​
Functions

def click(self, x: int, y: int, click_type: str = "left") -> None:
    """
    Move the mouse to (x, y) and click the specified button.
    click_type can be 'left', 'middle', or 'right'.
    """
Arguments:
  • x, y (int): The screen coordinates to move the mouse.
  • click_type (str): The mouse button to click ("left", "middle", or "right").
Returns:
  • None
def scroll(
    self,
    x: int,
    y: int,
    scroll_x: int = 0,
    scroll_y: int = 0
) -> None:
    """
    Move to (x, y) and scroll horizontally or vertically.
    """
Arguments:
  • x, y (int): The screen coordinates to move the mouse.
  • scroll_x (int): Horizontal scroll offset.
  • Negative => Scroll left (button 6)
  • Positive => Scroll right (button 7)
  • scroll_y (int): Vertical scroll offset.
  • Negative => Scroll up (button 4)
  • Positive => Scroll down (button 5)
Behavior:
  • Moves the mouse to (x, y).
  • Scrolls by scroll_x and scroll_y
Returns:
  • None
def keypress(self, keys: list[str]) -> None:
    """
    Press (and possibly hold) keys in sequence.
    """
Arguments:
  • keys (list[str]): A list of keys to press. Example: ["CTRL", "f"] for Ctrl+F.
Behavior:
  • Executes a keypress
  • Supports shortcuts like Ctrl+Fs
Returns:
  • None
def type_text(self, text: str) -> None:
    """
    Type a string of text (like using a keyboard) at the current cursor location.
    """
Arguments:
  • text (str): The string of text to type.
Behavior:
  • Types a string of text at the current cursor location.
Returns:
  • None
def get_screenshot(self) -> str:
    """
    Takes a screenshot of the current desktop.
    Returns the base64-encoded PNG screenshot.
    """
Behavior:
  • Takes a screenshot as a png
  • Captures the base64 result.
  • Returns that base64 string.
Returns:
  • (str): A base64-encoded PNG screenshot.
Exceptions:
  • RuntimeError if the screenshot command fails.
def goto(self, url: str) -> None:
    """
    Open Firefox in the container and navigate to the specified URL in a new tab.
    """
Arguments:
  • url (str): The URL to navigate to (e.g., https://example.com).
Behavior:
  • Opens Firefox in the container and navigates to the specified URL in a new tab
Returns:
  • None
def get_page_html(self, query="return document.documentElement.outerHTML;"):
    """
    Get the HTML content of the currently displayed webpage using Marionette.
    
    Args:
        query: JavaScript query to retrieve the HTML content. Defaults to retrieving the full DOM HTML.
    
    Returns:
        str: The HTML content of the current page, or an error message if retrieval fails.
    """
Arguments:
  • query (str): JavaScript query to retrieve the HTML content. Defaults to 'return document.documentElement.outerHTML;', which returns the full DOM HTML.
Behavior:
  • Uses the underlying agent to execute a JavaScript query and retrieve the current webpage’s HTML content.
Returns:
  • (str): The HTML content of the current page, or an error message if retrieval fails.