace-node": "^2.0.0",
     "@opentelemetry/sdk-trace-web": "^2.0.0",
     "@playwright/test": "^1.52.0",
+    "@radix-ui/react-context-menu": "^2.2.16",
     "@reduxjs/toolkit": "^2.2.5",
     "@shikijs/markdown-it": "^3.12.0",
     "@swc/plugin-styled-components": "^8.0.4",
+    "@tailwindcss/vite": "^4.1.13",
     "@tanstack/react-query": "^5.85.5",
     "@tanstack/react-virtual": "^3.13.12",
     "@testing-library/dom": "^10.4.0",
@@ -171,21 +189,30 @@
     "@truto/turndown-plugin-gfm": "^1.0.2",
     "@tryfabric/martian": "^1.2.4",
     "@types/cli-progress": "^3",
-    "@types/express": "^5.0.3",
+    "@types/content-type": "^1.1.9",
+    "@types/cors": "^2.8.19",
+    "@types/diff": "^7",
+    "@types/express": "^5",
     "@types/fs-extra": "^11",
     "@types/he": "^1",
+    "@types/html-to-text": "^9",
     "@types/lodash": "^4.17.5",
     "@types/markdown-it": "^14",
     "@types/md5": "^2.3.5",
+    "@types/mime-types": "^3",
     "@types/node": "^22.17.1",
     "@types/pako": "^1.0.2",
     "@types/react": "^19.0.12",
     "@types/react-dom": "^19.0.4",
     "@types/react-infinite-scroll-component": "^5.0.0",
     "@types/react-transition-group": "^4.4.12",
+    "@types/react-window": "^1",
+    "@types/swagger-jsdoc": "^6",
+    "@types/swagger-ui-express": "^4.1.8",
     "@types/tinycolor2": "^1",
     "@types/turndown": "^5.0.5",
     "@types/word-extractor": "^1",
+    "@typescript/native-preview": "latest",
     "@uiw/codemirror-extensions-langs": "^4.25.1",
     "@uiw/codemirror-themes-all": "^4.25.1",
     "@uiw/react-codemirror": "^4.25.1",
@@ -197,15 +224,18 @@
     "@viz-js/lang-dot": "^1.0.5",
     "@viz-js/viz": "^3.14.0",
     "@xyflow/react": "^12.4.4",
-    "ai": "^5.0.29",
+    "ai": "^5.0.44",
     "antd": "patch:antd@npm%3A5.27.0#~/.yarn/patches/antd-npm-5.27.0-aa91c36546.patch",
     "archiver": "^7.0.1",
     "async-mutex": "^0.5.0",
     "axios": "^1.7.3",
     "browser-image-compression": "^2.0.2",
     "chardet": "^2.1.0",
+    "check-disk-space": "3.4.0",
+    "cheerio": "^1.1.2",
     "chokidar": "^4.0.3",
     "cli-progress": "^3.12.0",
+    "clsx": "^2.1.1",
     "code-inspector-plugin": "^0.20.14",
     "color": "^5.0.0",
     "concurrently": "^9.2.1",
@@ -217,9 +247,11 @@
     "docx": "^9.0.2",
     "dompurify": "^3.2.6",
     "dotenv-cli": "^7.4.2",
+    "drizzle-kit": "^0.31.4",
     "electron": "37.4.0",
     "electron-builder": "26.0.15",
     "electron-devtools-installer": "^3.2.0",
+    "electron-reload": "^2.0.0-alpha.1",
     "electron-store": "^8.2.0",
     "electron-updater": "6.6.4",
     "electron-vite": "4.0.0",
@@ -228,18 +260,21 @@
     "emoji-picker-element": "^1.22.1",
     "epub": "patch:epub@npm%3A1.3.0#~/.yarn/patches/epub-npm-1.3.0-8325494ffe.patch",
     "eslint": "^9.22.0",
+    "eslint-plugin-oxlint": "^1.15.0",
     "eslint-plugin-react-hooks": "^5.2.0",
     "eslint-plugin-simple-import-sort": "^12.1.1",
     "eslint-plugin-unused-imports": "^4.1.4",
     "fast-diff": "^1.3.0",
     "fast-xml-parser": "^5.2.0",
     "fetch-socks": "1.3.2",
+    "framer-motion": "^12.23.12",
     "franc-min": "^6.2.0",
     "fs-extra": "^11.2.0",
     "google-auth-library": "^9.15.1",
     "he": "^1.2.0",
     "html-tags": "^5.1.0",
     "html-to-image": "^1.11.13",
+    "html-to-text": "^9.0.5",
     "htmlparser2": "^10.0.0",
     "husky": "^9.1.7",
     "i18next": "^23.11.5",
@@ -256,15 +291,17 @@
     "markdown-it": "^14.1.0",
     "mermaid": "^11.10.1",
     "mime": "^4.0.4",
+    "mime-types": "^3.0.1",
     "motion": "^12.10.5",
     "notion-helper": "^1.3.22",
     "npx-scope-finder": "^1.2.0",
     "openai": "patch:openai@npm%3A5.12.2#~/.yarn/patches/openai-npm-5.12.2-30b075401c.patch",
+    "oxlint": "^1.15.0",
+    "oxlint-tsgolint": "^0.2.0",
     "p-queue": "^8.1.0",
     "pdf-lib": "^1.17.1",
+    "pdf-parse": "^1.1.1",
     "playwright": "^1.52.0",
-    "prettier": "^3.5.3",
-    "prettier-plugin-sort-json": "^4.1.1",
     "proxy-agent": "^6.5.0",
     "react": "^19.0.0",
     "react-dom": "^19.0.0",
@@ -274,6 +311,7 @@
     "react-infinite-scroll-component": "^6.1.0",
     "react-json-view": "^1.21.3",
     "react-markdown": "^10.1.0",
+    "react-player": "^3.3.1",
     "react-redux": "^9.1.2",
     "react-router": "6",
     "react-router-dom": "6",
@@ -293,21 +331,23 @@
     "remark-math": "^6.0.0",
     "remove-markdown": "^0.6.2",
     "rollup-plugin-visualizer": "^5.12.0",
-    "sass": "^1.88.0",
     "shiki": "^3.12.0",
     "strict-url-sanitise": "^0.0.1",
     "string-width": "^7.2.0",
     "striptags": "^3.2.0",
     "styled-components": "^6.1.11",
+    "swr": "^2.3.6",
+    "tailwindcss": "^4.1.13",
     "tar": "^7.4.3",
     "tiny-pinyin": "^1.3.2",
     "tokenx": "^1.1.0",
     "tsx": "^4.20.3",
     "turndown-plugin-gfm": "^1.0.2",
-    "typescript": "^5.6.2",
+    "tw-animate-css": "^1.3.8",
+    "typescript": "~5.8.2",
     "undici": "6.21.2",
     "unified": "^11.0.5",
-    "uuid": "^10.0.0",
+    "uuid": "^13.0.0",
     "vite": "npm:rolldown-vite@latest",
     "vitest": "^3.2.4",
     "webdav": "^5.8.0",
@@ -315,9 +355,11 @@
     "winston-daily-rotate-file": "^5.0.0",
     "word-extractor": "^1.0.4",
     "y-protocols": "^1.0.6",
+    "yaml": "^2.8.1",
     "yjs": "^13.6.27",
+    "youtubei.js": "^15.0.1",
     "zipread": "^1.3.3",
-    "zod": "^3.25.74"
+    "zod": "^4.1.5"
   },
   "resolutions": {
     "@codemirror/language": "6.11.3",
@@ -338,22 +380,16 @@
     "pkce-challenge@npm:^4.1.0": "patch:pkce-challenge@npm%3A4.1.0#~/.yarn/patches/pkce-challenge-npm-4.1.0-fbc51695a3.patch",
     "undici": "6.21.2",
     "vite": "npm:rolldown-vite@latest",
-    "tesseract.js@npm:*": "patch:tesseract.js@npm%3A6.0.1#~/.yarn/patches/tesseract.js-npm-6.0.1-2562a7e46d.patch",
-    "@img/sharp-darwin-arm64": "0.34.3",
-    "@img/sharp-darwin-x64": "0.34.3",
-    "@img/sharp-linux-arm": "0.34.3",
-    "@img/sharp-linux-arm64": "0.34.3",
-    "@img/sharp-linux-x64": "0.34.3",
-    "@img/sharp-win32-x64": "0.34.3"
+    "tesseract.js@npm:*": "patch:tesseract.js@npm%3A6.0.1#~/.yarn/patches/tesseract.js-npm-6.0.1-2562a7e46d.patch"
   },
   "packageManager": "yarn@4.9.1",
   "lint-staged": {
     "*.{js,jsx,ts,tsx,cjs,mjs,cts,mts}": [
-      "prettier --write",
+      "biome format --write --no-errors-on-unmatched",
       "eslint --fix"
     ],
-    "*.{json,yml,yaml,css,scss,html}": [
-      "prettier --write"
+    "*.{json,yml,yaml,css,html}": [
+      "biome format --write --no-errors-on-unmatched"
     ]
   }
 }

packages/aiCore/examples/hub-provider-usage.ts

@@ -1,103 +0,0 @@
-/**
- * Hub Provider 使用示例
- *
- * 演示如何使用简化后的Hub Provider功能来路由到多个底层provider
- */
-
-import { createHubProvider, initializeProvider, providerRegistry } from '../src/index'
-
-async function demonstrateHubProvider() {
-  try {
-    // 1. 初始化底层providers
-    console.log('📦 初始化底层providers...')
-
-    initializeProvider('openai', {
-      apiKey: process.env.OPENAI_API_KEY || 'sk-test-key'
-    })
-
-    initializeProvider('anthropic', {
-      apiKey: process.env.ANTHROPIC_API_KEY || 'sk-ant-test-key'
-    })
-
-    // 2. 创建Hub Provider（自动包含所有已初始化的providers）
-    console.log('🌐 创建Hub Provider...')
-
-    const aihubmixProvider = createHubProvider({
-      hubId: 'aihubmix',
-      debug: true
-    })
-
-    // 3. 注册Hub Provider
-    providerRegistry.registerProvider('aihubmix', aihubmixProvider)
-
-    console.log('✅ Hub Provider "aihubmix" 注册成功')
-
-    // 4. 使用Hub Provider访问不同的模型
-    console.log('\n🚀 使用Hub模型...')
-
-    // 通过Hub路由到OpenAI
-    const openaiModel = providerRegistry.languageModel('aihubmix:openai:gpt-4')
-    console.log('✓ OpenAI模型已获取:', openaiModel.modelId)
-
-    // 通过Hub路由到Anthropic
-    const anthropicModel = providerRegistry.languageModel('aihubmix:anthropic:claude-3.5-sonnet')
-    console.log('✓ Anthropic模型已获取:', anthropicModel.modelId)
-
-    // 5. 演示错误处理
-    console.log('\n❌ 演示错误处理...')
-
-    try {
-      // 尝试访问未初始化的provider
-      providerRegistry.languageModel('aihubmix:google:gemini-pro')
-    } catch (error) {
-      console.log('预期错误:', error.message)
-    }
-
-    try {
-      // 尝试使用错误的模型ID格式
-      providerRegistry.languageModel('aihubmix:invalid-format')
-    } catch (error) {
-      console.log('预期错误:', error.message)
-    }
-
-    // 6. 多个Hub Provider示例
-    console.log('\n🔄 创建多个Hub Provider...')
-
-    const localHubProvider = createHubProvider({
-      hubId: 'local-ai'
-    })
-
-    providerRegistry.registerProvider('local-ai', localHubProvider)
-    console.log('✅ Hub Provider "local-ai" 注册成功')
-
-    console.log('\n🎉 Hub Provider演示完成！')
-  } catch (error) {
-    console.error('💥 演示过程中发生错误:', error)
-  }
-}
-
-// 演示简化的使用方式
-function simplifiedUsageExample() {
-  console.log('\n📝 简化使用示例:')
-  console.log(`
-// 1. 初始化providers
-initializeProvider('openai', { apiKey: 'sk-xxx' })
-initializeProvider('anthropic', { apiKey: 'sk-ant-xxx' })
-
-// 2. 创建并注册Hub Provider
-const hubProvider = createHubProvider({ hubId: 'aihubmix' })
-providerRegistry.registerProvider('aihubmix', hubProvider)
-
-// 3. 直接使用
-const model1 = providerRegistry.languageModel('aihubmix:openai:gpt-4')
-const model2 = providerRegistry.languageModel('aihubmix:anthropic:claude-3.5-sonnet')
-`)
-}
-
-// 运行演示
-if (require.main === module) {
-  demonstrateHubProvider()
-  simplifiedUsageExample()
-}
-
-export { demonstrateHubProvider, simplifiedUsageExample }

packages/aiCore/examples/image-generation.ts

@@ -1,167 +0,0 @@
-/**
- * Image Generation Example
- * 演示如何使用 aiCore 的文生图功能
- */
-
-import { createExecutor, generateImage } from '../src/index'
-
-async function main() {
-  // 方式1: 使用执行器实例
-  console.log('📸 创建 OpenAI 图像生成执行器...')
-  const executor = createExecutor('openai', {
-    apiKey: process.env.OPENAI_API_KEY!
-  })
-
-  try {
-    console.log('🎨 使用执行器生成图像...')
-    const result1 = await executor.generateImage('dall-e-3', {
-      prompt: 'A futuristic cityscape at sunset with flying cars',
-      size: '1024x1024',
-      n: 1
-    })
-
-    console.log('✅ 图像生成成功!')
-    console.log('📊 结果:', {
-      imagesCount: result1.images.length,
-      mediaType: result1.image.mediaType,
-      hasBase64: !!result1.image.base64,
-      providerMetadata: result1.providerMetadata
-    })
-  } catch (error) {
-    console.error('❌ 执行器生成失败:', error)
-  }
-
-  // 方式2: 使用直接调用 API
-  try {
-    console.log('🎨 使用直接 API 生成图像...')
-    const result2 = await generateImage('openai', { apiKey: process.env.OPENAI_API_KEY! }, 'dall-e-3', {
-      prompt: 'A magical forest with glowing mushrooms and fairy lights',
-      aspectRatio: '16:9',
-      providerOptions: {
-        openai: {
-          quality: 'hd',
-          style: 'vivid'
-        }
-      }
-    })
-
-    console.log('✅ 直接 API 生成成功!')
-    console.log('📊 结果:', {
-      imagesCount: result2.images.length,
-      mediaType: result2.image.mediaType,
-      hasBase64: !!result2.image.base64
-    })
-  } catch (error) {
-    console.error('❌ 直接 API 生成失败:', error)
-  }
-
-  // 方式3: 支持其他提供商 (Google Imagen)
-  if (process.env.GOOGLE_API_KEY) {
-    try {
-      console.log('🎨 使用 Google Imagen 生成图像...')
-      const googleExecutor = createExecutor('google', {
-        apiKey: process.env.GOOGLE_API_KEY!
-      })
-
-      const result3 = await googleExecutor.generateImage('imagen-3.0-generate-002', {
-        prompt: 'A serene mountain lake at dawn with mist rising from the water',
-        aspectRatio: '1:1'
-      })
-
-      console.log('✅ Google Imagen 生成成功!')
-      console.log('📊 结果:', {
-        imagesCount: result3.images.length,
-        mediaType: result3.image.mediaType,
-        hasBase64: !!result3.image.base64
-      })
-    } catch (error) {
-      console.error('❌ Google Imagen 生成失败:', error)
-    }
-  }
-
-  // 方式4: 支持插件系统
-  const pluginExample = async () => {
-    console.log('🔌 演示插件系统...')
-
-    // 创建一个示例插件，用于修改提示词
-    const promptEnhancerPlugin = {
-      name: 'prompt-enhancer',
-      transformParams: async (params: any) => {
-        console.log('🔧 插件: 增强提示词...')
-        return {
-          ...params,
-          prompt: `${params.prompt}, highly detailed, cinematic lighting, 4K resolution`
-        }
-      },
-      transformResult: async (result: any) => {
-        console.log('🔧 插件: 处理结果...')
-        return {
-          ...result,
-          enhanced: true
-        }
-      }
-    }
-
-    const executorWithPlugin = createExecutor(
-      'openai',
-      {
-        apiKey: process.env.OPENAI_API_KEY!
-      },
-      [promptEnhancerPlugin]
-    )
-
-    try {
-      const result4 = await executorWithPlugin.generateImage('dall-e-3', {
-        prompt: 'A cute robot playing in a garden'
-      })
-
-      console.log('✅ 插件系统生成成功!')
-      console.log('📊 结果:', {
-        imagesCount: result4.images.length,
-        enhanced: (result4 as any).enhanced,
-        mediaType: result4.image.mediaType
-      })
-    } catch (error) {
-      console.error('❌ 插件系统生成失败:', error)
-    }
-  }
-
-  await pluginExample()
-}
-
-// 错误处理演示
-async function errorHandlingExample() {
-  console.log('⚠️  演示错误处理...')
-
-  try {
-    const executor = createExecutor('openai', {
-      apiKey: 'invalid-key'
-    })
-
-    await executor.generateImage('dall-e-3', {
-      prompt: 'Test image'
-    })
-  } catch (error: any) {
-    console.log('✅ 成功捕获错误:', error.constructor.name)
-    console.log('📋 错误信息:', error.message)
-    console.log('🏷️  提供商ID:', error.providerId)
-    console.log('🏷️  模型ID:', error.modelId)
-  }
-}
-
-// 运行示例
-if (require.main === module) {
-  main()
-    .then(() => {
-      console.log('🎉 所有示例完成!')
-      return errorHandlingExample()
-    })
-    .then(() => {
-      console.log('🎯 示例程序结束')
-      process.exit(0)
-    })
-    .catch((error) => {
-      console.error('💥 程序执行出错:', error)
-      process.exit(1)
-    })
-}

packages/aiCore/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@cherrystudio/ai-core",
-  "version": "1.0.0-alpha.11",
+  "version": "1.0.0-alpha.18",
   "description": "Cherry Studio AI Core - Unified AI Provider Interface Based on Vercel AI SDK",
   "main": "dist/index.js",
   "module": "dist/index.mjs",
@@ -36,16 +36,16 @@
     "ai": "^5.0.26"
   },
   "dependencies": {
-    "@ai-sdk/anthropic": "^2.0.5",
-    "@ai-sdk/azure": "^2.0.16",
-    "@ai-sdk/deepseek": "^1.0.9",
-    "@ai-sdk/google": "^2.0.7",
-    "@ai-sdk/openai": "^2.0.19",
-    "@ai-sdk/openai-compatible": "^1.0.9",
+    "@ai-sdk/anthropic": "^2.0.17",
+    "@ai-sdk/azure": "^2.0.30",
+    "@ai-sdk/deepseek": "^1.0.17",
+    "@ai-sdk/google": "^2.0.14",
+    "@ai-sdk/openai": "^2.0.30",
+    "@ai-sdk/openai-compatible": "^1.0.17",
     "@ai-sdk/provider": "^2.0.0",
-    "@ai-sdk/provider-utils": "^3.0.4",
-    "@ai-sdk/xai": "^2.0.9",
-    "zod": "^3.25.0"
+    "@ai-sdk/provider-utils": "^3.0.9",
+    "@ai-sdk/xai": "^2.0.18",
+    "zod": "^4.1.5"
   },
   "devDependencies": {
     "tsdown": "^0.12.9",

packages/aiCore/src/core/models/ModelResolver.ts

@@ -84,7 +84,6 @@ export class ModelResolver {
    */
   private resolveTraditionalModel(providerId: string, modelId: string): LanguageModelV2 {
     const fullModelId = `${providerId}${DEFAULT_SEPARATOR}${modelId}`
-    console.log('fullModelId', fullModelId)
     return globalRegistryManagement.languageModel(fullModelId as any)
   }
 

packages/aiCore/src/core/options/factory.ts

@@ -59,7 +59,7 @@ export function createGoogleOptions(options: ExtractProviderOptions<'google'>) {
 /**
  * 创建OpenRouter供应商选项的便捷函数
  */
-export function createOpenRouterOptions(options: ExtractProviderOptions<'openrouter'>) {
+export function createOpenRouterOptions(options: ExtractProviderOptions<'openrouter'> | Record<string, any>) {
   return createProviderOptions('openrouter', options)
 }
 

packages/aiCore/src/core/options/openrouter.ts

@@ -1,38 +0,0 @@
-export type OpenRouterProviderOptions = {
-  models?: string[]
-
-  /**
-   * https://openrouter.ai/docs/use-cases/reasoning-tokens
-   * One of `max_tokens` or `effort` is required.
-   * If `exclude` is true, reasoning will be removed from the response. Default is false.
-   */
-  reasoning?: {
-    exclude?: boolean
-  } & (
-    | {
-        max_tokens: number
-      }
-    | {
-        effort: 'high' | 'medium' | 'low'
-      }
-  )
-
-  /**
-   * A unique identifier representing your end-user, which can
-   * help OpenRouter to monitor and detect abuse.
-   */
-  user?: string
-
-  extraBody?: Record<string, unknown>
-
-  /**
-   * Enable usage accounting to get detailed token usage information.
-   * https://openrouter.ai/docs/use-cases/usage-accounting
-   */
-  usage?: {
-    /**
-     * When true, includes token usage information in the response.
-     */
-    include: boolean
-  }
-}

packages/aiCore/src/core/options/types.ts

@@ -2,9 +2,8 @@ import { type AnthropicProviderOptions } from '@ai-sdk/anthropic'
 import { type GoogleGenerativeAIProviderOptions } from '@ai-sdk/google'
 import { type OpenAIResponsesProviderOptions } from '@ai-sdk/openai'
 import { type SharedV2ProviderMetadata } from '@ai-sdk/provider'
-
-import { type OpenRouterProviderOptions } from './openrouter'
-import { type XaiProviderOptions } from './xai'
+import { type XaiProviderOptions } from '@ai-sdk/xai'
+import { type OpenRouterProviderOptions } from '@openrouter/ai-sdk-provider'
 
 export type ProviderOptions<T extends keyof SharedV2ProviderMetadata> = SharedV2ProviderMetadata[T]
 

packages/aiCore/src/core/options/xai.ts

@@ -1,86 +0,0 @@
-// copy from @ai-sdk/xai/xai-chat-options.ts
-// 如果@ai-sdk/xai暴露出了xaiProviderOptions就删除这个文件
-
-import * as z from 'zod/v4'
-
-const webSourceSchema = z.object({
-  type: z.literal('web'),
-  country: z.string().length(2).optional(),
-  excludedWebsites: z.array(z.string()).max(5).optional(),
-  allowedWebsites: z.array(z.string()).max(5).optional(),
-  safeSearch: z.boolean().optional()
-})
-
-const xSourceSchema = z.object({
-  type: z.literal('x'),
-  xHandles: z.array(z.string()).optional()
-})
-
-const newsSourceSchema = z.object({
-  type: z.literal('news'),
-  country: z.string().length(2).optional(),
-  excludedWebsites: z.array(z.string()).max(5).optional(),
-  safeSearch: z.boolean().optional()
-})
-
-const rssSourceSchema = z.object({
-  type: z.literal('rss'),
-  links: z.array(z.url()).max(1) // currently only supports one RSS link
-})
-
-const searchSourceSchema = z.discriminatedUnion('type', [
-  webSourceSchema,
-  xSourceSchema,
-  newsSourceSchema,
-  rssSourceSchema
-])
-
-export const xaiProviderOptions = z.object({
-  /**
-   * reasoning effort for reasoning models
-   * only supported by grok-3-mini and grok-3-mini-fast models
-   */
-  reasoningEffort: z.enum(['low', 'high']).optional(),
-
-  searchParameters: z
-    .object({
-      /**
-       * search mode preference
-       * - "off": disables search completely
-       * - "auto": model decides whether to search (default)
-       * - "on": always enables search
-       */
-      mode: z.enum(['off', 'auto', 'on']),
-
-      /**
-       * whether to return citations in the response
-       * defaults to true
-       */
-      returnCitations: z.boolean().optional(),
-
-      /**
-       * start date for search data (ISO8601 format: YYYY-MM-DD)
-       */
-      fromDate: z.string().optional(),
-
-      /**
-       * end date for search data (ISO8601 format: YYYY-MM-DD)
-       */
-      toDate: z.string().optional(),
-
-      /**
-       * maximum number of search results to consider
-       * defaults to 20
-       */
-      maxSearchResults: z.number().min(1).max(50).optional(),
-
-      /**
-       * data sources to search from
-       * defaults to ["web", "x"] if not specified
-       */
-      sources: z.array(searchSourceSchema).optional()
-    })
-    .optional()
-})
-
-export type XaiProviderOptions = z.infer<typeof xaiProviderOptions>

packages/aiCore/src/core/plugins/built-in/googleToolsPlugin/index.ts

@@ -0,0 +1,38 @@
+import { google } from '@ai-sdk/google'
+
+import { definePlugin } from '../../'
+import type { AiRequestContext } from '../../types'
+
+const toolNameMap = {
+  googleSearch: 'google_search',
+  urlContext: 'url_context',
+  codeExecution: 'code_execution'
+} as const
+
+type ToolConfigKey = keyof typeof toolNameMap
+type ToolConfig = { googleSearch?: boolean; urlContext?: boolean; codeExecution?: boolean }
+
+export const googleToolsPlugin = (config?: ToolConfig) =>
+  definePlugin({
+    name: 'googleToolsPlugin',
+    transformParams: <T>(params: T, context: AiRequestContext): T => {
+      const { providerId } = context
+      if (providerId === 'google' && config) {
+        if (typeof params === 'object' && params !== null) {
+          const typedParams = params as T & { tools?: Record<string, unknown> }
+
+          if (!typedParams.tools) {
+            typedParams.tools = {}
+          }
+          // 使用类型安全的方式遍历配置
+          ;(Object.keys(config) as ToolConfigKey[]).forEach((key) => {
+            if (config[key] && key in toolNameMap && key in google.tools) {
+              const toolName = toolNameMap[key]
+              typedParams.tools![toolName] = google.tools[key]({})
+            }
+          })
+        }
+      }
+      return params
+    }
+  })

packages/aiCore/src/core/plugins/built-in/index.ts

@@ -4,7 +4,12 @@
  */
 export const BUILT_IN_PLUGIN_PREFIX = 'built-in:'
 
+export { googleToolsPlugin } from './googleToolsPlugin'
 export { createLoggingPlugin } from './logging'
 export { createPromptToolUsePlugin } from './toolUsePlugin/promptToolUsePlugin'
-export type { PromptToolUseConfig, ToolUseRequestContext, ToolUseResult } from './toolUsePlugin/type'
-export { webSearchPlugin } from './webSearchPlugin'
+export type {
+  PromptToolUseConfig,
+  ToolUseRequestContext,
+  ToolUseResult
+} from './toolUsePlugin/type'
+export { webSearchPlugin, type WebSearchPluginConfig } from './webSearchPlugin'

packages/aiCore/src/core/plugins/built-in/toolUsePlugin/StreamEventManager.ts

@@ -27,10 +27,20 @@ export class StreamEventManager {
   /**
    * 发送步骤完成事件
    */
-  sendStepFinishEvent(controller: StreamController, chunk: any): void {
+  sendStepFinishEvent(
+    controller: StreamController,
+    chunk: any,
+    context: AiRequestContext,
+    finishReason: string = 'stop'
+  ): void {
+    // 累加当前步骤的 usage
+    if (chunk.usage && context.accumulatedUsage) {
+      this.accumulateUsage(context.accumulatedUsage, chunk.usage)
+    }
+
     controller.enqueue({
       type: 'finish-step',
-      finishReason: 'stop',
+      finishReason,
       response: chunk.response,
       usage: chunk.usage,
       providerMetadata: chunk.providerMetadata
@@ -43,28 +53,32 @@ export class StreamEventManager {
   async handleRecursiveCall(
     controller: StreamController,
     recursiveParams: any,
-    context: AiRequestContext,
-    stepId: string
+    context: AiRequestContext
   ): Promise<void> {
-    try {
-      console.log('[MCP Prompt] Starting recursive call after tool execution...')
+    // try {
+    // 重置工具执行状态，准备处理新的步骤
+    context.hasExecutedToolsInCurrentStep = false
 
