- Add 'qwen' to tool calling models list
- Refactor MCP server hooks to use window.api methods
- Add 'more' translation key across localization files
- Improve MCP settings modal with window.api and window.modal methods
- Add ProxyManager service to handle system, custom, and no proxy configurations
- Integrate proxy support for Gemini, Knowledge, and WebDav services
- Add fetch-socks and undici for advanced proxy handling
- Enhance proxy configuration with environment variable and session management
* Enhance update error logging and fix duplicate type import
- Improve error logging in AppUpdater with more detailed error information and timestamps
- Remove duplicate MCPServer type import in Inputbar component
* fix: ensure directory existence and optimize file operations
Update SearchMessage and TopicMessages components to pass topic context to MessageItem, ensuring proper rendering of messages with their associated topics
* feat(message): add a compact style for the model list in message groups
* refactor: use button as action rather than state
---------
Co-authored-by: 亢奋猫 <kangfenmao@qq.com>
Use the new getTempDir utility function from file.ts to generate temporary file paths, maintaining consistency with recent file path utility refactoring
* Enhance update error logging and fix duplicate type import
- Improve error logging in AppUpdater with more detailed error information and timestamps
- Remove duplicate MCPServer type import in Inputbar component
* feat(loader): optimize EpubLoader memory usage with file streams
Replace in-memory arrays with file streams for EPUB processing to reduce
memory consumption when handling large e-books. Use temporary files for
chapter content, add completion logs, and ensure proper cleanup.
This prevents memory overflow issues with large EPUB files (>5MB).
Move hardcoded file path generation logic to dedicated utility functions in file.ts, improving code modularity and reducing duplication across services and IPC handlers
- Add single key checking functionality
- Implement ability to remove individual API keys
- Improve UI with remove and check buttons for each key
- Disable actions during checking to prevent conflicts
- Add styled remove icon for key deletion
* ✨ 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
* fix: finish_reason undefined
* fix: Improve translation error handling in MessageMenubar
---------
Co-authored-by: LiuVaayne <10231735+vaayne@users.noreply.github.com>
Co-authored-by: kangfenmao <kangfenmao@qq.com>
* feat: Add health check to check all the models at one time
* fix: add model avatars to the health-check list
* style: Use segmented instead of switch
* fix: remove redundant timing reports
* refactor: Extract small functions
* refactor: use more hooks to make the main component clearer
* fix: mask API keys with asterisks
* refactor: split health check popup and model list
- rename ModelHealthCheckPopup to HealthCheckPopup
- add HealthCheckModelList
- add maskApiKey to utils
* refactor: compute latency in checkApi
* fix: remove unused i18n keys
* refactor: use checkModel instead of checkApi for better semantics
* fix: update comments
* refactor: extract health checking functions to services
* refactor: extract model list
* refactor: render statuses on the existing model list
* fix: reset button style on completion
* fix: disable model card while checking
- remove unused i18n keys
- better window message
* refactor: show provider name in messages
* refactor: change default values
* refactor: fully migrate model list from ProviderSetting to ModelList
- Replace default Select components with StyledSelect for improved visual design
- Add explicit type casting for various select onChange handlers
- Improve type safety for message style, multi-model style, code style, and other settings
- Introduce StyledSelect with custom styling for consistent UI appearance
- Introduce messagesRef to track messages without causing re-renders
- Simplify event listener management with more concise useEffect hooks
- Improve auto-rename topic logic with current messages reference
- Remove commented-out code and unused event listeners
- Enhance type safety and reduce dependency complexity
- Introduce ToolsCallingIcon component for tool calling models
- Add isToolCallingModel function in models config
- Update ModelTags to support showing tool calling icon
- Add tooltips to model icons for better UX
- Update Chinese localization with tool calling translation
- Modify Inputbar and SelectModelButton to accommodate new icon
* fix: correctly concatenate model id
* perf: delay model sorting
* feat: sticky provider name during model selection
* fix: model selector group title animation
* fix: add back opacity
---------
Co-authored-by: 亢奋猫 <kangfenmao@qq.com>
- Improve error logging in AppUpdater with more detailed error information and timestamps
- Remove duplicate MCPServer type import in Inputbar component
* 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>
- Add dynamic selected keys for the model selection menu
- Ensure correct model is highlighted when pre-selected or navigated via keyboard
- Simplify selection logic in SelectModelPopup component
- Remove global style components from MentionModelsButton and MCPToolsButton
- Move dropdown styles to a centralized SCSS file
- Refactor components to use styled-components for localized styling
- Improve code organization and reduce redundant styling
- Adjust table column widths in MCPSettings for better layout
- Simplify dropdown rendering by removing unnecessary fragments
- Add useCallback for togglePin and handleModelSelect to prevent unnecessary re-renders
- Refactor dropdown menu styling with more specific CSS scoping
- Simplify dropdown open/close logic
- Improve performance by memoizing function dependencies
- Adjust dropdown overlay styling and animation
* ✨ 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.
