9afc6989af
* feat: Implement Redux-based message management with enhanced state handling - Add new Redux slice for managing messages with advanced state control - Introduce topic-specific message queues using p-queue for request management - Refactor message sending, loading, and updating logic - Improve error handling and state synchronization with database - Add selectors for efficient message retrieval and state access * feat: Implement streaming message handling in Redux store - Add stream message support in messages slice - Create MessageStream component for rendering streaming messages - Update Inputbar and Suggestions components to use new Redux message sending logic - Refactor message sending flow to use stream message management - Improve error handling and message state management * feat:添加StreamMessage，优化数据流展示，减少大面积rerender * refactor: Simplify messages state management and initialization - Refactor messages slice to use flat message array instead of separate user/assistant messages - Add initializeMessagesState thunk to load messages from database on app startup - Update message-related reducers to work with flat message array - Modify MessageStream and related components to use new state structure - Improve type safety and reduce complexity in messages state management * ✨ feat: add Model Context Protocol (MCP) support (#2809) * ✨ feat: add Model Context Protocol (MCP) server configuration (main) - Added `@modelcontextprotocol/sdk` dependency for MCP integration. - Introduced MCP server configuration UI in settings with add, edit, delete, and activation functionalities. - Created `useMCPServers` hook to manage MCP server state and actions. - Added i18n support for MCP settings with translation keys. - Integrated MCP settings into the application's settings navigation and routing. - Implemented Redux state management for MCP servers. - Updated `yarn.lock` with new dependencies and their resolutions. * 🌟 feat: implement mcp service and integrate with ipc handlers - Added `MCPService` class to manage Model Context Protocol servers. - Implemented various handlers in `ipc.ts` for managing MCP servers including listing, adding, updating, deleting, and activating/deactivating servers. - Integrated MCP related types into existing type declarations for consistency across the application. - Updated `preload` to expose new MCP related APIs to the renderer process. - Enhanced `MCPSettings` component to interact directly with the new MCP service for adding, updating, deleting servers and setting their active states. - Introduced selectors in the MCP Redux slice for fetching active and all servers from the store. - Moved MCP types to a centralized location in `@renderer/types` for reuse across different parts of the application. * feat: enhance MCPService initialization to prevent recursive calls and improve error handling * feat: enhance MCP integration by adding MCPTool type and updating related methods * feat: implement streaming support for tool calls in OpenAIProvider and enhance message processing * refactor: Improve message handling and type safety in message components - Update Message, MessageGroup, MessageStream, and MessageMenubar to require Topic prop - Modify message sending and resending logic in MessageMenubar - Remove commented-out code and simplify message state management - Enhance type safety by explicitly defining prop types * fix: finish_reason undefined * refactor: Streamline message resending and state management - Introduce `resendMessage` thunk for more robust message resending logic - Update `sendMessage` to support resending existing messages - Remove deprecated `onEditMessage` callback from MessageMenubar - Simplify message state updates using Redux actions - Improve type safety and reduce complexity in message handling * refactor: Optimize message resending and event handling - Remove deprecated `APPEND_MESSAGE` event and related callbacks - Update `resendMessage` thunk to support mentioning new models - Modify message state synchronization in database - Simplify dependency arrays and remove unused event listeners - Add migration step for initializing messages state * refactor: Enhance message translation and suggestions handling - Update MessageMenubar to use stream message actions for translation - Modify Suggestions component to optimize suggestion fetching - Remove deprecated event listeners and simplify component logic - Memoize MessageMenubar and Suggestions components for performance - Trigger AI auto-rename on message completion in messages slice * refactor: Optimize message streaming with throttled updates - Introduce throttled message update mechanism using lodash - Improve performance by limiting Redux state updates during streaming - Create a separate handler for response message updates - Enhance message synchronization with database - Prevent unnecessary re-renders and reduce computational overhead * fix: Remove unnecessary await in message dispatch Removes the `await` keyword from the message dispatch in Inputbar, which was causing an unnecessary async operation. Also adds a missing closing brace in the migration configuration file. * fix: Update Redux persist configuration for messages slice Modify