Add a2a on agent engine sample

[wadave]

Description

Thank you for opening a Pull Request!
Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

• Follow the CONTRIBUTING Guide.

Fixes #365 > 🦕

[gemini-code-assist]

Summary of Changes

Hello @wadave, 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 delivers a new, extensive sample application that illustrates how to build and deploy a multi-agent system using the Agent2Agent (A2A) protocol on Google's Vertex AI Agent Engine. The sample features a central 'Host Agent' that orchestrates requests to specialized 'Cocktail' and 'Weather' agents. These specialized agents, in turn, interact with dedicated Model Context Protocol (MCP) servers to fulfill user queries, showcasing a robust architecture for complex AI agent interactions and highlighting the capabilities of A2A and Agent Engine.

Highlights

• New Multi-Agent Sample: Introduced a comprehensive sample demonstrating a multi-agent system using the Agent2Agent (A2A) protocol on Google's Vertex AI Agent Engine.
• A2A Protocol Integration: Showcases the implementation and deployment of A2A-compliant agents, including AgentCard definitions and AgentExecutor logic for communication and task management.
• Specialized Agents and MCP Servers: Includes distinct 'Cocktail' and 'Weather' agents that interact with dedicated Model Context Protocol (MCP) servers, providing domain-specific functionalities.
• Deployment to Vertex AI Agent Engine: Provides detailed setup instructions, Dockerfiles, and Jupyter notebooks for deploying individual agents, host agents, and MCP servers to the managed Agent Engine platform.
• Authentication and Session Management: Demonstrates handling of Google Cloud authentication (OIDC tokens) and session management within the agent executors for secure and stateful interactions.

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.

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 adds a comprehensive and well-structured sample for a multi-agent A2A setup on Agent Engine. The inclusion of two different implementation options for both the hosting agent and the frontend is a great way to showcase different approaches. My review focuses on improving dependency management, ensuring correct model usage, standardizing logging practices, and addressing minor inconsistencies in code and configuration files.

[holtskinner]

Thanks for the contribution!

Could you separate out the hosting agent/frontend options to just use one option for this example? It makes this project much larger than is probably needed, and could be harder for users to understand. Any way this can be simplified?

[wadave]

@holtskinner Thanks for the comments. I removed one of the options.

[wadave]

@holtskinner please review it again. thanks.