```

feat(AI): 统一多模态模型架构，整合文本和视觉推理路径

- 将文本生成和VL(图→文)功能合并到单一的Qwen3.5-4B多模态MNN模型
- 移除独立的Qwen3-VL-4B模型依赖，MLX VL改为使用.llm的多模态模型
- 更新ModelKind枚举，新增userFacing集合用于面向用户展示
- MNN后端现在同时支持文本和视觉任务，模拟器回退到MLX

refactor(models): 模型管理和界面调整以适应新的多模态架构

- 更新模型管理界面，只显示统一的Qwen3.5-4B(MNN)模型给用户
- 修改就绪状态检查逻辑，使用ModelKind.userFacing替代allCases
- 更新模型文件清单，从Qwen3.5-2B升级到Qwen3.5-4B-4bit
- 调整模型管理页面UI，突出MNN+SME2端侧加速功能

feat(camera): 添加拍照识别引擎切换功能

- 实现双路径拍照识别：Apple Vision OCR + 文本模型 和 Qwen3-VL直接识别
- 添加预处理逻辑，优化Qwen3-VL对窄长区域图片的识别效果
- 在模型管理页面添加拍照识别引擎选择组件
- 提供用户界面选项，在两种识别方式间切换

style(ui): 优化输入框样式和颜色主题一致性

- 为指标快速表单添加浅色主题偏好
- 统一所有文本输入框的颜色样式(theme)
- 创建EntryInputField组件，替换原有的单行输入+按钮模式
- 实现聊天框风格的条目输入，支持多行自适应和圆形发送按钮

fix(build): 修正Xcode项目配置中的重复框架搜索路径

- 清理project.pbxproj中重复的FRAMEWORK_SEARCH_PATHS配置
- 重新排列Swift桥接头文件配置确保正确引用
- 修复因路径配置重复导致的编译警告问题

test: 增加区域图片预处理和模型清单测试覆盖

- 添加RegionImageCropper.prepareForQwenVL的单元测试
- 验证宽而矮图片的放大和填充逻辑
- 更新ModelManifestTests中的字节数预期值以匹配新模型
- 修正OCRService中VNRecognizedTextObservation类型的处理
```

康康.xcodeproj/project.pbxproj

@@ -420,6 +420,7 @@
 				ENABLE_HARDENED_RUNTIME = YES;
 				ENABLE_PREVIEWS = YES;
 				ENABLE_USER_SELECTED_FILES = readonly;
+				FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)/Frameworks";
 				GENERATE_INFOPLIST_FILE = YES;
 				INFOPLIST_KEY_CFBundleDisplayName = "康康";
 				INFOPLIST_KEY_ITSAppUsesNonExemptEncryption = NO;
@@ -447,8 +448,6 @@
 				PRODUCT_BUNDLE_IDENTIFIER = com.xuhuayong.kangkang;
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				REGISTER_APP_GROUPS = YES;
-				FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)/Frameworks";
-				SWIFT_OBJC_BRIDGING_HEADER = "康康/康康-Bridging-Header.h";
 				SDKROOT = auto;
 				STRING_CATALOG_GENERATE_SYMBOLS = YES;
 				SUPPORTED_PLATFORMS = "iphoneos iphonesimulator";
@@ -456,6 +455,7 @@
 				SWIFT_APPROACHABLE_CONCURRENCY = YES;
 				SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor;
 				SWIFT_EMIT_LOC_STRINGS = YES;
+				SWIFT_OBJC_BRIDGING_HEADER = "康康/康康-Bridging-Header.h";
 				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
 				SWIFT_VERSION = 5.0;
 				TARGETED_DEVICE_FAMILY = "1,2";
@@ -476,6 +476,7 @@
 				ENABLE_HARDENED_RUNTIME = YES;
 				ENABLE_PREVIEWS = YES;
 				ENABLE_USER_SELECTED_FILES = readonly;
+				FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)/Frameworks";
 				GENERATE_INFOPLIST_FILE = YES;
 				INFOPLIST_KEY_CFBundleDisplayName = "康康";
 				INFOPLIST_KEY_ITSAppUsesNonExemptEncryption = NO;
@@ -503,8 +504,6 @@
 				PRODUCT_BUNDLE_IDENTIFIER = com.xuhuayong.kangkang;
 				PRODUCT_NAME = "$(TARGET_NAME)";
 				REGISTER_APP_GROUPS = YES;
-				FRAMEWORK_SEARCH_PATHS = "$(PROJECT_DIR)/Frameworks";
-				SWIFT_OBJC_BRIDGING_HEADER = "康康/康康-Bridging-Header.h";
 				SDKROOT = auto;
 				STRING_CATALOG_GENERATE_SYMBOLS = YES;
 				SUPPORTED_PLATFORMS = "iphoneos iphonesimulator";
@@ -512,6 +511,7 @@
 				SWIFT_APPROACHABLE_CONCURRENCY = YES;
 				SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor;
 				SWIFT_EMIT_LOC_STRINGS = YES;
+				SWIFT_OBJC_BRIDGING_HEADER = "康康/康康-Bridging-Header.h";
 				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
 				SWIFT_VERSION = 5.0;
 				TARGETED_DEVICE_FAMILY = "1,2";

康康/AI/AIRuntime.swift

@@ -33,10 +33,11 @@ actor AIRuntime {
     private var vlSession: VLSession?
 
