Add Metal execution preferences

PLAN.md

@@ -45,7 +45,7 @@ Exit criterion: restart the app and see the same project/session tree.
 
 ## Phase 1 — model library and on-demand loading
 
-Status: **partially implemented**. Basic preferences, typed generation defaults,
+Status: **partially implemented**. Typed generation and execution preferences
 and the complete background download workflow are implemented; the remaining
 DS4 runtime preferences, loading, inference, and idle unloading remain open.
 
@@ -153,9 +153,9 @@ than inventing application-specific behavior.
   `--nothink`. Preserve DS4's explicit-vs-default distinction because GLM
   applies model-family sampling defaults only when the user has not overridden
   them.
-- **Backend and execution:** backend (`--backend` and its aliases), CPU helper
-  threads, GPU power percentage, prefill chunk, exact/quality kernels, and warm
-  weights. Only offer backend/device choices supported by the current build.
+- **Execution:** the macOS app uses Metal exclusively; omit the unnecessary CPU
+  backend and backend selector. Persist CPU helper threads for host-side work,
+  GPU power percentage, prefill chunk, exact/quality kernels, and warm weights.
 - **Speculative decoding:** MTP draft-token count and margin, GLM MTP, GLM MTP
   timing, DSpark enablement, DSpark confidence threshold, and DSpark strict
   target-only decode. Enabling a dependent control must enable or require its