Fix: Add fallback logic to retrieve user message when resuming async …

[ycsmiley]

Problem: When using run_async to resume an invocation (e.g., after a ToolConfirmation pause), the strict lookup for the user message using invocation_id often fails, leading to a ValueError: No user message available. This happens because the session persistence layer sometimes disconnects the original user message ID from the resumed invocation ID.

Solution: Added a fallback mechanism in _setup_context_for_resumed_invocation. If the strict lookup returns None, the runner now searches the session history (in reverse order) to find the most recent message authored by 'user'. This ensures the agent allows execution to resume with the correct context.

Testing: Verified locally with a Human-in-the-Loop workflow involving ToolConfirmation and run_async. The fix successfully recovered the user message and allowed the agent to proceed without crashing.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Summary of Changes

Hello @ycsmiley, 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 robust fallback mechanism to ensure that asynchronous invocation resumptions, particularly after pauses like ToolConfirmation, can reliably retrieve the correct user message. Previously, a strict lookup could fail due to session persistence issues, causing ValueError and preventing the agent from proceeding. The new logic enhances the system's resilience by searching the session history for the latest user message when the direct lookup is unsuccessful, thereby guaranteeing that the agent always has the necessary context to resume execution.

Highlights

• User Message Retrieval: Implemented a fallback mechanism in _setup_context_for_resumed_invocation to find the most recent user message in session history if the direct lookup by invocation_id fails. This addresses issues where session persistence might disconnect the original user message ID from the resumed invocation ID during run_async operations.
• Error Prevention: The change prevents ValueError: No user message available from being raised when resuming an invocation, ensuring the agent can proceed with the correct context even if the strict lookup fails.

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. ↩

[adk-bot]

Response from ADK Triaging Agent

Hello @ycsmiley, thank you for creating this PR!

To help us review your contribution, could you please address the following points from our contribution guidelines?

• Sign our Contributor License Agreement (CLA): It looks like the CLA check is failing. You can sign the CLA at https://cla.developers.google.com/.
• Associate an Issue: For bug fixes, we require an associated GitHub issue. If one doesn't exist, could you please create one?
• Add a Testing Plan: Please add a Testing Plan section to your PR description detailing how you tested these changes.
• Provide Logs or Screenshots: Please provide logs or screenshots that demonstrate the fix.

This information will help reviewers to review your PR more efficiently. Thanks!

[gemini-code-assist]

Code Review

This pull request introduces a fallback mechanism to retrieve a user message when resuming an asynchronous invocation, which is a good fix to prevent a ValueError. My feedback focuses on improving the robustness of this fallback. I've suggested adding a warning log to make it clear when this heuristic is being used, as it could potentially use an incorrect user message for context, leading to silent failures. This will greatly help with debugging. I've also included a minor indentation fix in my suggestion.

[ryanaiagent]

Hi @ycsmiley,Thank you for your contribution! We appreciate you taking the time to submit this pull request.
Before we can proceed with the review can you fix the failing lint errors using autoformat.sh.

[ycsmiley]

Hi @ryanaiagent
Thanks for the guidance. I've run autoformat.sh and pushed the fixes. The lint errors should be resolved now.