feat: Support Sub-agent Escalation event in Parallel Agent

[jinnigu]

Fixes #561

Problem

ADK ParallelAgent did not support short-circuiting concurrent requests when a sub-agent sent a termination signal via an escalation event.

Changes

Modified ParallelAgent.java to use .takeUntil() on the merged event stream, listening for events with the escalate flag.
Added ParallelAgentEscalationTest.java to verify the escalation event triggers termination of other sub-agents.

Testing

• ParallelAgentEscalationTest passes (verifies short-circuit behavior).
• ParallelAgentTest passes (no regressions for normal parallel execution).
• Verified that when one sub-agent escalates, other long-running sub-agents are cancelled immediately.

[gemini-code-assist]

Summary of Changes

Hello @jinnigu, 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 addresses a critical limitation in the ADK ParallelAgent where it previously lacked the ability to terminate concurrent sub-agent operations upon receiving an escalation signal. The changes introduce a reactive mechanism to immediately halt all ongoing sub-agent activities when one sub-agent indicates an escalation, thereby improving efficiency and responsiveness by preventing redundant work.

Highlights

• Sub-agent Escalation Support: The ParallelAgent now supports short-circuiting its execution when any of its sub-agents emit an event with an escalate flag set to true. This prevents unnecessary processing by other sub-agents once a critical event occurs.
• New Test Coverage: A new test file, ParallelAgentEscalationTest.java, has been added to specifically verify the correct behavior of the ParallelAgent when an escalation event is triggered, ensuring that other sub-agents are terminated as expected.

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 correctly implements the short-circuiting logic for escalation events in ParallelAgent by using the RxJava takeUntil operator. The accompanying new test, ParallelAgentEscalationTest, effectively validates this new behavior. However, I've identified a critical compilation issue in the test code due to a missing builder method, and a couple of medium-severity suggestions to improve code clarity and robustness in the test implementation.