-      const recursiveResult = await context.recursiveCall(recursiveParams)
+    const recursiveResult = await context.recursiveCall(recursiveParams)
 
-      if (recursiveResult && recursiveResult.fullStream) {
-        await this.pipeRecursiveStream(controller, recursiveResult.fullStream)
-      } else {
-        console.warn('[MCP Prompt] No fullstream found in recursive result:', recursiveResult)
-      }
-    } catch (error) {
-      this.handleRecursiveCallError(controller, error, stepId)
+    if (recursiveResult && recursiveResult.fullStream) {
+      await this.pipeRecursiveStream(controller, recursiveResult.fullStream, context)
+    } else {
+      console.warn('[MCP Prompt] No fullstream found in recursive result:', recursiveResult)
     }
+    // } catch (error) {
+    //   this.handleRecursiveCallError(controller, error, stepId)
+    // }
   }
 
   /**
    * 将递归流的数据传递到当前流
    */
-  private async pipeRecursiveStream(controller: StreamController, recursiveStream: ReadableStream): Promise<void> {
+  private async pipeRecursiveStream(
+    controller: StreamController,
+    recursiveStream: ReadableStream,
+    context?: AiRequestContext
+  ): Promise<void> {
     const reader = recursiveStream.getReader()
     try {
       while (true) {
@@ -73,9 +87,16 @@ export class StreamEventManager {
           break
         }
         if (value.type === 'finish') {
-          // 迭代的流不发finish
+          // 迭代的流不发finish，但需要累加其 usage
+          if (value.usage && context?.accumulatedUsage) {
+            this.accumulateUsage(context.accumulatedUsage, value.usage)
+          }
           break
         }
+        // 对于 finish-step 类型，累加其 usage
+        if (value.type === 'finish-step' && value.usage && context?.accumulatedUsage) {
+          this.accumulateUsage(context.accumulatedUsage, value.usage)
+        }
         // 将递归流的数据传递到当前流
         controller.enqueue(value)
       }
@@ -87,25 +108,25 @@ export class StreamEventManager {
   /**
    * 处理递归调用错误
    */
-  private handleRecursiveCallError(controller: StreamController, error: unknown, stepId: string): void {
-    console.error('[MCP Prompt] Recursive call failed:', error)
+  // private handleRecursiveCallError(controller: StreamController, error: unknown): void {
+  //   console.error('[MCP Prompt] Recursive call failed:', error)
 
-    // 使用 AI SDK 标准错误格式，但不中断流
-    controller.enqueue({
-      type: 'error',
-      error: {
-        message: error instanceof Error ? error.message : String(error),
-        name: error instanceof Error ? error.name : 'RecursiveCallError'
-      }
-    })
+  //   // 使用 AI SDK 标准错误格式，但不中断流
+  //   controller.enqueue({
+  //     type: 'error',
+  //     error: {
+  //       message: error instanceof Error ? error.message : String(error),
+  //       name: error instanceof Error ? error.name : 'RecursiveCallError'
+  //     }
+  //   })
 
-    // 继续发送文本增量，保持流的连续性
-    controller.enqueue({
-      type: 'text-delta',
-      id: stepId,
-      text: '\n\n[工具执行后递归调用失败，继续对话...]'
-    })
-  }
+  //   // // 继续发送文本增量，保持流的连续性
+  //   // controller.enqueue({
+  //   //   type: 'text-delta',
+  //   //   id: stepId,
+  //   //   text: '\n\n[工具执行后递归调用失败，继续对话...]'
+  //   // })
+  // }
 
   /**
    * 构建递归调用的参数
@@ -136,4 +157,18 @@ export class StreamEventManager {
 
     return recursiveParams
   }
+
+  /**
+   * 累加 usage 数据
+   */
+  private accumulateUsage(target: any, source: any): void {
+    if (!target || !source) return
+
+    // 累加各种 token 类型
+    target.inputTokens = (target.inputTokens || 0) + (source.inputTokens || 0)
+    target.outputTokens = (target.outputTokens || 0) + (source.outputTokens || 0)
+    target.totalTokens = (target.totalTokens || 0) + (source.totalTokens || 0)
+    target.reasoningTokens = (target.reasoningTokens || 0) + (source.reasoningTokens || 0)
+    target.cachedInputTokens = (target.cachedInputTokens || 0) + (source.cachedInputTokens || 0)
+  }
 }

packages/aiCore/src/core/plugins/built-in/toolUsePlugin/ToolExecutor.ts

@@ -4,7 +4,7 @@
  * 负责工具的执行、结果格式化和相关事件发送
  * 从 promptToolUsePlugin.ts 中提取出来以降低复杂度
  */
-import type { ToolSet } from 'ai'
+import type { ToolSet, TypedToolError } from 'ai'
 
 import type { ToolUseResult } from './type'
 
@@ -38,7 +38,6 @@ export class ToolExecutor {
     controller: StreamController
   ): Promise<ExecutedResult[]> {
     const executedResults: ExecutedResult[] = []
-
     for (const toolUse of toolUses) {
       try {
         const tool = tools[toolUse.toolName]
@@ -46,17 +45,12 @@ export class ToolExecutor {
           throw new Error(`Tool "${toolUse.toolName}" has no execute method`)
         }
 
-        // 发送工具调用开始事件
-        this.sendToolStartEvents(controller, toolUse)
-
-        console.log(`[MCP Prompt Stream] Executing tool: ${toolUse.toolName}`, toolUse.arguments)
-
         // 发送 tool-call 事件
         controller.enqueue({
           type: 'tool-call',
           toolCallId: toolUse.id,
           toolName: toolUse.toolName,
-          input: tool.inputSchema
+          input: toolUse.arguments
         })
 
         const result = await tool.execute(toolUse.arguments, {
@@ -111,45 +105,46 @@ export class ToolExecutor {
   /**
    * 发送工具调用开始相关事件
    */
-  private sendToolStartEvents(controller: StreamController, toolUse: ToolUseResult): void {
-    // 发送 tool-input-start 事件
-    controller.enqueue({
-      type: 'tool-input-start',
-      id: toolUse.id,
-      toolName: toolUse.toolName
-    })
-  }
+  // private sendToolStartEvents(controller: StreamController, toolUse: ToolUseResult): void {
+  //   // 发送 tool-input-start 事件
+  //   controller.enqueue({
+  //     type: 'tool-input-start',
+  //     id: toolUse.id,
+  //     toolName: toolUse.toolName
+  //   })
+  // }
 
   /**
    * 处理工具执行错误
    */
-  private handleToolError(
+  private handleToolError<T extends ToolSet>(
     toolUse: ToolUseResult,
     error: unknown,
     controller: StreamController
-    // _tools: ToolSet
   ): ExecutedResult {
     // 使用 AI SDK 标准错误格式
-    // const toolError: TypedToolError<typeof _tools> = {
-    //   type: 'tool-error',
-    //   toolCallId: toolUse.id,
-    //   toolName: toolUse.toolName,
-    //   input: toolUse.arguments,
-    //   error: error instanceof Error ? error.message : String(error)
-    // }
+    const toolError: TypedToolError<T> = {
+      type: 'tool-error',
+      toolCallId: toolUse.id,
+      toolName: toolUse.toolName,
+      input: toolUse.arguments,
+      error
+    }
 
-    // controller.enqueue(toolError)
+    controller.enqueue(toolError)
 
     // 发送标准错误事件
-    controller.enqueue({
-      type: 'error',
-      error: error instanceof Error ? error.message : String(error)
-    })
+    // controller.enqueue({
+    //   type: 'tool-error',
+    //   toolCallId: toolUse.id,
+    //   error: error instanceof Error ? error.message : String(error),
+    //   input: toolUse.arguments
+    // })
 
     return {
       toolCallId: toolUse.id,
       toolName: toolUse.toolName,
-      result: error instanceof Error ? error.message : String(error),
+      result: error,
       isError: true
     }
   }

packages/aiCore/src/core/plugins/built-in/toolUsePlugin/promptToolUsePlugin.ts

@@ -8,9 +8,19 @@ import type { TextStreamPart, ToolSet } from 'ai'
 import { definePlugin } from '../../index'
 import type { AiRequestContext } from '../../types'
 import { StreamEventManager } from './StreamEventManager'
+import { type TagConfig, TagExtractor } from './tagExtraction'
 import { ToolExecutor } from './ToolExecutor'
 import { PromptToolUseConfig, ToolUseResult } from './type'
 
+/**
+ * 工具使用标签配置
+ */
+const TOOL_USE_TAG_CONFIG: TagConfig = {
+  openingTag: '<tool_use>',
+  closingTag: '</tool_use>',
+  separator: '\n'
+}
+
 /**
  * 默认系统提示符模板（提取自 Cherry Studio）
  */
@@ -146,8 +156,10 @@ Assistant: The population of Shanghai is 26 million, while Guangzhou has a popul
 /**
  * 构建可用工具部分（提取自 Cherry Studio）
  */
-function buildAvailableTools(tools: ToolSet): string {
+function buildAvailableTools(tools: ToolSet): string | null {
   const availableTools = Object.keys(tools)
+  if (availableTools.length === 0) return null
+  const result = availableTools
     .map((toolName: string) => {
       const tool = tools[toolName]
       return `
@@ -162,7 +174,7 @@ function buildAvailableTools(tools: ToolSet): string {
     })
     .join('\n')
   return `<tools>
-${availableTools}
+${result}
 </tools>`
 }
 
@@ -171,6 +183,7 @@ ${availableTools}
  */
 function defaultBuildSystemPrompt(userSystemPrompt: string, tools: ToolSet): string {
   const availableTools = buildAvailableTools(tools)
+  if (availableTools === null) return userSystemPrompt
 
   const fullPrompt = DEFAULT_SYSTEM_PROMPT.replace('{{ TOOL_USE_EXAMPLES }}', DEFAULT_TOOL_USE_EXAMPLES)
     .replace('{{ AVAILABLE_TOOLS }}', availableTools)
@@ -249,13 +262,11 @@ export const createPromptToolUsePlugin = (config: PromptToolUseConfig = {}) => {
       }
 
       context.mcpTools = params.tools
-      console.log('tools stored in context', params.tools)
 
       // 构建系统提示符
       const userSystemPrompt = typeof params.system === 'string' ? params.system : ''
       const systemPrompt = buildSystemPrompt(userSystemPrompt, params.tools)
       let systemMessage: string | null = systemPrompt
-      console.log('config.context', context)
       if (config.createSystemMessage) {
         // 🎯 如果用户提供了自定义处理函数，使用它
         systemMessage = config.createSystemMessage(systemPrompt, params, context)
@@ -268,20 +279,40 @@ export const createPromptToolUsePlugin = (config: PromptToolUseConfig = {}) => {
         tools: undefined
       }
       context.originalParams = transformedParams
-      console.log('transformedParams', transformedParams)
       return transformedParams
     },
     transformStream: (_: any, context: AiRequestContext) => () => {
       let textBuffer = ''
-      let stepId = ''
+      // let stepId = ''
 
       if (!context.mcpTools) {
         throw new Error('No tools available')
       }
 
-      // 创建工具执行器和流事件管理器
+      // 从 context 中获取或初始化 usage 累加器
+      if (!context.accumulatedUsage) {
+        context.accumulatedUsage = {
+          inputTokens: 0,
+          outputTokens: 0,
+          totalTokens: 0,
+          reasoningTokens: 0,
+          cachedInputTokens: 0
+        }
+      }
+
+      // 创建工具执行器、流事件管理器和标签提取器
       const toolExecutor = new ToolExecutor()
       const streamEventManager = new StreamEventManager()
+      const tagExtractor = new TagExtractor(TOOL_USE_TAG_CONFIG)
+
+      // 在context中初始化工具执行状态，避免递归调用时状态丢失
+      if (!context.hasExecutedToolsInCurrentStep) {
+        context.hasExecutedToolsInCurrentStep = false
+      }
+
+      // 用于hold text-start事件，直到确认有非工具标签内容
+      let pendingTextStart: TextStreamPart<TOOLS> | null = null
+      let hasStartedText = false
 
       type TOOLS = NonNullable<typeof context.mcpTools>
       return new TransformStream<TextStreamPart<TOOLS>, TextStreamPart<TOOLS>>({
@@ -289,83 +320,106 @@ export const createPromptToolUsePlugin = (config: PromptToolUseConfig = {}) => {
           chunk: TextStreamPart<TOOLS>,
           controller: TransformStreamDefaultController<TextStreamPart<TOOLS>>
         ) {
-          // 收集文本内容
-          if (chunk.type === 'text-delta') {
-            textBuffer += chunk.text || ''
-            stepId = chunk.id || ''
-            controller.enqueue(chunk)
+          // Hold住text-start事件，直到确认有非工具标签内容
+          if ((chunk as any).type === 'text-start') {
+            pendingTextStart = chunk
             return
           }
 
-          if (chunk.type === 'text-end' || chunk.type === 'finish-step') {
-            const tools = context.mcpTools
-            if (!tools || Object.keys(tools).length === 0) {
-              controller.enqueue(chunk)
-              return
-            }
+          // text-delta阶段：收集文本内容并过滤工具标签
+          if (chunk.type === 'text-delta') {
+            textBuffer += chunk.text || ''
+            // stepId = chunk.id || ''
 
-            // 解析工具调用
-            const { results: parsedTools, content: parsedContent } = parseToolUse(textBuffer, tools)
-            const validToolUses = parsedTools.filter((t) => t.status === 'pending')
+            // 使用TagExtractor过滤工具标签，只传递非标签内容到UI层
+            const extractionResults = tagExtractor.processText(chunk.text || '')
 
-            // 如果没有有效的工具调用，直接传递原始事件
-            if (validToolUses.length === 0) {
-              controller.enqueue(chunk)
-              return
-            }
-
-            if (chunk.type === 'text-end') {
-              controller.enqueue({
-                type: 'text-end',
-                id: stepId,
-                providerMetadata: {
-                  text: {
-                    value: parsedContent
-                  }
+            for (const result of extractionResults) {
+              // 只传递非标签内容到UI层
+              if (!result.isTagContent && result.content) {
+                // 如果还没有发送text-start且有pending的text-start，先发送它
+                if (!hasStartedText && pendingTextStart) {
+                  controller.enqueue(pendingTextStart)
+                  hasStartedText = true
+                  pendingTextStart = null
                 }
-              })
-              return
+
+                const filteredChunk = {
+                  ...chunk,
+                  text: result.content
+                }
+                controller.enqueue(filteredChunk)
+              }
+            }
+            return
+          }
+
+          if (chunk.type === 'text-end') {
+            // 只有当已经发送了text-start时才发送text-end
+            if (hasStartedText) {
+              controller.enqueue(chunk)
+            }
+            return
+          }
+
+          if (chunk.type === 'finish-step') {
+            // 统一在finish-step阶段检查并执行工具调用
+            const tools = context.mcpTools
+            if (tools && Object.keys(tools).length > 0 && !context.hasExecutedToolsInCurrentStep) {
+              // 解析完整的textBuffer来检测工具调用
+              const { results: parsedTools } = parseToolUse(textBuffer, tools)
+              const validToolUses = parsedTools.filter((t) => t.status === 'pending')
+
+              if (validToolUses.length > 0) {
+                context.hasExecutedToolsInCurrentStep = true
+
+                // 执行工具调用（不需要手动发送 start-step，外部流已经处理）
+                const executedResults = await toolExecutor.executeTools(validToolUses, tools, controller)
+
+                // 发送步骤完成事件，使用 tool-calls 作为 finishReason
+                streamEventManager.sendStepFinishEvent(controller, chunk, context, 'tool-calls')
+
+                // 处理递归调用
+                const toolResultsText = toolExecutor.formatToolResults(executedResults)
+                const recursiveParams = streamEventManager.buildRecursiveParams(
+                  context,
+                  textBuffer,
+                  toolResultsText,
+                  tools
+                )
+
+                await streamEventManager.handleRecursiveCall(controller, recursiveParams, context)
+                return
+              }
             }
 
-            controller.enqueue({
-              ...chunk,
-              finishReason: 'tool-calls'
-            })
-
-            // 发送步骤开始事件
-            streamEventManager.sendStepStartEvent(controller)
-
-            // 执行工具调用
-            const executedResults = await toolExecutor.executeTools(validToolUses, tools, controller)
-
-            // 发送步骤完成事件
-            streamEventManager.sendStepFinishEvent(controller, chunk)
-
-            // 处理递归调用
-            if (validToolUses.length > 0) {
-              const toolResultsText = toolExecutor.formatToolResults(executedResults)
-              const recursiveParams = streamEventManager.buildRecursiveParams(
-                context,
-                textBuffer,
-                toolResultsText,
-                tools
-              )
-
-              await streamEventManager.handleRecursiveCall(controller, recursiveParams, context, stepId)
-            }
+            // 如果没有执行工具调用，直接传递原始finish-step事件
+            controller.enqueue(chunk)
 
             // 清理状态
             textBuffer = ''
             return
           }
 
-          // 对于其他类型的事件，直接传递
-          controller.enqueue(chunk)
+          // 处理 finish 类型，使用累加后的 totalUsage
+          if (chunk.type === 'finish') {
+            controller.enqueue({
+              ...chunk,
+              totalUsage: context.accumulatedUsage
+            })
+            return
+          }
+
+          // 对于其他类型的事件，直接传递（不包括text-start，已在上面处理）
+          if ((chunk as any).type !== 'text-start') {
+            controller.enqueue(chunk)
+          }
         },
 
         flush() {
-          // 流结束时的清理工作
-          console.log('[MCP Prompt] Stream ended, cleaning up...')
+          // 清理pending状态
+          pendingTextStart = null
+          hasStartedText = false
         }
       })
     }

packages/aiCore/src/core/plugins/built-in/webSearchPlugin/helper.ts

@@ -3,13 +3,16 @@ import { google } from '@ai-sdk/google'
 import { openai } from '@ai-sdk/openai'
 
 import { ProviderOptionsMap } from '../../../options/types'
+import { OpenRouterSearchConfig } from './openrouter'
 
 /**
  * 从 AI SDK 的工具函数中提取参数类型，以确保类型安全。
  */
-type OpenAISearchConfig = Parameters<typeof openai.tools.webSearchPreview>[0]
-type AnthropicSearchConfig = Parameters<typeof anthropic.tools.webSearch_20250305>[0]
-type GoogleSearchConfig = Parameters<typeof google.tools.googleSearch>[0]
+export type OpenAISearchConfig = NonNullable<Parameters<typeof openai.tools.webSearch>[0]>
+export type OpenAISearchPreviewConfig = NonNullable<Parameters<typeof openai.tools.webSearchPreview>[0]>
+export type AnthropicSearchConfig = NonNullable<Parameters<typeof anthropic.tools.webSearch_20250305>[0]>
+export type GoogleSearchConfig = NonNullable<Parameters<typeof google.tools.googleSearch>[0]>
+export type XAISearchConfig = NonNullable<ProviderOptionsMap['xai']['searchParameters']>
 
 /**
  * 插件初始化时接收的完整配置对象
@@ -18,10 +21,12 @@ type GoogleSearchConfig = Parameters<typeof google.tools.googleSearch>[0]
  */
 export interface WebSearchPluginConfig {
   openai?: OpenAISearchConfig
+  'openai-chat'?: OpenAISearchPreviewConfig
   anthropic?: AnthropicSearchConfig
   xai?: ProviderOptionsMap['xai']['searchParameters']
   google?: GoogleSearchConfig
   'google-vertex'?: GoogleSearchConfig
+  openrouter?: OpenRouterSearchConfig
 }
 
 /**
@@ -31,6 +36,7 @@ export const DEFAULT_WEB_SEARCH_CONFIG: WebSearchPluginConfig = {
   google: {},
   'google-vertex': {},
   openai: {},
+  'openai-chat': {},
   xai: {
     mode: 'on',
     returnCitations: true,
@@ -39,6 +45,14 @@ export const DEFAULT_WEB_SEARCH_CONFIG: WebSearchPluginConfig = {
   },
   anthropic: {
     maxUses: 5
+  },
+  openrouter: {
+    plugins: [
+      {
+        id: 'web',
+        max_results: 5
+      }
+    ]
   }
 }
 

packages/aiCore/src/core/plugins/built-in/webSearchPlugin/index.ts

@@ -6,7 +6,7 @@ import { anthropic } from '@ai-sdk/anthropic'
 import { google } from '@ai-sdk/google'
 import { openai } from '@ai-sdk/openai'
 
-import { createXaiOptions, mergeProviderOptions } from '../../../options'
+import { createOpenRouterOptions, createXaiOptions, mergeProviderOptions } from '../../../options'
 import { definePlugin } from '../../'
 import type { AiRequestContext } from '../../types'
 import { DEFAULT_WEB_SEARCH_CONFIG, WebSearchPluginConfig } from './helper'
@@ -27,7 +27,14 @@ export const webSearchPlugin = (config: WebSearchPluginConfig = DEFAULT_WEB_SEAR
         case 'openai': {
           if (config.openai) {
             if (!params.tools) params.tools = {}
-            params.tools.web_search_preview = openai.tools.webSearchPreview(config.openai)
+            params.tools.web_search = openai.tools.webSearch(config.openai)
+          }
+          break
+        }
+        case 'openai-chat': {
+          if (config['openai-chat']) {
+            if (!params.tools) params.tools = {}
+            params.tools.web_search_preview = openai.tools.webSearchPreview(config['openai-chat'])
           }
           break
         }
@@ -56,6 +63,14 @@ export const webSearchPlugin = (config: WebSearchPluginConfig = DEFAULT_WEB_SEAR
           }
           break
         }
+
+        case 'openrouter': {
+          if (config.openrouter) {
+            const searchOptions = createOpenRouterOptions(config.openrouter)
+            params.providerOptions = mergeProviderOptions(params.providerOptions, searchOptions)
+          }
+          break
+        }
       }
 
       return params

packages/aiCore/src/core/plugins/built-in/webSearchPlugin/openrouter.ts

@@ -0,0 +1,26 @@
+export type OpenRouterSearchConfig = {
+  plugins?: Array<{
+    id: 'web'
+    /**
+     * Maximum number of search results to include (default: 5)
+     */
+    max_results?: number
+    /**
+     * Custom search prompt to guide the search query
+     */
+    search_prompt?: string
+  }>
+  /**
+   * Built-in web search options for models that support native web search
+   */
+  web_search_options?: {
+    /**
+     * Maximum number of search results to include
+     */
+    max_results?: number
+    /**
+     * Custom search prompt to guide the search query
+     */
+    search_prompt?: string
+  }
+}

packages/aiCore/src/core/plugins/index.ts

@@ -1,5 +1,8 @@
 // 核心类型和接口
 export type { AiPlugin, AiRequestContext, HookResult, PluginManagerConfig } from './types'
+import type { ImageModelV2 } from '@ai-sdk/provider'
+import type { LanguageModel } from 'ai'
+
 import type { ProviderId } from '../providers'
 import type { AiPlugin, AiRequestContext } from './types'
 
@@ -9,16 +12,16 @@ export { PluginManager } from './manager'
 // 工具函数
 export function createContext<T extends ProviderId>(
   providerId: T,
-  modelId: string,
+  model: LanguageModel | ImageModelV2,
   originalParams: any
 ): AiRequestContext {
   return {
     providerId,
-    modelId,
+    model,
     originalParams,
     metadata: {},
     startTime: Date.now(),
-    requestId: `${providerId}-${modelId}-${Date.now()}-${Math.random().toString(36).slice(2)}`,
+    requestId: `${providerId}-${typeof model === 'string' ? model : model?.modelId}-${Date.now()}-${Math.random().toString(36).slice(2)}`,
     // 占位
     recursiveCall: () => Promise.resolve(null)
   }

packages/aiCore/src/core/plugins/types.ts

@@ -14,7 +14,7 @@ export type RecursiveCallFn = (newParams: any) => Promise<any>
  */
 export interface AiRequestContext {
   providerId: ProviderId
-  modelId: string
+  model: LanguageModel | ImageModelV2
   originalParams: any
   metadata: Record<string, any>
   startTime: number

packages/aiCore/src/core/providers/schemas.ts

@@ -9,9 +9,11 @@ import { createDeepSeek } from '@ai-sdk/deepseek'
 import { createGoogleGenerativeAI } from '@ai-sdk/google'
 import { createOpenAI, type OpenAIProviderSettings } from '@ai-sdk/openai'
 import { createOpenAICompatible } from '@ai-sdk/openai-compatible'
+import { LanguageModelV2 } from '@ai-sdk/provider'
 import { createXai } from '@ai-sdk/xai'
-import { customProvider, type Provider } from 'ai'
-import * as z from 'zod'
+import { createOpenRouter } from '@openrouter/ai-sdk-provider'
+import { customProvider, Provider } from 'ai'
+import { z } from 'zod'
 
 /**
  * 基础 Provider IDs
@@ -25,7 +27,8 @@ export const baseProviderIds = [
   'xai',
   'azure',
   'azure-responses',
-  'deepseek'
+  'deepseek',
+  'openrouter'
 ] as const
 
 /**
@@ -38,14 +41,16 @@ export const baseProviderIdSchema = z.enum(baseProviderIds)
  */
 export type BaseProviderId = z.infer<typeof baseProviderIdSchema>
 
-export const baseProviderSchema = z.object({
-  id: baseProviderIdSchema,
-  name: z.string(),
-  creator: z.function().args(z.any()).returns(z.any()) as z.ZodType<(options: any) => Provider>,
-  supportsImageGeneration: z.boolean()
-})
+export const isBaseProvider = (id: ProviderId): id is BaseProviderId => {
+  return baseProviderIdSchema.safeParse(id).success
+}
 
-export type BaseProvider = z.infer<typeof baseProviderSchema>
+type BaseProvider = {
+  id: BaseProviderId
+  name: string
+  creator: (options: any) => Provider | LanguageModelV2
+  supportsImageGeneration: boolean
+}
 
 /**
  * 基础 Providers 定义
@@ -121,6 +126,12 @@ export const baseProviders = [
     name: 'DeepSeek',
     creator: createDeepSeek,
     supportsImageGeneration: false
+  },
+  {
+    id: 'openrouter',
+    name: 'OpenRouter',
+    creator: createOpenRouter,
+    supportsImageGeneration: true
   }
 ] as const satisfies BaseProvider[]
 
