Update app.py

app.py

@@ -299,7 +299,7 @@ async def multi_agent_conversation(task_message: str, log_queue: queue.Queue, ap
 
         next_agent = await dispatcher.determine_next_agent(context, api_key)
         if next_agent == "code_reviewer" and context.review_comments and "APPROVE" in [comment.get('issue',"").upper() for comment_list in context.review_comments for comment in comment_list.get("comments",[])  ]:
-            next_agent = await dispatcher.determine_next_agent(context, api_key)
+          next_agent = await dispatcher.determine_next_agent(context, api_key)
         # Check for maximum revisions
         if next_agent == "coder" and len([entry for entry in context.conversation_history if entry["agent"] == "Coder"]) > 5:
           log_queue.put("Maximum revision iterations reached. Exiting.")
@@ -312,7 +312,7 @@ async def multi_agent_conversation(task_message: str, log_queue: queue.Queue, ap
 def process_conversation_generator(task_message: str, api_key: str, human_in_the_loop_event: threading.Event, human_input_queue: queue.Queue, log_queue: queue.Queue) -> Generator[str, None, None]:
     """
     Wraps the conversation, yields log messages, and handles human input within a single thread.
-    Crucially, takes the log_queue as an argument.
+    Crucially, takes the log_queue as an argument.  Yields Gradio updates.
     """
 
     # Run the multi-agent conversation *synchronously* within this function.
@@ -325,6 +325,7 @@ def process_conversation_generator(task_message: str, api_key: str, human_in_the
             msg = log_queue.get_nowait()  # Non-blocking get from the log queue.
             if isinstance(msg, tuple) and msg[0] == "result":
                 final_result = msg[1]
+                yield gr.Chatbot.update(final_result)  # Update the chatbot with the final result
                 yield "Conversation complete."  # Indicate completion.
                 break  # Exit the loop after processing the final result.
             else:
@@ -339,7 +340,7 @@ def process_conversation_generator(task_message: str, api_key: str, human_in_the
                 feedback_request = human_input_queue.get(
                     timeout=0.1)  # Get the context/question for feedback.
                 human_interface = get_human_feedback(feedback_request)
-                yield gr.Textbox.update(visible=False), gr.update(visible=True)
+                yield gr.Textbox.update(visible=False), gr.update(visible=True)  # Show feedback UI
                 human_feedback = human_input_queue.get(
                     timeout=300)  # Wait (block) for human feedback, with a timeout.
                 human_in_the_loop_event.clear()  # Reset the event after getting feedback.
@@ -352,11 +353,7 @@ def process_conversation_generator(task_message: str, api_key: str, human_in_the
         time.sleep(0.1)
 
 
-    if final_result:
-        conv_text = "\n=== Conversation ===\n"
-        for entry in final_result:
-            conv_text += f"[{entry['agent']}]: {entry['message']}\n\n"
-        yield conv_text
+
 
 def get_human_feedback(placeholder_text):
     """Gets human input using a Gradio Textbox."""
@@ -401,6 +398,7 @@ def multi_agent_chat(message: str, history: List[Any], openai_api_key: str = Non
 # Create the main chat interface
 iface = gr.ChatInterface(
     fn=multi_agent_chat,
+    chatbot=gr.Chatbot(type="feed"), # Use the 'feed' type for a better display of messages
     additional_inputs=[gr.Textbox(label="OpenAI API Key (optional)", type="password", placeholder="Leave blank to use env variable")],
     title="Multi-Agent Task Solver with Human-in-the-Loop",
     description="""
@@ -419,5 +417,4 @@ if __name__ == "__main__":
     demo = gr.TabbedInterface([iface, dummy_iface], ["Chatbot", "Dummy"])
     demo.launch(share=True)
 
-import time #Import the time module
-                                                                                       
+import time #Import the time module