     // MARK: - MNN 后端(CPU/SME2,挑战赛考核路径)
-    // 文本生成在 .mnn 引擎下走 MNN;VL(图→文)暂仍走 MLX(MNN VL 需 OMNI 构建)。
+    // .mnn 引擎下,文本生成与 VL(图→文)由同一个 Qwen3.5-4B 多模态 MNN 模型全包(已实测)。
+    // 模拟器无 MNN,VL 回退 MLX 的 Qwen3-VL-4B。
     private let mnn = MNNBackend()
     private(set) var mnnStatus: Status = .notReady
-    /// MNN 模型目录(下载/旁路导入到 Models/Qwen3.5-2B-MNN)。
+    /// MNN 模型目录(下载/旁路导入到 Models/Qwen3.5-4B-MNN)。
     nonisolated static var mnnModelFolder: URL {
         ModelStore.shared.localURL(for: .mnnLLM)
     }
@@ -265,8 +266,9 @@ actor AIRuntime {
         }
         if vlStatus == .ready { return }
 
-        // 同 prepare():用 isComplete 排除半下载(避免在残缺权重上崩溃),与下载服务判据一致。
+        // MLX VL 改用 .llm 的 Qwen3.5-4B 多模态(VLMModelFactory 走 qwen3_5 视觉路径),
-        guard ModelStore.shared.isComplete(for: .vl) else {
+        // 不再单独需要 Qwen3-VL-4B。用 isComplete 排除半下载,与下载服务判据一致。
+        guard ModelStore.shared.isComplete(for: .llm) else {
             vlStatus = .error("VL 模型未就绪")
             throw AIRuntimeError.notReady
         }
@@ -284,7 +286,7 @@ actor AIRuntime {
         vlStatus = .loading
         do {
             let session = try await VLSession.load(
-                folderURL: ModelStore.shared.localURL(for: .vl)
+                folderURL: ModelStore.shared.localURL(for: .llm)
             )
             self.vlSession = session
             vlStatus = .ready

康康/AI/MNNBackend.swift

@@ -3,8 +3,9 @@ import Foundation
 /// MNN(CPU / SME2)推理后端,封装 `MNNLLMBridge` 的文本流式生成。
 /// 与 `LLMSession`/`VLSession` 同款 actor 隔离;跨调用的串行化由上游 `AIRuntime` 闸门保证。
 ///
-/// VL(图→文)需 MNN OMNI 构建(OpenCV 解码图像),当前文本构建不支持;`analyze` 抛错,
+/// 文本与视觉(图→文)由同一个 Qwen3.5-4B 多模态 MNN 模型承担:`generate` 走文本,
-/// 上层在 VL 路径回退 MLX(见 `AIRuntime`)。
+/// `analyze` 把图片拼成 <img> 标签交给 Omni 内核 imread 解码(需 OMNI 构建,xcframework 已含)。
+/// 已实测可用,真机走此单模型全包路径;模拟器无 MNN,VL 仍回退 MLX(见 `AIRuntime`)。
 actor MNNBackend {
     private var bridge: MNNLLMBridge?
 

康康/AI/ModelManifest.swift

@@ -18,20 +18,18 @@ nonisolated enum ModelManifest {
     static func files(for kind: ModelKind) -> [ModelFile] {
         switch kind {
         case .llm:
-            // Qwen3.5-2B-4bit:多模态仓库,但走 LLMModelFactory 的 qwen3_5 文本路径加载。
+            // Qwen3.5-4B-4bit:多模态仓库,MLX 兜底用它同时做文本(LLMModelFactory qwen3_5 文本路径)
-            // 字节数取自 mlx-community/Qwen3.5-2B-4bit 仓库实际 blob 大小(HF API,2026-06 核对)。
+            // 与视觉(VLMModelFactory qwen3_5)。字节数取自 mlx-community/Qwen3.5-4B-4bit
-            // 该仓库 tokenizer 体系为 vocab.json + tokenizer.json(无 merges.txt /
+            // 仓库实际 blob 大小(HF API,2026-06 核对)。镜像全部运行文件(含视觉预处理配置),
-            // special_tokens_map.json / added_tokens.json),chat_template 改为 .jinja。
+            // 排除 README.md / .gitattributes。
-            // 一并镜像视觉预处理配置(preprocessor / processor / video_preprocessor),
-            // 文本加载用不到但体积可忽略,保持与仓库一致避免漏文件。
             return [
-                ModelFile(path: "config.json", bytes: 3_113),
+                ModelFile(path: "config.json", bytes: 3_366),
-                ModelFile(path: "model.safetensors", bytes: 1_722_271_785),
+                ModelFile(path: "model.safetensors", bytes: 3_034_300_695),
-                ModelFile(path: "model.safetensors.index.json", bytes: 81_722),
+                ModelFile(path: "model.safetensors.index.json", bytes: 101_944),
                 ModelFile(path: "tokenizer.json", bytes: 19_989_343),
                 ModelFile(path: "tokenizer_config.json", bytes: 1_139),
                 ModelFile(path: "vocab.json", bytes: 6_722_759),
-                ModelFile(path: "chat_template.jinja", bytes: 7_755),
+                ModelFile(path: "chat_template.jinja", bytes: 7_756),
                 ModelFile(path: "preprocessor_config.json", bytes: 390),
                 ModelFile(path: "processor_config.json", bytes: 1_300),
                 ModelFile(path: "video_preprocessor_config.json", bytes: 385),

