Skip to content

[model-gateway] add WorkerService abstraction for worker business logic#15580

Merged
slin1237 merged 1 commit intomainfrom
refactor-n/2
Dec 21, 2025
Merged

[model-gateway] add WorkerService abstraction for worker business logic#15580
slin1237 merged 1 commit intomainfrom
refactor-n/2

Conversation

@slin1237
Copy link
Copy Markdown
Collaborator

@slin1237 slin1237 commented Dec 21, 2025

Introduces a service layer that separates worker business logic from HTTP handlers. The WorkerService orchestrates WorkerRegistry and JobQueue operations, while server.rs handlers become thin wrappers.

Architecture:

  • src/core/worker_service.rs: Business logic + IntoResponse impls
  • src/server.rs: HTTP handlers (now thin wrappers)
  • src/app_context.rs: Holds Arc

This improves testability and maintains clean separation of concerns.

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist Bot commented Dec 21, 2025

Summary of Changes

Hello @slin1237, 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 significant architectural improvement by creating a WorkerService layer within the model-gateway. This new service centralizes the complex business logic for managing workers, which was previously scattered across HTTP handlers. By abstracting these operations, the change enhances the system's testability, promotes a cleaner separation of concerns, and simplifies the server.rs file, making it easier to understand and maintain the core routing logic.

Highlights

  • New WorkerService Abstraction: Introduced a new WorkerService module (src/core/worker_service.rs) to encapsulate all business logic related to worker management, including operations with WorkerRegistry and JobQueue.
  • Separation of Concerns: The WorkerService now acts as a dedicated service layer, cleanly separating worker-related business logic from HTTP handler concerns in src/server.rs. This improves modularity and maintainability.
  • Refactored HTTP Handlers: Existing HTTP handlers in src/server.rs for create_worker, list_workers_rest, get_worker, delete_worker, and update_worker have been refactored to become thin wrappers that delegate calls to the new WorkerService.
  • Enhanced AppContext: The AppContext struct now holds an Arc<WorkerService>, ensuring that the service is available throughout the application context and properly initialized during application startup.
  • Improved Error Handling and Responses: The WorkerService includes its own WorkerServiceError enum and implements IntoResponse for various operation results and errors, standardizing how responses are generated for worker-related API calls.

🧠 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.

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[bot]
gemini-code-assist Bot reviewed Dec 21, 2025
View reviewed changes
Copy link
Copy Markdown
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 WorkerService layer, which is an excellent architectural improvement. It successfully separates the business logic for worker management from the HTTP handlers in server.rs, making the handlers thin wrappers. This greatly improves separation of concerns, maintainability, and testability. The use of IntoResponse for service-level results and errors is a clean pattern that simplifies the handler code. My review includes a few suggestions to further improve performance and code style in the new service layer.

Comment thread sgl-model-gateway/src/core/worker_service.rs Outdated
Comment thread sgl-model-gateway/src/core/worker_service.rs Outdated
Comment thread sgl-model-gateway/src/core/worker_service.rs
@slin1237
[model-gateway] add WorkerService abstraction for worker business logic
c8d6c1e 
Introduces a service layer that separates worker business logic from HTTP
handlers. The WorkerService orchestrates WorkerRegistry and JobQueue
operations, while server.rs handlers become thin wrappers.

Architecture:
- src/core/worker_service.rs: Business logic + IntoResponse impls
- src/server.rs: HTTP handlers (now thin wrappers)
- src/app_context.rs: Holds Arc<WorkerService>

This improves testability and maintains clean separation of concerns.
@slin1237 slin1237 merged commit 1354063 into main Dec 21, 2025
56 of 59 checks passed
@slin1237 slin1237 deleted the refactor-n/2 branch December 21, 2025 22:35
jiaming1130 pushed a commit to zhuyijie88/sglang that referenced this pull request Dec 25, 2025
@slin1237 @jiaming1130
[model-gateway] add WorkerService abstraction for worker business log…
16ede45 
…ic (sgl-project#15580)
YChange01 pushed a commit to YChange01/sglang that referenced this pull request Jan 13, 2026
@slin1237 @YChange01
[model-gateway] add WorkerService abstraction for worker business log…
3343492 
…ic (sgl-project#15580)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@CatherineSue CatherineSue Awaiting requested review from CatherineSue CatherineSue is a code owner

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

model-gateway run-ci

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@slin1237