add model catalogs

.editorconfig

@@ -1,9 +1,9 @@
-root = true
-
-[*]
-charset = utf-8
-indent_style = space
-indent_size = 2
-end_of_line = lf
-insert_final_newline = true
-trim_trailing_whitespace = true
+root = true
+
+[*]
+charset = utf-8
+indent_style = space
+indent_size = 2
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true

.git-blame-ignore-revs

@@ -1,2 +0,0 @@
-# ignore #7923 eol change and code formatting
-4ac8a388347ff35f34de42c3ef4a2f81f03fb3b1

.gitattributes

@@ -1,3 +1,2 @@
-* text=auto eol=lf
 /.yarn/**            linguist-vendored
 /.yarn/releases/*    binary

.github/ISSUE_TEMPLATE/#3_others.yml

@@ -73,4 +73,4 @@ body:
     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
+      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/ISSUE_TEMPLATE/3_others.yml

@@ -73,4 +73,4 @@ body:
     id: additional
     attributes:
       label: Additional Information
-      description: Any other information that could help us better understand your question, including screenshots or relevant links
+      description: Any other information that could help us better understand your question, including screenshots or relevant links

.github/issue-checker.yml

@@ -9,115 +9,115 @@ labels:
   # skips and removes
   - name: skip all
     content:
-    regexes: '[Ss]kip (?:[Aa]ll |)[Ll]abels?'
+    regexes: "[Ss]kip (?:[Aa]ll |)[Ll]abels?"
   - name: remove all
     content:
-    regexes: '[Rr]emove (?:[Aa]ll |)[Ll]abels?'
+    regexes: "[Rr]emove (?:[Aa]ll |)[Ll]abels?"
 
   - name: skip kind/bug
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)kind/bug(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)kind/bug(?:`|)"
   - name: remove kind/bug
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)kind/bug(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)kind/bug(?:`|)"
 
   - name: skip kind/enhancement
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)kind/enhancement(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)kind/enhancement(?:`|)"
   - name: remove kind/enhancement
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)kind/enhancement(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)kind/enhancement(?:`|)"
 
   - name: skip kind/question
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)kind/question(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)kind/question(?:`|)"
   - name: remove kind/question
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)kind/question(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)kind/question(?:`|)"
 
   - name: skip area/Connectivity
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)area/Connectivity(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)area/Connectivity(?:`|)"
   - name: remove area/Connectivity
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)area/Connectivity(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)area/Connectivity(?:`|)"
 
   - name: skip area/UI/UX
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)area/UI/UX(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)area/UI/UX(?:`|)"
   - name: remove area/UI/UX
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)area/UI/UX(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)area/UI/UX(?:`|)"
 
   - name: skip kind/documentation
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)kind/documentation(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)kind/documentation(?:`|)"
   - name: remove kind/documentation
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)kind/documentation(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)kind/documentation(?:`|)"
 
   - name: skip client:linux
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)client:linux(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)client:linux(?:`|)"
   - name: remove client:linux
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)client:linux(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)client:linux(?:`|)"
 
   - name: skip client:mac
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)client:mac(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)client:mac(?:`|)"
   - name: remove client:mac
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)client:mac(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)client:mac(?:`|)"
 
   - name: skip client:win
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)client:win(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)client:win(?:`|)"
   - name: remove client:win
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)client:win(?:`|)'
-
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)client:win(?:`|)"
+  
   - name: skip sig/Assistant
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)sig/Assistant(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)sig/Assistant(?:`|)"
   - name: remove sig/Assistant
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)sig/Assistant(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)sig/Assistant(?:`|)"
 
   - name: skip sig/Data
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)sig/Data(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)sig/Data(?:`|)"
   - name: remove sig/Data
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)sig/Data(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)sig/Data(?:`|)"
 
   - name: skip sig/MCP
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)sig/MCP(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)sig/MCP(?:`|)"
   - name: remove sig/MCP
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)sig/MCP(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)sig/MCP(?:`|)"
 
   - name: skip sig/RAG
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)sig/RAG(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)sig/RAG(?:`|)"
   - name: remove sig/RAG
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)sig/RAG(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)sig/RAG(?:`|)"
 
   - name: skip lgtm
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)lgtm(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)lgtm(?:`|)"
   - name: remove lgtm
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)lgtm(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)lgtm(?:`|)"
 
   - name: skip License
     content:
-    regexes: '[Ss]kip (?:[Ll]abels? |)(?:`|)License(?:`|)'
+    regexes: "[Ss]kip (?:[Ll]abels? |)(?:`|)License(?:`|)"
   - name: remove License
     content:
-    regexes: '[Rr]emove (?:[Ll]abels? |)(?:`|)License(?:`|)'
+    regexes: "[Rr]emove (?:[Ll]abels? |)(?:`|)License(?:`|)"
 
   # `Dev Team`
   - name: Dev Team
@@ -129,7 +129,7 @@ labels:
   # Area labels
   - name: area/Connectivity
     content: area/Connectivity
-    regexes: '代理|[Pp]roxy'
+    regexes: "代理|[Pp]roxy"
     skip-if:
       - skip all
       - skip area/Connectivity
@@ -139,7 +139,7 @@ labels:
 
   - name: area/UI/UX
     content: area/UI/UX
-    regexes: '界面|[Uu][Ii]|重叠|按钮|图标|组件|渲染|菜单|栏目|头像|主题|样式|[Cc][Ss][Ss]'
+    regexes: "界面|[Uu][Ii]|重叠|按钮|图标|组件|渲染|菜单|栏目|头像|主题|样式|[Cc][Ss][Ss]"
     skip-if:
       - skip all
       - skip area/UI/UX
@@ -150,7 +150,7 @@ labels:
   # Kind labels
   - name: kind/documentation
     content: kind/documentation
-    regexes: '文档|教程|[Dd]oc(s|umentation)|[Rr]eadme'
+    regexes: "文档|教程|[Dd]oc(s|umentation)|[Rr]eadme"
     skip-if:
       - skip all
       - skip kind/documentation
@@ -161,7 +161,7 @@ labels:
   # Client labels
   - name: client:linux
     content: client:linux
-    regexes: '(?:[Ll]inux|[Uu]buntu|[Dd]ebian)'
+    regexes: "(?:[Ll]inux|[Uu]buntu|[Dd]ebian)"
     skip-if:
       - skip all
       - skip client:linux
@@ -171,7 +171,7 @@ labels:
 
   - name: client:mac
     content: client:mac
-    regexes: '(?:[Mm]ac|[Mm]acOS|[Oo]SX)'
+    regexes: "(?:[Mm]ac|[Mm]acOS|[Oo]SX)"
     skip-if:
       - skip all
       - skip client:mac
@@ -181,7 +181,7 @@ labels:
 
   - name: client:win
     content: client:win
-    regexes: '(?:[Ww]in|[Ww]indows)'
+    regexes: "(?:[Ww]in|[Ww]indows)"
     skip-if:
       - skip all
       - skip client:win
@@ -192,7 +192,7 @@ labels:
   # SIG labels
   - name: sig/Assistant
     content: sig/Assistant
-    regexes: '快捷助手|[Aa]ssistant'
+    regexes: "快捷助手|[Aa]ssistant"
     skip-if:
       - skip all
       - skip sig/Assistant
@@ -202,7 +202,7 @@ labels:
 
   - name: sig/Data
     content: sig/Data
-    regexes: '[Ww]ebdav|坚果云|备份|同步|数据|Obsidian|Notion|Joplin|思源'
+    regexes: "[Ww]ebdav|坚果云|备份|同步|数据|Obsidian|Notion|Joplin|思源"
     skip-if:
       - skip all
       - skip sig/Data
@@ -212,7 +212,7 @@ labels:
 
   - name: sig/MCP
     content: sig/MCP
-    regexes: '[Mm][Cc][Pp]'
+    regexes: "[Mm][Cc][Pp]"
     skip-if:
       - skip all
       - skip sig/MCP
@@ -222,7 +222,7 @@ labels:
 
   - name: sig/RAG
     content: sig/RAG
-    regexes: '知识库|[Rr][Aa][Gg]'
+    regexes: "知识库|[Rr][Aa][Gg]"
     skip-if:
       - skip all
       - skip sig/RAG
@@ -233,7 +233,7 @@ labels:
   # Other labels
   - name: lgtm
     content: lgtm
-    regexes: '(?:[Ll][Gg][Tt][Mm]|[Ll]ooks [Gg]ood [Tt]o [Mm]e)'
+    regexes: "(?:[Ll][Gg][Tt][Mm]|[Ll]ooks [Gg]ood [Tt]o [Mm]e)"
     skip-if:
       - skip all
       - skip lgtm
@@ -243,7 +243,7 @@ labels:
 
   - name: License
     content: License
-    regexes: '(?:[Ll]icense|[Cc]opyright|[Mm][Ii][Tt]|[Aa]pache)'
+    regexes: "(?:[Ll]icense|[Cc]opyright|[Mm][Ii][Tt]|[Aa]pache)"
     skip-if:
       - skip all
       - skip License

.github/workflows/issue-checker.yml

@@ -1,4 +1,4 @@
-name: 'Issue Checker'
+name: "Issue Checker"
 
 on:
   issues:
@@ -19,7 +19,7 @@ jobs:
     steps:
       - uses: MaaAssistantArknights/issue-checker@v1.14
         with:
-          repo-token: '${{ secrets.GITHUB_TOKEN }}'
+          repo-token: "${{ secrets.GITHUB_TOKEN }}"
           configuration-path: .github/issue-checker.yml
           not-before: 2022-08-05T00:00:00Z
-          include-title: 1
+          include-title: 1

.github/workflows/issue-management.yml

@@ -1,8 +1,8 @@
-name: 'Stale Issue Management'
+name: "Stale Issue Management"
 
 on:
   schedule:
-    - cron: '0 0 * * *'
+    - cron: "0 0 * * *"
   workflow_dispatch:
 
 env:
@@ -24,18 +24,18 @@ jobs:
         uses: actions/stale@v9
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          only-labels: 'needs-more-info'
+          only-labels: "needs-more-info"
           days-before-stale: ${{ env.daysBeforeStale }}
-          days-before-close: 0 # Close immediately after stale
-          stale-issue-label: 'inactive'
-          close-issue-label: 'closed:no-response'
+          days-before-close: 0  # Close immediately after stale
+          stale-issue-label: "inactive"
+          close-issue-label: "closed:no-response"
           stale-issue-message: |
             This issue has been labeled as needing more information and has been inactive for ${{ env.daysBeforeStale }} days. 
             It will be closed now due to lack of additional information.
-
+            
             该问题被标记为"需要更多信息"且已经 ${{ env.daysBeforeStale }} 天没有任何活动，将立即关闭。
           operations-per-run: 50
-          exempt-issue-labels: 'pending, Dev Team'
+          exempt-issue-labels: "pending, Dev Team"
           days-before-pr-stale: -1
           days-before-pr-close: -1
 
@@ -45,11 +45,11 @@ jobs:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           days-before-stale: ${{ env.daysBeforeStale }}
           days-before-close: ${{ env.daysBeforeClose }}
-          stale-issue-label: 'inactive'
+          stale-issue-label: "inactive"
           stale-issue-message: |
             This issue has been inactive for a prolonged period and will be closed automatically in ${{ env.daysBeforeClose }} days.
             该问题已长时间处于闲置状态，${{ env.daysBeforeClose }} 天后将自动关闭。
-          exempt-issue-labels: 'pending, Dev Team, kind/enhancement'
+          exempt-issue-labels: "pending, Dev Team, kind/enhancement"
           days-before-pr-stale: -1 # Completely disable stalling for PRs
           days-before-pr-close: -1 # Completely disable closing for PRs
 

.github/workflows/release.yml

@@ -77,10 +77,9 @@ jobs:
 
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
           NODE_OPTIONS: --max-old-space-size=8192
           MAIN_VITE_MINERU_API_KEY: ${{ vars.MAIN_VITE_MINERU_API_KEY }}
-          RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
-          RENDERER_VITE_PPIO_APP_SECRET: ${{ vars.RENDERER_VITE_PPIO_APP_SECRET }}
 
       - name: Build Mac
         if: matrix.os == 'macos-latest'
@@ -94,11 +93,10 @@ jobs:
           APPLE_ID: ${{ vars.APPLE_ID }}
           APPLE_APP_SPECIFIC_PASSWORD: ${{ vars.APPLE_APP_SPECIFIC_PASSWORD }}
           APPLE_TEAM_ID: ${{ vars.APPLE_TEAM_ID }}
+          RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NODE_OPTIONS: --max-old-space-size=8192
           MAIN_VITE_MINERU_API_KEY: ${{ vars.MAIN_VITE_MINERU_API_KEY }}
-          RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
-          RENDERER_VITE_PPIO_APP_SECRET: ${{ vars.RENDERER_VITE_PPIO_APP_SECRET }}
 
       - name: Build Windows
         if: matrix.os == 'windows-latest'
@@ -107,10 +105,9 @@ jobs:
           yarn build:win
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
           NODE_OPTIONS: --max-old-space-size=8192
           MAIN_VITE_MINERU_API_KEY: ${{ vars.MAIN_VITE_MINERU_API_KEY }}
-          RENDERER_VITE_AIHUBMIX_SECRET: ${{ vars.RENDERER_VITE_AIHUBMIX_SECRET }}
-          RENDERER_VITE_PPIO_APP_SECRET: ${{ vars.RENDERER_VITE_PPIO_APP_SECRET }}
 
       - name: Release
         uses: ncipollo/release-action@v1
@@ -120,4 +117,4 @@ jobs:
           makeLatest: false
           tag: ${{ steps.get-tag.outputs.tag }}
           artifacts: 'dist/*.exe,dist/*.zip,dist/*.dmg,dist/*.AppImage,dist/*.snap,dist/*.deb,dist/*.rpm,dist/*.tar.gz,dist/latest*.yml,dist/rc*.yml,dist/*.blockmap'
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -35,7 +35,6 @@ Thumbs.db
 node_modules
 dist
 out
-mcp_server
 stats.html
 
 # ENV
@@ -47,10 +46,6 @@ local
 .aider*
 .cursorrules
 .cursor/*
-.claude/*
-.gemini/*
-.trae/*
-.claude-code-router/*
 
 # vitest
 coverage

.prettierrc

@@ -1,11 +1,8 @@
 {
-  "bracketSameLine": true,
-  "endOfLine": "lf",
-  "jsonRecursiveSort": true,
-  "jsonSortOrder": "{\"*\": \"lexical\"}",
-  "plugins": ["prettier-plugin-sort-json"],
-  "printWidth": 120,
-  "semi": false,
   "singleQuote": true,
-  "trailingComma": "none"
+  "semi": false,
+  "printWidth": 120,
+  "trailingComma": "none",
+  "endOfLine": "lf",
+  "bracketSameLine": true
 }

.vscode/extensions.json

@@ -1,3 +1,3 @@
 {
-  "recommendations": ["dbaeumer.vscode-eslint", "esbenp.prettier-vscode", "editorconfig.editorconfig"]
+  "recommendations": ["dbaeumer.vscode-eslint"]
 }

.vscode/launch.json

@@ -10,7 +10,7 @@
       "windows": {
         "runtimeExecutable": "${workspaceRoot}/node_modules/.bin/electron-vite.cmd"
       },
-      "runtimeArgs": ["--inspect", "--sourcemap"],
+      "runtimeArgs": ["--sourcemap"],
       "env": {
         "REMOTE_DEBUGGING_PORT": "9222"
       }
@@ -21,7 +21,7 @@
       "request": "attach",
       "type": "chrome",
       "webRoot": "${workspaceFolder}/src/renderer",
-      "timeout": 3000000,
+      "timeout": 60000,
       "presentation": {
         "hidden": true
       }

.vscode/settings.json

@@ -4,7 +4,6 @@
     "source.fixAll.eslint": "explicit",
     "source.organizeImports": "never"
   },
-  "files.eol": "\n",
   "search.exclude": {
     "**/dist/**": true,
     ".yarn/releases/**": true

README.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">Italiano</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=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>
@@ -63,7 +63,7 @@
 
 # 🍒 Cherry Studio
 
-Cherry Studio is a desktop client that supports multiple LLM providers, available on Windows, Mac and Linux.
+Cherry Studio is a desktop client that supports for multiple LLM providers, available on Windows, Mac and Linux.
 
 👏 Join [Telegram Group](https://t.me/CherryStudioAI)｜[Discord](https://discord.gg/wez8HtpxqQ) | [QQ Group(575014769)](https://qm.qq.com/q/lo0D4qVZKi)
 
@@ -93,7 +93,7 @@ Cherry Studio is a desktop client that supports multiple LLM providers, availabl
 
 3. **Document & Data Processing**:
 
-- 📄 Supports Text, Images, Office, PDF, and more
+- 📄 Support for Text, Images, Office, PDF, and more
 - ☁️ WebDAV File Management and Backup
 - 📊 Mermaid Chart Visualization
 - 💻 Code Syntax Highlighting
@@ -110,7 +110,7 @@ Cherry Studio is a desktop client that supports multiple LLM providers, availabl
 5. **Enhanced User Experience**:
 
 - 🖥️ Cross-platform Support for Windows, Mac, and Linux
-- 📦 Ready to Use - No Environment Setup Required
+- 📦 Ready to Use, No Environment Setup Required
 - 🎨 Light/Dark Themes and Transparent Window
 - 📝 Complete Markdown Rendering
 - 🤲 Easy Content Sharing
@@ -121,11 +121,11 @@ We're actively working on the following features and improvements:
 
 1. 🎯 **Core Features**
 
-- Selection Assistant with smart content selection enhancement
-- Deep Research with advanced research capabilities
-- Memory System with global context awareness
-- Document Preprocessing with improved document handling
-- MCP Marketplace for Model Context Protocol ecosystem
+- Selection Assistant - Smart content selection enhancement
+- Deep Research - Advanced research capabilities
+- Memory System - Global context awareness
+- Document Preprocessing - Improved document handling
+- MCP Marketplace - Model Context Protocol ecosystem
 
 2. 🗂 **Knowledge Management**
 
@@ -199,7 +199,7 @@ To give back to our core contributors and create a virtuous cycle, we have estab
 
 **The inaugural tracking period for this program will be Q3 2025 (July, August, September). Rewards for this cycle will be distributed on October 1st.**
 
-Within any tracking period (e.g., July 1st to September 30th for the first cycle), any developer who contributes more than **30 meaningful commits** to any of Cherry Studio's open-source projects on GitHub will be eligible for the following benefits:
+Within any tracking period (e.g., July 1st to September 30th for the first cycle), any developer who contributes more than **30 meaningful commits** to any of Cherry Studio's open-source projects on GitHub is eligible for the following benefits:
 
 - **Cursor Subscription Sponsorship**: Receive a **$70 USD** credit or reimbursement for your [Cursor](https://cursor.sh/) subscription, making AI your most efficient coding partner.
 - **Unlimited Model Access**: Get **unlimited** API calls for the **DeepSeek** and **Qwen** models.
@@ -223,17 +223,17 @@ Let's build together.
 
