refactor: enhance ComputerToolBase functionality and add coordinate s…#102
Closed
danyalxahid-askui wants to merge 2 commits intoCL-1377-chat-enable-agent-to-search-through-displayfrom
Closed
Conversation
…caling - Added `_get_mouse_position_scaled` method to `ComputerToolBase` for retrieving and scaling mouse position. - Updated `action` method to return scaled mouse position. - Introduced `scale_coordinates_with_padding` function in `image_utils.py` for scaling coordinates with padding. - Cleaned up import statements for better organization and readability.
- Modified the return type of the `action` method in `Computer20250124Tool` to include `Coordinate` in addition to `Image.Image | None`, enhancing its functionality to return more comprehensive results.
adi-wan-askui
suggested changes
Jul 25, 2025
Comment on lines
+201
to
+218
| """Convert coordinates from an original image to a scaled and padded image. | ||
|
|
||
| This function takes coordinates from the original image and calculates | ||
| their corresponding position in an image that has been scaled and | ||
| padded to fit within `max_width` and `max_height`. | ||
|
|
||
| Args: | ||
| x (float): The x-coordinate in the original image. | ||
| y (float): The y-coordinate in the original image. | ||
| original_width (int): The width of the original image. | ||
| original_height (int): The height of the original image. | ||
| max_width (int): The maximum width of the output scaled and padded image. | ||
| max_height (int): The maximum height of the output scaled and padded image. | ||
|
|
||
| Returns: | ||
| Tuple[float, float]: A tuple of (scaled_x, scaled_y) coordinates | ||
| in the padded image. | ||
| """ |
Contributor
There was a problem hiding this comment.
I think we should adapt the docstring as it talks about an image where there is none 😆
Comment on lines
+235
to
+238
| if scaled_x < 0 or scaled_y < 0 or scaled_x > max_width or scaled_y > max_height: | ||
| error_msg = "Coordinates are outside the padded image area" | ||
| raise ValueError(error_msg) | ||
|
|
Contributor
There was a problem hiding this comment.
Can this even happen? Looks to me like this can be removed.
| ) | ||
|
|
||
|
|
||
| def scale_coordinates_with_padding( |
Contributor
There was a problem hiding this comment.
Can we reuse this inside the scale_image_with_padding?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…caling
_get_mouse_position_scaledmethod toComputerToolBasefor retrieving and scaling mouse position.actionmethod to return scaled mouse position.scale_coordinates_with_paddingfunction inimage_utils.pyfor scaling coordinates with padding.