Update app.py

app.py

@@ -1,3 +1,4 @@
+# app.py
 import os
 import gradio as gr
 import requests
@@ -9,7 +10,6 @@ from agents import Agent
 from tool import get_tools
 from model import get_model
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 MODEL_ID = "gemini/gemini-2.5-flash-preview-04-17"
@@ -31,11 +31,13 @@ async def process_question(agent, question: str, task_id: str) -> Dict:
         }
 
 async def run_questions_async(agent, questions_data: List[Dict]) -> tuple:
-    """Process questions sequentially instead of in batch"""
+    """Process questions sequentially"""
     submissions = []
     logs = []
     
-    for q in questions_data:
+    total = len(questions_data)
+    for idx, q in enumerate(questions_data):
+        print(f"Processing {idx+1}/{total}: {q['question'][:80]}...")
         result = await process_question(agent, q["question"], q["task_id"])
         submissions.append(result["submission"])
         logs.append(result["log"])
@@ -43,16 +45,15 @@ async def run_questions_async(agent, questions_data: List[Dict]) -> tuple:
     return submissions, logs
 
 
-async def run_and_submit_all( profile: gr.OAuthProfile | None):
+async def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    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
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -71,9 +72,9 @@ async def run_and_submit_all( profile: gr.OAuthProfile | None):
     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)
+    print(f"Agent code: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -82,22 +83,15 @@ async 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("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-        questions_data = questions_data[:2]
-    except requests.exceptions.RequestException as e:
+        # Remove this line to process all questions: questions_data = questions_data[:2]
+    except Exception 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
 
-    # 3. Run your Agent
+    # 3. Run Agent
     print(f"Running agent on {len(questions_data)} questions...")
     answers_payload, results_log = await run_questions_async(agent, questions_data)
 
@@ -106,73 +100,58 @@ async def run_and_submit_all( profile: gr.OAuthProfile | None):
         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)
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+    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()
         result_data = response.json()
         final_status = (
-            f"Submission Successful!\n"
+            f"✅ Submission Successful!\n\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)\n\n"
+            f"Message: {result_data.get('message', 'No message received.')}\n\n"
+            f"Leaderboard: {api_url}/leaderboard"
         )
         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}"
+        status_message = f"❌ Submission Failed: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+# --- Build Gradio Interface ---
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🤖 GAIA Agent Evaluation")
     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.
+        1. Log in to your Hugging Face account using the button below
+        2. Click 'Run Evaluation & Submit' to test your agent
+        3. The agent will use web search and other tools to answer questions
+        
+        **Current Setup:**
+        - Model: Gemini 2.5 Flash (via LiteLLM)
+        - Tools: Web search, Wikipedia, calculation, and more
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button("🚀 Run Evaluation & Submit", variant="primary")
 
-    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)
+    status_output = gr.Textbox(label="📊 Status / Results", lines=8, interactive=False)
+    results_table = gr.DataFrame(label="📋 Questions and Answers", wrap=True, max_height=400)
 
     run_button.click(
         fn=run_and_submit_all,
@@ -180,25 +159,18 @@ with gr.Blocks() as demo:
     )
 
 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
-        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("\n" + "="*70)
+    print("🤖 GAIA Agent Starting")
+    print("="*70)
+    
+    space_host = os.getenv("SPACE_HOST")
+    space_id = os.getenv("SPACE_ID")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    if space_host:
+        print(f"✅ Runtime URL: https://{space_host}.hf.space")
+    if space_id:
+        print(f"✅ Repo URL: https://huggingface.co/spaces/{space_id}")
+    
+    print("="*70 + "\n")
+    demo.launch(debug=True, share=False)
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)