Move prefix cache update from PreRequest to ResponseReceived

[zetxqx]

What type of PR is this?

/kind bug

What this PR does / why we need it:

This PR updates the prefixCacheScorer plugin to defer updating the cache index and recording metrics until
the ResponseReceived phase. This will prevent the case when request is shedded the prefix cache index is still updated.

See: #971 (comment) and #971 (comment)

Changes:

1. Moved the indexer update logic from PreRequest to ResponseReceived to ensure only served requests update
   the cache (avoiding updates from shedded requests).
2. Updated SchedulingContextState for prefixCacheScorer to persist selected servers and metric stats across the request lifecycle for ResponseReceived to process. This will prevent a larger refactor since the interface of ResponseReceived only have targetPod *datalayer.EndpointMetadata.

Which issue(s) this PR fixes:

Fixes partially #971

Does this PR introduce a user-facing change?:

Almost none, delayed the prefix cache update just after response is received.

[netlify]

✅ Deploy Preview for gateway-api-inference-extension ready!

Name	Link
🔨 Latest commit	7da5041
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/696522e985d4a90008c5b285
😎 Deploy Preview	https://deploy-preview-2125--gateway-api-inference-extension.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.

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: zetxqx
Once this PR has been reviewed and has the lgtm label, please assign liu-cong for approval. For more information see the Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• pkg/epp/scheduling/framework/plugins/multi/prefix/OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[k8s-ci-robot]

PR needs rebase.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

[ahg-g]

/assign @liu-cong

[nirrozenbaum]

just as a clarification for any reviewer - the extension point ResponseReceived is called when the response HEADERS are received, it is NOT waiting for the body to arrive.
(naming selection here is bad, we have an open issue to update the extension point name).

gateway-api-inference-extension/pkg/epp/requestcontrol/plugins.go

Lines 41 to 47 in c68bbe5

	// ResponseReceived is called by the director after the response headers are successfully received
	// which indicates the beginning of the response handling by the model server.
	// The given pod argument is the pod that served the request.
	type ResponseReceived interface {
	plugins.Plugin
	ResponseReceived(ctx context.Context, request *types.LLMRequest, response *Response, targetEndpoint *datalayer.EndpointMetadata)
	}