Skip to content

Feature Request: Add scroll to element tool #146

@ctsstc

Description

@ctsstc

I've noticed my agent sending key presses to move the screen around and constantly taking screenshots to see if it has made it to the element it wants to view on the page. This is very token intensive sending lots of images as it scrolls down the page looking for something. I often see it do something like:

  1. Send home key press
  2. Take screenshot
  3. Send down arrow key press
  4. Take screenshot
  5. Loop 3-4 until it finds what it wants.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions