Update app.py

app.py

@@ -58,7 +58,7 @@ AVAILABLE_MODELS = {
 
 # Chat memory (in-memory)
 chat_histories = defaultdict(list)
-MAX_HISTORY = 10  # limit memory to avoid crashes
+MAX_HISTORY = 100  # limit memory to avoid crashes
 
 # Generate response stream
 async def generate_ai_response(chat_id: str, model: str):