 # 🏢 Enterprise Edition
 
-Building on the Community Edition, we are proud to introduce **Cherry Studio Enterprise Edition**—a privately-deployable AI productivity and management platform designed for modern teams and enterprises.
+Building on the Community Edition, we are proud to introduce **Cherry Studio Enterprise Edition**—a privately deployable AI productivity and management platform designed for modern teams and enterprises.
 
 The Enterprise Edition addresses core challenges in team collaboration by centralizing the management of AI resources, knowledge, and data. It empowers organizations to enhance efficiency, foster innovation, and ensure compliance, all while maintaining 100% control over their data in a secure environment.
 
 ## Core Advantages
 
 - **Unified Model Management**: Centrally integrate and manage various cloud-based LLMs (e.g., OpenAI, Anthropic, Google Gemini) and locally deployed private models. Employees can use them out-of-the-box without individual configuration.
-- **Enterprise-Grade Knowledge Base**: Build, manage, and share team-wide knowledge bases. Ensures knowledge retention and consistency, enabling team members to interact with AI based on unified and accurate information.
+- **Enterprise-Grade Knowledge Base**: Build, manage, and share team-wide knowledge bases. Ensure knowledge is retained and consistent, enabling team members to interact with AI based on unified and accurate information.
 - **Fine-Grained Access Control**: Easily manage employee accounts and assign role-based permissions for different models, knowledge bases, and features through a unified admin backend.
 - **Fully Private Deployment**: Deploy the entire backend service on your on-premises servers or private cloud, ensuring your data remains 100% private and under your control to meet the strictest security and compliance standards.
-- **Reliable Backend Services**: Provides stable API services and enterprise-grade data backup and recovery mechanisms to ensure business continuity.
+- **Reliable Backend Services**: Provides stable API services, enterprise-grade data backup and recovery mechanisms to ensure business continuity.
 
 ## ✨ Online Demo
 
@@ -247,23 +247,23 @@ The Enterprise Edition addresses core challenges in team collaboration by centra
 
 | Feature           | Community Edition                          | Enterprise Edition                                                                                                                      |
 | :---------------- | :----------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------- |
-| **Open Source**   | ✅ Yes                                     | ⭕️ Partially released to customers                                                                                                      |
+| **Open Source**   | ✅ Yes                                     | ⭕️ part. released to cust.                                                                                                              |
 | **Cost**          | Free for Personal Use / Commercial License | Buyout / Subscription Fee                                                                                                               |
 | **Admin Backend** | —                                          | ● Centralized **Model** Access<br>● **Employee** Management<br>● Shared **Knowledge Base**<br>● **Access** Control<br>● **Data** Backup |
 | **Server**        | —                                          | ✅ Dedicated Private Deployment                                                                                                         |
 
 ## Get the Enterprise Edition
 
-We believe the Enterprise Edition will become your team's AI productivity engine. If you are interested in Cherry Studio Enterprise Edition and would like to learn more, request a quote, or schedule a demo, please feel free to contact us.
+We believe the Enterprise Edition will become your team's AI productivity engine. If you are interested in Cherry Studio Enterprise Edition and would like to learn more, request a quote, or schedule a demo, please contact us.
 
 - **For Business Inquiries & Purchasing**:
   **📧 [bd@cherry-ai.com](mailto:bd@cherry-ai.com)**
 
 # 🔗 Related Projects
 
-- [one-api](https://github.com/songquanpeng/one-api): LLM API management and distribution system supporting mainstream models like OpenAI, Azure, and Anthropic. Features a unified API interface, suitable for key management and secondary distribution.
+- [one-api](https://github.com/songquanpeng/one-api):LLM API management and distribution system, supporting mainstream models like OpenAI, Azure, and Anthropic. Features unified API interface, suitable for key management and secondary distribution.
 
-- [ublacklist](https://github.com/iorate/ublacklist): Blocks specific sites from appearing in Google search results
+- [ublacklist](https://github.com/iorate/ublacklist):Blocks specific sites from appearing in Google search results
 
 # 🚀 Contributors
 

SECURITY.md

@@ -1,64 +0,0 @@
-# Security Policy
-
-## 📢 Reporting a Vulnerability
-
-At Cherry Studio, we take security seriously and appreciate your efforts to responsibly disclose vulnerabilities. If you discover a security issue, please report it as soon as possible.
-
-**Please do not create public issues for security-related reports.**
-
-- To report a security issue, please use the GitHub Security Advisories tab to "[Open a draft security advisory](https://github.com/CherryHQ/cherry-studio/security/advisories/new)".
-- Include a detailed description of the issue, steps to reproduce, potential impact, and any possible mitigations.
-- If applicable, please also attach proof-of-concept code or screenshots.
-
-We will acknowledge your report within **72 hours** and provide a status update as we investigate.
-
----
-
-## 🔒 Supported Versions
-
-We aim to support the latest released version and one previous minor release.
-
-| Version         | Supported        |
-| --------------- | ---------------- |
-| Latest (`main`) | ✅ Supported     |
-| Previous minor  | ✅ Supported     |
-| Older versions  | ❌ Not supported |
-
-If you are using an unsupported version, we strongly recommend updating to the latest release to receive security fixes.
-
----
-
-## 💡 Security Measures
-
-Cherry Studio integrates several security best practices, including:
-
-- Strict dependency updates and regular vulnerability scanning.
-- TypeScript strict mode and linting to reduce potential injection or runtime issues.
-- Enforced code formatting and pre-commit hooks.
-- Internal security reviews before releases.
-- Dedicated MCP (Model Context Protocol) safeguards for model interactions and data privacy.
-
----
-
-## 🛡️ Disclosure Policy
-
-- We follow a **coordinated disclosure** approach.
-- We will not publicly disclose vulnerabilities until a fix has been developed and released.
-- Credit will be given to researchers who responsibly disclose vulnerabilities, if requested.
-
----
-
-## 🤝 Acknowledgements
-
-We greatly appreciate contributions from the security community and strive to recognize all researchers who help keep Cherry Studio safe.
-
----
-
-## 🌟 Questions?
-
-For any security-related questions not involving vulnerabilities, please reach out to:  
-**security@cherry-ai.com**
-
----
-
-Thank you for helping keep Cherry Studio and its users secure!

docs/features/memory-guide-zh.md

@@ -1,222 +0,0 @@
-# Cherry Studio 记忆功能指南
-
-## 功能介绍
-
-Cherry Studio 的记忆功能是一个强大的工具，能够帮助 AI 助手记住对话中的重要信息、用户偏好和上下文。通过记忆功能，您的 AI 助手可以：
-
-- 📝 **记住重要信息**：自动从对话中提取并存储关键事实和信息
-- 🧠 **个性化响应**：基于存储的记忆提供更加个性化和相关的回答
-- 🔍 **智能检索**：在需要时自动搜索相关记忆，增强对话的连贯性
-- 👥 **多用户支持**：为不同用户维护独立的记忆上下文
-
-记忆功能特别适用于需要长期保持上下文的场景，例如个人助手、客户服务、教育辅导等。
-
-## 如何启用记忆功能
-
-### 1. 全局配置（首次设置）
-
-在使用记忆功能之前，您需要先进行全局配置：
-
-1. 点击侧边栏的 **记忆** 图标（记忆棒图标）进入记忆管理页面
-2. 点击右上角的 **更多** 按钮（三个点），选择 **设置**
-3. 在设置弹窗中配置以下必要项：
-   - **LLM 模型**：选择用于处理记忆的语言模型（推荐使用 GPT-4 或 Claude 等高级模型）
-   - **嵌入模型**：选择用于生成向量嵌入的模型（如 text-embedding-3-small）
-   - **嵌入维度**：输入嵌入模型的维度（通常为 1536）
-4. 点击 **确定** 保存配置
-
-> ⚠️ **注意**：嵌入模型和维度一旦设置后无法更改，请谨慎选择。
-
-### 2. 为助手启用记忆
-
-完成全局配置后，您可以为特定助手启用记忆功能：
-
-1. 进入 **助手** 页面
-2. 选择要启用记忆的助手，点击 **编辑**
-3. 在助手设置中找到 **记忆** 部分
-4. 打开记忆功能开关
-5. 保存助手设置
-
-启用后，该助手将在对话过程中自动提取和使用记忆。
-
-## 使用方法
-
-### 查看记忆
-
-1. 点击侧边栏的 **记忆** 图标进入记忆管理页面
-2. 您可以看到所有存储的记忆卡片，包括：
-   - 记忆内容
-   - 创建时间
-   - 所属用户
-
-### 添加记忆
-
-手动添加记忆有两种方式：
-
-**方式一：在记忆管理页面添加**
-
-1. 点击右上角的 **添加记忆** 按钮
-2. 在弹窗中输入记忆内容
-3. 点击 **添加** 保存
-
-**方式二：在对话中自动提取**
-
-- 当助手启用记忆功能后，系统会自动从对话中提取重要信息并存储为记忆
-
-### 编辑记忆
-
-1. 在记忆卡片上点击 **更多** 按钮（三个点）
-2. 选择 **编辑**
-3. 修改记忆内容
-4. 点击 **保存**
-
-### 删除记忆
-
-1. 在记忆卡片上点击 **更多** 按钮
-2. 选择 **删除**
-3. 确认删除操作
-
-## 记忆搜索
-
-记忆管理页面提供了强大的搜索功能：
-
-1. 在页面顶部的搜索框中输入关键词
-2. 系统会实时过滤显示匹配的记忆
-3. 搜索支持模糊匹配，可以搜索记忆内容的任何部分
-
-## 用户管理
-
-记忆功能支持多用户，您可以为不同的用户维护独立的记忆库：
-
-### 切换用户
-
-1. 在记忆管理页面，点击右上角的用户选择器
-2. 选择要切换到的用户
-3. 页面会自动加载该用户的记忆
-
-### 添加新用户
-
-1. 点击用户选择器
-2. 选择 **添加新用户**
-3. 输入用户 ID（支持字母、数字、下划线和连字符）
-4. 点击 **添加**
-
-### 删除用户
-
-1. 切换到要删除的用户
-2. 点击右上角的 **更多** 按钮
-3. 选择 **删除用户**
-4. 确认删除（注意：这将删除该用户的所有记忆）
-
-> 💡 **提示**：默认用户（default-user）无法删除。
-
-## 设置说明
-
-### LLM 模型
-
-- 用于处理记忆提取和更新的语言模型
-- 建议选择能力较强的模型以获得更好的记忆提取效果
-- 可随时更改
-
-### 嵌入模型
-
-- 用于将文本转换为向量，支持语义搜索
-- 一旦设置后无法更改（为了保证现有记忆的兼容性）
-- 推荐使用 OpenAI 的 text-embedding 系列模型
-
-### 嵌入维度
-
-- 嵌入向量的维度，需要与选择的嵌入模型匹配
-- 常见维度：
-  - text-embedding-3-small: 1536
-  - text-embedding-3-large: 3072
-  - text-embedding-ada-002: 1536
-
-### 自定义提示词（可选）
-
-- **事实提取提示词**：自定义如何从对话中提取信息
-- **记忆更新提示词**：自定义如何更新现有记忆
-
-## 最佳实践
-
-### 1. 合理组织记忆
-
-- 保持记忆简洁明了，每条记忆专注于一个具体信息
-- 使用清晰的语言描述事实，避免模糊表达
-- 定期审查和清理过时或不准确的记忆
-
-### 2. 多用户场景
-
-- 为不同的使用场景创建独立用户（如工作、个人、学习等）
-- 使用有意义的用户 ID，便于识别和管理
-- 定期备份重要用户的记忆数据
-
-### 3. 模型选择建议
-
-- **LLM 模型**：GPT-4、Claude 3 等高级模型能更准确地提取和理解信息
-- **嵌入模型**：选择与您的主要使用语言匹配的模型
-
-### 4. 性能优化
-
-- 避免存储过多冗余记忆，这可能影响搜索性能
-- 定期整理和合并相似的记忆
-- 对于大量记忆的场景，考虑按主题或时间进行分类管理
-
-## 常见问题
-
-### Q: 为什么我无法启用记忆功能？
-
-A: 请确保您已经完成全局配置，包括选择 LLM 模型和嵌入模型。
-
-### Q: 记忆会自动同步到所有助手吗？
-
-A: 不会。每个助手的记忆功能需要单独启用，且记忆是按用户隔离的。
-
-### Q: 如何导出我的记忆数据？
-
-A: 目前系统暂不支持直接导出功能，但所有记忆都存储在本地数据库中。
-
-### Q: 删除的记忆可以恢复吗？
-
-A: 删除操作是永久的，无法恢复。建议在删除前仔细确认。
-
-### Q: 记忆功能会影响对话速度吗？
-
-A: 记忆功能在后台异步处理，不会明显影响对话响应速度。但过多的记忆可能会略微增加搜索时间。
-
-### Q: 如何清空所有记忆？
-
-A: 您可以删除当前用户并重新创建，或者手动删除所有记忆条目。
-
-## 注意事项
-
-### 隐私保护
-
-- 所有记忆数据都存储在您的本地设备上，不会上传到云端
-- 请勿在记忆中存储敏感信息（如密码、私钥等）
-- 定期审查记忆内容，确保没有意外存储的隐私信息
-
-### 数据安全
-
-- 记忆数据存储在本地数据库中
-- 建议定期备份重要数据
-- 更换设备时请注意迁移记忆数据
-
-### 使用限制
-
-- 单条记忆的长度建议不超过 500 字
-- 每个用户的记忆数量建议控制在 1000 条以内
-- 过多的记忆可能影响系统性能
-
-## 技术细节
-
-记忆功能使用了先进的 RAG（检索增强生成）技术：
-
-1. **信息提取**：使用 LLM 从对话中智能提取关键信息
-2. **向量化存储**：通过嵌入模型将文本转换为向量，支持语义搜索
-3. **智能检索**：在对话时自动搜索相关记忆，提供给 AI 作为上下文
-4. **持续学习**：随着对话进行，不断更新和完善记忆库
-
----
-
-💡 **提示**：记忆功能是 Cherry Studio 的高级特性，合理使用可以大大提升 AI 助手的智能程度和用户体验。如有更多问题，欢迎查阅文档或联系支持团队。

docs/technical/code-execution.md

@@ -1,127 +0,0 @@
-# 代码执行功能
-
-本文档说明了代码块的 Python 代码执行功能。该实现利用 [Pyodide][pyodide-link] 在浏览器环境中直接运行 Python 代码，并将其置于 Web Worker 中，以避免阻塞主 UI 线程。
-
-整个实现分为三个主要部分：UI 层、服务层和 Worker 层。
-
-## 执行流程图
-
-```mermaid
-sequenceDiagram
-    participant 用户
-    participant CodeBlockView (UI)
-    participant PyodideService (服务)
-    participant PyodideWorker (Worker)
-
-    用户->>CodeBlockView (UI): 点击“运行”按钮
-    CodeBlockView (UI)->>PyodideService (服务): 调用 runScript(code)
-    PyodideService (服务)->>PyodideWorker (Worker): 发送 postMessage({ id, python: code })
-    PyodideWorker (Worker)->>PyodideWorker (Worker): 加载 Pyodide 和相关包
-    PyodideWorker (Worker)->>PyodideWorker (Worker): (按需)注入垫片并合并代码
-    PyodideWorker (Worker)->>PyodideWorker (Worker): 执行合并后的 Python 代码
-    PyodideWorker (Worker)-->>PyodideService (服务): 返回 postMessage({ id, output })
-    PyodideService (服务)-->>CodeBlockView (UI): 返回 { text, image } 对象
-    CodeBlockView (UI)->>用户: 在状态栏中显示文本和/或图像输出
-```
-
-## 1. UI 层
-
-面向用户的代码执行组件是 [CodeBlockView][codeblock-view-link]。
-
-### 关键机制：
-
-- **运行按钮**：当代码块语言为 `python` 且 `codeExecution.enabled` 设置为 true 时，`CodeToolbar` 中会条件性地渲染一个“运行”按钮。
-- **事件处理**：运行按钮的 `onClick` 事件会触发 `handleRunScript` 函数。
-- **服务调用**：`handleRunScript` 调用 `pyodideService.runScript(code)`，将代码块中的 Python 代码传递给服务。
-- **状态管理与输出显示**：使用 `executionResult` 来管理所有执行输出，只要有任何结果（文本或图像），[StatusBar][statusbar-link] 组件就会被渲染以统一显示。
-
-```typescript
-// src/renderer/src/components/CodeBlockView/view.tsx
-const [executionResult, setExecutionResult] = useState<{ text: string; image?: string } | null>(null)
-
-const handleRunScript = useCallback(() => {
-  setIsRunning(true)
-  setExecutionResult(null)
-
-  pyodideService
-    .runScript(children, {}, codeExecution.timeoutMinutes * 60000)
-    .then((result) => {
-      setExecutionResult(result)
-    })
-    .catch((error) => {
-      console.error('Unexpected error:', error)
-      setExecutionResult({
-        text: `Unexpected error: ${error.message || 'Unknown error'}`
-      })
-    })
-    .finally(() => {
-      setIsRunning(false)
-    })
-}, [children, codeExecution.timeoutMinutes]);
-
-// ... 在 JSX 中
-{isExecutable && executionResult && (
-  <StatusBar>
-    {executionResult.text}
-    {executionResult.image && (
-      <ImageOutput>
-        <img src={executionResult.image} alt="Matplotlib plot" />
-      </ImageOutput>
-    )}
-  </StatusBar>
-)}
-```
-
-## 2. 服务层
-
-服务层充当 UI 组件和运行 Pyodide 的 Web Worker 之间的桥梁。其逻辑封装在位于单例类 [PyodideService][pyodide-service-link]。
-
-### 主要职责：
-
-- **Worker 管理**：初始化、管理并与 Pyodide Web Worker 通信。
-- **请求处理**：使用 `resolvers` Map 管理并发请求，通过唯一 ID 匹配请求和响应。
-- **为 UI 提供 API**：向 UI 提供 `runScript(script, context, timeout)` 方法。此方法的返回值已修改为 `Promise<{ text: string; image?: string }>`，以支持包括图像在内的多种输出类型。
-- **输出处理**：从 Worker 接收包含文本、错误和可选图像数据的 `output` 对象。它将文本和错误格式化为对用户友好的单个字符串，然后连同图像数据一起包装成对象返回给 UI 层。
-- **IPC 端点**：该服务还提供了一个 `python-execution-request` IPC 端点，允许主进程请求执行 Python 代码，展示了其灵活的架构。
-
-## 3. Worker 层
-
-核心的 Python 执行发生在 [pyodide.worker.ts][pyodide-worker-link] 中定义的 Web Worker 内部。这确保了计算密集的 Python 代码不会冻结用户界面。
-
-### Worker 逻辑：
-
-- **Pyodide 加载**：Worker 从 CDN 加载 Pyodide 引擎，并设置处理器以捕获 Python 的 `stdout` 和 `stderr`。
-- **动态包安装**：使用 `pyodide.loadPackagesFromImports()` 自动分析并安装代码中导入的依赖包。
-- **按需执行垫片代码**：Worker 会检查传入的代码中是否包含 "matplotlib" 字符串。如果是，它会先执行一段 Python“垫片”代码确保图像输出到全局命名空间。
-- **结果序列化**：执行结果通过 `.toJs()` 等方法被递归转换为可序列化的标准 JavaScript 对象。
-- **返回结构化输出**：执行后，Worker 将一个包含 `id` 和 `output` 对象的-消息发回服务层。`output` 对象是一个结构化对象，包含 `result`、`text`、`error` 以及一个可选的 `image` 字段（用于 Base64 图像数据）。
-
-### 数据流
-
-最终的数据流如下：
-
-1.  **UI 层 ([CodeBlockView][codeblock-view-link])**: 用户点击“运行”按钮。
-2.  **服务层 ([PyodideService][pyodide-service-link])**:
-    - 接收到代码执行请求。
-    - 调用 Web Worker ([pyodide.worker.ts][pyodide-worker-link])，传递用户代码。
-3.  **Worker 层 ([pyodide.worker.ts][pyodide-worker-link])**:
-    - 加载 Pyodide 运行时。
-    - 动态安装代码中 `import` 语句声明的依赖包。
-    - **注入 Matplotlib 垫片**: 如果代码中包含 `matplotlib`，则在用户代码前拼接垫片代码，强制使用 `AGG` 后端。
-    - **执行代码并捕获输出**: 在代码执行后，检查 `matplotlib.pyplot` 的所有 figure，如果存在图像，则将其保存到内存中的 `BytesIO` 对象，并编码为 Base64 字符串。
-    - **结构化返回**: 将捕获的文本输出和 Base64 图像数据封装在一个 JSON 对象中 (`{ "text": "...", "image": "data:image/png;base64,..." }`) 返回给主线程。
-4.  **服务层 ([PyodideService][pyodide-service-link])**:
-    - 接收来自 Worker 的结构化数据。
-    - 将数据原样传递给 UI 层。
-5.  **UI 层 ([CodeBlockView][codeblock-view-link])**:
-    - 接收包含文本和图像数据的对象。
-    - 使用一个 `useState` 来管理执行结果 (`executionResult`)。
-    - 在界面上分别渲染文本输出和图像（如果存在）。
-
-<!-- Link Definitions -->
-
-[pyodide-link]: https://pyodide.org/
-[codeblock-view-link]: /src/renderer/src/components/CodeBlockView/view.tsx
-[pyodide-service-link]: /src/renderer/src/services/PyodideService.ts
-[pyodide-worker-link]: /src/renderer/src/workers/pyodide.worker.ts
-[statusbar-link]: /src/renderer/src/components/CodeBlockView/StatusBar.tsx