- Add dynamic group management button that changes based on group's current state
- Simplify group add/remove logic with a single button
- Enhance visual feedback for group-level model management
* feat: a button a add a whole group of models
* feat: search as typing in EditModelsPopup
* feat: add a button to remove a whole group of models
* feat: add remove button for model group in the model list
- Add database version 5 with schema updates
- Create `upgradeToV5` function to migrate Tavily web search metadata to new format
- Update types to support new web search metadata structure
- Minor code cleanup and formatting improvements
- Remove `enabled` flag from WebSearchProvider type
- Add `hasObjectKey` utility function to check optional properties
- Update WebSearchService to check web search availability based on API key/host
- Modify WebSearchSettings and WebSearchProviderSetting components to support API key/host validation
- Add Searxng provider in migration script
- Simplify web search provider configuration and validation logic
* ✨ 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
* feat: Enhance MCPServer and MCPTool interfaces with optional properties and unique IDs
* fix(mcp): Refactor SSE transport initialization to use URL object
* fix(OpenAIProvider): correct inputSchema properties reference in tool parameters
* feat(MCPSettings): enhance server settings UI with new fields and improved layout
* feat(MCPSettings): add multilingual support for MCP server settings
* fix: remove unnecessary console log statements
* ✨ 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
- Modify AppUpdater to separate update dialog logic
- Add new IPC handler for manually showing update dialog
- Update renderer hooks and store to track downloaded update state
- Switch import for UpdateInfo from electron-updater to builder-util-runtime
* feat(export): Enhance markdown-to-docx export with table support
Add comprehensive table rendering capabilities to the ExportService, including:
- Support for table headers and body rows
- Configurable cell styling and alignment
- Handling of inline text formatting within table cells
* feat(export): Add hyperlink support in markdown-to-docx export
Enhance ExportService to handle hyperlinks during document export:
- Implement link detection in inline tokens
- Create ExternalHyperlink with proper styling
- Preserve link text and URL in exported document
- Add new `filterUserRoleStartMessages` function in MessagesService
- Update Anthropic, Gemini, and OpenAI providers to use new message filtering
- Refactor message handling to ensure user messages start the conversation
- Remove redundant message filtering logic from individual providers
- Add vision model check before image upload in Inputbar
- Implement flexible message start forcing for specific models
- Improve provider-level message routing logic
* feat: add resize handle to input textarea with drag interaction
* handle auto size inputbar
* optimize auto resize function and add i18n
* fix: expand button bug in inputbar and rebase to latest main
* rebase to main
- Fixed typo in Tencent Cloud TI provider key from 'tentent-cloud-ti' to 'tencent-cloud-ti'
- Enhanced ProviderSettings search input with search icon and custom styling
- Adjusted button border radius for consistent UI design
- Implemented `useKnowledgeFiles` hook for managing knowledge base files
- Added localization support for knowledge base file management in multiple languages
- Created UI option to remove all knowledge base files in DataSettings
- Updated file size formatting utility function
- Modified ContentView and FilesPage to use file size correctly
- Implemented detailed backup progress tracking in BackupManager
- Added new BackupPopup component for backup process visualization
- Enhanced backup process with file copy progress and stage tracking
- Updated localization files with backup progress translations
- Integrated backup progress reporting to renderer process
- Refactored reasoning effort handling for Claude models
- Added type definition for ReasoningEffort
- Simplified budget token calculation
- Improved type safety and readability of the method
- Refactored getReasoningEffort method to handle reasoning configuration more robustly
- Added type definitions for reasoning effort and configuration
