REDEFINING BROWSER INTELLIGENCE

for task_id in tasks:
    env = AWE(
      api_key=foundry_api_key, 
      task_id=task_id, 
      record_events=True
    )

    task = await env.get_task()
    await env.reset()

    try:
        cdp_url = await env.get_cdp_url()
    except Exception as e:
        print(f"Error executing task {task.id}: {e}")
        return

    if not env.id:
        print("Task execution failed due to invalid initialization")
        return

    # Run the agent with run_st_async integration
    result = await agent(
        task.prompt,
        cdp_url,
        task.start_url,
        task.login_credentials,
        task.payment_details,
        task.additional_instructions,
    )

    if not result.get("success", False):
        print(f"Agent execution failed: 
          {result.get('error', 'Unknown error')}")
        return

    # get the result, which is the final state of the environment
    final_state = await env.get_state()

    mutations = await env.get_state_mutations()
    events = await env.get_events()

    # compare the result with the ground truth
    score = heuristic(final_state, task.ground_truth)