Add interactive testing interface with two-tab design

- Remove automatic test execution on startup
- Add Interactive Testing tab for asking any question
- Keep GAIA Certification tab for official evaluation
- Improve local auth handling with helpful HF_TOKEN guidance
- Clean separation between testing and certification workflows

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

app.py

@@ -364,80 +364,104 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Enhanced Agent for GAIA Level 1 Certification")
     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.
+        **Test your agent interactively or run the full GAIA evaluation:**
 
+        **Option 1: Interactive Testing**
+        - Ask any question to test how the agent works
+        - See detailed logs of search, Wikipedia lookup, and reasoning
+        
+        **Option 2: GAIA Certification**
+        1. Log in to your Hugging Face account using the button below
+        2. Click 'Run Evaluation & Submit All Answers' for official scoring
+        
         ---
-        **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.
         """
     )
+    
+    with gr.Tab("Interactive Testing"):
+        gr.Markdown("### Ask the agent any question")
+        question_input = gr.Textbox(
+            label="Your Question", 
+            placeholder="e.g., What is 25 * 4? or Who invented the telephone?",
+            lines=2
+        )
+        ask_button = gr.Button("Ask Agent", variant="primary")
+        answer_output = gr.Textbox(
+            label="Agent's Answer", 
+            lines=3, 
+            interactive=False
+        )
+        
+        def ask_agent(question):
+            if not question.strip():
+                return "Please enter a question."
+            
+            agent = BasicAgent()
+            try:
+                answer = agent(question)
+                return answer
+            except Exception as e:
+                return f"Error: {e}"
+        
+        ask_button.click(
+            fn=ask_agent,
+            inputs=[question_input],
+            outputs=[answer_output]
+        )
+    
+    with gr.Tab("GAIA Certification"):
+        gr.Markdown("### Official GAIA Level 1 Evaluation")
+        gr.Markdown(
+            """
+            **Instructions:**
+            1. Log in to your Hugging Face account using the button below
+            2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score
+            
+            **Note:** This can take several minutes as the agent processes all questions.
+            """
+        )
 
-    gr.LoginButton()
+        gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+        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)
+        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]
+        )
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     
-    # Test the agent first if running locally
-    space_host_startup = os.getenv("SPACE_HOST")
-    if not space_host_startup:
-        print("Running local test of SimpleAgent...")
-        agent = BasicAgent()
-        
-        test_questions = [
-            "What is 15 + 27?",
-            "When was the Eiffel Tower built?",
-            "Who was the first person to walk on the moon?",
-            "What is the capital of France?"
-        ]
-        
-        print("Testing Simple Direct Agent:")
-        print("=" * 40)
-        
-        for i, question in enumerate(test_questions, 1):
-            print(f"\n{i}. Question: {question}")
-            answer = agent(question)
-            print(f"   Answer: {answer}")
-            print("-" * 25)
-        
-        print("\n" + "=" * 40)
-        print("Local test completed. Starting Gradio interface...\n")
-    
     # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    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?).")
+        print("ℹ️  SPACE_HOST environment variable not found (running locally).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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 (running locally). Repo URL cannot be determined.")
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for Enhanced Agent...")
+    # Set HF_TOKEN for local testing if not set
+    if not space_host_startup and not os.getenv("HF_TOKEN"):
+        print("💡 For local testing: Set HF_TOKEN environment variable to bypass auth issues")
+        print("   Example: export HF_TOKEN=hf_your_token_here")
+    
     demo.launch(debug=True, share=False)