- Create useTerminalRenderer.ts with all xterm.js logic
- Support custom theme, fontSize, fontFamily options
- Add handleReplay() for proper visibility handling
- Add getBufferContent() for copying terminal content
- Refactor FloatingTerminal.vue to use composable
- Refactor TerminalPage.vue to use composable
- Server: Add request-replay message type for on-demand replay
- Server: Remove auto-replay on connect (client requests when ready)
- Fix xterm.js rendering issues with hidden containers (v-show)
- Add file watcher on .git directory in terminal server
- Broadcast git-change events to connected clients
- Frontend auto-refreshes when changes detected
- Visual indicator shows realtime connection status
Add Files tab with browsable project structure and file content viewer.
New components: ProjectTree for navigation, FileViewer for content display.
Backend endpoints: /api/git/tree and /api/git/file.
- Center both modals with dark backdrop and blur effect
- Make voice modal larger (420px) with bigger record button
- Make response modal larger (540px) with bigger text (18px)
- Remove auto-dismiss from bubbles - manual dismiss only
- Add backdrop click to close response modal
- Remove unused bottom sheet code from FloatingVoice
- Add touch protection CSS to prevent text selection
- Clean up mobile-specific variables no longer needed
- Hold FAB to open panel and start recording immediately
- Release to stop recording and send after 1s buffer
- Orange pulsing animation when PTT active
- PTT also works on record button inside modal
- Added stopRecordingAndSend exposed method
- Add auto-reconnect when WebSocket disconnects (up to 10 attempts)
- Add disconnected/connecting overlay with visual feedback
- Add scroll buttons (up/down/end) for mobile
- Add refresh button to reconnect or redraw terminal
- Make all virtual keys bigger and more clickable
- Enable touch scrolling in terminal viewport
- Fix Whisper connection: don't connect when server not ready
Replace ConnectionDropdown with debug console button that intercepts
console.log/warn/error and displays them in an overlay panel. Allows
copying logs for debugging on mobile devices without dev tools.
- Create traefik/agent-ui.yml with full routing config for domain z590.nucleoriofrio.com
- Add frontend/src/config/endpoints.ts for automatic HTTP/HTTPS detection
- Update all hardcoded localhost URLs to use relative paths
- WebSocket connections auto-detect wss:// vs ws:// based on page protocol
- Configure path-based WebSocket routing (/ws/terminal, /ws/mcp, /ws/status, /ws/whisper)
- Add commented IP whitelist middleware for future security
- Add Nucleo atom logo with animated orbiting electrons
- Redesign FAB with glassmorphism effect and purple gradient
- Add connection indicator (green dot) when terminal is open
- Update FloatingTerminal header with Nucleo branding
- Add PermissionRequest hook support with red alert animation
- Document Nucleo in README with visual states table
- Create official Nucleo logo SVG in docs/
- Add multiple hook-driven animations for FAB (processing, reading, writing, subagent, sessionStart, notification)
- Create claude-status.ts route to handle status updates from Claude Code hooks
- Broadcast status via WebSocket to all connected clients
- Processing (UserPromptSubmit→Stop): orange pulsing dots
- Reading (Read/Glob/Grep): cyan eye icon with scan animation
- Writing (Edit/Write): green pencil icon with pulse
- Subagent: purple orbital ring animation
- SessionStart: green wake-up ripple effect (3s)
- Notification: yellow bounce animation (2s)
- Tool flash: quick white flash on any tool use
- Add /api/recordings endpoint with full CRUD operations
- Create voice_recordings SQLite table for metadata
- Save audio files to server/recordings/ as .webm
- Store transcription, duration, microphone name, file size
- Auto-save on each Whisper recording completion
- Add microphone device enumeration and selector dropdown
- Show current microphone name with click-to-change UI
- Microphone selection only available with Whisper GPU mode
- Add audio playback button to replay last recorded audio for debugging
- Improve dropdown animations with staggered item transitions
- Fix FloatingTerminal token request to type character by character
- Make server startup async to avoid Bun's 10s timeout
- Add frontend polling to detect when server is ready
- Use PowerShell Get-NetTCPConnection for reliable port detection
- Add starting state to prevent multiple simultaneous starts
- Reduce verbose logging, keep only essential info
- Add dev-dist and nul to gitignore
- Text appears letter by letter (15-25ms per character)
- Blinking cursor shows while text is animating
- Animation continues from last position for new chunks
- Smooth visual feedback for transcription progress
- Add ffmpeg conversion from WebM/Opus to WAV (16kHz mono PCM)
- Optimize transcription parameters (VAD, temperature, beam_size)
- Add Honduras Spanish context prompt with local expressions
- Fix chunk accumulation display in voice panel
- Add 1.5s recording buffer after releasing Ctrl+Space
- Skip small audio chunks (<5KB) that cause ffmpeg errors
- Use large-v3 model for better accuracy
- Add faster-whisper Python server for GPU-accelerated transcription
- Support dual mode: Web Speech API or Whisper GPU (toggleable)
- Progressive transcription every 3 seconds while recording
- Separate terminal server process (stable during hot-reload)
- Add Ctrl+V paste and Ctrl+C copy support in FloatingTerminal
- Add MCP tools: whisper_start, whisper_stop, whisper_toggle, whisper_status
- Update package.json with separate api/terminal/frontend processes
- Add page_refresh tool to reload the page via MCP
- Change push-to-talk shortcut from Ctrl+S to Ctrl+Space
- Use capture phase for keyboard events to intercept before terminal
- Add FloatingVoice component with Web Speech API transcription
- Each component has its own independent WebSocket session
- Voice panel connects on open, disconnects on close
- Sends transcribed text to Claude Code with Enter key
Add a floating response panel that allows the agent to display messages
directly in the UI instead of through the terminal. Includes support for
info, success, warning, and error message types with auto-dismiss.
