chore: TS SDK experimental server

[tomkis]

Summary

Linked Issues

Documentation

• No Docs Needed:

If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.

[gemini-code-assist]

Summary of Changes

Hello @tomkis, 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 introduces a foundational experimental server to the TypeScript SDK, significantly enhancing its capability to host and manage agents. The new server provides features for agent definition, automatic platform registration, and a robust execution environment that supports various extensions for services like LLMs and detailed UI configurations. This architectural shift aims to streamline agent development and deployment within the SDK, accompanied by a refactoring of shared data structures for improved organization.

Highlights

• Experimental Server Introduction: A new experimental server component has been added to the TypeScript SDK, enabling the definition and execution of agents directly within the SDK environment.
• Agent Auto-Registration: The server now includes an AutoRegistration mechanism that allows agents to automatically register with a platform, complete with retry logic and dynamic loading of environment variables.
• Agent Execution Model: An AgentExecutorImpl has been introduced to manage the execution of agent handlers, process messages, and handle task cancellation, supporting both synchronous and asynchronous (iterable) agent responses.
• Extensible Architecture: A flexible extension system has been implemented, allowing agents to integrate with various services such as LLMs and to define detailed UI configurations. This includes AgentDetailExtensionSpec and LLMExtensionSpec.
• Schema and Type Refactoring: Existing schema and type definitions related to LLM services and agent UI details have been refactored and moved into a new shared directory (src/shared/extensions) to promote reusability and maintainability across the SDK.
• Dependency Updates and Build Process: The package.json has been updated to include express as an optional peer dependency and tsx as a development dependency, along with corresponding type definitions. Build and dev scripts have also been adjusted to accommodate the new server files.
• Hello World Example: A new hello-world.ts example demonstrates how to define and run a basic agent using the new experimental server, showcasing its core functionality.

🧠 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.

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 introduces an experimental server for the TypeScript SDK, which is a significant and well-implemented feature. The changes include adding an express-based server, an example agent, and refactoring shared schemas and types into a shared directory, which improves code organization. The new server implementation is robust, featuring auto-registration with retry logic and graceful shutdown handling.

My review focuses on improving correctness, maintainability, and robustness. I've pointed out a type mismatch in an interface, suggested improvements to error handling and logging to avoid swallowing errors, and recommended deduplicating some logic to improve maintainability. Overall, this is a solid contribution.

[PetrBulanek]

Do we want to have this in package.json as it's part of an experimental feature?

[tomkis]

Good point, let's prefix this with experimental

[PetrBulanek]

Is this protocol version correct?