Files
OSGKeyboard/OSGKeyboardShared/Services/FlowSessionKeys.swift
T
Rocky df1c5ff32c feat: migrate on-device Qwen3 ASR to CoreML for background Flow dictation
Replace MLX GPU inference with CoreML bundles so transcription continues
while the host app is backgrounded. Adds model download and warm-up,
vendored Qwen3Speech, and updates onboarding, settings, and copy for the
~1.6 GB CoreML package (iOS 18+).
2026-06-23 00:46:58 +08:00

58 lines
2.4 KiB
Swift

// FlowSessionKeys.swift
// OSGKeyboard · Shared
//
// App Group keys for TypeWhisper-style Flow sessions between the
// keyboard extension and the host app (Session Owner).
import Foundation
public enum FlowSessionKeys {
public static let flowSessionActive = "flow.flowSessionActive"
public static let flowSessionExpires = "flow.flowSessionExpires"
public static let flowHeartbeat = "flow.flowHeartbeat"
public static let keyboardRecordingState = "flow.keyboardRecordingState"
public static let transcriptionLanguage = "flow.transcriptionLanguage"
public static let transcriptionResult = "flow.transcriptionResult"
/// Soft warning when polish failed but raw transcript was delivered.
public static let transcriptionPolishWarning = "flow.transcriptionPolishWarning"
public static let transcriptionError = "flow.transcriptionError"
public static let audioLevels = "flow.audioLevels"
/// Heartbeat older than this while the host is foreground → likely killed.
public static let heartbeatStaleInterval: TimeInterval = 3
/// Default Flow session length when started from the keyboard.
public static let defaultSessionDuration: TimeInterval = 480
/// Maximum duration for a single keyboard utterance (3 minutes).
public static let maxUtteranceDuration: TimeInterval = 180
/// Host polls for pipelined ASR drain after mic stop. Pipelining usually
/// finishes most chunks during recording; this is a soft deadline before
/// blocking on `asrTask.value` (which waits until the pipeline exits).
public static let localASRWaitTimeout: TimeInterval = 120
public static let localQwen3ASRWaitTimeout: TimeInterval = 180
public static let cloudASRWaitTimeout: TimeInterval = 120
/// Keyboard watchdog after the user stops recording (not utterance max length).
/// Must cover worst-case post-stop backlog: remaining MLX/SpeechAnalyzer chunks
/// plus cloud LLM polish (see `PolishingService.effectiveTimeout` cap).
public static func keyboardResultTimeout(
engineMode: String,
localASRBackend: LocalASRBackend
) -> TimeInterval {
if engineMode == "local" {
return localASRBackend == .qwen3ASR ? 240 : 180
}
return 240
}
public enum RecordingState: String, Sendable, Equatable {
case idle
case recording
case stopped
case processing
case aborted
}
}