- Slim, transparent Aero Glass design with backdrop blur
- Draggable window from titlebar
- Resizable from corner handle
- Ctrl+E toggle to open at cursor position
- Remove minimize functionality (close returns to sidebar button)
- Add PWA dev-dist files and lock files
- Configure VitePWA with manifest, icons and service worker
- Add PwaInstallBanner component for install prompt in header
- Enable CORS for z590.interno.com access
- Use dynamic hostname for terminal WebSocket connection
- Add generate-icons script with sharp for PWA icons
- Fix theme-color to match header background
- Add ToolsPage for managing MCP tools activation and persistence
- Centralize all tool handlers in services/tools/handlers/
- toolRegistry.ts is now the single source of truth for tool state
- Add tools store for pinned tools (persisted in localStorage)
- Tools can be pinned to stay active across page navigation
- Remove old individual tool files, replaced by centralized handlers
- Add cell click-to-copy with visual feedback
- Add text filter to search across all columns
- Add column visibility toggle (click schema columns to show/hide)
- Add row selection with checkboxes
- Copy All respects visible columns and selected rows
- Auto-reset selections when changing table/page/query
Split monolithic index.ts (~1400 lines) into modular structure:
- config.ts: Server configuration and constants
- db/: Database initialization, migrations, and seeds
- routes/: API handlers by domain (themes, canvas, components, etc.)
- services/: Terminal WebSocket server
- utils/: CORS helpers
Entry point now only coordinates initialization.
- Add token API endpoint to server for storing/retrieving pending tokens
- Add token polling in frontend to auto-detect and connect with tokens
- Add xterm dependencies for terminal functionality
- Add terminal page support in toolRegistry
- Server keeps PTY sessions alive on client disconnect
- Output buffer replays history on reconnect
- FloatingTerminal component accessible from any page
- Responsive: floating window on desktop, fullscreen on mobile
- macOS-style header with traffic light buttons
Separates dynamic canvas from homepage to avoid conflicts with default canvas.
- Changed route from /dynamic-canvas to /dynamic/canvas
- Added toolbar button for quick access to dynamic canvas
- Updated navigate_to tool with dynamic-canvas option
- Add /source page with file explorer and code viewer
- Connect to Gitea API for repository browsing
- Implement MCP tools: get_repo_info, list_repo_files, read_repo_file, search_repo_code
- Default to nucleo000/agent-ui repository
- Support branch switching and file search
- Add project_canvas and canvas_components tables for persistent canvas storage
- Add ProjectCanvas store with full CRUD operations
- Add ProjectCanvasPage for rendering saved canvas with components
- Add ProjectsPage for managing canvas list (create, clone, delete)
- Add HomePage that loads default canvas or falls back to dynamic canvas
- Add toolbar support for displaying canvas as pages with custom icons
- Add component usage validation to prevent deletion of components in use
- Add MCP tools for canvas management (list, create, update, delete, clone)
- Update router with /canvas/:id and /projects routes
- Update Toolbar to show dynamic canvas pages from database
Backend:
- Add PUT /api/themes/:id endpoint for updating existing themes
Store:
- Add updateTheme method to theme store
MCP:
- Add update_theme tool to modify name, description, or save current variables
UI:
- Add edit button to ThemeListItem (custom themes only)
- Add edit modal with name and description fields
- Support editing from both desktop sidebar and mobile dropdown
