Skip to content

Add test for refactored openai server #7161

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 2 commits into from
Jun 14, 2025
Merged

Add test for refactored openai server #7161

merged 2 commits into from
Jun 14, 2025

Conversation

jhinpan
Copy link
Collaborator

@jhinpan jhinpan commented Jun 13, 2025

Motivation

According to the requirement in Issue 7103

Based on the current implementation of api_server.py in #7105

  • Create new test directory (sglang/test/srt/openai/)
  • Implement test fixture in conftest.py to manage server lifecycle
  • Create basic test file (test_server.py) for health and models endpoints

Modifications

New Directory Structure

sglang/test/srt/openai/
 -  __init__.py               # marks package
 - conftest.py               # server-lifecycle fixture
 - test_server.py            # first endpoint checks
  1. conftest.py
  • Launches sglang.srt.entrypoints.openai.api_server in a background process.
  • Chooses an port automatically, preventing CI clashes.
  • Streams startup logs to a temporary file to avoid pipe blockage and prints them only on failure.
  • Polls /health until the server is ready (configurable timeout, default 120 s).
  • Provides a session-scoped openai_server fixture returning the base URL.
  • Ensures full cleanup by recursively killing the child process tree after tests.
  1. test_server.py
  • test_health – validates the /health endpoint (status 200, empty body).
  • test_models_endpoint – placeholder for /v1/models; marked xfail until the endpoint is implemented, so the suite stays green.

Checklist

gemini-code-assist[bot]
gemini-code-assist bot reviewed Jun 13, 2025
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Summary of Changes

Hello @jhinpan, 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 establishes the foundational test infrastructure for the SGLang OpenAI-compatible API server. It provides a robust mechanism to launch and manage the server process during testing and includes initial tests to verify basic endpoint functionality, paving the way for more comprehensive API testing.

Highlights

  • New Test Suite: Introduced a dedicated test suite for the OpenAI-compatible API server under test/srt/openai/.
  • Server Fixture: Added a pytest session-scoped fixture in conftest.py to automatically launch the API server in a background process before tests and clean it up afterwards.
  • Dynamic Port Allocation: The test fixture selects a free port dynamically to avoid conflicts, especially in CI environments.
  • Health Check & Readiness: The fixture includes logic to wait for the server to become healthy by polling the /health endpoint before tests begin.
  • Initial Endpoint Tests: Added basic tests in test_server.py to verify the /health endpoint and included an xfail placeholder test for the /v1/models endpoint which is not yet fully implemented.
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 is currently in preview and 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 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 configureGemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

@jhinpan
Copy link
Collaborator Author

jhinpan commented Jun 13, 2025

cc @CatherineSue .

Verification of testing:
Screenshot 2025-06-13 at 2 27 34 PM

gemini-code-assist[bot]
gemini-code-assist bot reviewed Jun 13, 2025
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a test suite for the SGLang OpenAI-Compatible API Server, including a pytest fixture to manage the server lifecycle and initial tests for health and model endpoints. The changes are well-structured and address the issue requirements.

CatherineSue
CatherineSue reviewed Jun 13, 2025
View reviewed changes
Copy link
Collaborator

@CatherineSue CatherineSue left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Overall LGTM. Left some comments for CI and reusability.

We should have more details once the api_server skeleton is finished.

@CatherineSue
Copy link
Collaborator

The failed unit-test-backend-1 seems not relevant to this change.

@zhyncs zhyncs merged commit 50876ab into sgl-project:main Jun 14, 2025
42 of 52 checks passed
@CatherineSue CatherineSue mentioned this pull request Jun 17, 2025
Closed
@jhinpan jhinpan deleted the feat/oai-server-test branch June 18, 2025 20:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@CatherineSue CatherineSue CatherineSue approved these changes

@zhyncs zhyncs zhyncs approved these changes

@merrymercy merrymercy Awaiting requested review from merrymercy

@Ying1123 Ying1123 Awaiting requested review from Ying1123

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@jhinpan @CatherineSue @zhyncs