import os import time import gradio as gr import requests import inspect import pandas as pd from agent import BasicAgent, GeminiAgent from typing import Optional from litellm.exceptions import RateLimitError, ContextWindowExceededError GEMINI_MODELS = [ # "gemini/gemini-2.5-flash-lite", # "gemini/gemini-2.5-flash", "gemini/gemma-3-27b-it" ] # Gemini agent configs MAX_TOTAL_REQUESTS = 10_000 request_count = 0 active_model_index = 0 # Helper: (re)load Gemini agent with fallback def load_gemini_agent(model_index: int) -> GeminiAgent: model_id = GEMINI_MODELS[model_index] print(f"Loading Gemini agent with model: {model_id}") return GeminiAgent(model_id=model_id) # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Create a Global Flag --- # This acts as our "Emergency Stop" signal interrupt_flag = False def request_stop(): global interrupt_flag interrupt_flag = True return "Stop requested. Finishing current task and submitting progress..." def run_and_submit_all( profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ global interrupt_flag interrupt_flag = False global request_count, active_model_index request_count = 0 active_model_index = 0 # --- 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 = load_gemini_agent(active_model_index) agent_type = "GeminiAgent" except Exception as main_agent_error: print(f"{agent_type} failed to initialize: {main_agent_error}.") try: agent = BasicAgent() agent_type = "BasicAgent" print(f"Falling back to {agent_type}.") except Exception as secondary_agent_error: print(f"{agent_type} failed to initialize: {secondary_agent_error}.") agent_type = "None" # replace with BasicAgent() if credits allow 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(f"Agent code: {agent_code}") print(f"Active agent: {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 = [] # track tokens used in the LAST 60 seconds tokens_used_this_minute = 0 TPM_LIMIT = 14000 # Keep a 1k safety buffer print(f"Running agent on {len(questions_data)} questions...") for item in questions_data: # --- Check the "Kill Switch" at the start of every loop iteration --- if interrupt_flag: print("🛑 STOP BUTTON PRESSED: Breaking loop and submitting partial results.") results_log.append({"Task ID": "MANUAL_STOP", "Question": "N/A", "Submitted Answer": "USER INTERRUPTED"}) break 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 # CONTENT FILTER SKIP (using .lower() for case-insensitivity) filter_keywords = ["chess", "video"] question_words = set(question_text.lower().split()) # Only matches if the exact word is used if any(word in question_words for word in filter_keywords): print(f"Skipping filtered question: {item}") results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": "SKIPPED: KEYWORD FILTER LOGIC"}) continue try: current_tokens = agent.check_token_safety(question_text) if (tokens_used_this_minute + current_tokens) > TPM_LIMIT: print(f"⏳TPM limit imminent ({tokens_used_this_minute}/{TPM_LIMIT}) Cooling down...") time.sleep(60) tokens_used_this_minute = 0 # Reset last_usage = agent.model.last_input_token_count + agent.model.last_output_token_count tokens_used_this_minute += last_usage if agent_type == "GeminiAgent" and request_count >= MAX_TOTAL_REQUESTS: raise RateLimitError("Global request cap reached") submitted_answer = agent(question_text) request_count +=1 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}) time.sleep(60 if not interrupt_flag else 1) # to not exceed RPM except RateLimitError as e: print(f"🛑 TARGET HIT: Rate limit reached.") print(f"Details: {e}") if agent_type == "GeminiAgent" and active_model_index + 1 < len(GEMINI_MODELS): active_model_index += 1 agent = load_gemini_agent(active_model_index) print("▶️ Switched to fallback Gemini model. Retrying question...") else: print("🛑 Stopping and submitting progress.") # This is where we break so the space doesn't hang results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": "STOPPED: API LIMIT REACHED"}) break except Exception as e: error_msg = str(e) print(f"Error running agent on task {task_id}: {error_msg}") # Check if the error message mentions a rate limit or quota if "RateLimitError" in error_msg or "429" in error_msg or "quota" in error_msg: print("🛑 CIRCUIT BREAKER TRIGGERED: Quota reached. Stopping to save progress.") # Record the stop in your log so you know where you left off results_log.append({ "Task ID": task_id, "Status": "STOPPED: DAILY QUOTA EXCEEDED" }) break # This WILL stop the loop else: results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}) # We don't 'break' here, we try the next question 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("# Basic Agent Evaluation 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. """ ) gr.LoginButton() with gr.Row(): run_button = gr.Button("Run Evaluation & Submit All Answers") stop_button = gr.Button("Stop & Submit Progress", variant="stop") 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) run_button.click( fn=run_and_submit_all, outputs=[status_output, results_table] ) # --- Connect the Stop Button --- stop_button.click( fn=request_stop, 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)