feat: attach trace context to LiteLLM headers

[uc4w6c]

Link to Issue or Description of Change

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

• Closes: #issue_number
• Related: #issue_number

2. Or, if no issue exists, describe the change:

If applicable, please follow the issue templates to provide as much detail as
possible.

Problem:
LiteLLM calls issued from ADK did not forward the active OpenTelemetry span, so downstream providers could not correlate requests with ADK traces.

Solution:
Use extra_headers.traceparent on LiteLLM calls to pass the current traceparent.

Testing Plan

Please describe the tests that you ran to verify your changes. This is required
for all PRs that are not small documentation or typo fixes.

Unit Tests:

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

Please include a summary of passed pytest results.

Manual End-to-End (E2E) Tests:

Please provide instructions on how to manually test your changes, including any
necessary setup or configuration. Please provide logs or screenshots to help
reviewers better understand the fix.

Screenshot:

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.

Additional context

Add any other context or screenshots about the feature request here.

[gemini-code-assist]

Summary of Changes

Hello @uc4w6c, 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 enhances the LiteLLMClient by integrating OpenTelemetry trace context propagation. It addresses the issue of disconnected traces by ensuring that the active traceparent is automatically included in the extra_headers of all LiteLLM API calls. This change significantly improves the ability to trace requests end-to-end across distributed services, providing better observability and simplifying debugging of interactions with large language models.

Highlights

• OpenTelemetry Trace Context Propagation: Implemented functionality to attach the active OpenTelemetry trace context to LiteLLM calls, ensuring better observability and correlation across distributed services.
• traceparent Header Injection: The W3C traceparent header is now dynamically generated from the current OpenTelemetry span and injected into the extra_headers of LiteLLM requests.
• New Helper Methods for Trace Context: Introduced _build_traceparent, _maybe_add_traceparent_header, and _attach_traceparent_header within LiteLLMClient to manage the creation and injection of trace context.
• Integration with Completion Methods: Both acompletion (async) and completion (sync) methods of LiteLLMClient now utilize the new helper methods to ensure trace context is consistently propagated with every LiteLLM API call.
• Comprehensive Unit Tests: Added new unit tests to validate the correct behavior of trace context injection under various conditions, including scenarios with existing headers, no existing headers, and no active span.

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 effectively adds OpenTelemetry trace context propagation to LiteLLM calls by attaching the traceparent header. The implementation is clean, with helper methods to build and attach the header, and it's great to see comprehensive unit tests covering various scenarios for this new functionality. I have one suggestion to improve type safety.

[gemini-code-assist]

To ensure type safety and prevent potential issues with litellm which expects a dict, it's better to be explicit that this function accepts a dict rather than a generic Mapping. This aligns with the return type hint Optional[dict[str, str]] and avoids a potential type violation if a non-dict Mapping were passed, as line 247 would return it directly.

Suggested change

	cls, extra_headers: Optional[Mapping[str, str]]
	cls, extra_headers: Optional[dict[str, str]]

[uc4w6c]

fixed

[ryanaiagent]

Hi @uc4w6c , Thank you for your work on this pull request. We appreciate the effort you've invested.
Can you please fix the failing unit tests before we can proceed with the review.