Document (new) exec & filesystem tools

[vorburger]

Relates to #1644 and #1762 for #1631.

Includes #1767, just to avoid rebase conflicts.

@temi-ro PTAL - OK for you?

[gemini-code-assist]

Summary of Changes

Hello @vorburger, 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 significantly improves the clarity and usability of Enola's exec and filesystem interaction capabilities. It centralizes and expands the documentation for these tools, making it easier for developers to understand and utilize them. Concurrently, the underlying Java implementation has been refined for better modularity and consistency, and agent configurations have been updated to leverage a more capable AI model, enhancing the overall system's functionality and maintainability.

Highlights

• Enhanced Tool Documentation: New and expanded documentation for exec and filesystem tools (read_file, write_file, etc.) has been added to docs/concepts/tool.md, including practical examples.
• Filesystem Tool Refactoring: The FileSystemTools class has been refactored to use snake_case for tool names and a non-static createToolSet method, improving consistency and integration.
• Simplified Built-in Toolset Integration: The Tools.java class now more cleanly integrates all filesystem tools into the built-in toolset.
• Model Upgrade: Several agent configurations and tests have been updated to utilize the gemini-2.5-flash model, moving away from gemini-2.5-flash-lite.
• New exec Tool Example: A new agent (linux-system-summary.agent.yaml) has been introduced to showcase the functionality of the exec tool.

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

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 documents the newly introduced exec and built-in filesystem tools, and refactors the tool registration logic for better maintainability. The changes are well-structured. My review includes a critical recommendation to add a security warning for the exec tool in the documentation and a minor correction to an instruction in a test agent file to improve clarity and correctness.

[gemini-code-assist]

The exec tool is very powerful as it can run any shell command. This introduces a significant security risk, as a compromised or manipulated prompt could lead to arbitrary code execution on the machine running Enola. It's crucial to add a prominent security warning to this documentation, similar to the cautions for other powerful tools.

For example:

> [!CAUTION]
> The `exec` tool can execute arbitrary shell commands. This is a powerful capability that introduces significant security risks. Only enable this tool in trusted environments.

[vorburger]

That's a great point, Thank You for pointing this out Gemini Code Assist. I've added warnings to the doc now.

@temi-ro FYI

[temi-ro]

Good idea!

[temi-ro]

LGTM!

[vorburger]

This is now merged as part of #1770.