[Feature] Initialize and Implement Aguvis Evaluation on OSWorld (#98)

* Initialize Aguvis eval on OSWorld

* Debug

* Debug

* v1, internal version

* Add experiments script

* Fix minor bugs

* Update new endpoint

* Update ip

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Fix model name

* Fix docker close issues; update prompting

* Fix missed

* Fix the default port to avoid crashing on examples like '_update_browse_history_setup'

* Fix server and chromium ports in setup

* Revert and add missed dependency

* Add VLC port for docker

* Update

* Clean

---------

Co-authored-by: Tianbao Xie <tianbaoxie@U-492FC39R-0217.local>
Co-authored-by: FredWuCZ <fredwucz@outlook.com>

desktop_env/controllers/setup.py

@@ -28,10 +28,11 @@ FILE_PATH = os.path.dirname(os.path.abspath(__file__))
 
 
 class SetupController:
-    def __init__(self, vm_ip: str, server_port: int, chromium_port: int, cache_dir: str):
+    def __init__(self, vm_ip: str, server_port: int = 5000, chromium_port: int = 9222, vlc_port: int = 8080, cache_dir: str = "cache"):
         self.vm_ip: str = vm_ip
         self.server_port: int = server_port
         self.chromium_port: int = chromium_port
+        self.vlc_port: int = vlc_port
         self.http_server: str = f"http://{vm_ip}:{server_port}"
         self.http_server_setup_root: str = f"http://{vm_ip}:{server_port}/setup"
         self.cache_dir: str = cache_dir
@@ -532,7 +533,7 @@ class SetupController:
 
         """
         host = self.vm_ip
-        port = 9222  # fixme: this port is hard-coded, need to be changed from config file
+        port = self.chromium_port
 
         remote_debugging_url = f"http://{host}:{port}"
         with sync_playwright() as p:
@@ -643,7 +644,7 @@ class SetupController:
 
         logger.info('Fake browsing history added successfully.')
 
-        controller = PythonController(self.vm_ip)
+        controller = PythonController(self.vm_ip, self.server_port)
 
         # get the path of the history file according to the platform
         os_type = controller.get_vm_platform()