feat(voice): add iOS VAD runtime support

This commit is contained in:
Edison Jwa
2026-05-21 20:51:45 +09:00
parent 171baf6e41
commit 6af4ecab0f
73 changed files with 11529 additions and 1249 deletions
+124 -30
View File
@@ -5,6 +5,7 @@ import AVFoundation
@main
@objc class AppDelegate: FlutterAppDelegate, FlutterImplicitEngineDelegate {
private var iosAudioLifecycleChannel: FlutterMethodChannel?
private var iosPlatformChannel: FlutterMethodChannel?
override func application(
_ application: UIApplication,
@@ -134,32 +135,12 @@ import AVFoundation
object: nil
)
// Request microphone access on first launch rather than waiting
// for the user's first voice-channel join. The latter is
// surprising: the user has only tapped "connect to server" and
// suddenly iOS pops the permission prompt because joining a
// text channel happens to trigger audio engine startup. Asking
// up-front matches user expectations for a voice-chat client.
//
// The request is asynchronous and non-blocking. If the user
// denies, voice_join will surface a clearer error later when
// the audio engine fails to open the input device. The
// permission state is cached by iOS so subsequent launches
// skip the prompt.
//
// Deferred ~1 s so iOS finishes initialising the keyboard /
// text-input subsystem before the permission alert appears.
// Firing the alert too early steals focus from the not-yet-
// ready text-input layer, with the symptom that the first tap
// on a TextField does nothing (the second tap works because
// by then iOS has caught up). DispatchQueue.main.asyncAfter
// keeps everything on the main thread; the permission API
// itself must be called there too.
DispatchQueue.main.asyncAfter(deadline: .now() + 1.0) {
AVAudioSession.sharedInstance().requestRecordPermission { granted in
NSLog("chanora_flutter: microphone permission granted=\(granted)")
}
}
NotificationCenter.default.addObserver(
self,
selector: #selector(handleMediaServicesReset(_:)),
name: AVAudioSession.mediaServicesWereResetNotification,
object: nil
)
return super.application(application, didFinishLaunchingWithOptions: launchOptions)
}
@@ -182,7 +163,7 @@ import AVFoundation
// wrong rate, causing pitch + timing artifacts).
logAudioSessionState(context: "setActive")
let s = AVAudioSession.sharedInstance()
let ins = s.currentRoute.inputs.map { "\($0.portType.rawValue)/\($0.portName)" }.joined(separator: ",")
let ins = s.currentRoute.inputs.map { $0.portType.rawValue }.joined(separator: ",")
NSLog(
"chanora_flutter: AVAudioSession actual: " +
"sampleRate=\(s.sampleRate) " +
@@ -221,9 +202,18 @@ import AVFoundation
let outputs = routeDescription.outputs.map { $0.portType.rawValue }.joined(separator: ",")
NSLog("chanora_flutter: route change reason=\(reason.rawValue) outputs=\(outputs)")
if reason == .oldDeviceUnavailable || reason == .newDeviceAvailable {
iosAudioLifecycleChannel?.invokeMethod("handleRouteChange", arguments: nil)
}
// P1: Send the detailed route class to Rust on every route change,
// not just device plug/unplug. This covers:
// - .newDeviceAvailable / .oldDeviceUnavailable (headset plug/unplug)
// - .override (speaker/earpiece toggle)
// - .categoryChange (session category changed)
// - .wakeFromSleep (device woke from sleep)
// - .routeConfigurationChange (BT HFP connect/disconnect)
// The Rust side uses the route class to recompute the processing
// policy (route_policy.rs) and reset AEC delay state if needed.
let routeClass = classifyAudioRoute(routeDescription)
NSLog("chanora_flutter: route class=\(routeClass) reason=\(reason.rawValue)")
iosAudioLifecycleChannel?.invokeMethod("handleRouteChange", arguments: routeClass)
}
@objc private func handleInterruption(_ notification: Notification) {
@@ -249,11 +239,115 @@ import AVFoundation
}
}
@objc private func handleMediaServicesReset(_ notification: Notification) {
NSLog("chanora_flutter: media services reset")
do {
let session = AVAudioSession.sharedInstance()
try session.setCategory(
.playAndRecord,
mode: .default,
options: [.defaultToSpeaker, .allowBluetoothHFP, .allowBluetoothA2DP]
)
try session.setPreferredIOBufferDuration(0.02)
try session.setPreferredSampleRate(48000.0)
try session.setActive(true, options: [])
logAudioSessionState(context: "mediaServicesWereReset")
} catch {
NSLog("chanora_flutter: AVAudioSession media-services reset rebuild failed: \(error)")
}
// P1: After rebuilding the session, send the current route class to
// Rust so it can recompute the processing policy and reset the
// AudioUnit. The Rust side handles this via ios_handle_media_services_reset
// which calls ios_restart_voice_unit.
