* feat(models): add support for new Qwen model and update effort ratio
- Introduced support for the 'qwen3-235b-a22b-thinking' model with a max token limit of 81,920.
- Updated the model options in ThinkingButton to include 'qwen_3235ba22b_thinking'.
- Adjusted the effort ratio for 'low' from 0.2 to 0.05 for improved performance.
* chore: remove
* feat(MCPService, MCPSettings, MessageTools): enhance long-running server support and UI integration
- Added support for long-running server configurations in MCPService, allowing for timeout adjustments based on server settings.
- Introduced a new `longRunning` property in MCPSettings to manage server behavior and UI elements accordingly.
- Integrated a ProgressBar component in MessageTools to visually represent progress for long-running operations, improving user experience.
* refactor(IpcChannel, MCPService, MessageTools): remove progress IPC channel and integrate progress handling
- Removed the `Mcp_SetProgress` channel from `IpcChannel` and its associated handlers in `ipc.ts` and `preload/index.ts`.
- Integrated progress handling directly in `McpService` to send progress updates to the main window.
- Updated `MessageTools` to display progress using Ant Design's `Progress` component, enhancing the user interface for long-running operations.
- Deleted the `ProgressBar` component as its functionality has been replaced by the new progress handling approach.
* feat(MCPService): add maxTotalTimeout configuration for long-running operations
- Introduced a new `maxTotalTimeout` property in MCPService to define a maximum timeout duration for long-running server operations, enhancing control over server behavior based on the `longRunning` setting.
* refactor(MCPService): remove unused notification handler for cancelled operations
* Removed the CancelledNotificationHandler from MCPService to streamline notification handling and improve code clarity.
* Updated MessageTools component to simplify rendering logic for status indicators, enhancing readability and maintainability.
* refactor(knowledge): simplify dimension settings, support base migration
Embedding dimension
- remove 'auto set dimension', let the user take control
- reuse findModelById
- improve error messages for VoyageEmbeddings
Knowledgebase migration
- enable migration when model or dimension changes
- add knowledgeThunk to reuse code
KnowledgeSettings
- unify UI for AddKnowledgeBasePopup and EditKnowledgeBasePopup
- refactor KnowledgeSettings, split it to smaller components
Tests:
- knowledgeThunk
- InputEmbeddingDimension
- KnowledgeBaseFormModal
- GeneralSettingsPanel
- AdvancedSettingsPanel
- InfoTooltip
Misc.
- add InfoTooltip
- remove MemoriesSettingsModal
* fix: i18n and vitest config
* refactor(useSmoothStream): optimize chunk handling and state management
- Replaced state management with refs for chunk queue to improve performance and reduce unnecessary re-renders.
- Introduced Intl.Segmenter for better character segmentation based on language support.
- Updated rendering logic to ensure final text is displayed correctly when the stream ends.
- Cleaned up unused effects and comments for improved code clarity.
* refactor(useSmoothStream): move segmenter initialization outside of addChunk function
- Moved the initialization of Intl.Segmenter to the top of the file for better performance and to avoid redundant instantiation within the addChunk callback.
- This change enhances the efficiency of chunk processing in the useSmoothStream hook.
Use spread operator to copy all fields from parsed JSON instead of manually
mapping specific fields. This ensures all MCPServer properties including
headers, timeout, dxtVersion, and other optional fields are preserved during
JSON import.
Previously missing fields:
- headers: Record<string, string>
- timeout: number
- dxtVersion: string
- dxtPath: string
- Other optional MCPServer properties
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* chore(env): add .env.example file and update .gitignore
- Introduced a new .env.example file with NODE_OPTIONS configuration.
- Updated .gitignore to exclude .env.example from being ignored.
- Added instructions in dev.md for copying .env.example to .env.
* fix(MessageTools): improve error handling and logging in message preview rendering (#8453)
- Enhanced the rendering logic for message previews by adding a try-catch block to handle JSON parsing errors more gracefully.
- Updated the error handling to provide clearer error messages in the preview when exceptions occur.
- Added debug logging to track the rendering process of message content.
* refactor(Theme): update theme management to use setTheme function
- Replaced toggleTheme with setTheme for more explicit theme handling.
- Removed unused SunMoon icon from TabContainer and Sidebar components.
- Updated theme icon rendering logic to directly reflect the current theme state.
- Adjusted ThemeProvider to include setTheme in context for better theme management.
* refactor(ModelList): streamline button layout and improve accessibility
- Removed tooltip wrappers from manage and add model buttons for a cleaner UI.
- Introduced a new Flex container for primary and default buttons, enhancing layout consistency.
- Updated button rendering to improve accessibility and user experience.
* feat(ModelList): add bulk add/remove functionality for models with confirmation dialog
- Implemented onAddAll and onRemoveAll functions to handle bulk actions for models.
- Added confirmation dialog for adding all models to the list, enhancing user experience.
- Updated translations for confirmation messages in multiple languages.
* chore(languages): update languages with a script (#8445)
* chore(languages): update languages with a script
* refactor: update languages and merge it into constants
* refactor: add usf and ush
* refactor(ipc): enhance write permission check and add untildify utility
- Updated the hasWritePermission function to resolve paths using the new untildify utility, improving path handling.
- Modified IPC handler to await the permission check for better asynchronous handling.
- Introduced a new untildify function to convert paths starting with '~' to the user's home directory.
* fix(ModelEdit): enhance model type management and introduce new selection logic (#8420)
* fix(ModelEdit): enhance model type management and introduce new selection logic
- Added support for 'rerank' model type in the ModelEditContent component.
- Refactored type selection logic to utilize new utility functions for finding differences and unions in model types.
- Updated model type handling to include user selection status, improving user experience in type management.
- Adjusted migration logic to initialize newType for existing models, ensuring backward compatibility.
- Introduced isUserSelectedModelType utility to streamline model type checks across the application.
* refactor(isFunctionCallingModel): simplify model type check logic
- Replaced the inline check for 'function_calling' model type with a call to the new utility function isUserSelectedModelType, enhancing code clarity and maintainability.