docs/technical/db.settings.md

@@ -1,11 +0,0 @@
-# 数据库设置字段
-
-此文档包含部分字段的数据类型说明。
-
-## 字段
-
-| 字段名                         | 类型                           | 说明         |
-| ------------------------------ | ------------------------------ | ------------ |
-| `translate:target:language`    | `LanguageCode`                 | 翻译目标语言 |
-| `translate:source:language`    | `LanguageCode`                 | 翻译源语言   |
-| `translate:bidirectional:pair` | `[LanguageCode, LanguageCode]` | 双向翻译对   |

docs/technical/how-to-use-logger-en.md

@@ -1,184 +0,0 @@
-# How to use the LoggerService
-
-This is a developer document on how to use the logger.
-
-CherryStudio uses a unified logging service to print and record logs. **Unless there is a special reason, do not use `console.xxx` to print logs**
-
-The following are detailed instructions.
-
-## Usage in the `main` process
-
-### Importing
-
-```typescript
-import { loggerService } from '@logger'
-```
-
-### Setting module information (Required by convention)
-
-After the import statements, set it up as follows:
-
-```typescript
-const logger = loggerService.withContext('moduleName')
-```
-
-- `moduleName` is the name of the current file's module. It can be named after the filename, main class name, main function name, etc. The principle is to be clear and understandable.
-- `moduleName` will be printed in the terminal and will also be present in the file log, making it easier to filter.
-
-### Setting `CONTEXT` information (Optional)
-
-In `withContext`, you can also set other `CONTEXT` information:
-
-```typescript
-const logger = loggerService.withContext('moduleName', CONTEXT)
-```
-
-- `CONTEXT` is an object of the form `{ key: value, ... }`.
-- `CONTEXT` information will not be printed in the terminal, but it will be recorded in the file log, making it easier to filter.
-
-### Logging
-
-In your code, you can call `logger` at any time to record logs. The supported levels are: `error`, `warn`, `info`, `verbose`, `debug`, and `silly`.
-For the meaning of each level, please refer to the subsequent sections.
-
-The following are the supported parameters for logging (using `logger.LEVEL` as an example, where `LEVEL` represents one of the levels mentioned above):
-
-```typescript
-logger.LEVEL(message)
-logger.LEVEL(message, CONTEXT)
-logger.LEVEL(message, error)
-logger.LEVEL(message, error, CONTEXT)
-```
-
-**Only the four calling methods above are supported**:
-
-| Parameter | Type     | Description                                                                                                                                                                                                                                                                                                                   |
-| --------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `message` | `string` | Required. This is the core field of the log, containing the main content to be recorded.                                                                                                                                                                                                                                      |
-| `CONTEXT` | `object` | Optional. Additional information to be recorded in the log file. It is recommended to use the `{ key: value, ...}` format.                                                                                                                                                                                                    |
-| `error`   | `Error`  | Optional. The error stack trace will also be printed.<br />Note that the `error` caught by `catch(error)` is of the `unknown` type. According to TypeScript best practices, you should first use `instanceof` for type checking. If you are certain it is an `Error` type, you can also use a type assertion like `as Error`. |
-
-### Log Levels
-
-- In the development environment, all log levels are printed to the terminal and recorded in the file log.
-- In the production environment, the default log level is `info`. Logs are only recorded to the file and are not printed to the terminal.
-
-Changing the log level:
-
-- You can change the log level with `logger.setLevel('newLevel')`.
-- `logger.resetLevel()` resets it to the default level.
-- `logger.getLevel()` gets the current log level.
-
-**Note:** Changing the log level has a global effect. Please do not change it arbitrarily in your code unless you are very clear about what you are doing.
-
-## Usage in the `renderer` process
-
-Usage in the `renderer` process for _importing_, _setting module information_, and _setting context information_ is **exactly the same** as in the `main` process.
-The following section focuses on the differences.
-
-### `initWindowSource`
-
-In the `renderer` process, there are different `window`s. Before starting to use the `logger`, we must set the `window` information:
-
-```typescript
-loggerService.initWindowSource('windowName')
-```
-
-As a rule, we will set this in the `window`'s `entryPoint.tsx`. This ensures that `windowName` is set before it's used.
-
-- An error will be thrown if `windowName` is not set, and the `logger` will not work.
-- `windowName` can only be set once; subsequent attempts to set it will have no effect.
-- `windowName` will not be printed in the `devTool`'s `console`, but it will be recorded in the `main` process terminal and the file log.
-- `initWindowSource` returns the LoggerService instance, allowing for method chaining
-
-### Log Levels
-
-- In the development environment, all log levels are printed to the `devTool`'s `console` by default.
-- In the production environment, the default log level is `info`, and logs are printed to the `devTool`'s `console`.
-- In both development and production environments, `warn` and `error` level logs are, by default, transmitted to the `main` process and recorded in the file log.
-  - In the development environment, the `main` process terminal will also print the logs transmitted from the renderer.
-
-#### Changing the Log Level
-
-Same as in the `main` process, you can manage the log level using `setLevel('level')`, `resetLevel()`, and `getLevel()`.
-Similarly, changing the log level is a global adjustment.
-
-#### Changing the Level Transmitted to `main`
-
-Logs from the `renderer` are sent to `main` to be managed and recorded to a file centrally (according to `main`'s file logging level). By default, only `warn` and `error` level logs are transmitted to `main`.
-
-There are two ways to change the log level for transmission to `main`:
-
-##### Global Change
-
-The following methods can be used to set, reset, and get the log level for transmission to `main`, respectively.
-
-```typescript
-logger.setLogToMainLevel('newLevel')
-logger.resetLogToMainLevel()
-logger.getLogToMainLevel()
-```
-
-**Note:** This method has a global effect. Please do not change it arbitrarily in your code unless you are very clear about what you are doing.
-
-##### Per-log Change
-
-By adding `{ logToMain: true }` at the end of the log call, you can force a single log entry to be transmitted to `main` (bypassing the global log level restriction), for example:
-
-```typescript
-logger.info('message', { logToMain: true })
-```
-
-## About `worker` Threads
-
-- Currently, logging is not supported for workers in the `main` process.
-- Logging is supported for workers started in the `renderer` process, but currently these logs are not sent to `main` for recording.
-
-### How to Use Logging in `renderer` Workers
-
-Since worker threads are independent, using LoggerService in them is equivalent to using it in a new `renderer` window. Therefore, you must first call `initWindowSource`.
-
-If the worker is relatively simple (just one file), you can also use method chaining directly:
-
-```typescript
-const logger = loggerService.initWindowSource('Worker').withContext('LetsWork')
-```
-
-## Filtering Logs with Environment Variables
-
-In a development environment, you can define environment variables to filter displayed logs by level and module. This helps developers focus on their specific logs and improves development efficiency.
-
-Environment variables can be set in the terminal or defined in the `.env` file in the project's root directory. The available variables are as follows:
-
-| Variable Name                  | Description                                                                                                                                                                 |
-| ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| CSLOGGER_MAIN_LEVEL            | Log level for the `main` process. Logs below this level will not be displayed.                                                                                              |
-| CSLOGGER_MAIN_SHOW_MODULES     | Filters log modules for the `main` process. Use a comma (`,`) to separate modules. The filter is case-sensitive. Only logs from modules in this list will be displayed.     |
-| CSLOGGER_RENDERER_LEVEL        | Log level for the `renderer` process. Logs below this level will not be displayed.                                                                                          |
-| CSLOGGER_RENDERER_SHOW_MODULES | Filters log modules for the `renderer` process. Use a comma (`,`) to separate modules. The filter is case-sensitive. Only logs from modules in this list will be displayed. |
-
-Example:
-
-```bash
-CSLOGGER_MAIN_LEVEL=verbose
-CSLOGGER_MAIN_SHOW_MODULES=MCPService,SelectionService
-```
-
-Note:
-
-- Environment variables are only effective in the development environment.
-- These variables only affect the logs displayed in the terminal or DevTools. They do not affect file logging or the `logToMain` recording logic.
-
-## Log Level Usage Guidelines
-
-There are many log levels. The following are the guidelines that should be followed in CherryStudio for when to use each level:
-(Arranged from highest to lowest log level)
-
-| Log Level     | Core Definition & Use case                                                                                                                                                                          | Example                                                                                                                                                                                                            |
-| :------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **`error`**   | **Critical error causing the program to crash or core functionality to become unusable.** <br> This is the highest-priority log, usually requiring immediate reporting or user notification.        | - Main or renderer process crash. <br> - Failure to read/write critical user data files (e.g., database, configuration files), preventing the application from running. <br> - All unhandled exceptions.           |
-| **`warn`**    | **Potential issue or unexpected situation that does not affect the program's core functionality.** <br> The program can recover or use a fallback.                                                  | - Configuration file `settings.json` is missing; started with default settings. <br> - Auto-update check failed, but does not affect the use of the current version. <br> - A non-essential plugin failed to load. |
-| **`info`**    | **Records application lifecycle events and key user actions.** <br> This is the default level that should be recorded in a production release to trace the user's main operational path.            | - Application start, exit. <br> - User successfully opens/saves a file. <br> - Main window created/closed. <br> - Starting an important task (e.g., "Start video export").                                         |
-| **`verbose`** | **More detailed flow information than `info`, used for tracing specific features.** <br> Enabled when diagnosing issues with a specific feature to help understand the internal execution flow.     | - Loading `Toolbar` module. <br> - IPC message `open-file-dialog` sent from the renderer process. <br> - Applying filter 'Sepia' to the image.                                                                     |
-| **`debug`**   | **Detailed diagnostic information used during development and debugging.** <br> **Must not be enabled by default in production releases**, as it may contain sensitive data and impact performance. | - Parameters for function `renderImage`: `{ width: 800, ... }`. <br> - Specific data content received by IPC message `save-file`. <br> - Details of Redux/Vuex state changes in the renderer process.              |
-| **`silly`**   | **The most detailed, low-level information, used only for extreme debugging.** <br> Rarely used in regular development; only for solving very difficult problems.                                   | - Real-time mouse coordinates `(x: 150, y: 320)`. <br> - Size of each data chunk when reading a file. <br> - Time taken for each rendered frame.                                                                   |

docs/technical/how-to-use-logger-zh.md

@@ -1,183 +0,0 @@
-# 如何使用日志 LoggerService
-
-这是关于如何使用日志的开发者文档。
-
-CherryStudio使用统一的日志服务来打印和记录日志，**若无特殊原因，请勿使用`console.xxx`来打印日志**
-
-以下是详细说明
-
-## 在`main`进程中使用
-
-### 引入
-
-```typescript
-import { loggerService } from '@logger'
-```
-
-### 设置module信息（规范要求）
-
-在import头之后，设置：
-
-```typescript
-const logger = loggerService.withContext('moduleName')
-```
-
-- `moduleName`是当前文件模块的名称，命名可以以文件名、主类名、主函数名等，原则是清晰明了
-- `moduleName`会在终端中打印出来，也会在文件日志中提现，方便筛选
-
-### 设置`CONTEXT`信息（可选）
-
-在`withContext`中，也可以设置其他`CONTEXT`信息：
-
-```typescript
-const logger = loggerService.withContext('moduleName', CONTEXT)
-```
-
-- `CONTEXT`为`{ key: value, ... }`
-- `CONTEXT`信息不会在终端中打印出来，但是会在文件日志中记录，方便筛选
-
-### 记录日志
-
-在代码中，可以随时调用 `logger` 来记录日志，支持的级别有：`error`, `warn`, `info`, `verbose`, `debug`, `silly`
-各级别的含义，请参考后面的章节。
-
-以下支持的记录日志的参数（以 `logger.LEVEL` 举例如何使用，`LEVEL`指代为上述级别）：
-
-```typescript
-logger.LEVEL(message)
-logger.LEVEL(message, CONTEXT)
-logger.LEVEL(message, error)
-logger.LEVEL(message, error, CONTEXT)
-```
-
-**只支持上述四种调用方式**：
-| 参数 | 类型 | 说明 |
-| ----- | ----- | ----- |
-| `message` | `string` | 必填项。这是日志的核心字段，记录的重点内容 |
-| `CONTEXT` | `object` | 可选。其他需要再日志文件中记录的信息，建议为`{ key: value, ...}`格式
-| `error` | `Error` | 可选。同时会打印错误堆栈信息。<br />注意`catch(error)`所捕获的`error`是`unknown`类型，按照`Typescript`最佳实践，请先用`instanceof`进行类型判断，如果确信一定是`Error`类型，也可用断言`as Error`。|
-
-### 记录级别
-
-- 开发环境下，所有级别的日志都会打印到终端，并且记录到文件日志中
-- 生产环境下，默认记录级别为`info`，日志只会记录到文件，不会打印到终端
-
-更改日志记录级别：
-
-- 可以通过 `logger.setLevel('newLevel')` 来更改日志记录级别
-- `logger.resetLevel()` 可以重置为默认级别
-- `logger.getLevel()` 可以获取当前记录记录级别
-
-**注意** 更改日志记录级别是全局生效的，请不要在代码中随意更改，除非你非常清楚自己在做什么
-
-## 在`renderer`进程中使用
-
-在`renderer`进程中使用，_引入方法_、_设置`module`信息_、*设置`context`信息的方法*和`main`进程中是**完全一样**的。
-下面着重讲一下不同之处。
-
-### `initWindowSource`
-
-`renderer`进程中，有不同的`window`，在开始使用`logger`之前，我们必须设置`window`信息：
-
-```typescript
-loggerService.initWindowSource('windowName')
-```
-
-原则上，我们将在`window`的`entryPoint.tsx`中进行设置，这可以保证`windowName`在开始使用前已经设置好了。
-
-- 未设置`windowName`会报错，`logger`将不起作用
-- `windowName`只能设置一次，重复设置将不生效
-- `windowName`不会在`devTool`的`console`中打印出来，但是会在`main`进程的终端和文件日志中记录
-- `initWindowSource`返回的是LoggerService的实例，因此可以做链式调用
-
-### 记录级别
-
-- 开发环境下，默认所有级别的日志都会打印到`devTool`的`console`
-- 生产环境下，默认记录级别为`info`，日志会打印到`devTool`的`console`
-- 在开发和生产环境下，默认`warn`和`error`级别的日志，会传输给`main`进程，并记录到文件日志
-  - 开发环境下，`main`进程终端中也会打印传输过来的日志
-
-#### 更改日志记录级别
-
-和`main`进程中一样，你可以通过`setLevel('level')`、`resetLevel()`和`getLevel()`来管理日志记录级别。
-同样，该日志记录级别也是全局调整的。
-
-#### 更改传输到`main`的级别
-
-将`renderer`的日志发送到`main`，并由`main`统一管理和记录到文件（根据`main`的记录到文件的级别），默认只有`warn`和`error`级别的日志会传输到`main`
-
-有以下两种方式，可以更改传输到`main`的日志级别：
-
-##### 全局更改
-
-以下方法可以分别设置、重置和获取传输到`main`的日志级别
-
-```typescript
-logger.setLogToMainLevel('newLevel')
-logger.resetLogToMainLevel()
-logger.getLogToMainLevel()
-```
-
-**注意** 该方法是全局生效的，请不要在代码中随意更改，除非你非常清楚自己在做什么
-
-##### 单条更改
-
-在日志记录的最末尾，加上`{ logToMain: true }`，即可将本条日志传输到`main`（不受全局日志级别限制），例如：
-
-```typescript
-logger.info('message', { logToMain: true })
-```
-
-## 关于`worker`线程
-
-- 现在不支持`main`进程中的`worker`的日志。
-- 支持`renderer`中起的`worker`的日志，但是现在该日志不会发送给`main`进行记录。
-
-### 如何在`renderer`的`worker`中使用日志
-
-由于`worker`线程是独立的，在其中使用LoggerService，等同于在一个新`renderer`窗口中使用。因此也必须先`initWindowSource`。
-
-如果`worker`比较简单，只有一个文件，也可以使用链式语法直接使用：
-
-```typescript
-const logger = loggerService.initWindowSource('Worker').withContext('LetsWork')
-```
-
-## 使用环境变量来筛选要显示的日志
-
-在开发环境中，可以通过环境变量的定义，来筛选要显示的日志的级别和module。开发者可以专注于自己的日志，提高开发效率。
-
-环境变量可以在终端中自行设置，或者在开发根目录的`.env`文件中进行定义，可以定义的变量如下：
-
-| 变量名                         | 含义                                                                                            |
-| ------------------------------ | ----------------------------------------------------------------------------------------------- |
-| CSLOGGER_MAIN_LEVEL            | 用于`main`进程的日志级别，低于该级别的日志将不显示                                              |
-| CSLOGGER_MAIN_SHOW_MODULES     | 用于`main`进程的日志module筛选，用`,`分隔，区分大小写。只有在该列表中的module的日志才会显示     |
-| CSLOGGER_RENDERER_LEVEL        | 用于`renderer`进程的日志级别，低于该级别的日志将不显示                                          |
-| CSLOGGER_RENDERER_SHOW_MODULES | 用于`renderer`进程的日志module筛选，用`,`分隔，区分大小写。只有在该列表中的module的日志才会显示 |
-
-示例：
-
-```bash
-CSLOGGER_MAIN_LEVEL=vebose
-CSLOGGER_MAIN_SHOW_MODULES=MCPService,SelectionService
-```
-
-注意：
-
-- 环境变量仅在开发环境中生效
-- 该变量仅会改变在终端或在devTools中显示的日志，不会影响文件日志和`logToMain`的记录逻辑
-
-## 日志级别的使用规范
-
-日志有很多级别，什么时候应该用哪个级别，下面是在CherryStudio中应该遵循的规范：
-(按日志级别从高到低排列)
-
-| 日志级别      | 核心定义与使用场景                                                                                       | 示例                                                                                                                                                  |
-| :------------ | :------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **`error`**   | **严重错误，导致程序崩溃或核心功能无法使用。** <br> 这是最高优的日志，通常需要立即上报或提示用户。       | - 主进程或渲染进程崩溃。 <br> - 无法读写用户关键数据文件（如数据库、配置文件），导致应用无法运行。<br> - 所有未捕获的异常。`                          |
-| **`warn`**    | **潜在问题或非预期情况，但不影响程序核心功能。** <br> 程序可以从中恢复或使用备用方案。                   | - 配置文件 `settings.json` 缺失，已使用默认配置启动。 <br> - 自动更新检查失败，但不影响当前版本使用。<br> - 某个非核心插件加载失败。`                 |
-| **`info`**    | **记录应用生命周期和关键用户行为。** <br> 这是发布版中默认应记录的级别，用于追踪用户的主要操作路径。     | - 应用启动、退出。<br> - 用户成功打开/保存文件。 <br> - 主窗口创建/关闭。<br> - 开始执行一项重要任务（如“开始导出视频”）。`                           |
-| **`verbose`** | **比 `info` 更详细的流程信息，用于追踪特定功能。** <br> 在诊断特定功能问题时开启，帮助理解内部执行流程。 | - 正在加载 `Toolbar` 模块。 <br> - IPC 消息 `open-file-dialog` 已从渲染进程发送。<br> - 正在应用滤镜 'Sepia' 到图像。`                                |
-| **`debug`**   | **开发和调试时使用的详细诊断信息。** <br> **严禁在发布版中默认开启**，因为它可能包含敏感数据并影响性能。 | - 函数 `renderImage` 的入参: `{ width: 800, ... }`。<br> - IPC 消息 `save-file` 收到的具体数据内容。<br> - 渲染进程中 Redux/Vuex 的 state 变更详情。` |
-| **`silly`**   | **最详尽的底层信息，仅用于极限调试。** <br> 几乎不在常规开发中使用，仅为解决棘手问题。                   | - 鼠标移动的实时坐标 `(x: 150, y: 320)`。<br> - 读取文件时每个数据块（chunk）的大小。<br> - 每一次渲染帧的耗时。                                      |

