Motivation

Follow up of #16516 , this PR further sweeps modules in sgl-model-gateway. It also cleans up some re-exports in modules.

Modifications

Tighten visibilities in:

• core, mcp, policies, tokenizer, tool_parser, observability
• Remove deadcode WorkerFactory
• Remove deadcode HarmonyStreamState

Cleanup re-exports in core, tokenizer, and mcp

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments (/tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci) or contact authorized users to do so.
4. After green CI and required approvals, ask Merge Oncalls to merge.