* feat(collection): add utility functions for array operations
- Introduced `findIntersection`, `findDifference`, and `findUnion` functions to handle array operations with support for custom key selectors and comparison functions.
- Removed previous implementations from `index.ts` to streamline utility exports.
- Added comprehensive tests for new functions covering basic types and object types with various edge cases.
* refactor(collection): rename utility functions for clarity
- Renamed `findIntersection`, `findDifference`, and `findUnion` to `getIntersection`, `getDifference`, and `getUnion` respectively for improved clarity and consistency in naming.
- Updated corresponding tests to reflect the new function names, ensuring all tests pass with the updated utility functions.
* refactor(ModelEditContent): update model type management and improve selection logic
- Replaced utility function calls to `findDifference` and `findUnion` with `getDifference` and `getUnion` for consistency.
- Introduced temporary state management for model types to enhance user selection handling.
- Added a reset functionality for model type selections, improving user experience.
- Updated the rendering logic to conditionally disable certain model types based on user selections.
* fix(ModelEditContent): enhance model type selection logic with conditional disabling
- Introduced logic to conditionally disable 'rerank' and 'embedding' model types based on user selections.
- Updated the state management for model types to ensure correct user selection handling.
- Improved the confirmation modal to reflect the updated selection logic for better user experience.
* fix(ModelEditContent): refine model type selection and update confirmation logic
- Enhanced the logic for model type selection to ensure accurate user selections for 'rerank' and 'embedding'.
- Updated the confirmation modal to reflect changes in selection handling, improving user experience.
- Adjusted state management to correctly handle updates based on selected model types.
* fix(models): update model support logic to include 'qwen3-235b-a22b-instruct'
* refactor(models): rename 'newType' to 'capabilities' and update related logic in ModelEditContent and migration scripts
* feat(ipc): add App_ResolvePath channel and update path handling
- Introduced a new IPC channel `App_ResolvePath` to resolve file paths, enhancing path management.
- Updated the `hasWritePermission` function to log the original directory instead of the resolved one.
- Modified the `LocalBackupSettings` component to utilize the new `resolvePath` method for improved directory validation.
* add ut
* fix comments
* fix clear manually
* delete duplicate var
---------
Co-authored-by: kangfenmao <kangfenmao@qq.com>
Co-authored-by: SuYao <sy20010504@gmail.com>
Co-authored-by: one <wangan.cs@gmail.com>
* refactor(CodeEditor): add fontSize to props
* feat: use CodeEditor in assistant prompt settings
* refactor(font): add code font family for windows
* refactor: support Sarasa
* chore(env): add .env.example file and update .gitignore
- Introduced a new .env.example file with NODE_OPTIONS configuration.
- Updated .gitignore to exclude .env.example from being ignored.
- Added instructions in dev.md for copying .env.example to .env.
* fix(MessageTools): improve error handling and logging in message preview rendering (#8453)
- Enhanced the rendering logic for message previews by adding a try-catch block to handle JSON parsing errors more gracefully.
- Updated the error handling to provide clearer error messages in the preview when exceptions occur.
- Added debug logging to track the rendering process of message content.
* refactor(Theme): update theme management to use setTheme function
- Replaced toggleTheme with setTheme for more explicit theme handling.
- Removed unused SunMoon icon from TabContainer and Sidebar components.
- Updated theme icon rendering logic to directly reflect the current theme state.
- Adjusted ThemeProvider to include setTheme in context for better theme management.
* refactor(ModelList): streamline button layout and improve accessibility
- Removed tooltip wrappers from manage and add model buttons for a cleaner UI.
- Introduced a new Flex container for primary and default buttons, enhancing layout consistency.
- Updated button rendering to improve accessibility and user experience.
* feat(ModelList): add bulk add/remove functionality for models with confirmation dialog
- Implemented onAddAll and onRemoveAll functions to handle bulk actions for models.
- Added confirmation dialog for adding all models to the list, enhancing user experience.
- Updated translations for confirmation messages in multiple languages.
* chore(languages): update languages with a script (#8445)
* chore(languages): update languages with a script
* refactor: update languages and merge it into constants
* refactor: add usf and ush
* fix(ModelEdit): enhance model type management and introduce new selection logic (#8420)
* fix(ModelEdit): enhance model type management and introduce new selection logic
- Added support for 'rerank' model type in the ModelEditContent component.
- Refactored type selection logic to utilize new utility functions for finding differences and unions in model types.
- Updated model type handling to include user selection status, improving user experience in type management.
- Adjusted migration logic to initialize newType for existing models, ensuring backward compatibility.
- Introduced isUserSelectedModelType utility to streamline model type checks across the application.
* refactor(isFunctionCallingModel): simplify model type check logic
- Replaced the inline check for 'function_calling' model type with a call to the new utility function isUserSelectedModelType, enhancing code clarity and maintainability.
* feat(collection): add utility functions for array operations
- Introduced `findIntersection`, `findDifference`, and `findUnion` functions to handle array operations with support for custom key selectors and comparison functions.
- Removed previous implementations from `index.ts` to streamline utility exports.
- Added comprehensive tests for new functions covering basic types and object types with various edge cases.
* refactor(collection): rename utility functions for clarity
- Renamed `findIntersection`, `findDifference`, and `findUnion` to `getIntersection`, `getDifference`, and `getUnion` respectively for improved clarity and consistency in naming.
- Updated corresponding tests to reflect the new function names, ensuring all tests pass with the updated utility functions.
* refactor(ModelEditContent): update model type management and improve selection logic
- Replaced utility function calls to `findDifference` and `findUnion` with `getDifference` and `getUnion` for consistency.
- Introduced temporary state management for model types to enhance user selection handling.
- Added a reset functionality for model type selections, improving user experience.
- Updated the rendering logic to conditionally disable certain model types based on user selections.
* fix(ModelEditContent): enhance model type selection logic with conditional disabling
- Introduced logic to conditionally disable 'rerank' and 'embedding' model types based on user selections.
