refactor: drop Qwen3 CoreML ASR, add local-engine cloud polish toggle

Rolls back the v0.2.0 Qwen3 CoreML on-device ASR stack and replaces the
'local engine' UX with iOS 26 SpeechAnalyzer + DictationTranscriber only.

The 'Cloud polish after ASR' toggle (ProviderConfig.localModeCloudPolishEnabled)
lets users opt into a post-ASR DeepSeek round-trip from the local engine.
Defaults to off so the local engine stays genuinely local. New PolishError.missingAPIError
surfaces an inline 'fill in your key' warning when the toggle is on but the
Keychain is empty. DeepSeek preset default model bumped to deepseek-v4-flash.

Deleted:
  - OSGKeyboard/ThirdParty/Qwen3Speech/ (74 files, ~16k LoC)
  - OSGKeyboard/Services/ModelManager.swift (492)
  - OSGKeyboard/Services/OnDeviceModelWarmup.swift (197)
  - OSGKeyboard/Services/Qwen3ASRService.swift (257)
  - OSGKeyboard/Services/ModelDownloadSourcePicker.swift (126)
  - OSGKeyboard/Views/OnDeviceModelsView.swift (184)
  - OSGKeyboard/Views/DownloadConfirmSheet.swift (96)
  - OSGKeyboardShared/Models/OnDeviceModel.swift (140)
  - OSGKeyboardShared/Services/OnDeviceModelStatus.swift (104)
  - Qwen3ASRServiceProvider registration in OSGKeyboardApp
  - Qwen3Speech package declaration in project.yml
  - 5 .qwen3ASR enum / branch reference sites in HomeView, OnboardingView,
    LocalEngineSettingsRows, FlowSessionManager, ASRService, EngineServiceLabel
  - Two pre-existing Swift 6 strict-concurrency errors in
    LiveDictationController + FlowSessionManager (the weak [weak self] in
    detached-task MainActor.run blocks) that were blocking clean builds

Added:
  - LocalModelsGroup: 'Built-in iOS SpeechAnalyzer' badge + 'Cloud polish
    after ASR' Switch toggle
  - PolishingService: honour localModeCloudPolishEnabled; new .missingAPIKey
    error case with localised warning
  - AppGroupStore.localModeCloudPolishEnabled (mirrored into App Group
    so the keyboard extension honours the toggle during live dictation)
  - SettingsView: show provider/api sections when local-mode cloud polish
    is on so the user can paste a DeepSeek key
  - FlowSessionManager: route through PolishingService for local + polish-on
    flow; translate missingAPIKey into a polished warning
  - KeyboardViewController: handle PolishingService.PolishError.missingAPIKey
    in the keyboard-side live polish path
  - CHANGELOG v0.2.1: documents the rollback + new toggle
  - README.md / README.zh.md: engine matrix section, data flow note

Verified: xcodebuild -scheme OSGKeyboard -destination 'generic/platform=iOS Simulator'
build succeeds under SWIFT_STRICT_CONCURRENCY=complete.

README.zh.md

@@ -28,6 +28,7 @@ OSGKeyboard 是商业语音输入工具的免费、源码可见替代方案。
 - 🎙 **按住说话**，Typeless 风格的圆形麦克风按钮
 - 🧠 **端侧 ASR**（iOS 26+ `SpeechAnalyzer` + `DictationTranscriber`）
 - ✍️ **AI 润色** —— 自动加结构、补标点、修正语法、可生成列表
+- 🧩 **本地 + 云端润色开关** —— 本地模式默认仅在设备上识别；若 iOS 语音识别效果不理想(远场、噪声、方言)，可开启「识别后云端润色」，默认走 DeepSeek
 - 🔌 **自带 API 接入** —— 兼容任何 OpenAI 兼容协议端点（OpenAI / DeepSeek / Qwen DashScope / 自建服务器 ……）
 - 🔒 **隐私优先** —— 音频不离开设备；只有润色文本会发给你选择的 LLM
 - 🎨 **原生 SwiftUI** —— 暗色主题、毛玻璃、约 2000 行 Swift
@@ -107,6 +108,12 @@ OSGKeyboard/
                    textDocumentProxy.insertText(润色后文本)
 ```
 
+**引擎模式：**
+
+- `cloud`（默认）：本地 `SpeechAnalyzer` 识别，文本发到云端 LLM 润色。
+- `local`：本地 `SpeechAnalyzer` 识别，原始文本直接插入，不联网。
+- `local` + 「识别后云端润色」开关（设置 → 本地模型）：与 `cloud` 类似，但使用本地引擎流程，识别完成后送 LLM 润色后再插入。需在 Keychain 中提前填好 DeepSeek（或任意 OpenAI 兼容提供方）API Key。
+
 ---
 
 ## 新增 LLM 提供商