- Implemented IPC handlers for checking Codex CLI installation status, retrieving available models, and checking provider statuses.
- Enhanced the SettingsView to include OpenAI API key management and connection testing.
- Updated the feature executor to support multiple model providers (Claude and Codex), allowing for improved flexibility in feature execution.
- Introduced utility functions to determine model types and support for thinking controls.
This update enhances the application's capabilities by integrating Codex CLI support and improving model management, providing users with a more robust experience.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
- Added a new service to detect the installation status of Claude Code CLI, providing users with installation recommendations and commands.
- Integrated CLI detection into the SettingsView to inform users about the CLI status and its benefits for ultrathink tasks.
- Enhanced feature creation and editing dialogs to allow users to select from multiple models (Haiku, Sonnet, Opus) and specify thinking levels (None, Low, Medium, High, Ultrathink).
- Updated the feature executor to utilize the selected model and thinking configuration during task execution, improving flexibility and performance.
This update enhances user experience by providing clearer options for model selection and ensuring optimal performance with the Claude CLI.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
- Added a reusable Markdown component to render markdown content with styled typography for dark mode.
- Updated KanbanCard to utilize the new Markdown component for displaying feature summaries, improving readability and presentation.
- Included the `react-markdown` library as a dependency for markdown parsing.
Modified: package.json, package-lock.json, markdown.tsx, kanban-card.tsx
Enhance Kanban cards to show comprehensive feature information:
- Add feature summary field to display completed work details
- Show agent context info (model, progress, tasks) on cards
- Display tool usage and token consumption metrics
- Add expandable summary dialog for detailed view
- Update prompts to require summary when marking features complete
- Improve UI for waiting_approval and verified states
Modified: kanban-card.tsx, board-view.tsx, feature-loader.js,
mcp-server-factory.js, prompt-builder.js, app-store.ts
Created: agent-context-parser.ts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
- Implemented asynchronous follow-up work in AutoModeService to allow immediate API response, enabling smoother user experience.
- Updated BoardView to handle follow-up prompts more efficiently, including state management and success notifications.
- Adjusted mock AutoMode API to simulate background processing for follow-up tasks, aligning with real implementation behavior.
These changes streamline the workflow for sending follow-up prompts and improve the responsiveness of the UI.
- Added functionality to allow users to send follow-up prompts for features in the waiting_approval status, enabling continued work with additional instructions.
- Implemented a commit feature that allows users to mark waiting_approval features as verified and commit changes directly.
- Updated the UI to include buttons for follow-up and commit actions on Kanban cards and integrated dialogs for user interaction.
- Enhanced the feature loader and executor to handle the new status and actions appropriately.
This update improves the workflow for managing features that require manual review and enhances user experience in the auto mode.
Add a parsed log viewer to the agent output modal that groups and colors
log entries by type (tool calls, phases, errors, success messages, etc.)
similar to Coolify logs. Includes:
- New log-parser.ts utility for parsing agent output into structured entries
- New LogViewer component with collapsible entries and colored badges
- Toggle between Parsed and Raw view modes in the modal header
- Type-specific colors (amber for tools, cyan for phases, red for errors)
- Expand/Collapse all buttons for better navigation
- JSON content detection and formatting within entries
Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add ability to drag and drop images into the description section when creating
new Kanban cards. Images are saved to a temp directory and their paths are stored
with the feature for agent context.
- Create DescriptionImageDropZone component with drag/drop support
- Integrate with Add Feature dialog in board-view
- Add FeatureImagePath interface to track temp file paths
- Update saveFeatures to persist imagePaths
- Add saveImageToTemp to mock electron API
- Add test utilities for image upload testing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added a new keyboard shortcut 'P' to open the project picker dropdown.
- Implemented functionality to select projects using number keys, allowing users to quickly switch between projects.
- Updated the feature list to include a new feature for project selection via keyboard shortcuts.
- Removed obsolete coding_prompt.md and added initializer_prompt.md for better session management.
- Introduced context management for features, enabling reading, writing, and deleting context files.
- Updated package dependencies to include @radix-ui/react-checkbox for enhanced UI components.
This commit enhances user experience by streamlining project selection and improves the overall feature management process.
🤖 Generated with Claude Code
When clicking the trash icon to delete a feature card, users now see a
confirmation dialog asking them to confirm the deletion. This prevents
accidental deletions and provides a clear cancel option.
- Added Dialog component with confirm/cancel buttons to kanban-card
- Updated mock electron API to support test feature injection via __mockFeatures
- Added test utilities for delete confirmation dialog interactions
- Fixed test infrastructure to properly load mock features
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Categories are now saved to a categories.json file in the .automaker
directory. This ensures categories persist even when all feature cards
are deleted. The category autocomplete now shows suggestions from both
existing features AND the persisted categories file.
- Add persistedCategories state and load/save functions in board-view
- Merge persisted categories with feature categories for suggestions
- Auto-save categories when adding or editing features
- Update mock Electron API to handle categories.json file
Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Removed obsolete feature from feature_list.json related to context file deletion.
- Added new features for keyboard shortcuts in Kanban and context management.
- Introduced project initialization utilities to create necessary .automaker directory structure and files when opening a new project.
- Updated the AgentOutputModal and other components to reference the new agents-context directory.
- Enhanced Playwright tests for context file management and project initialization.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When an agent marks a feature as verified, the context file in
.automaker/agents-context/{featureId}.md is now automatically deleted.
Changes:
- Updated mock implementation in electron.ts to delete context files
when simulateAutoModeLoop completes with verified status
- Added setupMockProjectWithContextFile utility function to tests/utils.ts
- Updated feature_list.json to mark feature as verified
The real implementation was already present in auto-mode-service.js:
- deleteContextFile() method removes the context file
- updateFeatureStatus() calls deleteContextFile when status="verified"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added Context view with file list sidebar and text/image editor
- Added Context navigation item to sidebar
- Added deleteFile API method to Electron IPC
- Updated coding_prompt.md to include Step 1.5 for loading context files
- Updated mock Electron API to properly handle context directory
- Added test utilities for context view navigation
Features:
- Left panel with list of all context files
- Text editor for editing .md, .txt, and other text files
- Image preview for .png, .jpg, .gif, and other image files
- Add new text or image files via dialog
- Delete files with confirmation dialog
- Drag and drop file upload support
- Auto-save detection with Save button
All Playwright tests passing (9/9)
Deleted test file after verification
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated references to `app_spec.txt` and `feature_list.json` in app_spec.txt to include the correct path.
- Enhanced coding_prompt.md by incorporating testing utilities for better test management and readability.
- Added new utility functions in tests/utils.ts to streamline test interactions.
This commit aims to improve documentation accuracy and maintainability of testing practices.
