Merge remote-tracking branch 'upstream/fix/aws-proxy'

desktop_env/controllers/setup.py

@@ -47,11 +47,12 @@ class SetupController:
         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
+        self.use_proxy: bool = False
 
     def reset_cache_dir(self, cache_dir: str):
         self.cache_dir = cache_dir
 
-    def setup(self, config: List[Dict[str, Any]])-> bool:
+    def setup(self, config: List[Dict[str, Any]], use_proxy: bool = False)-> bool:
         """
         Args:
             config (List[Dict[str, Any]]): list of dict like {str: Any}. each
@@ -59,10 +60,11 @@ class SetupController:
                 {
                     "type": str, corresponding to the `_{:}_setup` methods of
                       this class
-                    "parameters": dick like {str, Any} providing the keyword
+                    "parameters": dict like {str, Any} providing the keyword
                       parameters
                 }
         """  
+        self.use_proxy = use_proxy
         # make sure connection can be established
         logger.info(f"try to connect {self.http_server}")
         retry = 0
@@ -264,6 +266,9 @@ class SetupController:
         if not shell and isinstance(command, str) and len(command.split()) > 1:
             logger.warning("Command should be a list of strings. Now it is a string. Will split it by space.")
             command = command.split()
+            
+        if command[0] == "google-chrome" and self.use_proxy:
+            command.append("--proxy-server=http://127.0.0.1:18888")  # Use the proxy server set up by _proxy_setup
 
         payload = json.dumps({"command": command, "shell": shell})
         headers = {"Content-Type": "application/json"}
@@ -446,6 +451,19 @@ class SetupController:
         Args:
             client_password (str): Password for sudo operations, defaults to "password"
         """
+        retry = 0
+        while retry < MAX_RETRIES:
+            try:
+                _ = requests.get(self.http_server + "/terminal")
+                break
+            except:
+                time.sleep(5)
+                retry += 1
+                logger.info(f"retry: {retry}/{MAX_RETRIES}")
+            
+            if retry == MAX_RETRIES:
+                return False
+            
         # Get proxy from global proxy pool
         proxy_pool = get_global_proxy_pool()
         current_proxy = proxy_pool.get_next_proxy()
@@ -458,14 +476,21 @@ class SetupController:
         proxy_url = proxy_pool._format_proxy_url(current_proxy)
         logger.info(f"Setting up proxy: {current_proxy.host}:{current_proxy.port}")
         
-        # Configure system proxy environment variables
+        # Configure system proxy environment variables  
         proxy_commands = [
-            f"echo '{client_password}' | sudo -S bash -c \"echo 'export http_proxy={proxy_url}' >> /etc/environment\"",
+            f"echo '{client_password}' | sudo -S bash -c \"apt-get update\"", ## TODO: remove this line if ami is already updated
-            f"echo '{client_password}' | sudo -S bash -c \"echo 'export https_proxy={proxy_url}' >> /etc/environment\"",
+            f"echo '{client_password}' | sudo -S bash -c \"apt-get install -y tinyproxy\"", ## TODO: remove this line if tinyproxy is already installed
-            f"echo '{client_password}' | sudo -S bash -c \"echo 'export HTTP_PROXY={proxy_url}' >> /etc/environment\"",
+            f"echo '{client_password}' | sudo -S bash -c \"echo 'Port 18888' > /tmp/tinyproxy.conf\"",
-            f"echo '{client_password}' | sudo -S bash -c \"echo 'export HTTPS_PROXY={proxy_url}' >> /etc/environment\"",
+            f"echo '{client_password}' | sudo -S bash -c \"echo 'Allow 127.0.0.1' >> /tmp/tinyproxy.conf\"",
+            f"echo '{client_password}' | sudo -S bash -c \"echo 'Upstream http {current_proxy.username}:{current_proxy.password}@{current_proxy.host}:{current_proxy.port}' >> /tmp/tinyproxy.conf\"",
+            
+            # CML commands to set environment variables for proxy
+            f"echo 'export http_proxy={proxy_url}' >> ~/.bashrc",
+            f"echo 'export https_proxy={proxy_url}' >> ~/.bashrc",
+            f"echo 'export HTTP_PROXY={proxy_url}' >> ~/.bashrc",
+            f"echo 'export HTTPS_PROXY={proxy_url}' >> ~/.bashrc",
         ]
-        
+
         # Execute all proxy configuration commands
         for cmd in proxy_commands:
             try:
@@ -475,6 +500,8 @@ class SetupController:
                 proxy_pool.mark_proxy_failed(current_proxy)
                 raise
         
+        self._launch_setup(["tinyproxy -c /tmp/tinyproxy.conf -d"], shell=True)
+        
         # Reload environment variables
         reload_cmd = "source /etc/environment"
         try:

desktop_env/desktop_env.py

@@ -215,10 +215,13 @@ class DesktopEnv(gym.Env):
                 logger.info("Environment is clean, skipping snapshot revert (provider: {}).".format(self.provider_name))
 
             if task_config is not None:
+                if task_config.get("proxy", False) and self.enable_proxy:
+                    # If using proxy and proxy is enabled, set up the proxy configuration
+                    self.setup_controller._proxy_setup()
                 self._set_task_info(task_config)
                 self.setup_controller.reset_cache_dir(self.cache_dir)
                 logger.info("Setting up environment...")
-                success = self.setup_controller.setup(self.config)
+                success = self.setup_controller.setup(self.config, task_config.get("proxy", False) and self.enable_proxy)
                 if success:
                     # Mark environment as used when setup is successfully executed
                     if self.config:  # Only mark as used if there were actual setup operations
@@ -235,10 +238,6 @@ class DesktopEnv(gym.Env):
                 break
             
         logger.info("Environment setup complete.")
-    
-        if task_config.get("proxy", False) and self.enable_proxy:
-            # If using proxy and proxy is enabled, set up the proxy configuration
-            self.setup_controller._proxy_setup()
 
         observation = self._get_obs()
         return observation

desktop_env/providers/__init__.py

@@ -21,14 +21,8 @@ def create_vm_manager_and_provider(provider_name: str, region: str, use_proxy: b
         return VirtualBoxVMManager(), VirtualBoxProvider(region)
     elif provider_name in ["aws", "amazon web services"]:
         from desktop_env.providers.aws.manager import AWSVMManager
-        if use_proxy:
+        from desktop_env.providers.aws.provider import AWSProvider
-            # Use proxy-enabled AWS provider
+        return AWSVMManager(), AWSProvider(region)
-            from desktop_env.providers.aws.provider_with_proxy import AWSProviderWithProxy
-            return AWSVMManager(proxy_config_file="dataimpulse_proxy_config.json"), AWSProviderWithProxy(region, proxy_config_file="dataimpulse_proxy_config.json")
-        else:
-            # Use regular AWS provider
-            from desktop_env.providers.aws.provider import AWSProvider
-            return AWSVMManager(), AWSProvider(region)
     elif provider_name == "azure":
         from desktop_env.providers.azure.manager import AzureVMManager
         from desktop_env.providers.azure.provider import AzureProvider