feat: add initial Hold Slayer AI telephony gateway implementation

Complete project scaffolding and core implementation of an AI-powered
telephony system that calls companies, navigates IVR menus, waits on
hold, and transfers to the user when a human answers.

Key components:
- FastAPI server with REST API, WebSocket, and MCP (SSE) interfaces
- SIP/VoIP call management via PJSUA2 with RTP audio streaming
- LLM-powered IVR navigation using OpenAI/Anthropic with tool calling
- Hold detection service combining audio analysis and silence detection
- Real-time STT (Whisper/Deepgram) and TTS (OpenAI/Piper) pipelines
- Call recording with per-channel and mixed audio capture
- Event bus (asyncio pub/sub) for real-time client updates
- Web dashboard with live call monitoring
- SQLite persistence via SQLAlchemy with call history and analytics
- Notification support (email, SMS, webhook, desktop)
- Docker Compose deployment with Opal VoIP and Opal Media containers
- Comprehensive test suite with unit, integration, and E2E tests
- Simplified .gitignore and full project documentation in README

.env.example

@@ -0,0 +1,62 @@
+# ============================================================
+# Hold Slayer Gateway Configuration
+# ============================================================
+# Copy to .env and fill in your values
+
+# --- Database ---
+DATABASE_URL=postgresql+asyncpg://holdslayer:changeme@localhost:5432/holdslayer
+
+# --- SIP Trunk ---
+SIP_TRUNK_HOST=sip.yourprovider.com
+SIP_TRUNK_PORT=5060
+SIP_TRUNK_USERNAME=your_sip_username
+SIP_TRUNK_PASSWORD=your_sip_password
+SIP_TRUNK_TRANSPORT=udp
+# Your phone number on the trunk (E.164)
+SIP_TRUNK_DID=+15551234567
+
+# --- Gateway SIP Listener ---
+# Port for devices (softphones/hardphones) to register to
+GATEWAY_SIP_HOST=0.0.0.0
+GATEWAY_SIP_PORT=5080
+GATEWAY_SIP_DOMAIN=gateway.helu.ca
+
+# --- Speaches STT ---
+SPEACHES_URL=http://perseus.helu.ca:22070
+SPEACHES_PROD_URL=http://pan.helu.ca:22070
+SPEACHES_MODEL=whisper-large-v3
+
+# --- Audio Classifier ---
+# Thresholds for hold music detection (0.0 - 1.0)
+CLASSIFIER_MUSIC_THRESHOLD=0.7
+CLASSIFIER_SPEECH_THRESHOLD=0.6
+CLASSIFIER_SILENCE_THRESHOLD=0.85
+# Analysis window in seconds
+CLASSIFIER_WINDOW_SECONDS=3.0
+
+# --- LLM (OpenAI-compatible API) ---
+# Ollama, LM Studio, vLLM, or OpenAI — any OpenAI-compatible endpoint
+LLM_BASE_URL=http://localhost:11434/v1
+LLM_MODEL=llama3
+LLM_API_KEY=not-needed
+LLM_TIMEOUT=30.0
+LLM_MAX_TOKENS=1024
+LLM_TEMPERATURE=0.3
+
+# --- Hold Slayer ---
+# Default device to transfer to when human detected
+DEFAULT_TRANSFER_DEVICE=sip_phone
+# Max hold time before giving up (seconds)
+MAX_HOLD_TIME=7200
+# How often to check classification while on hold (seconds)
+HOLD_CHECK_INTERVAL=2.0
+
+# --- Notifications ---
+# SMS notification number (optional)
+NOTIFY_SMS_NUMBER=+15559876543
+
+# --- Server ---
+HOST=0.0.0.0
+PORT=8000
+DEBUG=true
+LOG_LEVEL=info