feat(mcp): revamp firebase init with orchestration API integration

[TrCaM]

• Integration with orchestration API
• Project/App/AiLogic provisioning
• App config file writing
• Local directory conflict handling

Conflict Handling

• Project conflicts: Prevents overwriting existing .firebaserc projects unless overwrite_project: true
• Config file conflicts: Prevents overwriting existing app config files unless overwrite_configs: true
• Directory resolution: Automatically finds existing apps or creates unique directory names

Testing with Gemini CLI

Clone PR with GitHub CLI:

gh pr checkout 9174

Install and link:

npm install
npm link

Update ~/.gemini/settings.json with:

{
  "mcpServers": {
    "firebase": {
      "command": "npx",
      "args": [
        "-y",
        "firebase-tools",
        "experimental:mcp",
        "--dir",
        "."
      ]
    }
  }
}

Start Gemini CLI and try a prompt like:

Help me create a project and an app with ai_logic enable with firebase mcp init tool.

Limitations

• Will follow up with prompt update to improve tool calling correctness. Gemini CLI takes several tries to get the input correct
• A workflow involving project creation / app creation / AI Logic enablement take up to 2.5mins to complete. Our team is investigating why the orchestration API is taking that long

[gemini-code-assist[bot]]

Summary of Changes

Hello @TrCaM, I'm Gemini Code Assist[^1]! 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 enhances the Firebase initialization experience by revamping the mcp (Managed Control Plane) to leverage a new orchestration API. This allows for a more automated and robust setup of Firebase projects, various app types (iOS, Android, Web), and AI Logic features. The changes also include comprehensive handling for potential conflicts with existing local project configurations and app files, ensuring a smoother developer workflow.

Highlights

• Orchestration API Integration: The Firebase initialization process now integrates with a new orchestration API, enabling programmatic provisioning of Firebase projects and apps.
• Project and App Provisioning: The init tool can now provision new Firebase projects and apps (iOS, Android, Web) directly through the API, including support for AI Logic features.
• Local Directory Conflict Handling: Introduced mechanisms to handle conflicts when a project is already configured in .firebaserc or when app configuration files already exist locally, with options to overwrite.
• AI Logic Feature Integration: The ailogic feature has been added to the initialization process, allowing for its provisioning as part of the overall setup.

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 :thumbsup: and :thumbsdown: 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.

[^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.

[joehan]

/gemini review