康康/AI/ModelStore.swift

@@ -2,16 +2,17 @@ import Foundation
 
 nonisolated enum ModelKind: String, CaseIterable {
     /// 也是沙盒 Models/ 下的子目录名 / CDN 路径段。
-    /// - llm:MLX(GPU)文本兜底,Qwen3.5-2B(多模态权重,走 qwen3_5 文本路径)。
+    /// 同一个 Qwen3.5-4B,两种格式两种引擎:
-    /// - vl :MLX(GPU)拍照识别,Qwen3-VL-4B。
+    /// - mnnLLM:MNN(CPU/SME2,考核路径)文本+视觉一肩挑,taobao-mnn 预转换。真机主用,只露它。
-    /// - mnnLLM:MNN(CPU/SME2,挑战赛考核路径)文本,Qwen3.5-4B 预转换 MNN 格式(taobao-mnn)。
+    /// - llm:MLX(GPU)兜底,Qwen3.5-4B-4bit 多模态(同时兜底文本与视觉,走 qwen3_5)。
-    case llm    = "Qwen3.5-2B-4bit"
+    /// - vl:已废弃(MLX VL 改走 .llm 多模态),保留枚举避免动一圈穷举 switch,不再下载/展示。
+    case llm    = "Qwen3.5-4B-4bit"
     case vl     = "Qwen3-VL-4B-Instruct-4bit"
     case mnnLLM = "Qwen3.5-4B-MNN"
 
     var displayName: String {
         switch self {
-        case .llm:    return "Qwen3.5-2B (MLX)"
+        case .llm:    return "Qwen3.5-4B (MLX)"
         case .vl:     return "Qwen3-VL-4B"
         case .mnnLLM: return "Qwen3.5-4B (MNN/SME2)"
         }
@@ -22,6 +23,12 @@ nonisolated enum ModelKind: String, CaseIterable {
 
     /// 用于判定该模型是否已就绪的最小标志文件
     var sentinelFilename: String { "config.json" }
+
+    /// 面向用户的模型集合:模型管理页 / 下载全部 / 就绪计数对外只暴露统一的
+    /// Qwen3.5-4B(MNN,文本+视觉全包,真机走它)。
+    /// MLX 的 .llm/.vl 仅作模拟器与兜底路径,保留枚举与下载能力(旁路导入仍可单独导),
+    /// 但不在「我的 · 模型管理」展示,也不计入「下载全部」与就绪计数。
+    static let userFacing: [ModelKind] = [.mnnLLM]
 }
 
 /// `@unchecked Sendable`:rootURL 是 let,方法只读 filesystem(线程安全),

康康/AI/Prompts/VLPrompts.swift

@@ -3,7 +3,7 @@ import Foundation
 /// VL 模型(Qwen3-VL)用于体检 / 化验单识别的 prompt 模板。
 /// 输出契约:严格 JSON,无任何解释文字、markdown 围栏或前后缀。
 /// 解析失败 → CaptureService 回退到手动录入(§3.2 失败回退红线)。
-enum VLPrompts {
+nonisolated enum VLPrompts {
 
     /// 输出 JSON 的字段定义(写进 prompt 里教模型):
     /// ```

康康/Features/Indicator/IndicatorQuickSheet.swift

@@ -143,6 +143,7 @@ struct IndicatorQuickSheet: View {
                 .clipShape(RoundedRectangle(cornerRadius: Tj.Radius.xl, style: .continuous))
                 .ignoresSafeArea(edges: .bottom)
         )
+        .preferredColorScheme(.light)
         .presentationDetents([.large])
         .presentationDragIndicator(.hidden)
         .presentationBackground(Tj.Palette.sand)
@@ -423,6 +424,8 @@ struct IndicatorQuickSheet: View {
             TextField(placeholder, text: value)
                 .keyboardType(.decimalPad)
                 .font(.tjScaled( 20, weight: .semibold, design: .monospaced))
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                 .multilineTextAlignment(.center)
                 .padding(.vertical, 10)
                 .frame(width: 90)
@@ -468,6 +471,8 @@ struct IndicatorQuickSheet: View {
             sectionLabel(String(appLoc: "指标名"))
             TextField("例如:血红蛋白", text: $name)
                 .textInputAutocapitalization(.never)
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                 .padding(.horizontal, 14)
                 .padding(.vertical, 12)
                 .background(fieldBg)
@@ -489,6 +494,8 @@ struct IndicatorQuickSheet: View {
                 TextField(monitorFieldPlaceholder, text: $value)
                     .keyboardType(.decimalPad)
                     .font(.tjScaled( 18, weight: .semibold, design: .monospaced))
+                    .foregroundStyle(Tj.Palette.text)
+                    .tint(Tj.Palette.ink)
                     .padding(.horizontal, 14)
                     .padding(.vertical, 12)
                     .background(fieldBg)
@@ -499,6 +506,8 @@ struct IndicatorQuickSheet: View {
                 TextField("mmol/L", text: $unit)
                     .textInputAutocapitalization(.never)
                     .autocorrectionDisabled()
+                    .foregroundStyle(Tj.Palette.text)
+                    .tint(Tj.Palette.ink)
                     .padding(.horizontal, 14)
                     .padding(.vertical, 12)
                     .background(fieldBg)
@@ -522,6 +531,8 @@ struct IndicatorQuickSheet: View {
             TextField("例如:< 3.40 或 3.9 - 6.1", text: $range)
                 .textInputAutocapitalization(.never)
                 .autocorrectionDisabled()
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                 .padding(.horizontal, 14)
                 .padding(.vertical, 12)
                 .background(fieldBg)
@@ -581,6 +592,8 @@ struct IndicatorQuickSheet: View {
             sectionLabel(String(appLoc: "备注(可选)"))
             TextField("例如:空腹采血", text: $note, axis: .vertical)
                 .lineLimit(1...3)
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                 .padding(.horizontal, 14)
                 .padding(.vertical, 12)
                 .background(fieldBg)

