args_runner.py s/name/task_name/

[fredsa]

Fix getting started flow

run-evals \
  --task question_answer \
  --model google/gemini-2.5-flash \
  --dataset ./my_first_sample.json

which fails with:

Failed to run evaluation: 'task_name'

Issue Link:

What is the link to the issue this cherry-pick is addressing?

https://github.com/flutter/flutter/issues/< Replace with issue link here >

It's a good idea to open an issue first for discussion.

• All tests pass
• Appropriate inline docstrings changes are included in the PR
• Appropriate documentation changes to the docs site are included in the PR

[gemini-code-assist]

Summary of Changes

Hello, 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 updates the task initialization logic within the argument runner to ensure consistent naming conventions for task definitions, facilitating a smoother execution flow for evaluation tasks.

Highlights

• Refactoring task definition: Updated the task definition dictionary key from 'name' to 'task_name' to align with expected configuration structures.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the task_def dictionary key from name to task_name in the arguments runner. Feedback suggests also including the sandbox_type in this dictionary when specified via CLI arguments to prevent validation errors for tasks requiring specific sandbox environments.

[gemini-code-assist]

While updating the key to task_name is correct, this dictionary should also include sandbox_type when a sandbox is specified via CLI arguments. Without sandbox_type, task-level validation (such as in validate_sandbox_tools) will default to assuming a local sandbox, which can cause incorrect failures for tasks that require a Linux container (e.g., those using bash_session or text_editor) even when the user has provided a valid sandbox configuration via the --sandbox flag.

Suggested change

	task_def = {"task_name": args.task}
	task_def = {"task_name": args.task}
	if args.sandbox:
	task_def["sandbox_type"] = args.sandbox[0]