Update app.py

app.py

@@ -1,196 +1,192 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Agent Definition ---
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("Inicializando o Agente do GAIA...")
+        
+        # Define o modelo
+        self.model = HfApiModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct")
+        
+        # Define as ferramentas
+        self.tools = [DuckDuckGoSearchTool()]
+        
+        # Prompt customizado para forçar o formato EXACT MATCH do GAIA
+        custom_prompt = """
+        You are an expert AI assistant solving tasks from the GAIA benchmark.
+        Your final answer MUST be extremely concise and exact. 
+        Do NOT include any conversational text, explanations, or the words "FINAL ANSWER" in your final output.
+        If the question asks for a comma-separated list, provide ONLY the list.
+        If the question asks for a number, provide ONLY the number.
+        """
+        
+        # Instancia o agente
+        self.agent = CodeAgent(
+            tools=self.tools,
+            model=self.model,
+            max_steps=6,
+            description="Agent designed to solve GAIA benchmark questions with exact match answers."
+        )
+        
+        # Injetando a instrução no sistema
+        self.agent.system_prompt = custom_prompt + "\n" + self.agent.system_prompt
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        try:
+            # O agente executa a pesquisa e raciocina
+            resposta_final = self.agent.run(question)
+            
+            # Limpeza básica de segurança para evitar que a string "FINAL ANSWER" vaze
+            resposta_limpa = str(resposta_final).replace("FINAL ANSWER", "").strip()
+            
+            print(f"Agent returning answer: {resposta_limpa}")
+            return resposta_limpa
+        except Exception as e:
+            print(f"Erro durante o raciocínio do agente: {e}")
+            return "ERROR"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+# --- Core Functions ---
+
+def run_agent_only(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Busca as perguntas, roda o agente para gerar as respostas e retorna 
+    os dados para visualização e o payload para o estado do Gradio.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+    if not profile:
+        return "Please Login to Hugging Face first.", pd.DataFrame(), []
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
     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)
+        return f"Error initializing agent: {e}", pd.DataFrame(), []
 
-    # 2. Fetch Questions
     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
+             return "Fetched questions list is empty.", pd.DataFrame(), []
     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}", pd.DataFrame(), []
 
-    # 3. Run your Agent
     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")
+        
         if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
             continue
+            
         try:
             submitted_answer = agent(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})
         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}"})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted 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)
+        return "Agent did not produce any 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)
+    status_update = f"Agent finished! Processed {len(answers_payload)} questions. Please review the table below before submitting."
+    results_df = pd.DataFrame(results_log)
+    
+    # Retorna o status, a tabela visível e o payload invisível (para o gr.State)
+    return status_update, results_df, answers_payload
 
-    # 5. Submit
+
+def submit_to_leaderboard(profile: gr.OAuthProfile | None, answers_payload: list):
+    """
+    Pega as respostas validadas no estado do Gradio e envia para a API.
+    """
+    if not profile:
+        return "Please Login to Hugging Face first."
+    
+    if not answers_payload or len(answers_payload) == 0:
+        return "No answers to submit. Please run the agent first."
+
+    username = profile.username
+    space_id = os.getenv("SPACE_ID", "local-environment")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    submit_url = f"{DEFAULT_API_URL}/submit"
+
+    submission_data = {
+        "username": username.strip(), 
+        "agent_code": agent_code, 
+        "answers": answers_payload
+    }
+    
     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"
             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
-    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
+        return final_status
     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 f"❌ Submission Failed: {e}"
     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
+        return f"❌ An unexpected error occurred: {e}"
 
 
-# --- 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 - Two-Step Runner")
     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.
-
-        ---
-        **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.
+        **Instruções de Validação:**
+        1. Faça o Login no Hugging Face.
+        2. Clique em **'1. Run Agent & Preview'**. O agente vai processar as questões e a tabela será preenchida. (Isso pode demorar vários minutos).
+        3. Valide as respostas na tabela. Se o formato estiver correto (Exact Match), clique em **'2. Submit to Leaderboard'** para enviar sua pontuação oficial.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    with gr.Row():
+        btn_run = gr.Button("1. Run Agent & Preview Answers", variant="secondary")
+        btn_submit = gr.Button("2. Submit to Leaderboard (Final)", 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="System Status", lines=3, interactive=False)
+    results_table = gr.DataFrame(label="Agent Answers Preview", wrap=True)
+    
+    # Variável de estado invisível para armazenar o payload JSON entre os cliques dos botões
+    stored_answers = gr.State([])
+
+    # Evento do Botão 1: Roda o agente, atualiza a interface e salva no estado
+    btn_run.click(
+        fn=run_agent_only,
+        outputs=[status_output, results_table, stored_answers]
+    )
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+    # Evento do Botão 2: Lê o estado e envia para a API
+    btn_submit.click(
+        fn=submit_to_leaderboard,
+        inputs=[stored_answers],
+        outputs=[status_output]
     )
 
 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...")
     demo.launch(debug=True, share=False)