Add Model Context Protocol (MCP) server integration to extend AI agent
capabilities with external tools. This allows users to configure MCP
servers (stdio, SSE, HTTP) in global settings and have agents use them.
Note: MCP servers are currently configured globally. Per-project MCP
server configuration is planned for a future update.
Features:
- New MCP Servers settings section with full CRUD operations
- Import/Export JSON configs (Claude Code format compatible)
- Configurable permission settings:
- Auto-approve MCP tools (bypass permission prompts)
- Unrestricted tools (allow all tools when MCP enabled)
- Refresh button to reload from settings file
Implementation:
- Added MCPServerConfig and MCPToolInfo types
- Added store actions for MCP server management
- Updated claude-provider to use configurable MCP permissions
- Updated sdk-options factory functions for MCP support
- Added settings helpers for loading MCP configs
- Removed the delay mechanism for starting newly created features, simplifying the process.
- Updated the logic to capture existing feature IDs before adding a new feature, allowing for immediate identification of the newly created feature.
- Enhanced error handling to notify users if the feature could not be started automatically.
Update waitForContextFile, selectContextFile, and waitForFileContentToLoad
helpers to use Playwright's expect().toPass() with retry intervals, handling
race conditions between API calls completing and UI re-rendering. Also add
waitForNetworkIdle after dialog closes in context-file-management test.
Add a global setting to enable/disable sandbox mode for Claude Agent SDK.
This allows users to control sandbox behavior based on their authentication
setup and system compatibility.
Changes:
- Add enableSandboxMode to GlobalSettings (default: true)
- Add sandbox mode checkbox in Claude settings UI
- Wire up setting through app store and settings service
- Update createChatOptions and createAutoModeOptions to use setting
- Add getEnableSandboxModeSetting helper function
- Remove hardcoded sandbox configuration from ClaudeProvider
- Add detailed logging throughout agent execution flow
The sandbox mode requires API key or OAuth token authentication. Users
experiencing issues with CLI-only auth can disable it in settings.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Replaced theme-specific scrollbar styles with a universal approach using CSS variables for better maintainability.
- Moved theme-specific scrollbar overrides from `global.css` to their respective theme files (`retro.css`, `red.css`)
- Introduced useOSDetection hook to determine the user's operating system.
- Updated FileBrowserDialog to utilize the OS detection for displaying the correct keyboard shortcut (⌘ or Ctrl) based on the detected OS.
- Replaced inline entry mapping with a memoized entryItems component for improved performance.
- Clarified keydown event handling comments to enhance understanding of ESC key behavior in relation to modal interactions.
- Updated keydown event logic to prevent search activation when input fields or contenteditable elements are focused.
- Enhanced ESC key handling to ensure parent modal does not close when search is open.
- Adjusted dependencies in useEffect to include entries length for better state management.
- Added Kbd and KbdGroup components for keyboard shortcuts in FileBrowserDialog.
- Implemented search functionality in PathInput, allowing users to search files and directories.
- Updated PathInput to handle file system entries and selection from search results.
- Improved UI/UX with better focus management and search input handling.
- Introduced a new setting to enable automatic loading of CLAUDE.md files from project-specific directories.
- Updated relevant services and components to support the new setting, including the AgentService and AutoModeService.
- Added UI controls for managing the auto-load setting in the settings view.
- Enhanced SDK options to incorporate settingSources for CLAUDE.md loading.
- Updated global and project settings interfaces to include autoLoadClaudeMd property.
- Changed the navigation instruction text in FileBrowserDialog to use an arrow symbol for clarity.
- Added an ArrowRight icon to the PathInput component's button for improved visual feedback when navigating to a path.
- Removed unused state and imports from FileBrowserDialog.
- Replaced direct path input with a new PathInput component for improved navigation.
- Enhanced state management for path navigation and error handling.
- Updated UI elements for better user experience and code clarity.
- Introduced a useRef hook to track component mount status, preventing state updates on unmounted components.
- Updated fetchIssues function to conditionally set state only if the component is still mounted, improving reliability during asynchronous operations.
- Ensured proper cleanup in useEffect to maintain accurate mounted state, enhancing overall component stability.
- Removed the isValidating prop from GitHubIssuesView and ValidationDialog components to streamline validation logic.
- Updated handleValidateIssue function to eliminate unnecessary dialog options, focusing on background validation notifications.
- Enhanced user feedback by notifying users when validation starts, improving overall experience during issue analysis.
- Added onDeleteTask functionality to allow task deletion from both board and graph views.
- Integrated delete options for dependencies in the graph view, enhancing user interaction.
- Updated ancestor context section to clarify the role of parent tasks in task descriptions.
- Improved layout handling in graph view to preserve node positions during updates.
This update enhances task management capabilities and improves user experience in the graph view.
- Added ErrorState component to display error messages with retry functionality, enhancing user experience during issue loading failures.
- Implemented LoadingState component to provide visual feedback while issues are being fetched, improving the overall responsiveness of the GitHubIssuesView.
- Refactored GitHubIssuesView to utilize the new components, streamlining error and loading handling logic.
- Introduced refs for selected issue and validation dialog state to prevent unnecessary re-subscribing on state changes.
- Added cleanup logic to ensure proper handling of asynchronous operations during component unmounting.
- Enhanced error handling in validation loading functions to only log errors if the component is still mounted, improving reliability.
- Simplified the validation staleness check by introducing a dedicated variable for stale validation status.
- Enhanced the conditions for unviewed and viewed validation indicators, improving user feedback on validation status.
- Added a visual indicator for viewed validations, enhancing the user interface and experience.
- Added support for default AI profile retrieval and integration into task creation, improving user experience in task management.
- Implemented current branch detection based on selected worktree, ensuring accurate context for issue handling.
- Updated fetchIssues function dependencies to include new profile and branch data, enhancing task creation logic.
- Introduced a new ConfirmDialog component for user confirmation prompts.
- Integrated ConfirmDialog into GitHubIssuesView to confirm re-validation of issues, enhancing user interaction and decision-making.
- Updated handleValidateIssue function to support re-validation options, improving flexibility in issue validation handling.
- Added a guard to ensure the unviewed count is only updated if the current project matches the reference, preventing potential race conditions during state updates.
- Introduced comprehensive unit tests for the validation storage module, covering functions such as writeValidation, readValidation, getAllValidations, deleteValidation, and others.
- Implemented tests to ensure correct behavior for validation creation, retrieval, deletion, and freshness checks.
- Enhanced test coverage for edge cases, including handling of non-existent validations and directory structure validation.
