Update app.py

app.py

@@ -71,53 +71,46 @@ def query_model(model_name: str, messages: List[Dict[str, str]]) -> str:
     except Exception as e:
         return f"{model_name} error: {str(e)}"
 
-class ConversationState:
-    def __init__(self):
-        self.messages = []
-        
-    def add_user_message(self, message: str):
-        self.messages.append({"role": "user", "content": message})
-        
-    def add_assistant_message(self, model_name: str, message: str):
-        self.messages.append({
-            "role": "assistant",
-            "model": model_name,
-            "content": message
-        })
-        
-    def get_context(self) -> List[Dict[str, str]]:
-        return [
-            {
-                "role": msg["role"],
-                "content": f"{msg.get('model', '')}: {msg['content']}" if msg["role"] == "assistant" else msg["content"]
-            }
-            for msg in self.messages
-        ]
-
-conversation_state = ConversationState()
-
 def respond(message: str, history: List[List[str]]) -> str:
-    """Handle sequential model responses with continuous conversation context"""
+    """Handle sequential model responses with continuous context"""
+    
+    # Build full conversation history from previous interactions
+    conversation = []
+    if history:
+        for user_msg, assistant_msg in history:
+            conversation.append({"role": "user", "content": user_msg})
+            if assistant_msg:
+                # Split assistant message into individual model responses
+                responses = assistant_msg.split("\n\n")
+                for resp in responses:
+                    if resp:
+                        conversation.append({"role": "assistant", "content": resp})
     
-    # Add current message to conversation state
-    conversation_state.add_user_message(message)
-    current_context = conversation_state.get_context()
+    # Add current message
+    conversation.append({"role": "user", "content": message})
     
     # Get first model's response
-    response1 = query_model("Qwen2.5-Coder-32B-Instruct", current_context)
-    conversation_state.add_assistant_message("Qwen2.5-Coder-32B-Instruct", response1)
+    response1 = query_model("Qwen2.5-Coder-32B-Instruct", conversation)
     yield f"**Qwen2.5-Coder-32B-Instruct**:\n{response1}"
     
-    # Get second model's response with updated context
-    current_context = conversation_state.get_context()
-    response2 = query_model("Qwen2.5-72B-Instruct", current_context)
-    conversation_state.add_assistant_message("Qwen2.5-72B-Instruct", response2)
+    # Add first response to context
+    conversation.append({
+        "role": "assistant",
+        "content": f"**Qwen2.5-Coder-32B-Instruct**:\n{response1}"
+    })
+    
+    # Get second model's response
+    response2 = query_model("Qwen2.5-72B-Instruct", conversation)
     yield f"**Qwen2.5-72B-Instruct**:\n{response2}"
     
-    # Get final model's response with complete context
-    current_context = conversation_state.get_context()
-    response3 = query_model("Llama3.3-70B-Instruct", current_context)
-    conversation_state.add_assistant_message("Llama3.3-70B-Instruct", response3)
+    # Add second response to context
+    conversation.append({
+        "role": "assistant",
+        "content": f"**Qwen2.5-72B-Instruct**:\n{response2}"
+    })
+    
+    # Get final model's response
+    response3 = query_model("Llama3.3-70B-Instruct", conversation)
     yield f"**Llama3.3-70B-Instruct**:\n{response3}"
 
 # Create the Gradio interface