康康/Features/Me/MeView.swift

@@ -152,10 +152,10 @@ struct MeView: View {
 
     private var modelDetail: String {
         let states = downloadService.states
-        if ModelKind.allCases.allSatisfy({ states[$0]?.phase == .ready }) { return String(appLoc: "已就绪") }
+        if ModelKind.userFacing.allSatisfy({ states[$0]?.phase == .ready }) { return String(appLoc: "已就绪") }
         if downloadService.isAnyDownloading { return String(appLoc: "下载中…") }
-        let readyCount = ModelKind.allCases.filter { states[$0]?.phase == .ready }.count
+        let readyCount = ModelKind.userFacing.filter { states[$0]?.phase == .ready }.count
-        return readyCount == 0 ? String(appLoc: "未下载") : String(appLoc: "\(readyCount)/\(ModelKind.allCases.count) 就绪")
+        return readyCount == 0 ? String(appLoc: "未下载") : String(appLoc: "\(readyCount)/\(ModelKind.userFacing.count) 就绪")
     }
 
     private var inferenceEngineCard: some View {

康康/Features/Me/ModelManagementView.swift

@@ -10,25 +10,29 @@ struct ModelManagementView: View {
     @State private var showCellularConfirm = false
     @State private var showImporter = false
     @State private var importError: String?
+    @AppStorage(QuickRegionRecognitionEngine.storageKey)
+    private var quickRegionEngineRaw = QuickRegionRecognitionEngine.defaultValue.rawValue
 
     private let monitor = NWPathMonitor()
     private let monitorQueue = DispatchQueue(label: "kk.netmonitor")
 
     private var allReady: Bool {
-        ModelKind.allCases.allSatisfy { service.states[$0]?.phase == .ready }
+        ModelKind.userFacing.allSatisfy { service.states[$0]?.phase == .ready }
     }
 
     var body: some View {
         ScrollView {
             VStack(spacing: 14) {
-                ForEach(ModelKind.allCases, id: \.self) { kind in
+                ForEach(ModelKind.userFacing, id: \.self) { kind in
                     modelCard(kind)
                 }
 
+                recognitionEngineCard
+
                 actionButtons
                     .padding(.top, 4)
 
-                if service.states[.llm]?.phase == .ready {
+                if service.states[.mnnLLM]?.phase == .ready {
                     NavigationLink {
                         ModelSelfTestView()
                     } label: {
@@ -76,6 +80,46 @@ struct ModelManagementView: View {
         }
     }
 
+    // MARK: - 拍照识别引擎
+
+    private var selectedRecognitionEngine: QuickRegionRecognitionEngine {
+        QuickRegionRecognitionEngine(storedValue: quickRegionEngineRaw)
+    }
+
+    private var recognitionEngineCard: some View {
+        VStack(alignment: .leading, spacing: 12) {
+            HStack(alignment: .top, spacing: 10) {
+                ZStack {
+                    Circle().fill(Tj.Palette.sand2)
+                    Image(systemName: "camera.metering.center.weighted")
+                        .font(.tjScaled( 18))
+                        .foregroundStyle(Tj.Palette.text2)
+                }
+                .frame(width: 38, height: 38)
+
+                VStack(alignment: .leading, spacing: 3) {
+                    Text("异常项拍照识别")
+                        .font(.tjScaled( 15, weight: .semibold))
+                        .foregroundStyle(Tj.Palette.text)
+                    Text(selectedRecognitionEngine.detail)
+                        .font(.tjScaled( 12))
+                        .foregroundStyle(Tj.Palette.text3)
+                }
+                Spacer()
+            }
+
+            Picker("异常项拍照识别", selection: $quickRegionEngineRaw) {
+                ForEach(QuickRegionRecognitionEngine.allCases) { engine in
+                    Text(engine.title).tag(engine.rawValue)
+                }
+            }
+            .pickerStyle(.segmented)
+        }
+        .padding(14)
+        .frame(maxWidth: .infinity, alignment: .leading)
+        .tjCard()
+    }
+
     // MARK: - 模型卡片
 
     private func modelCard(_ kind: ModelKind) -> some View {
@@ -146,7 +190,7 @@ struct ModelManagementView: View {
     private var actionButtons: some View {
         if service.isAnyDownloading {
             Button {
-                for kind in ModelKind.allCases { service.cancel(kind) }
+                for kind in ModelKind.userFacing { service.cancel(kind) }
             } label: {
                 Text("暂停下载").frame(maxWidth: .infinity)
             }
@@ -154,7 +198,7 @@ struct ModelManagementView: View {
         } else if allReady {
             HStack(spacing: 6) {
                 Image(systemName: "checkmark.seal.fill")
-                Text("两个模型都已就绪")
+                Text("Qwen3.5-4B 已就绪")
             }
             .font(.tjScaled( 13, weight: .semibold))
             .foregroundStyle(Tj.Palette.leaf)
@@ -198,8 +242,8 @@ struct ModelManagementView: View {
             defer { if scoped { folder.stopAccessingSecurityScopedResource() } }
 