docs/technical/how-to-write-middlewares.md

@@ -80,13 +80,15 @@ import { ChunkType } from '@renderer/types' // 调整路径
 
 export const createSimpleLoggingMiddleware = (): CompletionsMiddleware => {
   return (api: MiddlewareAPI<AiProviderMiddlewareCompletionsContext, [CompletionsParams]>) => {
+    // console.log(`[LoggingMiddleware] Initialized for provider: ${api.getProviderId()}`);
+
     return (next: (context: AiProviderMiddlewareCompletionsContext, params: CompletionsParams) => Promise<any>) => {
       return async (context: AiProviderMiddlewareCompletionsContext, params: CompletionsParams): Promise<void> => {
         const startTime = Date.now()
         // 从 context 中获取 onChunk (它最初来自 params.onChunk)
         const onChunk = context.onChunk
 
-        logger.debug(
+        console.log(
           `[LoggingMiddleware] Request for ${context.methodName} with params:`,
           params.messages?.[params.messages.length - 1]?.content
         )
@@ -102,14 +104,14 @@ export const createSimpleLoggingMiddleware = (): CompletionsMiddleware => {
           // 如果在之前，那么它需要自己处理 rawSdkResponse 或确保下游会处理。
 
           const duration = Date.now() - startTime
-          logger.debug(`[LoggingMiddleware] Request for ${context.methodName} completed in ${duration}ms.`)
+          console.log(`[LoggingMiddleware] Request for ${context.methodName} completed in ${duration}ms.`)
 
           // 假设下游已经通过 onChunk 发送了所有数据。
           // 如果这个中间件是链的末端，并且需要确保 BLOCK_COMPLETE 被发送，
           // 它可能需要更复杂的逻辑来跟踪何时所有数据都已发送。
         } catch (error) {
           const duration = Date.now() - startTime
-          logger.error(`[LoggingMiddleware] Request for ${context.methodName} failed after ${duration}ms:`, error)
+          console.error(`[LoggingMiddleware] Request for ${context.methodName} failed after ${duration}ms:`, error)
 
           // 如果 onChunk 可用，可以尝试发送一个错误块
           if (onChunk) {
@@ -205,7 +207,7 @@ export default middlewareConfig
 
 ### 调试技巧
 
-- 在中间件的关键点使用 `logger.debug` 或调试器来检查 `params`、`context` 的状态以及 `next` 的返回值。
+- 在中间件的关键点使用 `console.log` 或调试器来检查 `params`、`context` 的状态以及 `next` 的返回值。
 - 暂时简化中间件链，只保留你正在调试的中间件和最简单的核心逻辑，以隔离问题。
 - 编写单元测试来独立验证每个中间件的行为。
 

electron-builder.yml

@@ -54,7 +54,7 @@ files:
   - '!node_modules/mammoth/{mammoth.browser.js,mammoth.browser.min.js}'
   - '!node_modules/selection-hook/prebuilds/**/*' # we rebuild .node, don't use prebuilds
   - '!node_modules/pdfjs-dist/web/**/*'
-  - '!node_modules/pdfjs-dist/legacy/**/*'
+  - '!node_modules/pdfjs-dist/legacy/web/*'
   - '!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
   - '!**/*.{h,iobj,ipdb,tlog,recipe,vcxproj,vcxproj.filters,Makefile,*.Makefile}' # filter .node build files
@@ -117,10 +117,9 @@ afterSign: scripts/notarize.js
 artifactBuildCompleted: scripts/artifact-build-completed.js
 releaseInfo:
   releaseNotes: |
-    全新 UI 界面：在显示设置里开启抢先体验
-    添加浮动侧边栏方便快速切换模型和助手
-    改进文字流式输出体验
-    新增 Trace（调用链路可视化）功能，由 Alibaba Cloud EDAS 团队提供
-    新增开发者模式：在常规设置中开启，开启后可以查看 Trace 数据
-    修复多模型对比时不能横向滑动问题
-    错误修复和性能优化
+    划词助手：支持 macOS 系统
+    文档处理：增加 MinerU、Doc2x，Mistral 等服务商支持
+    知识库：新的知识库界面，增加扫描版 PDF 支持
+    OCR：macOS 增加系统 OCR 支持
+    服务商：支持一键添加服务商，新增 PH8 大模型开放平台, 支持 PPIO OAuth 登录
+    修复：Linux下数据目录移动问题

electron.vite.config.ts

@@ -8,9 +8,6 @@ const visualizerPlugin = (type: 'renderer' | 'main') => {
   return process.env[`VISUALIZER_${type.toUpperCase()}`] ? [visualizer({ open: true })] : []
 }
 
-const isDev = process.env.NODE_ENV === 'development'
-const isProd = process.env.NODE_ENV === 'production'
-
 export default defineConfig({
   main: {
     plugins: [externalizeDepsPlugin(), ...visualizerPlugin('main')],
@@ -18,50 +15,39 @@ export default defineConfig({
       alias: {
         '@main': resolve('src/main'),
         '@types': resolve('src/renderer/src/types'),
-        '@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')
+        '@shared': resolve('packages/shared')
       }
     },
     build: {
       rollupOptions: {
         external: ['@libsql/client', 'bufferutil', 'utf-8-validate', '@cherrystudio/mac-system-ocr'],
-        output: isProd
-          ? {
-              manualChunks: undefined, // 彻底禁用代码分割 - 返回 null 强制单文件打包
-              inlineDynamicImports: true // 内联所有动态导入，这是关键配置
-            }
-          : undefined
+        output: {
+          // 彻底禁用代码分割 - 返回 null 强制单文件打包
+          manualChunks: undefined,
+          // 内联所有动态导入，这是关键配置
+          inlineDynamicImports: true
+        }
       },
-      sourcemap: isDev
+      sourcemap: process.env.NODE_ENV === 'development'
     },
-    esbuild: isProd ? { legalComments: 'none' } : {},
     optimizeDeps: {
-      noDiscovery: isDev
+      noDiscovery: process.env.NODE_ENV === 'development'
     }
   },
   preload: {
-    plugins: [
-      react({
-        tsDecorators: true
-      }),
-      externalizeDepsPlugin()
-    ],
+    plugins: [externalizeDepsPlugin()],
     resolve: {
       alias: {
-        '@shared': resolve('packages/shared'),
-        '@mcp-trace/trace-core': resolve('packages/mcp-trace/trace-core')
+        '@shared': resolve('packages/shared')
       }
     },
     build: {
-      sourcemap: isDev
+      sourcemap: process.env.NODE_ENV === 'development'
     }
   },
   renderer: {
     plugins: [
       react({
-        tsDecorators: true,
         plugins: [
           [
             '@swc/plugin-styled-components',
@@ -74,16 +60,20 @@ export default defineConfig({
           ]
         ]
       }),
-      ...(isDev ? [CodeInspectorPlugin({ bundler: 'vite' })] : []), // 只在开发环境下启用 CodeInspectorPlugin
+      // 只在开发环境下启用 CodeInspectorPlugin
+      ...(process.env.NODE_ENV === 'development'
+        ? [
+            CodeInspectorPlugin({
+              bundler: 'vite'
+            })
+          ]
+        : []),
       ...visualizerPlugin('renderer')
     ],
     resolve: {
       alias: {
         '@renderer': resolve('src/renderer/src'),
-        '@shared': resolve('packages/shared'),
-        '@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')
+        '@shared': resolve('packages/shared')
       }
     },
     optimizeDeps: {
@@ -102,11 +92,9 @@ export default defineConfig({
           index: resolve(__dirname, 'src/renderer/index.html'),
           miniWindow: resolve(__dirname, 'src/renderer/miniWindow.html'),
           selectionToolbar: resolve(__dirname, 'src/renderer/selectionToolbar.html'),
-          selectionAction: resolve(__dirname, 'src/renderer/selectionAction.html'),
-          traceWindow: resolve(__dirname, 'src/renderer/traceWindow.html')
+          selectionAction: resolve(__dirname, 'src/renderer/selectionAction.html')
         }
       }
-    },
-    esbuild: isProd ? { legalComments: 'none' } : {}
+    }
   }
 })

eslint.config.mjs

@@ -26,45 +26,32 @@ export default defineConfig([
       'simple-import-sort/exports': 'error',
       'unused-imports/no-unused-imports': 'error',
       '@eslint-react/no-prop-types': 'error',
-      'prettier/prettier': ['error']
+      'prettier/prettier': ['error', { endOfLine: 'auto' }]
     }
   },
   // Configuration for ensuring compatibility with the original ESLint(8.x) rules
-  {
-    rules: {
-      '@typescript-eslint/no-require-imports': 'off',
-      '@typescript-eslint/no-unused-vars': ['error', { caughtErrors: 'none' }],
-      '@typescript-eslint/no-unused-expressions': 'off',
-      '@typescript-eslint/no-empty-object-type': 'off',
-      '@eslint-react/hooks-extra/no-direct-set-state-in-use-effect': 'off',
-      '@eslint-react/web-api/no-leaked-event-listener': 'off',
-      '@eslint-react/web-api/no-leaked-timeout': 'off',
-      '@eslint-react/no-unknown-property': 'off',
-      '@eslint-react/no-nested-component-definitions': 'off',
-      '@eslint-react/dom/no-dangerously-set-innerhtml': 'off',
-      '@eslint-react/no-array-index-key': 'off',
-      '@eslint-react/no-unstable-default-props': 'off',
-      '@eslint-react/no-unstable-context-value': 'off',
-      '@eslint-react/hooks-extra/prefer-use-state-lazy-initialization': 'off',
-      '@eslint-react/hooks-extra/no-unnecessary-use-prefix': 'off',
-      '@eslint-react/no-children-to-array': 'off'
+  ...[
+    {
+      rules: {
+        '@typescript-eslint/no-require-imports': 'off',
+        '@typescript-eslint/no-unused-vars': ['error', { caughtErrors: 'none' }],
+        '@typescript-eslint/no-unused-expressions': 'off',
+        '@typescript-eslint/no-empty-object-type': 'off',
+        '@eslint-react/hooks-extra/no-direct-set-state-in-use-effect': 'off',
+        '@eslint-react/web-api/no-leaked-event-listener': 'off',
+        '@eslint-react/web-api/no-leaked-timeout': 'off',
+        '@eslint-react/no-unknown-property': 'off',
+        '@eslint-react/no-nested-component-definitions': 'off',
+        '@eslint-react/dom/no-dangerously-set-innerhtml': 'off',
+        '@eslint-react/no-array-index-key': 'off',
+        '@eslint-react/no-unstable-default-props': 'off',
+        '@eslint-react/no-unstable-context-value': 'off',
+        '@eslint-react/hooks-extra/prefer-use-state-lazy-initialization': 'off',
+        '@eslint-react/hooks-extra/no-unnecessary-use-prefix': 'off',
+        '@eslint-react/no-children-to-array': 'off'
+      }
     }
-  },
-  {
-    // LoggerService Custom Rules - only apply to src directory
-    files: ['src/**/*.{ts,tsx,js,jsx}'],
-    ignores: ['src/**/__tests__/**', 'src/**/__mocks__/**', 'src/**/*.test.*'],
-    rules: {
-      'no-restricted-syntax': [
-        'warn',
-        {
-          selector: 'CallExpression[callee.object.name="console"]',
-          message:
-            '❗CherryStudio uses unified LoggerService: 📖 docs/technical/how-to-use-logger-en.md\n❗CherryStudio 使用统一的日志服务：📖 docs/technical/how-to-use-logger-zh.md\n\n'
-        }
-      ]
-    }
-  },
+  ],
   {
     ignores: [
       'node_modules/**',

package.json

@@ -1,14 +1,11 @@
 {
   "name": "CherryStudio",
-  "version": "1.5.2",
+  "version": "1.4.8",
   "private": true,
   "description": "A powerful AI assistant for producer.",
   "main": "./out/main/index.js",
   "author": "support@cherry-ai.com",
   "homepage": "https://github.com/CherryHQ/cherry-studio",
-  "engines": {
-    "node": ">=22.0.0"
-  },
   "workspaces": {
     "packages": [
       "local",
@@ -16,16 +13,13 @@
     ],
     "installConfig": {
       "hoistingLimits": [
-        "packages/database",
-        "packages/mcp-trace/trace-core",
-        "packages/mcp-trace/trace-node",
-        "packages/mcp-trace/trace-web"
+        "packages/database"
       ]
     }
   },
   "scripts": {
     "start": "electron-vite preview",
-    "dev": "dotenv electron-vite dev",
+    "dev": "electron-vite dev",
     "debug": "electron-vite -- --inspect --sourcemap --remote-debugging-port=9222",
     "build": "npm run typecheck && electron-vite build",
     "build:check": "yarn typecheck && yarn check:i18n && yarn test",
@@ -33,25 +27,23 @@
     "build:win": "dotenv npm run build && electron-builder --win --x64 --arm64",
     "build:win:x64": "dotenv npm run build && electron-builder --win --x64",
     "build:win:arm64": "dotenv npm run build && electron-builder --win --arm64",
-    "build:mac": "dotenv npm run build && electron-builder --mac --arm64 --x64",
-    "build:mac:arm64": "dotenv npm run build && electron-builder --mac --arm64",
-    "build:mac:x64": "dotenv npm run build && electron-builder --mac --x64",
-    "build:linux": "dotenv npm run build && electron-builder --linux --x64 --arm64",
-    "build:linux:arm64": "dotenv npm run build && electron-builder --linux --arm64",
-    "build:linux:x64": "dotenv npm run build && electron-builder --linux --x64",
+    "build:mac": "dotenv electron-vite build && electron-builder --mac --arm64 --x64",
+    "build:mac:arm64": "dotenv electron-vite build && electron-builder --mac --arm64",
+    "build:mac:x64": "dotenv electron-vite build && electron-builder --mac --x64",
+    "build:linux": "dotenv electron-vite build && electron-builder --linux --x64 --arm64",
+    "build:linux:arm64": "dotenv electron-vite build && electron-builder --linux --arm64",
+    "build:linux:x64": "dotenv electron-vite build && electron-builder --linux --x64",
     "build:npm": "node scripts/build-npm.js",
     "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",
-    "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": "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": "node scripts/check-i18n.js",
-    "sync:i18n": "node scripts/sync-i18n.js",
     "test": "vitest run --silent",
     "test:main": "vitest run --project main",
     "test:renderer": "vitest run --project renderer",
@@ -61,10 +53,9 @@
     "test:watch": "vitest",
     "test:e2e": "yarn playwright test",
     "test:lint": "eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts",
-    "test:scripts": "vitest scripts",
     "format": "prettier --write .",
     "lint": "eslint . --ext .js,.jsx,.cjs,.mjs,.ts,.tsx,.cts,.mts --fix",
-    "prepare": "git config blame.ignoreRevsFile .git-blame-ignore-revs && husky"
+    "prepare": "husky"
   },
   "dependencies": {
     "@cherrystudio/pdf-to-img-napi": "^0.0.1",
@@ -72,10 +63,12 @@
     "@libsql/win32-x64-msvc": "^0.4.7",
     "@strongtz/win32-arm64-msvc": "^0.4.7",
     "jsdom": "26.1.0",
+    "macos-release": "^3.4.0",
     "node-stream-zip": "^1.15.0",
+    "notion-helper": "^1.3.22",
     "os-proxy-config": "^1.1.2",
     "pdfjs-dist": "4.10.38",
-    "selection-hook": "^1.0.8",
+    "selection-hook": "^1.0.4",
     "turndown": "7.2.0"
   },
   "devDependencies": {
@@ -84,7 +77,6 @@
     "@agentic/tavily": "^7.3.3",
     "@ant-design/v5-patch-for-react-19": "^1.0.3",
     "@anthropic-ai/sdk": "^0.41.0",
-    "@aws-sdk/client-s3": "^3.840.0",
     "@cherrystudio/embedjs": "^0.1.31",
     "@cherrystudio/embedjs-libsql": "^0.1.31",
     "@cherrystudio/embedjs-loader-csv": "^0.1.31",
@@ -97,7 +89,6 @@
     "@cherrystudio/embedjs-loader-xml": "^0.1.31",
     "@cherrystudio/embedjs-ollama": "^0.1.31",
     "@cherrystudio/embedjs-openai": "^0.1.31",
-    "@codemirror/view": "^6.0.0",
     "@electron-toolkit/eslint-config-prettier": "^3.0.0",
     "@electron-toolkit/eslint-config-ts": "^3.0.0",
     "@electron-toolkit/preload": "^3.0.0",
@@ -113,15 +104,9 @@
     "@langchain/community": "^0.3.36",
     "@langchain/ollama": "^0.2.1",
     "@mistralai/mistralai": "^1.6.0",
-    "@modelcontextprotocol/sdk": "^1.12.3",
+    "@modelcontextprotocol/sdk": "^1.11.4",
     "@mozilla/readability": "^0.6.0",
     "@notionhq/client": "^2.2.15",
-    "@opentelemetry/api": "^1.9.0",
-    "@opentelemetry/core": "2.0.0",
-    "@opentelemetry/exporter-trace-otlp-http": "^0.200.0",
-    "@opentelemetry/sdk-trace-base": "^2.0.0",
-    "@opentelemetry/sdk-trace-node": "^2.0.0",
-    "@opentelemetry/sdk-trace-web": "^2.0.0",
     "@playwright/test": "^1.52.0",
     "@reduxjs/toolkit": "^2.2.5",
     "@shikijs/markdown-it": "^3.7.0",
@@ -153,8 +138,6 @@
     "@vitest/coverage-v8": "^3.1.4",
     "@vitest/ui": "^3.1.4",
     "@vitest/web-worker": "^3.1.4",
-    "@viz-js/lang-dot": "^1.0.5",
-    "@viz-js/viz": "^3.14.0",
     "@xyflow/react": "^12.4.4",
     "antd": "patch:antd@npm%3A5.24.7#~/.yarn/patches/antd-npm-5.24.7-356a553ae5.patch",
     "archiver": "^7.0.1",
@@ -170,12 +153,13 @@
     "diff": "^7.0.0",
     "docx": "^9.0.2",
     "dotenv-cli": "^7.4.2",
-    "electron": "37.2.3",
+    "electron": "35.6.0",
     "electron-builder": "26.0.15",
     "electron-devtools-installer": "^3.2.0",
+    "electron-log": "^5.1.5",
     "electron-store": "^8.2.0",
     "electron-updater": "6.6.4",
-    "electron-vite": "4.0.0",
+    "electron-vite": "^3.1.0",
     "electron-window-state": "^5.0.3",
     "emittery": "^1.0.3",
     "emoji-picker-element": "^1.22.1",
@@ -186,34 +170,27 @@
     "eslint-plugin-unused-imports": "^4.1.4",
     "fast-diff": "^1.3.0",
     "fast-xml-parser": "^5.2.0",
-    "fetch-socks": "1.3.2",
     "franc-min": "^6.2.0",
     "fs-extra": "^11.2.0",
     "google-auth-library": "^9.15.1",
     "html-to-image": "^1.11.13",
     "husky": "^9.1.7",
     "i18next": "^23.11.5",
-    "iconv-lite": "^0.6.3",
-    "jaison": "^2.0.2",
     "jest-styled-components": "^7.2.0",
-    "jschardet": "^3.1.4",
     "lint-staged": "^15.5.0",
     "lodash": "^4.17.21",
     "lru-cache": "^11.1.0",
     "lucide-react": "^0.487.0",
-    "macos-release": "^3.4.0",
     "markdown-it": "^14.1.0",
     "mermaid": "^11.7.0",
     "mime": "^4.0.4",
     "motion": "^12.10.5",
-    "notion-helper": "^1.3.22",
     "npx-scope-finder": "^1.2.0",
-    "officeparser": "^4.2.0",
+    "officeparser": "^4.1.1",
     "openai": "patch:openai@npm%3A5.1.0#~/.yarn/patches/openai-npm-5.1.0-0e7b3ccb07.patch",
     "p-queue": "^8.1.0",
     "playwright": "^1.52.0",
     "prettier": "^3.5.3",
-    "prettier-plugin-sort-json": "^4.1.1",
     "proxy-agent": "^6.5.0",
     "rc-virtual-list": "^3.18.6",
     "react": "^19.0.0",
@@ -221,7 +198,6 @@
     "react-hotkeys-hook": "^4.6.1",
     "react-i18next": "^14.1.2",
     "react-infinite-scroll-component": "^6.1.0",
-    "react-json-view": "^1.21.3",
     "react-markdown": "^10.1.0",
     "react-redux": "^9.1.2",
     "react-router": "6",
@@ -230,7 +206,6 @@
     "react-window": "^1.8.11",
     "redux": "^5.0.1",
     "redux-persist": "^6.0.0",
-    "reflect-metadata": "0.2.2",
     "rehype-katex": "^7.0.1",
     "rehype-mathjax": "^7.1.0",
     "rehype-raw": "^7.0.0",
@@ -241,24 +216,18 @@
     "rollup-plugin-visualizer": "^5.12.0",
     "sass": "^1.88.0",
     "shiki": "^3.7.0",
-    "strict-url-sanitise": "^0.0.1",
     "string-width": "^7.2.0",
     "styled-components": "^6.1.11",
     "tar": "^7.4.3",
     "tiny-pinyin": "^1.3.2",
     "tokenx": "^1.1.0",
     "typescript": "^5.6.2",
-    "undici": "6.21.2",
-    "unified": "^11.0.5",
     "uuid": "^10.0.0",
     "vite": "6.2.6",
     "vitest": "^3.1.4",
     "webdav": "^5.8.0",
-    "winston": "^3.17.0",
-    "winston-daily-rotate-file": "^5.0.0",
     "word-extractor": "^1.0.4",
-    "zipread": "^1.3.3",
-    "zod": "^3.25.74"
+    "zipread": "^1.3.3"
   },
   "optionalDependencies": {
     "@cherrystudio/mac-system-ocr": "^0.2.2"
@@ -273,9 +242,7 @@
     "app-builder-lib@npm:26.0.13": "patch:app-builder-lib@npm%3A26.0.13#~/.yarn/patches/app-builder-lib-npm-26.0.13-a064c9e1d0.patch",
     "openai@npm:^4.87.3": "patch:openai@npm%3A5.1.0#~/.yarn/patches/openai-npm-5.1.0-0e7b3ccb07.patch",
     "app-builder-lib@npm:26.0.15": "patch:app-builder-lib@npm%3A26.0.15#~/.yarn/patches/app-builder-lib-npm-26.0.15-360e5b0476.patch",
-    "@langchain/core@npm:^0.3.26": "patch:@langchain/core@npm%3A0.3.44#~/.yarn/patches/@langchain-core-npm-0.3.44-41d5c3cb0a.patch",
-    "node-abi": "4.12.0",
-    "undici": "6.21.2"
+    "@langchain/core@npm:^0.3.26": "patch:@langchain/core@npm%3A0.3.44#~/.yarn/patches/@langchain-core-npm-0.3.44-41d5c3cb0a.patch"
   },
   "packageManager": "yarn@4.9.1",
   "lint-staged": {

packages/mcp-trace/trace-core/core/spanConvert.ts

@@ -1,26 +0,0 @@
-import { SpanKind, SpanStatusCode } from '@opentelemetry/api'
-import { ReadableSpan } from '@opentelemetry/sdk-trace-base'
-
-import { SpanEntity } from '../types/config'
-
-/**
- * convert ReadableSpan to SpanEntity
- * @param span ReadableSpan
- * @returns SpanEntity
- */
-export function convertSpanToSpanEntity(span: ReadableSpan): SpanEntity {
-  return {
-    id: span.spanContext().spanId,
-    traceId: span.spanContext().traceId,
-    parentId: span.parentSpanContext?.spanId || '',
-    name: span.name,
-    startTime: span.startTime[0] * 1e3 + Math.floor(span.startTime[1] / 1e6), // 转为毫秒
-    endTime: span.endTime ? span.endTime[0] * 1e3 + Math.floor(span.endTime[1] / 1e6) : undefined, // 转为毫秒
-    attributes: { ...span.attributes },
-    status: SpanStatusCode[span.status.code],
-    events: span.events,
-    kind: SpanKind[span.kind],
-    links: span.links,
-    modelName: span.attributes?.modelName
-  } as SpanEntity
-}

packages/mcp-trace/trace-core/core/traceCache.ts

@@ -1,7 +0,0 @@
-import { ReadableSpan } from '@opentelemetry/sdk-trace-base'
-
-export interface TraceCache {
-  createSpan: (span: ReadableSpan) => void
-  endSpan: (span: ReadableSpan) => void
-  clear: () => void
-}

packages/mcp-trace/trace-core/core/traceMethod.ts

@@ -1,163 +0,0 @@
-import 'reflect-metadata'
-
-import { SpanStatusCode, trace } from '@opentelemetry/api'
-import { context as traceContext } from '@opentelemetry/api'
-
-import { defaultConfig } from '../types/config'
-
-export interface SpanDecoratorOptions {
-  spanName?: string
-  traceName?: string
-  tag?: string
-}
-
-export function TraceMethod(traced: SpanDecoratorOptions) {
-  return function (target: any, propertyKey?: any, descriptor?: PropertyDescriptor | undefined) {
-    // 兼容静态方法装饰器只传2个参数的情况
-    if (!descriptor) {
-      descriptor = Object.getOwnPropertyDescriptor(target, propertyKey)
-    }
-    if (!descriptor || typeof descriptor.value !== 'function') {
-      throw new Error('TraceMethod can only be applied to methods.')
-    }
-
-    const originalMethod = descriptor.value
-    const traceName = traced.traceName || defaultConfig.defaultTracerName || 'default'
-    const tracer = trace.getTracer(traceName)
-
-    descriptor.value = function (...args: any[]) {
-      const name = traced.spanName || propertyKey
-      return tracer.startActiveSpan(name, async (span) => {
-        try {
-          span.setAttribute('inputs', convertToString(args))
-          span.setAttribute('tags', traced.tag || '')
-          const result = await originalMethod.apply(this, args)
-          span.setAttribute('outputs', convertToString(result))
-          span.setStatus({ code: SpanStatusCode.OK })
-          return result
-        } catch (error) {
-          const err = error instanceof Error ? error : new Error(String(error))
-          span.setStatus({
-            code: SpanStatusCode.ERROR,
-            message: err.message
-          })
-          span.recordException(err)
-          throw error
-        } finally {
-          span.end()
-        }
-      })
-    }
-    return descriptor
-  }
-}
-
-export function TraceProperty(traced: SpanDecoratorOptions) {
-  return (target: any, propertyKey: string, descriptor?: PropertyDescriptor) => {
-    // 处理箭头函数类属性
-    const traceName = traced.traceName || defaultConfig.defaultTracerName || 'default'
-    const tracer = trace.getTracer(traceName)
-    const name = traced.spanName || propertyKey
-
-    if (!descriptor) {
-      const originalValue = target[propertyKey]
-
-      Object.defineProperty(target, propertyKey, {
-        value: async function (...args: any[]) {
-          const span = tracer.startSpan(name)
-          try {
-            span.setAttribute('inputs', convertToString(args))
-            span.setAttribute('tags', traced.tag || '')
-            const result = await originalValue.apply(this, args)
-            span.setAttribute('outputs', convertToString(result))
-            return result
-          } catch (error) {
-            const err = error instanceof Error ? error : new Error(String(error))
-            span.recordException(err)
-            span.setStatus({ code: SpanStatusCode.ERROR, message: err.message })
-            throw error
-          } finally {
-            span.end()
-          }
-        },
-        configurable: true,
-        writable: true
-      })
-      return
-    }
-
-    // 标准方法装饰器逻辑
-    const originalMethod = descriptor.value
-
-    descriptor.value = async function (...args: any[]) {
-      const span = tracer.startSpan(name)
-      try {
-        span.setAttribute('inputs', convertToString(args))
-        span.setAttribute('tags', traced.tag || '')
-        const result = await originalMethod.apply(this, args)
-        span.setAttribute('outputs', convertToString(result))
-        return result
-      } catch (error) {
-        const err = error instanceof Error ? error : new Error(String(error))
-        span.recordException(err)
-        span.setStatus({ code: SpanStatusCode.ERROR, message: err.message })
-        throw error
-      } finally {
-        span.end()
-      }
-    }
-  }
-}
-
-export function withSpanFunc<F extends (...args: any[]) => any>(
-  name: string,
-  tag: string,
-  fn: F,
-  args: Parameters<F>
-): ReturnType<F> {
-  const traceName = defaultConfig.defaultTracerName || 'default'
-  const tracer = trace.getTracer(traceName)
-  const _name = name || fn.name || 'anonymousFunction'
-  return traceContext.with(traceContext.active(), () =>
-    tracer.startActiveSpan(
-      _name,
-      {
-        attributes: {
-          tags: tag || '',
-          inputs: JSON.stringify(args)
-        }
-      },
-      (span) => {
-        // 在这里调用原始函数
-        const result = fn(...args)
-        if (result instanceof Promise) {
-          return result
-            .then((res) => {
-              span.setStatus({ code: SpanStatusCode.OK })
-              span.setAttribute('outputs', convertToString(res))
-              return res
-            })
-            .catch((error) => {
-              const err = error instanceof Error ? error : new Error(String(error))
-              span.setStatus({ code: SpanStatusCode.ERROR, message: err.message })
-              span.recordException(err)
-              throw error
-            })
-            .finally(() => span.end())
-        } else {
-          span.setStatus({ code: SpanStatusCode.OK })
-          span.setAttribute('outputs', convertToString(result))
-          span.end()
-        }
-        return result
-      }
-    )
-  )
-}
-
-function convertToString(args: any | any[]): string | boolean | number {
-  if (typeof args === 'string' || typeof args === 'boolean' || typeof args === 'number') {
-    return args
-  }
-  return JSON.stringify(args)
-}

packages/mcp-trace/trace-core/exporters/FuncSpanExporter.ts

@@ -1,26 +0,0 @@
-import { ExportResult, ExportResultCode } from '@opentelemetry/core'
-import { ReadableSpan, SpanExporter } from '@opentelemetry/sdk-trace-base'
-
-export type SaveFunction = (spans: ReadableSpan[]) => Promise<void>
-
-export class FunctionSpanExporter implements SpanExporter {
-  private exportFunction: SaveFunction
-
-  constructor(fn: SaveFunction) {
-    this.exportFunction = fn
-  }
-
-  shutdown(): Promise<void> {
-    return Promise.resolve()
-  }
-
-  export(spans: ReadableSpan[], resultCallback: (result: ExportResult) => void): void {
-    this.exportFunction(spans)
-      .then(() => {
-        resultCallback({ code: ExportResultCode.SUCCESS })
-      })
-      .catch((error) => {
-        resultCallback({ code: ExportResultCode.FAILED, error: error })
-      })
-  }
-}

packages/mcp-trace/trace-core/index.ts

@@ -1,8 +0,0 @@
-export * from './core/spanConvert'
-export * from './core/traceCache'
-export * from './core/traceMethod'
-export * from './exporters/FuncSpanExporter'
-export * from './processors/CacheSpanProcessor'
-export * from './processors/EmitterSpanProcessor'
-export * from './processors/FuncSpanProcessor'
-export * from './types/config'

packages/mcp-trace/trace-core/processors/CacheSpanProcessor.ts

@@ -1,40 +0,0 @@
-import { Context, trace } from '@opentelemetry/api'
-import { BatchSpanProcessor, BufferConfig, ReadableSpan, Span, SpanExporter } from '@opentelemetry/sdk-trace-base'
-
-import { TraceCache } from '../core/traceCache'
-
-export class CacheBatchSpanProcessor extends BatchSpanProcessor {
-  private cache: TraceCache
-
-  constructor(_exporter: SpanExporter, cache: TraceCache, config?: BufferConfig) {
-    super(_exporter, config)
-    this.cache = cache
-  }
-
-  override onEnd(span: ReadableSpan): void {
-    super.onEnd(span)
-    this.cache.endSpan(span)
-  }
-
-  override onStart(span: Span, parentContext: Context): void {
-    super.onStart(span, parentContext)
-    this.cache.createSpan({
-      name: span.name,
-      kind: span.kind,
-      spanContext: () => span.spanContext(),
-      parentSpanContext: trace.getSpanContext(parentContext),
-      startTime: span.startTime,
-      status: span.status,
-      attributes: span.attributes,
-      links: span.links,
-      events: span.events,
-      duration: span.duration,
-      ended: span.ended,
-      resource: span.resource,
-      instrumentationScope: span.instrumentationScope,
-      droppedAttributesCount: span.droppedAttributesCount,
-      droppedEventsCount: span.droppedEventsCount,
-      droppedLinksCount: span.droppedLinksCount
-    } as ReadableSpan)
-  }
-}