@@ -148,7 +159,12 @@ export const providerConfigSchema = z
   .object({
     id: customProviderIdSchema, // 只允许自定义ID
     name: z.string().min(1),
-    creator: z.function().optional(),
+    creator: z
+      .function({
+        input: z.any(),
+        output: z.any()
+      })
+      .optional(),
     import: z.function().optional(),
     creatorFunctionName: z.string().optional(),
     supportsImageGeneration: z.boolean().default(false),

packages/aiCore/src/core/runtime/executor.ts

@@ -4,12 +4,12 @@
  */
 import { ImageModelV2, LanguageModelV2, LanguageModelV2Middleware } from '@ai-sdk/provider'
 import {
-  experimental_generateImage as generateImage,
-  generateObject,
-  generateText,
+  experimental_generateImage as _generateImage,
+  generateObject as _generateObject,
+  generateText as _generateText,
   LanguageModel,
-  streamObject,
-  streamText
+  streamObject as _streamObject,
+  streamText as _streamText
 } from 'ai'
 
 import { globalModelResolver } from '../models'
@@ -18,7 +18,14 @@ import { type AiPlugin, type AiRequestContext, definePlugin } from '../plugins'
 import { type ProviderId } from '../providers'
 import { ImageGenerationError, ImageModelResolutionError } from './errors'
 import { PluginEngine } from './pluginEngine'
-import { type RuntimeConfig } from './types'
+import type {
+  generateImageParams,
+  generateObjectParams,
+  generateTextParams,
+  RuntimeConfig,
+  streamObjectParams,
+  streamTextParams
+} from './types'
 
 export class RuntimeExecutor<T extends ProviderId = ProviderId> {
   public pluginEngine: PluginEngine<T>
@@ -75,12 +82,12 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
    * 流式文本生成
    */
   async streamText(
-    params: Parameters<typeof streamText>[0],
+    params: streamTextParams,
     options?: {
       middlewares?: LanguageModelV2Middleware[]
     }
-  ): Promise<ReturnType<typeof streamText>> {
-    const { model, ...restParams } = params
+  ): Promise<ReturnType<typeof _streamText>> {
+    const { model } = params
 
     // 根据 model 类型决定插件配置
     if (typeof model === 'string') {
@@ -94,19 +101,16 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
 
     return this.pluginEngine.executeStreamWithPlugins(
       'streamText',
-      model,
-      restParams,
-      async (resolvedModel, transformedParams, streamTransforms) => {
+      params,
+      (resolvedModel, transformedParams, streamTransforms) => {
         const experimental_transform =
           params?.experimental_transform ?? (streamTransforms.length > 0 ? streamTransforms : undefined)
 
-        const finalParams = {
-          model: resolvedModel,
+        return _streamText({
           ...transformedParams,
+          model: resolvedModel,
           experimental_transform
-        } as Parameters<typeof streamText>[0]
-
-        return await streamText(finalParams)
+        })
       }
     )
   }
@@ -117,12 +121,12 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
    * 生成文本
    */
   async generateText(
-    params: Parameters<typeof generateText>[0],
+    params: generateTextParams,
     options?: {
       middlewares?: LanguageModelV2Middleware[]
     }
-  ): Promise<ReturnType<typeof generateText>> {
-    const { model, ...restParams } = params
+  ): Promise<ReturnType<typeof _generateText>> {
+    const { model } = params
 
     // 根据 model 类型决定插件配置
     if (typeof model === 'string') {
@@ -134,12 +138,10 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
       this.pluginEngine.usePlugins([this.createConfigureContextPlugin()])
     }
 
-    return this.pluginEngine.executeWithPlugins(
+    return this.pluginEngine.executeWithPlugins<Parameters<typeof _generateText>[0], ReturnType<typeof _generateText>>(
       'generateText',
-      model,
-      restParams,
-      async (resolvedModel, transformedParams) =>
-        generateText({ model: resolvedModel, ...transformedParams } as Parameters<typeof generateText>[0])
+      params,
+      (resolvedModel, transformedParams) => _generateText({ ...transformedParams, model: resolvedModel })
     )
   }
 
@@ -147,12 +149,12 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
    * 生成结构化对象
    */
   async generateObject(
-    params: Parameters<typeof generateObject>[0],
+    params: generateObjectParams,
     options?: {
       middlewares?: LanguageModelV2Middleware[]
     }
-  ): Promise<ReturnType<typeof generateObject>> {
-    const { model, ...restParams } = params
+  ): Promise<ReturnType<typeof _generateObject>> {
+    const { model } = params
 
     // 根据 model 类型决定插件配置
     if (typeof model === 'string') {
@@ -164,25 +166,23 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
       this.pluginEngine.usePlugins([this.createConfigureContextPlugin()])
     }
 
-    return this.pluginEngine.executeWithPlugins(
+    return this.pluginEngine.executeWithPlugins<generateObjectParams, ReturnType<typeof _generateObject>>(
       'generateObject',
-      model,
-      restParams,
-      async (resolvedModel, transformedParams) =>
-        generateObject({ model: resolvedModel, ...transformedParams } as Parameters<typeof generateObject>[0])
+      params,
+      async (resolvedModel, transformedParams) => _generateObject({ ...transformedParams, model: resolvedModel })
     )
   }
 
   /**
    * 流式生成结构化对象
    */
-  async streamObject(
-    params: Parameters<typeof streamObject>[0],
+  streamObject(
+    params: streamObjectParams,
     options?: {
       middlewares?: LanguageModelV2Middleware[]
     }
-  ): Promise<ReturnType<typeof streamObject>> {
-    const { model, ...restParams } = params
+  ): Promise<ReturnType<typeof _streamObject>> {
+    const { model } = params
 
     // 根据 model 类型决定插件配置
     if (typeof model === 'string') {
@@ -194,23 +194,17 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
       this.pluginEngine.usePlugins([this.createConfigureContextPlugin()])
     }
 
-    return this.pluginEngine.executeWithPlugins(
-      'streamObject',
-      model,
-      restParams,
-      async (resolvedModel, transformedParams) =>
-        streamObject({ model: resolvedModel, ...transformedParams } as Parameters<typeof streamObject>[0])
+    return this.pluginEngine.executeStreamWithPlugins('streamObject', params, (resolvedModel, transformedParams) =>
+      _streamObject({ ...transformedParams, model: resolvedModel })
     )
   }
 
   /**
    * 生成图像
    */
-  async generateImage(
-    params: Omit<Parameters<typeof generateImage>[0], 'model'> & { model: string | ImageModelV2 }
-  ): Promise<ReturnType<typeof generateImage>> {
+  generateImage(params: generateImageParams): Promise<ReturnType<typeof _generateImage>> {
     try {
-      const { model, ...restParams } = params
+      const { model } = params
 
       // 根据 model 类型决定插件配置
       if (typeof model === 'string') {
@@ -219,13 +213,8 @@ export class RuntimeExecutor<T extends ProviderId = ProviderId> {
         this.pluginEngine.usePlugins([this.createConfigureContextPlugin()])
       }
 
-      return await this.pluginEngine.executeImageWithPlugins(
-        'generateImage',
-        model,
-        restParams,
-        async (resolvedModel, transformedParams) => {
-          return await generateImage({ model: resolvedModel, ...transformedParams })
-        }
+      return this.pluginEngine.executeImageWithPlugins('generateImage', params, (resolvedModel, transformedParams) =>
+        _generateImage({ ...transformedParams, model: resolvedModel })
       )
     } catch (error) {
       if (error instanceof Error) {

packages/aiCore/src/core/runtime/pluginEngine.ts

@@ -1,6 +1,6 @@
 /* eslint-disable @eslint-react/naming-convention/context-name */
 import { ImageModelV2 } from '@ai-sdk/provider'
-import { LanguageModel } from 'ai'
+import { experimental_generateImage, generateObject, generateText, LanguageModel, streamObject, streamText } from 'ai'
 
 import { type AiPlugin, createContext, PluginManager } from '../plugins'
 import { type ProviderId } from '../providers/types'
@@ -62,17 +62,19 @@ export class PluginEngine<T extends ProviderId = ProviderId> {
    * 执行带插件的操作（非流式）
    * 提供给AiExecutor使用
    */
-  async executeWithPlugins<TParams, TResult>(
+  async executeWithPlugins<
+    TParams extends Parameters<typeof generateText | typeof generateObject>[0],
+    TResult extends ReturnType<typeof generateText | typeof generateObject>
+  >(
     methodName: string,
-    model: LanguageModel,
     params: TParams,
-    executor: (model: LanguageModel, transformedParams: TParams) => Promise<TResult>,
+    executor: (model: LanguageModel, transformedParams: TParams) => TResult,
     _context?: ReturnType<typeof createContext>
   ): Promise<TResult> {
     // 统一处理模型解析
     let resolvedModel: LanguageModel | undefined
     let modelId: string
-
+    const { model } = params
     if (typeof model === 'string') {
       // 字符串：需要通过插件解析
       modelId = model
@@ -83,13 +85,13 @@ export class PluginEngine<T extends ProviderId = ProviderId> {
     }
 
     // 使用正确的createContext创建请求上下文
-    const context = _context ? _context : createContext(this.providerId, modelId, params)
+    const context = _context ? _context : createContext(this.providerId, model, params)
 
     // 🔥 为上下文添加递归调用能力
     context.recursiveCall = async (newParams: any): Promise<TResult> => {
       // 递归调用自身，重新走完整的插件流程
       context.isRecursiveCall = true
-      const result = await this.executeWithPlugins(methodName, model, newParams, executor, context)
+      const result = await this.executeWithPlugins(methodName, newParams, executor, context)
       context.isRecursiveCall = false
       return result
     }
@@ -138,17 +140,19 @@ export class PluginEngine<T extends ProviderId = ProviderId> {
    * 执行带插件的图像生成操作
    * 提供给AiExecutor使用
    */
-  async executeImageWithPlugins<TParams, TResult>(
+  async executeImageWithPlugins<
+    TParams extends Omit<Parameters<typeof experimental_generateImage>[0], 'model'> & { model: string | ImageModelV2 },
+    TResult extends ReturnType<typeof experimental_generateImage>
+  >(
     methodName: string,
-    model: ImageModelV2 | string,
     params: TParams,
-    executor: (model: ImageModelV2, transformedParams: TParams) => Promise<TResult>,
+    executor: (model: ImageModelV2, transformedParams: TParams) => TResult,
     _context?: ReturnType<typeof createContext>
   ): Promise<TResult> {
     // 统一处理模型解析
     let resolvedModel: ImageModelV2 | undefined
     let modelId: string
-
+    const { model } = params
     if (typeof model === 'string') {
       // 字符串：需要通过插件解析
       modelId = model
@@ -159,13 +163,13 @@ export class PluginEngine<T extends ProviderId = ProviderId> {
     }
 
     // 使用正确的createContext创建请求上下文
-    const context = _context ? _context : createContext(this.providerId, modelId, params)
+    const context = _context ? _context : createContext(this.providerId, model, params)
 
     // 🔥 为上下文添加递归调用能力
     context.recursiveCall = async (newParams: any): Promise<TResult> => {
       // 递归调用自身，重新走完整的插件流程
       context.isRecursiveCall = true
-      const result = await this.executeImageWithPlugins(methodName, model, newParams, executor, context)
+      const result = await this.executeImageWithPlugins(methodName, newParams, executor, context)
       context.isRecursiveCall = false
       return result
     }
@@ -214,17 +218,19 @@ export class PluginEngine<T extends ProviderId = ProviderId> {
    * 执行流式调用的通用逻辑（支持流转换器）
    * 提供给AiExecutor使用
    */
-  async executeStreamWithPlugins<TParams, TResult>(
+  async executeStreamWithPlugins<
+    TParams extends Parameters<typeof streamText | typeof streamObject>[0],
+    TResult extends ReturnType<typeof streamText | typeof streamObject>
+  >(
     methodName: string,
-    model: LanguageModel,
     params: TParams,
-    executor: (model: LanguageModel, transformedParams: TParams, streamTransforms: any[]) => Promise<TResult>,
+    executor: (model: LanguageModel, transformedParams: TParams, streamTransforms: any[]) => TResult,
     _context?: ReturnType<typeof createContext>
   ): Promise<TResult> {
     // 统一处理模型解析
     let resolvedModel: LanguageModel | undefined
     let modelId: string
-
+    const { model } = params
     if (typeof model === 'string') {
       // 字符串：需要通过插件解析
       modelId = model
@@ -235,13 +241,13 @@ export class PluginEngine<T extends ProviderId = ProviderId> {
     }
 
     // 创建请求上下文
-    const context = _context ? _context : createContext(this.providerId, modelId, params)
+    const context = _context ? _context : createContext(this.providerId, model, params)
 
     // 🔥 为上下文添加递归调用能力
     context.recursiveCall = async (newParams: any): Promise<TResult> => {
       // 递归调用自身，重新走完整的插件流程
       context.isRecursiveCall = true
-      const result = await this.executeStreamWithPlugins(methodName, model, newParams, executor, context)
+      const result = await this.executeStreamWithPlugins(methodName, newParams, executor, context)
       context.isRecursiveCall = false
       return result
     }

packages/aiCore/src/core/runtime/types.ts

@@ -1,6 +1,9 @@
 /**
  * Runtime 层类型定义
  */
+import { ImageModelV2 } from '@ai-sdk/provider'
+import { experimental_generateImage, generateObject, generateText, streamObject, streamText } from 'ai'
+
 import { type ModelConfig } from '../models/types'
 import { type AiPlugin } from '../plugins'
 import { type ProviderId } from '../providers/types'
@@ -13,3 +16,11 @@ export interface RuntimeConfig<T extends ProviderId = ProviderId> {
   providerSettings: ModelConfig<T>['providerSettings'] & { mode?: 'chat' | 'responses' }
   plugins?: AiPlugin[]
 }
+
+export type generateImageParams = Omit<Parameters<typeof experimental_generateImage>[0], 'model'> & {
+  model: string | ImageModelV2
+}
+export type generateObjectParams = Parameters<typeof generateObject>[0]
+export type generateTextParams = Parameters<typeof generateText>[0]
+export type streamObjectParams = Parameters<typeof streamObject>[0]
+export type streamTextParams = Parameters<typeof streamText>[0]

packages/aiCore/tsconfig.json

@@ -1,26 +1,21 @@
 {
   "compilerOptions": {
-    "target": "ES2020",
+    "allowSyntheticDefaultImports": true,
+    "declaration": true,
+    "emitDecoratorMetadata": true,
+    "esModuleInterop": true,
+    "experimentalDecorators": true,
+    "forceConsistentCasingInFileNames": true,
     "module": "ESNext",
     "moduleResolution": "bundler",
-    "declaration": true,
-    "outDir": "./dist",
-    "rootDir": "./src",
-    "strict": true,
-    "esModuleInterop": true,
-    "skipLibCheck": true,
-    "forceConsistentCasingInFileNames": true,
-    "resolveJsonModule": true,
-    "allowSyntheticDefaultImports": true,
     "noEmitOnError": false,
-    "experimentalDecorators": true,
-    "emitDecoratorMetadata": true
+    "outDir": "./dist",
+    "resolveJsonModule": true,
+    "rootDir": "./src",
+    "skipLibCheck": true,
+    "strict": true,
+    "target": "ES2020"
   },
-  "include": [
-    "src/**/*"
-  ],
-  "exclude": [
-    "node_modules",
-    "dist"
-  ]
-} 
+  "exclude": ["node_modules", "dist"],
+  "include": ["src/**/*"]
+}

packages/extension-table-plus/package.json

@@ -67,13 +67,13 @@
     "dist"
   ],
   "devDependencies": {
+    "@biomejs/biome": "2.2.4",
     "@tiptap/core": "^3.2.0",
     "@tiptap/pm": "^3.2.0",
     "eslint": "^9.22.0",
     "eslint-plugin-react-hooks": "^5.2.0",
     "eslint-plugin-simple-import-sort": "^12.1.1",
     "eslint-plugin-unused-imports": "^4.1.4",
-    "prettier": "^3.5.3",
     "tsdown": "^0.13.3"
   },
   "peerDependencies": {
@@ -87,7 +87,7 @@
   },
   "scripts": {
     "build": "tsdown",
-    "lint": "prettier ./src/ --write && eslint --fix ./src/"
+    "lint": "biome format ./src/ --write && eslint --fix ./src/"
   },
   "packageManager": "yarn@4.9.1"
 }

packages/shared/IpcChannel.ts

@@ -35,8 +35,10 @@ export enum IpcChannel {
   App_InstallBunBinary = 'app:install-bun-binary',
   App_LogToMain = 'app:log-to-main',
   App_SaveData = 'app:save-data',
+  App_GetDiskInfo = 'app:get-disk-info',
   App_SetFullScreen = 'app:set-full-screen',
   App_IsFullScreen = 'app:is-full-screen',
+  App_GetSystemFonts = 'app:get-system-fonts',
 
   App_MacIsProcessTrusted = 'app:mac-is-process-trusted',
   App_MacRequestProcessTrust = 'app:mac-request-process-trust',
@@ -83,10 +85,13 @@ export enum IpcChannel {
   Mcp_UploadDxt = 'mcp:upload-dxt',
   Mcp_AbortTool = 'mcp:abort-tool',
   Mcp_GetServerVersion = 'mcp:get-server-version',
-
+  Mcp_Progress = 'mcp:progress',
   // Python
   Python_Execute = 'python:execute',
 
+  // agent messages
+  AgentMessage_PersistExchange = 'agent-message:persist-exchange',
+
   //copilot
   Copilot_GetAuthMessage = 'copilot:get-auth-message',
   Copilot_GetCopilotToken = 'copilot:get-copilot-token',
@@ -123,6 +128,12 @@ export enum IpcChannel {
   Windows_SetMinimumSize = 'window:set-minimum-size',
   Windows_Resize = 'window:resize',
   Windows_GetSize = 'window:get-size',
+  Windows_Minimize = 'window:minimize',
+  Windows_Maximize = 'window:maximize',
+  Windows_Unmaximize = 'window:unmaximize',
+  Windows_Close = 'window:close',
+  Windows_IsMaximized = 'window:is-maximized',
+  Windows_MaximizedChanged = 'window:maximized-changed',
 
   KnowledgeBase_Create = 'knowledge-base:create',
   KnowledgeBase_Reset = 'knowledge-base:reset',
@@ -250,7 +261,6 @@ export enum IpcChannel {
 
   // Provider
   Provider_AddKey = 'provider:add-key',
-  Provider_GetClaudeCodePort = 'provider:get-claude-code-port',
 
   //Selection Assistant
   Selection_TextSelected = 'selection:text-selected',
@@ -297,6 +307,21 @@ export enum IpcChannel {
   TRACE_CLEAN_LOCAL_DATA = 'trace:cleanLocalData',
   TRACE_ADD_STREAM_MESSAGE = 'trace:addStreamMessage',
 
+  // API Server
+  ApiServer_Start = 'api-server:start',
+  ApiServer_Stop = 'api-server:stop',
+  ApiServer_Restart = 'api-server:restart',
+  ApiServer_GetStatus = 'api-server:get-status',
+  ApiServer_GetConfig = 'api-server:get-config',
+
+  // Anthropic OAuth
+  Anthropic_StartOAuthFlow = 'anthropic:start-oauth-flow',
+  Anthropic_CompleteOAuthWithCode = 'anthropic:complete-oauth-with-code',
+  Anthropic_CancelOAuthFlow = 'anthropic:cancel-oauth-flow',
+  Anthropic_GetAccessToken = 'anthropic:get-access-token',
+  Anthropic_HasCredentials = 'anthropic:has-credentials',
+  Anthropic_ClearCredentials = 'anthropic:clear-credentials',
+
   // CodeTools
   CodeTools_Run = 'code-tools:run',
 

packages/shared/config/constant.ts

@@ -216,5 +216,6 @@ export enum codeTools {
   qwenCode = 'qwen-code',
   claudeCode = 'claude-code',
   geminiCli = 'gemini-cli',
-  openaiCodex = 'openai-codex'
+  openaiCodex = 'openai-codex',
+  iFlowCli = 'iflow-cli'
 }

packages/shared/config/types.ts

@@ -7,7 +7,7 @@ export type LoaderReturn = {
   loaderType: string
   status?: ProcessingStatus
   message?: string
-  messageSource?: 'preprocess' | 'embedding'
+  messageSource?: 'preprocess' | 'embedding' | 'validation'
 }
 
 export type FileChangeEventType = 'add' | 'change' | 'unlink' | 'addDir' | 'unlinkDir'
@@ -17,3 +17,8 @@ export type FileChangeEvent = {
   filePath: string
   watchPath: string
 }
+
+export type MCPProgressEvent = {
+  callId: string
+  progress: number // 0-1 range
+}

packages/shared/utils.ts

@@ -0,0 +1,6 @@
+export const defaultAppHeaders = () => {
+  return {
+    'HTTP-Referer': 'https://cherry-ai.com',
+    'X-Title': 'Cherry Studio'
+  }
+}

resources/cherry-studio/license.html

@@ -1,199 +1,274 @@
-<!DOCTYPE html>
+<!doctype html>
 <html lang="zh-CN">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>许可协议 | License Agreement</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+  </head>
 
-<head>
-  <meta charset="UTF-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>许可协议 | License Agreement</title>
-  <script src="https://cdn.tailwindcss.com"></script>
-</head>
+  <body class="bg-gray-50">
+    <div class="mx-auto max-w-4xl px-4 py-8">
+      <!-- 中文版本 -->
+      <div class="mb-12">
+        <h1 class="mb-8 text-3xl font-bold text-gray-900">许可协议</h1>
 
-<body class="bg-gray-50">
-  <div class="max-w-4xl mx-auto px-4 py-8">
-    <!-- 中文版本 -->
-    <div class="mb-12">
-      <h1 class="text-3xl font-bold mb-8 text-gray-900">许可协议</h1>
-
-      <p class="mb-6 text-gray-700">本项目采用<strong>区分用户的双重许可 (User-Segmented Dual Licensing)</strong> 模式。</p>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">核心原则</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li><strong>个人用户 和 10人及以下企业/组织:</strong> 默认适用 <strong>GNU Affero 通用公共许可证 v3.0 (AGPLv3)</strong>。</li>
-          <li><strong>超过10人的企业/组织:</strong> <strong>必须</strong> 获取 <strong>商业许可证 (Commercial License)</strong>。</li>
-        </ul>
-      </section>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">定义："10人及以下"</h2>
-        <p class="text-gray-700">
-          指在您的组织（包括公司、非营利组织、政府机构、教育机构等任何实体）中，能够访问、使用或以任何方式直接或间接受益于本软件（Cherry
-          Studio）功能的个人总数不超过10人。这包括但不限于开发者、测试人员、运营人员、最终用户、通过集成系统间接使用者等。
+        <p class="mb-6 text-gray-700">
+          本项目采用<strong>区分用户的双重许可 (User-Segmented Dual Licensing)</strong> 模式。
         </p>
-      </section>
 
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">1. 开源许可证 (Open Source License): AGPLv3 - 适用于个人及10人及以下组织
-        </h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li>如果您是个人用户，或者您的组织满足上述"10人及以下"的定义，您可以在 <strong>AGPLv3</strong> 的条款下自由使用、修改和分发 Cherry Studio。AGPLv3 的完整文本可以访问
-            <a href="https://www.gnu.org/licenses/agpl-3.0.html"
-              class="text-blue-600 hover:underline">https://www.gnu.org/licenses/agpl-3.0.html</a> 获取。
-          </li>
-          <li><strong>核心义务：</strong> AGPLv3 的一个关键要求是，如果您修改了 Cherry Studio 并通过网络提供服务，或者分发了修改后的版本，您必须以 AGPLv3
-            许可证向接收者提供相应的<strong>完整源代码</strong>。即使您符合"10人及以下"的标准，如果您希望避免此源代码公开义务，您也需要考虑获取商业许可证（见下文）。</li>
-          <li>使用前请务必仔细阅读并理解 AGPLv3 的所有条款。</li>
-        </ul>
-      </section>
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">核心原则</h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              <strong>个人用户 和 10人及以下企业/组织:</strong> 默认适用
+              <strong>GNU Affero 通用公共许可证 v3.0 (AGPLv3)</strong>。
+            </li>
+            <li>
+              <strong>超过10人的企业/组织:</strong> <strong>必须</strong> 获取
+              <strong>商业许可证 (Commercial License)</strong>。
+            </li>
+          </ul>
+        </section>
 
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">2. 商业许可证 (Commercial License) - 适用于超过10人的组织，或希望规避 AGPLv3
-          义务的用户</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li><strong>强制要求：</strong>
-            如果您的组织<strong>不</strong>满足上述"10人及以下"的定义（即有11人或更多人可以访问、使用或受益于本软件），您<strong>必须</strong>联系我们获取并签署一份商业许可证才能使用
-            Cherry Studio。</li>
-          <li><strong>自愿选择：</strong> 即使您的组织满足"10人及以下"的条件，但如果您的使用场景<strong>无法满足 AGPLv3
-              的条款要求</strong>（特别是关于<strong>源代码公开</strong>的义务），或者您需要 AGPLv3 <strong>未提供</strong>的特定商业条款（如保证、赔偿、无 Copyleft
-            限制等），您也<strong>必须</strong>联系我们获取并签署一份商业许可证。</li>
-          <li><strong>需要商业许可证的常见情况包括（但不限于）：</strong>
-            <ul class="list-disc pl-6 mt-2 space-y-1">
-              <li>您的组织规模超过10人。</li>
-              <li>（无论组织规模）您希望分发修改过的 Cherry Studio 版本，但<strong>不希望</strong>根据 AGPLv3 公开您修改部分的源代码。</li>
-              <li>（无论组织规模）您希望基于修改过的 Cherry Studio 提供网络服务（SaaS），但<strong>不希望</strong>根据 AGPLv3 向服务使用者提供修改后的源代码。</li>
-              <li>（无论组织规模）您的公司政策、客户合同或项目要求不允许使用 AGPLv3 许可的软件，或要求闭源分发及保密。</li>
-            </ul>
-          </li>
-          <li><strong>获取商业许可：</strong> 请通过邮箱 <a href="mailto:bd@cherry-ai.com"
-              class="text-blue-600 hover:underline">bd@cherry-ai.com</a> 联系 Cherry Studio 开发团队洽谈商业授权事宜。</li>
-        </ul>
-      </section>
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">定义："10人及以下"</h2>
+          <p class="text-gray-700">
+            指在您的组织（包括公司、非营利组织、政府机构、教育机构等任何实体）中，能够访问、使用或以任何方式直接或间接受益于本软件（Cherry
+            Studio）功能的个人总数不超过10人。这包括但不限于开发者、测试人员、运营人员、最终用户、通过集成系统间接使用者等。
+          </p>
+        </section>
 
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">3. 贡献 (Contributions)</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li>我们欢迎社区对 Cherry Studio 的贡献。所有向本项目提交的贡献都将被视为在 <strong>AGPLv3</strong> 许可证下提供。</li>
-          <li>通过向本项目提交贡献（例如通过 Pull Request），即表示您同意您的代码以 AGPLv3 许可证授权给本项目及所有后续使用者（无论这些使用者最终遵循 AGPLv3 还是商业许可）。</li>
-          <li>您也理解并同意，您的贡献可能会被包含在根据商业许可证分发的 Cherry Studio 版本中。</li>
-        </ul>
-      </section>
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">
+            1. 开源许可证 (Open Source License): AGPLv3 - 适用于个人及10人及以下组织
+          </h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              如果您是个人用户，或者您的组织满足上述"10人及以下"的定义，您可以在
+              <strong>AGPLv3</strong> 的条款下自由使用、修改和分发 Cherry Studio。AGPLv3 的完整文本可以访问
+              <a href="https://www.gnu.org/licenses/agpl-3.0.html" class="text-blue-600 hover:underline"
+                >https://www.gnu.org/licenses/agpl-3.0.html</a
+              >
+              获取。
+            </li>
+            <li>
+              <strong>核心义务：</strong> AGPLv3 的一个关键要求是，如果您修改了 Cherry Studio
+              并通过网络提供服务，或者分发了修改后的版本，您必须以 AGPLv3
+              许可证向接收者提供相应的<strong>完整源代码</strong>。即使您符合"10人及以下"的标准，如果您希望避免此源代码公开义务，您也需要考虑获取商业许可证（见下文）。
+            </li>
+            <li>使用前请务必仔细阅读并理解 AGPLv3 的所有条款。</li>
+          </ul>
+        </section>
 
