lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add flexible recording control and improve execution logging

Browse Source
This commit is contained in:
cui0711
2026-01-30 16:28:13 +08:00
parent 47bcfc0f0b
commit 716d82f4d1
4 changed files with 67 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
desktop_env/desktop_env.py
View File

@@ -101,7 +101,7 @@ class DesktopEnv(gym.Env):
provider_name: str = "vmware",
region: str = None,
path_to_vm: str = None,
snapshot_name: str = "init_state",
snapshot_name: str = "snapshot",
action_space: str = "pyautogui",
cache_dir: str = "cache",
screen_size: Tuple[int] = (int(os.environ.get("SCREEN_WIDTH", 1920)), int(os.environ.get("SCREEN_HEIGHT", 1080))),
@@ -117,7 +117,7 @@ class DesktopEnv(gym.Env):
provider_name (str): virtualization provider name, default to "vmware"
region (str): the region for allocate machines, work for cloud services, default to "us-east-1"
path_to_vm (str): path to .vmx file
snapshot_name (str): snapshot name to revert to, default to "init_state"
snapshot_name (str): snapshot name to revert to, default to "snapshot"
action_space (str): "computer_13" | "pyautogui"
cache_dir (str): cache directory to cache task-related stuffs like
reference file for evaluation
@@ -265,7 +265,7 @@ class DesktopEnv(gym.Env):
self.current_use_proxy = task_use_proxy
if self.is_environment_used:
logger.info("Environment has been used, reverting to snapshot {}...".format(self.snapshot_name))
logger.info("Environment has been used, reverting to snapshot: {}...".format(self.snapshot_name))
self._revert_to_snapshot()
logger.info("Starting emulator...")
self._start_emulator()
@@ -402,6 +402,7 @@ class DesktopEnv(gym.Env):
if self.action_space == "computer_13":
# the set of all possible actions defined in the action representation
logger.info(f"======executing here======{self.action_space}========================")
self.controller.execute_action(action)
elif self.action_space == "pyautogui" or self.action_space == "claude_computer_use":
if action in ['WAIT', 'FAIL', 'DONE'] or (type(action) == dict and action.get('action_type') in ['WAIT', 'FAIL', 'DONE']):
@@ -411,6 +412,8 @@ class DesktopEnv(gym.Env):
if type(action) == str:
# Fix PyAutoGUI '<' character bug before execution
fixed_command = _fix_pyautogui_less_than_bug(action)
logger.info(f"======executing here======{self.action_space}========================")
logger.info(f"Fixed command: {fixed_command}")
self.controller.execute_python_command(fixed_command)
elif type(action) == dict:
# Fix PyAutoGUI '<' character bug before execution