packages/mcp-trace/trace-core/processors/EmitterSpanProcessor.ts

@@ -1,28 +0,0 @@
-import { Context } from '@opentelemetry/api'
-import { BatchSpanProcessor, BufferConfig, ReadableSpan, Span, SpanExporter } from '@opentelemetry/sdk-trace-base'
-import { EventEmitter } from 'stream'
-
-import { convertSpanToSpanEntity } from '../core/spanConvert'
-
-export const TRACE_DATA_EVENT = 'trace_data_event'
-export const ON_START = 'start'
-export const ON_END = 'end'
-
-export class EmitterSpanProcessor extends BatchSpanProcessor {
-  private emitter: EventEmitter
-
-  constructor(_exporter: SpanExporter, emitter: NodeJS.EventEmitter, config?: BufferConfig) {
-    super(_exporter, config)
-    this.emitter = emitter
-  }
-
-  override onEnd(span: ReadableSpan): void {
-    super.onEnd(span)
-    this.emitter.emit(TRACE_DATA_EVENT, ON_END, convertSpanToSpanEntity(span))
-  }
-
-  override onStart(span: Span, parentContext: Context): void {
-    super.onStart(span, parentContext)
-    this.emitter.emit(TRACE_DATA_EVENT, ON_START, convertSpanToSpanEntity(span))
-  }
-}

packages/mcp-trace/trace-core/processors/FuncSpanProcessor.ts

@@ -1,42 +0,0 @@
-import { Context, trace } from '@opentelemetry/api'
-import { BatchSpanProcessor, BufferConfig, ReadableSpan, Span, SpanExporter } from '@opentelemetry/sdk-trace-base'
-
-export type SpanFunction = (span: ReadableSpan) => void
-
-export class FunctionSpanProcessor extends BatchSpanProcessor {
-  private start: SpanFunction
-  private end: SpanFunction
-
-  constructor(_exporter: SpanExporter, start: SpanFunction, end: SpanFunction, config?: BufferConfig) {
-    super(_exporter, config)
-    this.start = start
-    this.end = end
-  }
-
-  override onEnd(span: ReadableSpan): void {
-    super.onEnd(span)
-    this.end(span)
-  }
-
-  override onStart(span: Span, parentContext: Context): void {
-    super.onStart(span, parentContext)
-    this.start({
-      name: span.name,
-      kind: span.kind,
-      spanContext: () => span.spanContext(),
-      parentSpanContext: trace.getSpanContext(parentContext),
-      startTime: span.startTime,
-      status: span.status,
-      attributes: span.attributes,
-      links: span.links,
-      events: span.events,
-      duration: span.duration,
-      ended: span.ended,
-      resource: span.resource,
-      instrumentationScope: span.instrumentationScope,
-      droppedAttributesCount: span.droppedAttributesCount,
-      droppedEventsCount: span.droppedEventsCount,
-      droppedLinksCount: span.droppedLinksCount
-    } as ReadableSpan)
-  }
-}

packages/mcp-trace/trace-core/types/config.ts

@@ -1,65 +0,0 @@
-import { Link } from '@opentelemetry/api'
-import { TimedEvent } from '@opentelemetry/sdk-trace-base'
-
-export type AttributeValue =
-  | string
-  | number
-  | boolean
-  | Array<null | undefined | string>
-  | Array<null | undefined | number>
-  | Array<null | undefined | boolean>
-  | { [key: string]: string | number | boolean }
-  | Array<null | undefined | { [key: string]: string | number | boolean }>
-
-export type Attributes = {
-  [key: string]: AttributeValue
-}
-
-export interface TelemetryConfig {
-  serviceName: string
-  endpoint?: string
-  headers?: Record<string, string>
-  defaultTracerName?: string
-}
-
-export interface TraceConfig extends TelemetryConfig {
-  maxAttributesPerSpan?: number
-}
-
-export interface TraceEntity {
-  id: string
-  name: string
-}
-
-export interface TokenUsage {
-  prompt_tokens: number
-  completion_tokens: number
-  total_tokens: number
-  prompt_tokens_details?: {
-    [key: string]: number
-  }
-}
-
-export interface SpanEntity {
-  id: string
-  name: string
-  parentId: string
-  traceId: string
-  status: string
-  kind: string
-  attributes: Attributes | undefined
-  isEnd: boolean
-  events: TimedEvent[] | undefined
-  startTime: number
-  endTime: number | null
-  links: Link[] | undefined
-  topicId?: string
-  usage?: TokenUsage
-  modelName?: string
-}
-
-export const defaultConfig: TelemetryConfig = {
-  serviceName: 'default',
-  headers: {},
-  defaultTracerName: 'default'
-}

packages/mcp-trace/trace-node/nodeTracer.ts

@@ -1,46 +0,0 @@
-import { trace, Tracer } from '@opentelemetry/api'
-import { AsyncLocalStorageContextManager } from '@opentelemetry/context-async-hooks'
-import { W3CTraceContextPropagator } from '@opentelemetry/core'
-import { OTLPTraceExporter } from '@opentelemetry/exporter-trace-otlp-http'
-import { BatchSpanProcessor, ConsoleSpanExporter, SpanProcessor } from '@opentelemetry/sdk-trace-base'
-import { NodeTracerProvider } from '@opentelemetry/sdk-trace-node'
-
-import { defaultConfig, TraceConfig } from '../trace-core/types/config'
-
-export class NodeTracer {
-  private static provider: NodeTracerProvider
-  private static defaultTracer: Tracer
-  private static spanProcessor: SpanProcessor
-
-  static init(config?: TraceConfig, spanProcessor?: SpanProcessor) {
-    if (config) {
-      defaultConfig.serviceName = config.serviceName || defaultConfig.serviceName
-      defaultConfig.endpoint = config.endpoint || defaultConfig.endpoint
-      defaultConfig.headers = config.headers || defaultConfig.headers
-      defaultConfig.defaultTracerName = config.defaultTracerName || defaultConfig.defaultTracerName
-    }
-    this.spanProcessor = spanProcessor || new BatchSpanProcessor(this.getExporter())
-    this.provider = new NodeTracerProvider({
-      spanProcessors: [this.spanProcessor]
-    })
-    this.provider.register({
-      propagator: new W3CTraceContextPropagator(),
-      contextManager: new AsyncLocalStorageContextManager()
-    })
-    this.defaultTracer = trace.getTracer(config?.defaultTracerName || 'default')
-  }
-
-  private static getExporter(config?: TraceConfig) {
-    if (config && config.endpoint) {
-      return new OTLPTraceExporter({
-        url: `${config.endpoint}/v1/traces`,
-        headers: config.headers || undefined
-      })
-    }
-    return new ConsoleSpanExporter()
-  }
-
-  public static getTracer() {
-    return this.defaultTracer
-  }
-}

packages/mcp-trace/trace-web/TopicContextManager.ts

@@ -1,75 +0,0 @@
-import { Context, ContextManager, ROOT_CONTEXT } from '@opentelemetry/api'
-
-export class TopicContextManager implements ContextManager {
-  private topicContextStack: Map<string, Context[]>
-  private _topicContexts: Map<string, Context>
-
-  constructor() {
-    // topicId -> context
-    this.topicContextStack = new Map()
-    this._topicContexts = new Map()
-  }
-
-  // 绑定一个context到topicId
-  startContextForTopic(topicId, context: Context) {
-    const currentContext = this.getCurrentContext(topicId)
-    this._topicContexts.set(topicId, context)
-    if (!this.topicContextStack.has(topicId) && !this.topicContextStack.get(topicId)) {
-      this.topicContextStack.set(topicId, [currentContext])
-    } else {
-      this.topicContextStack.get(topicId)?.push(currentContext)
-    }
-  }
-
-  // 获取topicId对应的context
-  getContextForTopic(topicId) {
-    return this.getCurrentContext(topicId)
-  }
-
-  endContextForTopic(topicId) {
-    const context = this.getHistoryContext(topicId)
-    this._topicContexts.set(topicId, context)
-  }
-
-  cleanContextForTopic(topicId) {
-    this.topicContextStack.delete(topicId)
-    this._topicContexts.delete(topicId)
-  }
-
-  private getHistoryContext(topicId): Context {
-    const hasContext = this.topicContextStack.has(topicId) && this.topicContextStack.get(topicId)
-    const context = hasContext && hasContext.length > 0 && hasContext.pop()
-    return context ? context : ROOT_CONTEXT
-  }
-
-  private getCurrentContext(topicId): Context {
-    const hasContext = this._topicContexts.has(topicId) && this._topicContexts.get(topicId)
-    return hasContext || ROOT_CONTEXT
-  }
-
-  // OpenTelemetry接口实现
-  active() {
-    // 不支持全局active，必须显式传递
-    return ROOT_CONTEXT
-  }
-
-  with(_, fn, thisArg, ...args) {
-    // 直接调用fn，不做全局active切换
-    return fn.apply(thisArg, args)
-  }
-
-  bind(target, context) {
-    // 显式绑定
-    target.__ot_context = context
-    return target
-  }
-
-  enable() {
-    return this
-  }
-
-  disable() {
-    this._topicContexts.clear()
-    return this
-  }
-}

packages/mcp-trace/trace-web/index.ts

@@ -1,3 +0,0 @@
-export * from './TopicContextManager'
-export * from './traceContextPromise'
-export * from './webTracer'

packages/mcp-trace/trace-web/traceContextPromise.ts

@@ -1,99 +0,0 @@
-import { Context, context } from '@opentelemetry/api'
-
-const originalPromise = globalThis.Promise
-
-class TraceContextPromise<T> extends Promise<T> {
-  _context: Context
-
-  constructor(
-    executor: (resolve: (value: T | PromiseLike<T>) => void, reject: (reason?: any) => void) => void,
-    ctx?: Context
-  ) {
-    const capturedContext = ctx || context.active()
-    super((resolve, reject) => {
-      context.with(capturedContext, () => {
-        executor(
-          (value) => context.with(capturedContext, () => resolve(value)),
-          (reason) => context.with(capturedContext, () => reject(reason))
-        )
-      })
-    })
-    this._context = capturedContext
-  }
-
-  // 兼容 Promise.resolve/reject
-  static resolve(): Promise<void>
-  static resolve<T>(value: T | PromiseLike<T>): Promise<T>
-  static resolve<T>(value: T | PromiseLike<T>, ctx?: Context): Promise<T>
-  static resolve<T>(value?: T | PromiseLike<T>, ctx?: Context): Promise<T | void> {
-    return new TraceContextPromise<T | void>((resolve) => resolve(value as T), ctx)
-  }
-
-  static reject<T = never>(reason?: any): Promise<T>
-  static reject<T = never>(reason?: any, ctx?: Context): Promise<T> {
-    return new TraceContextPromise<T>((_, reject) => reject(reason), ctx)
-  }
-
-  static all<T>(values: (T | PromiseLike<T>)[]): Promise<T[]> {
-    // 尝试从缓存获取 context
-    let capturedContext = context.active()
-    const newValues = values.map((v) => {
-      if (v instanceof Promise && !(v instanceof TraceContextPromise)) {
-        return new TraceContextPromise((resolve, reject) => v.then(resolve, reject), capturedContext)
-      } else if (typeof v === 'function') {
-        // 如果 v 是一个 Function，使用 context 传递 trace 上下文
-        return (...args: any[]) => context.with(capturedContext, () => v(...args))
-      } else {
-        return v
-      }
-    })
-    if (Array.isArray(values) && values.length > 0 && values[0] instanceof TraceContextPromise) {
-      capturedContext = (values[0] as TraceContextPromise<any>)._context
-    }
-    return originalPromise.all(newValues) as Promise<T[]>
-  }
-
-  static race<T>(values: (T | PromiseLike<T>)[]): Promise<T> {
-    const capturedContext = context.active()
-    return new TraceContextPromise<T>((resolve, reject) => {
-      originalPromise.race(values).then(
-        (result) => context.with(capturedContext, () => resolve(result)),
-        (err) => context.with(capturedContext, () => reject(err))
-      )
-    }, capturedContext)
-  }
-
-  static allSettled<T>(values: (T | PromiseLike<T>)[]): Promise<PromiseSettledResult<T>[]> {
-    const capturedContext = context.active()
-    return new TraceContextPromise<PromiseSettledResult<T>[]>((resolve, reject) => {
-      originalPromise.allSettled(values).then(
-        (result) => context.with(capturedContext, () => resolve(result)),
-        (err) => context.with(capturedContext, () => reject(err))
-      )
-    }, capturedContext)
-  }
-
-  static any<T>(values: (T | PromiseLike<T>)[]): Promise<T> {
-    const capturedContext = context.active()
-    return new TraceContextPromise<T>((resolve, reject) => {
-      originalPromise.any(values).then(
-        (result) => context.with(capturedContext, () => resolve(result)),
-        (err) => context.with(capturedContext, () => reject(err))
-      )
-    }, capturedContext)
-  }
-}
-
-/**
- * 用 TraceContextPromise 替换全局 Promise
- */
-export function instrumentPromises() {
-  globalThis.Promise = TraceContextPromise as unknown as PromiseConstructor
-}
-
-/**
- * 恢复原生 Promise
- */
-export function uninstrumentPromises() {
-  globalThis.Promise = originalPromise
-}

packages/mcp-trace/trace-web/webTracer.ts

@@ -1,46 +0,0 @@
-import { W3CTraceContextPropagator } from '@opentelemetry/core'
-import { OTLPTraceExporter } from '@opentelemetry/exporter-trace-otlp-http'
-import { BatchSpanProcessor, ConsoleSpanExporter, SpanProcessor } from '@opentelemetry/sdk-trace-base'
-import { WebTracerProvider } from '@opentelemetry/sdk-trace-web'
-
-import { defaultConfig, TraceConfig } from '../trace-core/types/config'
-import { TopicContextManager } from './TopicContextManager'
-
-export const contextManager = new TopicContextManager()
-
-export class WebTracer {
-  private static provider: WebTracerProvider
-  private static processor: SpanProcessor
-
-  static init(config?: TraceConfig, spanProcessor?: SpanProcessor) {
-    if (config) {
-      defaultConfig.serviceName = config.serviceName || defaultConfig.serviceName
-      defaultConfig.endpoint = config.endpoint || defaultConfig.endpoint
-      defaultConfig.headers = config.headers || defaultConfig.headers
-      defaultConfig.defaultTracerName = config.defaultTracerName || defaultConfig.defaultTracerName
-    }
-    this.processor = spanProcessor || new BatchSpanProcessor(this.getExporter())
-    this.provider = new WebTracerProvider({
-      spanProcessors: [this.processor]
-    })
-    this.provider.register({
-      propagator: new W3CTraceContextPropagator(),
-      contextManager: contextManager
-    })
-  }
-
-  private static getExporter() {
-    if (defaultConfig.endpoint) {
-      return new OTLPTraceExporter({
-        url: `${defaultConfig.endpoint}/v1/traces`,
-        headers: defaultConfig.headers
-      })
-    }
-    return new ConsoleSpanExporter()
-  }
-}
-
-export const startContext = contextManager.startContextForTopic.bind(contextManager)
-export const getContext = contextManager.getContextForTopic.bind(contextManager)
-export const endContext = contextManager.endContextForTopic.bind(contextManager)
-export const cleanContext = contextManager.cleanContextForTopic.bind(contextManager)

packages/shared/IpcChannel.ts

@@ -31,7 +31,6 @@ export enum IpcChannel {
   App_GetBinaryPath = 'app:get-binary-path',
   App_InstallUvBinary = 'app:install-uv-binary',
   App_InstallBunBinary = 'app:install-bun-binary',
-  App_LogToMain = 'app:log-to-main',
 
   App_MacIsProcessTrusted = 'app:mac-is-process-trusted',
   App_MacRequestProcessTrust = 'app:mac-request-process-trust',
@@ -75,10 +74,6 @@ export enum IpcChannel {
   Mcp_ServersChanged = 'mcp:servers-changed',
   Mcp_ServersUpdated = 'mcp:servers-updated',
   Mcp_CheckConnectivity = 'mcp:check-connectivity',
-  Mcp_UploadDxt = 'mcp:upload-dxt',
-  Mcp_SetProgress = 'mcp:set-progress',
-  Mcp_AbortTool = 'mcp:abort-tool',
-  Mcp_GetServerVersion = 'mcp:get-server-version',
 
   // Python
   Python_Execute = 'python:execute',
@@ -150,7 +145,6 @@ export enum IpcChannel {
   File_Base64File = 'file:base64File',
   File_GetPdfInfo = 'file:getPdfInfo',
   Fs_Read = 'fs:read',
-  File_OpenWithRelativePath = 'file:openWithRelativePath',
 
   // file service
   FileService_Upload = 'file-service:upload',
@@ -171,16 +165,6 @@ export enum IpcChannel {
   Backup_CheckConnection = 'backup:checkConnection',
   Backup_CreateDirectory = 'backup:createDirectory',
   Backup_DeleteWebdavFile = 'backup:deleteWebdavFile',
-  Backup_BackupToLocalDir = 'backup:backupToLocalDir',
-  Backup_RestoreFromLocalBackup = 'backup:restoreFromLocalBackup',
-  Backup_ListLocalBackupFiles = 'backup:listLocalBackupFiles',
-  Backup_DeleteLocalBackupFile = 'backup:deleteLocalBackupFile',
-  Backup_SetLocalBackupDir = 'backup:setLocalBackupDir',
-  Backup_BackupToS3 = 'backup:backupToS3',
-  Backup_RestoreFromS3 = 'backup:restoreFromS3',
-  Backup_ListS3Files = 'backup:listS3Files',
-  Backup_DeleteS3File = 'backup:deleteS3File',
-  Backup_CheckS3Connection = 'backup:checkS3Connection',
 
