Misc. bug: The llama-server not read the "--keep" param that user input in the cli

[ZUIcat]

Name and Version

version b5124

Operating systems

Windows

Which llama.cpp modules do you know to be affected?

llama-server

Command line

"llama-server.exe" ^
-m test.guff ^
--host 127.0.0.1 --port 8090 ^
--keep 0

Problem description & steps to reproduce

The llama-server not read the "keep" param that user input in the cli.
I have read the code. Here, https://github.com/ggml-org/llama.cpp/blob/bc091a4dc585af25c438c8473285a8cfec5c7695/examples/server/server.cpp#L242A
params.n_keep = json_value(data, "n_keep", defaults.n_keep);
shoud be
params.n_keep = json_value(data, "n_keep", params_base.n_keep);

First Bad Commit

No response

Relevant log output

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.

[ZUIcat]

Fixed in #14120