[AI] Add AGENTS.md for FirebaseAI/Sources

[paulb777]

This pull request significantly enhances the documentation of the FirebaseAI library by introducing a series of AGENTS.md files throughout its source code. This initiative aims to provide clear, structured explanations of the library's architecture, making it easier for developers to navigate, understand, and contribute to the codebase. By detailing the contents and purpose of various directories and files, especially distinguishing between public and internal components, the PR improves maintainability and onboarding for new contributors.

Highlights

• New Documentation Files: Added multiple AGENTS.md files across the FirebaseAI/Sources directory to provide detailed overviews and documentation for the codebase structure.
• Codebase Clarity: Each AGENTS.md file describes the purpose of its respective directory, lists the Swift files contained within, and distinguishes between public and internal APIs for better understanding.
• Structured Information: The documentation categorizes protocols and data types, offering insights into error handling, Imagen features, live streaming capabilities, API requests, and tool-related functionalities.

#no-changelog

[gemini-code-assist]

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.

[paulb777]

/gemini review

[danger-firebase-ios]

	1 Warning
⚠️	New public headers were added, did you remember to add them to the umbrella header?

Generated by 🚫 Danger

[gemini-code-assist]

Code Review

This pull request introduces AGENTS.md files across the FirebaseAI/Sources directory tree. These AI-generated markdown files serve as documentation, providing an overview of each directory's purpose and a summary of the files within it. The content is well-structured, accurate, and provides helpful context for developers. I have one minor suggestion to improve the titles of these files for better clarity, but overall, this is a valuable addition for code navigation and understanding.

[paulb777]

/gemini review

[gemini-code-assist]

Code Review

This pull request adds a comprehensive set of AGENTS.md files, providing excellent documentation for the FirebaseAI/Sources directory structure. These overviews are clear, detailed, and will be very helpful for developers navigating the codebase. The changes significantly improve the project's maintainability. I have a couple of minor suggestions to enhance the clarity of some descriptions even further.

[paulb777]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces AGENTS.md files across the FirebaseAI/Sources directory, providing valuable documentation and overviews of the codebase. The content is well-written and informative. I've included a few minor suggestions to improve consistency in headings and enhance the readability of some descriptions. Overall, this is an excellent addition that will improve the project's maintainability.

[paulb777]

/gemini summarize

[gemini-code-assist]

Summary of Changes

This pull request significantly enhances the documentation of the FirebaseAI library by introducing a series of AGENTS.md files throughout its source code. This initiative aims to provide clear, structured explanations of the library's architecture, making it easier for developers to navigate, understand, and contribute to the codebase. By detailing the contents and purpose of various directories and files, especially distinguishing between public and internal components, the PR improves maintainability and onboarding for new contributors.

Highlights

• New Documentation Files: Added multiple AGENTS.md files across the FirebaseAI/Sources directory to provide detailed overviews and documentation for the codebase structure.
• Codebase Clarity: Each AGENTS.md file describes the purpose of its respective directory, lists the Swift files contained within, and distinguishes between public and internal APIs for better understanding.
• Structured Information: The documentation categorizes protocols and data types, offering insights into error handling, Imagen features, live streaming capabilities, API requests, and tool-related functionalities.

🧠 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.

Activity

• gemini-code-assist[bot] provided guidance on using Gemini Code Assist.
• paulb777 requested reviews from Gemini Code Assist multiple times.
• danger-firebase-ios[bot] issued a warning regarding new public headers not being added to the umbrella header.
• gemini-code-assist[bot] suggested improvements for clarity and consistency in the newly added AGENTS.md files, including refining titles, descriptions, and heading formats.

[andrewheard]

LGTM. Do you have a prompt we should use to update these as we add new files or re-organize existing ones?

[paulb777]

Thanks for the review.

More exploration is needed both for the prompts to keep these up to date - and the prompts to make sure that agents find these.

Will merge and continue to investigate best practices.