feat: add computer use (desktop control) for openai, codex, and anthropic#34
Merged
Conversation
# Conflicts: # crates/goat-agent/src/lib.rs
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 computer use to goat: the model can take screenshots and drive the mouse/keyboard on the local desktop. Delivered as a built-in
Computerfunction tool (cross-platform viaenigo+xcap), gated behind an opt-in config flag. Screenshots flow back as multimodal tool results, which required broadening the tool/content layer to carry images. The exact wire format (function tool +function_call_outputwithinput_image) was validated live against the Codex backend.Verification
cargo fmt --all -- --check— passedcargo clippy --workspace --all-targets -- -D warnings— passedcargo test --workspace— passed (57 suites)