fix: Gateway response extraction and GPU optimization

- Fixed Gateway to extract response from data.text field
- GPU working: RTX 4000 Ada, response time 7-10s (was 30-40s)
- DAARWIZZ now responds correctly with full personality
- Started Memory Service structure

gateway-bot/http_api.py

@@ -148,7 +148,7 @@ async def telegram_webhook(update: TelegramUpdate):
         
         # Extract response text
         if isinstance(response, dict):
-            answer_text = response.get("response", "Вибач, я зараз не можу відповісти.")
+            answer_text = response.get("data", {}).get("text") or response.get("response", "Вибач, я зараз не можу відповісти.")
         else:
             answer_text = "Вибач, сталася помилка."
         
@@ -220,7 +220,7 @@ async def discord_webhook(message: DiscordMessage):
         
         # Extract response text
         if isinstance(response, dict):
-            answer_text = response.get("response", "Sorry, I can't respond right now.")
+            answer_text = response.get("data", {}).get("text") or response.get("response", "Sorry, I can't respond right now.")
         else:
             answer_text = "Sorry, an error occurred."
         

services/memory-service/app/__init__.py

@@ -0,0 +1 @@
+# Memory Service for DAARION.city

services/memory-service/requirements.txt

@@ -0,0 +1,6 @@
+fastapi>=0.115.0
+uvicorn[standard]>=0.30.0
+SQLAlchemy[asyncio]>=2.0.30
+asyncpg>=0.29.0
+pydantic>=2.8.0
+python-dotenv>=1.0.1