Update app.py

app.py

@@ -1,7 +1,6 @@
 
 
 import os
-import re
 import gradio as gr
 import requests
 import pandas as pd
@@ -9,6 +8,7 @@ import pandas as pd
 from smolagents import CodeAgent, DuckDuckGoSearchTool
 from smolagents.models import OpenAIServerModel
 
+# 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].
@@ -17,42 +17,24 @@ 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"
 
-def extract_final_answer(response_text: str) -> str:
-    match = re.search(r"FINAL ANSWER:\s*(.*)", response_text, re.IGNORECASE)
-    return match.group(1).strip() if match else response_text.strip()
+# Patched model to prepend system prompt correctly
+class PatchedOpenAIServerModel(OpenAIServerModel):
+    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 list of message dicts")
+
+        return super().generate(messages=messages, stop_sequences=stop_sequences, **kwargs)
 
 class MyAgent:
     def __init__(self):
-        self.model = OpenAIServerModel(model_id="gpt-4")
-        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:
-        messages = [
-            {"role": "system", "content": SYSTEM_PROMPT},
-            {"role": "user", "content": question}
-        ]
-        try:
-            response = self.model(messages)
-            # Extract the actual text from response
-            if isinstance(response, dict):
-                choices = response.get('choices')
-                if choices and len(choices) > 0:
-                    text = choices[0].get('message', {}).get('content', '')
-                else:
-                    text = ''
-            elif isinstance(response, str):
-                text = response
-            else:
-                text = str(response)
-
-            return extract_final_answer(text)
-        except Exception as e:
-            import traceback
-            traceback.print_exc()
-            return f"AGENT ERROR: {e}"
+        return self.agent.run(question)
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
@@ -71,22 +53,26 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     try:
         agent = MyAgent()
     except Exception as e:
+        print(f"Error initializing agent: {e}")
         return f"Error initializing agent: {e}", None
 
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(f"Agent code URL: {agent_code}")
 
+    print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
             return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
     except Exception as e:
         return f"Error fetching questions: {e}", None
 
     results_log = []
     answers_payload = []
-
+    print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
@@ -97,12 +83,14 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             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:
-            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:
         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}
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -117,30 +105,26 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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]}"
-        return f"Submission Failed: {error_detail}", pd.DataFrame(results_log)
+            detail = e.response.text[:500]
+        return f"Submission Failed: {detail}", pd.DataFrame(results_log)
     except requests.exceptions.Timeout:
         return "Submission Failed: The request timed out.", pd.DataFrame(results_log)
     except Exception as e:
         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")
@@ -169,7 +153,6 @@ 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)