- Updated the state management for model types to ensure correct user selection handling.
- Improved the confirmation modal to reflect the updated selection logic for better user experience.
* fix(ModelEditContent): refine model type selection and update confirmation logic
- Enhanced the logic for model type selection to ensure accurate user selections for 'rerank' and 'embedding'.
- Updated the confirmation modal to reflect changes in selection handling, improving user experience.
- Adjusted state management to correctly handle updates based on selected model types.
* fix(models): update model support logic to include 'qwen3-235b-a22b-instruct'
* refactor(models): rename 'newType' to 'capabilities' and update related logic in ModelEditContent and migration scripts
* refactor(ModelEditContent): remove maskClosable prop for improved modal behavior
* fix(ThinkingTagExtraction): add new tag configuration for 'kimi-vl-a3b-thinking' model (#8459)
* feat(ThinkingTagExtraction): add new tag configuration for 'kimi-vl-a3b-thinking' model and update model regex patterns in config
- Introduced a new tag configuration for the 'kimi-vl-a3b-thinking' model in ThinkingTagExtractionMiddleware.
- Updated models.ts to include regex patterns for 'kimi-vl-a3b-thinking', 'llama-guard-4', and 'llama-4' to enhance model compatibility.
* feat(models): add regex pattern for 'gemma3' model to enhance model compatibility
* fix(RawStreamListenerMiddleware): update model check (#8433)
* fix(RawStreamListenerMiddleware): update model check for Anthropic API integration
- Replaced provider type check with model ID check to enhance compatibility with Claude models.
- Improved clarity in the middleware logic for handling raw output from the SDK.
* refactor(RawStreamListenerMiddleware): enhance model identification for Anthropic integration
- Introduced a new utility function `isAnthropicModel` to streamline model checks across the codebase.
- Updated middleware logic to utilize the new function for improved clarity and maintainability.
- Adjusted related tests to ensure compatibility with the updated model identification approach.
* test(ApiService.test): add mock for isAnthropicModel to enhance test coverage for model identification
* refactor(ChatNavbar, Navbar): simplify toggle functions and remove unused fullscreen hook
- Removed unnecessary useCallback functions for toggling assistants and topics, directly using the toggle functions instead.
- Eliminated the unused fullscreen hook import to clean up the code.
- Updated click handlers in the Navbar components for better readability and efficiency.
* chore(version): 1.5.3
* style(MinAppsPage): adjust padding for AppsContainerWrapper based on navbar position
- Increased padding for the AppsContainerWrapper to 50px for better spacing.
- Added conditional padding for when the navbar is positioned at the top, reverting to 20px for improved layout consistency.
* fix(AiProvider): remove unnecessary middleware removal logic for… (#8437)
* refactor(AiProvider): remove unnecessary middleware removal logic for improved clarity
* feat(PPIOAPIClient): add compatibility type check for OpenAIAPIClient
* refactor(ModelEditContent): rename state variable for clarity and update model capabilities handling
- Renamed `tempModelTypes` to `modelCapabilities` for improved clarity in the ModelEditContent component.
- Updated state management and logic to consistently use the new `modelCapabilities` variable throughout the component, enhancing readability and maintainability.
* Feat/vertex-claude-support (#7564)
* feat(migrate): add default settings for assistants during migration
- Introduced a new migration step to assign default settings for assistants that lack configuration.
- Default settings include temperature, context count, and other parameters to ensure consistent behavior across the application.
* chore(store): increment version number to 115 for persisted reducer
* feat(vertex-sdk): integrate Anthropic Vertex SDK and add access token retrieval
- Added support for the new `@anthropic-ai/vertex-sdk` in the project.
- Introduced a new IPC channel `VertexAI_GetAccessToken` to retrieve access tokens.
- Implemented `getAccessToken` method in `VertexAIService` to handle service account authentication.
- Updated the `IpcChannel` enum and related IPC handlers to support the new functionality.
- Enhanced the `VertexAPIClient` to utilize the `AnthropicVertexClient` for model handling.
- Refactored existing code to accommodate the integration of the Vertex SDK and improve modularity.
* feat(vertex-ai): enhance VertexAI settings and API host management
- Added a new method to format the API host URL in both AnthropicVertexClient and VertexAPIClient.
- Updated getBaseURL methods to utilize the new formatting logic.
- Enhanced VertexAISettings component to include an input for API host configuration, with help text for user guidance.
- Updated localization files to include new help text for the API host field in multiple languages.
* fix(vertex-sdk): update baseURL handling and patch dependencies
- Refactored baseURL assignment in AnthropicVertexClient to ensure it defaults to undefined when the URL is empty.
- Updated yarn.lock to reflect changes in dependency resolution and checksum for @anthropic-ai/vertex-sdk patch.
* refactor(VertexAISetting): use provider.id rather than provider
* refactor: improve API host formatting in AnthropicVertexClient
- Updated the `formatApiHost` method to streamline host URL handling.
- Introduced a helper function to determine if the original host should be used based on its format.
- Ensured consistent appending of the `/v1/` path for valid API requests.
* fix: handle empty host in AnthropicVertexClient
- Added a check in the `getBaseURL` method to return the host if it is empty, preventing potential errors.
- Included a console log for the base URL to aid in debugging and verification of the URL formatting.
* feat(AnthropicVertexClient): add logging for authentication errors and mock client in tests
- Introduced logging functionality in AnthropicVertexClient to replace console.error with logger service for better error tracking.
- Added mock implementation for AnthropicVertexClient in tests to enhance testing capabilities.
- Updated package.json to include the @aws-sdk/client-s3 dependency.
* feat(tests): add comprehensive tests for client compatibility types
- Introduced a new test file to validate compatibility types for various API clients including OpenAI, Anthropic, Gemini, Aihubmix, NewAPI, and Vertex.
- Implemented mock services to facilitate testing and ensure isolation of client behavior.
- Added tests for both direct API clients and decorator pattern clients, ensuring correct compatibility type returns.
