feat: complete phase 5 -- error hardening, frontend, Docker, demo, docs

Backend:
- ConversationTracker: Protocol + PostgresConversationTracker for lifecycle tracking
- Error handler: ErrorCategory enum, classify_error(), with_retry() exponential backoff
- Wire PostgresAnalyticsRecorder + ConversationTracker into ws_handler
- Rate limiting (10 msg/10s per thread), edge case hardening
- Health endpoint GET /api/health, version 0.5.0
- Demo seed data script + sample OpenAPI spec

Frontend (all new):
- React Router with NavBar (Chat / Replay / Dashboard / Review)
- ReplayListPage + ReplayPage with ReplayTimeline component
- DashboardPage with MetricCard, range selector, zero-state
- ReviewPage for OpenAPI classification review
- ErrorBanner for WebSocket disconnect handling
- API client (api.ts) with typed fetch wrappers

Infrastructure:
- Frontend Dockerfile (multi-stage node -> nginx)
- nginx.conf with SPA routing + API/WS proxy
- docker-compose.yml with frontend service + healthchecks
- .env.example files (root + backend)

Documentation:
- README.md with quick start and architecture
- Agent configuration guide
- OpenAPI import guide
- Deployment guide
- Demo script

48 new tests, 449 total passing, 92.87% coverage

backend/.env.example

@@ -1,19 +1,34 @@
-# Database
+# Smart Support Backend -- environment variables
+# Copy to .env and fill in your values
+
+# Required: PostgreSQL connection string
 DATABASE_URL=postgresql://smart_support:dev_password@localhost:5432/smart_support
 
-# LLM Provider: anthropic | openai | google
+# Required: LLM provider configuration
+# provider: anthropic | openai | google
 LLM_PROVIDER=anthropic
 LLM_MODEL=claude-sonnet-4-6
 
-# API Keys (set the one matching your LLM_PROVIDER)
+# API keys -- provide the one matching LLM_PROVIDER
 ANTHROPIC_API_KEY=
 OPENAI_API_KEY=
 GOOGLE_API_KEY=
 
-# Session
+# Optional: webhook endpoint for escalation notifications
+# The backend will POST a JSON payload when a conversation is escalated.
+WEBHOOK_URL=
+WEBHOOK_TIMEOUT_SECONDS=10
+WEBHOOK_MAX_RETRIES=3
+
+# Session management
 SESSION_TTL_MINUTES=30
 INTERRUPT_TTL_MINUTES=30
 
-# Server
+# Optional: load a named agent template instead of agents.yaml
+# Leave blank to use the default agents.yaml in the backend directory.
+# Available templates: ecommerce, saas, generic
+TEMPLATE_NAME=
+
+# Server binding
 WS_HOST=0.0.0.0
 WS_PORT=8000