batch

ufo/agents/agent/host_agent.py

@@ -235,10 +235,16 @@ def create_app_agent(
         :return: The app agent.
         """
 
-        if mode == "normal":
-
-            agent_name = "AppAgent/{root}/{process}".format(
-                root=application_root_name, process=application_window_name
+        if mode == "normal" or "batch_normal":
+
+            agent_name = (
+                "AppAgent/{root}/{process}".format(
+                    root=application_root_name, process=application_window_name
+                )
+                if mode == "normal"
+                else "BatchAgent/{root}/{process}".format(
+                    root=application_root_name, process=application_window_name
+                )
             )
 
             app_agent: AppAgent = self.create_subagent(
@@ -273,26 +279,6 @@ def create_app_agent(
                 api_prompt=configs["API_PROMPT"],
                 app_info_prompt=app_info_prompt,
             )
-        elif mode == "batch_normal":
-
-            # Load additional app info prompt.
-            app_info_prompt = configs.get("APP_INFO_PROMPT", None)
-
-            agent_name = "BatchAgent/{root}/{process}".format(
-                root=application_root_name, process=application_window_name
-            )
-
-            # Create the app agent in the batch_normal mode.
-            app_agent: AppAgent = self.create_subagent(
-                agent_type="app",
-                agent_name=agent_name,
-                process_name=application_window_name,
-                app_root_name=application_root_name,
-                is_visual=configs["APP_AGENT"]["VISUAL_MODE"],
-                main_prompt=configs["APPAGENT_PROMPT"],
-                example_prompt=configs["APPAGENT_EXAMPLE_PROMPT"],
-                api_prompt=configs["API_PROMPT"],
-            )
 
         else:
             raise ValueError(f"The {mode} mode is not supported.")

ufo/module/sessions/plan_reader.py

@@ -25,6 +25,7 @@ def __init__(self, plan_file: str):
         with open(plan_file, "r") as f:
             self.plan = json.load(f)
         self.remaining_steps = self.get_steps()
+        self.support_apps = ["word", "excel", "powerpoint"]
 
     def get_close(self) -> bool:
         """
@@ -56,7 +57,7 @@ def get_operation_object(self) -> str:
         :return: The operation object.
         """
 
-        return self.plan.get("object", None)
+        return self.plan.get("object", None).lower()
 
     def get_initial_request(self) -> str:
         """
@@ -99,6 +100,14 @@ def get_file_path(self):
 
         return os.path.join(file_path, file)
 
+    def get_support_apps(self) -> List[str]:
+        """
+        Get the support apps in the plan.
+        :return: The support apps in the plan.
+        """
+
+        return self.support_apps
+
     def get_host_request(self) -> str:
         """
         Get the request for the host agent.
@@ -107,7 +116,7 @@ def get_host_request(self) -> str:
 
         task = self.get_task()
         object_name = self.get_operation_object()
-        if object_name:
+        if object_name in self.support_apps:
             request = task
         else:
             request = f"Open the application of {task}. You must output the selected application with their control text and label even if it is already open."

ufo/module/sessions/session.py

@@ -348,6 +348,7 @@ def __init__(
         super().__init__(task, should_evaluate, id)
         self.plan_file = plan_file
         self.plan_reader = PlanReader(plan_file)
+        self.support_apps = self.plan_reader.get_support_apps()
         self.close = self.plan_reader.get_close()
         self.task_name = task.split("/")[1]
         self.object_name = ""
@@ -474,13 +475,15 @@ def setup_application_environment(self):
         if self.object_name:
             suffix = os.path.splitext(self.object_name)[1]
             self.app_name = self.get_app_name(suffix)
-            app_com = self.get_app_com(suffix)
+            if self.app_name not in self.support_apps:
+                return  # The app is not supported, so we don't need to setup the environment.
             file = self.plan_reader.get_file_path()
             code_snippet = f"import os\nos.system('start {self.app_name} \"{file}\"')"
             code_snippet = code_snippet.replace("\\", "\\\\")  # escape backslashes
             try:
                 exec(code_snippet, globals())
-                time.sleep(3)  # wait for the app to boot
+                app_com = self.get_app_com(suffix)
+                time.sleep(2)  # wait for the app to boot
                 word_app = win32com.client.Dispatch(app_com)
                 word_app.WindowState = 1  # wdWindowStateMaximize
             except Exception as e: