feat(ai): template chat and function calling api

[cynthiajoan]

Hey there! So you want to contribute to a Firebase SDK?
Before you file this pull request, please read these guidelines:

Discussion

• Read the contribution guidelines (CONTRIBUTING.md).
• If this has been discussed in an issue, make sure to link to the issue here.
  If not, go file an issue about this before creating a pull request to discuss.

Testing

• Make sure all existing tests in the repository pass after your change.
• If you fixed a bug or added a feature, add a new test to cover your code.

API Changes

• Changes that affect the public API will require internal review. Before making a
  PR that changes the public API, we would suggest first proposing your change in an
  issue so that we can discuss it together.

[changeset-bot]

⚠️ No Changeset found

Latest commit: 33dd398

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[gemini-code-assist]

Summary of Changes

Hello, 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 enhances the AI SDK by introducing robust support for server-side template-based chat sessions. It provides a dedicated class for managing conversational history and integrates automatic function calling capabilities, enabling more dynamic and interactive AI experiences. The changes extend the TemplateGenerativeModel to seamlessly incorporate these new chat functionalities, alongside introducing necessary type definitions to support the new API.

Highlights

• New TemplateChatSession Class: Introduced a new TemplateChatSession class to manage chat interactions with server-side AI templates, including history management and sequential message processing.
• Automatic Function Calling: Implemented automatic function calling within TemplateChatSession, allowing the model to request and execute user-defined functions during a chat turn, with a configurable limit on sequential calls.
• TemplateGenerativeModel Integration: Added a startChat method to TemplateGenerativeModel to easily initiate a TemplateChatSession with specified parameters.
• New Type Definitions: Defined new public types including StartTemplateChatParams for configuring template chat sessions, and TemplateFunctionDeclaration and TemplateFunctionDeclarationsTool for template-specific function calling.

🧠 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.

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.

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 introduces TemplateChatSession and related types to enable chat functionality with server-side templates, including automatic function calling. The TemplateChatSession class manages chat history and handles both streaming and non-streaming message exchanges. Key changes include defining StartTemplateChatParams and TemplateFunctionDeclaration for template-specific configurations and tools. Review feedback highlights a critical bug where parallel function calls with the same name might be overwritten due to the use of a Map in _callFunctionsAsNeeded. Additionally, there's a typo in maxSequentalFunctionCalls that needs correction, duplicated logic for finding functionDeclarationsTool, and a missing id in FunctionResponse that could impact call correlation. A redundant export of TemplateChatSession was also noted.

[gemini-code-assist]

TemplateChatSession is already exported from public-types.ts, which is then re-exported by this file on line 52. This explicit export is redundant and can be removed to simplify the code.

[gemini-code-assist]

The logic to find functionDeclarationsTool is duplicated from the _getCallableFunctionCalls method. To improve maintainability and reduce redundancy, consider extracting this logic into a private helper method, for example _getFunctionDeclarationsTool().