Files
voice-cat/clients/apple/iOS/VoiceCatiOS/AudioSessionManager.swift
Talon fdcc84fb42 fix(ios): stereo mic + A2DP output, add vc_audio_restart ABI
Diagnosed by comparing against TeamTalk5 (Client/iTeamTalk), which
achieves stereo mic + A2DP output. Five fixes:

1. configureStereoCapture now calls setPreferredInput +
   setInputDataSource (mirroring TeamTalk5's SoundDevicesModel).
   Previously omitted based on incorrect diagnosis that
   setPreferredInput collapsed A2DP — the real culprit was
   setPreferredInputNumberOfChannels(2), which neither project uses.

2. New C ABI: vc_audio_restart (full stop + re-init, unlike
   suspend/resume which only stop/start). Swift wrapper added.
   The withAudioSuspend wrapper that used it was removed after
   on-device testing showed it killed all audio (including
   VoiceOver) when switching presets — the core's
   set_capture_channels handles engine restart internally.

3. Bluetooth options: Voice Chat preset now includes BOTH
   .allowBluetoothHFP AND .allowBluetoothA2DP (matching TeamTalk5's
   UtilSound.swift:228). Previously HFP-only blocked A2DP headphones.

4. Capture channels now reset when switching stereo→mono via
   selectCaptureChannels/applyPreset. AudioSessionManager tracks
   activeMicStreamId (set by SessionState on join/leave voice).

5. Docs synced: voice.md, tech-stack.md, architecture.md,
   PROGRESS.md. Removed stale setPreferredInputNumberOfChannels(2)
   references.

Verified: ctest --preset dev 21/21 green, iOS client builds.
Stereo mic + A2DP output still needs on-device debugging — the
core recipe is correct but iOS 26 route behavior requires
hands-on testing with a debugger.
2026-06-19 16:58:21 +02:00

