Update app.py

app.py

@@ -1,209 +1,142 @@
 import os
 import gradio as gr
 import requests
-# import inspect # No longer needed
 import pandas as pd
-from dotenv import load_dotenv # Keep for consistency if final_agent uses it
-import traceback # For better error logging
-from typing import Optional
+from dotenv import load_dotenv
+import traceback
+from typing import Optional # Make sure this import is present
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# ----- THIS IS WHERE YOU INTEGRATE YOUR AGENT -----
-
-# 1. IMPORT your agent function from your agent file
+# --- Agent Integration ---
+# 1. IMPORT your main agent function
 try:
-    # Make sure the filename 'final_agent' matches the file you uploaded
+    # Ensure this matches the filename and function name exactly
     from final_agent import answer_gaia_task
     print("Successfully imported answer_gaia_task from final_agent.py")
-except ImportError:
-    print("ERROR: Could not import answer_gaia_task from final_agent.py. Check filename and function name.")
-    # Define a dummy function for graceful failure of the app
-    def answer_gaia_task(question: str, file_path: Optional[str] = None) -> str:
-        return "ERROR: Agent function 'answer_gaia_task' not found in final_agent.py."
+    AGENT_AVAILABLE = True
+except ImportError as e:
+    print(f"ERROR: Could not import answer_gaia_task from final_agent.py: {e}")
+    print("Ensure final_agent.py exists and has no syntax errors.")
+    AGENT_AVAILABLE = False
 except Exception as e:
     print(f"ERROR during import or initial setup in final_agent.py: {e}")
     traceback.print_exc()
-    # Define a dummy function
+    AGENT_AVAILABLE = False
+
+# Define a dummy function if import fails, so Gradio app can still load
+if not AGENT_AVAILABLE:
     def answer_gaia_task(question: str, file_path: Optional[str] = None) -> str:
-        return f"ERROR: Agent setup failed - {e}"
+        return "ERROR: Agent function could not be loaded. Check Space logs."
 
-class AgentRunner: # Renamed from BasicAgent
+# 2. Define a Runner Class to use the imported function
+class AgentRunner:
     def __init__(self):
-        # Agent initialization (LLM, tools, graph compile) happens globally
-        # when final_agent.py is imported. No specific actions needed here now.
-        print("AgentRunner initialized. LangGraph agent from final_agent.py should be ready.")
-        # Optional: Add checks here if needed (e.g., API key validation)
-        if not os.getenv("GEMINI_API_KEY") or not os.getenv("TAVILY_API_KEY"):
-             print("WARNING: GEMINI_API_KEY or TAVILY_API_KEY might not be set in Space secrets.")
+        print("AgentRunner initialized.")
+        if not AGENT_AVAILABLE:
+            print("WARNING: Agent function failed to load during startup.")
+        # Optional: Add environment variable checks if needed
+        # if not os.getenv("GROQ_API_KEY") or not os.getenv("TAVILY_API_KEY"):
+        #     print("WARNING: Required API keys might not be set in Space secrets.")
 
     def __call__(self, question: str) -> str:
         """Runs the imported agent function on a single question."""
         print(f"AgentRunner received question (first 50 chars): {question[:50]}...")
+        if not AGENT_AVAILABLE:
+            return "ERROR: Agent function could not be loaded."
         try:
-            # Call the imported function. Assume file_path handling is within answer_gaia_task or via question text.
+            # Call the imported function
             final_answer = answer_gaia_task(question=question, file_path=None)
-            # Ensure result is always a string for submission
+            # Ensure result is always a string
             final_answer_str = str(final_answer)
             print(f"Agent function returned answer: {final_answer_str}")
             return final_answer_str
         except Exception as e:
              print(f"ERROR calling answer_gaia_task: {e}")
-             traceback.print_exc() # Log the full error to Space logs
+             traceback.print_exc()
              return f"ERROR: Agent failed during execution - {e}"
 
-# ----- END OF AGENT INTEGRATION SECTION -----
-
-
+# --- Submission Logic (Mostly unchanged) ---
 def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the integrated agent on them, submits all answers,
-    and displays the results.
-    """
+    """Fetches questions, runs agent, submits answers."""
     space_id = os.getenv("SPACE_ID")
 
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face using the button.", None
+    if not profile:
+        print("User not logged in."); return "Please Login to Hugging Face.", None
+    username= f"{profile.username}"; print(f"User logged in: {username}")
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    api_url = DEFAULT_API_URL; questions_url = f"{api_url}/questions"; submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent Runner (which uses your imported function)
+    # 1. Instantiate Agent Runner
     try:
-        agent = AgentRunner() # This now sets up to use your LangGraph agent
+        agent = AgentRunner()
     except Exception as e:
-        print(f"Error instantiating AgentRunner: {e}")
-        return f"Error initializing agent runner: {e}", None
+        print(f"Error instantiating AgentRunner: {e}"); return f"Error initializing agent runner: {e}", None
 
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Code URL not available (SPACE_ID not set)"
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Code URL N/A"
     print(f"Agent code reference: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=30)
-        response.raise_for_status()
+        response = requests.get(questions_url, timeout=30); 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
+        if not questions_data: print("Fetched questions list is empty."); return "Questions list empty.", 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
+    except Exception as e: print(f"Error fetching questions: {e}"); return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent on each question
-    results_log = []
-    answers_payload = []
+    # 3. Run Agent on each question
+    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")
-        # file_path = item.get("file_path") # Check if needed/provided
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
-            continue
+        task_id = item.get("task_id"); question_text = item.get("question")
+        if not task_id or question_text is None: print(f"Skipping item: {item}"); continue
         try:
-            # This call triggers AgentRunner.__call__, which runs your answer_gaia_task
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text) # Calls AgentRunner.__call__
             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:
-             # Catch errors during the agent's execution on a specific task
-             print(f"Error running agent on task {task_id}: {e}")
-             traceback.print_exc()
-             # Log the error but continue to the next question
+             print(f"Error running agent on task {task_id}: {e}"); traceback.print_exc()
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT RUN ERROR: {e}"})
-             # Optionally submit the error message, or skip submitting for this task_id
              answers_payload.append({"task_id": task_id, "submitted_answer": f"AGENT RUN 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)
+    if not answers_payload: print("Agent produced no answers."); return "Agent produced no answers.", 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)
+    print(f"Submitting {len(answers_payload)} answers for user '{username}'...")
 
     # 5. Submit
-    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()
+        response = requests.post(submit_url, json=submission_data, timeout=60); response.raise_for_status()
         result_data = response.json()
-        final_status = (
-            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.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        final_status = (f"Submission Successful!\nUser: {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', 'N/A')}")
+        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
-    except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"; print(status_message)
-        traceback.print_exc(); results_df = pd.DataFrame(results_log); return status_message, results_df
+        except requests.exceptions.JSONDecodeError: error_detail += f" Response: {e.response.text[:200]}"
+        status_message = f"Submission Failed: {error_detail}"
+    except Exception as e: status_message = f"Submission Failed: Unexpected error - {e}"
+    print(status_message); traceback.print_exc(); results_df = pd.DataFrame(results_log); return status_message, results_df
 
 
 # --- Build Gradio Interface (Unchanged) ---
 with gr.Blocks() as demo:
-    gr.Markdown("# GAIA Agent Evaluation Runner") # Updated Title
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Ensure your agent logic is in `final_agent.py` and dependencies in `requirements.txt`. Set secrets in Space settings.
-        2. Log in to Hugging Face using the button below.
-        3. Click 'Run Evaluation & Submit All Answers' to run your agent. Check Logs for detailed progress.
-        ---
-        **Disclaimers:** Execution can take significant time.
-        """
-    )
+    gr.Markdown("# GAIA Agent Evaluation Runner"); gr.Markdown("...") # Keep markdown content
     gr.LoginButton()
     run_button = gr.Button("Run Evaluation & Submit All Answers")
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     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.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 # --- Main execution block (Unchanged) ---
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID")
-    if space_host_startup: print(f"✅ SPACE_HOST found: {space_host_startup}")
-    else: print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-    if space_id_startup: print(f"✅ SPACE_ID found: {space_id_startup}")
-    else: print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    # ... Keep startup checks ...
     print("Launching Gradio Interface for GAIA Agent Evaluation...")
-    # Set debug=False for less verbose logs once stable
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False) # debug=True helps during development