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">4. 其他条款 (Other Terms)</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li>关于商业许可证的具体条款和条件，以双方签署的正式商业许可协议为准。</li>
-          <li>项目维护者保留根据需要更新本许可政策（包括用户规模定义和阈值）的权利。相关更新将通过项目官方渠道（如代码仓库、官方网站）进行通知。</li>
-        </ul>
-      </section>
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">
+            2. 商业许可证 (Commercial License) - 适用于超过10人的组织，或希望规避 AGPLv3 义务的用户
+          </h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              <strong>强制要求：</strong>
+              如果您的组织<strong>不</strong>满足上述"10人及以下"的定义（即有11人或更多人可以访问、使用或受益于本软件），您<strong>必须</strong>联系我们获取并签署一份商业许可证才能使用
+              Cherry Studio。
+            </li>
+            <li>
+              <strong>自愿选择：</strong> 即使您的组织满足"10人及以下"的条件，但如果您的使用场景<strong
+                >无法满足 AGPLv3 的条款要求</strong
+              >（特别是关于<strong>源代码公开</strong>的义务），或者您需要 AGPLv3
+              <strong>未提供</strong>的特定商业条款（如保证、赔偿、无 Copyleft
+              限制等），您也<strong>必须</strong>联系我们获取并签署一份商业许可证。
+            </li>
+            <li>
+              <strong>需要商业许可证的常见情况包括（但不限于）：</strong>
+              <ul class="mt-2 list-disc space-y-1 pl-6">
+                <li>您的组织规模超过10人。</li>
+                <li>
+                  （无论组织规模）您希望分发修改过的 Cherry Studio 版本，但<strong>不希望</strong>根据 AGPLv3
+                  公开您修改部分的源代码。
+                </li>
+                <li>
+                  （无论组织规模）您希望基于修改过的 Cherry Studio 提供网络服务（SaaS），但<strong>不希望</strong>根据
+                  AGPLv3 向服务使用者提供修改后的源代码。
+                </li>
+                <li>
+                  （无论组织规模）您的公司政策、客户合同或项目要求不允许使用 AGPLv3 许可的软件，或要求闭源分发及保密。
+                </li>
+              </ul>
+            </li>
+            <li>
+              <strong>获取商业许可：</strong> 请通过邮箱
+              <a href="mailto:bd@cherry-ai.com" class="text-blue-600 hover:underline">bd@cherry-ai.com</a> 联系 Cherry
+              Studio 开发团队洽谈商业授权事宜。
+            </li>
+          </ul>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">3. 贡献 (Contributions)</h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              我们欢迎社区对 Cherry Studio 的贡献。所有向本项目提交的贡献都将被视为在
+              <strong>AGPLv3</strong> 许可证下提供。
+            </li>
+            <li>
+              通过向本项目提交贡献（例如通过 Pull Request），即表示您同意您的代码以 AGPLv3
+              许可证授权给本项目及所有后续使用者（无论这些使用者最终遵循 AGPLv3 还是商业许可）。
+            </li>
+            <li>您也理解并同意，您的贡献可能会被包含在根据商业许可证分发的 Cherry Studio 版本中。</li>
+          </ul>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">4. 其他条款 (Other Terms)</h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>关于商业许可证的具体条款和条件，以双方签署的正式商业许可协议为准。</li>
+            <li>
+              项目维护者保留根据需要更新本许可政策（包括用户规模定义和阈值）的权利。相关更新将通过项目官方渠道（如代码仓库、官方网站）进行通知。
+            </li>
+          </ul>
+        </section>
+      </div>
+
+      <hr class="my-12 border-gray-300" />
+
+      <!-- English Version -->
+      <div>
+        <h1 class="mb-8 text-3xl font-bold text-gray-900">Licensing</h1>
+
+        <p class="mb-6 text-gray-700">This project employs a <strong>User-Segmented Dual Licensing</strong> model.</p>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">Core Principle</h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              <strong>Individual Users and Organizations with 10 or Fewer Individuals:</strong> Governed by default
+              under the <strong>GNU Affero General Public License v3.0 (AGPLv3)</strong>.
+            </li>
+            <li>
+              <strong>Organizations with More Than 10 Individuals:</strong> <strong>Must</strong> obtain a
+              <strong>Commercial License</strong>.
+            </li>
+          </ul>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">Definition: "10 or Fewer Individuals"</h2>
+          <p class="text-gray-700">
+            Refers to any organization (including companies, non-profits, government agencies, educational institutions,
+            etc.) where the total number of individuals who can access, use, or in any way directly or indirectly
+            benefit from the functionality of this software (Cherry Studio) does not exceed 10. This includes, but is
+            not limited to, developers, testers, operations staff, end-users, and indirect users via integrated systems.
+          </p>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">
+            1. Open Source License: AGPLv3 - For Individuals and Organizations of 10 or Fewer
+          </h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              If you are an individual user, or if your organization meets the "10 or Fewer Individuals" definition
+              above, you are free to use, modify, and distribute Cherry Studio under the terms of the
+              <strong>AGPLv3</strong>. The full text of the AGPLv3 can be found at
+              <a href="https://www.gnu.org/licenses/agpl-3.0.html" class="text-blue-600 hover:underline"
+                >https://www.gnu.org/licenses/agpl-3.0.html</a
+              >.
+            </li>
+            <li>
+              <strong>Core Obligation:</strong> A key requirement of the AGPLv3 is that if you modify Cherry Studio and
+              make it available over a network, or distribute the modified version, you must provide the
+              <strong>complete corresponding source code</strong> under the AGPLv3 license to the recipients. Even if
+              you qualify under the "10 or Fewer Individuals" rule, if you wish to avoid this source code disclosure
+              obligation, you will need to obtain a Commercial License (see below).
+            </li>
+            <li>Please read and understand the full terms of the AGPLv3 carefully before use.</li>
+          </ul>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">
+            2. Commercial License - For Organizations with More Than 10 Individuals, or Users Needing to Avoid AGPLv3
+            Obligations
+          </h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              <strong>Mandatory Requirement:</strong> If your organization does <strong>not</strong> meet the "10 or
+              Fewer Individuals" definition above (i.e., 11 or more individuals can access, use, or benefit from the
+              software), you <strong>must</strong> contact us to obtain and execute a Commercial License to use Cherry
+              Studio.
+            </li>
+            <li>
+              <strong>Voluntary Option:</strong> Even if your organization meets the "10 or Fewer Individuals"
+              condition, if your intended use case
+              <strong>cannot comply with the terms of the AGPLv3</strong> (particularly the obligations regarding
+              <strong>source code disclosure</strong>), or if you require specific commercial terms
+              <strong>not offered</strong> by the AGPLv3 (such as warranties, indemnities, or freedom from copyleft
+              restrictions), you also <strong>must</strong> contact us to obtain and execute a Commercial License.
+            </li>
+            <li>
+              <strong>Common scenarios requiring a Commercial License include (but are not limited to):</strong>
+              <ul class="mt-2 list-disc space-y-1 pl-6">
+                <li>
+                  Your organization has more than 10 individuals who can access, use, or benefit from the software.
+                </li>
+                <li>
+                  (Regardless of organization size) You wish to distribute a modified version of Cherry Studio but
+                  <strong>do not want</strong> to disclose the source code of your modifications under AGPLv3.
+                </li>
+                <li>
+                  (Regardless of organization size) You wish to provide a network service (SaaS) based on a modified
+                  version of Cherry Studio but <strong>do not want</strong> to provide the modified source code to users
+                  of the service under AGPLv3.
+                </li>
+                <li>
+                  (Regardless of organization size) Your corporate policies, client contracts, or project requirements
+                  prohibit the use of AGPLv3-licensed software or mandate closed-source distribution and
+                  confidentiality.
+                </li>
+              </ul>
+            </li>
+            <li>
+              <strong>Obtaining a Commercial License:</strong> Please contact the Cherry Studio development team via
+              email at <a href="mailto:bd@cherry-ai.com" class="text-blue-600 hover:underline">bd@cherry-ai.com</a> to
+              discuss commercial licensing options.
+            </li>
+          </ul>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">3. Contributions</h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              We welcome community contributions to Cherry Studio. All contributions submitted to this project are
+              considered to be offered under the <strong>AGPLv3</strong> license.
+            </li>
+            <li>
+              By submitting a contribution to this project (e.g., via a Pull Request), you agree to license your code
+              under the AGPLv3 to the project and all its downstream users (regardless of whether those users ultimately
+              operate under AGPLv3 or a Commercial License).
+            </li>
+            <li>
+              You also understand and agree that your contribution may be included in distributions of Cherry Studio
+              offered under our commercial license.
+            </li>
+          </ul>
+        </section>
+
+        <section class="mb-8">
+          <h2 class="mb-4 text-xl font-semibold text-gray-900">4. Other Terms</h2>
+          <ul class="list-disc space-y-2 pl-6 text-gray-700">
+            <li>
+              The specific terms and conditions of the Commercial License are governed by the formal commercial license
+              agreement signed by both parties.
+            </li>
+            <li>
+              The project maintainers reserve the right to update this licensing policy (including the definition and
+              threshold for user count) as needed. Updates will be communicated through official project channels (e.g.,
+              code repository, official website).
+            </li>
+          </ul>
+        </section>
+      </div>
     </div>
-
-    <hr class="my-12 border-gray-300">
-
-    <!-- English Version -->
-    <div>
-      <h1 class="text-3xl font-bold mb-8 text-gray-900">Licensing</h1>
-
-      <p class="mb-6 text-gray-700">This project employs a <strong>User-Segmented Dual Licensing</strong> model.</p>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">Core Principle</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li><strong>Individual Users and Organizations with 10 or Fewer Individuals:</strong> Governed by default
-            under the <strong>GNU Affero General Public License v3.0 (AGPLv3)</strong>.</li>
-          <li><strong>Organizations with More Than 10 Individuals:</strong> <strong>Must</strong> obtain a
-            <strong>Commercial License</strong>.
-          </li>
-        </ul>
-      </section>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">Definition: "10 or Fewer Individuals"</h2>
-        <p class="text-gray-700">
-          Refers to any organization (including companies, non-profits, government agencies, educational institutions,
-          etc.) where the total number of individuals who can access, use, or in any way directly or indirectly benefit
-          from the functionality of this software (Cherry Studio) does not exceed 10. This includes, but is not limited
-          to, developers, testers, operations staff, end-users, and indirect users via integrated systems.
-        </p>
-      </section>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">1. Open Source License: AGPLv3 - For Individuals and
-          Organizations of 10 or Fewer</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li>If you are an individual user, or if your organization meets the "10 or Fewer Individuals" definition
-            above, you are free to use, modify, and distribute Cherry Studio under the terms of the
-            <strong>AGPLv3</strong>. The full text of the AGPLv3 can be found at <a
-              href="https://www.gnu.org/licenses/agpl-3.0.html"
-              class="text-blue-600 hover:underline">https://www.gnu.org/licenses/agpl-3.0.html</a>.
-          </li>
-          <li><strong>Core Obligation:</strong> A key requirement of the AGPLv3 is that if you modify Cherry Studio and
-            make it available over a network, or distribute the modified version, you must provide the <strong>complete
-              corresponding source code</strong> under the AGPLv3 license to the recipients. Even if you qualify under
-            the "10 or Fewer Individuals" rule, if you wish to avoid this source code disclosure obligation, you will
-            need to obtain a Commercial License (see below).</li>
-          <li>Please read and understand the full terms of the AGPLv3 carefully before use.</li>
-        </ul>
-      </section>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">2. Commercial License - For Organizations with More Than 10
-          Individuals, or Users Needing to Avoid AGPLv3 Obligations</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li><strong>Mandatory Requirement:</strong> If your organization does <strong>not</strong> meet the "10 or
-            Fewer Individuals" definition above (i.e., 11 or more individuals can access, use, or benefit from the
-            software), you <strong>must</strong> contact us to obtain and execute a Commercial License to use Cherry
-            Studio.</li>
-          <li><strong>Voluntary Option:</strong> Even if your organization meets the "10 or Fewer Individuals"
-            condition, if your intended use case <strong>cannot comply with the terms of the AGPLv3</strong>
-            (particularly the obligations regarding <strong>source code disclosure</strong>), or if you require specific
-            commercial terms <strong>not offered</strong> by the AGPLv3 (such as warranties, indemnities, or freedom
-            from copyleft restrictions), you also <strong>must</strong> contact us to obtain and execute a Commercial
-            License.</li>
-          <li><strong>Common scenarios requiring a Commercial License include (but are not limited to):</strong>
-            <ul class="list-disc pl-6 mt-2 space-y-1">
-              <li>Your organization has more than 10 individuals who can access, use, or benefit from the software.</li>
-              <li>(Regardless of organization size) You wish to distribute a modified version of Cherry Studio but
-                <strong>do not want</strong> to disclose the source code of your modifications under AGPLv3.
-              </li>
-              <li>(Regardless of organization size) You wish to provide a network service (SaaS) based on a modified
-                version of Cherry Studio but <strong>do not want</strong> to provide the modified source code to users
-                of the service under AGPLv3.</li>
-              <li>(Regardless of organization size) Your corporate policies, client contracts, or project requirements
-                prohibit the use of AGPLv3-licensed software or mandate closed-source distribution and confidentiality.
-              </li>
-            </ul>
-          </li>
-          <li><strong>Obtaining a Commercial License:</strong> Please contact the Cherry Studio development team via
-            email at <a href="mailto:bd@cherry-ai.com" class="text-blue-600 hover:underline">bd@cherry-ai.com</a> to
-            discuss commercial licensing options.</li>
-        </ul>
-      </section>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">3. Contributions</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li>We welcome community contributions to Cherry Studio. All contributions submitted to this project are
-            considered to be offered under the <strong>AGPLv3</strong> license.</li>
-          <li>By submitting a contribution to this project (e.g., via a Pull Request), you agree to license your code
-            under the AGPLv3 to the project and all its downstream users (regardless of whether those users ultimately
-            operate under AGPLv3 or a Commercial License).</li>
-          <li>You also understand and agree that your contribution may be included in distributions of Cherry Studio
-            offered under our commercial license.</li>
-        </ul>
-      </section>
-
-      <section class="mb-8">
-        <h2 class="text-xl font-semibold mb-4 text-gray-900">4. Other Terms</h2>
-        <ul class="list-disc pl-6 space-y-2 text-gray-700">
-          <li>The specific terms and conditions of the Commercial License are governed by the formal commercial license
-            agreement signed by both parties.</li>
-          <li>The project maintainers reserve the right to update this licensing policy (including the definition and
-            threshold for user count) as needed. Updates will be communicated through official project channels (e.g.,
-            code repository, official website).</li>
-        </ul>
-      </section>
-    </div>
-  </div>
-</body>
-
-</html>
+  </body>
+</html>

resources/cherry-studio/releases.html

@@ -12,18 +12,18 @@
 
   <body id="app">
     <div :class="isDark ? 'dark-bg' : 'bg'" class="min-h-screen">
-      <div class="max-w-3xl mx-auto py-12 px-4">
-        <h1 class="text-3xl font-bold mb-8" :class="isDark ? 'text-white' : 'text-gray-900'">Release Timeline</h1>
+      <div class="mx-auto max-w-3xl px-4 py-12">
+        <h1 class="mb-8 text-3xl font-bold" :class="isDark ? 'text-white' : 'text-gray-900'">Release Timeline</h1>
 
         <!-- Loading状态 -->
-        <div v-if="loading" class="text-center py-8">
+        <div v-if="loading" class="py-8 text-center">
           <div
-            class="inline-block animate-spin rounded-full h-8 w-8 border-4"
+            class="inline-block h-8 w-8 animate-spin rounded-full border-4"
             :class="isDark ? 'border-gray-700 border-t-blue-500' : 'border-gray-300 border-t-blue-500'"></div>
         </div>
 
         <!-- Error 状态 -->
-        <div v-else-if="error" class="text-red-500 text-center py-8">{{ error }}</div>
+        <div v-else-if="error" class="py-8 text-center text-red-500">{{ error }}</div>
 
         <!-- Release 列表 -->
         <div v-else class="space-y-8">
@@ -32,21 +32,21 @@
             :key="release.id"
             class="relative pl-8"
             :class="isDark ? 'border-l-2 border-gray-700' : 'border-l-2 border-gray-200'">
-            <div class="absolute -left-2 top-0 w-4 h-4 rounded-full bg-green-500"></div>
+            <div class="absolute top-0 -left-2 h-4 w-4 rounded-full bg-green-500"></div>
             <div
-              class="rounded-lg shadow-sm p-6 transition-shadow"
+              class="rounded-lg p-6 shadow-sm transition-shadow"
               :class="isDark ? 'bg-black hover:shadow-md hover:shadow-black' : 'bg-white hover:shadow-md'">
-              <div class="flex items-start justify-between mb-4">
+              <div class="mb-4 flex items-start justify-between">
                 <div>
                   <h2 class="text-xl font-semibold" :class="isDark ? 'text-white' : 'text-gray-900'">
                     {{ release.name || release.tag_name }}
                   </h2>
-                  <p class="text-sm mt-1" :class="isDark ? 'text-gray-400' : 'text-gray-500'">
+                  <p class="mt-1 text-sm" :class="isDark ? 'text-gray-400' : 'text-gray-500'">
                     {{ formatDate(release.published_at) }}
                   </p>
                 </div>
                 <span
-                  class="inline-flex items-center px-3 py-1 rounded-full text-sm font-medium"
+                  class="inline-flex items-center rounded-full px-3 py-1 text-sm font-medium"
                   :class="isDark ? 'bg-green-900 text-green-200' : 'bg-green-100 text-green-800'">
                   {{ release.tag_name }}
                 </span>

resources/database/drizzle/0000_confused_wendigo.sql

@@ -0,0 +1,53 @@
+--> statement-breakpoint
+CREATE TABLE `migrations` (
+	`version` integer PRIMARY KEY NOT NULL,
+	`tag` text NOT NULL,
+	`executed_at` integer NOT NULL
+);
+
+CREATE TABLE `agents` (
+	`id` text PRIMARY KEY NOT NULL,
+	`type` text NOT NULL,
+	`name` text NOT NULL,
+	`description` text,
+	`accessible_paths` text,
+	`instructions` text,
+	`model` text NOT NULL,
+	`plan_model` text,
+	`small_model` text,
+	`mcps` text,
+	`allowed_tools` text,
+	`configuration` text,
+	`created_at` text NOT NULL,
+	`updated_at` text NOT NULL
+);
+
+--> statement-breakpoint
+CREATE TABLE `sessions` (
+	`id` text PRIMARY KEY NOT NULL,
+	`agent_type` text NOT NULL,
+	`agent_id` text NOT NULL,
+	`name` text NOT NULL,
+	`description` text,
+	`accessible_paths` text,
+	`instructions` text,
+	`model` text NOT NULL,
+	`plan_model` text,
+	`small_model` text,
+	`mcps` text,
+	`allowed_tools` text,
+	`configuration` text,
+	`created_at` text NOT NULL,
+	`updated_at` text NOT NULL
+);
+
+--> statement-breakpoint
+CREATE TABLE `session_messages` (
+	`id` integer PRIMARY KEY AUTOINCREMENT NOT NULL,
+	`session_id` text NOT NULL,
+	`role` text NOT NULL,
+	`content` text NOT NULL,
+	`metadata` text,
+	`created_at` text NOT NULL,
+	`updated_at` text NOT NULL
+);

resources/database/drizzle/0001_woozy_captain_flint.sql

@@ -0,0 +1 @@
+ALTER TABLE `session_messages` ADD `agent_session_id` text DEFAULT '';

resources/database/drizzle/meta/0000_snapshot.json

@@ -0,0 +1,331 @@
+{
+  "version": "6",
+  "dialect": "sqlite",
+  "id": "35efb412-0230-4767-9c76-7b7c4d40369f",
+  "prevId": "00000000-0000-0000-0000-000000000000",
+  "tables": {
+    "agents": {
+      "name": "agents",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "type": {
+          "name": "type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "accessible_paths": {
+          "name": "accessible_paths",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "instructions": {
+          "name": "instructions",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "model": {
+          "name": "model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "plan_model": {
+          "name": "plan_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "small_model": {
+          "name": "small_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "mcps": {
+          "name": "mcps",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "allowed_tools": {
+          "name": "allowed_tools",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "configuration": {
+          "name": "configuration",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "created_at": {
+          "name": "created_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "updated_at": {
+          "name": "updated_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "session_messages": {
+      "name": "session_messages",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "integer",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": true
+        },
+        "session_id": {
+          "name": "session_id",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "role": {
+          "name": "role",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "content": {
+          "name": "content",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "metadata": {
+          "name": "metadata",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "created_at": {
+          "name": "created_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "updated_at": {
+          "name": "updated_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "migrations": {
+      "name": "migrations",
+      "columns": {
+        "version": {
+          "name": "version",
+          "type": "integer",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "tag": {
+          "name": "tag",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "executed_at": {
+          "name": "executed_at",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "sessions": {
+      "name": "sessions",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "agent_type": {
+          "name": "agent_type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "agent_id": {
+          "name": "agent_id",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "accessible_paths": {
+          "name": "accessible_paths",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "instructions": {
+          "name": "instructions",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "model": {
+          "name": "model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "plan_model": {
+          "name": "plan_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "small_model": {
+          "name": "small_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "mcps": {
+          "name": "mcps",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "allowed_tools": {
+          "name": "allowed_tools",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "configuration": {
+          "name": "configuration",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "created_at": {
+          "name": "created_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "updated_at": {
+          "name": "updated_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    }
+  },
+  "views": {},
+  "enums": {},
+  "_meta": {
+    "schemas": {},
+    "tables": {},
+    "columns": {}
+  },
+  "internal": {
+    "indexes": {}
+  }
+}

resources/database/drizzle/meta/0001_snapshot.json

@@ -0,0 +1,339 @@
+{
+  "version": "6",
+  "dialect": "sqlite",
+  "id": "dabab6db-a2cd-4e96-b06e-6cb87d445a87",
+  "prevId": "35efb412-0230-4767-9c76-7b7c4d40369f",
+  "tables": {
+    "agents": {
+      "name": "agents",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "type": {
+          "name": "type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "accessible_paths": {
+          "name": "accessible_paths",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "instructions": {
+          "name": "instructions",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "model": {
+          "name": "model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "plan_model": {
+          "name": "plan_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "small_model": {
+          "name": "small_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "mcps": {
+          "name": "mcps",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "allowed_tools": {
+          "name": "allowed_tools",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "configuration": {
+          "name": "configuration",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "created_at": {
+          "name": "created_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "updated_at": {
+          "name": "updated_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "session_messages": {
+      "name": "session_messages",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "integer",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": true
+        },
+        "session_id": {
+          "name": "session_id",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "role": {
+          "name": "role",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "content": {
+          "name": "content",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "agent_session_id": {
+          "name": "agent_session_id",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false,
+          "default": "''"
+        },
+        "metadata": {
+          "name": "metadata",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "created_at": {
+          "name": "created_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "updated_at": {
+          "name": "updated_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "migrations": {
+      "name": "migrations",
+      "columns": {
+        "version": {
+          "name": "version",
+          "type": "integer",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "tag": {
+          "name": "tag",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "executed_at": {
+          "name": "executed_at",
+          "type": "integer",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    },
+    "sessions": {
+      "name": "sessions",
+      "columns": {
+        "id": {
+          "name": "id",
+          "type": "text",
+          "primaryKey": true,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "agent_type": {
+          "name": "agent_type",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "agent_id": {
+          "name": "agent_id",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "name": {
+          "name": "name",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "description": {
+          "name": "description",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "accessible_paths": {
+          "name": "accessible_paths",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "instructions": {
+          "name": "instructions",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "model": {
+          "name": "model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "plan_model": {
+          "name": "plan_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "small_model": {
+          "name": "small_model",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "mcps": {
+          "name": "mcps",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "allowed_tools": {
+          "name": "allowed_tools",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "configuration": {
+          "name": "configuration",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": false,
+          "autoincrement": false
+        },
+        "created_at": {
+          "name": "created_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        },
+        "updated_at": {
+          "name": "updated_at",
+          "type": "text",
+          "primaryKey": false,
+          "notNull": true,
+          "autoincrement": false
+        }
+      },
+      "indexes": {},
+      "foreignKeys": {},
+      "compositePrimaryKeys": {},
+      "uniqueConstraints": {},
+      "checkConstraints": {}
+    }
+  },
+  "views": {},
+  "enums": {},
+  "_meta": {
+    "schemas": {},
+    "tables": {},
+    "columns": {}
+  },
+  "internal": {
+    "indexes": {}
+  }
+}

resources/database/drizzle/meta/_journal.json

@@ -0,0 +1,20 @@
+{
+  "version": "7",
+  "dialect": "sqlite",
+  "entries": [
+    {
+      "idx": 0,
+      "version": "6",
+      "when": 1758091173882,
+      "tag": "0000_confused_wendigo",
+      "breakpoints": true
+    },
+    {
+      "idx": 1,
+      "version": "6",
+      "when": 1758187378775,
+      "tag": "0001_woozy_captain_flint",
+      "breakpoints": true
+    }
+  ]
+}

scripts/auto-translate-i18n.ts

@@ -9,8 +9,9 @@ import * as path from 'path'
 
 const localesDir = path.join(__dirname, '../src/renderer/src/i18n/locales')
 const translateDir = path.join(__dirname, '../src/renderer/src/i18n/translate')
-const baseLocale = 'zh-cn'
+const baseLocale = process.env.BASE_LOCALE ?? 'zh-cn'
 const baseFileName = `${baseLocale}.json`
+const baseLocalePath = path.join(__dirname, '../src/renderer/src/i18n/locales', baseFileName)
 
 type I18NValue = string | { [key: string]: I18NValue }
 type I18N = { [key: string]: I18NValue }
@@ -105,6 +106,9 @@ const translateRecursively = async (originObj: I18N, systemPrompt: string): Prom
 }
 
 const main = async () => {
+  if (!fs.existsSync(baseLocalePath)) {
+    throw new Error(`${baseLocalePath} not found.`)
+  }
   const localeFiles = fs
     .readdirSync(localesDir)
     .filter((file) => file.endsWith('.json') && file !== baseFileName)

scripts/before-pack.js

@@ -35,6 +35,9 @@ const allX64 = {
   '@napi-rs/system-ocr-win32-x64-msvc': '1.0.2'
 }
 
+const claudeCodeVenderPath = '@anthropic-ai/claude-code/vendor'
+const claudeCodeVenders = ['arm64-darwin', 'arm64-linux', 'x64-darwin', 'x64-linux', 'x64-win32']
+
 const platformToArch = {
   mac: 'darwin',
   windows: 'win32',
@@ -46,9 +49,6 @@ exports.default = async function (context) {
   const archType = arch === Arch.arm64 ? 'arm64' : 'x64'
   const platform = context.packager.platform.name
 
-  const arm64Filters = Object.keys(allArm64).map((f) => '!node_modules/' + f + '/**')
-  const x64Filters = Object.keys(allX64).map((f) => '!node_modules/' + f + '/*')
-
   const downloadPackages = async (packages) => {
     console.log('downloading packages ......')
     const downloadPromises = []
@@ -67,25 +67,39 @@ exports.default = async function (context) {
     await Promise.all(downloadPromises)
   }
 
