fixed history handling

app.py

@@ -47,7 +47,12 @@ def codegemma(message: str,
     Returns:
         str: The generated response.
     """
-    input_ids = tokenizer.encode(message, return_tensors="pt").to(model.device)
+    conversation = []
+    for user, assistant in history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt").to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)