Conversation
Summary of ChangesHello @wt17, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request focuses on enhancing the project's documentation and command-line interface to reflect the integration of new Gemini 3 models. The changes ensure that users are well-informed about the available models for the computer use tool and can easily configure their usage through updated instructions and CLI help text. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request adds documentation for the newly available Gemini 3 models. The changes are mostly in the README.md file, with a small update to the help text in main.py. My review focuses on improving the clarity of the documentation and the robustness of the command-line argument parsing. I've suggested correcting a discrepancy in the README.md regarding whether the --model argument is required, and recommended using argparse's choices parameter in main.py to validate model inputs.
README.md
Outdated
| | `--env` | The computer use environment to use. Must be one of the following: `playwright`, or `browserbase` | No | N/A | All | | ||
| | `--initial_url` | The initial URL to load when the browser starts. | No | https://www.google.com | All | | ||
| | `--highlight_mouse` | If specified, the agent will attempt to highlight the mouse cursor's position in the screenshots. This is useful for visual debugging. | No | False (not highlighted) | `playwright` | | ||
| | `--model` | The model to use. See the "Available Models" section for more information. | Yes | `gemini-2.5-computer-use-preview-10-2025` | All | |
There was a problem hiding this comment.
The --model argument is documented as required (Yes), but it has a default value (gemini-2.5-computer-use-preview-10-2025). Arguments with default values are not required for the user to specify. Please update the 'Required' column to 'No' to avoid confusion.
| | `--model` | The model to use. See the "Available Models" section for more information. | Yes | `gemini-2.5-computer-use-preview-10-2025` | All | | |
| | `--model` | The model to use. See the "Available Models" section for more information. | No | `gemini-2.5-computer-use-preview-10-2025` | All | |
There was a problem hiding this comment.
--model should not be required so users don't have to specify if they were not already doing it. wdyt?
main.py
Outdated
| "--model", | ||
| default='gemini-2.5-computer-use-preview-10-2025', | ||
| help="Set which main model to use.", | ||
| help="Set which main model to use. Should be one of the following: gemini-2.5-computer-use-preview-10-2025, gemini-3-flash-preview, gemini-3-pro-preview.", |
There was a problem hiding this comment.
Instead of listing the available models in the help string, it's better to use the choices parameter in argparse. This will enforce that only valid model names are provided, and argparse will automatically include the available choices in the help message, reducing redundancy and improving robustness.
"--model",
default='gemini-2.5-computer-use-preview-10-2025',
choices=['gemini-2.5-computer-use-preview-10-2025', 'gemini-3-flash-preview', 'gemini-3-pro-preview'],
help="Set which main model to use.",There was a problem hiding this comment.
I like adding the choices parameter for people to easily debug.
mquirosbloch
left a comment
There was a problem hiding this comment.
Please address both comments. Ty!
The computer use tool can now be used with one of the following models:
gemini-2.5-computer-use-preview-10-2025: This is the default model.gemini-3-flash-preview: The preview version of Gemini 3 Flash.gemini-3-pro-preview: The preview version of Gemini 3 Pro.