Bug fix streaming in PD disaggregation and add unit tests

[varungup90]

Pull Request Description

[Please provide a clear and concise description of your changes here]

Related Issues

Resolves: #[Insert issue number(s)]

Important: Before submitting, please complete the description above and review the checklist below.

---

Contribution Guidelines (Expand for Details)

We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:

Pull Request Title Format

Your PR title should start with one of these prefixes to indicate the nature of the change:

• [Bug]: Corrections to existing functionality
• [CI]: Changes to build process or CI pipeline
• [Docs]: Updates or additions to documentation
• [API]: Modifications to aibrix's API or interface
• [CLI]: Changes or additions to the Command Line Interface
• [Misc]: For changes not covered above (use sparingly)

Note: For changes spanning multiple categories, use multiple prefixes in order of importance.

Submission Checklist

• PR title includes appropriate prefix(es)
• Changes are clearly explained in the PR description
• New and existing tests pass successfully
• Code adheres to project style and best practices
• Documentation updated to reflect changes (if applicable)
• Thorough testing completed, no regressions introduced

By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.

[gemini-code-assist]

Summary of Changes

Hello @varungup90, 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 primarily addresses a bug within the PD (Pod Disaggregation) routing algorithm, specifically concerning how prefill requests are handled to ensure they are not treated as streaming requests. To validate this fix and improve code robustness, I've also added a new set of unit tests that significantly increase the test coverage for the PD disaggregation logic. Minor code refinements for constants and error logging were also included.

Highlights

• Bug Fix (Streaming): I've corrected the prefill request payload in preparePrefillPayload to explicitly set stream to false and remove any stream_options, addressing a bug related to streaming in PD disaggregation (lines 217-224 in pd_disaggregation.go).
• Bug Fix (Error Handling): I've improved error handling in the asynchronous SGLang prefill request goroutine within doPrefillRequest by adding a return statement after logging an error, ensuring the goroutine exits immediately (lines 178-185 in pd_disaggregation.go).
• Test Coverage: I've introduced a new, comprehensive suite of unit tests in pd_disaggregation_test.go for the pd_disaggregation algorithm. This includes tests for routing logic, pod filtering, and the doPrefillRequest function, which uses a mock HTTP server to validate prefill request payloads for both VLLM and SGLang engines (new file pd_disaggregation_test.go).
• Code Refinement: I've refactored constant names for improved clarity and consistency (LLMEngineLabel to LLMEngineIdentifier, getSGLangBootstrapPortIdentifier to SGLangBootstrapPortIdentifier) and introduced a constant for the SGLang bootstrap port. I also removed some redundant error logging (lines 38-48, 83-90, 228-233, 270-279 in pd_disaggregation.go).

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 or fill out our survey to provide feedback.

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 introduces a bug fix for streaming in PD disaggregation and adds a corresponding set of unit tests. The code changes in pd_disaggregation.go are solid, addressing the bug correctly and improving code clarity by removing magic numbers and redundant logging. The addition of unit tests is a significant improvement for maintainability.

My review focuses on the new test file, pd_disaggregation_test.go, where I've identified a critical issue in one test that will cause a panic, and a couple of medium-severity issues related to test robustness that could lead to flaky tests. Addressing these points will ensure the new tests are reliable and effective.