fix(core): Encourage non-interactive flags for scaffolding commands

[NTaylorMullen]

Summary

This PR updates the system prompt's New Applications workflow to explicitly enforce the use of non-interactive flags (like -y, --yes, or specific template flags like --template react-ts) when the agent utilizes scaffolding tools (e.g., npm create, npm init). This resolves an issue where the CLI would hang waiting for user input during application generation.

Details

• Strengthened instructions in packages/core/src/prompts/snippets.ts warning that interactive wizards will hang the CLI environment unless bypassed.
• Implemented a new ALWAYS_PASSES behavioral evaluation case (should use non-interactive flags when scaffolding a new app) in evals/interactive-hang.eval.ts to guarantee the model consistently avoids interactive hangs during project setup.

Related Issues

N/A

How to Validate

Run the behavioral evaluations:
npm run test:always_passing_evals -- -t "should use non-interactive flags when scaffolding a new app"

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed)
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • MacOS
    • npm run
    • npx
    • Docker
    • Podman
    • Seatbelt
  • Windows
    • npm run
    • npx
    • Docker
  • Linux
    • npm run
    • npx
    • Docker

[gemini-code-assist]

Summary of Changes

Hello @NTaylorMullen, 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 enhances the system's ability to create new applications by preventing command-line interface hangs during the scaffolding process. It achieves this by modifying the core prompts to explicitly instruct the agent to use non-interactive flags with scaffolding tools, thereby streamlining the automated application generation workflow.

Highlights

• Enforced Non-Interactive Flags: Updated the system prompt's New Applications workflow to explicitly enforce the use of non-interactive flags (like -y, --yes, or specific template flags) when the agent utilizes scaffolding tools.
• Prevented CLI Hangs: This change resolves an issue where the CLI would hang waiting for user input during application generation by ensuring scaffolding commands are non-interactive.
• New Behavioral Evaluation: Implemented a new ALWAYS_PASSES behavioral evaluation case ('should use non-interactive flags when scaffolding a new app') to guarantee the model consistently avoids interactive hangs during project setup.

Changelog

• evals/interactive-hang.eval.ts
  • Added a new evalTest case to validate that scaffolding commands use non-interactive flags.
• packages/core/src/prompts/snippets.ts
  • Modified the newApplicationSteps function to include explicit instructions for using non-interactive flags with interactive scaffolding tools.

Activity

• The pull request was authored by NTaylorMullen.
• It includes a pre-merge checklist, with tests added/updated and MacOS validation completed.
• Validation instructions are provided, suggesting running specific behavioral evaluations.

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.

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

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 correctly updates the system prompt to enforce non-interactive flags for scaffolding commands. However, the new behavioral evaluation test in evals/interactive-hang.eval.ts contains a critical flaw. It incorrectly attempts to validate the command arguments by testing against the raw JSON string of toolRequest.args instead of parsing it to access the command property, as required by the project's general rules. This makes the test unreliable. I've provided comments with suggestions to fix this.

[github-actions]

Size Change: +754 B (0%)

Total Size: 24.4 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	24.4 MB	+754 B (0%)
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B
./bundle/sandbox-macos-strict-open.sb	4.82 kB	0 B
./bundle/sandbox-macos-strict-proxied.sb	5.02 kB	0 B

_{compressed-size-action}