Lohnt sich dein eigenes Vapi?

Build me a focused, self-hosted alternative to Vapi for one inbound support number.
Requirements:

- Use Python 3.12 and livekit-agents~=1.5 with one named AgentServer worker.
  Use direct provider plugins, not LiveKit Inference or another managed agent host.
- Run LiveKit Server, Redis, and LiveKit SIP with Docker Compose on one Ubuntu VM.
  Put Caddy in front of HTTPS/WSS; expose only the documented SIP and UDP media ports.
- Provision one Telnyx DID and credential-authenticated SIP trunk. Include checked-in
  LiveKit inbound-trunk and dispatch-rule JSON that sends calls to support-agent.
- Build an AgentSession with Silero VAD, Deepgram Nova-3 STT, gpt-5-mini through
  the OpenAI plugin, and Cartesia Sonic-3 TTS. Load every secret from .env.
- Give the agent one narrow support prompt, interruption handling, and two tools:
  look up an order in SQLite and save a callback request after caller confirmation.
- Persist call id, timestamps, transcript, tool results, and outcome to SQLite.
  Add structured JSON logs and /healthz; recording is off by default.
- Include unit tests for both tools and scripted agent tests for lookup, refusal to
  invent an order, callback confirmation, and a caller interruption.
- Provide make setup, make dev, make smoke, and docker compose up -d commands.
  The smoke test must work in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, dispatch, provider-key, and test-call
  steps, plus common one-way-audio and SIP authentication checks.
- The cost section must say the Vapi fee is removed, while the DID, SIP minutes,
  model usage, VM, failed calls, monitoring, and operator time remain. Link the
  source-backed calculator at https://voice.oss.codes for changing rates.
- Out of scope: outbound campaigns, a multi-tenant dashboard, squads, billing,
  automatic provider failover, call recording, compliance claims, and high availability.