feat: add conversation persistence and context management layer

- SQLAlchemy async database layer (SQLite dev, PostgreSQL prod)
- Conversation and Message models with UUID primary keys
- Token counting utilities using litellm
- Context summarization at 80% token threshold
- REST API endpoints for multi-turn conversations
- 19 conversation tests, 6 token tests (176 total passing)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

webber-api/src/main.py

@@ -31,13 +31,18 @@ async def lifespan(app: FastAPI):
     logger.info(f"Port: {settings.port}")
     logger.info(f"Ollama: {settings.ollama_url}")
     logger.info(f"Agent model: {settings.ollama_agent_model}")
+    logger.info(f"Database: {settings.database_url}")
     logger.info("=" * 60)
 
-    # TODO: Initialize resources (LLM clients, etc.)
-
     yield
 
     # Cleanup
+    from src.db import get_database
+    try:
+        database = get_database()
+        await database.close()
+    except Exception:
+        pass
     logger.info("Shutting down")