fix: use request id to locate the correct cache entry to update

[aeft]

What type of PR is this?

fix: use request id to locate the correct cache entry to update

What this PR does / why we need it:

The major change:

1. Update the cache interface to use request id to locate the cache entry

Other changes:

• Added request_id to Milvus storage.
• Replaced the insert operation with upsert in MilvusCache.addEntry. Previously, it always inserted two entries into storage—one for AddPendingRequest and another for UpdateWithResponse. Now, it updates the entry if a cache entry with the same request_id already exists.
• Removed the logic that added an unknown cache entry when no cache entry was found in UpdateWithResponse. I think it's not useful because we this unknown cache entry doesn't have model field.
• Removed pendingRequests and pendingRequestsLock since they are no longer in use.
• Added a Docker command to milvus.mk to enable starting Attu (the Milvus UI), which is helpful for browsing data.

Which issue(s) this PR fixes:

Fixes #144

Release Notes: Yes/No

[netlify]

✅ Deploy Preview for vllm-semantic-router ready!

Name	Link
🔨 Latest commit	7835da2
🔍 Latest deploy log	https://app.netlify.com/projects/vllm-semantic-router/deploys/68cae07350da10000862ba6e
😎 Deploy Preview	https://deploy-preview-154--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:

📁 Root Directory

Owners: @rootfs, @Xunzhuo
Files changed:

• CONTRIBUTING.md
• tools/make/common.mk
• tools/make/milvus.mk

📁 src

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

• src/semantic-router/pkg/cache/cache_interface.go
• src/semantic-router/pkg/cache/cache_test.go
• src/semantic-router/pkg/cache/inmemory_cache.go
• src/semantic-router/pkg/cache/milvus_cache.go
• src/semantic-router/pkg/extproc/error_metrics_test.go
• src/semantic-router/pkg/extproc/metrics_integration_test.go
• src/semantic-router/pkg/extproc/request_handler.go
• src/semantic-router/pkg/extproc/response_handler.go
• src/semantic-router/pkg/extproc/router.go
• src/semantic-router/pkg/extproc/test_utils_test.go
• src/semantic-router/pkg/extproc/testing_helpers_test.go

---

🎉 Thanks for your contributions!

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