Add Gemini 3.6 Flash and 3.5 Flash-Lite; default to Gemini 3.6 Flash

[mquirosbloch]

Reflect the latest model launches in the available models list and switch the default model from gemini-3.5-flash to gemini-3.6-flash.

• README: list gemini-3.6-flash (new default) and gemini-3.5-flash-lite, and update the --model default in the CLI arguments table.
• main.py: change the --model default to gemini-3.6-flash.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Code Review

This pull request updates the default model to gemini-3.6-flash in both the documentation (README.md) and the CLI argument parser (main.py), and documents additional supported models. The review feedback suggests restricting the --model CLI argument to the predefined set of supported models using the choices parameter in argparse to improve validation, and using double quotes for consistency.

[gemini-code-assist]

To improve validation and automatically generate helpful error messages, we should restrict the --model argument to the predefined set of supported models using the choices parameter in argparse. Additionally, let's use double quotes for the default value to maintain consistency with the rest of the file.

    parser.add_argument(
        "--model",
        default="gemini-3.6-flash",
        choices=(
            "gemini-3.6-flash",
            "gemini-3.5-flash-lite",
            "gemini-3.5-flash",
            "gemini-2.5-computer-use-preview-10-2025",
            "gemini-3-flash-preview",
            "gemini-3.1-pro-preview",
        ),
        help="Set which main model to use.",
    )

References

1. Use the choices parameter in argparse for arguments with a predefined set of valid string values to enable automatic validation and help message generation.