feat: add Grok 4.5 computer use support#102
Merged
Merged
Conversation
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 437f15c. Configure here.
NikhilShahi
approved these changes
Jul 13, 2026
Align created_at, completed_at, and error with CuaStepResponse so completed Grok task payloads parse without Pydantic validation errors. Reuse CUA step helper models for structured error, incomplete_details, and reasoning fields. Co-authored-by: Shri Sukhani <[email protected]>
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add SDK support for the new Grok 4.5 computer-use agent (
grokcu) introduced inbrowserctrl#1212.Changes
GrokComputerUseLlm(grok-4.5) andGrokReasoningEffort(low/medium/high) constants.GrokComputerUseApiKeys,StartGrokComputerUseTaskParams, and response models (GrokComputerUseTaskResponse,GrokComputerUseTaskData, etc.).GrokComputerUseManager(client.agents.grok_computer_use) wiring to/task/grok-computer-useendpoints.hyperbrowser.models.Validation
poetry run ruff check .poetry run ruff format .(ran, no issues)Link to Devin session: https://app.devin.ai/sessions/5a70ddea4e9f4f0cb35baef951897bed
Requested by: @shrisukhani
Note
Low Risk
Additive SDK surface parallel to existing computer-use agents; no changes to auth, billing, or core transport beyond new routes and models.
Overview
Adds Grok computer-use as a first-class agent in the Python SDK, mirroring existing Gemini/Claude computer-use integrations.
New Pydantic models cover start params (task,
grok-4.5LLM, reasoning effort, session/options, optional xAI API keys,useComputerAction), job responses, step payloads (reusing CUA step error/reasoning shapes), and metadata.GrokComputerUseLlmandGrokReasoningEffortare added toconstsand re-exported fromhyperbrowser.models.Sync and async
GrokComputerUseManagerexposestart,get,get_status,stop, andstart_and_waitagainst/task/grok-computer-use(with polling on terminal statuses).client.agents.grok_computer_useis wired on both clientAgentsfacades.A unit test asserts
GrokComputerUseTaskResponseparses xAI-style step JSON (snake_case fields, nested error/incomplete/reasoning).Reviewed by Cursor Bugbot for commit b0120da. Bugbot is set up for automated code reviews on this repo. Configure here.