import os import gradio as gr import requests import inspect import pandas as pd from langchain_core.messages import HumanMessage from agent import build_graph # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- class BasicAgent: """Langgraph agent.""" def __init__(self): print("BasicAgent initialized.") self.graph = build_graph() def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") messages = [HumanMessage(content=question)] # IMPORTANT: We invoke the full graph to see the entire process full_response = self.graph.invoke({"messages": messages}) # The final answer is in the last message final_message = full_response['messages'][-1] # We return the full content for debugging, not just the sliced answer # The main submission function will handle slicing if needed. return final_message.content # ============================================================================== # === SECTION 1: ADD THIS NEW FUNCTION FOR SINGLE-QUESTION TESTING === # ============================================================================== def test_single_question(question: str): """ Runs the agent on a single question and shows the FULL thought process. """ if not question.strip(): return "Please enter a question to test." print("--- Running Single Test ---") try: # We instantiate the graph directly to get the full output graph = build_graph() messages = [HumanMessage(content=question)] # We can configure the graph to stream all intermediate steps # This gives us a play-by-play of the agent's actions. full_thought_process = "" events = graph.stream( {"messages": messages}, # Increase the recursion limit for debugging complex tasks # but the real goal is to fix the loop, not just extend it. {"recursion_limit": 50} ) for event in events: # We are interested in the 'assistant' node's output and the 'tools' node's output if "assistant" in event: message = event["assistant"]["messages"][-1] full_thought_process += f"--- Assistant ---\n" full_thought_process += f"Content: {message.content}\n" if message.tool_calls: full_thought_process += f"Tool Calls: {message.tool_calls}\n" full_thought_process += "---\n\n" if "tools" in event: tool_outputs = event["tools"]["messages"] full_thought_process += f"--- Tools Output ---\n" for tool_output in tool_outputs: full_thought_process += f"Tool Output: {tool_output.content}\n" full_thought_process += "---\n\n" print("--- Single Test Complete ---") return full_thought_process except Exception as e: print(f"Error during single test: {e}") # Make the error message more readable in the UI import traceback return f"AGENT ERROR:\n{type(e).__name__}\n{str(e)}\n\nTraceback:\n{traceback.format_exc()}" # ============================================================================== def run_and_submit_all( profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent 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 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 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) # 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 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 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: file_name = item.get("file_name") full_file_path = f"validation/{file_name}" if file_name else None augmented_question = question_text if file_name and full_file_path and os.path.exists(full_file_path): augmented_question = f"{question_text}. Here is the file Path: {full_file_path}." augmented_question = augmented_question + " The answer must be as short as possible, no residual words." # We call the agent which now returns the full response full_answer = agent(augmented_question) # For submission, we slice the "FINAL ANSWER: " prefix if "FINAL ANSWER: " in full_answer: submitted_answer = full_answer.split("FINAL ANSWER: ")[1] else: submitted_answer = full_answer answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": full_answer}) # Log the full 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}"}) 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) # 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"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 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 # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# GAIA Agent Evaluation Runner") # --- The existing part for submission --- with gr.Accordion("Official Scored Run", open=True): gr.Markdown( """ **Instructions:** 1. Log in to your Hugging Face account using the button below. 2. Click 'Run Evaluation & Submit All Answers' to run your agent against the official hidden dataset and submit for scoring. """ ) 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) # ============================================================================== # === SECTION 2: ADD THIS NEW UI BLOCK FOR SINGLE-QUESTION TESTING === # ============================================================================== with gr.Accordion("Agent Debugger / Single Question Tester", open=False): gr.Markdown( """ Use this section to test your agent's response to a specific question. This will not be submitted for scoring. """ ) test_question_input = gr.Textbox( label="Enter your question here", placeholder="e.g., What is 2+2?", lines=3 ) test_button = gr.Button("Run Single Test") test_output = gr.Textbox(label="Raw Agent Output", lines=10, interactive=False) # ============================================================================== # Wire up the main evaluation button run_button.click( fn=run_and_submit_all, outputs=[status_output, results_table] ) # Wire up the new test button test_button.click( fn=test_single_question, inputs=[test_question_input], outputs=[test_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 GAIA Agent Evaluation...") demo.launch(debug=True, share=False)