Class MobileUse

eval/utils/utils_qwen/agent_function_call.py:7–144

@register_tool("mobile_use")
class MobileUse(BaseTool):
    @property
    def description(self):
        return f"""
Use a touchscreen to interact with a mobile device, and take screenshots.
* This is an interface to a mobile device with touchscreen. You can perform actions like clicking, typing, swiping, etc.
* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions.
* The screen's resolution is {self.display_width_px}x{self.display_height_px}.
* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.
""".strip()

    parameters = {
        "properties": {
            "action": {
                "description": """
The action to perform. The available actions are:
* `key`: Perform a key event on the mobile device.
    - This supports adb's `keyevent` syntax.
    - Examples: "volume_up", "volume_down", "power", "camera", "clear".
* `click`: Click the point on the screen with coordinate (x, y).
* `long_press`: Press the point on the screen with coordinate (x, y) for specified seconds.
* `swipe`: Swipe from the starting point with coordinate (x, y) to the end point with coordinates2 (x2, y2).
* `type`: Input the specified text into the activated input box.
* `system_button`: Press the system button.
* `open`: Open an app on the device.
* `wait`: Wait specified seconds for the change to happen.
* `terminate`: Terminate the current task and report its completion status.
""".strip(),
                "enum": [
                    "key",
                    "click",
                    "long_press",
                    "swipe",
                    "type",
                    "system_button",
                    "open",
                    "wait",
                    "terminate",
                ],
                "type": "string",
            },
            "coordinate": {
                "description": "(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=click`, `action=long_press`, and `action=swipe`.",
                "type": "array",
            },
            "coordinate2": {
                "description": "(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=swipe`.",
                "type": "array",
            },
            "text": {
                "description": "Required only by `action=key`, `action=type`, and `action=open`.",
                "type": "string",
            },
            "time": {
                "description": "The seconds to wait. Required only by `action=long_press` and `action=wait`.",
                "type": "number",
            },
            "button": {