llama.cpp backend: allow `--reasoning on|off` in runtime flag allowlist

llama.cpp's llama-server (verified on build 9879 / 72874f559) exposes a first-class server flag:

--reasoning [on|off|auto]   Use reasoning/thinking in the chat (default: auto = detect from template)

docker model configure rejects it:

$ docker model configure <model> -- --reasoning off
runtime flag "--reasoning" is not allowed for backend "llama.cpp"

It's missing from pkg/inference/runtime_flags_allowlist.go (which already allows --reasoning-format, --reasoning-budget, --reasoning-preserve, --chat-template-kwargs).

Why it matters: for hybrid thinking models (Qwen 3.5/4B family), the current way to pin a model non-thinking at the server level is --chat-template-kwargs '{"enable_thinking": false}'. On current builds this logs a deprecation warning at every server start:

W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead.

The flag is a simple enum, touches no files or external resources, and fits the existing allowlist security model (cf. #1032 for the reasoning-preserve flags).

Related: #1028 (request-body reasoning_effort: none), #1032 (reasoning-preserve flags).

Start in pkg/inference/runtime_flags_allowlist.go, where the existing llama.cpp reasoning-related flags are defined. Compare the allowlist entries with the documented llama-server --reasoning on|off|auto flag, then verify that docker model configure -- --reasoning off is accepted without the previous rejection.