feat: add turn_id to Event for grouping streaming chunks by LLM call

[ferponse]

Summary

• Adds an optional turn_id: int field to Event that groups all streaming chunks belonging to the same LLM call
• turn_id is a 1-based counter that increments with each LLM call inside run_async, making it easy to identify turn boundaries (turn 1, turn 2, …)
• Consumers can use this field to trivially separate streaming chunks into message bubbles without brittle heuristics based on event type transitions

Problem

When using runner.run_async() with StreamingMode.SSE, there is no way to distinguish which partial streaming chunks belong to which LLM response turn. The invocation_id is shared across all events in the invocation, and id changes on every yield. The only workaround is observing transition patterns (partial → function_call → function_response), which is fragile.

Solution

A new turn_id: Optional[int] field on Event:

• 1-based counter incremented with each LLM call in run_async
• Remains the same across all partial chunks and the final aggregated event of that call
• Increments when a new LLM call starts (next iteration of the while True loop)
• Also set in the BIDI (live streaming) flow for consistency
• None by default, so existing code is unaffected

Changes

File	Change
src/google/adk/events/event.py	Added turn_id: Optional[int] field with docstring
src/google/adk/flows/llm_flows/base_llm_flow.py	Counter in run_async loop, passed to _run_one_step_async; counter in BIDI flow
tests/unittests/flows/llm_flows/test_turn_id.py	3 new tests

Test plan

• test_partial_chunks_share_same_turn_id — partial chunks from one LLM call share turn_id=1
• test_turn_id_present_on_final_response — a single final response carries turn_id=1
• test_different_llm_calls_get_different_turn_ids — events from separate LLM calls (text → tool → text) get turn_id 1 and 2
• All 108 existing flow + runner tests pass unchanged

[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, 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 new turn_id field to the Event object to solve the ambiguity in distinguishing streaming chunks from different LLM calls within a single invocation. Previously, invocation_id was too broad and id too granular. The turn_id provides a robust, incremental identifier for each LLM call, enabling clients to reliably group related streaming events and process multi-turn LLM interactions more effectively.

Highlights

• New turn_id field in Event: Added an optional turn_id: int field to the Event class to group all streaming chunks belonging to the same LLM call, providing a clear way to identify related events.
• Turn ID counter for LLM calls: turn_id is a 1-based counter that increments with each distinct LLM call within the run_async method, making it straightforward to identify boundaries between different LLM response turns.
• Improved consumer experience: Consumers can now easily separate streaming chunks into distinct message bubbles using the turn_id, eliminating the need for fragile heuristics based on event type transitions.

🧠 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.

Changelog

• src/google/adk/events/event.py
  • Added turn_id: Optional[int] field with docstring
• src/google/adk/flows/llm_flows/base_llm_flow.py
  • Counter in run_async loop, passed to _run_one_step_async
  • Counter in BIDI flow
• tests/unittests/flows/llm_flows/test_turn_id.py
  • 3 new tests

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 @ferponse, thank you for creating this PR!

This PR is a new feature, could you please create a github issue for this PR and associate it with this PR?

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

[gemini-code-assist]

Code Review

This pull request introduces a turn_id to group streaming event chunks, which is a great feature for consumers. The implementation for the run_async flow looks correct and is well-tested. However, I've found a critical issue in the implementation for the run_live (BIDI streaming) flow where the turn_id is incremented incorrectly. I've also noted that the new tests don't cover this live streaming path, which would be important to add to prevent regressions.

[gemini-code-assist]

This line incorrectly increments turn_id for every streaming chunk, which defeats the purpose of grouping chunks by turn. The turn_id should remain constant for all chunks of a single conversational turn and only be incremented when a new turn begins.

In the live streaming flow, the llm_response.turn_complete flag can be used to detect the end of a turn. I recommend managing the turn_id state outside this loop and incrementing it only when llm_response.turn_complete is True.

[gemini-code-assist]

These tests provide good coverage for the run_async flow. However, the turn_id logic is also implemented for the run_live (BIDI streaming) flow in _receive_from_model, but that path is not covered by these tests. Given the different logic for the live flow, adding tests specifically for it would be highly beneficial to ensure turn_id behaves as expected and to catch potential issues like the one identified in the live implementation.

[ferponse]

Closing in favour of a new PR with scope limited to SSE flow only (removed BIDI changes).