server : improve cache reuse diagnostics for SWA and hybrid models

[1oridevs]

Overview

This PR improves diagnostics when prompt cache reuse falls back to full prompt re-processing.

It adds additional logging around SWA and hybrid/recurrent memory cases so it is easier to understand why cache reuse fails. This change does not modify any cache reuse logic — it only improves observability.

Additional information

The change is limited to tools/server/server-context.cpp and only affects logging behavior.

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure: YES — I used AI for brainstorming and wording help, but I wrote and verified the changes myself and take full responsibility for this PR.

[ggml-gh-bot]

Hi @1oridevs, thanks for your contribution!

Per our contribution guidelines, the automated PR checker found the following issue(s) that need your attention:

• AI-generated content: This project does not accept PRs, descriptions or commit messages that are fully or predominantly AI-generated. If you have used AI to assist you in writing code, please make sure to disclose that explicitly.

---

Please note that maintainers reserve the right to make final decisions on PRs. If you believe there is a mistake, please comment below.

[1oridevs]

Thanks for the note. I updated the PR description with an explicit AI usage disclosure.

I used AI for brainstorming and wording assistance only. I made the code changes myself, reviewed the diff, built the project locally, and take full responsibility for this submission.

If any further clarification is needed, I’m happy to provide it.