```

feat(iOS): 更新MNN后端模型配置优化性能

将MNN主模型从Qwen3.5-4B(~2.64GiB)降级为Qwen3.5-2B(~1.1GiB)，因为4B版本
实测运行过慢，影响用户体验。iPhone17+/SME2设备使用2B模型，保留MLX
兜底方案用于模拟器和备用场景，确保AI推理性能和存储效率的平衡。
```

康康/Features/Me/InferenceSettingsView.swift

@@ -3,10 +3,10 @@ import SwiftUI
 /// 推理引擎设置:在 MNN(CPU/SME2,考核路径)与 MLX(GPU,兜底)间切换,并展示 SME2 探测状态。
 /// 切换只改持久化选择;下一次 AI 调用(prepare/generate)按新引擎加载。
 struct InferenceSettingsView: View {
-    @AppStorage("kk.inferenceEngine") private var engineRaw = InferenceEngine.mnn.rawValue
+    @AppStorage("kk.inferenceEngine") private var engineRaw = EnginePreference.auto.rawValue
 
-    private var selected: InferenceEngine {
-        InferenceEngine(rawValue: engineRaw) ?? .mnn
+    private var selected: EnginePreference {
+        EnginePreference(rawValue: engineRaw) ?? .auto
     }
 
     var body: some View {
@@ -21,7 +21,7 @@ struct InferenceSettingsView: View {
                 .padding(.top, 4)
                 .padding(.bottom, 6)
 
-                ForEach(InferenceEngine.allCases, id: \.self) { engine in
+                ForEach(EnginePreference.allCases, id: \.self) { engine in
                     engineRow(engine)
                 }
 
@@ -34,8 +34,8 @@ struct InferenceSettingsView: View {
         .background(Tj.Palette.sand.ignoresSafeArea())
     }
 
-    private func engineRow(_ engine: InferenceEngine) -> some View {
-        let available = engine.isAvailable
+    private func engineRow(_ engine: EnginePreference) -> some View {
+        let available = isAvailable(engine)
         let isOn = (selected == engine)
         return Button {
             guard available else { return }
@@ -44,7 +44,7 @@ struct InferenceSettingsView: View {
             HStack(spacing: 12) {
                 ZStack {
                     Circle().fill(isOn ? Tj.Palette.amber.opacity(0.25) : Tj.Palette.sand2)
-                    Image(systemName: engine == .mnn ? "cpu.fill" : "bolt.fill")
+                    Image(systemName: iconName(engine))
                         .font(.tjScaled(18))
                         .foregroundStyle(isOn ? Tj.Palette.ink : Tj.Palette.text2)
                 }
@@ -74,8 +74,35 @@ struct InferenceSettingsView: View {
         .disabled(!available)
     }
 
-    private func subtitle(_ engine: InferenceEngine, available: Bool) -> String {
+    /// .auto 永远可用;具体引擎看自身可用性。
+    private func isAvailable(_ engine: EnginePreference) -> Bool {
         switch engine {
+        case .auto: return true
+        case .mnn:  return InferenceEngine.mnn.isAvailable
+        case .mlx:  return InferenceEngine.mlx.isAvailable
+        }
+    }
+
+    private func iconName(_ engine: EnginePreference) -> String {
+        switch engine {
+        case .auto: return "wand.and.stars"
+        case .mnn:  return "cpu.fill"
+        case .mlx:  return "bolt.fill"
+        }
+    }
+
+    private func subtitle(_ engine: EnginePreference, available: Bool) -> String {
+        switch engine {
+        case .auto:
+            // 显示自动解析后实际命中的引擎,让用户看清「这台机选了什么」。
+            let resolved = engine.resolved
+            if resolved == .mnn {
+                return InferenceEngine.cpuSupportsSME2
+                    ? String(appLoc: "按本机配置选择 · 当前 MNN + SME2")
+                    : String(appLoc: "按本机配置选择 · 当前 MNN(NEON)")
+            } else {
+                return String(appLoc: "按本机配置选择 · 当前 MLX(MNN 不可用)")
+            }
         case .mnn:
             if !available { return String(appLoc: "本设备/模拟器不可用,自动回退 MLX") }
             return InferenceEngine.cpuSupportsSME2