- Enhanced middleware compatibility logic tests to verify correct identification of compatible clients.
---------
Co-authored-by: one <wangan.cs@gmail.com>
* fix(mcp-tools): enhance tool lookup logic to support partial matches (#8473)
* fix(mcp-tools): enhance tool lookup logic to support partial matches
- Updated the tool lookup logic in `geminiFunctionCallToMcpTool` to include partial matches for both tool IDs and names, improving the flexibility of tool identification.
* refactor(mcp-tools): simplify tool lookup logic for improved clarity
- Refactored the tool lookup logic in `geminiFunctionCallToMcpTool` to streamline the identification process by consolidating checks for tool IDs and names into a single variable. This enhances readability and maintains functionality for partial matches.
* chore(deps): update vite to rolldown-vite (#8460)
* chore(deps): update vite to rolldown-vite and add new dependencies
- Updated vite dependency to rolldown-vite@latest in package.json.
- Added new dependencies including @emnapi/core, @emnapi/runtime, and @napi-rs/wasm-runtime in yarn.lock.
- Introduced patches for atomically and file-stream-rotator packages.
- Added process import in index.ts for improved functionality.
* updrade vitest
* not package graceful-fs
* update yarn.lock
* fix(AppUpdater): improve update handling and logging for test plans
- Enhanced the update logic in AppUpdater to prevent sending an 'update not available' event when a test plan is enabled and the channel is not the latest.
- Refactored the feed URL and channel setting into a private method for better code organization.
- Added logging to provide clearer insights into the update check results and channel settings, particularly when the test plan is active.
---------
Co-authored-by: kangfenmao <kangfenmao@qq.com>
Co-authored-by: SuYao <sy20010504@gmail.com>
Co-authored-by: one <wangan.cs@gmail.com>
- Removed the reasoning check from the ThinkChunkMiddleware to streamline the processing logic.
- This change enhances the middleware's efficiency by focusing on handling streams directly without the reasoning condition.
- Updated navigation logic in `useMCPServers` and `McpServersList` to use server IDs in the URL for better routing.
- Implemented scroll position memory in `McpServersList` to enhance user experience when navigating back to the server list.
- Adjusted route parameters in `MCPSettings` to retrieve server IDs from the URL, improving data handling and clarity.
* chore(deps): update vite to rolldown-vite and add new dependencies
- Updated vite dependency to rolldown-vite@latest in package.json.
- Added new dependencies including @emnapi/core, @emnapi/runtime, and @napi-rs/wasm-runtime in yarn.lock.
- Introduced patches for atomically and file-stream-rotator packages.
- Added process import in index.ts for improved functionality.
* updrade vitest
* not package graceful-fs
* update yarn.lock
* fix(mcp-tools): enhance tool lookup logic to support partial matches
- Updated the tool lookup logic in `geminiFunctionCallToMcpTool` to include partial matches for both tool IDs and names, improving the flexibility of tool identification.
* refactor(mcp-tools): simplify tool lookup logic for improved clarity
- Refactored the tool lookup logic in `geminiFunctionCallToMcpTool` to streamline the identification process by consolidating checks for tool IDs and names into a single variable. This enhances readability and maintains functionality for partial matches.
* feat(migrate): add default settings for assistants during migration
- Introduced a new migration step to assign default settings for assistants that lack configuration.
- Default settings include temperature, context count, and other parameters to ensure consistent behavior across the application.
* chore(store): increment version number to 115 for persisted reducer
* feat(vertex-sdk): integrate Anthropic Vertex SDK and add access token retrieval
- Added support for the new `@anthropic-ai/vertex-sdk` in the project.
- Introduced a new IPC channel `VertexAI_GetAccessToken` to retrieve access tokens.
- Implemented `getAccessToken` method in `VertexAIService` to handle service account authentication.
- Updated the `IpcChannel` enum and related IPC handlers to support the new functionality.
- Enhanced the `VertexAPIClient` to utilize the `AnthropicVertexClient` for model handling.
- Refactored existing code to accommodate the integration of the Vertex SDK and improve modularity.
* feat(vertex-ai): enhance VertexAI settings and API host management
- Added a new method to format the API host URL in both AnthropicVertexClient and VertexAPIClient.
- Updated getBaseURL methods to utilize the new formatting logic.
- Enhanced VertexAISettings component to include an input for API host configuration, with help text for user guidance.
- Updated localization files to include new help text for the API host field in multiple languages.
* fix(vertex-sdk): update baseURL handling and patch dependencies
- Refactored baseURL assignment in AnthropicVertexClient to ensure it defaults to undefined when the URL is empty.
- Updated yarn.lock to reflect changes in dependency resolution and checksum for @anthropic-ai/vertex-sdk patch.
* refactor(VertexAISetting): use provider.id rather than provider
* refactor: improve API host formatting in AnthropicVertexClient
- Updated the `formatApiHost` method to streamline host URL handling.
- Introduced a helper function to determine if the original host should be used based on its format.
- Ensured consistent appending of the `/v1/` path for valid API requests.
* fix: handle empty host in AnthropicVertexClient
- Added a check in the `getBaseURL` method to return the host if it is empty, preventing potential errors.
- Included a console log for the base URL to aid in debugging and verification of the URL formatting.
* feat(AnthropicVertexClient): add logging for authentication errors and mock client in tests
- Introduced logging functionality in AnthropicVertexClient to replace console.error with logger service for better error tracking.
- Added mock implementation for AnthropicVertexClient in tests to enhance testing capabilities.
- Updated package.json to include the @aws-sdk/client-s3 dependency.
* feat(tests): add comprehensive tests for client compatibility types
- Introduced a new test file to validate compatibility types for various API clients including OpenAI, Anthropic, Gemini, Aihubmix, NewAPI, and Vertex.
- Implemented mock services to facilitate testing and ensure isolation of client behavior.
- Added tests for both direct API clients and decorator pattern clients, ensuring correct compatibility type returns.
- Enhanced middleware compatibility logic tests to verify correct identification of compatible clients.
