[Firebase AI] Add logic for Developer Live API

[a-maurice]

Description

Provide details of the change, and generalize the change in the PR title above.

Add the necessary bits for Developer Live API. Note that this requires backend support still.

---

Testing

Describe how you've tested these changes.

Testing locally

---

Type of Change

Place an x the applicable box:

• Bug fix. Add the issue # below if applicable.
• New feature. A non-breaking change which adds functionality.
• Other, such as a build process or documentation change.

---

[gemini-code-assist]

Summary of Changes

Hello @a-maurice, 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!

I've prepared this pull request to introduce the foundational client-side logic for the new Developer Live API within the Firebase AI SDK. This work primarily focuses on enabling the LiveGenerativeModel to support real-time interactions with different AI backends, specifically VertexAI and GoogleAI, by dynamically configuring connection parameters. While the full backend support is still pending, this PR lays crucial groundwork for future live AI capabilities.

Highlights

• Live API Backend Flexibility: I've removed the previous restriction that LiveGenerativeModel only supported the VertexAI backend, allowing for broader compatibility with other AI services.
• Dynamic Endpoint Configuration: I've implemented logic within LiveGenerativeModel to dynamically construct WebSocket URLs and model names based on the selected backend provider (VertexAI or GoogleAI), facilitating connections to the appropriate live API endpoints.
• Robust Audio Data Handling: I've enhanced the parsing of live session responses to more flexibly recognize audio data by checking for MIME types that start with 'audio/pcm', accommodating various audio stream formats.
• Resilient Model Content Deserialization: I've improved the ModelContent deserialization process to gracefully handle cases where the 'role' field might be missing from backend responses, defaulting it to 'model' to prevent parsing errors.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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

The code changes introduce logic for the Developer Live API, including modifications to support different backend providers (VertexAI and GoogleAI) and handling audio content. The changes also include updating the ModelContent to handle missing roles from the backend.