test_run.py

from grader import grade_agent
from tasks import get_task

def run_test():
    print("--- Starting WarehouseMaster Task 1 Test ---")
    
    # Task 1: [0,0] -> [5,5] -> [0,0]
    # Sequence: 5 Right, 5 Up, Pick(4), 5 Left, 5 Down, Drop(5)
    sequence = [3]*5 + [0]*5 + [4] + [2]*5 + [1]*5 + [5]
    
    # Run the automated grader
    result = grade_agent(task_id=1, actions=sequence)
    
    print(f"Task Name: {get_task(1)['name']}")
    print(f"Status:    {result['status']}")
    print(f"Items:     {result['items_collected']}/{result['target_count']}")
    print(f"Steps:     {result['steps_taken']}")
    print(f"Final Score: {result['final_score']}/100")
    
    if result['is_success']:
        print("\n✅ Verification Successful: Environment and Grader are fully functional!")
    else:
        print("\n❌ Verification Failed: Logic error detected.")

if __name__ == "__main__":
    run_test()