Migrate a Text Agent to a Nova Sonic Voice Agent

This skill converts any text-based agent into a real-time voice agent using Strands BidiAgent with Amazon Nova Sonic. The migration is broken into two layers:

1. Frontend — Browser client that captures mic audio and plays back voice responses over WebSocket
2. Orchestrator — FastAPI + BidiAgent server that takes the text agent's system prompt and tools and runs them as a bidirectional audio streaming agent

┌──────────────┐    ┌──────────────────────────────────────────┐
│   Frontend   │    │            Orchestrator                  │
│              │    │                                          │
│  Browser Mic  ─────▶ FastAPI /ws ──▶ BidiAgent ──▶ Nova Sonic│
│              │    │                     │                    │
│  Speaker ◀────────── WebSocket ◀── BidiAgent ◀── Nova Sonic  │
│              │    │                     │                    │
└──────────────┘    │              Tools (Strands @tool)       │
                    └──────────────────────────────────────────┘