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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request introduces a new agent for OpenAI's Computer-Using Agent (CUA) and includes various updates to support this new functionality. The changes span multiple files, adding new agent settings, scripts, and key mappings. Below are the most important changes:
New Agent Integration:
api/models.py: AddedOPENAI_COMPUTER_USEto theModelProviderenum and updated thedefault_modelfunction to include a default model for this provider. [1] [2]api/plugins/__init__.py: Included the newopenai_computer_use_agentin the imports and updatedWebAgentTypeandSettingConfigto support the new agent. [1] [2] [3] [4]api/plugins/openai_computer_use/__init__.py: Added the initialization for theopenai_computer_use_agent.Supporting Scripts and Mappings:
api/plugins/openai_computer_use/cursor_overlay.py: Introduced a script to inject a visible cursor overlay into the browser for better tracking of agent actions.api/plugins/openai_computer_use/key_mapping.py: Created a mapping of OpenAI CUA keys to Playwright-compatible keys and a function to translate these keys.api/plugins/openai_computer_use/tools.py: Added various tools and actions that the agent can perform, such as clicking, typing, scrolling, and navigating.Prompt and Settings Updates:
api/plugins/openai_computer_use/prompts.py: Defined a system prompt for the OpenAI Computer-Using Agent.api/utils/types.py: Updated theAgentSettingsclass to include new settings for the agent, such as viewport dimensions and maximum steps.Additional Changes:
app/chat/page.tsx: Added a new handler for chat responses and refactored the rendering of chat messages. [1] [2] [3]app/contexts/SettingsContext.tsx: Updated theAgentSettingsinterface to include new settings for the OpenAI agent.package.json: Modified the scripts for starting the FastAPI server to use the virtual environment's Python interpreter.