Restore original Gradio interface while maintaining enhanced GAIA agent features

app.py

@@ -769,86 +769,70 @@ class ModularGAIAAgent:
             logger.error(f"Batch processing overall error: {e}")
             yield "Error in batch processing", []
 
-# --- Basic Agent Definition (now wraps ModularGAIAAgent) ---
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent (GAIA Modular Agent) initialized.")
-        self.agent = ModularGAIAAgent()
-    def __call__(self, question: str, file_name: str = "") -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        try:
-            answer, trace = self.agent.answer_question({"task_id": "manual", "question": question, "file_name": file_name})
-            print(f"Agent returning answer: {answer}")
-            return answer
-        except Exception as e:
-            print(f"Agent error: {e}")
-            return f"AGENT ERROR: {e}"
+# --- Build Gradio Interface using Blocks (Maintaining Original Architecture) ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Smart Agent Evaluation Runner")
+    gr.Markdown("""
+        **Instructions:**
+        1. Clone this space, define your agent logic, tools, packages, etc.
+        2. Log in to Hugging Face.
+        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the 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)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+
+if __name__ == "__main__":
+    print("Launching Gradio Interface for Smart Agent Evaluation...")
+    demo.launch(debug=True, share=False)
 
+# Update run_and_submit_all to use the enhanced ModularGAIAAgent
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
     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
+
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
-    try:
-        agent = BasicAgent()
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
+
+    agent = ModularGAIAAgent(api_url=DEFAULT_API_URL)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-    print(f"Fetching questions from: {questions_url}")
+
     try:
         response = requests.get(questions_url, timeout=15)
         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
+
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+    correct_answers = 0
+
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
-        file_name = item.get("file_name", "")
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
+        if not task_id or not question_text:
             continue
-        try:
-            submitted_answer = agent(question_text, file_name)
-            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}"})
+
+        submitted_answer, trace = agent.answer_question(item)
+        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, "Reasoning Trace": "\n".join(trace)})
+
     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)
+
     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 to: {submit_url}")
+
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -858,130 +842,9 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             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.")
+            f"Message: {result_data.get('message', 'No message received.')}"
+        )
         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)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-# --- Gradio UI with Enhanced Feedback and Control ---
-with gr.Blocks(title="GAIA Agent - Multi-Tab with Progress Tracking") as app:
-    gr.Markdown("# GAIA Agent for Hugging Face AI Agents Course\nTarget: 30%+ on GAIA Benchmark for Certification")
-    with gr.Tabs() as tabs:
-        # Tab 1: Fetch GAIA Questions with Progress
-        with gr.TabItem("Fetch GAIA Questions"):
-            with gr.Row():
-                token_input = gr.Textbox(label="Hugging Face Token", placeholder="Enter your HF token", type="password")
-                fetch_btn = gr.Button("Fetch Questions")
-            fetch_progress = gr.Textbox(label="Progress", value="Not started", interactive=False)
-            questions_output = gr.JSON(label="Fetched Questions")
-            fetch_btn.click(
-                fn=lambda token: ("Fetching...", agent.fetch_questions(token)),
-                inputs=token_input,
-                outputs=[fetch_progress, questions_output]
-            )
-        # Tab 2: Manual Question Input with Detailed Feedback
-        with gr.TabItem("Manual Question Input"):
-            question_input = gr.Textbox(label="Ask a Question", placeholder="Type your question here")
-            with gr.Row():
-                file_upload = gr.File(label="Upload File (optional)", file_types=[".jpg", ".png", ".mp3", ".csv", ".xlsx", ".py"])
-                context_upload = gr.File(label="Context Files (optional)", file_count="multiple")
-            answer_btn = gr.Button("Get Answer")
-            with gr.Row():
-                answer_output = gr.Textbox(label="Answer", interactive=False)
-                reasoning_trace = gr.Textbox(label="Reasoning Trace", interactive=False)
-            answer_btn.click(
-                fn=lambda q, f, ctx: agent.answer_question_manual(q, f, ctx),
-                inputs=[question_input, file_upload, context_upload],
-                outputs=[answer_output, reasoning_trace]
-            )
-        # Tab 3: Submit Answers and View Score with Progress Bar
-        with gr.TabItem("Submit & Score"):
-            with gr.Row():
-                submit_token = gr.Textbox(label="Hugging Face Token", placeholder="Enter your HF token", type="password")
-                submit_btn = gr.Button("Run on All & Submit")
-            submit_progress = gr.Textbox(label="Submission Progress", value="Not started", interactive=False)
-            score_output = gr.Textbox(label="Score", interactive=False)
-            with gr.Row():
-                progress_bar = gr.Slider(minimum=0, maximum=100, value=0, label="Completion", interactive=False)
-                status_text = gr.Textbox(label="Status", value="Idle", interactive=False)
-            submit_btn.click(
-                fn=lambda token: agent.run_and_submit_all(token),
-                inputs=submit_token,
-                outputs=[submit_progress, score_output, progress_bar, status_text]
-            )
-        # Tab 4: Agent Details and Configuration
-        with gr.TabItem("Agent Details"):
-            gr.Markdown("## Agent Capabilities\n- **Tools**: Web search, image/audio analysis, table QA, YouTube QA, chess analysis, botanical classification\n- **Reasoning**: Thought-Action-Observation cycle with ReAct prompting (up to 5 steps)\n- **API**: Full GAIA API integration for fetching and submitting\n- **Performance**: Optimized with caching and error recovery")
-            with gr.Row():
-                tool_list = gr.Textbox(label="Available Tools", value=", ".join(TOOL_REGISTRY.keys()), interactive=False)
-                config_btn = gr.Button("Refresh Configuration")
-            config_output = gr.Textbox(label="Configuration Status", interactive=False)
-            config_btn.click(
-                fn=lambda: ("Configuration refreshed", ", ".join(TOOL_REGISTRY.keys())),
-                inputs=None,
-                outputs=[config_output, tool_list]
-            )
-        # Tab 5: Batch Processing with Progress Tracking
-        with gr.TabItem("Batch Processing"):
-            batch_token = gr.Textbox(label="Hugging Face Token", placeholder="Enter your HF token", type="password")
-            batch_btn = gr.Button("Process Batch of Questions")
-            batch_progress = gr.Textbox(label="Batch Progress", value="0/0 questions processed", interactive=False)
-            batch_results = gr.JSON(label="Batch Results")
-            batch_btn.click(
-                fn=lambda token: agent.process_batch(token),
-                inputs=batch_token,
-                outputs=[batch_progress, batch_results]
-            )
-
-# Launch app with public link for easy access
-app.launch(share=True)
-
-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("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    app.launch(debug=True, share=False)
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)