---------
Co-authored-by: one <wangan.cs@gmail.com>
- Renamed `tempModelTypes` to `modelCapabilities` for improved clarity in the ModelEditContent component.
- Updated state management and logic to consistently use the new `modelCapabilities` variable throughout the component, enhancing readability and maintainability.
- Increased padding for the AppsContainerWrapper to 50px for better spacing.
- Added conditional padding for when the navbar is positioned at the top, reverting to 20px for improved layout consistency.
- Removed unnecessary useCallback functions for toggling assistants and topics, directly using the toggle functions instead.
- Eliminated the unused fullscreen hook import to clean up the code.
- Updated click handlers in the Navbar components for better readability and efficiency.
* fix(RawStreamListenerMiddleware): update model check for Anthropic API integration
- Replaced provider type check with model ID check to enhance compatibility with Claude models.
- Improved clarity in the middleware logic for handling raw output from the SDK.
* refactor(RawStreamListenerMiddleware): enhance model identification for Anthropic integration
- Introduced a new utility function `isAnthropicModel` to streamline model checks across the codebase.
- Updated middleware logic to utilize the new function for improved clarity and maintainability.
- Adjusted related tests to ensure compatibility with the updated model identification approach.
* test(ApiService.test): add mock for isAnthropicModel to enhance test coverage for model identification
* feat(ThinkingTagExtraction): add new tag configuration for 'kimi-vl-a3b-thinking' model and update model regex patterns in config
- Introduced a new tag configuration for the 'kimi-vl-a3b-thinking' model in ThinkingTagExtractionMiddleware.
- Updated models.ts to include regex patterns for 'kimi-vl-a3b-thinking', 'llama-guard-4', and 'llama-4' to enhance model compatibility.
* feat(models): add regex pattern for 'gemma3' model to enhance model compatibility
* feat:update kimi setting
* feat:update kimi logo
* mergei18n
* 仅修复 eslint error
Improves code readability by reformatting Moonshot provider configuration and related ternary expressions. Indentation and spacing are adjusted for consistency, with no functional changes.
* change kimi logo to 200x200
* update
* update 2 warnings in AssistantModelSettings.tsx
* fix: lint error
* fix: test error
---------
Co-authored-by: 自由的世界人 <3196812536@qq.com>
Co-authored-by: xiaochen <gongxiaochen@msh.team>
* fix(ModelEdit): enhance model type management and introduce new selection logic
- Added support for 'rerank' model type in the ModelEditContent component.
- Refactored type selection logic to utilize new utility functions for finding differences and unions in model types.
- Updated model type handling to include user selection status, improving user experience in type management.
- Adjusted migration logic to initialize newType for existing models, ensuring backward compatibility.
- Introduced isUserSelectedModelType utility to streamline model type checks across the application.
* refactor(isFunctionCallingModel): simplify model type check logic
- Replaced the inline check for 'function_calling' model type with a call to the new utility function isUserSelectedModelType, enhancing code clarity and maintainability.
* feat(collection): add utility functions for array operations
- Introduced `findIntersection`, `findDifference`, and `findUnion` functions to handle array operations with support for custom key selectors and comparison functions.
- Removed previous implementations from `index.ts` to streamline utility exports.
- Added comprehensive tests for new functions covering basic types and object types with various edge cases.
* refactor(collection): rename utility functions for clarity
- Renamed `findIntersection`, `findDifference`, and `findUnion` to `getIntersection`, `getDifference`, and `getUnion` respectively for improved clarity and consistency in naming.
- Updated corresponding tests to reflect the new function names, ensuring all tests pass with the updated utility functions.
* refactor(ModelEditContent): update model type management and improve selection logic
- Replaced utility function calls to `findDifference` and `findUnion` with `getDifference` and `getUnion` for consistency.
- Introduced temporary state management for model types to enhance user selection handling.
- Added a reset functionality for model type selections, improving user experience.
- Updated the rendering logic to conditionally disable certain model types based on user selections.
* fix(ModelEditContent): enhance model type selection logic with conditional disabling
- Introduced logic to conditionally disable 'rerank' and 'embedding' model types based on user selections.
- Updated the state management for model types to ensure correct user selection handling.
- Improved the confirmation modal to reflect the updated selection logic for better user experience.
* fix(ModelEditContent): refine model type selection and update confirmation logic
- Enhanced the logic for model type selection to ensure accurate user selections for 'rerank' and 'embedding'.
- Updated the confirmation modal to reflect changes in selection handling, improving user experience.
- Adjusted state management to correctly handle updates based on selected model types.
* fix(models): update model support logic to include 'qwen3-235b-a22b-instruct'
* refactor(models): rename 'newType' to 'capabilities' and update related logic in ModelEditContent and migration scripts
- Implemented onAddAll and onRemoveAll functions to handle bulk actions for models.
- Added confirmation dialog for adding all models to the list, enhancing user experience.
- Updated translations for confirmation messages in multiple languages.
- Removed tooltip wrappers from manage and add model buttons for a cleaner UI.
- Introduced a new Flex container for primary and default buttons, enhancing layout consistency.
- Updated button rendering to improve accessibility and user experience.
- Replaced toggleTheme with setTheme for more explicit theme handling.
- Removed unused SunMoon icon from TabContainer and Sidebar components.
- Updated theme icon rendering logic to directly reflect the current theme state.
- Adjusted ThemeProvider to include setTheme in context for better theme management.
- Enhanced the rendering logic for message previews by adding a try-catch block to handle JSON parsing errors more gracefully.
- Updated the error handling to provide clearer error messages in the preview when exceptions occur.
- Added debug logging to track the rendering process of message content.
- Introduced a new .env.example file with NODE_OPTIONS configuration.
- Updated .gitignore to exclude .env.example from being ignored.
- Added instructions in dev.md for copying .env.example to .env.
- Updated lucide-react dependency from 0.487.0 to 0.525.0 in package.json and yarn.lock.
- Added fallback language configuration in i18n setup for improved localization support.