-  const changeFilters = async (packages, filtersToExclude, filtersToInclude) => {
-    await downloadPackages(packages)
+  const changeFilters = async (filtersToExclude, filtersToInclude) => {
     // remove filters for the target architecture (allow inclusion)
-
     let filters = context.packager.config.files[0].filter
     filters = filters.filter((filter) => !filtersToInclude.includes(filter))
+
     // add filters for other architectures (exclude them)
     filters.push(...filtersToExclude)
 
     context.packager.config.files[0].filter = filters
   }
 
-  if (arch === Arch.arm64) {
-    await changeFilters(allArm64, x64Filters, arm64Filters)
-    return
-  }
+  await downloadPackages(arch === Arch.arm64 ? allArm64 : allX64)
 
-  if (arch === Arch.x64) {
-    await changeFilters(allX64, arm64Filters, x64Filters)
-    return
+  const arm64Filters = Object.keys(allArm64).map((f) => '!node_modules/' + f + '/**')
+  const x64Filters = Object.keys(allX64).map((f) => '!node_modules/' + f + '/*')
+  const excludeClaudeCodeRipgrepFilters = claudeCodeVenders
+    .filter((f) => f !== `${archType}-${platformToArch[platform]}`)
+    .map((f) => '!node_modules/' + claudeCodeVenderPath + '/ripgrep/' + f + '/**')
+  const excludeClaudeCodeJBPlutins = ['!node_modules/' + claudeCodeVenderPath + '/' + 'claude-code-jetbrains-plugin']
+
+  const includeClaudeCodeFilters = [
+    '!node_modules/' + claudeCodeVenderPath + '/' + `${archType}-${platformToArch[platform]}/**`
+  ]
+
+  if (arch === Arch.arm64) {
+    await changeFilters(
+      [...x64Filters, ...excludeClaudeCodeRipgrepFilters, ...excludeClaudeCodeJBPlutins],
+      [...arm64Filters, ...includeClaudeCodeFilters]
+    )
+  } else {
+    await changeFilters(
+      [...arm64Filters, ...excludeClaudeCodeRipgrepFilters, ...excludeClaudeCodeJBPlutins],
+      [...x64Filters, ...includeClaudeCodeFilters]
+    )
   }
 }

scripts/check-i18n.ts

@@ -4,7 +4,7 @@ import * as path from 'path'
 import { sortedObjectByKeys } from './sort'
 
 const translationsDir = path.join(__dirname, '../src/renderer/src/i18n/locales')
-const baseLocale = 'zh-cn'
+const baseLocale = process.env.BASE_LOCALE ?? 'zh-cn'
 const baseFileName = `${baseLocale}.json`
 const baseFilePath = path.join(translationsDir, baseFileName)
 

scripts/sync-i18n.ts

@@ -5,7 +5,7 @@ import { sortedObjectByKeys } from './sort'
 
 const localesDir = path.join(__dirname, '../src/renderer/src/i18n/locales')
 const translateDir = path.join(__dirname, '../src/renderer/src/i18n/translate')
-const baseLocale = 'zh-cn'
+const baseLocale = process.env.BASE_LOCALE ?? 'zh-cn'
 const baseFileName = `${baseLocale}.json`
 const baseFilePath = path.join(localesDir, baseFileName)
 

scripts/update-languages.ts

@@ -1,6 +1,6 @@
 import { exec } from 'child_process'
 import * as fs from 'fs/promises'
-import linguistLanguages from 'linguist-languages'
+import * as linguistLanguages from 'linguist-languages'
 import * as path from 'path'
 import { promisify } from 'util'
 
@@ -75,17 +75,17 @@ export const languages: Record<string, LanguageData> = ${languagesObjectString};
 }
 
 /**
- * Formats a file using Prettier.
+ * Formats a file using Biome.
  * @param filePath The path to the file to format.
  */
-async function formatWithPrettier(filePath: string): Promise<void> {
-  console.log('🎨 Formatting file with Prettier...')
+async function format(filePath: string): Promise<void> {
+  console.log('🎨 Formatting file with Biome...')
   try {
-    await execAsync(`yarn prettier --write ${filePath}`)
-    console.log('✅ Prettier formatting complete.')
+    await execAsync(`yarn biome format --write ${filePath}`)
+    console.log('✅ Biome formatting complete.')
   } catch (e: any) {
-    console.error('❌ Prettier formatting failed:', e.stdout || e.stderr)
-    throw new Error('Prettier formatting failed.')
+    console.error('❌ Biome formatting failed:', e.stdout || e.stderr)
+    throw new Error('Biome formatting failed.')
   }
 }
 
@@ -116,7 +116,7 @@ async function updateLanguagesFile(): Promise<void> {
     await fs.writeFile(LANGUAGES_FILE_PATH, fileContent, 'utf-8')
     console.log(`✅ Successfully wrote to ${LANGUAGES_FILE_PATH}`)
 
-    await formatWithPrettier(LANGUAGES_FILE_PATH)
+    await format(LANGUAGES_FILE_PATH)
     await checkTypeScript(LANGUAGES_FILE_PATH)
 
     console.log('🎉 Successfully updated languages.ts file!')

src/main/apiServer/app.ts

@@ -0,0 +1,129 @@
+import { loggerService } from '@main/services/LoggerService'
+import cors from 'cors'
+import express from 'express'
+import { v4 as uuidv4 } from 'uuid'
+
+import { authMiddleware } from './middleware/auth'
+import { errorHandler } from './middleware/error'
+import { setupOpenAPIDocumentation } from './middleware/openapi'
+import { agentsRoutes } from './routes/agents'
+import { chatRoutes } from './routes/chat'
+import { mcpRoutes } from './routes/mcp'
+import { messagesRoutes } from './routes/messages'
+import { modelsRoutes } from './routes/models'
+
+const logger = loggerService.withContext('ApiServer')
+
+const app = express()
+
+// Global middleware
+app.use((req, res, next) => {
+  const start = Date.now()
+  res.on('finish', () => {
+    const duration = Date.now() - start
+    logger.info(`${req.method} ${req.path} - ${res.statusCode} - ${duration}ms`)
+  })
+  next()
+})
+
+app.use((_req, res, next) => {
+  res.setHeader('X-Request-ID', uuidv4())
+  next()
+})
+
+app.use(
+  cors({
+    origin: '*',
+    allowedHeaders: ['Content-Type', 'Authorization'],
+    methods: ['GET', 'POST', 'PUT', 'DELETE', 'OPTIONS']
+  })
+)
+
+/**
+ * @swagger
+ * /health:
+ *   get:
+ *     summary: Health check endpoint
+ *     description: Check server status (no authentication required)
+ *     tags: [Health]
+ *     security: []
+ *     responses:
+ *       200:
+ *         description: Server is healthy
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 status:
+ *                   type: string
+ *                   example: ok
+ *                 timestamp:
+ *                   type: string
+ *                   format: date-time
+ *                 version:
+ *                   type: string
+ *                   example: 1.0.0
+ */
+app.get('/health', (_req, res) => {
+  res.json({
+    status: 'ok',
+    timestamp: new Date().toISOString(),
+    version: process.env.npm_package_version || '1.0.0'
+  })
+})
+
+/**
+ * @swagger
+ * /:
+ *   get:
+ *     summary: API information
+ *     description: Get basic API information and available endpoints
+ *     tags: [General]
+ *     security: []
+ *     responses:
+ *       200:
+ *         description: API information
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 name:
+ *                   type: string
+ *                   example: Cherry Studio API
+ *                 version:
+ *                   type: string
+ *                   example: 1.0.0
+ *                 endpoints:
+ *                   type: object
+ */
+app.get('/', (_req, res) => {
+  res.json({
+    name: 'Cherry Studio API',
+    version: '1.0.0',
+    endpoints: {
+      health: 'GET /health'
+    }
+  })
+})
+
+// API v1 routes with auth
+const apiRouter = express.Router()
+apiRouter.use(authMiddleware)
+apiRouter.use(express.json())
+// Mount routes
+apiRouter.use('/chat', chatRoutes)
+apiRouter.use('/mcps', mcpRoutes)
+apiRouter.use('/messages', messagesRoutes)
+apiRouter.use('/models', modelsRoutes)
+apiRouter.use('/agents', agentsRoutes)
+app.use('/v1', apiRouter)
+
+// Setup OpenAPI documentation
+setupOpenAPIDocumentation(app)
+
+// Error handling (must be last)
+app.use(errorHandler)
+
+export { app }

src/main/apiServer/config.ts

@@ -0,0 +1,65 @@
+import { ApiServerConfig } from '@types'
+import { v4 as uuidv4 } from 'uuid'
+
+import { loggerService } from '../services/LoggerService'
+import { reduxService } from '../services/ReduxService'
+
+const logger = loggerService.withContext('ApiServerConfig')
+
+const defaultHost = 'localhost'
+const defaultPort = 23333
+
+class ConfigManager {
+  private _config: ApiServerConfig | null = null
+
+  private generateApiKey(): string {
+    return `cs-sk-${uuidv4()}`
+  }
+
+  async load(): Promise<ApiServerConfig> {
+    try {
+      const settings = await reduxService.select('state.settings')
+      const serverSettings = settings?.apiServer
+      let apiKey = serverSettings?.apiKey
+      if (!apiKey || apiKey.trim() === '') {
+        apiKey = this.generateApiKey()
+        await reduxService.dispatch({
+          type: 'settings/setApiServerApiKey',
+          payload: apiKey
+        })
+      }
+      this._config = {
+        enabled: serverSettings?.enabled ?? false,
+        port: serverSettings?.port ?? defaultPort,
+        host: defaultHost,
+        apiKey: apiKey
+      }
+      return this._config
+    } catch (error: any) {
+      logger.warn('Failed to load config from Redux, using defaults:', error)
+      this._config = {
+        enabled: false,
+        port: defaultPort,
+        host: defaultHost,
+        apiKey: this.generateApiKey()
+      }
+      return this._config
+    }
+  }
+
+  async get(): Promise<ApiServerConfig> {
+    if (!this._config) {
+      await this.load()
+    }
+    if (!this._config) {
+      throw new Error('Failed to load API server configuration')
+    }
+    return this._config
+  }
+
+  async reload(): Promise<ApiServerConfig> {
+    return await this.load()
+  }
+}
+
+export const config = new ConfigManager()

src/main/apiServer/index.ts

@@ -0,0 +1,2 @@
+export { config } from './config'
+export { apiServer } from './server'

src/main/apiServer/middleware/auth.ts

@@ -0,0 +1,62 @@
+import crypto from 'crypto'
+import { NextFunction, Request, Response } from 'express'
+
+import { config } from '../config'
+
+export const authMiddleware = async (req: Request, res: Response, next: NextFunction) => {
+  const auth = req.header('Authorization') || ''
+  const xApiKey = req.header('x-api-key') || ''
+
+  // Fast rejection if neither credential header provided
+  if (!auth && !xApiKey) {
+    return res.status(401).json({ error: 'Unauthorized: missing credentials' })
+  }
+
+  let token: string | undefined
+
+  // Prefer Bearer if well‑formed
+  if (auth) {
+    const trimmed = auth.trim()
+    const bearerPrefix = /^Bearer\s+/i
+    if (bearerPrefix.test(trimmed)) {
+      const candidate = trimmed.replace(bearerPrefix, '').trim()
+      if (!candidate) {
+        return res.status(401).json({ error: 'Unauthorized: empty bearer token' })
+      }
+      token = candidate
+    }
+  }
+
+  // Fallback to x-api-key if token still not resolved
+  if (!token && xApiKey) {
+    if (!xApiKey.trim()) {
+      return res.status(401).json({ error: 'Unauthorized: empty x-api-key' })
+    }
+    token = xApiKey.trim()
+  }
+
+  if (!token) {
+    // At this point we had at least one header, but none yielded a usable token
+    return res.status(401).json({ error: 'Unauthorized: invalid credentials format' })
+  }
+
+  const { apiKey } = await config.get()
+
+  if (!apiKey) {
+    // If server not configured, treat as forbidden (or could be 500). Choose 403 to avoid leaking config state.
+    return res.status(403).json({ error: 'Forbidden' })
+  }
+
+  // Timing-safe compare when lengths match, else immediate forbidden
+  if (token.length !== apiKey.length) {
+    return res.status(403).json({ error: 'Forbidden' })
+  }
+
+  const tokenBuf = Buffer.from(token)
+  const keyBuf = Buffer.from(apiKey)
+  if (!crypto.timingSafeEqual(tokenBuf, keyBuf)) {
+    return res.status(403).json({ error: 'Forbidden' })
+  }
+
+  return next()
+}

src/main/apiServer/middleware/error.ts

@@ -0,0 +1,21 @@
+import { NextFunction, Request, Response } from 'express'
+
+import { loggerService } from '../../services/LoggerService'
+
+const logger = loggerService.withContext('ApiServerErrorHandler')
+
+// oxlint-disable-next-line @typescript-eslint/no-unused-vars
+export const errorHandler = (err: Error, _req: Request, res: Response, _next: NextFunction) => {
+  logger.error('API Server Error:', err)
+
+  // Don't expose internal errors in production
+  const isDev = process.env.NODE_ENV === 'development'
+
+  res.status(500).json({
+    error: {
+      message: isDev ? err.message : 'Internal server error',
+      type: 'server_error',
+      ...(isDev && { stack: err.stack })
+    }
+  })
+}

src/main/apiServer/middleware/openapi.ts

@@ -0,0 +1,206 @@
+import { Express } from 'express'
+import swaggerJSDoc from 'swagger-jsdoc'
+import swaggerUi from 'swagger-ui-express'
+
+import { loggerService } from '../../services/LoggerService'
+
+const logger = loggerService.withContext('OpenAPIMiddleware')
+
+const swaggerOptions: swaggerJSDoc.Options = {
+  definition: {
+    openapi: '3.0.0',
+    info: {
+      title: 'Cherry Studio API',
+      version: '1.0.0',
+      description: 'OpenAI-compatible API for Cherry Studio with additional Cherry-specific endpoints',
+      contact: {
+        name: 'Cherry Studio',
+        url: 'https://github.com/CherryHQ/cherry-studio'
+      }
+    },
+    servers: [
+      {
+        url: 'http://localhost:23333',
+        description: 'Local development server'
+      }
+    ],
+    components: {
+      securitySchemes: {
+        BearerAuth: {
+          type: 'http',
+          scheme: 'bearer',
+          bearerFormat: 'JWT',
+          description: 'Use the API key from Cherry Studio settings'
+        }
+      },
+      schemas: {
+        Error: {
+          type: 'object',
+          properties: {
+            error: {
+              type: 'object',
+              properties: {
+                message: { type: 'string' },
+                type: { type: 'string' },
+                code: { type: 'string' }
+              }
+            }
+          }
+        },
+        ChatMessage: {
+          type: 'object',
+          properties: {
+            role: {
+              type: 'string',
+              enum: ['system', 'user', 'assistant', 'tool']
+            },
+            content: {
+              oneOf: [
+                { type: 'string' },
+                {
+                  type: 'array',
+                  items: {
+                    type: 'object',
+                    properties: {
+                      type: { type: 'string' },
+                      text: { type: 'string' },
+                      image_url: {
+                        type: 'object',
+                        properties: {
+                          url: { type: 'string' }
+                        }
+                      }
+                    }
+                  }
+                }
+              ]
+            },
+            name: { type: 'string' },
+            tool_calls: {
+              type: 'array',
+              items: {
+                type: 'object',
+                properties: {
+                  id: { type: 'string' },
+                  type: { type: 'string' },
+                  function: {
+                    type: 'object',
+                    properties: {
+                      name: { type: 'string' },
+                      arguments: { type: 'string' }
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        ChatCompletionRequest: {
+          type: 'object',
+          required: ['model', 'messages'],
+          properties: {
+            model: {
+              type: 'string',
+              description: 'The model to use for completion, in format provider:model-id'
+            },
+            messages: {
+              type: 'array',
+              items: { $ref: '#/components/schemas/ChatMessage' }
+            },
+            temperature: {
+              type: 'number',
+              minimum: 0,
+              maximum: 2,
+              default: 1
+            },
+            max_tokens: {
+              type: 'integer',
+              minimum: 1
+            },
+            stream: {
+              type: 'boolean',
+              default: false
+            },
+            tools: {
+              type: 'array',
+              items: {
+                type: 'object',
+                properties: {
+                  type: { type: 'string' },
+                  function: {
+                    type: 'object',
+                    properties: {
+                      name: { type: 'string' },
+                      description: { type: 'string' },
+                      parameters: { type: 'object' }
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        Model: {
+          type: 'object',
+          properties: {
+            id: { type: 'string' },
+            object: { type: 'string', enum: ['model'] },
+            created: { type: 'integer' },
+            owned_by: { type: 'string' }
+          }
+        },
+        MCPServer: {
+          type: 'object',
+          properties: {
+            id: { type: 'string' },
+            name: { type: 'string' },
+            command: { type: 'string' },
+            args: {
+              type: 'array',
+              items: { type: 'string' }
+            },
+            env: { type: 'object' },
+            disabled: { type: 'boolean' }
+          }
+        }
+      }
+    },
+    security: [
+      {
+        BearerAuth: []
+      }
+    ]
+  },
+  apis: ['./src/main/apiServer/routes/*.ts', './src/main/apiServer/app.ts']
+}
+
+export function setupOpenAPIDocumentation(app: Express) {
+  try {
+    const specs = swaggerJSDoc(swaggerOptions)
+
+    // Serve OpenAPI JSON
+    app.get('/api-docs.json', (_req, res) => {
+      res.setHeader('Content-Type', 'application/json')
+      res.send(specs)
+    })
+
+    // Serve Swagger UI
+    app.use(
+      '/api-docs',
+      swaggerUi.serve,
+      swaggerUi.setup(specs, {
+        customCss: `
+        .swagger-ui .topbar { display: none; }
+        .swagger-ui .info .title { color: #1890ff; }
+      `,
+        customSiteTitle: 'Cherry Studio API Documentation'
+      })
+    )
+
+    logger.info('OpenAPI documentation setup complete')
+    logger.info('Documentation available at /api-docs')
+    logger.info('OpenAPI spec available at /api-docs.json')
+  } catch (error) {
+    logger.error('Failed to setup OpenAPI documentation:', error as Error)
+  }
+}

src/main/apiServer/routes/agents/handlers/agents.ts

@@ -0,0 +1,532 @@
+import { loggerService } from '@logger'
+import { AgentModelValidationError, agentService } from '@main/services/agents'
+import { ListAgentsResponse,type ReplaceAgentRequest, type UpdateAgentRequest } from '@types'
+import { Request, Response } from 'express'
+
+import type { ValidationRequest } from '../validators/zodValidator'
+
+const logger = loggerService.withContext('ApiServerAgentsHandlers')
+
+const modelValidationErrorBody = (error: AgentModelValidationError) => ({
+  error: {
+    message: `Invalid ${error.context.field}: ${error.detail.message}`,
+    type: 'invalid_request_error',
+    code: error.detail.code
+  }
+})
+
+/**
+ * @swagger
+ * /v1/agents:
+ *   post:
+ *     summary: Create a new agent
+ *     description: Creates a new autonomous agent with the specified configuration
+ *     tags: [Agents]
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             $ref: '#/components/schemas/CreateAgentRequest'
+ *     responses:
+ *       201:
+ *         description: Agent created successfully
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       400:
+ *         description: Validation error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+export const createAgent = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    logger.info('Creating new agent')
+    logger.debug('Agent data:', req.body)
+
+    const agent = await agentService.createAgent(req.body)
+
+    logger.info(`Agent created successfully: ${agent.id}`)
+    return res.status(201).json(agent)
+  } catch (error: any) {
+    if (error instanceof AgentModelValidationError) {
+      logger.warn('Agent model validation error during create:', {
+        agentType: error.context.agentType,
+        field: error.context.field,
+        model: error.context.model,
+        detail: error.detail
+      })
+      return res.status(400).json(modelValidationErrorBody(error))
+    }
+
+    logger.error('Error creating agent:', error)
+    return res.status(500).json({
+      error: {
+        message: `Failed to create agent: ${error.message}`,
+        type: 'internal_error',
+        code: 'agent_creation_failed'
+      }
+    })
+  }
+}
+
+/**
+ * @swagger
+ * /v1/agents:
+ *   get:
+ *     summary: List all agents
+ *     description: Retrieves a paginated list of all agents
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: query
+ *         name: limit
+ *         schema:
+ *           type: integer
+ *           minimum: 1
+ *           maximum: 100
+ *           default: 20
+ *         description: Number of agents to return
+ *       - in: query
+ *         name: offset
+ *         schema:
+ *           type: integer
+ *           minimum: 0
+ *           default: 0
+ *         description: Number of agents to skip
+ *     responses:
+ *       200:
+ *         description: List of agents
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 data:
+ *                   type: array
+ *                   items:
+ *                     $ref: '#/components/schemas/AgentEntity'
+ *                 total:
+ *                   type: integer
+ *                   description: Total number of agents
+ *                 limit:
+ *                   type: integer
+ *                   description: Number of agents returned
+ *                 offset:
+ *                   type: integer
+ *                   description: Number of agents skipped
+ *       400:
+ *         description: Validation error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+export const listAgents = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const limit = req.query.limit ? parseInt(req.query.limit as string) : 20
+    const offset = req.query.offset ? parseInt(req.query.offset as string) : 0
+
+    logger.info(`Listing agents with limit=${limit}, offset=${offset}`)
+
+    const result = await agentService.listAgents({ limit, offset })
+
+    logger.info(`Retrieved ${result.agents.length} agents (total: ${result.total})`)
+    return res.json({
+      data: result.agents,
+      total: result.total,
+      limit,
+      offset
+    } satisfies ListAgentsResponse)
+  } catch (error: any) {
+    logger.error('Error listing agents:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to list agents',
+        type: 'internal_error',
+        code: 'agent_list_failed'
+      }
+    })
+  }
+}
+
+/**
+ * @swagger
+ * /v1/agents/{agentId}:
+ *   get:
+ *     summary: Get agent by ID
+ *     description: Retrieves a specific agent by its ID
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     responses:
+ *       200:
+ *         description: Agent details
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+export const getAgent = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const { agentId } = req.params
+    logger.info(`Getting agent: ${agentId}`)
+
+    const agent = await agentService.getAgent(agentId)
+
+    if (!agent) {
+      logger.warn(`Agent not found: ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Agent not found',
+          type: 'not_found',
+          code: 'agent_not_found'
+        }
+      })
+    }
+
+    logger.info(`Agent retrieved successfully: ${agentId}`)
+    return res.json(agent)
+  } catch (error: any) {
+    logger.error('Error getting agent:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to get agent',
+        type: 'internal_error',
+        code: 'agent_get_failed'
+      }
+    })
+  }
+}
+
+/**
+ * @swagger
+ * /v1/agents/{agentId}:
+ *   put:
+ *     summary: Update agent
+ *     description: Updates an existing agent with the provided data
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             $ref: '#/components/schemas/CreateAgentRequest'
+ *     responses:
+ *       200:
+ *         description: Agent updated successfully
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       400:
+ *         description: Validation error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+export const updateAgent = async (req: Request, res: Response): Promise<Response> => {
+  const { agentId } = req.params
+  try {
+    logger.info(`Updating agent: ${agentId}`)
+    logger.debug('Update data:', req.body)
+
+    const { validatedBody } = req as ValidationRequest
+    const replacePayload = (validatedBody ?? {}) as ReplaceAgentRequest
+
+    const agent = await agentService.updateAgent(agentId, replacePayload, { replace: true })
+
+    if (!agent) {
+      logger.warn(`Agent not found for update: ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Agent not found',
+          type: 'not_found',
+          code: 'agent_not_found'
+        }
+      })
+    }
+
+    logger.info(`Agent updated successfully: ${agentId}`)
+    return res.json(agent)
+  } catch (error: any) {
+    if (error instanceof AgentModelValidationError) {
+      logger.warn('Agent model validation error during update:', {
+        agentId,
+        agentType: error.context.agentType,
+        field: error.context.field,
+        model: error.context.model,
+        detail: error.detail
+      })
+      return res.status(400).json(modelValidationErrorBody(error))
+    }
+
+    logger.error('Error updating agent:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to update agent: ' + error.message,
+        type: 'internal_error',
+        code: 'agent_update_failed'
+      }
+    })
+  }
+}
+
+/**
+ * @swagger
+ * /v1/agents/{agentId}:
+ *   patch:
+ *     summary: Partially update agent
+ *     description: Partially updates an existing agent with only the provided fields
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             type: object
+ *             properties:
+ *               name:
+ *                 type: string
+ *                 description: Agent name
+ *               description:
+ *                 type: string
+ *                 description: Agent description
+ *               avatar:
+ *                 type: string
+ *                 description: Agent avatar URL
+ *               instructions:
+ *                 type: string
+ *                 description: System prompt/instructions
+ *               model:
+ *                 type: string
+ *                 description: Main model ID
+ *               plan_model:
+ *                 type: string
+ *                 description: Optional planning model ID
+ *               small_model:
+ *                 type: string
+ *                 description: Optional small/fast model ID
+ *               built_in_tools:
+ *                 type: array
+ *                 items:
+ *                   type: string
+ *                 description: Built-in tool IDs
+ *               mcps:
+ *                 type: array
+ *                 items:
+ *                   type: string
+ *                 description: MCP tool IDs
+ *               knowledges:
+ *                 type: array
+ *                 items:
+ *                   type: string
+ *                 description: Knowledge base IDs
+ *               configuration:
+ *                 type: object
+ *                 description: Extensible settings
+ *               accessible_paths:
+ *                 type: array
+ *                 items:
+ *                   type: string
+ *                 description: Accessible directory paths
+ *               permission_mode:
+ *                 type: string
+ *                 enum: [readOnly, acceptEdits, bypassPermissions]
+ *                 description: Permission mode
+ *               max_steps:
+ *                 type: integer
+ *                 description: Maximum steps the agent can take
+ *             description: Only include the fields you want to update
+ *     responses:
+ *       200:
+ *         description: Agent updated successfully
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       400:
+ *         description: Validation error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+export const patchAgent = async (req: Request, res: Response): Promise<Response> => {
+  const { agentId } = req.params
+  try {
+    logger.info(`Partially updating agent: ${agentId}`)
+    logger.debug('Partial update data:', req.body)
+
+    const { validatedBody } = req as ValidationRequest
+    const updatePayload = (validatedBody ?? {}) as UpdateAgentRequest
+
+    const agent = await agentService.updateAgent(agentId, updatePayload)
+
+    if (!agent) {
+      logger.warn(`Agent not found for partial update: ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Agent not found',
+          type: 'not_found',
+          code: 'agent_not_found'
+        }
+      })
+    }
+
+    logger.info(`Agent partially updated successfully: ${agentId}`)
+    return res.json(agent)
+  } catch (error: any) {
+    if (error instanceof AgentModelValidationError) {
+      logger.warn('Agent model validation error during partial update:', {
+        agentId,
+        agentType: error.context.agentType,
+        field: error.context.field,
+        model: error.context.model,
+        detail: error.detail
+      })
+      return res.status(400).json(modelValidationErrorBody(error))
+    }
+
+    logger.error('Error partially updating agent:', error)
+    return res.status(500).json({
+      error: {
+        message: `Failed to partially update agent: ${error.message}`,
+        type: 'internal_error',
+        code: 'agent_patch_failed'
+      }
+    })
+  }
+}
+
+/**
+ * @swagger
+ * /v1/agents/{agentId}:
+ *   delete:
+ *     summary: Delete agent
+ *     description: Deletes an agent and all associated sessions and logs
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     responses:
+ *       204:
+ *         description: Agent deleted successfully
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+export const deleteAgent = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const { agentId } = req.params
+    logger.info(`Deleting agent: ${agentId}`)
+
+    const deleted = await agentService.deleteAgent(agentId)
+
+    if (!deleted) {
+      logger.warn(`Agent not found for deletion: ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Agent not found',
+          type: 'not_found',
+          code: 'agent_not_found'
+        }
+      })
+    }
+
+    logger.info(`Agent deleted successfully: ${agentId}`)
+    return res.status(204).send()
+  } catch (error: any) {
+    logger.error('Error deleting agent:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to delete agent',
+        type: 'internal_error',
+        code: 'agent_delete_failed'
+      }
+    })
+  }
+}