- Simplified logic for calculating budget tokens
- Improved type safety and readability of the method
* refactor: Improve Ellipsis component and usage
- Modify Ellipsis component to use children instead of text prop
- Add support for multi-line and single-line ellipsis with styled-components
- Update KnowledgeContent to use new Ellipsis component structure
- Enhance ClickableSpan styling for better text truncation
* fix: Improve text wrapping in Ellipsis component
Add overflow-wrap: break-word to ensure long words are properly truncated in multi-line ellipsis
* refactor: Improve link and tooltip rendering in KnowledgeContent
- Wrap links with ClickableSpan for better interaction and styling
- Adjust Tooltip and Ellipsis placement for improved readability
- Remove unnecessary inline styling for links in ItemInfo
---------
Co-authored-by: lizhixuan <zhixuan.li@banosuperapp.com>
- Created detailed technical documentation explaining the KnowledgeService's task queue and workload management
- Added JSDoc comment to KnowledgeService.ts to provide high-level overview
- Documented key aspects of concurrent task processing, including workload evaluation, task state management, and resource optimization strategies
* feat: Improve file upload for the knowledge base
* feat: Improve file upload for the knowledge base
* feat: Improve file upload for the knowledge base
---------
Co-authored-by: 亢奋猫 <kangfenmao@qq.com>
- Added Zhihu (知乎直答) mini app logo
- Updated minapps configuration to include Zhihu mini app
- Modified store migration to enable Zhihu mini app by default
- Added Cici mini app logo in WebP format
- Updated mini apps grid to display 8 columns instead of 6
- Updated store migration to include Cici in enabled mini apps
- Updated Cici app logo import path
- Move StyleSheetManager logic from App.tsx to a new dedicated context component
- Simplify App.tsx by importing the new StyleSheetManager
- Preserve existing prop validation and filtering logic
- Add Babel plugin for styled-components with performance and naming optimizations
- Integrate @emotion/is-prop-valid for improved prop filtering in StyleSheetManager
- Update Antd Input components to use variant="borderless" instead of deprecated bordered prop
- Add new dependencies for styled-components configuration
- Add hunyuan-turbos-latest
- Add hunyuan-embedding
- Fix the issue of the embedding model displaying the internet icon (when the provider fully supports web search)
- Add min-width and min-height to ModelAvatar to ensure consistent sizing
- Separate AssistantName into a new styled component for better text overflow handling
- Refactor AssistantItem to improve text display and icon alignment
- Implement alphabetical sorting for model groups
- Use lodash's sortBy and toPairs to order model groups
- Modify rendering to use sorted model groups
- Create new ModelEditContent component in ProviderSettings
- Separate model editing logic from ProviderSetting
- Adjust styling for AssistantItem and TopicsTab list items
- Refine Segmented component styling with transparent background
- Improve modal layout and interaction for model type configuration
- Implement new setting to show/hide model icons in assistant list
- Add localization support for new assistant settings
- Update UI to conditionally render model avatar in AssistantItem
- Modify settings store to include showAssistantIcon state
- Enhance display settings with new toggle switch for assistant icon
- Remove custom Segmented styling from AntdProvider
- Update HomeTabs Segmented component with refined styles
- Consolidate Segmented styling in a single location
- Improve visual consistency with rounded corners and transparent background
- Update window vibrancy to 'sidebar' for better visual effect
- Refine input bar styling with softer background and rounded corners
- Adjust toolbar button sizes and styling
- Modify topic position selection to use Segmented component
- Tweak light theme background opacity
* feat: add "More Settings" option in multiple languages and enhance model type selection UI
* feat: add "More Settings" option with warnings and confirmation prompts in multiple languages
* fix: improve modal close handling and reset model type visibility
Restrictions are introduced in earlier beta versions of MacOS Sequoia.
However, in the public release, Apple revoke this restrictions.
Alt+[Char] shortcut has no restrictions now.
- Add location check to prevent navigating to settings when already on settings page
- Enable hotkey on content editable and form elements
- Use useLocation to track current route
* feat: Implement robust favicon loading with fallback mechanisms
* refactor: Improve favicon loading state and use Promise Method
* refactor: Extract FallbackFavicon into a separate component
* feat: Add Splitbee favicon service to fallback favicon URLs
* feat: Add search button to the knowledge base, and adjusted the display for drag-and-drop uploads
* feat: Add search button to the knowledge base, and adjusted the display for drag-and-drop uploads
- Standardize spacing and capitalization in Chinese (Simplified and Traditional) locales
- Enhance readability of error and configuration messages
- Consistent formatting for API keys, database IDs, and URLs
- Update Tavily description across locales to emphasize AI agent capabilities
- Add blacklist functionality for web search results
- Introduce configurable maximum search results
- Improve localization for web search settings in multiple languages
This commit involves minor reorganization and cleanup of translation files across multiple languages (en-us, ja-jp, ru-ru, zh-cn, zh-tw). Changes include:
- Reordering of some translation keys
- Removing duplicate entries
- Slight restructuring of nested translation objects
- Minor formatting adjustments
This commit removes unnecessary console.log statements and makes minor code cleanup in several files:
- PlantUML component
- WebSearchSettings
- WebSearchService
- Store settings
Additionally, it updates the store migration to handle LM Studio provider addition and reverts the store version
- Added `gemini-2.0` to `visionAllowedModels`.
- Introduced new Gemini models in `SYSTEM_MODELS`:
- `gemini-1.5-flash-8b`
- `gemini-2.0-flash`
- Updated Yi model configurations:
- Renamed `yi-lightning` to "Yi Lightning".
- Deprecated `yi-medium`, `yi-large`, and `yi-vision` (replaced by `yi-lightning` per documentation).
- Added `yi-vision-v2` as a new version of Yi Vision.
- Added new image asset `codestral.png` for Codestral model.
- Updated `embedings.ts` to include the `mistral-embed` embedding model with `max_context: 8000`.
- Updated `models.ts` to:
- Add support for Codestral model with `codestral-latest` ID.
- Introduce new Mistral models, including:
- `ministral-3b-latest`
- `ministral-8b-latest`
- `mistral-large-latest`
- `mistral-small-latest`
- `mistral-embed`
- Organize models into appropriate groups (e.g., "Mistral Chat", "Mistral Code").
- Adjusted `getModelLogo` function to include Codestral and Ministral logos.
This commit involves several improvements to localization files across different languages:
- Reordered and cleaned up translation keys
- Removed redundant entries
- Ensured consistent ordering of keys
- Added missing translations for various features
- Normalized whitespace and formatting
- i18n Updates:
- Refactored WebDAV-related translations into nested JSON structures for better organization.
- Added support for pluralization in time intervals (minutes and hours) across all locales (en-us, ja-jp, ru-ru, zh-cn, zh-tw).
- UI Enhancements:
- Updated `DataSettings` and `WebDavSettings` components to use the new i18n keys for time intervals.
- Improved the `Select` dropdown for sync intervals with dynamic pluralization based on locale.