let routeClass = classifyAudioRoute(AVAudioSession.sharedInstance().currentRoute)
NSLog("chanora_flutter: media services reset complete, route=\(routeClass)")
iosAudioLifecycleChannel?.invokeMethod("handleMediaServicesReset", arguments: routeClass)
}
override func applicationWillResignActive(_ application: UIApplication) {
iosAudioLifecycleChannel?.invokeMethod("handleWillResignActive", arguments: nil)
}
override func applicationDidEnterBackground(_ application: UIApplication) {
iosAudioLifecycleChannel?.invokeMethod("handleDidEnterBackground", arguments: nil)
}
override func applicationWillEnterForeground(_ application: UIApplication) {
iosAudioLifecycleChannel?.invokeMethod("handleWillEnterForeground", arguments: nil)
}
override func applicationWillTerminate(_ application: UIApplication) {
iosAudioLifecycleChannel?.invokeMethod("handleWillTerminate", arguments: nil)
}
func didInitializeImplicitFlutterEngine(_ engineBridge: FlutterImplicitEngineBridge) {
GeneratedPluginRegistrant.register(with: engineBridge.pluginRegistry)
iosAudioLifecycleChannel = FlutterMethodChannel(
name: "chanora/ios_audio_lifecycle",
binaryMessenger: engineBridge.applicationRegistrar.messenger()
)
iosPlatformChannel = FlutterMethodChannel(
name: "chanora/ios_platform",
binaryMessenger: engineBridge.applicationRegistrar.messenger()
)
iosPlatformChannel?.setMethodCallHandler { call, result in
switch call.method {
case "getMicrophonePermissionState":
result(self.microphonePermissionStateString())
case "requestMicrophonePermission":
AVAudioSession.sharedInstance().requestRecordPermission { granted in
DispatchQueue.main.async {
result(granted ? "Granted" : self.microphonePermissionStateString())
}
}
case "openAppSettings":
guard let url = URL(string: UIApplication.openSettingsURLString) else {
result(false)
return
}
UIApplication.shared.open(url, options: [:]) { opened in
result(opened)
}
default:
result(FlutterMethodNotImplemented)
}
}
}
private func classifyAudioRoute(_ route: AVAudioSessionRouteDescription) -> String {
for output in route.outputs {
switch output.portType {
case .builtInReceiver:
return "Earpiece"
case .builtInSpeaker:
return "Speaker"
case .headphones, .usbAudio:
return "WiredHeadset"
case .bluetoothHFP:
return "BluetoothHfp"
case .bluetoothA2DP:
return "BluetoothA2dp"
default:
break
}
}
return "Unknown"
}
private func microphonePermissionStateString() -> String {
switch AVAudioSession.sharedInstance().recordPermission {
case .granted:
return "Granted"
case .denied:
return "Denied"
case .undetermined:
return "NotDetermined"
@unknown default:
return "Unknown"
}
}
deinit {
NotificationCenter.default.removeObserver(self)
}
}
+3 -5
View File
@@ -4,6 +4,9 @@
<dict>
<key>CADisableMinimumFrameDurationOnPhone</key>
<true/>
<!-- Opt into ProMotion / high-refresh-rate CADisplayLink ranges on
supported iPhones. Flutter's iOS embedder reads this key; no
additional Flutter package is required for dynamic refresh. -->
<key>CFBundleDevelopmentRegion</key>
<string>$(DEVELOPMENT_LANGUAGE)</string>
<key>CFBundleDisplayName</key>
@@ -74,11 +77,6 @@
<string>UIInterfaceOrientationLandscapeLeft</string>
<string>UIInterfaceOrientationLandscapeRight</string>
</array>
<!-- Make Chanora's Documents folder visible to the Files.app and
accessible via iTunes / Finder file-sharing. We write
diagnostic logs (chanora.log) into Documents/ so users can
export them for support. Both keys are required for the
"On My iPhone -> Chanora" listing to appear in Files.app. -->
<key>UIFileSharingEnabled</key>
<true/>
<key>LSSupportsOpeningDocumentsInPlace</key>