src/main/apiServer/routes/agents/handlers/index.ts

@@ -0,0 +1,3 @@
+export * as agentHandlers from './agents'
+export * as messageHandlers from './messages'
+export * as sessionHandlers from './sessions'

src/main/apiServer/routes/agents/handlers/messages.ts

@@ -0,0 +1,230 @@
+import { loggerService } from '@logger'
+import { Request, Response } from 'express'
+
+import { agentService, sessionMessageService, sessionService } from '../../../../services/agents'
+
+const logger = loggerService.withContext('ApiServerMessagesHandlers')
+
+// Helper function to verify agent and session exist and belong together
+const verifyAgentAndSession = async (agentId: string, sessionId: string) => {
+  const agentExists = await agentService.agentExists(agentId)
+  if (!agentExists) {
+    throw { status: 404, code: 'agent_not_found', message: 'Agent not found' }
+  }
+
+  const session = await sessionService.getSession(agentId, sessionId)
+  if (!session) {
+    throw { status: 404, code: 'session_not_found', message: 'Session not found' }
+  }
+
+  if (session.agent_id !== agentId) {
+    throw { status: 404, code: 'session_not_found', message: 'Session not found for this agent' }
+  }
+
+  return session
+}
+
+export const createMessage = async (req: Request, res: Response): Promise<void> => {
+  try {
+    const { agentId, sessionId } = req.params
+
+    const session = await verifyAgentAndSession(agentId, sessionId)
+
+    const messageData = req.body
+
+    logger.info(`Creating streaming message for session: ${sessionId}`)
+    logger.debug('Streaming message data:', messageData)
+
+    // Set SSE headers
+    res.setHeader('Content-Type', 'text/event-stream')
+    res.setHeader('Cache-Control', 'no-cache')
+    res.setHeader('Connection', 'keep-alive')
+    res.setHeader('Access-Control-Allow-Origin', '*')
+    res.setHeader('Access-Control-Allow-Headers', 'Cache-Control')
+
+    const abortController = new AbortController()
+    const { stream, completion } = await sessionMessageService.createSessionMessage(
+      session,
+      messageData,
+      abortController
+    )
+    const reader = stream.getReader()
+
+    // Track stream lifecycle so we keep the SSE connection open until persistence finishes
+    let responseEnded = false
+    let streamFinished = false
+
+    const finalizeResponse = () => {
+      if (responseEnded) {
+        return
+      }
+
+      if (!streamFinished) {
+        return
+      }
+
+      responseEnded = true
+      try {
+        // res.write('data: {"type":"finish"}\n\n')
+        res.write('data: [DONE]\n\n')
+      } catch (writeError) {
+        logger.error('Error writing final sentinel to SSE stream:', { error: writeError as Error })
+      }
+      res.end()
+    }
+
+    /**
+     * Client Disconnect Detection for Server-Sent Events (SSE)
+     *
+     * We monitor multiple HTTP events to reliably detect when a client disconnects
+     * from the streaming response. This is crucial for:
+     * - Aborting long-running Claude Code processes
+     * - Cleaning up resources and preventing memory leaks
+     * - Avoiding orphaned processes
+     *
+     * Event Priority & Behavior:
+     * 1. res.on('close') - Most common for SSE client disconnects (browser tab close, curl Ctrl+C)
+     * 2. req.on('aborted') - Explicit request abortion
+     * 3. req.on('close') - Request object closure (less common with SSE)
+     *
+     * When any disconnect event fires, we:
+     * - Abort the Claude Code SDK process via abortController
+     * - Clean up event listeners to prevent memory leaks
+     * - Mark the response as ended to prevent further writes
+     */
+    const handleDisconnect = () => {
+      if (responseEnded) return
+      logger.info(`Client disconnected from streaming message for session: ${sessionId}`)
+      responseEnded = true
+      abortController.abort('Client disconnected')
+      reader.cancel('Client disconnected').catch(() => {})
+    }
+
+    req.on('close', handleDisconnect)
+    req.on('aborted', handleDisconnect)
+    res.on('close', handleDisconnect)
+
+    const pumpStream = async () => {
+      try {
+        while (!responseEnded) {
+          const { done, value } = await reader.read()
+          if (done) {
+            break
+          }
+
+          res.write(`data: ${JSON.stringify(value)}\n\n`)
+        }
+
+        streamFinished = true
+        finalizeResponse()
+      } catch (error) {
+        if (responseEnded) return
+        logger.error('Error reading agent stream:', { error })
+        try {
+          res.write(
+            `data: ${JSON.stringify({
+              type: 'error',
+              error: {
+                message: (error as Error).message || 'Stream processing error',
+                type: 'stream_error',
+                code: 'stream_processing_failed'
+              }
+            })}\n\n`
+          )
+        } catch (writeError) {
+          logger.error('Error writing stream error to SSE:', { error: writeError })
+        }
+        responseEnded = true
+        res.end()
+      }
+    }
+
+    pumpStream().catch((error) => {
+      logger.error('Pump stream failure:', { error })
+    })
+
+    completion
+      .then(() => {
+        streamFinished = true
+        finalizeResponse()
+      })
+      .catch((error) => {
+        if (responseEnded) return
+        logger.error(`Streaming message error for session: ${sessionId}:`, error)
+        try {
+          res.write(
+            `data: ${JSON.stringify({
+              type: 'error',
+              error: {
+                message: (error as { message?: string })?.message || 'Stream processing error',
+                type: 'stream_error',
+                code: 'stream_processing_failed'
+              }
+            })}\n\n`
+          )
+        } catch (writeError) {
+          logger.error('Error writing completion error to SSE stream:', { error: writeError })
+        }
+        responseEnded = true
+        res.end()
+      })
+
+    // Set a timeout to prevent hanging indefinitely
+    const timeout = setTimeout(
+      () => {
+        if (!responseEnded) {
+          logger.error(`Streaming message timeout for session: ${sessionId}`)
+          try {
+            res.write(
+              `data: ${JSON.stringify({
+                type: 'error',
+                error: {
+                  message: 'Stream timeout',
+                  type: 'timeout_error',
+                  code: 'stream_timeout'
+                }
+              })}\n\n`
+            )
+          } catch (writeError) {
+            logger.error('Error writing timeout to SSE stream:', { error: writeError })
+          }
+          abortController.abort('stream timeout')
+          reader.cancel('stream timeout').catch(() => {})
+          responseEnded = true
+          res.end()
+        }
+      },
+      10 * 60 * 1000
+    ) // 10 minutes timeout
+
+    // Clear timeout when response ends
+    res.on('close', () => clearTimeout(timeout))
+    res.on('finish', () => clearTimeout(timeout))
+  } catch (error: any) {
+    logger.error('Error in streaming message handler:', error)
+
+    // Send error as SSE if possible
+    if (!res.headersSent) {
+      res.setHeader('Content-Type', 'text/event-stream')
+      res.setHeader('Cache-Control', 'no-cache')
+      res.setHeader('Connection', 'keep-alive')
+    }
+
+    try {
+      const errorResponse = {
+        type: 'error',
+        error: {
+          message: error.status ? error.message : 'Failed to create streaming message',
+          type: error.status ? 'not_found' : 'internal_error',
+          code: error.status ? error.code : 'stream_creation_failed'
+        }
+      }
+
+      res.write(`data: ${JSON.stringify(errorResponse)}\n\n`)
+    } catch (writeError) {
+      logger.error('Error writing initial error to SSE stream:', { error: writeError })
+    }
+
+    res.end()
+  }
+}

src/main/apiServer/routes/agents/handlers/sessions.ts

@@ -0,0 +1,370 @@
+import { loggerService } from '@logger'
+import {
+  AgentModelValidationError,
+  sessionMessageService,
+  sessionService
+} from '@main/services/agents'
+import {
+  CreateSessionResponse,
+  ListAgentSessionsResponse,
+  type ReplaceSessionRequest,
+  UpdateSessionResponse
+} from '@types'
+import { Request, Response } from 'express'
+
+import type { ValidationRequest } from '../validators/zodValidator'
+
+const logger = loggerService.withContext('ApiServerSessionsHandlers')
+
+const modelValidationErrorBody = (error: AgentModelValidationError) => ({
+  error: {
+    message: `Invalid ${error.context.field}: ${error.detail.message}`,
+    type: 'invalid_request_error',
+    code: error.detail.code
+  }
+})
+
+export const createSession = async (req: Request, res: Response): Promise<Response> => {
+  const { agentId } = req.params
+  try {
+    const sessionData = req.body
+
+    logger.info(`Creating new session for agent: ${agentId}`)
+    logger.debug('Session data:', sessionData)
+
+    const session = (await sessionService.createSession(agentId, sessionData)) satisfies CreateSessionResponse
+
+    logger.info(`Session created successfully: ${session.id}`)
+    return res.status(201).json(session)
+  } catch (error: any) {
+    if (error instanceof AgentModelValidationError) {
+      logger.warn('Session model validation error during create:', {
+        agentId,
+        agentType: error.context.agentType,
+        field: error.context.field,
+        model: error.context.model,
+        detail: error.detail
+      })
+      return res.status(400).json(modelValidationErrorBody(error))
+    }
+
+    logger.error('Error creating session:', error)
+    return res.status(500).json({
+      error: {
+        message: `Failed to create session: ${error.message}`,
+        type: 'internal_error',
+        code: 'session_creation_failed'
+      }
+    })
+  }
+}
+
+export const listSessions = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const { agentId } = req.params
+    const limit = req.query.limit ? parseInt(req.query.limit as string) : 20
+    const offset = req.query.offset ? parseInt(req.query.offset as string) : 0
+    const status = req.query.status as any
+
+    logger.info(`Listing sessions for agent: ${agentId} with limit=${limit}, offset=${offset}, status=${status}`)
+
+    const result = await sessionService.listSessions(agentId, { limit, offset })
+
+    logger.info(`Retrieved ${result.sessions.length} sessions (total: ${result.total}) for agent: ${agentId}`)
+    return res.json({
+      data: result.sessions,
+      total: result.total,
+      limit,
+      offset
+    })
+  } catch (error: any) {
+    logger.error('Error listing sessions:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to list sessions',
+        type: 'internal_error',
+        code: 'session_list_failed'
+      }
+    })
+  }
+}
+
+export const getSession = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const { agentId, sessionId } = req.params
+    logger.info(`Getting session: ${sessionId} for agent: ${agentId}`)
+
+    const session = await sessionService.getSession(agentId, sessionId)
+
+    if (!session) {
+      logger.warn(`Session not found: ${sessionId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    // // Verify session belongs to the agent
+    //   logger.warn(`Session ${sessionId} does not belong to agent ${agentId}`)
+    //   return res.status(404).json({
+    //     error: {
+    //       message: 'Session not found for this agent',
+    //       type: 'not_found',
+    //       code: 'session_not_found'
+    //     }
+    //   })
+    // }
+
+    // Fetch session messages
+    logger.info(`Fetching messages for session: ${sessionId}`)
+    const { messages } = await sessionMessageService.listSessionMessages(sessionId)
+
+    // Add messages to session
+    const sessionWithMessages = {
+      ...session,
+      messages: messages
+    }
+
+    logger.info(`Session retrieved successfully: ${sessionId} with ${messages.length} messages`)
+    return res.json(sessionWithMessages)
+  } catch (error: any) {
+    logger.error('Error getting session:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to get session',
+        type: 'internal_error',
+        code: 'session_get_failed'
+      }
+    })
+  }
+}
+
+export const updateSession = async (req: Request, res: Response): Promise<Response> => {
+  const { agentId, sessionId } = req.params
+  try {
+    logger.info(`Updating session: ${sessionId} for agent: ${agentId}`)
+    logger.debug('Update data:', req.body)
+
+    // First check if session exists and belongs to agent
+    const existingSession = await sessionService.getSession(agentId, sessionId)
+    if (!existingSession || existingSession.agent_id !== agentId) {
+      logger.warn(`Session ${sessionId} not found for agent ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found for this agent',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    const { validatedBody } = req as ValidationRequest
+    const replacePayload = (validatedBody ?? {}) as ReplaceSessionRequest
+
+    const session = await sessionService.updateSession(agentId, sessionId, replacePayload)
+
+    if (!session) {
+      logger.warn(`Session not found for update: ${sessionId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    logger.info(`Session updated successfully: ${sessionId}`)
+    return res.json(session satisfies UpdateSessionResponse)
+  } catch (error: any) {
+    if (error instanceof AgentModelValidationError) {
+      logger.warn('Session model validation error during update:', {
+        agentId,
+        sessionId,
+        agentType: error.context.agentType,
+        field: error.context.field,
+        model: error.context.model,
+        detail: error.detail
+      })
+      return res.status(400).json(modelValidationErrorBody(error))
+    }
+
+    logger.error('Error updating session:', error)
+    return res.status(500).json({
+      error: {
+        message: `Failed to update session: ${error.message}`,
+        type: 'internal_error',
+        code: 'session_update_failed'
+      }
+    })
+  }
+}
+
+export const patchSession = async (req: Request, res: Response): Promise<Response> => {
+  const { agentId, sessionId } = req.params
+  try {
+    logger.info(`Patching session: ${sessionId} for agent: ${agentId}`)
+    logger.debug('Patch data:', req.body)
+
+    // First check if session exists and belongs to agent
+    const existingSession = await sessionService.getSession(agentId, sessionId)
+    if (!existingSession || existingSession.agent_id !== agentId) {
+      logger.warn(`Session ${sessionId} not found for agent ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found for this agent',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    const updateSession = { ...existingSession, ...req.body }
+    const session = await sessionService.updateSession(agentId, sessionId, updateSession)
+
+    if (!session) {
+      logger.warn(`Session not found for patch: ${sessionId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    logger.info(`Session patched successfully: ${sessionId}`)
+    return res.json(session)
+  } catch (error: any) {
+    if (error instanceof AgentModelValidationError) {
+      logger.warn('Session model validation error during patch:', {
+        agentId,
+        sessionId,
+        agentType: error.context.agentType,
+        field: error.context.field,
+        model: error.context.model,
+        detail: error.detail
+      })
+      return res.status(400).json(modelValidationErrorBody(error))
+    }
+
+    logger.error('Error patching session:', error)
+    return res.status(500).json({
+      error: {
+        message: `Failed to patch session, ${error.message}`,
+        type: 'internal_error',
+        code: 'session_patch_failed'
+      }
+    })
+  }
+}
+
+export const deleteSession = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const { agentId, sessionId } = req.params
+    logger.info(`Deleting session: ${sessionId} for agent: ${agentId}`)
+
+    // First check if session exists and belongs to agent
+    const existingSession = await sessionService.getSession(agentId, sessionId)
+    if (!existingSession || existingSession.agent_id !== agentId) {
+      logger.warn(`Session ${sessionId} not found for agent ${agentId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found for this agent',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    const deleted = await sessionService.deleteSession(agentId, sessionId)
+
+    if (!deleted) {
+      logger.warn(`Session not found for deletion: ${sessionId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    logger.info(`Session deleted successfully: ${sessionId}`)
+    return res.status(204).send()
+  } catch (error: any) {
+    logger.error('Error deleting session:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to delete session',
+        type: 'internal_error',
+        code: 'session_delete_failed'
+      }
+    })
+  }
+}
+
+// Convenience endpoints for sessions without agent context
+export const listAllSessions = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const limit = req.query.limit ? parseInt(req.query.limit as string) : 20
+    const offset = req.query.offset ? parseInt(req.query.offset as string) : 0
+    const status = req.query.status as any
+
+    logger.info(`Listing all sessions with limit=${limit}, offset=${offset}, status=${status}`)
+
+    const result = await sessionService.listSessions(undefined, { limit, offset })
+
+    logger.info(`Retrieved ${result.sessions.length} sessions (total: ${result.total})`)
+    return res.json({
+      data: result.sessions,
+      total: result.total,
+      limit,
+      offset
+    } satisfies ListAgentSessionsResponse)
+  } catch (error: any) {
+    logger.error('Error listing all sessions:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to list sessions',
+        type: 'internal_error',
+        code: 'session_list_failed'
+      }
+    })
+  }
+}
+
+export const getSessionById = async (req: Request, res: Response): Promise<Response> => {
+  try {
+    const { sessionId } = req.params
+    logger.info(`Getting session: ${sessionId}`)
+
+    const session = await sessionService.getSessionById(sessionId)
+
+    if (!session) {
+      logger.warn(`Session not found: ${sessionId}`)
+      return res.status(404).json({
+        error: {
+          message: 'Session not found',
+          type: 'not_found',
+          code: 'session_not_found'
+        }
+      })
+    }
+
+    logger.info(`Session retrieved successfully: ${sessionId}`)
+    return res.json(session)
+  } catch (error: any) {
+    logger.error('Error getting session:', error)
+    return res.status(500).json({
+      error: {
+        message: 'Failed to get session',
+        type: 'internal_error',
+        code: 'session_get_failed'
+      }
+    })
+  }
+}

src/main/apiServer/routes/agents/index.ts

@@ -0,0 +1,927 @@
+import express from 'express'
+
+import { agentHandlers, messageHandlers, sessionHandlers } from './handlers'
+import { checkAgentExists, handleValidationErrors } from './middleware'
+import {
+  validateAgent,
+  validateAgentId,
+  validateAgentReplace,
+  validateAgentUpdate,
+  validatePagination,
+  validateSession,
+  validateSessionId,
+  validateSessionMessage,
+  validateSessionReplace,
+  validateSessionUpdate
+} from './validators'
+
+// Create main agents router
+const agentsRouter = express.Router()
+
+/**
+ * @swagger
+ * components:
+ *   schemas:
+ *     PermissionMode:
+ *       type: string
+ *       enum: [default, acceptEdits, bypassPermissions, plan]
+ *       description: Permission mode for agent operations
+ *
+ *     AgentType:
+ *       type: string
+ *       enum: [claude-code]
+ *       description: Type of agent
+ *
+ *     AgentConfiguration:
+ *       type: object
+ *       properties:
+ *         permission_mode:
+ *           $ref: '#/components/schemas/PermissionMode'
+ *           default: default
+ *         max_turns:
+ *           type: integer
+ *           default: 10
+ *           description: Maximum number of interaction turns
+ *       additionalProperties: true
+ *
+ *     AgentBase:
+ *       type: object
+ *       properties:
+ *         name:
+ *           type: string
+ *           description: Agent name
+ *         description:
+ *           type: string
+ *           description: Agent description
+ *         accessible_paths:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of directory paths the agent can access
+ *         instructions:
+ *           type: string
+ *           description: System prompt/instructions
+ *         model:
+ *           type: string
+ *           description: Main model ID
+ *         plan_model:
+ *           type: string
+ *           description: Optional planning model ID
+ *         small_model:
+ *           type: string
+ *           description: Optional small/fast model ID
+ *         mcps:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of MCP tool IDs
+ *         allowed_tools:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of allowed tool IDs (whitelist)
+ *         configuration:
+ *           $ref: '#/components/schemas/AgentConfiguration'
+ *       required:
+ *         - model
+ *         - accessible_paths
+ *
+ *     AgentEntity:
+ *       allOf:
+ *         - $ref: '#/components/schemas/AgentBase'
+ *         - type: object
+ *           properties:
+ *             id:
+ *               type: string
+ *               description: Unique agent identifier
+ *             type:
+ *               $ref: '#/components/schemas/AgentType'
+ *             created_at:
+ *               type: string
+ *               format: date-time
+ *               description: ISO timestamp of creation
+ *             updated_at:
+ *               type: string
+ *               format: date-time
+ *               description: ISO timestamp of last update
+ *           required:
+ *             - id
+ *             - type
+ *             - created_at
+ *             - updated_at
+ *     CreateAgentRequest:
+ *       allOf:
+ *         - $ref: '#/components/schemas/AgentBase'
+ *         - type: object
+ *           properties:
+ *             type:
+ *               $ref: '#/components/schemas/AgentType'
+ *             name:
+ *               type: string
+ *               minLength: 1
+ *               description: Agent name (required)
+ *             model:
+ *               type: string
+ *               minLength: 1
+ *               description: Main model ID (required)
+ *           required:
+ *             - type
+ *             - name
+ *             - model
+ *
+ *     UpdateAgentRequest:
+ *       type: object
+ *       properties:
+ *         name:
+ *           type: string
+ *           description: Agent name
+ *         description:
+ *           type: string
+ *           description: Agent description
+ *         accessible_paths:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of directory paths the agent can access
+ *         instructions:
+ *           type: string
+ *           description: System prompt/instructions
+ *         model:
+ *           type: string
+ *           description: Main model ID
+ *         plan_model:
+ *           type: string
+ *           description: Optional planning model ID
+ *         small_model:
+ *           type: string
+ *           description: Optional small/fast model ID
+ *         mcps:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of MCP tool IDs
+ *         allowed_tools:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of allowed tool IDs (whitelist)
+ *         configuration:
+ *           $ref: '#/components/schemas/AgentConfiguration'
+ *       description: Partial update - all fields are optional
+ *
+ *     ReplaceAgentRequest:
+ *       $ref: '#/components/schemas/AgentBase'
+ *
+ *     SessionEntity:
+ *       allOf:
+ *         - $ref: '#/components/schemas/AgentBase'
+ *         - type: object
+ *           properties:
+ *             id:
+ *               type: string
+ *               description: Unique session identifier
+ *             agent_id:
+ *               type: string
+ *               description: Primary agent ID for the session
+ *             agent_type:
+ *               $ref: '#/components/schemas/AgentType'
+ *             created_at:
+ *               type: string
+ *               format: date-time
+ *               description: ISO timestamp of creation
+ *             updated_at:
+ *               type: string
+ *               format: date-time
+ *               description: ISO timestamp of last update
+ *           required:
+ *             - id
+ *             - agent_id
+ *             - agent_type
+ *             - created_at
+ *             - updated_at
+ *
+ *     CreateSessionRequest:
+ *       allOf:
+ *         - $ref: '#/components/schemas/AgentBase'
+ *         - type: object
+ *           properties:
+ *             model:
+ *               type: string
+ *               minLength: 1
+ *               description: Main model ID (required)
+ *           required:
+ *             - model
+ *
+ *     UpdateSessionRequest:
+ *       type: object
+ *       properties:
+ *         name:
+ *           type: string
+ *           description: Session name
+ *         description:
+ *           type: string
+ *           description: Session description
+ *         accessible_paths:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of directory paths the agent can access
+ *         instructions:
+ *           type: string
+ *           description: System prompt/instructions
+ *         model:
+ *           type: string
+ *           description: Main model ID
+ *         plan_model:
+ *           type: string
+ *           description: Optional planning model ID
+ *         small_model:
+ *           type: string
+ *           description: Optional small/fast model ID
+ *         mcps:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of MCP tool IDs
+ *         allowed_tools:
+ *           type: array
+ *           items:
+ *             type: string
+ *           description: Array of allowed tool IDs (whitelist)
+ *         configuration:
+ *           $ref: '#/components/schemas/AgentConfiguration'
+ *       description: Partial update - all fields are optional
+ *
+ *     ReplaceSessionRequest:
+ *       allOf:
+ *         - $ref: '#/components/schemas/AgentBase'
+ *         - type: object
+ *           properties:
+ *             model:
+ *               type: string
+ *               minLength: 1
+ *               description: Main model ID (required)
+ *           required:
+ *             - model
+ *
+ *     CreateSessionMessageRequest:
+ *       type: object
+ *       properties:
+ *         content:
+ *           type: string
+ *           minLength: 1
+ *           description: Message content
+ *       required:
+ *         - content
+ *
+ *     PaginationQuery:
+ *       type: object
+ *       properties:
+ *         limit:
+ *           type: integer
+ *           minimum: 1
+ *           maximum: 100
+ *           default: 20
+ *           description: Number of items to return
+ *         offset:
+ *           type: integer
+ *           minimum: 0
+ *           default: 0
+ *           description: Number of items to skip
+ *         status:
+ *           type: string
+ *           enum: [idle, running, completed, failed, stopped]
+ *           description: Filter by session status
+ *
+ *     ListAgentsResponse:
+ *       type: object
+ *       properties:
+ *         agents:
+ *           type: array
+ *           items:
+ *             $ref: '#/components/schemas/AgentEntity'
+ *         total:
+ *           type: integer
+ *           description: Total number of agents
+ *         limit:
+ *           type: integer
+ *           description: Number of items returned
+ *         offset:
+ *           type: integer
+ *           description: Number of items skipped
+ *       required:
+ *         - agents
+ *         - total
+ *         - limit
+ *         - offset
+ *
+ *     ListSessionsResponse:
+ *       type: object
+ *       properties:
+ *         sessions:
+ *           type: array
+ *           items:
+ *             $ref: '#/components/schemas/SessionEntity'
+ *         total:
+ *           type: integer
+ *           description: Total number of sessions
+ *         limit:
+ *           type: integer
+ *           description: Number of items returned
+ *         offset:
+ *           type: integer
+ *           description: Number of items skipped
+ *       required:
+ *         - sessions
+ *         - total
+ *         - limit
+ *         - offset
+ *
+ *     ErrorResponse:
+ *       type: object
+ *       properties:
+ *         error:
+ *           type: object
+ *           properties:
+ *             message:
+ *               type: string
+ *               description: Error message
+ *             type:
+ *               type: string
+ *               description: Error type
+ *             code:
+ *               type: string
+ *               description: Error code
+ *           required:
+ *             - message
+ *             - type
+ *             - code
+ *       required:
+ *         - error
+ */
+
+/**
+ * @swagger
+ * /api/agents:
+ *   post:
+ *     summary: Create a new agent
+ *     tags: [Agents]
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             $ref: '#/components/schemas/CreateAgentRequest'
+ *     responses:
+ *       201:
+ *         description: Agent created successfully
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       400:
+ *         description: Invalid request body
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ */
+// Agent CRUD routes
+agentsRouter.post('/', validateAgent, handleValidationErrors, agentHandlers.createAgent)
+
+/**
+ * @swagger
+ * /api/agents:
+ *   get:
+ *     summary: List all agents with pagination
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: query
+ *         name: limit
+ *         schema:
+ *           type: integer
+ *           minimum: 1
+ *           maximum: 100
+ *           default: 20
+ *         description: Number of agents to return
+ *       - in: query
+ *         name: offset
+ *         schema:
+ *           type: integer
+ *           minimum: 0
+ *           default: 0
+ *         description: Number of agents to skip
+ *       - in: query
+ *         name: status
+ *         schema:
+ *           type: string
+ *           enum: [idle, running, completed, failed, stopped]
+ *         description: Filter by agent status
+ *     responses:
+ *       200:
+ *         description: List of agents
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ListAgentsResponse'
+ */
+agentsRouter.get('/', validatePagination, handleValidationErrors, agentHandlers.listAgents)
+
+/**
+ * @swagger
+ * /api/agents/{agentId}:
+ *   get:
+ *     summary: Get agent by ID
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     responses:
+ *       200:
+ *         description: Agent details
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ */
+agentsRouter.get('/:agentId', validateAgentId, handleValidationErrors, agentHandlers.getAgent)
+/**
+ * @swagger
+ * /api/agents/{agentId}:
+ *   put:
+ *     summary: Replace agent (full update)
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             $ref: '#/components/schemas/ReplaceAgentRequest'
+ *     responses:
+ *       200:
+ *         description: Agent updated successfully
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       400:
+ *         description: Invalid request body
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ */
+agentsRouter.put('/:agentId', validateAgentId, validateAgentReplace, handleValidationErrors, agentHandlers.updateAgent)
+/**
+ * @swagger
+ * /api/agents/{agentId}:
+ *   patch:
+ *     summary: Update agent (partial update)
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             $ref: '#/components/schemas/UpdateAgentRequest'
+ *     responses:
+ *       200:
+ *         description: Agent updated successfully
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/AgentEntity'
+ *       400:
+ *         description: Invalid request body
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ */
+agentsRouter.patch('/:agentId', validateAgentId, validateAgentUpdate, handleValidationErrors, agentHandlers.patchAgent)
+/**
+ * @swagger
+ * /api/agents/{agentId}:
+ *   delete:
+ *     summary: Delete agent
+ *     tags: [Agents]
+ *     parameters:
+ *       - in: path
+ *         name: agentId
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: Agent ID
+ *     responses:
+ *       204:
+ *         description: Agent deleted successfully
+ *       404:
+ *         description: Agent not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/ErrorResponse'
+ */
+agentsRouter.delete('/:agentId', validateAgentId, handleValidationErrors, agentHandlers.deleteAgent)
+
+// Create sessions router with agent context
+const createSessionsRouter = (): express.Router => {
+  const sessionsRouter = express.Router({ mergeParams: true })
+
+  // Session CRUD routes (nested under agent)
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions:
+   *   post:
+   *     summary: Create a new session for an agent
+   *     tags: [Sessions]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *     requestBody:
+   *       required: true
+   *       content:
+   *         application/json:
+   *           schema:
+   *             $ref: '#/components/schemas/CreateSessionRequest'
+   *     responses:
+   *       201:
+   *         description: Session created successfully
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/SessionEntity'
+   *       400:
+   *         description: Invalid request body
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   *       404:
+   *         description: Agent not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  sessionsRouter.post('/', validateSession, handleValidationErrors, sessionHandlers.createSession)
+
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions:
+   *   get:
+   *     summary: List sessions for an agent
+   *     tags: [Sessions]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *       - in: query
+   *         name: limit
+   *         schema:
+   *           type: integer
+   *           minimum: 1
+   *           maximum: 100
+   *           default: 20
+   *         description: Number of sessions to return
+   *       - in: query
+   *         name: offset
+   *         schema:
+   *           type: integer
+   *           minimum: 0
+   *           default: 0
+   *         description: Number of sessions to skip
+   *       - in: query
+   *         name: status
+   *         schema:
+   *           type: string
+   *           enum: [idle, running, completed, failed, stopped]
+   *         description: Filter by session status
+   *     responses:
+   *       200:
+   *         description: List of sessions
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ListSessionsResponse'
+   *       404:
+   *         description: Agent not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  sessionsRouter.get('/', validatePagination, handleValidationErrors, sessionHandlers.listSessions)
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions/{sessionId}:
+   *   get:
+   *     summary: Get session by ID
+   *     tags: [Sessions]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *       - in: path
+   *         name: sessionId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Session ID
+   *     responses:
+   *       200:
+   *         description: Session details
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/SessionEntity'
+   *       404:
+   *         description: Agent or session not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  sessionsRouter.get('/:sessionId', validateSessionId, handleValidationErrors, sessionHandlers.getSession)
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions/{sessionId}:
+   *   put:
+   *     summary: Replace session (full update)
+   *     tags: [Sessions]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *       - in: path
+   *         name: sessionId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Session ID
+   *     requestBody:
+   *       required: true
+   *       content:
+   *         application/json:
+   *           schema:
+   *             $ref: '#/components/schemas/ReplaceSessionRequest'
+   *     responses:
+   *       200:
+   *         description: Session updated successfully
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/SessionEntity'
+   *       400:
+   *         description: Invalid request body
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   *       404:
+   *         description: Agent or session not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  sessionsRouter.put(
+    '/:sessionId',
+    validateSessionId,
+    validateSessionReplace,
+    handleValidationErrors,
+    sessionHandlers.updateSession
+  )
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions/{sessionId}:
+   *   patch:
+   *     summary: Update session (partial update)
+   *     tags: [Sessions]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *       - in: path
+   *         name: sessionId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Session ID
+   *     requestBody:
+   *       required: true
+   *       content:
+   *         application/json:
+   *           schema:
+   *             $ref: '#/components/schemas/UpdateSessionRequest'
+   *     responses:
+   *       200:
+   *         description: Session updated successfully
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/SessionEntity'
+   *       400:
+   *         description: Invalid request body
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   *       404:
+   *         description: Agent or session not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  sessionsRouter.patch(
+    '/:sessionId',
+    validateSessionId,
+    validateSessionUpdate,
+    handleValidationErrors,
+    sessionHandlers.patchSession
+  )
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions/{sessionId}:
+   *   delete:
+   *     summary: Delete session
+   *     tags: [Sessions]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *       - in: path
+   *         name: sessionId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Session ID
+   *     responses:
+   *       204:
+   *         description: Session deleted successfully
+   *       404:
+   *         description: Agent or session not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  sessionsRouter.delete('/:sessionId', validateSessionId, handleValidationErrors, sessionHandlers.deleteSession)
+
+  return sessionsRouter
+}
+
+// Create messages router with agent and session context
+const createMessagesRouter = (): express.Router => {
+  const messagesRouter = express.Router({ mergeParams: true })
+
+  // Message CRUD routes (nested under agent/session)
+  /**
+   * @swagger
+   * /api/agents/{agentId}/sessions/{sessionId}/messages:
+   *   post:
+   *     summary: Create a new message in a session
+   *     tags: [Messages]
+   *     parameters:
+   *       - in: path
+   *         name: agentId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Agent ID
+   *       - in: path
+   *         name: sessionId
+   *         required: true
+   *         schema:
+   *           type: string
+   *         description: Session ID
+   *     requestBody:
+   *       required: true
+   *       content:
+   *         application/json:
+   *           schema:
+   *             $ref: '#/components/schemas/CreateSessionMessageRequest'
+   *     responses:
+   *       201:
+   *         description: Message created successfully
+   *         content:
+   *           application/json:
+   *             schema:
+   *               type: object
+   *               properties:
+   *                 id:
+   *                   type: number
+   *                   description: Message ID
+   *                 session_id:
+   *                   type: string
+   *                   description: Session ID
+   *                 role:
+   *                   type: string
+   *                   enum: [assistant, user, system, tool]
+   *                   description: Message role
+   *                 content:
+   *                   type: object
+   *                   description: Message content (AI SDK format)
+   *                 agent_session_id:
+   *                   type: string
+   *                   description: Agent session ID for resuming
+   *                 metadata:
+   *                   type: object
+   *                   description: Additional metadata
+   *                 created_at:
+   *                   type: string
+   *                   format: date-time
+   *                 updated_at:
+   *                   type: string
+   *                   format: date-time
+   *       400:
+   *         description: Invalid request body
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   *       404:
+   *         description: Agent or session not found
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/ErrorResponse'
+   */
+  messagesRouter.post('/', validateSessionMessage, handleValidationErrors, messageHandlers.createMessage)
+  return messagesRouter
+}
+
+// Mount nested resources with clear hierarchy
+const sessionsRouter = createSessionsRouter()
+const messagesRouter = createMessagesRouter()
+
+// Mount sessions under specific agent
+agentsRouter.use('/:agentId/sessions', validateAgentId, checkAgentExists, handleValidationErrors, sessionsRouter)
+
+// Mount messages under specific agent/session
+agentsRouter.use(
+  '/:agentId/sessions/:sessionId/messages',
+  validateAgentId,
+  validateSessionId,
+  handleValidationErrors,
+  messagesRouter
+)
+
+// Export main router and convenience router
+export const agentsRoutes = agentsRouter