- Adjusted input field widths for better alignment and consistency.
- Code Cleanup:
- Removed redundant comments and unused code in `WebDavSettings.tsx`.
- Simplified button and input styling for a cleaner layout.
* feat: agent can select multiple knowledge bases
* feat: basic search multiple knowledge base
* fix bug: knowledge base is delete, assistants and agents sync delete
* fix bug: assistant and knowledge base button sync
* feat: allow to search multiple knowledge base
* chore: finish rebase to upstream/main
- Update llm.ts to include LM Studio and ModelScope in initial system providers
- Modify migrate.ts to add migration logic for adding these new providers
- Ensure providers are added only if they don't already exist in the configuration
PR #1253 fixed reasoning time calculation for APIs that return reasoning
content in `delta.content`, but introduced a regression for those
returning it in `delta.reasoning_content`. This commit fixes the
regression.
Fixes#1593
- Remove image loader from dependencies
- Update file loading to skip image, video, and audio files
- Add logging for knowledge base file processing
- Modify common file extensions list
- Add type ignore for LocalPathLoader to resolve TypeScript issues
- Update OpenAI package to version 4.77.3
- Add confirmation modal for max tokens setting
- Modify max tokens input to use InputNumber instead of Slider
- Update localization strings for max tokens and URL input
- Enhance knowledge base URL input to support multiple URLs
- Improve error handling and input validation
* feat: knowledge base support more file types
* chore: add common document types
* feat: finish basic odloader
* feat: finish open document loader
* feat: support more type from dictionary
* fix: 删除目录时仍能检索到信息
* chore
* feat: 🎸 使用@呼出模型选择列表
输入第一个字符为@符号的时候可以呼出选择模型的列表
* feat: 🎸 Only one can be chosen at a time
一次只能选择一个模型，选择后自动关闭。选择过的模型不在出现在列表，避免删除模型的时候显示异常。
* fix: 🐛 When choosing the model, Enter will send a message
* feat: 🎸 选中的模型显示供应商
* feat: 🎸 pinned module show privoder
* feat: 🎸 only selected modle show provider
* feat: 🎸 删除@符号以后自动关闭
* feat: 🎸 增加模糊搜索
---------
Co-authored-by: duanyongcheng77 <duanyongcheng77@gmail.com>
* fix: retain selected model when regenerating message instead of reverting to default model
* fix: use props model
---------
Co-authored-by: Shern <shenkeji@corp.netease.com>
- Incremented version from 60 to 61 in the persisted reducer configuration.
- Updated migration logic to change the provider type for 'qwenlm' from 'openai' to 'qwenlm', ensuring correct identification in the state management.
- Updated Message component to fallback to message.model if model retrieval fails, improving robustness.
- Refactored MessageHeader to utilize getModelName for better user name display based on message role, enhancing clarity.
- Introduced getModelName function in ModelService to streamline model name retrieval, improving code modularity and readability.
- Updated AddAssistantPopup to improve layout and styling, ensuring better overflow handling and text display.
- Refactored AgentsPage to utilize a new utility function for grouping agents, enhancing data management and organization.
- Exported getAgentsFromSystemAgents function for better modularity and reusability across components.
- Updated translateText function to accept an optional callback for handling translated text directly within the function.
- Refactored MessageMenubar to utilize the new callback mechanism, improving the flow of translated content handling.
- Enhanced error handling during translation to ensure better user feedback in case of failures.
- Introduced FileService to handle file reading operations via IPC.
- Implemented a new IPC handler for reading files, enhancing the application's ability to access and manage data.
- Integrated system agents from a JSON file, allowing dynamic loading of agent data into the application.
- Updated the AgentsPage and AddAssistantPopup components to utilize the new system agents, improving user experience and functionality.
- Enhanced application state management by adding resourcesPath to the runtime state, ensuring proper resource handling across components.
- Replaced direct usage of modelId with model object in Message, MessageHeader, MessageMenubar, and TranslatePage components for consistency.
