Update app.py

app.py

@@ -237,7 +237,7 @@ class AgentDispatcher:
         if not agent:
             raise ValueError(f"Unknown agent: {agent_name}")
 
-        self.log_queue.put(f"[{agent_name.replace('_', ' ').title()}]: Starting task...")
+        self.log_queue.put(f"[{agent_name.replace('_', ' ').title()}]: Starting task...")  # Log here
         if agent_name == "prompt_optimizer":
             context = await agent.optimize_prompt(context, api_key)
         elif agent_name == "orchestrator":
@@ -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.")
@@ -309,20 +309,20 @@ async def multi_agent_conversation(task_message: str, log_queue: queue.Queue, ap
     log_queue.put(("result", context.conversation_history))
 
 # -------------------- Process Generator and Human Input --------------------
-def process_conversation_generator(task_message: str, api_key: str, human_in_the_loop_event: threading.Event, human_input_queue: queue.Queue) -> Generator[str, None, None]:
+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.
     """
-    log_q: queue.Queue = queue.Queue()
 
     # Run the multi-agent conversation *synchronously* within this function.
-    asyncio.run(multi_agent_conversation(task_message, log_q, api_key, human_in_the_loop_event, human_input_queue))
+    asyncio.run(multi_agent_conversation(task_message, log_queue, api_key, human_in_the_loop_event, human_input_queue))
 
     # Process the log queue and handle human-in-the-loop
     final_result = None
     while True:  # Loop indefinitely to handle multiple potential human feedback requests.
         try:
-            msg = log_q.get_nowait()  # Non-blocking get from the log queue.
+            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 "Conversation complete."  # Indicate completion.
@@ -389,8 +389,11 @@ def multi_agent_chat(message: str, history: List[Any], openai_api_key: str = Non
 
     human_in_the_loop_event = threading.Event()
     human_input_queue = queue.Queue()  # Use a single queue for both requests and responses
+    log_queue = queue.Queue() #Create log queue here
+
+    yield from process_conversation_generator(message, openai_api_key, human_in_the_loop_event, human_input_queue, log_queue)
+
 
-    yield from process_conversation_generator(message, openai_api_key, human_in_the_loop_event, human_input_queue)
 
 
 # -------------------- Launch the Chatbot --------------------
@@ -416,4 +419,5 @@ 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
+