feat(backend): add response caching and user management

Replace USE_DATABASE toggle with USE_CACHE for smarter LLM response handling:
- Add prompt hashing for efficient cache lookups
- Cache API responses in database to reduce token usage
- Always store responses for analytics (cache or fresh)

Add user authentication infrastructure:
- User table with bcrypt password hashing
- CRUD operations for user management
- Role-based access control (admin/user)

Dependencies: add bcrypt and PyJWT for auth

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

SPARC/config.py

@@ -13,10 +13,15 @@ api_key = os.getenv("API_KEY")
 # OpenRouter API key for LLM analysis
 openrouter_api_key = os.getenv("OPENROUTER_API_KEY")
 
-# Database configuration
+# Database configuration - all messages are stored in the database
+# The database serves as both a persistent store and a cache layer
 database_url = os.getenv("DATABASE_URL", "postgresql://postgres:postgres@localhost:5432/sparc")
 
-# Toggle between database mode and API mode
-# When True: stores all messages in database instead of sending to OpenRouter
-# When False: sends messages to OpenRouter API as normal
+# Cache configuration
+# When enabled (default), the system checks the database for cached responses
+# before making API calls, saving tokens and reducing latency
+use_cache = os.getenv("USE_CACHE", "true").lower() in ("true", "1", "yes")
+
+# Legacy compatibility - USE_DATABASE is deprecated, database is always used
+# This variable is kept for backwards compatibility but has no effect
 use_database = os.getenv("USE_DATABASE", "false").lower() in ("true", "1", "yes")