store configuration to exclude 'messages' slice from persistence and remove unnecessary migration step for message state initialization * feat: Enhance message streaming and multi-model support - Refactor Redux messages slice to support multiple stream messages per topic - Update MessageStream and messages slice to handle message streaming with message-specific IDs - Implement support for multi-model message generation - Modify queue concurrency to improve parallel message processing - Update message selection and streaming logic to be more flexible and robust * feat: Implement file upload handling in message sending - Add FileManager service integration for file uploads in Inputbar - Modify sendMessage action to use uploaded file references - Update messages slice to conditionally dispatch messages during resend * ✨ feat(MCP): add support for enabling/disabling MCPServers per message (#2989) * ✨ feat: add MCP servers in chat input - Introduce MCPToolsButton component for managing MCP servers - Add new icon for MCP server tools in iconfont.css - Update Inputbar to include MCP tools functionality - Add toggle functionality for enabling/disabling MCP servers - Implement styled dropdown menu for server selection - Add necessary type imports and useState for MCP server management * ✨ feat: add support for enabling/disabling MCPServers per message (main) - Added `enabledMCPs` property to the `Message` type to track enabled MCPServers. - Modified `MCPToolsButton` to enable all active MCPServers by default using a new `enableAll` state. - Introduced `filterMCPTools` utility to filter tools based on enabled MCPServers. - Updated `AnthropicProvider`, `GeminiProvider`, and `OpenAIProvider` to filter tools using `filterMCPTools`. - Enhanced `Inputbar` to include `enabledMCPs` in the message payload when set. * ✨ feat(MCP): add enabledMCPs parameter to sendMessage action - Update sendMessage action type to include optional enabledMCPs parameter - Import MCPServer type for type safety - Modify action signature to support passing enabled MCP servers per message --------- Co-authored-by: lizhixuan <zhixuan.li@banosuperapp.com> Co-authored-by: lizhixuan <zhixuanli219643@sohu-inc.com> Co-authored-by: LiuVaayne <10231735+vaayne@users.noreply.github.com> Co-authored-by: kangfenmao <kangfenmao@qq.com>
🍒 Cherry Studio
Cherry Studio is a desktop client that supports for multiple LLM providers, available on Windows, Mac and Linux.
👏 Join Telegram Group｜Discord | QQ Group(1025067911)
❤️ Like Cherry Studio? Give it a star 🌟 or Sponsor to support the development!
🌠 Screenshot
🌟 Key Features
-
Diverse LLM Provider Support:
- ☁️ Major LLM Cloud Services: OpenAI, Gemini, Anthropic, and more
- 🔗 AI Web Service Integration: Claude, Peplexity, Poe, and others
- 💻 Local Model Support with Ollama, LM Studio
-
AI Assistants & Conversations:
- 📚 300+ Pre-configured AI Assistants
- 🤖 Custom Assistant Creation
- 💬 Multi-model Simultaneous Conversations
-
Document & Data Processing:
- 📄 Support for Text, Images, Office, PDF, and more
- ☁️ WebDAV File Management and Backup
- 📊 Mermaid Chart Visualization
- 💻 Code Syntax Highlighting
-
Practical Tools Integration:
- 🔍 Global Search Functionality
- 📝 Topic Management System
- 🔤 AI-powered Translation
- 🎯 Drag-and-drop Sorting
- 🔌 Mini Program Support
-
Enhanced User Experience:
- 🖥️ Cross-platform Support for Windows, Mac, and Linux
- 📦 Ready to Use, No Environment Setup Required
- 🎨 Light/Dark Themes and Transparent Window
- 📝 Complete Markdown Rendering
- 🤲 Easy Content Sharing
📝 TODO
- Quick popup (read clipboard, quick question, explain, translate, summarize)
- Comparison of multi-model answers
- Support login using SSO provided by service providers
- All models support networking
- Launch of the first official version
- Bug fixes and improvements (In progress...)
- Plugin functionality (JavaScript)
- Browser extension (highlight text to translate, summarize, add to knowledge base)
- iOS & Android client
- AI notes
- Voice input and output (AI call)
- Data backup supports custom backup content
🖥️ Develop
IDE Setup
Project Setup
Install
yarn
Development
yarn dev
Build
# For windows
$ yarn build:win
# For macOS
$ yarn build:mac
# For Linux
$ yarn build:linux
🤝 Contributing
We welcome contributions to Cherry Studio! Here are some ways you can contribute:
- Contribute Code: Develop new features or optimize existing code.
- Fix Bugs: Submit fixes for any bugs you find.
- Maintain Issues: Help manage GitHub issues.
- Product Design: Participate in design discussions.
- Write Documentation: Improve user manuals and guides.
- Community Engagement: Join discussions and help users.
- Promote Usage: Spread the word about Cherry Studio.
Getting Started
- Fork the Repository: Fork and clone it to your local machine.
- Create a Branch: For your changes.
- Submit Changes: Commit and push your changes.
- Open a Pull Request: Describe your changes and reasons.
For more detailed guidelines, please refer to our Contributing Guide.
Thank you for your support and contributions!
Related Projects
-
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:Blocks specific sites from appearing in Google search results
🚀 Contributors
🌐 Community
📣 Product Hunt
