fix: set output schema when mode==task and outputs schema is set

[sasha-gitg]

fixes unit test

[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 addresses a bug where the output schema was not being correctly applied for agents operating in 'task' mode when an output_schema was specified. The change ensures that the agent's output is properly structured in these scenarios, resolving a related unit test failure.

Highlights

• Output Schema Handling: Modified the condition for setting set_event_output in the _maybe_save_output_to_state method. This ensures that the output schema is correctly applied when the agent is in 'task' mode and an output_schema is defined.

🧠 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. ↩

[adk-bot]

Response from ADK Triaging Agent

Hello @sasha-gitg, thank you for creating this PR!

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

• Associate an Issue: This PR is a bug fix. Could you please associate a GitHub issue with this PR? If one doesn't exist, please create one.
• Testing Plan: Please add a testing plan section to your PR description to describe how you have tested these changes.
• Code Formatting: The pyink-check has failed. Please run ./autoformat.sh to format the code and push the changes.

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

[gemini-code-assist]

Code Review

The pull request modifies the _maybe_save_output_to_state method in src/google/adk/agents/llm_agent.py to include a condition where the event output is set when the agent mode is 'task' and the output schema is defined. This change aims to fix a unit test by ensuring the output schema is correctly applied in task mode scenarios.

[gemini-code-assist]

The current logic uses and which requires both conditions (self.mode == 'task' and self.output_schema) to be true. If self.output_schema is not set, the condition will evaluate to false even if the mode is 'task'. Consider using parentheses to improve readability and ensure the intended logic is correctly expressed.

Suggestion: Add parentheses to group the conditions for better clarity.

Suggested change

	set_event_output = self.mode == 'single_turn' or (self.mode == 'task' and self.output_schema)
	set_output_key = bool(self.output_key)
	set_event_output = self.mode == 'single_turn' or (self.mode == 'task' and self.output_schema) # clearer with parens