- Refactored Tabs component to utilize classNames for conditional styling.
- Adjusted TopicsTab component's style for better layout management.
- Introduced a button in AboutSettings to open documentation based on the user's language preference.
* fix(inputSchemas): convert input schemas to JSON schema format for consistency across DifyKnowledgeServer and FileSystemServer
* fix(AnthropicAPIClient): handle empty accumulated JSON input gracefully and improve auto-approval logic for built-in tools
* feat(ApiService.test): add tests for Anthropic API client integration and response handling
- Introduced mock implementation for AnthropicAPIClient to simulate completions and response transformations.
- Added test cases to validate the streaming of chunks with correct types and content for the Anthropic model.
- Enhanced existing tests to ensure compatibility with both Gemini and Anthropic API clients.
* feat(ApiService.test): enhance tests for Anthropic API client with streaming support
- Added new test cases for streaming responses from the Anthropic API client, validating chunk types and content.
- Refactored existing tests to differentiate between non-streaming and streaming chunk generators.
- Updated mock implementations to support both streaming and non-streaming scenarios for comprehensive testing.
* test: add test for thinking tag extraction middleware
* revert: unrelated changes
---------
Co-authored-by: one <wangan.cs@gmail.com>
* refactor: streamline system prompt handling and introduce built-in tools
- Removed the static SYSTEM_PROMPT_THRESHOLD from BaseApiClient and replaced it with a constant in constant.ts.
- Updated API clients (AnthropicAPIClient, GeminiAPIClient, OpenAIApiClient, OpenAIResponseAPIClient) to simplify system prompt logic by eliminating unnecessary checks and using new utility functions for prompt building.
- Introduced built-in tools functionality, including a new 'think' tool, to enhance the tool usage experience.
- Refactored ApiService to integrate built-in tools and adjust system prompt modifications accordingly.
- Added utility functions for managing built-in tools in mcp-tools.ts and created a new tools index for better organization.
* refactor(tests): update prompt tests to use new buildSystemPromptWithTools function
- Renamed the function used in prompt tests from buildSystemPrompt to buildSystemPromptWithTools to reflect recent changes in prompt handling.
- Adjusted test cases to ensure compatibility with the updated function, maintaining the integrity of user prompt handling.
* refactor(ApiService, mcp-tools, prompt): enhance tool usage and prompt handling
- Updated ApiService to improve system prompt construction based on tool usage mode, ensuring clearer logic for tool integration.
- Enhanced mcp-tools with a new response structure for the 'think' tool, allowing for better handling of tool responses.
- Expanded prompt utility functions to include detailed instructions for using the 'think' tool, improving user guidance.
- Refactored tests to validate new prompt building logic and tool integration, ensuring robust functionality across scenarios.
* fix: enhance prompt
* feat(McpToolChunkMiddleware): enhance tool call handling with built-in tool support
- Added support for built-in tools in the parseAndCallTools function, allowing for conditional tool invocation based on tool type.
- Implemented a check to return early if the tool call response is null, improving error handling.
refactor(useSmoothStream): remove unnecessary comments and improve state initialization in Markdown component
- Cleaned up comments in useSmoothStream for clarity.
- Updated displayedContent state initialization in Markdown to handle post-processing conditionally.
* refactor(AiProvider): enhance client compatibility checks and middleware handling
- Updated AiProvider to use a compatibility type check for API clients, improving type safety and middleware management.
- Implemented getClientCompatibilityType in AihubmixAPIClient, NewAPIClient, and OpenAIResponseAPIClient to return actual client types.
- Added support for Hunyuan models in various model checks and updated the ThinkingButton component to reflect these changes.
- Improved logging for middleware construction in AiProvider.
* test(ApiService): add client compatibility type checks for mock API clients
* fix: minimax-m1 reasoning export btw
---------
Co-authored-by: Pleasurecruise <3196812536@qq.com>
* feat: ui switch
* chore: update migration version to 122 and adjust settings topic position
* refactor: replace PinnedApps component with SidebarPinnedApps and SidebarOpenedMinappTabs for improved structure
* feat(i18n): add launchpad apps and minapps translations for multiple languages
* style: update MinAppIcon and IconContainer dimensions for improved UI consistency
* refactor: remove unused SidebarContainer component from AppsPage
* refactor: adjust Navbar padding and enhance search functionality in AgentsPage
* feat(minapps): implement MinApps page and enhance mini app management features
- Added MinAppsPage for managing mini applications.
- Introduced NewAppButton for adding custom mini apps.
- Created MiniAppSettings for configuring mini app settings.
- Enhanced mini app icon management with MiniAppIconsManager.
- Updated Router to include MinAppsPage and replaced AppsPage with MinAppsPage.
- Added translations for new mini app features in multiple languages.
* wip
* refactor: rename App component to MinApp and streamline LaunchpadPage logic
- Renamed App component to MinApp for clarity.
- Removed unnecessary state management in LaunchpadPage.
- Simplified minapp sorting logic by directly using openedKeepAliveMinapps.
* feat(i18n): update translations for multiple languages and restructure title entries
- Added missing title entries for various sections in English, Japanese, Russian, Chinese (Simplified and Traditional).
- Restructured the launchpad and minapp translations for better organization.
- Enhanced navbar display settings translations across all supported languages.
* feat: add header prop to DraggableVirtualList and implement Add Topic button in TopicsTab
- Introduced a new `header` prop in the DraggableVirtualList component to allow custom header content.
- Added an Add Topic button in the TopicsTab with a corresponding styled component and translation support for multiple languages.
- Updated styles in AssistantsTab and adjusted overflow behavior in Tabs index for better UI experience.
* style: adjust margins and max-width for improved layout in various components
- Updated margin-top in HtmlArtifactsCard for consistent spacing.
- Set max-width in MessageGroup to enhance responsiveness based on navbar position.
- Modified Add Topic button in TopicsTab to emit an event for better functionality.
* fix: correct state property name in migration for navbar position
- Updated the migration logic to set the correct state property from `topicPosition` to `navbarPosition` for proper configuration handling.