             let name = folder.lastPathComponent
-            guard let kind = ModelKind.allCases.first(where: { $0.rawValue == name }) else {
+            guard let kind = ModelKind.userFacing.first(where: { $0.rawValue == name }) else {
-                let names = ModelKind.allCases.map(\.rawValue).joined(separator: " 或 ")
+                let names = ModelKind.userFacing.map(\.rawValue).joined(separator: " 或 ")
                 importError = String(appLoc: "请选择名为 \(names) 的文件夹")
                 return
             }
@@ -213,14 +257,14 @@ struct ModelManagementView: View {
     // MARK: - 辅助
 
     private var totalAllBytes: Int {
-        ModelKind.allCases.reduce(0) { $0 + ModelManifest.totalBytes(for: $1) }
+        ModelKind.userFacing.reduce(0) { $0 + ModelManifest.totalBytes(for: $1) }
     }
 
     private func subtitle(_ kind: ModelKind) -> String {
         switch kind {
         case .llm:    return String(appLoc: "文本解读 · 趋势 / 问答(MLX 兜底)")
         case .vl:     return String(appLoc: "拍照识别报告 → 结构化指标")
-        case .mnnLLM: return String(appLoc: "文本解读 · MNN + SME2 端侧加速")
+        case .mnnLLM: return String(appLoc: "文本解读 + 拍照识别 · MNN + SME2 端侧加速")
         }
     }
 

康康/Features/Profile/ProfileEditView.swift

@@ -370,17 +370,14 @@ private struct ChronicSection: View {
                 }
             }
 
-            HStack {
+            EntryInputField(placeholder: String(appLoc: "自定义慢病"), text: $newCustomCondition) {
-                TextField("自定义慢病", text: $newCustomCondition)
-                Button("加") {
                 let trimmed = newCustomCondition.trimmingCharacters(in: .whitespaces)
                 guard !trimmed.isEmpty,
                       !profile.chronicConditions.contains(trimmed) else { return }
                 profile.chronicConditions.append(trimmed)
                 newCustomCondition = ""
             }
-                .disabled(newCustomCondition.trimmingCharacters(in: .whitespaces).isEmpty)
+            .listRowBackground(Color.clear)
-            }
         } header: {
             Text("慢病(影响参考范围与 AI 解读)")
         }
@@ -408,6 +405,48 @@ private struct ChronicSection: View {
     }
 }
 
+// MARK: - 聊天框风格的条目输入(圆角容器 + 多行增长 + 圆形发送按钮)
+
+/// 替代原先单行 `TextField + “加”` 的搜索框观感:文字随内容换行增长(1~4 行),
+/// 右侧圆形发送按钮(内容为空时禁用变灰)。过敏 / 家族史 / 用药 / 自定义慢病共用。
+private struct EntryInputField: View {
+    let placeholder: String
+    @Binding var text: String
+    var onSubmit: () -> Void
+
+    private var canSubmit: Bool {
+        !text.trimmingCharacters(in: .whitespaces).isEmpty
+    }
+
+    var body: some View {
+        HStack(alignment: .bottom, spacing: 8) {
+            TextField(placeholder, text: $text, axis: .vertical)
+                .lineLimit(1...4)
+                .padding(.horizontal, 14)
+                .padding(.vertical, 10)
+                .background(
+                    RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
+                        .fill(Tj.Palette.paper)
+                )
+                .overlay(
+                    RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
+                        .strokeBorder(Tj.Palette.line, lineWidth: 1)
+                )
+
+            Button {
+                if canSubmit { onSubmit() }
+            } label: {
+                Image(systemName: "arrow.up.circle.fill")
+                    .font(.tjScaled(28))
+                    .foregroundStyle(canSubmit ? Tj.Palette.ink : Tj.Palette.text3)
+            }
+            .buttonStyle(.plain)
+            .disabled(!canSubmit)
+        }
+        .padding(.vertical, 2)
+    }
+}
+
 // MARK: - 过敏 / 家族史 / 用药(每节自带 @State,敲字只重算本节)
 
 private struct StringListSection: View {
@@ -431,16 +470,13 @@ private struct StringListSection: View {
                     .buttonStyle(.borderless)
                 }
             }
-            HStack {
+            EntryInputField(placeholder: placeholder, text: $newInput) {
-                TextField(placeholder, text: $newInput)
-                Button("加") {
                 let trimmed = newInput.trimmingCharacters(in: .whitespaces)
                 guard !trimmed.isEmpty, !items.contains(trimmed) else { return }
                 items.append(trimmed)
                 newInput = ""
             }
-                .disabled(newInput.trimmingCharacters(in: .whitespaces).isEmpty)
+            .listRowBackground(Color.clear)
-            }
         }
     }
 }

康康/Features/Quick/QuickRegionCaptureFlow.swift

@@ -15,6 +15,8 @@ struct QuickRegionCaptureFlow: View {
     @Environment(\.modelContext) private var ctx
     let onClose: () -> Void
 
