feat(macos): local ASR model manager, menu-bar polish, and release 0.5.2

Adds a bundled local ASR model catalog for the macOS app with one-click
Sherpa Qwen3 / SenseVoice downloads (pause/resume, inline actions) and a
shared model storage directory used by MLX Qwen3. Fixes the light-mode
sidebar material and makes the menu-bar icon follow the system appearance
with a refreshed status mark. Renames the built product to OSGKeyboard.app.

Bumps version to 0.5.2 (build 19).

OSGKeyboardMac/MacLocalASRService.swift

@@ -1,13 +1,15 @@
 // MacLocalASRService.swift
 // OSGKeyboard · Mac
 //
-// On-device ASR for macOS. Primary: Qwen3-ASR-1.7B (MLX via mlx-swift-asr).
-// Falls back to Apple Speech when Qwen3 weights are absent or backend is Apple Speech.
+// On-device ASR for macOS. Routes through the bundled local ASR catalog:
+// Qwen3 MLX (default), Sherpa Qwen3 hotwords POC, SenseVoice, Apple Speech fallback.
 
 import Foundation
 
 enum MacLocalASRBackend: String, Sendable, CaseIterable {
     case qwen3MLX
+    case sherpaQwen3
+    case sherpaSenseVoice
     case appleSpeech
 }
 
@@ -39,28 +41,33 @@ enum MacLocalASRError: Error, LocalizedError {
 
 enum MacLocalASRPreferences {
     static let backendKey = "mac.localASR.backend"
-    static let qwen3ModelPathKey = "mac.localASR.qwen3ModelPath"
+    static let selectedModelIdKey = LocalASRPreferenceKeys.selectedModelId
+    /// Shared managed subfolder for the manually-provided MLX weights.
+    static let qwen3ModelRelativePath = "models/qwen3-asr-1.7b-mlx"
 
-    static var backend: MacLocalASRBackend {
+    static var selectedModelId: String {
         get {
-            guard let raw = UserDefaults.standard.string(forKey: backendKey),
-                  let value = MacLocalASRBackend(rawValue: raw) else {
-                return .qwen3MLX
+            if let raw = UserDefaults.standard.string(forKey: selectedModelIdKey), !raw.isEmpty {
+                return raw
             }
-            return value
+            return legacyBackend == .appleSpeech ? "apple-speech-fallback" : "qwen3-mlx-1.7b"
         }
-        set { UserDefaults.standard.set(newValue.rawValue, forKey: backendKey) }
+        set { UserDefaults.standard.set(newValue, forKey: selectedModelIdKey) }
     }
 
+    static var legacyBackend: MacLocalASRBackend {
+        guard let raw = UserDefaults.standard.string(forKey: backendKey),
+              let value = MacLocalASRBackend(rawValue: raw) else {
+            return .qwen3MLX
+        }
+        return value
+    }
+
+    /// Fixed location inside the shared managed model storage root. All three
+    /// catalog models live under the same directory, so MLX no longer needs a
+    /// per-model folder picker — the user drops converted weights here.
     static var qwen3ModelPath: String {
-        get { UserDefaults.standard.string(forKey: qwen3ModelPathKey) ?? defaultQwen3ModelPath }
-        set { UserDefaults.standard.set(newValue, forKey: qwen3ModelPathKey) }
-    }
-
-    /// Default install location for MLX-converted Qwen3-ASR weights.
-    static var defaultQwen3ModelPath: String {
-        let appSupport = FileManager.default.urls(for: .applicationSupportDirectory, in: .userDomainMask).first!
-        return appSupport.appendingPathComponent("OSGKeyboard/models/qwen3-asr-1.7b-mlx", isDirectory: true).path
+        LocalASRModelInstallState.installDirectory(for: qwen3ModelRelativePath).path
     }
 
     static func qwen3ModelIsInstalled(at path: String = qwen3ModelPath) -> Bool {
@@ -80,24 +87,93 @@ enum MacLocalASRPreferences {
 }
 
 enum MacLocalASRService {
-    /// Transcribe using the user's preferred local backend with automatic
-    /// fallback to Apple Speech when Qwen3 weights are not present.
-    static func transcribe(samples: [Float], locale: Locale) async throws -> String {
-        let preferQwen3 = MacLocalASRPreferences.backend == .qwen3MLX
-        if preferQwen3, MacLocalASRPreferences.qwen3ModelIsInstalled() {
+
+    static func loadCatalog() -> LocalASRCatalogDocument? {
+        try? LocalASRModelCatalog.loadBundled()
+    }
+
+    static func selectedModelDefinition() -> LocalASRModelDefinition? {
+        guard let catalog = loadCatalog() else { return nil }
+        let manifest = LocalASRInstalledManifestIO.load(defaultModelId: catalog.defaultModelId)
+        let selectedId = manifest.selectedModelId.isEmpty
+            ? MacLocalASRPreferences.selectedModelId
+            : manifest.selectedModelId
+        if selectedId == "apple-speech-fallback" { return nil }
+        return LocalASRModelCatalog.model(selectedId, in: catalog)
+            ?? LocalASRModelCatalog.model(catalog.defaultModelId, in: catalog)
+    }
+
+    static func currentCapabilities() -> LocalASRCapabilities {
+        guard let model = selectedModelDefinition() else { return .appleSpeech }
+        return LocalASRModelCatalog.capabilities(for: model)
+    }
+
+    static func currentBackendLabel() -> String {
+        guard let model = selectedModelDefinition() else { return "Apple Speech" }
+        return model.displayName
+    }
+
+    static func isModelInstalled(_ model: LocalASRModelDefinition) -> Bool {
+        LocalASRModelInstallState.isInstalled(
+            model,
+            manualMLXPath: MacLocalASRPreferences.qwen3ModelPath
+        )
+    }
+
+    /// Transcribe using the selected catalog model, with MLX → Apple Speech fallback.
+    static func transcribe(
+        samples: [Float],
+        locale: Locale,
+        bias: LocalASRBiasPayload? = nil
+    ) async throws -> String {
+        if let model = selectedModelDefinition(), isModelInstalled(model) {
             do {
-                return try await MacQwen3LocalASR.transcribe(
-                    samples: samples,
-                    sampleRate: 16_000,
-                    locale: locale,
-                    modelPath: MacLocalASRPreferences.qwen3ModelPath
-                )
-            } catch MacLocalASRError.qwen3ModelMissing {
-                // Fall through to Apple Speech when weights are absent.
+                return try await transcribeWithModel(model, samples: samples, locale: locale, bias: bias)
             } catch {
-                throw error
+                if model.backend != .mlx {
+                    throw error
+                }
             }
         }
+
+        if MacLocalASRPreferences.qwen3ModelIsInstalled() {
+            return try await MacQwen3LocalASR.transcribe(
+                samples: samples,
+                sampleRate: 16_000,
+                locale: locale,
+                modelPath: MacLocalASRPreferences.qwen3ModelPath,
+                bias: bias
+            )
+        }
+
         return try await MacSpeechLocalASR.transcribe(samples: samples, locale: locale)
     }
+
+    private static func transcribeWithModel(
+        _ model: LocalASRModelDefinition,
+        samples: [Float],
+        locale: Locale,
+        bias: LocalASRBiasPayload?
+    ) async throws -> String {
+        switch model.backend {
+        case .mlx:
+            return try await MacQwen3LocalASR.transcribe(
+                samples: samples,
+                sampleRate: 16_000,
+                locale: locale,
+                modelPath: MacLocalASRPreferences.qwen3ModelPath,
+                bias: bias
+            )
+        case .sherpaQwen3, .sherpaSenseVoice:
+            return try await MacSherpaLocalASR.transcribe(
+                samples: samples,
+                sampleRate: 16_000,
+                locale: locale,
+                model: model,
+                bias: bias
+            )
+        case .appleSpeech:
+            return try await MacSpeechLocalASR.transcribe(samples: samples, locale: locale)
+        }
+    }
 }