large to medium llm

README.md

@@ -35,8 +35,8 @@ This is a demo of an AI agent designed to assist industries and service provider
 
 ### Design
 
-* The agent is implemented using **Mistral AI** via the `mistral-large-2411` LLM.  
-* Its capabilities have been enhanced with a chain-of-thought reasoning process, allowing it to think, act, observe, and respond effectively to user queries.  
+* The agent is implemented using **Mistral AI** via the **mistral-medium-2505** LLM.  
+* Its capabilities have been enhanced with a **chain-of-thought** reasoning process, allowing it to think, act, observe, and respond effectively to user queries.  
 * The agent is presented through a **Gradio interface**, which is well-suited for both real-time visualization and LLM interaction.
 
 ### Purposes  

app.py

@@ -48,7 +48,7 @@ This is a demo of an AI agent designed to assist industries and service provider
                 """
 ## Design
 
-The agent is implemented using **Mistral AI** via the `mistral-large-2411` LLM. Its capabilities have been enhanced with a chain-of-thought reasoning process, allowing it to `think`, `act`, `observe`, and `respond` effectively to user queries. The agent is presented through a **Gradio interface**, which is well-suited for both real-time visualization and LLM interaction. 
+The agent is implemented using **Mistral AI** via the `mistral-medium-2505` LLM. Its capabilities have been enhanced with a chain-of-thought reasoning process, allowing it to `think`, `act`, `observe`, and `respond` effectively to user queries. The agent is presented through a **Gradio interface**, which is well-suited for both real-time visualization and LLM interaction. 
 
 [See video overview](https://drive.google.com/file/d/1Bv1uF3-4EeR1HePSafZN1yzInr7YcQXZ/view?usp=share_link)
 

src/agent/stream.py

@@ -92,24 +92,6 @@ async def respond(message, history=None, state=None):
                 if current_phase == "think":
                     history[-1] = ChatMessage(role="assistant", content=buffer, metadata={"title": "Thinking...", "status": "pending", "id": state['cycle']})
 
-                #elif current_phase == "act":
-                    #parent_message = next((msg for msg in history if msg.metadata.get("id") == state['cycle']), None)
-                    #if parent_message:
-                    #    parent_message.content += "\n\n" + buffer
-                    #    parent_message.metadata["title"] = "Acting..."
-                    #else:
-                    #    history[-1] = ChatMessage(role="assistant", content=buffer, metadata={"title": "Acting...", "status": "pending", "id": state['cycle']+1, 'parent_id': state["cycle"]})
-
-                #elif current_phase == "observe":
-                #    parent_message = next((msg for msg in history if msg.metadata.get("id") == state['cycle']), None)
-                #    if parent_message:
-                #        parent_message.content += "\n\n" + buffer
-                #        parent_message.metadata["title"] = "Acting..."
-                #    else:
-                #        history[-1] = ChatMessage(role="assistant", content=buffer, metadata={"title": "Observing...", "status": "pending", "id": state['cycle']+2, 'parent_id': state["cycle"]})
-#
-                #yield history
-
                 if current_phase == "final":
                     delta_content = delta.content or ""
                     final_full += delta_content