* fix: adjust traffic light position and navbar height for improved UI consistency
- Updated traffic light position in WindowService to enhance layout.
- Adjusted navbar height in color.scss for better alignment across components.
- Modified TabContainer to track last settings path and improve navigation handling.
* style: update AddTopicButton styling for improved hover effect in TopicsTab
- Changed AddTopicButton from a button to a div for better styling flexibility.
- Removed dashed border and added background color on hover for enhanced user experience.
- Retained border-radius for consistent design across components.
* feat: add TextBadge component and integrate into Display and Memory settings
- Introduced a new TextBadge component for displaying styled badges.
- Integrated TextBadge into DisplaySettings to highlight the navbar title as "New".
- Replaced inline badge implementation in MemorySettings with the new TextBadge component for consistency and improved maintainability.
* fix: adjust tab and navbar styling for improved UI consistency
- Increased height of title bar overlays for better visual balance.
- Updated tab creation logic to prevent duplicate tabs for specific paths.
- Modified tab icon and close button sizes for a more compact design.
- Enhanced tab spacing and padding for improved layout across components.
* style: update PinnedMinapps component for improved UI consistency
- Increased icon size and adjusted border radius for better visual appeal.
- Modified TopNavContainer padding and margin for enhanced layout.
- Reduced dimensions of TopNavIcon for a more compact design.
* refactor: enhance TabsContainer logic and styling for improved tab management
- Introduced a new `removeSpecialTabs` function to manage special tab removal more effectively.
- Updated tab filtering logic to utilize a dedicated `specialTabs` array for better maintainability.
- Adjusted styling in PinnedMinapps for consistent icon sizing and background color improvements.
* style: adjust layout and padding for improved UI consistency in Chat and Inputbar components
- Updated main height calculation in Chat component to account for additional spacing.
- Modified padding in Inputbar component for better alignment when navbar is positioned at the top.
- Ensured consistent minimum height in Tabs component to match updated navbar height calculations.
* refactor: update app menu item text keys for improved localization
- Changed text keys in the app menu items from specific titles to a more generalized 'title' namespace for better consistency and maintainability.
- Ensured that the visual representation of the menu items remains unchanged while enhancing the localization structure.
* refactor: simplify sidebar toggle logic in ChatNavbar and Navbar components
- Removed unnecessary cooldown logic when toggling the visibility of assistants and topics.
- Updated HomePage to conditionally render the Navbar based on the sidebar state for improved UI responsiveness.
* refactor: streamline Chat component and introduce useChatMaxWidth hook
- Consolidated max width calculation logic into a new `useChatMaxWidth` hook for better reusability.
- Removed unused variables and simplified state management in the Chat component.
- Updated MessageGroup to utilize the new `useChatMaxWidth` hook for consistent layout handling.
* refactor: remove FloatingSidebar component and integrate AssistantsDrawer for improved UI management
- Deleted the FloatingSidebar component to streamline the codebase.
- Introduced AssistantsDrawer for managing assistant interactions, enhancing user experience.
- Updated Navbar and ChatNavbar components to utilize AssistantsDrawer instead of FloatingSidebar for better responsiveness and maintainability.
* refactor: implement TabsService for improved tab management functionality
- Introduced TabsService to centralize tab operations, including closing and setting active tabs.
- Updated TabsContainer and LaunchpadPage components to utilize TabsService for closing tabs, enhancing code maintainability.
- Made minor UI adjustments in PinnedMinapps for consistent icon sizing and layout improvements.
* fix: prevent default event behavior when not in fullscreen mode
- Updated WindowService to conditionally call event.preventDefault() only when the main window is not in fullscreen, improving event handling logic.
* refactor: match provider and model using a consistent method
* refactor: use keywords matching across model selectors
* refactor: update match, reuse getFancyProviderName
* refactor: use modelSelectFilter in knowledgebase settings
* refactor: use filter in ModelList
* refactor: add filterModelsByKeywords
* refactor: add getModelSelectOptions
* style: better function names
* fix: update effect dependencies in popup and panel components
Adjusted dependency arrays in HtmlArtifactsPopup and QuickPanelView to ensure correct effect execution. This change improves state synchronization and prevents unnecessary updates.
* refactor: use match in memory settings
* refactor: add avatar to model selector
* refactor: simplify utils, move select options to components
* docs: add comments
* refactor: move filter to SelectOptions
* test: add tests for SelectOptions
* test: remove type mock
* refactor: use match in EditModelsPopup
* refactor: use SelectOptions in SelectProviderModelPopup, add more tests
* fix: api check model select
* refactor: improve websearch rag model select style
* refactor: add a ModelSelector
* test: update tests for ModelSelector
* docs: comments
---------
Co-authored-by: 自由的世界人 <3196812536@qq.com>
* fix: ensure add button is always visible for empty model providers
- Move add button outside of isEmpty(models) condition to fix regression
- Keep manage and health check buttons conditional (only show when models exist)
- Fixes issue where users cannot add first model to custom providers
- Maintains clean UI by hiding management features when no content exists
Resolves the UX blocker introduced in commit 2b0c46bf where all buttons
were hidden for empty providers, preventing users from adding initial models.
* fix: remove isEmpty check to always show model management buttons
Remove isEmpty(models) conditions for manage, search, and health check buttons
to ensure all functionality is available even with empty model lists.
* feat: implement useSmoothStream hook for dynamic text rendering
- Added a new custom hook `useSmoothStream` to manage smooth text streaming with adjustable delays.
- Integrated `useSmoothStream` into the Markdown component to enhance content display during streaming.
- Implemented logic to handle content updates and reset conditions based on block status.
* feat: enhance chunk processing in useSmoothStream hook
- Updated the `addChunk` function to split text into characters for Chinese and words for English using a regular expression.
- Improved text rendering logic to support mixed language content more effectively.
* refactor: improve regular expression for chunk processing in useSmoothStream hook
- Updated the regular expression to enhance text splitting capabilities, allowing for better handling of mixed language content, including Chinese characters and alphanumeric sequences.