   // zip
   Zip_Compress = 'zip:compress',
@@ -245,32 +229,5 @@ export enum IpcChannel {
   Selection_ActionWindowMinimize = 'selection:action-window-minimize',
   Selection_ActionWindowPin = 'selection:action-window-pin',
   Selection_ProcessAction = 'selection:process-action',
-  Selection_UpdateActionData = 'selection:update-action-data',
-
-  // Memory
-  Memory_Add = 'memory:add',
-  Memory_Search = 'memory:search',
-  Memory_List = 'memory:list',
-  Memory_Delete = 'memory:delete',
-  Memory_Update = 'memory:update',
-  Memory_Get = 'memory:get',
-  Memory_SetConfig = 'memory:set-config',
-  Memory_DeleteUser = 'memory:delete-user',
-  Memory_DeleteAllMemoriesForUser = 'memory:delete-all-memories-for-user',
-  Memory_GetUsersList = 'memory:get-users-list',
-
-  // TRACE
-  TRACE_SAVE_DATA = 'trace:saveData',
-  TRACE_GET_DATA = 'trace:getData',
-  TRACE_SAVE_ENTITY = 'trace:saveEntity',
-  TRACE_GET_ENTITY = 'trace:getEntity',
-  TRACE_BIND_TOPIC = 'trace:bindTopic',
-  TRACE_CLEAN_TOPIC = 'trace:cleanTopic',
-  TRACE_TOKEN_USAGE = 'trace:tokenUsage',
-  TRACE_CLEAN_HISTORY = 'trace:cleanHistory',
-  TRACE_OPEN_WINDOW = 'trace:openWindow',
-  TRACE_SET_TITLE = 'trace:setTitle',
-  TRACE_ADD_END_MESSAGE = 'trace:addEndMessage',
-  TRACE_CLEAN_LOCAL_DATA = 'trace:cleanLocalData',
-  TRACE_ADD_STREAM_MESSAGE = 'trace:addStreamMessage'
+  Selection_UpdateActionData = 'selection:update-action-data'
 }

packages/shared/config/constant.ts

@@ -193,7 +193,6 @@ const textExtsByCategory = new Map([
       '.htm',
       '.xhtml', // HTML
       '.xml', // XML
-      '.fxml', // JavaFX XML
       '.org', // Org-mode
       '.wiki', // Wiki
       '.tex',
@@ -348,8 +347,7 @@ const textExtsByCategory = new Map([
       '.x3d', // X3D文件
       '.gltf', // glTF JSON
       '.prefab', // Unity预制体 (YAML格式)
-      '.meta', // Unity元数据文件 (YAML格式)
-      '.tscn' // Godot场景文件
+      '.meta' // Unity元数据文件 (YAML格式)
     ]
   ],
   [

packages/shared/config/logger.ts

@@ -1,32 +0,0 @@
-export type LogSourceWithContext = {
-  process: 'main' | 'renderer'
-  window?: string // only for renderer process
-  module?: string
-  context?: Record<string, any>
-}
-
-type NullableObject = object | undefined | null
-
-export type LogContextData = [] | [Error | NullableObject] | [Error | NullableObject, ...NullableObject[]]
-
-export type LogLevel = 'error' | 'warn' | 'info' | 'debug' | 'verbose' | 'silly' | 'none'
-
-export const LEVEL = {
-  ERROR: 'error',
-  WARN: 'warn',
-  INFO: 'info',
-  DEBUG: 'debug',
-  VERBOSE: 'verbose',
-  SILLY: 'silly',
-  NONE: 'none'
-} satisfies Record<string, LogLevel>
-
-export const LEVEL_MAP: Record<LogLevel, number> = {
-  error: 10,
-  warn: 8,
-  info: 6,
-  debug: 4,
-  verbose: 2,
-  silly: 0,
-  none: -1
-}

resources/model-catalogs/01-ai/yi-large.yaml

@@ -0,0 +1,47 @@
+id: 01-ai/yi-large
+canonical_slug: 01-ai/yi-large
+hugging_face_id: ''
+name: '01.AI: Yi Large'
+type: chat
+created: 1719273600
+description: |-
+  The Yi Large model was designed by 01.AI with the following usecases in mind: knowledge search, data classification, human-like chat bots, and customer service.
+
+  It stands out for its multilingual proficiency, particularly in Spanish, Chinese, Japanese, German, and French.
+
+  Check out the [launch announcement](https://01-ai.github.io/blog/01.ai-yi-large-llm-launch) to learn more.
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Yi
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000003'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - response_format
+  - structured_outputs
+  - logit_bias
+  - logprobs
+  - top_logprobs
+model_provider: 01-ai

resources/model-catalogs/aetherwiing/mn-starcannon-12b.yaml

@@ -0,0 +1,42 @@
+id: aetherwiing/mn-starcannon-12b
+canonical_slug: aetherwiing/mn-starcannon-12b
+hugging_face_id: aetherwiing/MN-12B-Starcannon-v2
+name: 'Aetherwiing: Starcannon 12B'
+type: chat
+created: 1723507200
+description: |-
+  Starcannon 12B v2 is a creative roleplay and story writing model, based on Mistral Nemo, using [nothingiisreal/mn-celeste-12b](/nothingiisreal/mn-celeste-12b) as a base, with [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1) merged in using the [TIES](https://arxiv.org/abs/2306.01708) method.
+
+  Although more similar to Magnum overall, the model remains very creative, with a pleasant writing style. It is recommended for people wanting more variety than Magnum, and yet more verbose prose than Celeste.
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Mistral
+  instruct_type: chatml
+pricing:
+  prompt: '0.0000008'
+  completion: '0.0000012'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: aetherwiing

resources/model-catalogs/ai21/jamba-1.6-large.yaml

@@ -0,0 +1,38 @@
+id: ai21/jamba-1.6-large
+canonical_slug: ai21/jamba-1.6-large
+hugging_face_id: ai21labs/AI21-Jamba-Large-1.6
+name: 'AI21: Jamba 1.6 Large'
+type: chat
+created: 1741905173
+description: |-
+  AI21 Jamba Large 1.6 is a high-performance hybrid foundation model combining State Space Models (Mamba) with Transformer attention mechanisms. Developed by AI21, it excels in extremely long-context handling (256K tokens), demonstrates superior inference efficiency (up to 2.5x faster than comparable models), and supports structured JSON output and tool-use capabilities. It has 94 billion active parameters (398 billion total), optimized quantization support (ExpertsInt8), and multilingual proficiency in languages such as English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew.
+
+  Usage of this model is subject to the [Jamba Open Model License](https://www.ai21.com/licenses/jamba-open-model-license).
+context_length: 256000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.000002'
+  completion: '0.000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+model_provider: ai21

resources/model-catalogs/ai21/jamba-1.6-mini.yaml

@@ -0,0 +1,38 @@
+id: ai21/jamba-1.6-mini
+canonical_slug: ai21/jamba-1.6-mini
+hugging_face_id: ai21labs/AI21-Jamba-Mini-1.6
+name: 'AI21: Jamba Mini 1.6'
+type: chat
+created: 1741905171
+description: |-
+  AI21 Jamba Mini 1.6 is a hybrid foundation model combining State Space Models (Mamba) with Transformer attention mechanisms. With 12 billion active parameters (52 billion total), this model excels in extremely long-context tasks (up to 256K tokens) and achieves superior inference efficiency, outperforming comparable open models on tasks such as retrieval-augmented generation (RAG) and grounded question answering. Jamba Mini 1.6 supports multilingual tasks across English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew, along with structured JSON output and tool-use capabilities.
+
+  Usage of this model is subject to the [Jamba Open Model License](https://www.ai21.com/licenses/jamba-open-model-license).
+context_length: 256000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000002'
+  completion: '0.0000004'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+model_provider: ai21

resources/model-catalogs/aion-labs/aion-1.0-mini.yaml

@@ -0,0 +1,34 @@
+id: aion-labs/aion-1.0-mini
+canonical_slug: aion-labs/aion-1.0-mini
+hugging_face_id: FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
+name: 'AionLabs: Aion-1.0-Mini'
+type: chat
+created: 1738697107
+description: Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant of a FuseAI model that outperforms R1-Distill-Qwen-32B and R1-Distill-Llama-70B, with benchmark results available on its [Hugging Face page](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview), independently replicated for verification.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000007'
+  completion: '0.0000014'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+model_provider: aion-labs

resources/model-catalogs/aion-labs/aion-1.0.yaml

@@ -0,0 +1,34 @@
+id: aion-labs/aion-1.0
+canonical_slug: aion-labs/aion-1.0
+hugging_face_id: ''
+name: 'AionLabs: Aion-1.0'
+type: chat
+created: 1738697557
+description: Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree of Thoughts (ToT) and Mixture of Experts (MoE). It is Aion Lab's most powerful reasoning model.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.000004'
+  completion: '0.000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - reasoning
+  - include_reasoning
+model_provider: aion-labs

resources/model-catalogs/aion-labs/aion-rp-llama-3.1-8b.yaml

@@ -0,0 +1,32 @@
+id: aion-labs/aion-rp-llama-3.1-8b
+canonical_slug: aion-labs/aion-rp-llama-3.1-8b
+hugging_face_id: ''
+name: 'AionLabs: Aion-RP 1.0 (8B)'
+type: chat
+created: 1738696718
+description: Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model rather than an instruct model, designed to produce more natural and varied writing.
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000002'
+  completion: '0.0000002'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+model_provider: aion-labs

resources/model-catalogs/alfredpros/codellama-7b-instruct-solidity.yaml

@@ -0,0 +1,39 @@
+id: alfredpros/codellama-7b-instruct-solidity
+canonical_slug: alfredpros/codellama-7b-instruct-solidity
+hugging_face_id: AlfredPros/CodeLlama-7b-Instruct-Solidity
+name: 'AlfredPros: CodeLLaMa 7B Instruct Solidity'
+type: chat
+created: 1744641874
+description: A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.
+context_length: 4096
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: alpaca
+pricing:
+  prompt: '0.0000008'
+  completion: '0.0000012'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: alfredpros

resources/model-catalogs/all-hands/openhands-lm-32b-v0.1.yaml

@@ -0,0 +1,44 @@
+id: all-hands/openhands-lm-32b-v0.1
+canonical_slug: all-hands/openhands-lm-32b-v0.1
+hugging_face_id: all-hands/openhands-lm-32b-v0.1
+name: OpenHands LM 32B V0.1
+type: chat
+created: 1743613013
+description: |-
+  OpenHands LM v0.1 is a 32B open-source coding model fine-tuned from Qwen2.5-Coder-32B-Instruct using reinforcement learning techniques outlined in SWE-Gym. It is optimized for autonomous software development agents and achieves strong performance on SWE-Bench Verified, with a 37.2% resolve rate. The model supports a 128K token context window, making it well-suited for long-horizon code reasoning and large codebase tasks.
+
+  OpenHands LM is designed for local deployment and runs on consumer-grade GPUs such as a single 3090. It enables fully offline agent workflows without dependency on proprietary APIs. This release is intended as a research preview, and future updates aim to improve generalizability, reduce repetition, and offer smaller variants.
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000026'
+  completion: '0.0000034'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: all-hands

resources/model-catalogs/alpindale/goliath-120b.yaml

@@ -0,0 +1,48 @@
+id: alpindale/goliath-120b
+canonical_slug: alpindale/goliath-120b
+hugging_face_id: alpindale/goliath-120b
+name: Goliath 120B
+type: chat
+created: 1699574400
+description: |-
+  A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.
+
+  Credits to
+  - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergekit](https://github.com/cg123/mergekit).
+  - [@Undi95](https://huggingface.co/Undi95) for helping with the merge ratios.
+
+  #merge
+context_length: 6144
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Llama2
+  instruct_type: airoboros
+pricing:
+  prompt: '0.00001'
+  completion: '0.0000125'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - logit_bias
+  - top_k
+  - min_p
+  - seed
+  - top_a
+model_provider: alpindale

resources/model-catalogs/alpindale/magnum-72b.yaml

@@ -0,0 +1,42 @@
+id: alpindale/magnum-72b
+canonical_slug: alpindale/magnum-72b
+hugging_face_id: alpindale/magnum-72b-v1
+name: Magnum 72B
+type: chat
+created: 1720656000
+description: |-
+  From the maker of [Goliath](https://openrouter.ai/models/alpindale/goliath-120b), Magnum 72B is the first in a new family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet.
+
+  The model is based on [Qwen2 72B](https://openrouter.ai/models/qwen/qwen-2-72b-instruct) and trained with 55 million tokens of highly curated roleplay (RP) data.
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: chatml
+pricing:
+  prompt: '0.000004'
+  completion: '0.000006'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+model_provider: alpindale

resources/model-catalogs/amazon/nova-lite-v1.yaml

@@ -0,0 +1,39 @@
+id: amazon/nova-lite-v1
+canonical_slug: amazon/nova-lite-v1
+hugging_face_id: ''
+name: 'Amazon: Nova Lite 1.0'
+type: chat
+created: 1733437363
+description: |-
+  Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.
+
+  With an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.
+context_length: 300000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Nova
+  instruct_type: null
+pricing:
+  prompt: '0.00000006'
+  completion: '0.00000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0.00009'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: amazon

resources/model-catalogs/amazon/nova-micro-v1.yaml

@@ -0,0 +1,35 @@
+id: amazon/nova-micro-v1
+canonical_slug: amazon/nova-micro-v1
+hugging_face_id: ''
+name: 'Amazon: Nova Micro 1.0'
+type: chat
+created: 1733437237
+description: Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has  simple mathematical reasoning and coding abilities.
+context_length: 128000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Nova
+  instruct_type: null
+pricing:
+  prompt: '0.000000035'
+  completion: '0.00000014'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: amazon

resources/model-catalogs/amazon/nova-pro-v1.yaml

@@ -0,0 +1,41 @@
+id: amazon/nova-pro-v1
+canonical_slug: amazon/nova-pro-v1
+hugging_face_id: ''
+name: 'Amazon: Nova Pro 1.0'
+type: chat
+created: 1733436303
+description: |-
+  Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December 2024, it achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).
+
+  Amazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.
+
+  **NOTE**: Video input is not supported at this time.
+context_length: 300000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Nova
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.0000032'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0.0012'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: amazon

resources/model-catalogs/anthracite-org/magnum-v2-72b.yaml

@@ -0,0 +1,43 @@
+id: anthracite-org/magnum-v2-72b
+canonical_slug: anthracite-org/magnum-v2-72b
+hugging_face_id: anthracite-org/magnum-v2-72b
+name: Magnum v2 72B
+type: chat
+created: 1727654400
+description: |-
+  From the maker of [Goliath](https://openrouter.ai/models/alpindale/goliath-120b), Magnum 72B is the seventh in a family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet.
+
+  The model is based on [Qwen2 72B](https://openrouter.ai/models/qwen/qwen-2-72b-instruct) and trained with 55 million tokens of highly curated roleplay (RP) data.
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: chatml
+pricing:
+  prompt: '0.000003'
+  completion: '0.000003'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - logit_bias
+  - top_k
+  - min_p
+  - seed
+model_provider: anthracite-org

resources/model-catalogs/anthracite-org/magnum-v4-72b.yaml

@@ -0,0 +1,44 @@
+id: anthracite-org/magnum-v4-72b
+canonical_slug: anthracite-org/magnum-v4-72b
+hugging_face_id: anthracite-org/magnum-v4-72b
+name: Magnum v4 72B
+type: chat
+created: 1729555200
+description: |-
+  This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).
+
+  The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
+context_length: 16384
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Qwen
+  instruct_type: chatml
+pricing:
+  prompt: '0.0000025'
+  completion: '0.000003'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - repetition_penalty
+  - top_k
+  - min_p
+  - seed
+  - logit_bias
+  - top_a
+model_provider: anthracite-org

resources/model-catalogs/anthropic/claude-2-beta.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2:beta
+canonical_slug: anthropic/claude-2
+hugging_face_id: ''
+name: 'Anthropic: Claude v2 (self-moderated)'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.0-beta.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.0:beta
+canonical_slug: anthropic/claude-2.0
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.0 (self-moderated)'
+type: chat
+created: 1690502400
+description: Anthropic's flagship model. Superior performance on tasks that require complex reasoning. Supports hundreds of pages of text.
+context_length: 100000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.0.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.0
+canonical_slug: anthropic/claude-2.0
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.0'
+type: chat
+created: 1690502400
+description: Anthropic's flagship model. Superior performance on tasks that require complex reasoning. Supports hundreds of pages of text.
+context_length: 100000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.1-beta.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.1:beta
+canonical_slug: anthropic/claude-2.1
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.1 (self-moderated)'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.1.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2.1
+canonical_slug: anthropic/claude-2.1
+hugging_face_id: ''
+name: 'Anthropic: Claude v2.1'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-2.yaml

@@ -0,0 +1,34 @@
+id: anthropic/claude-2
+canonical_slug: anthropic/claude-2
+hugging_face_id: ''
+name: 'Anthropic: Claude v2'
+type: chat
+created: 1700611200
+description: 'Claude 2 delivers advancements in key capabilities for enterprises—including an industry-leading 200K token context window, significant reductions in rates of model hallucination, system prompts and a new beta feature: tool use.'
+context_length: 200000
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000008'
+  completion: '0.000024'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-haiku-beta.yaml

@@ -0,0 +1,43 @@
+id: anthropic/claude-3-haiku:beta
+canonical_slug: anthropic/claude-3-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Haiku (self-moderated)'
+type: chat
+created: 1710288000
+description: |-
+  Claude 3 Haiku is Anthropic's fastest and most compact model for
+  near-instant responsiveness. Quick and accurate targeted performance.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.00000025'
+  completion: '0.00000125'
+  input_cache_read: '0.00000003'
+  input_cache_write: '0.0000003'
+  request: '0'
+  image: '0.0004'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-haiku.yaml

