Files
voice-cat/clients/apple/iOS/VoiceCatiOS/AudioSessionManager.swift
Talon fb73b694d0
Some checks failed
Build Linux Binaries / linux/amd64 (push) Has been cancelled
Build Linux Binaries / linux/arm64 (push) Has been cancelled
fix(ios): VPIO silent playback + quiet speaker in stereo/studio presets
Two on-device bugs in the native iOS Voice-Processing path (Swift-only;
no core/ABI change).

1. Voice Chat (VPIO) silent playback: doStartMicStream() called
   audioRestart() BEFORE startStream, so when the engine was already
   running (a remote stream had started it) it reopened with
   external_capture=false and opened a hardware miniaudio capture device.
   The announce-result restart then early-returns (engine already running)
   so that device was never dropped and fought the AVAudioEngine VPIO unit,
   silencing playback. Now: setExternalPlayback first, then startStream
   (stores external_feed synchronously), THEN audioRestart() — the core
   reopens in full external mode (no hardware devices). Added VPIO
   diagnostics: graph/route formats at start, ring written/read totals at
   teardown.

2. Stereo Mic / Studio quiet earpiece: the .builtInMicBtA2dp presets omit
   .defaultToSpeaker (it breaks A2DP) and skip forceSpeaker, so with no
   Bluetooth connected output pinned to the quiet receiver. New
   IOSAudioRouter.applyA2dpSpeakerFallback() overrides to the built-in
   speaker when no external (A2DP/wired/AirPlay) output is present and
   clears the override when one is — called after activation and on
   device-change route changes.
2026-06-22 03:43:00 +02:00

190 lines
9.5 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?
/// Set by `SessionState`. Invoked by `IOSAudioRouter` after an audio-config change so the
/// voice path (native VPIO vs the core's miniaudio path) can be restarted to match the new
/// preset/route when the mic is active. No-op when not in voice. See
/// `SessionState.reconcileVoicePath()` and `IOSVoiceProcessingEngine`.
var reconcileVoicePath: (() -> Void)?
/// Tracks whether WE activated the session. The session must be active whenever the
/// AudioEngine is running (for capture OR playback), so it is activated when any audio
/// needs to play (a remote stream started OR the user joins voice) and only deactivated
/// when disconnecting from the server not when leaving voice, since the user may still
/// want to hear remote audio.
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, pick the right output once the session is live: defer to
// a connected A2DP/wired/AirPlay route, but fall back to the loud built-in speaker (not
// the quiet earpiece) when nothing external is connected. See applyA2dpSpeakerFallback().
IOSAudioRouter.shared.applyA2dpSpeakerFallback()
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)]")
logSessionState("after activate")
}
/// 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")
}
/// Log the full AVAudioSession state category, mode, options, and active route.
/// Useful for diagnosing routing issues, e.g. confirming the session stays
/// `PlayAndRecord` with `allowBluetoothA2DP` and keeps the A2DP output route even
/// after the mic engine starts.
func logSessionState(_ when: String) {
let s = AVAudioSession.sharedInstance()
var opts: [String] = []
let o = s.categoryOptions
if o.contains(.mixWithOthers) { opts.append("mixWithOthers") }
if o.contains(.duckOthers) { opts.append("duckOthers") }
if o.contains(.allowBluetoothHFP) { opts.append("allowBluetoothHFP") }
if o.contains(.allowBluetoothA2DP) { opts.append("allowBluetoothA2DP") }
if o.contains(.allowAirPlay) { opts.append("allowAirPlay") }
if o.contains(.defaultToSpeaker) { opts.append("defaultToSpeaker") }
let outs = s.currentRoute.outputs.map { "\($0.portName)[\($0.portType.rawValue)]" }
.joined(separator: ", ")
let ins = s.currentRoute.inputs.map { "\($0.portName)[\($0.portType.rawValue)]" }
.joined(separator: ", ")
logger.info("""
[SESSION @ \(when, privacy: .public)] category=\(s.category.rawValue, privacy: .public) \
mode=\(s.mode.rawValue, privacy: .public) options=[\(opts.joined(separator: ","), privacy: .public)] \
inputs=[\(ins, privacy: .public)] outputs=[\(outs, privacy: .public)] \
inputCh=\(s.inputNumberOfChannels) outputCh=\(s.outputNumberOfChannels)
""")
}
@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()
// Re-evaluate the A2DP-mode speaker fallback: a Bluetooth unplug should drop us onto
// the loud speaker (not the earpiece), and a replug should hand output back to A2DP.
if isSessionActive {
IOSAudioRouter.shared.applyA2dpSpeakerFallback()
}
}
IOSAudioRouter.shared.refreshRoutes()
NotificationCenter.default.post(name: .voiceCatDeviceListChanged, object: nil)
logSessionState("route change (\(reasonLabel(reason)))")
}
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")
}