Pass parent session ID to child sessions in AgentTool

[mattmcc-attest]

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

• Closes: Feature Request: Pass Root Agent session id and invocation_id to Tool Agents #3802

Problem:
New session IDs were being generated when calling agent tools causing issues debugging and with tracking (emitting metrics etc). This issue was specifically seen when adding plugins to a parent agent. When the agent tool was called and the plugin checked the session ID - it was not the same as the parents.

Solution:
When AgentTool creates a child session for a sub-agent, it now passes the parent session ID to maintain session continuity across agent boundaries. This ensures that child agents can properly track and reference their parent session context.

Changes:

• Added session_id parameter to create_session call in agent_tool.py
• Added test_agent_tool_passes_parent_session_id to verify the behavior

Testing Plan

Testing:

• All 16 unit tests pass
• New test specifically validates session ID propagation (test_agent_tool_passes_parent_session_id)

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

===================== test session starts ====================== collected 16 items tests/unittests/tools/test_agent_tool.py::test_agent_tool_passes_parent_session_id PASSED ... ================ 16 passed, 25 warnings in 1.67s ================

Manual End-to-End (E2E) Tests:

You can uv build and point your sample application to the locally built version of ADK. If you add a plugin or a callback you should see the before/after:

    async def before_model_callback(
        self,
        *,
        callback_context: CallbackContext,
        llm_request: LlmRequest,
    ) -> None:
    	session_id = callback_context.._invocation_context.session.id
        self.logger.info(
            "before_model_callback: session_id=%s", session_id)

Checklist

• I have read the CONTRIBUTING.md document.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

[gemini-code-assist]

Summary of Changes

Hello @mattmcc-attest, 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 resolves a critical issue in the AgentTool where child sessions were not inheriting the session ID from their parent agents. By explicitly passing the parent session ID during child session creation, this change ensures seamless session continuity across nested agent interactions, significantly improving the accuracy of debugging, tracking, and metric collection within the ADK framework.

Highlights

• Session ID Propagation: The pull request ensures that when an AgentTool creates a child session for a sub-agent, the parent session ID is now explicitly passed, maintaining session continuity.
• Debugging and Tracking Improvement: This change resolves issues with debugging and tracking metrics by ensuring child sessions inherit the correct parent session context, which was previously fragmented.
• New Unit Test: A new unit test, test_agent_tool_passes_parent_session_id, has been added to specifically validate that the parent session ID is correctly propagated to child sessions.

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 addresses the issue of propagating the parent session ID to child sessions created by AgentTool. The change is simple and effective. The new unit test, test_agent_tool_passes_parent_session_id, thoroughly validates this behavior. My main feedback is on the test file, where there is significant code duplication between the new test and an existing one. I've suggested refactoring this into a shared pytest fixture to improve maintainability.

[ryanaiagent]

Hi @mattmcc-attest , Thank you for your contribution! We appreciate you taking the time to submit this pull request. Your PR has been received by the team and is currently under review. We will provide feedback as soon as we have an update to share.

[ryanaiagent]

Hi @seanzhou1023 , can you please review this.