feat: support /v1/models in direct response

[Xunzhuo]

What type of PR is this?

feat: support /v1/models in direct response

[netlify]

✅ Deploy Preview for vllm-semantic-router ready!

Name	Link
🔨 Latest commit	ce9c4f9
🔍 Latest deploy log	https://app.netlify.com/projects/vllm-semantic-router/deploys/68dbbadd3bca670008eed1d8
😎 Deploy Preview	https://deploy-preview-283--vllm-semantic-router.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[github-actions]

👥 vLLM Semantic Team Notification

The following members have been identified for the changed files in this PR and have been automatically assigned:

📁 src

Owners: @rootfs, @Xunzhuo, @wangchen615
Files changed:

• src/semantic-router/pkg/extproc/models_endpoint_test.go
• src/semantic-router/pkg/extproc/request_handler.go

---

🎉 Thanks for your contributions!

This comment was automatically generated based on the OWNER files in the repository.

[rootfs]

@Xunzhuo can you review this solution too?
#186 (comment)

[Xunzhuo]

This need additional xDS config generation which is not standard for InferencePool implementation, so that using direct response. Otherwise we need every Gateway implementation to inject one more cluster to support our models api.

[rootfs]

@Xunzhuo sounds good. Can you run precommit? It is ready to go.
cc @JaredforReal

[JaredforReal]

Sounds good to me

[Xunzhuo]

tested and move this forward