Add hosted GBOX agent for OSWorld evaluation (#376)

lib_run_single.py

@@ -10,12 +10,15 @@ logger = logging.getLogger("desktopenv.experiment")
 
 def run_single_example(agent, env, example, max_steps, instruction, args, example_result_dir, scores):
     runtime_logger = setup_logger(example, example_result_dir)
-    try:
-        agent.reset(runtime_logger)
-    except Exception as e:
-        agent.reset()
 
+    # Reset environment first to get fresh VM IP
     env.reset(task_config=example)
+
+    # Reset agent with fresh VM IP (for snapshot reverts)
+    try:
+        agent.reset(runtime_logger, vm_ip=env.vm_ip)
+    except Exception as e:
+        agent.reset(vm_ip=env.vm_ip)
     
     time.sleep(60) # Wait for the environment to be ready
     obs = env._get_obs() # Get the initial observation