- Introduced getMessageModelId utility function to streamline model retrieval from messages.
- Updated event handling in Messages component to align with new model structure.
- Enhanced code readability and maintainability by reducing redundancy in model handling.
- Updated MessageMenubar to display the resend button only for user messages, enhancing user experience and preventing unnecessary actions for other roles.
- Refactored the children prop of TextEditPopup to include conditional rendering logic based on message role.
- Added new styles for message thought containers and group message wrappers to improve UI layout.
- Updated MessageGroup component to dynamically set the selected message index based on message length.
- Introduced a new event for appending messages, enhancing message handling capabilities.
- Refactored MessageMenubar to support the new append message functionality.
- Adjusted multi-model message style setting to 'fold' for better user experience.
- Improved responsiveness of message grid layout for smaller screens.
- Replaced hardcoded language translation options with a dynamic mapping from TranslateLanguageOptions.
- Improved maintainability and scalability of the translation feature by utilizing a centralized configuration for language options.
- Introduced a new image asset for the FlagOpen model in the assets directory.
- Updated the models configuration to include the FlagOpen logo, allowing for its use in the model logo mapping.
- Refactored `getMessageBackground` function for better readability.
- Updated `MessageContent` component to use a new `withMessageThought` utility for extracting reasoning content from messages.
- Changed fragment usage to `Fragment` for consistency in JSX.
- Enhanced message handling by separating reasoning content from the main message content.
* Fix: ESC key to exit the expanded editor
* Add the shortcuts for 'clear' and 'new context' to the input bar
Clear Messages: Ctrl+L
New Context: Ctrl+R
https://github.com/CherryHQ/cherry-studio/issues/740https://github.com/CherryHQ/cherry-studio/issues/766
* Fix: the paste issue when copying from an email (content was pasted as an image; ensure it is pasted as text). Prioritize the text in the clipboard during pasting.
If there is no subsequent message or if the next message is from the user, this message should be resent. delete the old message after processing is complete.
* add custom api parameters
* allow more data types for custom api parameters
* pass parameter to api payload
* add custom parameter settings to sidebar
* remove unnecessary object and array types
* extract API custom parameter method to BaseProvider
* add i18n for custom parameter settings
---------
Co-authored-by: 亢奋猫 <kangfenmao@qq.com>
* added locale for context-menu
* fix: when changing the values in the inputs in the tab Default Assisting, they do not change
---------
Co-authored-by: injurka <ikornilov.ext@prosebya.ru~>
- Added new translation strings for API URL actions and hints.
- Updated Chinese translations and added new provider API URL descriptions.
- Added new translations for API URL preview and reset tip.
- Added support for Open AI API settings preview and hint.
- Added a new isOpenAIProvider function to handle specific provider type checks.
- Added a new function to validate if a given URL has a valid non-root path.
- Added conditional rendering to MessageTokens component.
- Added parameter 'isLastMessage' to MessageTokens component to determine conditional rendering based on message position.
- Increased file list pagination size to improve data display.
- Disable inline styles for Markdown content.
- Removed overflow functionality for a smoother scrolling experience.
- Added event listeners for estimated token count and add new topic events.
- Updated default topic handling when clearing messages.
- Removed feature to add new topics directly in Navbar and replaced it with emitting an event to create a new topic.
- Added the functionality to add new topics, clear messages, and handle topic switching with improved conditional logic.
- The event constants configuration has been updated to include two new event names.
- Added a border radius to scrollbar thumb styles for improved aesthetic.
- Updated the Divider component to include a border for better visual separation.
- Added border to the divider in SelectModelPopup for improved visibility.
- Renamed the display of model names to show the exact model name instead of capitalized first letter.
- Fixed logic to handle model name retrieval for assistant messages.
- Renaming of model display name to use the model's original name instead of a capitalized version.
- Removed unnecessary import and corrected label formatting in the options array.
