feat: complete phase 1 -- core framework with chat loop, agents, and React UI

Backend:
- FastAPI WebSocket /ws endpoint with streaming via LangGraph astream
- LangGraph Supervisor connecting 3 mock agents (order_lookup, order_actions, fallback)
- YAML Agent Registry with Pydantic validation and immutable configs
- PostgresSaver checkpoint persistence via langgraph-checkpoint-postgres
- Session TTL with 30-min sliding window and interrupt extension
- LLM provider abstraction (Anthropic/OpenAI/Google)
- Token usage + cost tracking callback handler
- Input validation: message size cap, thread_id format, content length
- Security: no hardcoded defaults, startup API key validation, no input reflection

Frontend:
- React 19 + TypeScript + Vite chat UI
- WebSocket hook with reconnect + exponential backoff
- Streaming token display with agent attribution
- Interrupt approval/reject UI for write operations
- Collapsible tool call viewer

Testing:
- 87 unit tests, 87% coverage (exceeds 80% requirement)
- Ruff lint + format clean

Infrastructure:
- Docker Compose (PostgreSQL 16 + backend)
- pyproject.toml with full dependency management

docker-compose.yml

@@ -0,0 +1,39 @@
+services:
+  postgres:
+    image: postgres:16
+    environment:
+      POSTGRES_DB: smart_support
+      POSTGRES_USER: smart_support
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-dev_password}
+    ports:
+      - "5432:5432"
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U smart_support -d smart_support"]
+      interval: 5s
+      timeout: 3s
+      retries: 5
+
+  backend:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    ports:
+      - "8000:8000"
+    environment:
+      DATABASE_URL: postgresql://smart_support:${POSTGRES_PASSWORD:-dev_password}@postgres:5432/smart_support
+      LLM_PROVIDER: ${LLM_PROVIDER:-anthropic}
+      LLM_MODEL: ${LLM_MODEL:-claude-sonnet-4-6}
+      ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
+      OPENAI_API_KEY: ${OPENAI_API_KEY:-}
+      GOOGLE_API_KEY: ${GOOGLE_API_KEY:-}
+    depends_on:
+      postgres:
+        condition: service_healthy
+    volumes:
+      - ./backend:/app
+    command: uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload
+
+volumes:
+  pgdata: