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/app/agents/fallback.py

@@ -0,0 +1,18 @@
+"""Fallback agent tools -- handles unmatched intents."""
+
+from __future__ import annotations
+
+from langchain_core.tools import tool
+
+
+@tool
+def fallback_respond(query: str) -> str:
+    """Provide a helpful response when the user's intent doesn't match a specific agent."""
+    return (
+        "I'm here to help with order inquiries and actions. "
+        "Here's what I can do:\n"
+        "- Check order status (e.g., 'What is the status of order 1042?')\n"
+        "- Get tracking information (e.g., 'Track order 1042')\n"
+        "- Cancel an order (e.g., 'Cancel order 1042')\n\n"
+        "Could you please rephrase your request?"
+    )