Files
OSGKeyboard/OSGKeyboardShared/Services/LLMClient.swift
T
Rocky bec36befa2 feat: comprehensive rewrite — push-to-talk pipeline, Typeless UI, Chinese
This is a major rewrite of OpenLessKeyboard, renamed to OSGKeyboard
and rebuilt end-to-end. 59 files changed (+3205/-1550).

Architecture
------------
- Rename project, targets, directories from OpenLess* to OSGKeyboard*
  (OpenLess / OpenLessKeyboard / OpenLessShared / OpenLessTests).
- AudioCaptureService rewritten as @unchecked Sendable class with
  OSAllocatedUnfairLock instead of an actor, so it survives Swift 6
  strict-concurrency checks while still serialising engine + converter
  state correctly.
- Single design system (Palette / Spacing / Radius / TypeStyle /
  Motion) lifted into OSGKeyboardShared so the host app and the
  keyboard extension stay in lock-step.

Push-to-talk — first-principles fix
-----------------------------------
- App Group + audio-input entitlements were stripped by Xcode's
  Automatic Signing. They are now declared in project.yml so
  'xcodegen generate' re-emits them every time. iOS Developer
  Account is untouched; only the App Group capability was added.
- State machine uses a real stored `phase` (was a derived shim
  that locked out every press after the first because
  recordStream was never nilled after the pipeline finished).
- Microphone permission is requested inside pressBegan (async
  Task) so the press flow optimistically enters .recording;
  permission denial surfaces a short error and returns to idle.
- Replaced LongPressGesture(0.15s) with a DragGesture +
  TapGesture pair separated by pressArmed, so a single tap no
  longer fires both onPressBegan and onTap simultaneously.
- Real RMS / peak level meter from the AVAudioEngine tap (was a
  pseudo-random walk); the visible waveform is now driven by
  actual audio.
- SFSpeechRecognizer(locale:) with selectable ASR locales
  (auto / zh-Hans / zh-Hant / en-US / ja-JP / ko-KR) for
  first-class Chinese / English / Japanese / Korean dictation,
  with on-device recognition when supported.
- AVAudioSession now deactivates on stop so other apps' audio
  routing is restored.

Keyboard UI — Typeless-inspired layout
---------------------------------------
- Hero area is 280 pt with a 96 pt record disc, breathing outer
  ring, and a 12-bar waveform driven by the real RMS.
- inputView.allowsSelfSizing + a heightAnchor constraint so iOS
  no longer crops the keyboard under the Spotlight bar / home
  indicator.
- Top bar: mode chip (Off / 转写 / 润色) + locale chip
  (Auto / 简体 / 繁體 / EN / 日 / 한) + status badge + ⚙.
- Bottom bar: globe / delete / 空格 / return — all 40 pt and
  balanced.
- RecordButton onPressEnded is now safe to fire from a quick
  press; pressArmed prevents double-firing.

LLM / Polishing
---------------
- LLMClient: stopped leaking the server response body in errors
  (server body is now logged at debug, never surfaced to UI);
  added a dedicated .rateLimited case for 429.
- PolishingService timeout 8s → 12s to accommodate slower
  domestic LLM providers.
- AppGroupStore.defaultSystemPrompt is now provider-aware
  (Chinese for zhipu/moonshot/qwen/deepseek, English otherwise).

Onboarding & Settings
---------------------
- Re-themed OnboardingView / HomeView / SettingsView on the
  new design system.
- ProviderPickerSection now shows 6 providers (OpenAI, DeepSeek,
  Qwen DashScope, 智谱 GLM, 月之暗面 Moonshot, Custom) with
  blurb + selected accent.
- PickerRow for Mode and ASR locale; System Prompt editor with
  reset-to-default.
- API settings page "Get an API key" used SwiftUI Link, which
  has a hit-test bug on iOS 18 that ate gestures from adjacent
  TextFields (manifested as "typing jumps to a website"). It is
  now an explicit Button + contentShape + .submitLabel(.done) on
  the fields.

Polish & tests
--------------
- LLMClientTests: 4 unit tests passing (ProviderConfig
  persistence + OpenAI request/response + HTTP error + missing
  key); test App Group renamed to the correct identifier.
- ProviderConfig.apply now captures the previous provider id
  *before* mutating, so switching providers actually resets the
  system prompt to the new default.

Build
-----
- Swift 6 strict concurrency, iOS 18.0 deployment target.
- Tested on Xcode 26 + iPhone 17 Pro simulator. A real device on
  iOS 27 beta aborts with __abort_with_payload (dispatch
  library ABI mismatch); use an iOS 18 real device or the
  iOS 26 simulator for now.

🤖 Generated with Claude Code
2026-06-18 01:22:12 +08:00

126 lines
4.2 KiB
Swift

// LLMClient.swift
// OSGKeyboard · Shared
//
// Protocol-based LLM client. Default implementation is the OpenAI-compatible
// chat completion client. Add other impls (Anthropic, Gemini) as needed.
import Foundation
public enum LLMError: Error, LocalizedError, Sendable {
case invalidURL
case noAPIKey
case http(status: Int)
case decoding(String)
case transport(String)
case cancelled
case rateLimited
public var errorDescription: String? {
switch self {
case .invalidURL: return "API 地址无效。请在设置中检查 Base URL。"
case .noAPIKey: return "未填写 API Key。"
case .http(let s): return "API 返回 HTTP \(s)。请稍后重试或联系服务方。"
case .decoding: return "解析 API 响应失败。"
case .transport: return "网络错误,请检查连接后重试。"
case .rateLimited: return "API 调用过于频繁,请稍候再试。"
case .cancelled: return "请求已取消。"
}
}
}
public protocol LLMClient: Sendable {
func polish(_ text: String, systemPrompt: String) async throws -> String
}
// MARK: - OpenAI-compatible implementation
public struct OpenAICompatibleClient: LLMClient {
public let baseURL: String
public let apiKey: String
public let model: String
public let session: URLSession
public init(
baseURL: String,
apiKey: String,
model: String,
session: URLSession = .shared
) {
self.baseURL = baseURL
self.apiKey = apiKey
self.model = model
self.session = session
}
public func polish(_ text: String, systemPrompt: String) async throws -> String {
guard !apiKey.isEmpty else { throw LLMError.noAPIKey }
let urlString = baseURL.hasSuffix("/")
? "\(baseURL)chat/completions"
: "\(baseURL)/chat/completions"
guard let url = URL(string: urlString) else { throw LLMError.invalidURL }
let request = LLMRequest(
model: model,
messages: [
.system(systemPrompt),
.user(text)
],
temperature: 0.3,
maxTokens: nil
)
var req = URLRequest(url: url)
req.httpMethod = "POST"
req.setValue("application/json", forHTTPHeaderField: "Content-Type")
req.setValue("Bearer \(apiKey)", forHTTPHeaderField: "Authorization")
req.timeoutInterval = 15
let encoder = JSONEncoder()
req.httpBody = try encoder.encode(request)
do {
let (data, response) = try await session.data(for: req)
guard let http = response as? HTTPURLResponse else {
throw LLMError.transport("non-HTTP response")
}
if !(200..<300).contains(http.statusCode) {
#if DEBUG
// Log full body for debugging — never expose to UI.
let body = String(data: data, encoding: .utf8) ?? ""
print("⚠️ LLM HTTP \(http.statusCode): \(body.prefix(500))")
#endif
if http.statusCode == 429 { throw LLMError.rateLimited }
throw LLMError.http(status: http.statusCode)
}
do {
let decoded = try JSONDecoder().decode(LLMResponse.self, from: data)
return decoded.content.trimmingCharacters(in: .whitespacesAndNewlines)
} catch {
throw LLMError.decoding(String(describing: error))
}
} catch let err as LLMError {
throw err
} catch is CancellationError {
throw LLMError.cancelled
} catch let urlError as URLError where urlError.code == .cancelled {
throw LLMError.cancelled
} catch {
throw LLMError.transport(String(describing: error))
}
}
}
// MARK: - Factory
public enum LLMClientFactory {
/// Build a client from the current `ProviderConfig`.
public static func make(from config: ProviderConfig) -> LLMClient {
OpenAICompatibleClient(
baseURL: config.baseURL,
apiKey: config.apiKey,
model: config.model
)
}
}