feat(computer): add macOS support for computer tool #324
Conversation
This file contains 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
Owner
ErikBjare
commented
Dec 11, 2024
ErikBjare
commented
- Add native macOS implementations using osascript and screencapture
- Add platform detection and conditional execution
- Improve security with input sanitization
- Add comprehensive error handling
- Update documentation with macOS-specific details
- Add native macOS implementations using osascript and screencapture - Add platform detection and conditional execution - Improve security with input sanitization - Add comprehensive error handling - Update documentation with macOS-specific details
Codecov ReportAttention: Patch coverage is
✅ All tests successful. No failed tests found.
Additional details and impacted files@@ Coverage Diff @@
## master #324 +/- ##
==========================================
- Coverage 72.79% 71.64% -1.16%
==========================================
Files 67 67
Lines 4933 5000 +67
==========================================
- Hits 3591 3582 -9
- Misses 1342 1418 +76
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
ErikBjare
commented
Dec 12, 2024
Comment on lines
+476
to
+505
| Assistant: I'll capture the current screen using the native screenshot tool. | ||
| {ToolUse("ipython", [], 'computer("screenshot")').to_output(tool_format)} | ||
| System: Viewing image... | ||
|
|
||
| User: Type "Hello, World!" into the active window | ||
| Assistant: I'll type the text with realistic delays. | ||
| Assistant: I'll type the text with realistic delays using the native input method. | ||
| {ToolUse("ipython", [], 'computer("type", text="Hello, World!")').to_output(tool_format)} | ||
| System: Typed text: Hello, World! | ||
|
|
||
| User: Move the mouse to coordinates (100, 200) and click | ||
| Assistant: I'll move the mouse and perform a left click. | ||
| Assistant: I'll move the mouse and perform a left click using native mouse control. | ||
| {ToolUse("ipython", [], 'computer("mouse_move", coordinate=(100, 200))').to_output(tool_format)} | ||
| System: Moved mouse to 100,200 | ||
| {ToolUse("ipython", [], 'computer("left_click")').to_output(tool_format)} | ||
| System: Performed left_click | ||
|
|
||
| User: Press Ctrl+C | ||
| Assistant: I'll send the Control+C key sequence. | ||
| Assistant: I'll send the Control+C key sequence using platform-appropriate key names. | ||
| {ToolUse("ipython", [], 'computer("key", text="Control_L+c")').to_output(tool_format)} | ||
| System: Sent key sequence: Control_L+c | ||
|
|
||
| User: Get the current mouse position | ||
| Assistant: I'll get the cursor position using the native method. | ||
| {ToolUse("ipython", [], 'computer("cursor_position")').to_output(tool_format)} | ||
| System: Cursor position: X=512,Y=384 | ||
|
|
||
| User: Double-click at current position | ||
| Assistant: I'll perform a double-click using the native method. | ||
| {ToolUse("ipython", [], 'computer("double_click")').to_output(tool_format)} | ||
| System: Performed double_click |
There was a problem hiding this comment.
Silly repetitive "using the native method"
|
@Miyou Wanna give this a spin? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.