Conversation
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A repeated
use_desktoptool call currently creates a new random receipt and can dispatch the same click or key input again. This matters when the first response is lost or a model turn repeats an uncertain step.Require an
operationIdfor the agent's desktop tool and scope it to the chat request or task. Persist a stable receipt ID and the hash of the full validated action before input dispatch. A repeated ID returns the prior receipt and retained screenshot, if available, without sending new input; a changed action with that ID conflicts. Direct desktop API calls keep their existing behavior.A synthetic E2B driver fixture demonstrates the before/after effect count, restart replay, changed-input conflict, full typed-text binding beyond the receipt label, and uncertain input replay. No live E2B sandbox or user account was used.
Verification: 341 upstream tests passed; server and mobile typecheck, changed-file Biome, and diff whitespace check passed.