feat(AppShell): improve token storage message styling for better visibility
feat(ProjectDetail): implement skeleton loading state for project details
fix(ProjectSidebar): refactor variable declaration for clarity
style(PriorityBadge): enhance priority badge colors for better contrast
refactor(TaskRow): simplify className handling with utility function
fix(TasksPage): replace loader icon with clock icon for in-progress tasks
feat(TimelinePage): enhance empty state with descriptive messaging and icon
Register AI sections across all content pages with dual-anchor scroll
tracking, cross-page navigation via [SECTION:xxx] tags, and right-margin
positioning for the notes editor.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add FLIP animation so the floating chat visually morphs into a newly-created
TaskRow when the AI creates a task. Uses Framer Motion's shared layoutId
across FloatingChat and TaskRow, with LayoutGroup wrapping the app shell.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a new ai:action IPC channel so the renderer can react to AI tool
side-effects (task creation, checkpoint/task suggestions). Also mark
AI-created tasks with isAiSuggested: 1 in both project and global
add_task tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Create the floating AI chat popup rendered via portal to document.body.
Uses useAIChat for chat logic, useFloatingChat for position/state,
Framer Motion for enter/exit animations, and pointer-event dragging.
Includes: close on Escape, close on route change, auto-scroll,
auto-focus, window resize clamping, and compact message rendering.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Refactor AIChatPanel to consume the existing useAIChat hook instead of
managing chat state inline. Removes duplicate ChatMessage interface,
inline state (messages, input, isStreaming, streamingContent), and the
65-line handleSend callback, replacing them with a single useAIChat()
call and a thin briefLoading guard wrapper.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Implemented useAIChat hook to handle chat messages, input state, and streaming responses.
- Added types for ChatMessage and ChatContext to ensure type safety.
- Integrated TRPC mutation for sending messages and handling responses.
- Included functionality for clearing messages and managing streaming content.
- Created a new settings.local.json file to enable MCP servers with "shadcn".
- Updated .mcp.json to change the command execution from "npx" to "cmd" for better compatibility.
- 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.