155 lines
7.4 KiB
Swift

import AVFoundation
import os
import VoiceCatCore
private let logger = Logger(subsystem: "cat.voice.VoiceCatiOS", category: "AudioSessionManager")
@MainActor
final class AudioSessionManager {
static let shared = AudioSessionManager()
weak var client: VoiceCatClient?
/// The stream ID of the currently active local MIC stream, if any. Set by `SessionState`
/// when the user joins/leaves voice so `IOSAudioRouter` can reset the core's capture
/// channel count (e.g. when switching stereo mono) without going through `SessionState`.
var activeMicStreamId: UInt32?
/// Tracks whether WE activated the session. The session must be active whenever the
/// AudioEngine is running (for capture OR playback). Previously, the session was only
/// activated when the user joined voice (startMicStream), which meant:
/// - Remote audio was silent if the user hadn't joined voice yet.
/// - Leaving voice (stopMicStream) deactivated the session, killing remote audio.
/// Now the session is activated when any audio needs to play (remote stream started OR
/// user joins voice) and only deactivated when disconnecting from the server.
private var isSessionActive = false
func configure() {
// Load stored audio routing preferences and apply them before any audio session
// activation. IOSAudioRouter drives all iOS audio route selection via AVAudioSession;
// miniaudio (the core) does NOT touch AVAudioSession on iOS.
IOSAudioRouter.shared.loadStoredPreferences()
IOSAudioRouter.shared.applyConfiguration()
IOSAudioRouter.shared.refreshRoutes()
NotificationCenter.default.addObserver(
self, selector: #selector(handleInterruption),
name: AVAudioSession.interruptionNotification, object: nil)
NotificationCenter.default.addObserver(
self, selector: #selector(handleRouteChange),
name: AVAudioSession.routeChangeNotification, object: nil)
}
/// Activate the AVAudioSession if not already active. Call before any audio I/O:
/// when the user joins voice, or when a remote stream starts (so playback works even
/// before the user has joined voice). Idempotent safe to call multiple times.
func ensureSessionActive() throws {
guard !isSessionActive else {
logger.debug("ensureSessionActive — already active, skipping")
return
}
IOSAudioRouter.shared.applyConfiguration()
let session = AVAudioSession.sharedInstance()
try session.setActive(true, options: [])
isSessionActive = true
// For the A2DP output presets, make sure output isn't pinned to the built-in speaker.
// A2DP routing in .playAndRecord is fragile; clearing any speaker override after the
// session is live nudges iOS to honor the Bluetooth output route.
if IOSAudioRouter.shared.wantsA2dpOutput {
try? session.overrideOutputAudioPort(.none)
}
let route = AVAudioSession.sharedInstance().currentRoute
let outputNames = route.outputs.map { $0.portName }.joined(separator: ", ")
let inputNames = route.inputs.map { $0.portName }.joined(separator: ", ")
logger.info("session activated — outputs: [\(outputNames)], inputs: [\(inputNames)]")
}
/// Deactivate the AVAudioSession. Call ONLY when disconnecting from the server not
/// when leaving voice (the user may still want to hear remote audio).
func deactivateSession() {
guard isSessionActive else {
logger.debug("deactivateSession — not active, skipping")
return
}
try? AVAudioSession.sharedInstance().setActive(false,
options: .notifyOthersOnDeactivation)
isSessionActive = false
logger.info("session deactivated")
}
@objc private func handleInterruption(_ notification: Notification) {
guard let info = notification.userInfo,
let typeValue = info[AVAudioSessionInterruptionTypeKey] as? UInt,
let type = AVAudioSession.InterruptionType(rawValue: typeValue)
else { return }
switch type {
case .began:
logger.info("interruption began — session suspended by system")
isSessionActive = false // system deactivated us
client?.audioSuspend()
case .ended:
let optionsValue = info[AVAudioSessionInterruptionOptionKey] as? UInt ?? 0
let options = AVAudioSession.InterruptionOptions(rawValue: optionsValue)
if options.contains(.shouldResume) {
do {
try AVAudioSession.sharedInstance().setActive(true)
isSessionActive = true
logger.info("interruption ended — session reactivated")
client?.audioResume()
} catch {
logger.error("interruption ended — reactivation failed: \(error.localizedDescription)")
}
}
@unknown default: break
}
}
@objc private func handleRouteChange(_ notification: Notification) {
guard let info = notification.userInfo,
let reasonValue = info[AVAudioSessionRouteChangeReasonKey] as? UInt,
let reason = AVAudioSession.RouteChangeReason(rawValue: reasonValue)
else {
logger.warning("routeChange — unknown reason, refreshing only")
IOSAudioRouter.shared.refreshRoutes()
NotificationCenter.default.post(name: .voiceCatDeviceListChanged, object: nil)
return
}
logger.info("routeChange reason=\(self.reasonLabel(reason))")
// Re-apply preferences ONLY on external device plug/unplug. Do NOT re-apply on
// .categoryChange / .routeConfigurationChange those are triggered by our own
// applyConfiguration() calls (setCategory, setPreferredInput, etc.), and re-applying
// would create an infinite notification loop:
// handleRouteChange applyConfiguration setCategory routeChange ...
// That loop burns CPU and cycles the audio session on/off the "glitching" bug.
// IOSAudioRouter.applyConfiguration() also has a re-entrancy guard for synchronous
// notifications, but the reason check here is the primary defense.
if reason == .oldDeviceUnavailable || reason == .newDeviceAvailable {
logger.info("routeChange — external device change, re-applying config")
IOSAudioRouter.shared.applyConfiguration()
}
IOSAudioRouter.shared.refreshRoutes()
NotificationCenter.default.post(name: .voiceCatDeviceListChanged, object: nil)
}
private func reasonLabel(_ reason: AVAudioSession.RouteChangeReason) -> String {
switch reason {
case .oldDeviceUnavailable: return "oldDeviceUnavailable"
case .newDeviceAvailable: return "newDeviceAvailable"
case .categoryChange: return "categoryChange"
case .override: return "override"
case .wakeFromSleep: return "wakeFromSleep"
case .noSuitableRouteForCategory: return "noSuitableRouteForCategory"
case .routeConfigurationChange: return "routeConfigurationChange"
@unknown default: return "unknown"
}
}
}
extension Notification.Name {
static let voiceCatDeviceListChanged = Notification.Name("cat.voice.deviceListChanged")
}