+    @AppStorage(QuickRegionRecognitionEngine.storageKey)
+    private var recognitionEngineRaw = QuickRegionRecognitionEngine.defaultValue.rawValue
     @State private var phase: Phase = .idle
 
     enum Phase {
@@ -98,8 +100,20 @@ struct QuickRegionCaptureFlow: View {
     // MARK: - 识别(框内子图 → OCR → LLM)
 
     /// 对已裁好的框内子图跑识别。失败/超时返回提示文案,绝不抛出(由 RegionAdjustView 展示)。
-    /// 链路:Vision 端侧 OCR 取文本 → Qwen3-1.7B 结构化抽指标(对齐 indicator-capture-ocr-llm)。
+    /// 链路由「我的 → 模型管理 → 拍照识别引擎」决定:
+    /// - Apple Vision:Vision 端侧 OCR → Qwen3-1.7B 结构化抽指标
+    /// - Qwen3-VL:局部图片 → Qwen3-VL 直接结构化抽指标
     private func recognizeRegion(_ image: UIImage) async -> (items: [QuickRegionItem], warning: String?) {
+        let engine = QuickRegionRecognitionEngine(storedValue: recognitionEngineRaw)
+        switch engine {
+        case .appleVision:
+            return await recognizeWithAppleVision(image)
+        case .qwenVL:
+            return await recognizeWithQwenVL(image)
+        }
+    }
+
+    private func recognizeWithAppleVision(_ image: UIImage) async -> (items: [QuickRegionItem], warning: String?) {
         do {
             let text = try await OCRService.recognizeText(in: image)
             if Task.isCancelled { return ([], nil) }   // 超时:文案由调用方给
@@ -125,6 +139,30 @@ struct QuickRegionCaptureFlow: View {
         }
     }
 
+    private func recognizeWithQwenVL(_ image: UIImage) async -> (items: [QuickRegionItem], warning: String?) {
+        let prepared = RegionImageCropper.prepareForQwenVL(image)
+        guard let data = prepared.jpegData(compressionQuality: 0.95) else {
+            return ([], String(appLoc: "图片编码失败,手动补充"))
+        }
+        #if DEBUG
+        print("🖼️ [Qwen3-VL region] prepared image=\(Int(prepared.size.width))x\(Int(prepared.size.height)), bytes=\(data.count)")
+        #endif
+        do {
+            let parsed = try await CaptureService.shared.recognizeRegion(imageData: data)
+            if Task.isCancelled { return ([], nil) }
+            let items = Self.buildItems(from: parsed)
+            return (items, items.isEmpty ? String(appLoc: "没读出指标,挪一下框再试") : nil)
+        } catch CaptureError.modelNotReady {
+            return ([], String(appLoc: "模型未就绪,请在模型管理下载或切回 Apple Vision"))
+        } catch let CaptureError.parseFailed(msg) {
+            return ([], String(appLoc: "解析失败:\(msg)"))
+        } catch let CaptureError.inferenceFailed(msg) {
+            return ([], Task.isCancelled ? nil : String(appLoc: "识别失败:\(msg)"))
+        } catch {
+            return ([], Task.isCancelled ? nil : String(appLoc: "未知错误:\(error.localizedDescription)"))
+        }
+    }
+
     /// LLM 结果 → 可编辑行,异常项(high/low)置顶、默认勾选。
     private static func buildItems(from parsed: [ParsedReport.ParsedIndicator]) -> [QuickRegionItem] {
         let mapped = parsed.map {

康康/Features/Quick/QuickRegionRecognitionEngine.swift

@@ -0,0 +1,31 @@
+import Foundation
+
+enum QuickRegionRecognitionEngine: String, CaseIterable, Identifiable, Sendable {
+    case appleVision
+    case qwenVL
+
+    static let storageKey = "quickRegionRecognitionEngine"
+    static let defaultValue: QuickRegionRecognitionEngine = .appleVision
+
+    var id: String { rawValue }
+
+    init(storedValue: String) {
+        self = QuickRegionRecognitionEngine(rawValue: storedValue) ?? Self.defaultValue
+    }
+
+    var title: String {
+        switch self {
+        case .appleVision: return String(appLoc: "Apple Vision")
+        case .qwenVL:      return String(appLoc: "大模型直读")
+        }
+    }
+
+    var detail: String {
+        switch self {
+        case .appleVision:
+            return String(appLoc: "系统 OCR + 文本模型解析")
+        case .qwenVL:
+            return String(appLoc: "Qwen3.5-4B 多模态直接看图(MNN/MLX)")
+        }
+    }
+}

