- Added `vectordb` as a dependency in `package.json`.
- Implemented `embedText` function in `src/main/ai/embeddings.ts` to handle text embeddings using GitHub Copilot OAuth token or OpenAI token.
- Created `vectordb.ts` for managing LanceDB connection and embedding notes with upsert strategy.
- Updated `index.ts` to initialize vector database and migrate existing notes on app ready.
- Modified `router/index.ts` to fire-and-forget embedding calls on note creation and updates.
- Enhanced `progress.txt` with detailed implementation notes and learnings regarding the integration.
- Added AIChatPanel component with context header, user and AI message handling.
- Integrated streaming responses via IPC and error handling for chat mutations.
- Enhanced user experience with input handling and auto-scrolling features.
- Updated AppShell to derive AI chat context from the current route.
- Introduced ScrollArea component for better scrolling behavior in various dialogs.
- Added support for Tailwind typography and improved global styles.
- Updated project and task dialogs to utilize ScrollArea for better UX.
- Added @github/copilot-sdk and related dependencies for GitHub Copilot integration.
- Implemented ChatCopilot adapter for LangChain compatibility.
- Created LLM factory to return provider-specific models (OpenAI, Anthropic, Copilot).
- Developed Orchestrator agent using LangGraph for intent routing and context assembly.
- Enhanced IPC communication for streaming AI responses to the renderer.
- Updated progress documentation with implementation details and learnings.
- Introduced a new `task_comments` table in the database schema.
- Implemented task comments API endpoints for listing, creating, and deleting comments.
- Enhanced the task detail dialog to display comments and allow users to add new comments.
- Updated task row component to handle click events for viewing task details.
- Added a theme provider to manage light/dark mode across the application.
- Refactored Milkdown editor to use Crepe for improved markdown editing experience.
- Updated global styles to accommodate new editor and theme changes.
- Enhanced task filtering and sorting functionality in the tasks page.
- Added Milkdown dependencies: @milkdown/kit, @milkdown/react, @milkdown/theme-nord.
- Implemented MilkdownEditor component for rich text editing in notes.
- Updated /notes/$noteId route to include editable title and auto-saving functionality.
- Enhanced UI with loading states, saving indicators, and delete confirmation dialog.
- Applied Milkdown-specific CSS overrides for consistent theming and styling.
- Improved note update logic with debounced saving and cleanup on unmount.
- Implemented a Gantt timeline using GanttChart component scoped to project checkpoints.
- Added functionality to create and manage checkpoints with AddCheckpointDialog.
- Introduced EditCheckpointDialog for editing existing checkpoints.
- Created a notes section displaying a list of notes with the ability to add new notes.
- Updated routing to include notes detail page.
- Enhanced GanttChart with context menu for editing and deleting checkpoints.
- Improved UI components for better user experience.
- Established database schema with five tables using better-sqlite3 and drizzle-orm
- Developed tRPC routers for clients, projects, tasks, checkpoints, and notes with full CRUD operations
- Integrated lazy initialization for electron-store to manage app settings
- Enhanced UI components for task management, including NewTaskDialog and GanttChart
- Implemented search and filter functionalities across various views
- Ensured type safety and strict TypeScript configurations throughout the codebase
- Documented learnings and best practices for future iterations in progress.txt
- Created prd.json with detailed user stories, acceptance criteria, and implementation notes for the Adiuva project.
- Updated progress.txt to reflect recent implementations of routers for checkpoints and notes, along with learnings for future iterations.
- Modified ralph.sh to change the default tool from "amp" to "claude" for improved compatibility.
- Implemented Input component for user input fields.
- Created Separator component for visual separation in UI.
- Added Sheet component for modal-like overlays with customizable content.
- Developed Sidebar component with collapsible functionality and mobile responsiveness.
- Introduced Skeleton component for loading placeholders.
- Implemented Tooltip component for contextual hints.
- Updated global CSS variables for sidebar theming.
- Added useIsMobile hook for responsive design handling.
- Modified projects route to include ProjectSidebar.
- Enhanced Tailwind CSS configuration for improved styling.
- Updated Vite preload configuration for custom entry file naming.
feat: implement ralph.sh for long-running AI agent loop with tool selection and iteration control
feat: create PRD for Adiuva MVP implementation detailing goals, user stories, and technical considerations
