- Titlebar only keeps toggle and close buttons
- Toggle button wider to use freed space
- Nav bar opens as popup below terminal (no internal space change)
- Added Start/Restart agent buttons to TerminalNavButtons
- Backdrop blur on popup bar
- Extract nav buttons (MCP, Claude, Continue, Resume, Clear, Refresh, keys, arrows, scroll) into TerminalNavButtons.vue
- Add toggle button in AgentTerminal titlebar to show/hide nav bar
- Add sendRaw() to useAgentTerminal for raw PTY input (no \r append)
- Add touch drag support for AgentTerminal on mobile
- Skip auto-focus on small screens to prevent virtual keyboard popup
- Connect WebSocket BEFORE loading history to catch real-time permissions
- loadHistory() now preserves unresolved intervention cards
- loadPendingPermissions() runs AFTER loadHistory() to avoid race condition
PromptBar now auto-opens when a permission request arrives and it's hidden.
Permission cards show rich contextual info: tool badge, description, code
blocks for Bash, diff preview for Edit, file paths for Write, and icons
on Allow/Deny buttons.
- Broadcast PermissionRequest hook as claude-permission WS event
- Fix dedup bug where undefined requestId blocked all permission cards
- Add sendInput() to AgentTerminal for char-by-char PTY responses
- Make AskUserQuestion options clickable (sends option number to PTY)
- Add Approve/Reject buttons for ExitPlanMode plan cards
- Permission Allow/Deny now sends y/n to PTY instead of broken HTTP call
- Add :key to PromptBar to force remount on agent switch, fixing shared terminal session bug
- Raise AgentTerminal z-index above PromptBar backdrop so floating terminal is visible/clickable
- Send prompt text char-by-char (15ms delay) matching FloatingVoice pattern for Claude Code compat
- Guard xterm dispose against unloaded addons to prevent errors on agent switch
- Widen PromptBar panel from 360px to 420px to fit all ChatInput buttons
Extract voice recording logic from FloatingVoice.vue into useVoiceCapture
composable. TranscriptCard now does real recording instead of mock typing.
InputSettings allows voice mode toggle (WebSpeech/Whisper GPU), mic
selection, and debug audio playback. ChatInput gets a settings gear button.
Long-press on FloatBubble shows a floating TranscriptCard (push-to-talk)
instead of opening the full PromptBar. Release stops recording after a
500ms buffer. Click still opens PromptBar normally.
Parallel MediaRecorder captures raw audio in WebSpeech mode for DB save
and debug playback. Transient errors (no-speech) no longer kill sessions.
Touch selection prevention on FloatBubble for tablets.
- Add transcript-engine service that parses Claude Code JSONL transcripts
with session listing, message extraction, token/stats analysis, and caching
- Add transcript REST routes (sessions list, latest, by session ID, section filtering)
- Rewrite ConversationHistory to fetch from /api/transcript/* instead of mock data
- Add session pills for switching between conversation sessions
- Add stats bar footer with model, duration, tokens, and tool count
- Add TranscriptSession/TranscriptMessage types, ChatInput, InputSettings,
PromptBar updates, TranscriptCard, and useVoiceCapture composable
Replace hardcoded PowerShell status hooks with stdin-forwarding hooks
that send full Claude Code hook data (tool_input, tool_response, prompt,
session_id, model, etc.) to /api/claude-hook endpoint.
- PowerShell hooks read stdin JSON and POST to /api/claude-hook
- Server derives status for backward-compat FAB animations
- Server extracts assistant_response from transcript on Stop events
- New /api/claude-permission endpoint with Promise-based allow/deny flow
- HookNotifications.vue: toast system showing session, prompt, tool use,
tool results, notifications, and final assistant response
- WebSocket broadcast for claude-hook and claude-permission message types
- Add StatusTree component with collapsible directory hierarchy for staged/unstaged/untracked files
- Replace flat file lists in GitPage with tree view showing file type icons and git status badges
- Add AgentBar arc dock with per-agent terminal frame and voice modal
- Update ejecutor settings with hooks for claude-status reporting
- Add ui.json configs for Main (purple) and Ejecutor (red) agents
- AgentBar: fused arc-shaped dock at bottom with dynamic glow
- Quick press opens styled terminal frame mockup
- Hold opens voice modal with Web Speech API streaming transcription
- Responsive: full-width mobile, max-width on tablet/desktop/4K
- Agents API: serve uiConfig from ui.json in agent directories
- Agents page: route, store, toolbar integration
- Auto-save rendered Vue components to DB on render_vue_component
- Soft delete (archive) instead of hard delete for components
- Tags support for component categorization
- Gallery limited to 10 most recent items per section
- Upsert with ON CONFLICT for component saves
- PUT endpoint for partial component updates
- Collapsible toolbar with animated toggle button
- Window Controls Overlay support for PWA titlebar
- Compact header mode (32px) with hidden dot toggle
- Dynamic theme-color meta sync for Windows titlebar
Replace the empty dynamic canvas placeholder with a gallery showing
saved canvases, snapshots and Vue components. Users can create new
canvases, restore snapshots, load components, and manage canvas
toolbar/archive settings from the gallery.
- Backend: soft delete (archive) instead of hard delete, status column
- Frontend: CanvasGallery component with grid, search, settings popover
- Show canvas name in global header when viewing a project canvas
- Remove ProjectsPage (replaced by gallery), clean all references
- MCP tools: project category available on canvas page, update handlers
Server is now source of truth for autoRequest. When a client enables it,
all other clients lose it. Broadcast includes autoRequest per client,
frontend syncs from server state on each torch-update.
- Named clients persisted in localStorage, editable from dropdown
- Auto-request: clients can auto-receive torch when no holder exists
- Early torch init in App.vue (fires before WebMCP, awaited later)
- Deferred torch connection in toolRegistry for race condition safety
- TorchButton rewritten as dropdown with name editor, toggle, client list
- Server broadcasts client names, supports update-name message
- MCP tool handlers display client names
- Add WindowContainer.vue with Liquid Glass styling, drag, resize, close
- Add windows store for managing window state (position, size, z-index)
- Modify dynamicComponents.ts to wrap Vue components in floating windows
- Add MCP tools: move_window, resize_window, close_window, list_windows
- Add isolated Claude profiles (ejecutor, nucleo000) with versioned configs
- Consolidate git and torch WebSocket servers on port 4105
- Create separate handlers for git and torch in handlers/ directory
- Combine TorchButton with connection status into single pill button
- Remove StatusBar (now redundant with TorchButton)
- Remove auto-assign torch on register/disconnect
- Remove auto-connect to MCP on page load
- Connection only happens when user explicitly requests torch
- Add TorchButton component to header (replaces dropdowns)
- Add torch store for managing torch state
- Add torch service for requesting/releasing torch
- Add torch event handlers in WebMCP service
- Remove ComponentsDropdown and ToolsDropdown from header
The torch system allows controlling which browser receives
MCP tool calls when multiple browsers are connected.
Requires WebMCP library update to fully function.
- 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 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
- 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 /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