康康/Features/Quick/RegionCameraView.swift

@@ -352,6 +352,49 @@ enum RegionImageCropper {
         guard rect.width >= 1, rect.height >= 1, let cropped = cg.cropping(to: rect) else { return up }
         return UIImage(cgImage: cropped, scale: up.scale, orientation: .up)
     }
+
+    /// Qwen3-VL 局部图预处理:宽而矮的小框直接喂 VL 时,processor 再缩放容易把小字压没。
+    /// 这里只用于 Qwen3-VL 分支,Apple Vision OCR 保持吃原始裁剪图。
+    static func prepareForQwenVL(_ image: UIImage,
+                                 minimumShortEdge: CGFloat = 448,
+                                 maximumLongEdge: CGFloat = 2400,
+                                 padding: CGFloat = 64) -> UIImage {
+        let up = image.normalizedUp()
+        guard let cg = up.cgImage else { return up }
+
+        let sourceSize = CGSize(width: cg.width, height: cg.height)
+        guard sourceSize.width > 0, sourceSize.height > 0 else { return up }
+
+        let short = min(sourceSize.width, sourceSize.height)
+        let long = max(sourceSize.width, sourceSize.height)
+        var scale = max(1, minimumShortEdge / short)
+        if long * scale > maximumLongEdge {
+            scale = maximumLongEdge / long
+        }
+
+        let contentSize = CGSize(
+            width: max(1, (sourceSize.width * scale).rounded()),
+            height: max(1, (sourceSize.height * scale).rounded())
+        )
+        let canvasSize = CGSize(
+            width: contentSize.width + padding * 2,
+            height: contentSize.height + padding * 2
+        )
+
+        let format = UIGraphicsImageRendererFormat.default()
+        format.scale = 1
+        format.opaque = true
+        let renderer = UIGraphicsImageRenderer(size: canvasSize, format: format)
+        return renderer.image { ctx in
+            UIColor.white.setFill()
+            ctx.fill(CGRect(origin: .zero, size: canvasSize))
+
+            UIImage(cgImage: cg, scale: 1, orientation: .up).draw(
+                in: CGRect(x: padding, y: padding,
+                           width: contentSize.width, height: contentSize.height)
+            )
+        }
+    }
 }
 
 extension UIImage {

康康/Localizable.xcstrings

@@ -1314,9 +1314,15 @@
           }
         }
       }
+    },
+    "Apple Vision" : {
+
     },
     "Apple 健康里没有可导入的生日、性别、身高或血型。" : {
 
+    },
+    "Arm SME2" : {
+
     },
     "B 型" : {
       "localizations" : {
@@ -1386,12 +1392,18 @@
     },
     "lo" : {
 
+    },
+    "Metal GPU · 兜底 / 对照" : {
+
     },
     "mmHg" : {
 
     },
     "mmol/L" : {
 
+    },
+    "MNN 在端侧 CPU 上以 Arm SME2 指令集加速 Qwen 推理(本地、不上云)。切换后下一次 AI 调用生效。" : {
+
     },
     "O 型" : {
       "localizations" : {
@@ -1414,6 +1426,12 @@
           }
         }
       }
+    },
+    "Qwen3.5-4B 多模态直接看图(MNN/MLX)" : {
+
+    },
+    "Qwen3.5-4B 已就绪" : {
+
     },
     "s" : {
 
@@ -1853,6 +1871,7 @@
       }
     },
     "两个模型都已就绪" : {
+      "extractionState" : "stale",
       "localizations" : {
         "en" : {
           "stringUnit" : {
@@ -3635,6 +3654,7 @@
       }
     },
     "加" : {
+      "extractionState" : "stale",
       "localizations" : {
         "en" : {
           "stringUnit" : {
@@ -4322,6 +4342,9 @@
           }
         }
       }
+    },
+    "图片编码失败,手动补充" : {
+
     },
     "在「+ 新建 → 指标记录 → %@」记录一次" : {
       "localizations" : {
@@ -4600,6 +4623,9 @@
     },
     "大" : {
 
+    },
+    "大模型直读" : {
+
     },
     "失眠" : {
       "localizations" : {
@@ -5939,6 +5965,9 @@
     },
     "异常项快拍需要相机。去「设置 → 康康 → 相机」打开后再回来。" : {
 
+    },
+    "异常项拍照识别" : {
+
     },
     "强度" : {
       "localizations" : {
@@ -7111,6 +7140,9 @@
           }
         }
       }
+    },
+    "推理引擎" : {
+
     },
     "推理自检" : {
       "localizations" : {
@@ -7618,6 +7650,7 @@
       }
     },
     "文本解读 · 趋势 / 问答" : {
+      "extractionState" : "stale",
       "localizations" : {
         "en" : {
           "stringUnit" : {
@@ -7638,6 +7671,12 @@
           }
         }
       }
+    },
+    "文本解读 · 趋势 / 问答(MLX 兜底)" : {
+
+    },
+    "文本解读 + 拍照识别 · MNN + SME2 端侧加速" : {
+
     },
     "新建" : {
       "localizations" : {
@@ -8617,6 +8656,15 @@
           }
         }
       }
+    },
+    "本设备/模拟器不可用,自动回退 MLX" : {
+
+    },
+    "本设备不支持(需 A19/iPhone 17+)" : {
+
+    },
+    "本设备支持,MNN 已启用 SME2 加速" : {
+
     },
     "本设备未设置 Face ID 或密码" : {
       "localizations" : {
@@ -8860,6 +8908,9 @@
           }
         }
       }
+    },
+    "模型未就绪,请在模型管理下载或切回 Apple Vision" : {
+
     },
     "模型未就绪时 App 仍可使用,AI 功能会提示前往下载。" : {
       "localizations" : {
@@ -9872,6 +9923,12 @@
           }
         }
       }
+    },
+    "端侧 CPU + SME2 加速 · 挑战赛考核路径" : {
+
+    },
+    "端侧 CPU(本机无 SME2,NEON 回退)" : {
+
     },
     "第 %lld 轮 · 基于你刚才更新的文本 · %lld 条" : {
       "localizations" : {
@@ -10014,6 +10071,9 @@
           }
         }
       }
+    },
+    "系统 OCR + 文本模型解析" : {
+
     },
     "系统:iOS 17 或更新版本。" : {
       "localizations" : {

