Update app.py

app.py

@@ -1,103 +1,126 @@
+"""
+app.py
+
+This script provides the Gradio web interface to run the evaluation for the
+Hugging Face Agents course. It fetches questions from a server, runs the
+agent defined in agent.py on them, and submits the answers for scoring.
+"""
+
 import os
+import re # <-- 1. ADDED IMPORT for Regular Expressions
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
+# --- Import your agent's factory function ---
+from agent import create_agent_executor # <-- 2. ADDED IMPORT for your agent
+
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-# class BasicAgent:
-#     def __init__(self):
-#         print("BasicAgent initialized.")
-#     def __call__(self, question: str) -> str:
-#         print(f"Agent received question (first 50 chars): {question[:50]}...")
-#         fixed_answer = "This is a default answer."
-#         print(f"Agent returning fixed answer: {fixed_answer}")
-#         return fixed_answer
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+# --- DELETED BasicAgent class as it's no longer needed ---
+
+# --- 3. ADDED HELPER FUNCTION TO PARSE THE AGENT'S OUTPUT ---
+def parse_final_answer(agent_response: str) -> str:
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Extracts the final answer from the agent's full response string.
+    The agent is prompted to return 'FINAL ANSWER: [answer]'.
+    This function isolates and returns '[answer]'.
+    """
+    # Use a regular expression to find the text after "FINAL ANSWER:"
+    match = re.search(r"FINAL ANSWER:\s*(.*)", agent_response, re.IGNORECASE | re.DOTALL)
+    if match:
+        # If a match is found, return the captured group, stripped of whitespace
+        return match.group(1).strip()
+    
+    # As a fallback, if the specific format is not found, return the last non-empty line
+    lines = [line for line in agent_response.split('\n') if line.strip()]
+    if lines:
+        return lines[-1].strip()
+        
+    # If all else fails, return a default message
+    return "Could not parse a final answer."
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the agent on them, submits all answers,
     and displays the results.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
+    if not profile:
         print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
-
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+        return "Please log in to Hugging Face with the button above to submit.", None
+    
+    username = profile.username
+    print(f"User logged in: {username}")
+    
+    space_id = os.getenv("SPACE_ID")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    questions_url = f"{DEFAULT_API_URL}/questions"
+    submit_url = f"{DEFAULT_API_URL}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # --- 4. MODIFIED AGENT INSTANTIATION AND EXECUTION ---
+    
+    # 1. Instantiate Agent (using your factory function from agent.py)
+    print("Initializing your custom agent...")
     try:
         agent_executor = create_agent_executor(provider="google") # or "groq"
     except Exception as e:
         print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+        return f"Fatal Error: Could not initialize agent. Check logs. Details: {e}", None
 
-    # 2. Fetch Questions
+    # 2. Fetch Questions (this part is correct)
     print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(questions_url, timeout=20)
         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 requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run your Agent (THIS IS THE MOST IMPORTANTLY CORRECTED SECTION)
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
+        
         if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
+            print(f"Skipping item with missing data: {item}")
             continue
+        
+        print(f"\n--- Running Task {i+1}/{len(questions_data)} (ID: {task_id}) ---")
+        print(f"Question: {question_text}")
+        
         try:
-            submitted_answer = agent(question_text)
+            # CORRECT INVOCATION: Use the agent_executor with the .invoke() method
+            # The input must be a dictionary with a "messages" key
+            result = agent_executor.invoke({"messages": [("user", question_text)]})
+            
+            # The agent's final response is in the 'messages' list of the output
+            raw_answer = result['messages'][-1].content
+            
+            # Use our helper function to extract the clean answer
+            submitted_answer = parse_final_answer(raw_answer)
+            
+            print(f"Raw LLM Response: '{raw_answer}'")
+            print(f"PARSED FINAL ANSWER: '{submitted_answer}'")
+
             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}"})
+             print(f"!! AGENT ERROR on task {task_id}: {e}")
+             # It's important to log errors so you can see them in the UI
+             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT RUNTIME ERROR: {e}"})
 
     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)
 
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # 4. Prepare and 5. Submit (these parts are correct)
+    submission_data = {"username": username, "agent_code": agent_code, "answers": answers_payload}
+    print(f"\nSubmitting {len(answers_payload)} answers for user '{username}'...")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -106,91 +129,35 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
             f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)"
         )
         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)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
+        status_message = f"Submission Failed: {e}"
         print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return status_message, pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Build Gradio Interface using Blocks (This part is correct) ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-        """
-    )
-
+    gr.Markdown("# Agent Evaluation Runner")
+    gr.Markdown("Run your custom agent against the evaluation questions and submit for a score.")
     gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=4, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True, max_rows=10)
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    # The startup info logs are helpful, so we keep them.
+    space_id_startup = os.getenv("SPACE_ID")
+    if space_id_startup:
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
+        print("ℹ️  SPACE_ID environment variable not found (likely running locally).")
     print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print("Launching Gradio Interface...")
+    demo.launch()