- 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