康康/Services/HealthExportDialogue.swift

@@ -7,7 +7,7 @@ struct HealthExportDialogueTurn: Identifiable, Hashable, Sendable {
 
         var transcriptLabel: String {
             switch self {
-            case .user: return String(appLoc: "患者")
+            case .user: return String(appLoc: "我")
             case .assistant: return String(appLoc: "康康")
             }
         }

康康/Services/ModelDownloadService.swift

@@ -58,7 +58,7 @@ final class ModelDownloadService {
     }
 
     func downloadAll() {
-        for kind in ModelKind.allCases { download(kind) }
+        for kind in ModelKind.userFacing { download(kind) }
     }
 
     /// 暂停下载。已下载的 .part 保留,下次从断点续传。

康康/Services/OCRService.swift

@@ -23,7 +23,7 @@ enum OCRService {
                 let handler = VNImageRequestHandler(cgImage: cgImage, orientation: .up, options: [:])
                 do {
                     try handler.perform([request])
-                    let obs = (request.results as? [VNRecognizedTextObservation]) ?? []
+                    let obs = request.results ?? []
                     cont.resume(returning: assemble(obs))
                 } catch {
                     cont.resume(throwing: error)

康康Tests/ModelManifestTests.swift

@@ -13,7 +13,7 @@ struct ModelManifestTests {
     }
 
     @Test func llmTotalBytesMatchesManifest() {
-        #expect(ModelManifest.totalBytes(for: .llm) == 1_749_079_691)
+        #expect(ModelManifest.totalBytes(for: .llm) == 3_061_129_077)
     }
 
     @Test func vlTotalBytesMatchesManifest() {
@@ -62,8 +62,8 @@ struct ModelManifestTests {
     }
 
     @Test func fileURLIsBaseSlashRepoSlashPath() {
-        let file = ModelFile(path: "config.json", bytes: 3_113)
+        let file = ModelFile(path: "config.json", bytes: 3_366)
         let url = ModelManifest.fileURL(for: .llm, file: file)
-        #expect(url.absoluteString == "https://file.myv0.com/Qwen3.5-2B-4bit/config.json")
+        #expect(url.absoluteString == "https://file.myv0.com/Qwen3.5-4B-4bit/config.json")
     }
 }

康康Tests/QuickRegionRecognitionEngineTests.swift

@@ -0,0 +1,18 @@
+import Testing
+@testable import 康康
+
+struct QuickRegionRecognitionEngineTests {
+
+    @Test func defaultsToAppleVisionOCR() {
+        #expect(QuickRegionRecognitionEngine.defaultValue == .appleVision)
+    }
+
+    @Test func rawValuesAreStableForAppStorage() {
+        #expect(QuickRegionRecognitionEngine.appleVision.rawValue == "appleVision")
+        #expect(QuickRegionRecognitionEngine.qwenVL.rawValue == "qwenVL")
+    }
+
+    @Test func unknownStoredValueFallsBackToDefault() {
+        #expect(QuickRegionRecognitionEngine(storedValue: "missing") == .appleVision)
+    }
+}

康康Tests/RegionImageCropperTests.swift

@@ -112,4 +112,41 @@ final class RegionImageCropperTests: XCTestCase {
                                                  imageFrame: CGRect(x: 0, y: 0, width: 100, height: 100)),
             .zero)
     }
+
+    /// Qwen3-VL 对宽而矮的局部小图更容易在 processor 缩放后丢字。
+    /// 进入 VL 前应把短边放大并加白边,但不拉伸内容。
+    func testPrepareForQwenVLUpscalesWideShortCropAndAddsPadding() {
+        let image = solidImage(size: CGSize(width: 320, height: 80))
+
+        let prepared = RegionImageCropper.prepareForQwenVL(image)
+
+        XCTAssertGreaterThanOrEqual(prepared.size.height, 448)
+        XCTAssertGreaterThan(prepared.size.width, 320)
+        XCTAssertEqual(prepared.size.width / prepared.size.height,
+                       4.0,
+                       accuracy: 0.8,
+                       "预处理应大致保留宽条内容比例,只允许白边造成轻微变化")
+    }
+
+    func testPrepareForQwenVLDoesNotEnlargePastLongEdgeLimit() {
+        let image = solidImage(size: CGSize(width: 5000, height: 900))
+
+        let prepared = RegionImageCropper.prepareForQwenVL(image)
+
+        XCTAssertLessThanOrEqual(max(prepared.size.width, prepared.size.height), 2400 + 128)
+    }
+
+    private func solidImage(size: CGSize) -> UIImage {
+        let format = UIGraphicsImageRendererFormat.default()
+        format.scale = 1
+        return UIGraphicsImageRenderer(size: size, format: format).image { ctx in
+            UIColor.white.setFill()
+            ctx.fill(CGRect(origin: .zero, size: size))
+            UIColor.black.setFill()
+            ctx.fill(CGRect(x: size.width * 0.1,
+                            y: size.height * 0.35,
+                            width: size.width * 0.8,
+                            height: size.height * 0.3))
+        }
+    }
 }