refactor(core): refine Security & System Integrity section in system prompt

[NTaylorMullen]

Summary

Refines the system prompt's security section for better architectural clarity and reduced conversational chitchat.

Details

• Renamed the header from "Security Protocols" to "Security & System Integrity". This better reflects the section's scope, which includes repository health (integrity) as well as credential protection (security).
• Removed the "Tool Permissions" bullet point (formerly "Protocol"). The instruction "Do not ask for permission to use tools" is now implicit in the operational guidelines and the overall system design where the environment handles confirmations. This reduces prompt density and avoids redundant instructions about justification that are covered in "Tone and Style".

Related Issues

N/A

How to Validate

1. Run npm test -w @google/gemini-cli-core -- src/core/prompts.test.ts to ensure all prompt generation logic and snapshots are correct.
2. Run npm run lint and npm run typecheck to ensure code integrity.

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 focuses on enhancing the clarity and conciseness of the system prompt's security section. By updating the header to reflect a broader scope of security and system integrity, and by removing a redundant instruction regarding tool permissions, the prompt becomes more architecturally clear and reduces unnecessary conversational overhead, streamlining the system's interaction logic.

Highlights

• System Prompt Refinement: The 'Security Protocols' header in the system prompt has been renamed to 'Security & System Integrity' to better encompass repository health and credential protection.
• Reduced Prompt Density: The 'Tool Permissions' bullet point, which instructed not to ask for permission to use tools, has been removed. This instruction is now implicitly handled by the system's operational guidelines, reducing redundancy.

Changelog

• packages/core/src/core/snapshots/prompts.test.ts.snap
  • Updated snapshot tests to reflect changes in the system prompt's security section.
  • Renamed 'Security Protocols' header to 'Security & System Integrity'.
  • Removed the 'Protocol' bullet point regarding tool permissions.
• packages/core/src/prompts/snippets.ts
  • Modified the renderCoreMandates function to update the security section of the system prompt.
  • Changed the header from 'Security Protocols' to 'Security & System Integrity'.
  • Removed the instruction '- Protocol: Do not ask for permission to use tools; the system handles confirmation. Your responsibility is to justify the action, not to seek authorization.'

Activity

• No human activity (comments, reviews) has been recorded on this pull request yet.

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 refines the system prompt's security section by renaming it to 'Security & System Integrity' for better clarity and removing a redundant instruction about tool permissions, which is already covered elsewhere. The changes are straightforward, well-justified, and correctly applied to both the prompt generation logic and the corresponding test snapshots. This is a good improvement for prompt conciseness and clarity.

[github-actions]

Size Change: -155 B (0%)

Total Size: 23.9 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	23.9 MB	-155 B (0%)
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB	0 B
./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-closed.sb	3.29 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

_{compressed-size-action}