feat(adapter): add CheckAdapter for generic check interface

[fohte]

Why

• Any LLM agent should be able to query command permissions via runok check --command "..."
  • Leverage the common evaluation flow by implementing the existing Endpoint trait

What

• Add CheckAdapter as an Endpoint trait implementation that returns permission decisions as JSON
  • Provide two constructors: from_command() (CLI argument) and from_stdin() (stdin JSON)
  • handle_action converts Action to CheckOutput JSON (decision, reason, fix_suggestion, sandbox) on stdout (exit 0)
  • handle_no_match returns a decision based on defaults.action (exit 0)
  • handle_error writes to stderr (exit 2)
  • Sandbox information is included as informational data: preset name or merged policy details

---

[gemini-code-assist]

Summary of Changes

Hello @fohte, 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 introduces a new CheckAdapter to facilitate a standardized way for LLM agents and other tools to query command permissions using the runok check command. By implementing the Endpoint trait, it provides a consistent JSON output for permission decisions, including detailed sandbox information, making it easier to integrate with automated systems. The change enhances the runok tool's ability to provide programmatic access to its rule evaluation capabilities.

Highlights

• New CheckAdapter for runok check: A new CheckAdapter struct was introduced to provide a generic interface for checking command permissions via the runok check command.
• JSON Output for Permission Decisions: The CheckAdapter implements the Endpoint trait to output permission decisions (allow, deny, ask) and associated details (reason, fix suggestion, sandbox info) as JSON to stdout.
• Flexible Command Input: The CheckAdapter supports two ways to receive the command to be checked: directly from a CLI argument using from_command() or from JSON input via stdin using from_stdin().
• Comprehensive Error and No-Match Handling: The adapter includes dedicated handlers for processing rule engine actions (handle_action), cases where no rule matches (handle_no_match based on default actions), and errors (handle_error), ensuring consistent exit codes and output.
• Detailed Sandbox Information: Sandbox policy details, including preset names, writable roots, and network allowance, are now included in the JSON output for informational purposes.

Changelog

• src/adapter/check_adapter.rs
  • Added CheckAdapter struct and its associated logic for handling command checks.
  • Defined CheckInput, CheckOutput, and CheckSandboxInfo structs for JSON serialization/deserialization.
  • Implemented the Endpoint trait for CheckAdapter, including extract_command, handle_action, handle_no_match, and handle_error methods.
  • Included helper functions build_sandbox_info and merged_policy_to_sandbox_info to format sandbox data for output.
  • Added comprehensive unit tests for CheckAdapter construction, action handling, no-match scenarios, error handling, and sandbox info building.
• src/adapter/mod.rs
  • Added pub mod check_adapter; to expose the new check_adapter module.

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. ↩

[codecov]

Codecov Report

❌ Patch coverage is 98.76543% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 90.38%. Comparing base (0aee28c) to head (f98bef4).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
src/adapter/check_adapter.rs	98.76%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #53      +/-   ##
==========================================
+ Coverage   90.17%   90.38%   +0.20%     
==========================================
  Files          19       20       +1     
  Lines        4234     4315      +81     
==========================================
+ Hits         3818     3900      +82     
+ Misses        416      415       -1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[devin-ai-integration]

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no potential bugs to report.

View in Devin Review to see 2 additional findings.