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

backend/.env.example

@@ -0,0 +1,19 @@
+# Database
+DATABASE_URL=postgresql://smart_support:dev_password@localhost:5432/smart_support
+
+# LLM Provider: anthropic | openai | google
+LLM_PROVIDER=anthropic
+LLM_MODEL=claude-sonnet-4-6
+
+# API Keys (set the one matching your LLM_PROVIDER)
+ANTHROPIC_API_KEY=
+OPENAI_API_KEY=
+GOOGLE_API_KEY=
+
+# Session
+SESSION_TTL_MINUTES=30
+INTERRUPT_TTL_MINUTES=30
+
+# Server
+WS_HOST=0.0.0.0
+WS_PORT=8000