added test

app.py

@@ -3,7 +3,7 @@ import gradio as gr
 import requests
 import pandas as pd
 
-from agent import create_agent
+from agent import create_agent, fetch_random_question
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
@@ -11,24 +11,24 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the SmolAgent on them, submits all answers,
-    and displays the results.
+    Fetch all questions, run the SmolAgent on them, submit all answers,
+    and display 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 = profile.username
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        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"
 
-    # 1. Instantiate Agent
+    # 1. Instantiate SmolAgent
     try:
         agent = create_agent()
         print("SmolAgent initialized.")
@@ -36,11 +36,11 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
 
-    # Link to codebase for verification
+    # Code link for verification
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
-    # 2. Fetch Questions
+    # 2. Fetch all questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -50,18 +50,11 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             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:
+    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 Agent
+    # 3. Run agent on each question
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -69,117 +62,78 @@ 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 item with missing task_id or question: {item}")
+            print(f"Skipping invalid item: {item}")
             continue
         try:
-            submitted_answer = agent.run(question=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})
+            answer = agent.run(question=question_text)
+            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Answer": 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"Error on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Answer": f"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)
+        return "Agent produced no answers.", pd.DataFrame(results_log)
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # 4. Submit answers
+    payload = {"username": username, "agent_code": agent_code, "answers": answers_payload}
+    print(f"Submitting {len(answers_payload)} answers...")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
+        resp = requests.post(submit_url, json=payload, timeout=60)
+        resp.raise_for_status()
+        data = resp.json()
+        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.')}"
+            f"User: {data.get('username')}\n"
+            f"Score: {data.get('score')}% ({data.get('correct_count')}/{data.get('total_attempted')})\n"
+            f"Message: {data.get('message')}"
         )
-        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 status, pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        print(f"Submission error: {e}")
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+def test_random_question(profile: gr.OAuthProfile | None):
+    """
+    Fetch a random GAIA question and get the agent's answer for testing.
+    """
+    if not profile:
+        return "Please login to test.", ""
+
+    try:
+        q = fetch_random_question()
+        agent = create_agent()
+        ans = agent.run(question=q.get('question', ''))
+        return q.get('question', ''), ans
+    except Exception as e:
+        print(f"Test error: {e}")
+        return f"Error: {e}", ""
+
+
+# --- Build Gradio Interface ---
 with gr.Blocks() as demo:
     gr.Markdown("# SmolAgent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1.  Clone this space and define your agent logic in agent.py.
-        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 the score.
-
-        ---
-        **Disclaimers:**
-        After clicking the submit button, it can take some time for the agent to process all questions.
-        This space offers a basic setup; feel free to optimize or extend it (e.g., caching answers, async execution).
+        1. Clone this space and define your agent logic in agent.py.
+        2. Log in with your Hugging Face account.
+        3. Use 'Run Evaluation & Submit All Answers' or 'Test Random Question'.
         """
     )
 
-    gr.LoginButton()
+    login = gr.LoginButton()
+    run_all_btn = gr.Button("Run Evaluation & Submit All Answers")
+    test_btn = gr.Button("Test Random Question")
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_box = gr.Textbox(label="Status / Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Full Results Table", wrap=True)
+    question_box = gr.Textbox(label="Random Question", lines=3, interactive=False)
+    answer_box = gr.Textbox(label="Agent Answer", lines=3, interactive=False)
 
-    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_all_btn.click(fn=run_and_submit_all, inputs=[login], outputs=[status_box, results_table])
+    test_btn.click(fn=test_random_question, inputs=[login], outputs=[question_box, answer_box])
 
 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}")
-        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(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("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for SmolAgent Evaluation...")
     demo.launch(debug=True, share=False)