Update script to handle streaming properly.

If a response was set to streaming, the sub agent will return unusable data.

multi-agent-collaboration.py

@@ -1,7 +1,7 @@
 """
 title: Multi Agent Collaboration System for Open WebUI
 Description: Allows for Multiple Models to act as Agents in collaboration
-version: 0.5.6
+version: 0.7.6
 """
 
 from pydantic import BaseModel, Field
@@ -72,9 +72,16 @@ class Pipe:
         agents = __user__["valves"].agent_list
         operator_model = __user__["valves"].operator_model
         number_of_agents = len(agents)
+        if "### Task:" in body["messages"][0]["content"]:
+            body["model"] = operator_model
+            print("Internal Request")
+            return await generate_chat_completion(__request__, body, user)
+        # Capture Stream Setting
+        original_stream = body["stream"]
         if number_of_agents > 0:
             # Process through each agent in the list
             for agent_model in agents:
+                body["stream"] = False
                 # Temporarily change the model to the agent model
                 body["model"] = agent_model
                 print(f"Model being use: {agent_model}")
@@ -83,6 +90,8 @@ class Pipe:
                     description=message, status="agent_processing", done=True
                 )
                 response = await generate_chat_completion(__request__, body, user)
+                content = response["choices"][0]["message"]["content"]
+                print(f"This is the content from {agent_model}: {content}")
                 # Add Agent response as context
                 body["messages"].append(
                     {
@@ -90,11 +99,9 @@ class Pipe:
                         "content": f"{response} \n (Provided by Agent: {agent_model})",
                     }
                 )
-            # set Operator for final processing
-            body["model"] = operator_model
-            print(f"Model being use: {operator_model}")
-            message = f"Final Response from {operator_model}"
-            await emitter.emit(
-                description=message, status="final_processing", done=True
-            )
+        body["model"] = operator_model
+        body["stream"] = original_stream
+        print(f"Model being use: {operator_model}")
+        message = f"Final Response from {operator_model}"
+        await emitter.emit(description=message, status="final_processing", done=True)
         return await generate_chat_completion(__request__, body, user)