Repository navigation
Add OpenAI computer-use mode with Responses, Decisions, and API-key settings - #1
Draft
Ambassators wants to merge 1 commit into
Draft
Ambassators wants to merge 1 commit into
Ambassators wants to merge 1 commit into
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds an optional OpenAI computer-use mode for approved app sessions. Users enter their API key in local Settings, choose models and a step limit, then start a run from the UI or
computer_api_runover MCP. Responses proposes a structured action and Decisions evaluates it; Decisions itself only returns classification/scoring answers.The loop requires local consent to send screenshots and app text to OpenAI, reviews each action, reobserves before input, and executes each approved action once. It supports cancellation, confidence/refusal handoffs, retry keys, connection/grant isolation, and step/time limits. Existing macOS Codex app-server and Windows native session controls supply capture/input. The key is write-only, saved separately with restricted Unix permissions, and omitted from UI state, MCP results and activity logs; storage is plaintext, not OS-keychain encrypted.
Validation:
npm test— 122 passed, 5 platform-specific skips, 0 failures.npm run check— 60/60 JavaScript files passed.git diff --checkpassed. Tests use mocked OpenAI/desktop responses and real local HTTP authentication routes. Browser verification was blocked by a missing Chromium executable and failed browser download. Live API access, model behavior, and desktop input remain unverified without a user API key and macOS/Windows environment.Setup, outcomes, limits, privacy and official API references are documented in
docs/OPENAI_COMPUTER_USE.md.