src/main/apiServer/routes/agents/middleware/common.ts

@@ -0,0 +1,41 @@
+import { Request, Response } from 'express'
+
+import { agentService } from '../../../../services/agents'
+import { loggerService } from '../../../../services/LoggerService'
+
+const logger = loggerService.withContext('ApiServerMiddleware')
+
+// Since Zod validators handle their own errors, this is now a pass-through
+export const handleValidationErrors = (_req: Request, _res: Response, next: any): void => {
+  next()
+}
+
+// Middleware to check if agent exists
+export const checkAgentExists = async (req: Request, res: Response, next: any): Promise<void> => {
+  try {
+    const { agentId } = req.params
+    const exists = await agentService.agentExists(agentId)
+
+    if (!exists) {
+      res.status(404).json({
+        error: {
+          message: 'Agent not found',
+          type: 'not_found',
+          code: 'agent_not_found'
+        }
+      })
+      return
+    }
+
+    next()
+  } catch (error) {
+    logger.error('Error checking agent existence:', error as Error)
+    res.status(500).json({
+      error: {
+        message: 'Failed to validate agent',
+        type: 'internal_error',
+        code: 'agent_validation_failed'
+      }
+    })
+  }
+}

src/main/apiServer/routes/agents/middleware/index.ts

@@ -0,0 +1 @@
+export * from './common'

src/main/apiServer/routes/agents/validators/agents.ts

@@ -0,0 +1,24 @@
+import {
+  AgentIdParamSchema,
+  CreateAgentRequestSchema,
+  ReplaceAgentRequestSchema,
+  UpdateAgentRequestSchema
+} from '@types'
+
+import { createZodValidator } from './zodValidator'
+
+export const validateAgent = createZodValidator({
+  body: CreateAgentRequestSchema
+})
+
+export const validateAgentReplace = createZodValidator({
+  body: ReplaceAgentRequestSchema
+})
+
+export const validateAgentUpdate = createZodValidator({
+  body: UpdateAgentRequestSchema
+})
+
+export const validateAgentId = createZodValidator({
+  params: AgentIdParamSchema
+})

src/main/apiServer/routes/agents/validators/common.ts

@@ -0,0 +1,7 @@
+import { PaginationQuerySchema } from '@types'
+
+import { createZodValidator } from './zodValidator'
+
+export const validatePagination = createZodValidator({
+  query: PaginationQuerySchema
+})

src/main/apiServer/routes/agents/validators/index.ts

@@ -0,0 +1,4 @@
+export * from './agents'
+export * from './common'
+export * from './messages'
+export * from './sessions'

src/main/apiServer/routes/agents/validators/messages.ts

@@ -0,0 +1,7 @@
+import { CreateSessionMessageRequestSchema } from '@types'
+
+import { createZodValidator } from './zodValidator'
+
+export const validateSessionMessage = createZodValidator({
+  body: CreateSessionMessageRequestSchema
+})

src/main/apiServer/routes/agents/validators/sessions.ts

@@ -0,0 +1,24 @@
+import {
+  CreateSessionRequestSchema,
+  ReplaceSessionRequestSchema,
+  SessionIdParamSchema,
+  UpdateSessionRequestSchema
+} from '@types'
+
+import { createZodValidator } from './zodValidator'
+
+export const validateSession = createZodValidator({
+  body: CreateSessionRequestSchema
+})
+
+export const validateSessionReplace = createZodValidator({
+  body: ReplaceSessionRequestSchema
+})
+
+export const validateSessionUpdate = createZodValidator({
+  body: UpdateSessionRequestSchema
+})
+
+export const validateSessionId = createZodValidator({
+  params: SessionIdParamSchema
+})

src/main/apiServer/routes/agents/validators/zodValidator.ts

@@ -0,0 +1,68 @@
+import { NextFunction,Request, Response } from 'express'
+import { ZodError, ZodType } from 'zod'
+
+export interface ValidationRequest extends Request {
+  validatedBody?: any
+  validatedParams?: any
+  validatedQuery?: any
+}
+
+export interface ZodValidationConfig {
+  body?: ZodType
+  params?: ZodType
+  query?: ZodType
+}
+
+export const createZodValidator = (config: ZodValidationConfig) => {
+  return (req: ValidationRequest, res: Response, next: NextFunction): void => {
+    try {
+      if (config.body && req.body) {
+        req.validatedBody = config.body.parse(req.body)
+      }
+
+      if (config.params && req.params) {
+        req.validatedParams = config.params.parse(req.params)
+      }
+
+      if (config.query && req.query) {
+        req.validatedQuery = config.query.parse(req.query)
+      }
+
+      next()
+    } catch (error) {
+      if (error instanceof ZodError) {
+        const validationErrors = error.issues.map((err) => ({
+          type: 'field',
+          value: err.input,
+          msg: err.message,
+          path: err.path.map(p => String(p)).join('.'),
+          location: getLocationFromPath(err.path, config)
+        }))
+
+        res.status(400).json({
+          error: {
+            message: 'Validation failed',
+            type: 'validation_error',
+            details: validationErrors
+          }
+        })
+        return
+      }
+
+      res.status(500).json({
+        error: {
+          message: 'Internal validation error',
+          type: 'internal_error',
+          code: 'validation_processing_failed'
+        }
+      })
+    }
+  }
+}
+
+function getLocationFromPath(path: (string | number | symbol)[], config: ZodValidationConfig): string {
+  if (config.body && path.length > 0) return 'body'
+  if (config.params && path.length > 0) return 'params'
+  if (config.query && path.length > 0) return 'query'
+  return 'unknown'
+}

src/main/apiServer/routes/chat.ts

@@ -0,0 +1,244 @@
+import express, { Request, Response } from 'express'
+import { ChatCompletionCreateParams } from 'openai/resources'
+
+import { loggerService } from '../../services/LoggerService'
+import {
+  ChatCompletionModelError,
+  chatCompletionService,
+  ChatCompletionValidationError
+} from '../services/chat-completion'
+
+const logger = loggerService.withContext('ApiServerChatRoutes')
+
+const router = express.Router()
+
+interface ErrorResponseBody {
+  error: {
+    message: string
+    type: string
+    code: string
+  }
+}
+
+const mapChatCompletionError = (error: unknown): { status: number; body: ErrorResponseBody } => {
+  if (error instanceof ChatCompletionValidationError) {
+    logger.warn('Chat completion validation error:', {
+      errors: error.errors
+    })
+
+    return {
+      status: 400,
+      body: {
+        error: {
+          message: error.errors.join('; '),
+          type: 'invalid_request_error',
+          code: 'validation_failed'
+        }
+      }
+    }
+  }
+
+  if (error instanceof ChatCompletionModelError) {
+    logger.warn('Chat completion model error:', error.error)
+
+    return {
+      status: 400,
+      body: {
+        error: {
+          message: error.error.message,
+          type: 'invalid_request_error',
+          code: error.error.code
+        }
+      }
+    }
+  }
+
+  if (error instanceof Error) {
+    let statusCode = 500
+    let errorType = 'server_error'
+    let errorCode = 'internal_error'
+
+    if (error.message.includes('API key') || error.message.includes('authentication')) {
+      statusCode = 401
+      errorType = 'authentication_error'
+      errorCode = 'invalid_api_key'
+    } else if (error.message.includes('rate limit') || error.message.includes('quota')) {
+      statusCode = 429
+      errorType = 'rate_limit_error'
+      errorCode = 'rate_limit_exceeded'
+    } else if (error.message.includes('timeout') || error.message.includes('connection')) {
+      statusCode = 502
+      errorType = 'server_error'
+      errorCode = 'upstream_error'
+    }
+
+    logger.error('Chat completion error:', { error })
+
+    return {
+      status: statusCode,
+      body: {
+        error: {
+          message: error.message || 'Internal server error',
+          type: errorType,
+          code: errorCode
+        }
+      }
+    }
+  }
+
+  logger.error('Chat completion unknown error:', { error })
+
+  return {
+    status: 500,
+    body: {
+      error: {
+        message: 'Internal server error',
+        type: 'server_error',
+        code: 'internal_error'
+      }
+    }
+  }
+}
+
+/**
+ * @swagger
+ * /v1/chat/completions:
+ *   post:
+ *     summary: Create chat completion
+ *     description: Create a chat completion response, compatible with OpenAI API
+ *     tags: [Chat]
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             $ref: '#/components/schemas/ChatCompletionRequest'
+ *     responses:
+ *       200:
+ *         description: Chat completion response
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 id:
+ *                   type: string
+ *                 object:
+ *                   type: string
+ *                   example: chat.completion
+ *                 created:
+ *                   type: integer
+ *                 model:
+ *                   type: string
+ *                 choices:
+ *                   type: array
+ *                   items:
+ *                     type: object
+ *                     properties:
+ *                       index:
+ *                         type: integer
+ *                       message:
+ *                         $ref: '#/components/schemas/ChatMessage'
+ *                       finish_reason:
+ *                         type: string
+ *                 usage:
+ *                   type: object
+ *                   properties:
+ *                     prompt_tokens:
+ *                       type: integer
+ *                     completion_tokens:
+ *                       type: integer
+ *                     total_tokens:
+ *                       type: integer
+ *           text/event-stream:
+ *             schema:
+ *               type: string
+ *               description: Server-sent events stream (when stream=true)
+ *       400:
+ *         description: Bad request
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       401:
+ *         description: Unauthorized
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       429:
+ *         description: Rate limit exceeded
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ *       500:
+ *         description: Internal server error
+ *         content:
+ *           application/json:
+ *             schema:
+ *               $ref: '#/components/schemas/Error'
+ */
+router.post('/completions', async (req: Request, res: Response) => {
+  try {
+    const request: ChatCompletionCreateParams = req.body
+
+    if (!request) {
+      return res.status(400).json({
+        error: {
+          message: 'Request body is required',
+          type: 'invalid_request_error',
+          code: 'missing_body'
+        }
+      })
+    }
+
+    logger.info('Chat completion request:', {
+      model: request.model,
+      messageCount: request.messages?.length || 0,
+      stream: request.stream,
+      temperature: request.temperature
+    })
+
+    const isStreaming = !!request.stream
+
+    if (isStreaming) {
+      const { stream } = await chatCompletionService.processStreamingCompletion(request)
+
+      res.setHeader('Content-Type', 'text/event-stream; charset=utf-8')
+      res.setHeader('Cache-Control', 'no-cache, no-transform')
+      res.setHeader('Connection', 'keep-alive')
+      res.setHeader('X-Accel-Buffering', 'no')
+      res.flushHeaders()
+
+      try {
+        for await (const chunk of stream) {
+          res.write(`data: ${JSON.stringify(chunk)}\n\n`)
+        }
+        res.write('data: [DONE]\n\n')
+      } catch (streamError: any) {
+        logger.error('Stream error:', streamError)
+        res.write(
+          `data: ${JSON.stringify({
+            error: {
+              message: 'Stream processing error',
+              type: 'server_error',
+              code: 'stream_error'
+            }
+          })}\n\n`
+        )
+      } finally {
+        res.end()
+      }
+      return
+    }
+
+    const { response } = await chatCompletionService.processCompletion(request)
+    return res.json(response)
+  } catch (error: unknown) {
+    const { status, body } = mapChatCompletionError(error)
+    return res.status(status).json(body)
+  }
+})
+
+export { router as chatRoutes }

src/main/apiServer/routes/mcp.ts

@@ -0,0 +1,153 @@
+import express, { Request, Response } from 'express'
+
+import { loggerService } from '../../services/LoggerService'
+import { mcpApiService } from '../services/mcp'
+
+const logger = loggerService.withContext('ApiServerMCPRoutes')
+
+const router = express.Router()
+
+/**
+ * @swagger
+ * /v1/mcps:
+ *   get:
+ *     summary: List MCP servers
+ *     description: Get a list of all configured Model Context Protocol servers
+ *     tags: [MCP]
+ *     responses:
+ *       200:
+ *         description: List of MCP servers
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 success:
+ *                   type: boolean
+ *                 data:
+ *                   type: array
+ *                   items:
+ *                     $ref: '#/components/schemas/MCPServer'
+ *       503:
+ *         description: Service unavailable
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 success:
+ *                   type: boolean
+ *                   example: false
+ *                 error:
+ *                   $ref: '#/components/schemas/Error'
+ */
+router.get('/', async (req: Request, res: Response) => {
+  try {
+    logger.info('Get all MCP servers request received')
+    const servers = await mcpApiService.getAllServers(req)
+    return res.json({
+      success: true,
+      data: servers
+    })
+  } catch (error: any) {
+    logger.error('Error fetching MCP servers:', error)
+    return res.status(503).json({
+      success: false,
+      error: {
+        message: `Failed to retrieve MCP servers: ${error.message}`,
+        type: 'service_unavailable',
+        code: 'servers_unavailable'
+      }
+    })
+  }
+})
+
+/**
+ * @swagger
+ * /v1/mcps/{server_id}:
+ *   get:
+ *     summary: Get MCP server info
+ *     description: Get detailed information about a specific MCP server
+ *     tags: [MCP]
+ *     parameters:
+ *       - in: path
+ *         name: server_id
+ *         required: true
+ *         schema:
+ *           type: string
+ *         description: MCP server ID
+ *     responses:
+ *       200:
+ *         description: MCP server information
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 success:
+ *                   type: boolean
+ *                 data:
+ *                   $ref: '#/components/schemas/MCPServer'
+ *       404:
+ *         description: MCP server not found
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 success:
+ *                   type: boolean
+ *                   example: false
+ *                 error:
+ *                   $ref: '#/components/schemas/Error'
+ */
+router.get('/:server_id', async (req: Request, res: Response) => {
+  try {
+    logger.info('Get MCP server info request received')
+    const server = await mcpApiService.getServerInfo(req.params.server_id)
+    if (!server) {
+      logger.warn('MCP server not found')
+      return res.status(404).json({
+        success: false,
+        error: {
+          message: 'MCP server not found',
+          type: 'not_found',
+          code: 'server_not_found'
+        }
+      })
+    }
+    return res.json({
+      success: true,
+      data: server
+    })
+  } catch (error: any) {
+    logger.error('Error fetching MCP server info:', error)
+    return res.status(503).json({
+      success: false,
+      error: {
+        message: `Failed to retrieve MCP server info: ${error.message}`,
+        type: 'service_unavailable',
+        code: 'server_info_unavailable'
+      }
+    })
+  }
+})
+
+// Connect to MCP server
+router.all('/:server_id/mcp', async (req: Request, res: Response) => {
+  const server = await mcpApiService.getServerById(req.params.server_id)
+  if (!server) {
+    logger.warn('MCP server not found')
+    return res.status(404).json({
+      success: false,
+      error: {
+        message: 'MCP server not found',
+        type: 'not_found',
+        code: 'server_not_found'
+      }
+    })
+  }
+  return await mcpApiService.handleRequest(req, res, server)
+})
+
+export { router as mcpRoutes }

src/main/apiServer/routes/messages.ts

@@ -0,0 +1,290 @@
+import { MessageCreateParams } from '@anthropic-ai/sdk/resources'
+import express, { Request, Response } from 'express'
+
+import { loggerService } from '../../services/LoggerService'
+import { messagesService } from '../services/messages'
+import { validateModelId } from '../utils'
+
+const logger = loggerService.withContext('ApiServerMessagesRoutes')
+
+const router = express.Router()
+
+/**
+ * @swagger
+ * /v1/messages:
+ *   post:
+ *     summary: Create message
+ *     description: Create a message response using Anthropic's API format
+ *     tags: [Messages]
+ *     requestBody:
+ *       required: true
+ *       content:
+ *         application/json:
+ *           schema:
+ *             type: object
+ *             required:
+ *               - model
+ *               - max_tokens
+ *               - messages
+ *             properties:
+ *               model:
+ *                 type: string
+ *                 description: Model ID in format "provider:model_id"
+ *                 example: "my-anthropic:claude-3-5-sonnet-20241022"
+ *               max_tokens:
+ *                 type: integer
+ *                 minimum: 1
+ *                 description: Maximum number of tokens to generate
+ *                 example: 1024
+ *               messages:
+ *                 type: array
+ *                 items:
+ *                   type: object
+ *                   properties:
+ *                     role:
+ *                       type: string
+ *                       enum: [user, assistant]
+ *                     content:
+ *                       oneOf:
+ *                         - type: string
+ *                         - type: array
+ *               system:
+ *                 type: string
+ *                 description: System message
+ *               temperature:
+ *                 type: number
+ *                 minimum: 0
+ *                 maximum: 1
+ *                 description: Sampling temperature
+ *               top_p:
+ *                 type: number
+ *                 minimum: 0
+ *                 maximum: 1
+ *                 description: Nucleus sampling
+ *               top_k:
+ *                 type: integer
+ *                 minimum: 0
+ *                 description: Top-k sampling
+ *               stream:
+ *                 type: boolean
+ *                 description: Whether to stream the response
+ *               tools:
+ *                 type: array
+ *                 description: Available tools for the model
+ *     responses:
+ *       200:
+ *         description: Message response
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 id:
+ *                   type: string
+ *                 type:
+ *                   type: string
+ *                   example: message
+ *                 role:
+ *                   type: string
+ *                   example: assistant
+ *                 content:
+ *                   type: array
+ *                   items:
+ *                     type: object
+ *                 model:
+ *                   type: string
+ *                 stop_reason:
+ *                   type: string
+ *                 stop_sequence:
+ *                   type: string
+ *                 usage:
+ *                   type: object
+ *                   properties:
+ *                     input_tokens:
+ *                       type: integer
+ *                     output_tokens:
+ *                       type: integer
+ *           text/event-stream:
+ *             schema:
+ *               type: string
+ *               description: Server-sent events stream (when stream=true)
+ *       400:
+ *         description: Bad request
+ *         content:
+ *           application/json:
+ *             schema:
+ *               type: object
+ *               properties:
+ *                 type:
+ *                   type: string
+ *                   example: error
+ *                 error:
+ *                   type: object
+ *                   properties:
+ *                     type:
+ *                       type: string
+ *                     message:
+ *                       type: string
+ *       401:
+ *         description: Unauthorized
+ *       429:
+ *         description: Rate limit exceeded
+ *       500:
+ *         description: Internal server error
+ */
+router.post('/', async (req: Request, res: Response) => {
+  try {
+    const request: MessageCreateParams = req.body
+
+    if (!request) {
+      return res.status(400).json({
+        type: 'error',
+        error: {
+          type: 'invalid_request_error',
+          message: 'Request body is required'
+        }
+      })
+    }
+
+    logger.info('Anthropic message request:', {
+      model: request.model,
+      messageCount: request.messages?.length || 0,
+      stream: request.stream,
+      max_tokens: request.max_tokens,
+      temperature: request.temperature
+    })
+
+    // Validate model ID and get provider
+    const modelValidation = await validateModelId(request.model)
+    if (!modelValidation.valid) {
+      const error = modelValidation.error!
+      logger.warn(`Model validation failed for '${request.model}':`, error)
+      return res.status(400).json({
+        type: 'error',
+        error: {
+          type: 'invalid_request_error',
+          message: error.message
+        }
+      })
+    }
+
+    const provider = modelValidation.provider!
+
+    // Ensure provider is Anthropic type
+    if (provider.type !== 'anthropic') {
+      return res.status(400).json({
+        type: 'error',
+        error: {
+          type: 'invalid_request_error',
+          message: `Invalid provider type '${provider.type}' for messages endpoint. Expected 'anthropic' provider.`
+        }
+      })
+    }
+
+    const modelId = modelValidation.modelId!
+    request.model = modelId
+
+    logger.info('Model validation successful:', {
+      provider: provider.id,
+      providerType: provider.type,
+      modelId: modelId,
+      fullModelId: request.model
+    })
+
+    // Validate request
+    const validation = messagesService.validateRequest(request)
+    if (!validation.isValid) {
+      return res.status(400).json({
+        type: 'error',
+        error: {
+          type: 'invalid_request_error',
+          message: validation.errors.join('; ')
+        }
+      })
+    }
+
+    // Handle streaming
+    if (request.stream) {
+      res.setHeader('Content-Type', 'text/event-stream; charset=utf-8')
+      res.setHeader('Cache-Control', 'no-cache, no-transform')
+      res.setHeader('Connection', 'keep-alive')
+      res.setHeader('X-Accel-Buffering', 'no')
+      res.flushHeaders()
+
+      try {
+        for await (const chunk of messagesService.processStreamingMessage(request, provider)) {
+          res.write(`data: ${JSON.stringify(chunk)}\n\n`)
+        }
+        res.write('data: [DONE]\n\n')
+      } catch (streamError: any) {
+        logger.error('Stream error:', streamError)
+        res.write(
+          `data: ${JSON.stringify({
+            type: 'error',
+            error: {
+              type: 'api_error',
+              message: 'Stream processing error'
+            }
+          })}\n\n`
+        )
+      } finally {
+        res.end()
+      }
+      return
+    }
+
+    // Handle non-streaming
+    const response = await messagesService.processMessage(request, provider)
+    return res.json(response)
+  } catch (error: any) {
+    logger.error('Anthropic message error:', error)
+
+    let statusCode = 500
+    let errorType = 'api_error'
+    let errorMessage = 'Internal server error'
+
+    const anthropicStatus = typeof error?.status === 'number' ? error.status : undefined
+    const anthropicError = error?.error
+
+    if (anthropicStatus) {
+      statusCode = anthropicStatus
+    }
+
+    if (anthropicError?.type) {
+      errorType = anthropicError.type
+    }
+
+    if (anthropicError?.message) {
+      errorMessage = anthropicError.message
+    } else if (error instanceof Error && error.message) {
+      errorMessage = error.message
+    }
+
+    if (!anthropicStatus && error instanceof Error) {
+      if (error.message.includes('API key') || error.message.includes('authentication')) {
+        statusCode = 401
+        errorType = 'authentication_error'
+      } else if (error.message.includes('rate limit') || error.message.includes('quota')) {
+        statusCode = 429
+        errorType = 'rate_limit_error'
+      } else if (error.message.includes('timeout') || error.message.includes('connection')) {
+        statusCode = 502
+        errorType = 'api_error'
+      } else if (error.message.includes('validation') || error.message.includes('invalid')) {
+        statusCode = 400
+        errorType = 'invalid_request_error'
+      }
+    }
+
+    return res.status(statusCode).json({
+      type: 'error',
+      error: {
+        type: errorType,
+        message: errorMessage,
+        requestId: error?.request_id
+      }
+    })
+  }
+})
+
+export { router as messagesRoutes }

