feat: Add Whisper GPU speech-to-text with progressive transcription

- 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

server/index.ts

@@ -1,7 +1,6 @@
 import { PORT_HTTP, WORKING_DIR } from './config'
 import { initDatabase } from './db'
 import { handleRequest } from './routes'
-import { startTerminalServer } from './services/terminal'
 
 // Initialize database
 initDatabase()
@@ -12,18 +11,10 @@ Bun.serve({
   fetch: handleRequest
 })
 
-console.log(`[HTTP] API running at http://localhost:${PORT_HTTP}`)
-
-// Start Terminal WebSocket server
-startTerminalServer()
-
 // Startup summary
 console.log('')
 console.log('='.repeat(50))
-console.log('Agent UI Server started')
+console.log('Agent UI API Server (hot-reload enabled)')
 console.log(`  API: http://localhost:${PORT_HTTP}`)
-console.log(`  Terminal: ws://localhost:4103`)
 console.log(`  Working Dir: ${WORKING_DIR}`)
-console.log('')
-console.log('WebMCP starts separately with Claude Code MCP')
 console.log('='.repeat(50))