@@ -0,0 +1,43 @@
+id: anthropic/claude-3-haiku
+canonical_slug: anthropic/claude-3-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Haiku'
+type: chat
+created: 1710288000
+description: |-
+  Claude 3 Haiku is Anthropic's fastest and most compact model for
+  near-instant responsiveness. Quick and accurate targeted performance.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.00000025'
+  completion: '0.00000125'
+  input_cache_read: '0.00000003'
+  input_cache_write: '0.0000003'
+  request: '0'
+  image: '0.0004'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-opus-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-opus:beta
+canonical_slug: anthropic/claude-3-opus
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Opus (self-moderated)'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000015'
+  completion: '0.000075'
+  input_cache_read: '0.0000015'
+  input_cache_write: '0.00001875'
+  request: '0'
+  image: '0.024'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-opus.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-opus
+canonical_slug: anthropic/claude-3-opus
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Opus'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000015'
+  completion: '0.000075'
+  input_cache_read: '0.0000015'
+  input_cache_write: '0.00001875'
+  request: '0'
+  image: '0.024'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-sonnet-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-sonnet:beta
+canonical_slug: anthropic/claude-3-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Sonnet (self-moderated)'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3-sonnet.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3-sonnet
+canonical_slug: anthropic/claude-3-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3 Sonnet'
+type: chat
+created: 1709596800
+description: |-
+  Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-family)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku-20241022-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku-20241022:beta
+canonical_slug: anthropic/claude-3-5-haiku-20241022
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku (2024-10-22) (self-moderated)'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.
+
+  It does not support image inputs.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku-20241022.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku-20241022
+canonical_slug: anthropic/claude-3-5-haiku-20241022
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku (2024-10-22)'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features enhancements across all skill sets including coding, tool use, and reasoning. As the fastest model in the Anthropic lineup, it offers rapid response times suitable for applications that require high interactivity and low latency, such as user-facing chatbots and on-the-fly code completions. It also excels in specialized tasks like data extraction and real-time content moderation, making it a versatile tool for a broad range of industries.
+
+  It does not support image inputs.
+
+  See the launch announcement and benchmark results [here](https://www.anthropic.com/news/3-5-models-and-computer-use)
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku-beta.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku:beta
+canonical_slug: anthropic/claude-3-5-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku (self-moderated)'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.
+
+  This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.
+
+  This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-haiku.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-3.5-haiku
+canonical_slug: anthropic/claude-3-5-haiku
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Haiku'
+type: chat
+created: 1730678400
+description: |-
+  Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.
+
+  This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.
+
+  This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.0000008'
+  completion: '0.000004'
+  input_cache_read: '0.00000008'
+  input_cache_write: '0.000001'
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet-20240620-beta.yaml

@@ -0,0 +1,47 @@
+id: anthropic/claude-3.5-sonnet-20240620:beta
+canonical_slug: anthropic/claude-3.5-sonnet-20240620
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet (2024-06-20) (self-moderated)'
+type: chat
+created: 1718841600
+description: |-
+  Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  For the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet-20240620.yaml

@@ -0,0 +1,47 @@
+id: anthropic/claude-3.5-sonnet-20240620
+canonical_slug: anthropic/claude-3.5-sonnet-20240620
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet (2024-06-20)'
+type: chat
+created: 1718841600
+description: |-
+  Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Autonomously writes, edits, and runs code with reasoning and troubleshooting
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  For the latest version (2024-10-23), check out [Claude 3.5 Sonnet](/anthropic/claude-3.5-sonnet).
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet-beta.yaml

@@ -0,0 +1,45 @@
+id: anthropic/claude-3.5-sonnet:beta
+canonical_slug: anthropic/claude-3.5-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet (self-moderated)'
+type: chat
+created: 1729555200
+description: |-
+  New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.5-sonnet.yaml

@@ -0,0 +1,45 @@
+id: anthropic/claude-3.5-sonnet
+canonical_slug: anthropic/claude-3.5-sonnet
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.5 Sonnet'
+type: chat
+created: 1729555200
+description: |-
+  New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at:
+
+  - Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding
+  - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights
+  - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone
+  - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems)
+
+  #multimodal
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - top_k
+  - stop
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.7-sonnet-beta.yaml

@@ -0,0 +1,37 @@
+id: anthropic/claude-3.7-sonnet:beta
+canonical_slug: anthropic/claude-3-7-sonnet-20250219
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.7 Sonnet (self-moderated)'
+type: chat
+created: 1740422110
+description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.7-sonnet-thinking.yaml

@@ -0,0 +1,37 @@
+id: anthropic/claude-3.7-sonnet:thinking
+canonical_slug: anthropic/claude-3-7-sonnet-20250219
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.7 Sonnet (thinking)'
+type: chat
+created: 1740422110
+description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-3.7-sonnet.yaml

@@ -0,0 +1,39 @@
+id: anthropic/claude-3.7-sonnet
+canonical_slug: anthropic/claude-3-7-sonnet-20250219
+hugging_face_id: ''
+name: 'Anthropic: Claude 3.7 Sonnet'
+type: chat
+created: 1740422110
+description: "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and extended, step-by-step processing for complex tasks. The model demonstrates notable improvements in coding, particularly in front-end development and full-stack updates, and excels in agentic workflows, where it can autonomously navigate multi-step processes. \n\nClaude 3.7 Sonnet maintains performance parity with its predecessor in standard mode while offering an extended reasoning mode for enhanced accuracy in math, coding, and instruction-following tasks.\n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-3-7-sonnet)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-opus-4.yaml

@@ -0,0 +1,39 @@
+id: anthropic/claude-opus-4
+canonical_slug: anthropic/claude-4-opus-20250522
+hugging_face_id: ''
+name: 'Anthropic: Claude Opus 4'
+type: chat
+created: 1747931245
+description: "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation. \n\nRead more at the [blog post here](https://www.anthropic.com/news/claude-4)"
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - image
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000015'
+  completion: '0.000075'
+  input_cache_read: '0.0000015'
+  input_cache_write: '0.00001875'
+  request: '0'
+  image: '0.024'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+model_provider: anthropic

resources/model-catalogs/anthropic/claude-sonnet-4.yaml

@@ -0,0 +1,42 @@
+id: anthropic/claude-sonnet-4
+canonical_slug: anthropic/claude-4-sonnet-20250522
+hugging_face_id: ''
+name: 'Anthropic: Claude Sonnet 4'
+type: chat
+created: 1747930371
+description: |-
+  Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%), Sonnet 4 balances capability and computational efficiency, making it suitable for a broad range of applications from routine coding tasks to complex software development projects. Key enhancements include improved autonomous codebase navigation, reduced error rates in agent-driven workflows, and increased reliability in following intricate instructions. Sonnet 4 is optimized for practical everyday use, providing advanced reasoning capabilities while maintaining efficiency and responsiveness in diverse internal and external scenarios.
+
+  Read more at the [blog post here](https://www.anthropic.com/news/claude-4)
+context_length: 200000
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - image
+    - text
+  output_modalities:
+    - text
+  tokenizer: Claude
+  instruct_type: null
+pricing:
+  prompt: '0.000003'
+  completion: '0.000015'
+  input_cache_read: '0.0000003'
+  input_cache_write: '0.00000375'
+  request: '0'
+  image: '0.0048'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+model_provider: anthropic

resources/model-catalogs/arcee-ai/arcee-blitz.yaml

@@ -0,0 +1,40 @@
+id: arcee-ai/arcee-blitz
+canonical_slug: arcee-ai/arcee-blitz
+hugging_face_id: arcee-ai/arcee-blitz
+name: 'Arcee AI: Arcee Blitz'
+type: chat
+created: 1746470100
+description: 'Arcee Blitz is a 24 B‑parameter dense model distilled from DeepSeek and built on Mistral architecture for "everyday" chat. The distillation‑plus‑refinement pipeline trims compute while keeping DeepSeek‑style reasoning, so Blitz punches above its weight on MMLU, GSM‑8K and BBH compared with other mid‑size open models. With a default 128 k context window and competitive throughput, it serves as a cost‑efficient workhorse for summarization, brainstorming and light code help. Internally, Arcee uses Blitz as the default writer in Conductor pipelines when the heavier Virtuoso line is not required. Users therefore get near‑70 B quality at ~⅓ the latency and price. '
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000045'
+  completion: '0.00000075'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/caller-large.yaml

@@ -0,0 +1,42 @@
+id: arcee-ai/caller-large
+canonical_slug: arcee-ai/caller-large
+hugging_face_id: ''
+name: 'Arcee AI: Caller Large'
+type: chat
+created: 1746487869
+description: 'Caller Large is Arcee''s specialist "function‑calling" SLM built to orchestrate external tools and APIs. Instead of maximizing next‑token accuracy, training focuses on structured JSON outputs, parameter extraction and multi‑step tool chains, making Caller a natural choice for retrieval‑augmented generation, robotic process automation or data‑pull chatbots. It incorporates a routing head that decides when (and how) to invoke a tool versus answering directly, reducing hallucinated calls. The model is already the backbone of Arcee Conductor''s auto‑tool mode, where it parses user intent, emits clean function signatures and hands control back once the tool response is ready. Developers thus gain an OpenAI‑style function‑calling UX without handing requests to a frontier‑scale model. '
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000055'
+  completion: '0.00000085'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/coder-large.yaml

@@ -0,0 +1,40 @@
+id: arcee-ai/coder-large
+canonical_slug: arcee-ai/coder-large
+hugging_face_id: ''
+name: 'Arcee AI: Coder Large'
+type: chat
+created: 1746478663
+description: 'Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file refactoring or long diff review in a single call, and understands 30‑plus programming languages with special attention to TypeScript, Go and Terraform. Internal benchmarks show 5–8 pt gains over CodeLlama‑34 B‑Python on HumanEval and competitive BugFix scores thanks to a reinforcement pass that rewards compilable output. The model emits structured explanations alongside code blocks by default, making it suitable for educational tooling as well as production copilot scenarios. Cost‑wise, Together AI prices it well below proprietary incumbents, so teams can scale interactive coding without runaway spend. '
+context_length: 32768
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.0000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/maestro-reasoning.yaml

@@ -0,0 +1,40 @@
+id: arcee-ai/maestro-reasoning
+canonical_slug: arcee-ai/maestro-reasoning
+hugging_face_id: ''
+name: 'Arcee AI: Maestro Reasoning'
+type: chat
+created: 1746481269
+description: 'Maestro Reasoning is Arcee''s flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B preview, the production 32 B release widens the context window to 128 k tokens and doubles pass‑rate on MATH and GSM‑8K, while also lifting code completion accuracy. Its instruction style encourages structured "thought → answer" traces that can be parsed or hidden according to user preference. That transparency pairs well with audit‑focused industries like finance or healthcare where seeing the reasoning path matters. In Arcee Conductor, Maestro is automatically selected for complex, multi‑constraint queries that smaller SLMs bounce. '
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000009'
+  completion: '0.0000033'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/spotlight.yaml

@@ -0,0 +1,41 @@
+id: arcee-ai/spotlight
+canonical_slug: arcee-ai/spotlight
+hugging_face_id: ''
+name: 'Arcee AI: Spotlight'
+type: chat
+created: 1746481552
+description: 'Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal conversations that combine lengthy documents with one or more images. Training emphasized fast inference on consumer GPUs while retaining strong captioning, visual‐question‑answering, and diagram‑analysis accuracy. As a result, Spotlight slots neatly into agent workflows where screenshots, charts or UI mock‑ups need to be interpreted on the fly. Early benchmarks show it matching or out‑scoring larger VLMs such as LLaVA‑1.6 13 B on popular VQA and POPE alignment tests. '
+context_length: 131072
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - image
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000018'
+  completion: '0.00000018'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/virtuoso-large.yaml

@@ -0,0 +1,42 @@
+id: arcee-ai/virtuoso-large
+canonical_slug: arcee-ai/virtuoso-large
+hugging_face_id: ''
+name: 'Arcee AI: Virtuoso Large'
+type: chat
+created: 1746478885
+description: Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k context inherited from Qwen 2.5, letting it ingest books, codebases or financial filings wholesale. Training blended DeepSeek R1 distillation, multi‑epoch supervised fine‑tuning and a final DPO/RLHF alignment stage, yielding strong performance on BIG‑Bench‑Hard, GSM‑8K and long‑context Needle‑In‑Haystack tests. Enterprises use Virtuoso‑Large as the "fallback" brain in Conductor pipelines when other SLMs flag low confidence. Despite its size, aggressive KV‑cache optimizations keep first‑token latency in the low‑second range on 8× H100 nodes, making it a practical production‑grade powerhouse.
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.00000075'
+  completion: '0.0000012'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/arcee-ai/virtuoso-medium-v2.yaml

@@ -0,0 +1,42 @@
+id: arcee-ai/virtuoso-medium-v2
+canonical_slug: arcee-ai/virtuoso-medium-v2
+hugging_face_id: arcee-ai/Virtuoso-Medium-v2
+name: 'Arcee AI: Virtuoso Medium V2'
+type: chat
+created: 1746478434
+description: 'Virtuoso‑Medium‑v2 is a 32 B model distilled from DeepSeek‑v3 logits and merged back onto a Qwen 2.5 backbone, yielding a sharper, more factual successor to the original Virtuoso Medium. The team harvested ~1.1 B logit tokens and applied "fusion‑merging" plus DPO alignment, which pushed scores past Arcee‑Nova 2024 and many 40 B‑plus peers on MMLU‑Pro, MATH and HumanEval. With a 128 k context and aggressive quantization options (from BF16 down to 4‑bit GGUF), it balances capability with deployability on single‑GPU nodes. Typical use cases include enterprise chat assistants, technical writing aids and medium‑complexity code drafting where Virtuoso‑Large would be overkill. '
+context_length: 131072
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Other
+  instruct_type: null
+pricing:
+  prompt: '0.0000005'
+  completion: '0.0000008'
+  input_cache_read: ''
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  unit: 1
+  currency: USD
+supported_parameters:
+  - tools
+  - tool_choice
+  - max_tokens
+  - temperature
+  - top_p
+  - stop
+  - frequency_penalty
+  - presence_penalty
+  - top_k
+  - repetition_penalty
+  - logit_bias
+  - min_p
+  - response_format
+model_provider: arcee-ai

resources/model-catalogs/bytedance/doubao-embedding-large-text-240715.yaml

@@ -0,0 +1,24 @@
+id: bytedance/doubao-embedding-text-240715
+canonical_slug: bytedance/doubao-embedding-text-240715
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Text (240715)'
+description: |-
+  Doubao Embedding Large 是字节跳动语义向量化模型的最新升级版，模型以豆包语言模型为基座，具备强大的语言理解能力；主要面向向量检索的使用场景，支持中、英双语。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-large-text-240915.yaml

@@ -0,0 +1,25 @@
+id: bytedance/doubao-embedding-large-text-240915
+canonical_slug: bytedance/doubao-embedding-large-text-240915
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Large Text (240915)'
+description: |-
+  Doubao Embedding Large 是字节跳动语义向量化模型的最新升级版，模型以豆包语言模型为基座，具备强大的语言理解能力；主要面向向量检索的使用场景，支持中、英双语。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+  - 4096
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-text-240515.yaml

@@ -0,0 +1,24 @@
+id: bytedance/doubao-embedding-text-240715
+canonical_slug: bytedance/doubao-embedding-text-240715
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding'
+description: |-
+  由字节跳动研发的语义向量化模型，主要面向向量检索的使用场景，支持中、英双语，最长 4K 上下文长度。向量维度 2048 维，支持 512、1024 降维使用。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.5'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-text-240715.yaml

@@ -0,0 +1,25 @@
+id: bytedance/doubao-embedding-text-240715
+canonical_slug: bytedance/doubao-embedding-text-240715
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding'
+description: |-
+  由字节跳动研发的语义向量化模型，主要面向向量检索的使用场景，支持中、英双语，最长 4K 上下文长度。向量维度 2048 维，支持 512、1024 降维使用。
+context_length: 4000
+dimensions:
+  - 512
+  - 1024
+  - 2048
+  - 2560
+architecture:
+  modality: text->text
+  input_modalities:
+    - text
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.5'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-vision-241215.yaml

@@ -0,0 +1,24 @@
+id: bytedance/doubao-embedding-vision-241215
+canonical_slug: bytedance/doubao-embedding-vision-241215
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Vision'
+description: |-
+  Doubao-embedding-vision，全新升级图文多模态向量化模型，主要面向图文多模向量检索的使用场景，支持图片输入及中、英双语文本输入，最长 8K 上下文长度。
+context_length: 8000
+dimensions:
+  - 3072
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  prompt_image: '1.8'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-embedding-vision-250328.yaml

@@ -0,0 +1,25 @@
+id: bytedance/doubao-embedding-vision-250328
+canonical_slug: bytedance/doubao-embedding-vision-250328
+type: embedding
+hugging_face_id: null
+name: 'ByteDance: Doubao Embedding Vision'
+description: |-
+  Doubao-embedding-vision，全新升级图文多模态向量化模型，主要面向图文多模向量检索的使用场景，支持图片输入及中、英双语文本输入，最长 8K 上下文长度。
+context_length: 8000
+dimensions:
+  - 1024
+  - 2048
+architecture:
+  modality: text+image->text
+  input_modalities:
+    - text
+    - image
+  output_modalities:
+    - text
+  tokenizer: Doubao
+pricing:
+  prompt: '0.7'
+  prompt_image: '1.8'
+  unit: 1000000
+  currency: CNY
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-seed-1.6-flash.yaml

@@ -0,0 +1,41 @@
+id: bytedance/doubao-seed-1.6-flash
+canonical_slug: bytedance/doubao-seed-1.6-flash
+type: chat
+hugging_face_id: ''
+name: 'ByteDance: Doubao Seed 1.6 Flash'
+created: 1738402289
+description: 有极致推理速度的多模态深度思考模型；同时支持文本和视觉理解。文本理解能力超过上一代 Lite 系列模型，视觉理解比肩友商 Pro 系列模型。
+context_length: 256000
+architecture:
+  modality: text+image+vedio->text
+  input_modalities:
+    - text
+    - image
+    - video
+  output_modalities:
+    - text
+  tokenizer: Doubao
+  instruct_type: null
+pricing:
+  prompt: '0.15'
+  completion: '1.5'
+  input_cache_read: '0.03'
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  currency: CNY
+  unit: 1000000
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+  - structured_outputs
+model_provider: bytedance

resources/model-catalogs/bytedance/doubao-seed-1.6-thinking.yaml

@@ -0,0 +1,41 @@
+id: bytedance/doubao-seed-1.6-thinking
+canonical_slug: bytedance/doubao-seed-1.6-thinking
+type: chat
+hugging_face_id: ''
+name: 'ByteDance: Doubao Seed 1.6 Thinking'
+created: 1738402289
+description: 在思考能力上进行了大幅强化， 对比 doubao 1.5 代深度理解模型，在编程、数学、逻辑推理等基础能力上进一步提升， 支持视觉理解。
+context_length: 256000
+architecture:
+  modality: text+image+vedio->text
+  input_modalities:
+    - text
+    - image
+    - video
+  output_modalities:
+    - text
+  tokenizer: Doubao
+  instruct_type: null
+pricing:
+  prompt: '0.8'
+  completion: '8.0'
+  input_cache_read: '0.16'
+  input_cache_write: ''
+  request: '0'
+  image: '0'
+  web_search: '0'
+  internal_reasoning: '0'
+  currency: CNY
+  unit: 1000000
+supported_parameters:
+  - max_tokens
+  - temperature
+  - stop
+  - reasoning
+  - include_reasoning
+  - tools
+  - tool_choice
+  - top_p
+  - top_k
+  - structured_outputs
+model_provider: bytedance