[codex] Add macOS Use manifest safety tests#2
Draft
mimeding wants to merge 1 commit into
Draft
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds manifest safety tests for macOS Use screenshot, action-observe, and session tools, and makes the display listing test deterministic in no-display runners.
Business Rationale
Desktop automation needs very clear tool contracts because actions can change local applications. These tests make capture, stale-recovery, and telemetry-only session semantics explicit for safer automation.
Coding Rationale
The plugin already exposes the automation behavior through manifest descriptions and tool schemas. This PR codifies those contracts in tests and removes a display-count assumption that can fail in CI or headless environments.
Expected LLM Performance Improvement
Models should better understand when to observe, act, and re-observe after mutations, which improves recovery from stale UI snapshots and reduces blind desktop automation steps.
Changes
Test Plan
swift testswift build -c releaseswift-format lint --strict Tests/osaurus_macos_use_tests/PluginTests.swiftgit diff --check