Update app.py

app.py

@@ -6,7 +6,7 @@ import pandas as pd
 from smolagents import CodeAgent, DuckDuckGoSearchTool
 from smolagents.models import OpenAIServerModel
 
-# System prompt as per your instructions
+# Define the system prompt
 SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question.
 Report your thoughts, and finish your answer with the following template:
 FINAL ANSWER: [YOUR FINAL ANSWER].
@@ -15,38 +15,21 @@ of numbers and/or strings. If you are asked for a number, don't use comma to wri
 
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# Custom model wrapper that injects system message
-#class PatchedOpenAIServerModel(OpenAIServerModel):
- #   def generate(self, messages, *args, **kwargs):
- #       messages = [{"role": "system", "content": SYSTEM_PROMPT}] + messages
- #       return super().generate(messages, *args, **kwargs)
-
+# Patched model to prepend system prompt correctly
 class PatchedOpenAIServerModel(OpenAIServerModel):
-    def generate(self, messages, *args, **kwargs):
-        # Handle string inputs (raw prompts)
-        if isinstance(messages, str):
-            messages = [
-                {"role": "system", "content": SYSTEM_PROMPT},
-                {"role": "user", "content": messages}
-            ]
-        elif isinstance(messages, list):
-            # Assume already in proper format
-            messages = [{"role": "system", "content": SYSTEM_PROMPT}] + messages
+    def generate(self, messages, stop_sequences=None, **kwargs):
+        if isinstance(messages, list):
+            if not any(m["role"] == "system" for m in messages):
+                messages = [{"role": "system", "content": SYSTEM_PROMPT}] + messages
         else:
-            raise TypeError("Expected messages to be a string or list of dicts")
-        
-        return super().generate(messages, *args, **kwargs)
+            raise TypeError("Expected 'messages' to be a list of message dicts")
 
+        return super().generate(messages=messages, stop_sequences=stop_sequences, **kwargs)
 
 class MyAgent:
     def __init__(self):
-        self.model = PatchedOpenAIServerModel(
-            model_id="gpt-4"  # system_message removed; injected manually
-        )
-        self.agent = CodeAgent(
-            tools=[DuckDuckGoSearchTool()],
-            model=self.model
-        )
+        self.model = PatchedOpenAIServerModel(model_id="gpt-4")
+        self.agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=self.model)
 
     def __call__(self, question: str) -> str:
         return self.agent.run(question)
@@ -80,11 +63,9 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-            print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except Exception as e:
-        print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
 
     results_log = []
@@ -94,18 +75,16 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
-            print(f"Skipping invalid item: {item}")
             continue
         try:
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-            print(f"Error running agent on task {task_id}: {e}")
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            error_msg = f"AGENT ERROR: {e}"
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg})
 
     if not answers_payload:
-        print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
@@ -121,40 +100,29 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
-        print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
         try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+            detail = e.response.json().get("detail", e.response.text)
         except Exception:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        return status_message, pd.DataFrame(results_log)
+            detail = e.response.text[:500]
+        return f"Submission Failed: {detail}", pd.DataFrame(results_log)
     except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        return "Submission Failed: The request timed out.", pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
 
+# Gradio UI setup
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
+    gr.Markdown("""
         **Instructions:**
         1. Clone this space, modify code to define your agent's logic, tools, and packages.
         2. Log in to your Hugging Face account using the button below.
         3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your score.
-        
         **Note:** Submitting can take some time.
-        """
-    )
+    """)
 
     gr.LoginButton()
     run_button = gr.Button("Run Evaluation & Submit All Answers")
@@ -183,6 +151,5 @@ if __name__ == "__main__":
         print("ℹ️  SPACE_ID environment variable not found (running locally?).")
 
     print("-"*(60 + len(" App Starting ")) + "\n")
-
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)