src/main/apiServer/routes/models.ts

@@ -0,0 +1,130 @@
+import { ApiModelsFilterSchema, ApiModelsResponse } from '@types'
+import express, { Request, Response } from 'express'
+
+import { loggerService } from '../../services/LoggerService'
+import { modelsService } from '../services/models'
+
+const logger = loggerService.withContext('ApiServerModelsRoutes')
+
+const router = express
+  .Router()
+
+  /**
+   * @swagger
+   * /v1/models:
+   *   get:
+   *     summary: List available models
+   *     description: Returns a list of available AI models from all configured providers with optional filtering
+   *     tags: [Models]
+   *     parameters:
+   *       - in: query
+   *         name: providerType
+   *         schema:
+   *           type: string
+   *           enum: [openai, openai-response, anthropic, gemini]
+   *         description: Filter models by provider type
+   *       - in: query
+   *         name: offset
+   *         schema:
+   *           type: integer
+   *           minimum: 0
+   *           default: 0
+   *         description: Pagination offset
+   *       - in: query
+   *         name: limit
+   *         schema:
+   *           type: integer
+   *           minimum: 1
+   *         description: Maximum number of models to return
+   *     responses:
+   *       200:
+   *         description: List of available models
+   *         content:
+   *           application/json:
+   *             schema:
+   *               type: object
+   *               properties:
+   *                 object:
+   *                   type: string
+   *                   example: list
+   *                 data:
+   *                   type: array
+   *                   items:
+   *                     $ref: '#/components/schemas/Model'
+   *                 total:
+   *                   type: integer
+   *                   description: Total number of models (when using pagination)
+   *                 offset:
+   *                   type: integer
+   *                   description: Current offset (when using pagination)
+   *                 limit:
+   *                   type: integer
+   *                   description: Current limit (when using pagination)
+   *       400:
+   *         description: Invalid query parameters
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/Error'
+   *       503:
+   *         description: Service unavailable
+   *         content:
+   *           application/json:
+   *             schema:
+   *               $ref: '#/components/schemas/Error'
+   */
+  .get('/', async (req: Request, res: Response) => {
+    try {
+      logger.info('Models list request received', { query: req.query })
+
+      // Validate query parameters using Zod schema
+      const filterResult = ApiModelsFilterSchema.safeParse(req.query)
+
+      if (!filterResult.success) {
+        logger.warn('Invalid query parameters:', filterResult.error.issues)
+        return res.status(400).json({
+          error: {
+            message: 'Invalid query parameters',
+            type: 'invalid_request_error',
+            code: 'invalid_parameters',
+            details: filterResult.error.issues.map((issue) => ({
+              field: issue.path.join('.'),
+              message: issue.message
+            }))
+          }
+        })
+      }
+
+      const filter = filterResult.data
+      const response = await modelsService.getModels(filter)
+
+      if (response.data.length === 0) {
+        logger.warn(
+          'No models available from providers. This may be because no OpenAI/Anthropic providers are configured or enabled.',
+          { filter }
+        )
+      }
+
+      logger.info(`Returning ${response.data.length} models`, {
+        filter,
+        total: response.total
+      })
+      logger.debug(
+        'Model IDs:',
+        response.data.map((m) => m.id)
+      )
+
+      return res.json(response satisfies ApiModelsResponse)
+    } catch (error: any) {
+      logger.error('Error fetching models:', error)
+      return res.status(503).json({
+        error: {
+          message: 'Failed to retrieve models from available providers',
+          type: 'service_unavailable',
+          code: 'models_unavailable'
+        }
+      })
+    }
+  })
+
+export { router as modelsRoutes }

src/main/apiServer/server.ts

@@ -0,0 +1,71 @@
+import { createServer } from 'node:http'
+
+import { agentService } from '../services/agents'
+import { loggerService } from '../services/LoggerService'
+import { app } from './app'
+import { config } from './config'
+
+const logger = loggerService.withContext('ApiServer')
+
+export class ApiServer {
+  private server: ReturnType<typeof createServer> | null = null
+
+  async start(): Promise<void> {
+    if (this.server) {
+      logger.warn('Server already running')
+      return
+    }
+
+    // Load config
+    const { port, host, apiKey } = await config.load()
+
+    // Initialize AgentService
+    logger.info('Initializing AgentService...')
+    await agentService.initialize()
+    logger.info('AgentService initialized successfully')
+
+    // Create server with Express app
+    this.server = createServer(app)
+
+    // Start server
+    return new Promise((resolve, reject) => {
+      this.server!.listen(port, host, () => {
+        logger.info(`API Server started at http://${host}:${port}`)
+        logger.info(`API Key: ${apiKey}`)
+        resolve()
+      })
+
+      this.server!.on('error', reject)
+    })
+  }
+
+  async stop(): Promise<void> {
+    if (!this.server) return
+
+    return new Promise((resolve) => {
+      this.server!.close(() => {
+        logger.info('API Server stopped')
+        this.server = null
+        resolve()
+      })
+    })
+  }
+
+  async restart(): Promise<void> {
+    await this.stop()
+    await config.reload()
+    await this.start()
+  }
+
+  isRunning(): boolean {
+    const hasServer = this.server !== null
+    const isListening = this.server?.listening || false
+    const result = hasServer && isListening
+
+    logger.debug('isRunning check:', { hasServer, isListening, result })
+
+    return result
+  }
+}
+
+export const apiServer = new ApiServer()

src/main/apiServer/services/chat-completion.ts

@@ -0,0 +1,248 @@
+import { Provider } from '@types'
+import OpenAI from 'openai'
+import { ChatCompletionCreateParams, ChatCompletionCreateParamsStreaming } from 'openai/resources'
+
+import { loggerService } from '../../services/LoggerService'
+import { ModelValidationError, validateModelId } from '../utils'
+
+const logger = loggerService.withContext('ChatCompletionService')
+
+export interface ValidationResult {
+  isValid: boolean
+  errors: string[]
+}
+
+export class ChatCompletionValidationError extends Error {
+  constructor(public readonly errors: string[]) {
+    super(`Request validation failed: ${errors.join('; ')}`)
+    this.name = 'ChatCompletionValidationError'
+  }
+}
+
+export class ChatCompletionModelError extends Error {
+  constructor(public readonly error: ModelValidationError) {
+    super(`Model validation failed: ${error.message}`)
+    this.name = 'ChatCompletionModelError'
+  }
+}
+
+export type PrepareRequestResult =
+  | { status: 'validation_error'; errors: string[] }
+  | { status: 'model_error'; error: ModelValidationError }
+  | {
+      status: 'ok'
+      provider: Provider
+      modelId: string
+      client: OpenAI
+      providerRequest: ChatCompletionCreateParams
+    }
+
+export class ChatCompletionService {
+  async resolveProviderContext(model: string): Promise<
+    | { ok: false; error: ModelValidationError }
+    | { ok: true; provider: Provider; modelId: string; client: OpenAI }
+  > {
+    const modelValidation = await validateModelId(model)
+    if (!modelValidation.valid) {
+      return {
+        ok: false,
+        error: modelValidation.error!
+      }
+    }
+
+    const provider = modelValidation.provider!
+
+    if (provider.type !== 'openai') {
+      return {
+        ok: false,
+        error: {
+          type: 'unsupported_provider_type',
+          message: `Provider '${provider.id}' of type '${provider.type}' is not supported for OpenAI chat completions`,
+          code: 'unsupported_provider_type'
+        }
+      }
+    }
+
+    const modelId = modelValidation.modelId!
+
+    const client = new OpenAI({
+      baseURL: provider.apiHost,
+      apiKey: provider.apiKey
+    })
+
+    return {
+      ok: true,
+      provider,
+      modelId,
+      client
+    }
+  }
+
+  async prepareRequest(request: ChatCompletionCreateParams, stream: boolean): Promise<PrepareRequestResult> {
+    const requestValidation = this.validateRequest(request)
+    if (!requestValidation.isValid) {
+      return {
+        status: 'validation_error',
+        errors: requestValidation.errors
+      }
+    }
+
+    const providerContext = await this.resolveProviderContext(request.model!)
+    if (!providerContext.ok) {
+      return {
+        status: 'model_error',
+        error: providerContext.error
+      }
+    }
+
+    const { provider, modelId, client } = providerContext
+
+    logger.info('Model validation successful:', {
+      provider: provider.id,
+      providerType: provider.type,
+      modelId,
+      fullModelId: request.model
+    })
+
+    return {
+      status: 'ok',
+      provider,
+      modelId,
+      client,
+      providerRequest: stream
+        ? {
+            ...request,
+            model: modelId,
+            stream: true as const
+          }
+        : {
+            ...request,
+            model: modelId,
+            stream: false as const
+          }
+    }
+  }
+
+  validateRequest(request: ChatCompletionCreateParams): ValidationResult {
+    const errors: string[] = []
+
+    // Validate messages
+    if (!request.messages) {
+      errors.push('Messages array is required')
+    } else if (!Array.isArray(request.messages)) {
+      errors.push('Messages must be an array')
+    } else if (request.messages.length === 0) {
+      errors.push('Messages array cannot be empty')
+    } else {
+      // Validate each message
+      request.messages.forEach((message, index) => {
+        if (!message.role) {
+          errors.push(`Message ${index}: role is required`)
+        }
+        if (!message.content) {
+          errors.push(`Message ${index}: content is required`)
+        }
+      })
+    }
+
+    // Validate optional parameters
+
+    return {
+      isValid: errors.length === 0,
+      errors
+    }
+  }
+
+  async processCompletion(request: ChatCompletionCreateParams): Promise<{
+    provider: Provider
+    modelId: string
+    response: OpenAI.Chat.Completions.ChatCompletion
+  }> {
+    try {
+      logger.info('Processing chat completion request:', {
+        model: request.model,
+        messageCount: request.messages.length,
+        stream: request.stream
+      })
+
+      const preparation = await this.prepareRequest(request, false)
+      if (preparation.status === 'validation_error') {
+        throw new ChatCompletionValidationError(preparation.errors)
+      }
+
+      if (preparation.status === 'model_error') {
+        throw new ChatCompletionModelError(preparation.error)
+      }
+
+      const { provider, modelId, client, providerRequest } = preparation
+
+      logger.debug('Sending request to provider:', {
+        provider: provider.id,
+        model: modelId,
+        apiHost: provider.apiHost
+      })
+
+      const response = (await client.chat.completions.create(providerRequest)) as OpenAI.Chat.Completions.ChatCompletion
+
+      logger.info('Successfully processed chat completion')
+      return {
+        provider,
+        modelId,
+        response
+      }
+    } catch (error: any) {
+      logger.error('Error processing chat completion:', error)
+      throw error
+    }
+  }
+
+  async processStreamingCompletion(
+    request: ChatCompletionCreateParams
+  ): Promise<{
+    provider: Provider
+    modelId: string
+    stream: AsyncIterable<OpenAI.Chat.Completions.ChatCompletionChunk>
+  }> {
+    try {
+      logger.info('Processing streaming chat completion request:', {
+        model: request.model,
+        messageCount: request.messages.length
+      })
+
+      const preparation = await this.prepareRequest(request, true)
+      if (preparation.status === 'validation_error') {
+        throw new ChatCompletionValidationError(preparation.errors)
+      }
+
+      if (preparation.status === 'model_error') {
+        throw new ChatCompletionModelError(preparation.error)
+      }
+
+      const { provider, modelId, client, providerRequest } = preparation
+
+      logger.debug('Sending streaming request to provider:', {
+        provider: provider.id,
+        model: modelId,
+        apiHost: provider.apiHost
+      })
+
+      const streamRequest = providerRequest as ChatCompletionCreateParamsStreaming
+      const stream = (await client.chat.completions.create(streamRequest)) as AsyncIterable<
+        OpenAI.Chat.Completions.ChatCompletionChunk
+      >
+
+      logger.info('Successfully started streaming chat completion')
+      return {
+        provider,
+        modelId,
+        stream
+      }
+    } catch (error: any) {
+      logger.error('Error processing streaming chat completion:', error)
+      throw error
+    }
+  }
+}
+
+// Export singleton instance
+export const chatCompletionService = new ChatCompletionService()

src/main/apiServer/services/mcp.ts

@@ -0,0 +1,226 @@
+import mcpService from '@main/services/MCPService'
+import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp'
+import {
+  isJSONRPCRequest,
+  JSONRPCMessage,
+  JSONRPCMessageSchema,
+  MessageExtraInfo
+} from '@modelcontextprotocol/sdk/types'
+import { MCPServer } from '@types'
+import { randomUUID } from 'crypto'
+import { EventEmitter } from 'events'
+import { Request, Response } from 'express'
+import { IncomingMessage, ServerResponse } from 'http'
+
+import { loggerService } from '../../services/LoggerService'
+import { getMcpServerById, getMCPServersFromRedux } from '../utils/mcp'
+
+const logger = loggerService.withContext('MCPApiService')
+const transports: Record<string, StreamableHTTPServerTransport> = {}
+
+interface McpServerDTO {
+  id: MCPServer['id']
+  name: MCPServer['name']
+  type: MCPServer['type']
+  description: MCPServer['description']
+  url: string
+}
+
+interface McpServersResp {
+  servers: Record<string, McpServerDTO>
+}
+
+/**
+ * MCPApiService - API layer for MCP server management
+ *
+ * This service provides a REST API interface for MCP servers while integrating
+ * with the existing application architecture:
+ *
+ * 1. Uses ReduxService to access the renderer's Redux store directly
+ * 2. Syncs changes back to the renderer via Redux actions
+ * 3. Leverages existing MCPService for actual server connections
+ * 4. Provides session management for API clients
+ */
+class MCPApiService extends EventEmitter {
+  private transport: StreamableHTTPServerTransport = new StreamableHTTPServerTransport({
+    sessionIdGenerator: () => randomUUID()
+  })
+
+  constructor() {
+    super()
+    this.initMcpServer()
+    logger.silly('MCPApiService initialized')
+  }
+
+  private initMcpServer() {
+    this.transport.onmessage = this.onMessage
+  }
+
+  // get all activated servers
+  async getAllServers(req: Request): Promise<McpServersResp> {
+    try {
+      const servers = await getMCPServersFromRedux()
+      logger.silly(`Returning ${servers.length} servers`)
+      const resp: McpServersResp = {
+        servers: {}
+      }
+      for (const server of servers) {
+        if (server.isActive) {
+          resp.servers[server.id] = {
+            id: server.id,
+            name: server.name,
+            type: 'streamableHttp',
+            description: server.description,
+            url: `${req.protocol}://${req.host}/v1/mcps/${server.id}/mcp`
+          }
+        }
+      }
+      return resp
+    } catch (error: any) {
+      logger.error('Failed to get all servers:', error)
+      throw new Error('Failed to retrieve servers')
+    }
+  }
+
+  // get server by id
+  async getServerById(id: string): Promise<MCPServer | null> {
+    try {
+      logger.silly(`getServerById called with id: ${id}`)
+      const servers = await getMCPServersFromRedux()
+      const server = servers.find((s) => s.id === id)
+      if (!server) {
+        logger.warn(`Server with id ${id} not found`)
+        return null
+      }
+      logger.silly(`Returning server with id ${id}`)
+      return server
+    } catch (error: any) {
+      logger.error(`Failed to get server with id ${id}:`, error)
+      throw new Error('Failed to retrieve server')
+    }
+  }
+
+  async getServerInfo(id: string): Promise<any> {
+    try {
+      logger.silly(`getServerInfo called with id: ${id}`)
+      const server = await this.getServerById(id)
+      if (!server) {
+        logger.warn(`Server with id ${id} not found`)
+        return null
+      }
+      logger.silly(`Returning server info for id ${id}`)
+
+      const client = await mcpService.initClient(server)
+      const tools = await client.listTools()
+
+      logger.info(`Server with id ${id} info:`, { tools: JSON.stringify(tools) })
+
+      // const [version, tools, prompts, resources] = await Promise.all([
+      //   () => {
+      //     try {
+      //       return client.getServerVersion()
+      //     } catch (error) {
+      //       logger.error(`Failed to get server version for id ${id}:`, { error: error })
+      //       return '1.0.0'
+      //     }
+      //   },
+      //   (() => {
+      //     try {
+      //       return client.listTools()
+      //     } catch (error) {
+      //       logger.error(`Failed to list tools for id ${id}:`, { error: error })
+      //       return []
+      //     }
+      //   })(),
+      //   (() => {
+      //     try {
+      //       return client.listPrompts()
+      //     } catch (error) {
+      //       logger.error(`Failed to list prompts for id ${id}:`, { error: error })
+      //       return []
+      //     }
+      //   })(),
+      //   (() => {
+      //     try {
+      //       return client.listResources()
+      //     } catch (error) {
+      //       logger.error(`Failed to list resources for id ${id}:`, { error: error })
+      //       return []
+      //     }
+      //   })()
+      // ])
+
+      return {
+        id: server.id,
+        name: server.name,
+        type: server.type,
+        description: server.description,
+        tools
+      }
+    } catch (error: any) {
+      logger.error(`Failed to get server info with id ${id}:`, error)
+      throw new Error('Failed to retrieve server info')
+    }
+  }
+
+  async handleRequest(req: Request, res: Response, server: MCPServer) {
+    const sessionId = req.headers['mcp-session-id'] as string | undefined
+    logger.silly(`Handling request for server with sessionId ${sessionId}`)
+    let transport: StreamableHTTPServerTransport
+    if (sessionId && transports[sessionId]) {
+      transport = transports[sessionId]
+    } else {
+      transport = new StreamableHTTPServerTransport({
+        sessionIdGenerator: () => randomUUID(),
+        onsessioninitialized: (sessionId) => {
+          transports[sessionId] = transport
+        }
+      })
+
+      transport.onclose = () => {
+        logger.info(`Transport for sessionId ${sessionId} closed`)
+        if (transport.sessionId) {
+          delete transports[transport.sessionId]
+        }
+      }
+      const mcpServer = await getMcpServerById(server.id)
+      if (mcpServer) {
+        await mcpServer.connect(transport)
+      }
+    }
+    const jsonpayload = req.body
+    const messages: JSONRPCMessage[] = []
+
+    if (Array.isArray(jsonpayload)) {
+      for (const payload of jsonpayload) {
+        const message = JSONRPCMessageSchema.parse(payload)
+        messages.push(message)
+      }
+    } else {
+      const message = JSONRPCMessageSchema.parse(jsonpayload)
+      messages.push(message)
+    }
+
+    for (const message of messages) {
+      if (isJSONRPCRequest(message)) {
+        if (!message.params) {
+          message.params = {}
+        }
+        if (!message.params._meta) {
+          message.params._meta = {}
+        }
+        message.params._meta.serverId = server.id
+      }
+    }
+
+    logger.info(`Request body`, { rawBody: req.body, messages: JSON.stringify(messages) })
+    await transport.handleRequest(req as IncomingMessage, res as ServerResponse, messages)
+  }
+
+  private onMessage(message: JSONRPCMessage, extra?: MessageExtraInfo) {
+    logger.info(`Received message: ${JSON.stringify(message)}`, extra)
+    // Handle message here
+  }
+}
+
+export const mcpApiService = new MCPApiService()

src/main/apiServer/services/messages.ts

@@ -0,0 +1,106 @@
+import Anthropic from '@anthropic-ai/sdk'
+import { Message, MessageCreateParams, RawMessageStreamEvent } from '@anthropic-ai/sdk/resources'
+import { Provider } from '@types'
+
+import { loggerService } from '../../services/LoggerService'
+
+const logger = loggerService.withContext('MessagesService')
+
+export interface ValidationResult {
+  isValid: boolean
+  errors: string[]
+}
+
+export class MessagesService {
+  // oxlint-disable-next-line no-unused-vars
+  validateRequest(request: MessageCreateParams): ValidationResult {
+    // TODO: Implement comprehensive request validation
+    const errors: string[] = []
+
+    if (!request.model) {
+      errors.push('Model is required')
+    }
+
+    if (!request.max_tokens || request.max_tokens < 1) {
+      errors.push('max_tokens is required and must be at least 1')
+    }
+
+    if (!request.messages || !Array.isArray(request.messages) || request.messages.length === 0) {
+      errors.push('messages is required and must be a non-empty array')
+    }
+
+    return {
+      isValid: errors.length === 0,
+      errors
+    }
+  }
+
+  async processMessage(request: MessageCreateParams, provider: Provider): Promise<Message> {
+    logger.info('Processing Anthropic message request:', {
+      model: request.model,
+      messageCount: request.messages.length,
+      stream: request.stream,
+      max_tokens: request.max_tokens
+    })
+
+    // Create Anthropic client for the provider
+    const client = new Anthropic({
+      baseURL: provider.apiHost,
+      apiKey: provider.apiKey
+    })
+
+    // Prepare request with the actual model ID
+    const anthropicRequest: MessageCreateParams = {
+      ...request,
+      stream: false
+    }
+
+    logger.debug('Sending request to Anthropic provider:', {
+      provider: provider.id,
+      apiHost: provider.apiHost
+    })
+
+    const response = await client.messages.create(anthropicRequest)
+
+    logger.info('Successfully processed Anthropic message')
+    return response
+  }
+
+  async *processStreamingMessage(
+    request: MessageCreateParams,
+    provider: Provider
+  ): AsyncIterable<RawMessageStreamEvent> {
+    logger.info('Processing streaming Anthropic message request:', {
+      model: request.model,
+      messageCount: request.messages.length
+    })
+
+    // Create Anthropic client for the provider
+    const client = new Anthropic({
+      baseURL: provider.apiHost,
+      apiKey: provider.apiKey
+    })
+
+    // Prepare streaming request
+    const streamingRequest: MessageCreateParams = {
+      ...request,
+      stream: true
+    }
+
+    logger.debug('Sending streaming request to Anthropic provider:', {
+      provider: provider.id,
+      apiHost: provider.apiHost
+    })
+
+    const stream = client.messages.stream(streamingRequest)
+
+    for await (const chunk of stream) {
+      yield chunk
+    }
+
+    logger.info('Successfully completed streaming Anthropic message')
+  }
+}
+
+// Export singleton instance
+export const messagesService = new MessagesService()

src/main/apiServer/services/models.ts

@@ -0,0 +1,93 @@
+import { ApiModel, ApiModelsFilter, ApiModelsResponse } from '../../../renderer/src/types/apiModels'
+import { loggerService } from '../../services/LoggerService'
+import { getAvailableProviders, listAllAvailableModels, transformModelToOpenAI } from '../utils'
+
+const logger = loggerService.withContext('ModelsService')
+
+// Re-export for backward compatibility
+
+export type ModelsFilter = ApiModelsFilter
+
+export class ModelsService {
+  async getModels(filter: ModelsFilter): Promise<ApiModelsResponse> {
+    try {
+      logger.debug('Getting available models from providers', { filter })
+
+      const models = await listAllAvailableModels()
+      const providers = await getAvailableProviders()
+
+      // Use Map to deduplicate models by their full ID (provider:model_id)
+      const uniqueModels = new Map<string, ApiModel>()
+
+      for (const model of models) {
+        const openAIModel = transformModelToOpenAI(model, providers)
+        const fullModelId = openAIModel.id // This is already in format "provider:model_id"
+
+        // Only add if not already present (first occurrence wins)
+        if (!uniqueModels.has(fullModelId)) {
+          uniqueModels.set(fullModelId, openAIModel)
+        } else {
+          logger.debug(`Skipping duplicate model: ${fullModelId}`)
+        }
+      }
+
+      let modelData = Array.from(uniqueModels.values())
+      if (filter.providerType) {
+        // Apply filters
+        const providerType = filter.providerType
+        modelData = modelData.filter((model) => {
+          // Find the provider for this model and check its type
+          return model.provider_type === providerType
+        })
+        logger.debug(`Filtered by provider type '${providerType}': ${modelData.length} models`)
+      }
+
+      const total = modelData.length
+
+      // Apply pagination
+      const offset = filter?.offset || 0
+      const limit = filter?.limit
+
+      if (limit !== undefined) {
+        modelData = modelData.slice(offset, offset + limit)
+        logger.debug(
+          `Applied pagination: offset=${offset}, limit=${limit}, showing ${modelData.length} of ${total} models`
+        )
+      } else if (offset > 0) {
+        modelData = modelData.slice(offset)
+        logger.debug(`Applied offset: offset=${offset}, showing ${modelData.length} of ${total} models`)
+      }
+
+      logger.info(`Successfully retrieved ${modelData.length} models from ${models.length} total models`)
+
+      if (models.length > total) {
+        logger.debug(`Filtered out ${models.length - total} models after deduplication and filtering`)
+      }
+
+      const response: ApiModelsResponse = {
+        object: 'list',
+        data: modelData
+      }
+
+      // Add pagination metadata if applicable
+      if (filter?.limit !== undefined || filter?.offset !== undefined) {
+        response.total = total
+        response.offset = offset
+        if (filter?.limit !== undefined) {
+          response.limit = filter.limit
+        }
+      }
+
+      return response
+    } catch (error: any) {
+      logger.error('Error getting models:', error)
+      return {
+        object: 'list',
+        data: []
+      }
+    }
+  }
+}
+
+// Export singleton instance
+export const modelsService = new ModelsService()