[feat] Enable session key in request body

[zerofishnoodles]

Enable session key in request body

Related to #735

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @zerofishnoodles, 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 SessionRouter by enabling it to process session keys embedded within the request body, alongside the existing support for header-based session keys. This change improves the adaptability of the routing mechanism by offering more options for session identifier transmission. The implementation includes a new, unified method for session ID extraction, updates to the route_request signature to accommodate body inspection, and comprehensive modifications to existing tests, along with a new test case, to ensure the robustness and correctness of the new functionality.

Highlights

• Session Key in Request Body: The SessionRouter now supports extracting session keys from the request body, in addition to the existing functionality of retrieving them from request headers. This provides greater flexibility for clients to pass session identifiers.
• Unified Session ID Extraction Logic: A new private helper method, _extract_session_id, has been introduced within the SessionRouter. This method centralizes the logic for retrieving session IDs by first checking request headers and then falling back to the request body if not found in headers.
• Asynchronous Routing and Testing: The route_request method in SessionRouter has been updated to be asynchronous. Correspondingly, all existing unit tests for the SessionRouter have been converted to async functions using pytest.mark.asyncio and now correctly await calls to the routing method.
• New Test Case for Body Extraction: A dedicated test, test_session_key_in_request_body, has been added to specifically validate the functionality of extracting session keys when they are provided within the request body.

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 enables extracting the session key from the request body in addition to the headers, which increases flexibility for clients. The changes are well-contained, updating the SessionRouter and its usage. My review includes suggestions to improve method visibility and type hinting for the new session extraction logic, and to make a new test case more robust by not depending on specific hash results.

[Shaoting-Feng]

/gemini review

[gemini-code-assist]

Code Review

This pull request enables extracting the session key from the request body for session-based routing, in addition to request headers. The changes involve updating the SessionRouter and related components to handle the request body. The tests have been updated accordingly, and a new test case for the feature has been added.

My review identifies a high-severity issue where requests with an empty body could cause a crash due to unsafe JSON parsing. I've also suggested improvements to a new helper method regarding its access level and type hints for better code quality and maintainability.

[Shaoting-Feng]

Please check whether the Gemini reviews need any fixes. Resolve all conversations that you believe are fine. Once everything is resolved, I’ll approve this PR.