* refactor: simplify character processing in useSmoothStream hook
- Replaced the regular expression for character extraction with a direct conversion of the chunk to an array of characters.
- This change streamlines the chunk processing logic, enhancing performance and readability.
* feat: add post-processing capability to Markdown component
- Enhanced the Markdown component to accept an optional post-processing function for text manipulation during streaming.
- Updated MainTextBlock to utilize the new postProcess prop, allowing for dynamic content adjustments based on citation references.
* fix: update mock Markdown component to support post-processing
- Modified the mock implementation of the Markdown component to accept and apply an optional postProcess function, ensuring that the test environment accurately reflects the updated functionality introduced in the previous commit.
* refactor(ProviderSetting): add a backtop to provider setting
* refactor: decouple ModelList from ProviderSetting
* refactor: move modellist to a single dir
* refactor: allow more props for CollapsibleSearchBar
* refactor: split ModelList into ModelList, ModelListGroup and ModelListItem
* refactor: simplify health check types, improve file structure
* refactor: split HealthStatusIndicator from list items
* refactor: better indicator tooltip
* refactor: improve model search, simplify some expressions
* refactor: further simplify ModelList by extracting onHealthCheck
* refactor: remove double scroller from EditModelsPopup
* revert: remove backtop
* fix: i18n order
* refactor: sort buttons
* refactor: move initAppDataDir function to a new utils module
- Updated the import path for initAppDataDir in bootstrap.ts to reflect its new location in the utils/init module.
- Removed the initAppDataDir function and related code from file.ts to streamline the file and improve organization.
* refactor: update import structure in ipc.ts
- Removed the import of updateAppDataConfig from file.ts and added it to the new init module for better organization and clarity in the code structure.
* refactor: rename getConfigPath to getConfigDir and update related references
- Renamed the function getConfigPath to getConfigDir for clarity.
- Updated references to the renamed function in getAppDataPathFromConfig and updateAppDataConfig to reflect the new naming convention.
* refactor: update pdfjs import and improve file filtering in electron-builder configuration
- Changed pdfjs import to a direct import from 'pdfjs-dist' for consistency across modules.
- Updated file filtering in electron-builder.yml to exclude all legacy files from pdfjs-dist instead of just specific ones.
* format code
* fix: fix persistent "Searching..." indicators for o3 model web search
- Add missing LLM_WEB_SEARCH_IN_PROGRESS event in OpenAIAPIClient
- Prevent duplicate CitationBlock creation
- Ensure search status updates correctly after completion
Fixes#8307
* fix: prevent duplicate citation blocks in web search callbacks
- Add checks in onExternalToolInProgress and onLLMWebSearchInProgress
- Return early if citationBlockId already exists
- Fixes persistent "Searching..." indicator for o3 model web search
refactor(Logger): enhance logging with environment variable support
- Updated LoggerService to utilize environment variables for filtering logs by level and module in development mode.
- Modified the logging level handling to use constants from the logger configuration.
- Enhanced documentation to include details on using environment variables for log filtering in both English and Chinese documentation files.
- Cleaned up unused type definitions related to logging.
* docs: enhance LoggerService documentation and usage guidelines
- Added details about `initWindowSource` method, emphasizing its return of the LoggerService instance for method chaining.
- Introduced a section on using LoggerService within `worker` threads, highlighting the need to call `initWindowSource` first.
- Updated both English and Chinese documentation files to reflect these changes, ensuring clarity in usage instructions for developers.
* docs: update LoggerService documentation and improve environment checks
- Enhanced documentation for using LoggerService in worker threads, clarifying logging support limitations in main and renderer processes.
- Added environment checks for development and production modes directly in the LoggerService.
- Removed the unused env utility file to streamline the codebase.
* refactor(ShikiStreamService): update highlighter management and improve test assertions
- Modified the highlighter management in ShikiStreamService to clear the reference instead of disposing it directly, as it is now managed by AsyncInitializer.
- Enhanced unit tests to verify the initialization of worker and main highlighters, ensuring that either one is active but not both, and updated assertions related to highlighter disposal.
* fix/selection-not-copy
* fix: abort not copy
* test: add actionUtil test
Update onStream callback to accept content parameter and set copyable content
during streaming instead of only at completion. Removes redundant content
tracking in ActionUtils and properly passes content to callbacks as it's
received. Adds test directory structure for components.
* refactor: improve streaming content handling and fix error states
Refine content handling in ActionUtils by tracking content internally rather than
passing it through onStream callbacks. Properly set error status in message
updates and ensure content is finalized on errors. Fix typo in test filename.
* fix: show error
* chore: remove unuse
* chore: remove console
* refactor: replace console logging with logger service across multiple components
- Updated various files to utilize the logger service instead of console.log for improved logging consistency and error tracking.
- Enhanced logging levels to better categorize messages, including debug and error levels.
- Refactored logging in components such as ApiClientFactory, KnowledgeService, and MemoryProcessor to align with the new logging standards.
* refactor: update logging level in App component from error to info
- Changed the logging level in the App component to provide a more appropriate context for initialization messages, enhancing clarity in the logging output.
* refactor(logging): replace console.log with logger service in middleware and update ESLint comments
- Updated the logging implementation in the createSimpleLoggingMiddleware function to use logger.debug and logger.error instead of console.log and console.error for improved logging consistency.
- Added eslint-disable comments for restricted syntax in preload and useAppInit hooks to suppress warnings.
* chore: update ESLint configuration and LoggerService formatting
- Refactored ESLint configuration to include custom rules for LoggerService, applying them specifically to the src directory while ignoring test and mock files.
- Commented out date formatting options in LoggerService for improved clarity in development logging.
* fix: add eslint-disable comments for restricted syntax in LoggerService
- Added eslint-disable comments to suppress warnings for restricted syntax in LoggerService for both main and renderer services.
- Improved error handling by logging messages when the window source is not initialized in the renderer LoggerService.
