feat: Linux AT-SPI cursorless automation with ydotool fallback [#29]#45
Open
richard-devbot wants to merge 4 commits intoCursorTouch:mainfrom
Open
feat: Linux AT-SPI cursorless automation with ydotool fallback [#29]#45richard-devbot wants to merge 4 commits intoCursorTouch:mainfrom
richard-devbot wants to merge 4 commits intoCursorTouch:mainfrom
Conversation
…ursorTouch#29] Implements LinuxATSPIAutomation in operator_use/computer/linux/atapi.py: - click(app_name, element_name): traverses AT-SPI tree, invokes Action interface; falls back to ydotool click when pyatspi unavailable or element not found - type_text(app_name, element_name, text): sets text via EditableText/Value AT-SPI interfaces; falls back to ydotool type - is_available(): returns True when pyatspi D-Bus session reachable or ydotool binary present; returns False on non-Linux platforms All dependencies are optional — pyatspi import is wrapped in try/except, module never hard-fails at import time. ydotool is a system tool documented under the new [linux-automation] optional-dependency group in pyproject.toml. 27 tests added in tests/test_linux_atapi.py covering AT-SPI primary path, ydotool fallback, is_available() variants, and cross-platform import guard.
- test_control_center.py: update import from operator_use.agent.tools.builtin (deleted in main) to operator_use.tools.control_center; add side-effect import of operator_use.agent.tools to resolve circular import; update all patch paths. - test_computer_plugin.py: remove BEFORE_LLM_CALL assertions — 9f5d002 removed _state_hook registration from BEFORE_LLM_CALL by design (state captured inside computer_task loop, not on every main-agent LLM call). - test_browser_plugin.py: same BEFORE_LLM_CALL removal; register_hooks now only stores the hooks reference without registering any handler. Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
richard-devbot
force-pushed
the
richardson/phase2-linux-atapi
branch
from
7b0fa34 to
b218dba
Compare
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
1 participant
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.
Summary
Sub-component 1 of #29 (agent workspace isolation).
Adds
LinuxATSPIAutomationfor cursorless click/type on GNOME/GTK apps via the AT-SPI D-Bus accessibility API. Falls back toydotoolfor Wayland input injection when AT-SPI element lookup fails.pip install operator-use[linux-automation]Related: #29