- Updated release notes to reflect changes including image preview and download.
- Added interactive image preview component with toolbar for rotation, zooming, and downloading.
- Added support for image previews in Markdown rendering.
- Added functionality to download files from a URL with automatic filename detection and handling.
- This commit updates release notes to include new features and fix existing issues.
- Removed non-essential keyboard shortcuts from context menu items.
- Adjusted padding styles in AssistantModelSettings component.
- The addition of a close button to the Assistant Prompt Settings component to enhance its functionality.
- Added OK callback event to AssistantPromptSettings component.
- Added translations for new UI elements.
- Updated translation data for Chinese language.
- Added new translations and updated existing values in the language file to incorporate additional features.
- Added functionality to automatically scroll to the bottom of the messages container upon receiving new messages.
- Return null when suggestions list is empty instead of displaying an empty container.
- Improved formula rendering by removing unnecessary escaping of dollar numbers.
- Implemented two new string escaping functions to prevent incorrect LaTeX formula rendering.
#101
- Improved functionality for handling text input and file uploads in the input bar.
- Added functionality to insert text at cursor position in a text area.
- Added smooth all property transition effect to Icon component.
- Added hover effect and conditional rendering for Switch Topic Sidebar button on current assistant.
- Updated the existing conditional options array to consistently include both topic and settings options.
- Improved hover effects on topic list items.
- Added functionality for handling MinApp window closure and provided a default close event handler.
- Added event listeners to Sidebar menus to interact with MinApp.
- Added a margin bottom to the Upload component in the MessageAttachments page for improved layout.
- Added support for not displaying file contents for specific providers.
- Added translations for a new field.
- Added new column for file count in the FilesPage view.
- Improved handling of message tokens in the UI.
- Added functionality to display message tokens for messages with specific roles.
- Added window style selection and styling adjustments to the General Settings page.
- Added support for vision models in OpenAIProvider.
- This commit addresses key feature enhancements and minor optimizations for improved user experience and functionality.
- Adjusted margin top for upload container to a positive value.
- Adjusted the max-height of the container to improve rendering on smaller screens.
- Updated file manager to use FileManager class instead of File class.
- Improved file management functionality with features for finding duplicate files, file uploading, and storage management.
- Added styles to wrap and truncate text in a no-drag area.
- Added explicit file extensions to imageExts constant.
- Added the 'paste long text as file' input setting.
- Added image file display and UI improvements for file names and overflow.
- Improved file paste and long text handling functionality.
- awaited onSendMessage function call and added message to chat completion.
- Implemented new option to paste long text as file in the Settings page.
- Updated content display logic to include file origin name along with the file content for text files.
- Improved functionality for handling image and text file contents in the Gemini chat provider.
- Updated file content formatting logic for text files with origin name and content prefix.
- Added a new setting "pasteLongTextAsFile" and its corresponding action to the application settings.
- Estimated usage calculation has been added to chat completion fetching to track message usage.
- Added functionality to estimate completion usage tokens based on input and prompt data.
- Added functionality to move topics between assistants.
- Updated i18n translations to improve user interface clarity and accessibility.
- Improved code organization and functionality to support moving topics between assistants.
- Updated restore function now clears database and restores specific data from backup.
- Removed unused imports and refactored logic for item transformation in the '24' migration step.
- Removed ability to open developer tools in main window.
- Added and removed a link to the "/files" route in the Sidebar component.
- Fixed file deletion logic to correctly delete files from both the database and the file system.
- Updated configuration to exclude additional directories from electron-builder's build process.
- Dropped the creation of the "files" table in the database schema.
- Improved code organization and extracted the data path into a reusable function.
- Updated database migration configuration to use a new migration manager.
- Added database migration to create a table for file management.
- A migration to remove the "files" table has been applied.
- Updated color palette settings have been implemented.
- Added VisionIcon component utilizing Ant Design icons and styled components for visual customization.
- Updated vision model regex to include additional models.
- Added support for multiple file columns in i18n resources.
- Added translations to column titles.
- Added support for vision models in the Select Model Button component.
- Added functionality to display a vision model icon next to the model name on dropdown items.
- Implemented changes to add vision model support to the Edit Models Popup.
- Added icon to display vision models in provider settings.
- Added a "count" column with default value 1 to the "files" table for tracking purposes.
- Improved file duplication and deletion handling.
- Updated regular expression for vision models to include additional providers.
- Improved removal of topics for assistants from local storage.
- Added support for human-readable date formats in file metadata.
- Improved handling of messages with image attachments to include base64 encoded images in the response.
- Added new 'count' property to the FileMetadata interface.
- Improved IPC image handling to return mime type and base64 encoded data alongside the image data.
- Updated type definition for `base64` method in image object to return an object with mime, base64, and data properties.
- Added support for vision models using new function and regex.
- Table cell size has been reduced on the FilesPage component.
- Added support for vision model attachments.
- Added model dependency to AttachmentButton component.
- Implemented new functionality to handle image messages in the GeminiProvider class.
- Update image base64 encoding to directly use API response data.
- Improved functionality for file management has been added.
- Added file system management functionality through IPC.
- Added functionality to interact with files including selection, upload, deletion, and batch operations.
- Added new file operations to the custom API, including file select, upload, delete, batch upload, and batch delete functions.
- Implemented feature to select and upload files via API.
- Updated English translations in internationalization resources to simplify search assistant placeholder.
- Removed unused import, improved text search UI and adjusted font sizes for better readability.
- Added a new SVG logo for the GitHub provider.
- Added a new social media platform provider to the SYSTEM_MODELS configuration.
- Added support for Github provider in the application configuration.
- Added two new translation keys: 'github' with 'GitHub Models' and updated the existing key 'graphrag-kylin-mountain'.
- Added width parameter to EditModelsPopup configuration.
- Added GitHub-specific model handling to OpenAIProvider class.
- Incremented the application version to 25.
- Added support for a new LLM model type.
- Added a new migration step to configure and enable a GitHub LLM provider.
- Improved functionality to search Assistants with enhanced user interaction and command shortcuts.
- Implemented search functionality with runtime state management.
- Added functionality to return default assistant settings and updated conversion of agents to assistants to include default settings.
- Added a new 'searching' boolean field and corresponding state update action to the runtime store.
- Added support for configurable Droppable component props to the DragableList component.
- Updated translations for multiple components and languages.
- Implemented search functionality in the Assistants page.
- Adjusted various font and layout styles to refine the user interface.
- Updated the minimum width of the NavbarRightContainer to match the var(--topic-list-width) setting.
- Added logic to synchronize local _activeTopic with activeTopic state.
- Improve logic for dynamically updating tab state in RightSidebar component based on position and topic settings.
- Removed unneeded console statement from font size slider's onChangeComplete event.
- Adjusted the width of the SettingMenus component to utilize the --settings-width variable.
- Added new styles for the business smart assistant icon.
- Adjusted the sizes and positions of the ArrowRightButton components.
- Removed conditional style for NavbarLeft component.
- Implemented logic to resolve tab initialization based on component position.
- Added the centered property to the OK button on the AgentsPage.
- Added centered option to modal confirmation dialog.
- Centred the delete button in the ProvidersList component.
- Added centered confirmation to reset modal.
- Centered the 'Add Assistant' popup in the chat modal.
- Added centered alignment to the AssistantSettingPopup component.
- The text area prompt input field now has a larger height.
- Updated the positioning of the Manage Agents popup to be centered.
- Added a centered attribute to the AddModelPopup modal footer.
- Added centered positioning to ProviderSettings AddProviderPopup.
- Centered layout has been added to the SearchContainer.
- Added list styling functionality to the DragableList component.
- Removed unused imports and updated container height to accommodate additional content.
