Files
voice-cat/clients/apple/iOS/VoiceCatiOS/SessionState.swift
Talon dcb7e6eeca fix(ios): fix stereo mic + A2DP output silence
Three coordinated fixes for the bug where enabling stereo mic capture
caused all audio output (A2DP, speaker, wired) to go silent:

1. audio_engine.cpp — open playback before capture
   On iOS, starting the stereo capture AudioUnit can trigger an audio
   route reconfiguration that drops A2DP before the playback device has
   a chance to claim the route. Opening and starting the playback device
   first commits the output route (A2DP), so iOS is less likely to drop
   it when stereo capture activates afterward.

2. client.cpp — decouple set_capture_channels from engine restart
   Previously vc_set_capture_channels() stopped and restarted the engine
   immediately, which opened capture first (old ordering) and raced
   against the settling AVAudioSession route. Now it only stores the
   channel count; the caller (Swift via vc_audio_restart) controls when
   the engine restarts, after the route has settled.

3. IOSAudioRouter.swift — call audioRestart() after channel config
   selectCaptureChannels() and applyPreset() now call audioRestart()
   after applyConfiguration() + setCaptureChannels(). This is the
   vc_audio_restart() path that was added to the ABI in fdcc84f but
   never wired up in the Swift layer. The restart sees the stored
   channel count and reopens devices in the correct order (playback
   first, capture second).

The doStartMicStream path is unaffected: setCaptureChannels is called
before the server acknowledges the stream (engine not yet running), so
ensure_audio_running() picks up capture_channels=2 directly when the
stream is confirmed and opens with the right count from the start.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-19 17:39:23 +02:00

314 lines
11 KiB
Swift

import Foundation
import AVFoundation
import VoiceCatCore
// MARK: - Helper types
struct ChatMessage: Identifiable {
let id = UUID()
let timestamp: Date
let senderName: String
let text: String
let scope: VoiceCatTextScope
}
struct ActivityEntry: Identifiable {
let id = UUID()
let timestamp: Date
let text: String
}
struct VoiceState {
var micActive = false
var selfMuted = false
var selfDeafened = false
var serverMuted = false
var serverDeafened = false
var inputMode: VoiceCatInputMode = .voiceActivation
var vadThreshold: Float = 0.025
var level: Float = 0.0
var currentDeviceId: String?
var localStreamId: UInt32 = 0
}
// MARK: - SessionState
@Observable
@MainActor
final class SessionState {
let client: VoiceCatClient
let selfUserId: UInt32
var channels: [Channel] = []
var users: [User] = []
var currentChannelId: UInt32 = 0
var messages: [ChatMessage] = []
var activityLog: [ActivityEntry] = []
var voiceState = VoiceState()
var permissions: Permissions
var accounts: [Account] = []
var devices: [Device] = []
init(client: VoiceCatClient, selfUserId: UInt32, permissions: Permissions) {
self.client = client
self.selfUserId = selfUserId
self.permissions = permissions
AudioSessionManager.shared.client = client
refreshChannels()
refreshUsers()
syncSelfChannel()
refreshDevices()
client.onEvent = { [weak self] ev in
Task { @MainActor [weak self] in self?.handleEvent(ev) }
}
client.onLevel = { [weak self] _, rms in
Task { @MainActor [weak self] in self?.voiceState.level = rms }
}
}
deinit {
MainActor.assumeIsolated {
AudioSessionManager.shared.client = nil
}
}
// MARK: - Event dispatch
func handleEvent(_ ev: VoiceCatEvent) {
switch ev.type {
case .channelList:
refreshChannels()
syncSelfChannel()
case .userJoined, .userLeft:
refreshUsers()
syncSelfChannel()
case .userUpdated:
refreshUsers()
syncSelfChannel()
if let me = users.first(where: { $0.id == selfUserId }) {
applyServerMuteState(muted: me.serverMuted, deafened: me.serverDeafened)
}
case .textMessage:
let sender = users.first(where: { $0.id == ev.userId })?.nickname ?? "Unknown"
messages.append(ChatMessage(
timestamp: Date(timeIntervalSince1970: Double(ev.timestampUnixMs) / 1000),
senderName: sender,
text: ev.text ?? "",
scope: ev.textScope))
case .talkState:
let talking = ev.u32a != 0
let who = users.first(where: { $0.id == ev.userId })?.nickname ?? "user \(ev.userId)"
addActivity(talking ? "\(who) started talking" : "\(who) stopped talking")
case .streamStarted:
// A remote user started a stream ensure the audio session is active so we can
// hear them even if we haven't joined voice ourselves. Previously the session was
// only activated when the user pressed Join Voice, so remote audio was silent.
if ev.userId != selfUserId {
do {
try AudioSessionManager.shared.ensureSessionActive()
} catch {
addActivity("Audio session activate failed: \(error)")
}
}
addActivity("Stream started (user \(ev.userId))")
case .streamStopped:
addActivity("Stream stopped (user \(ev.userId))")
case .joinResult:
if ev.result == .ok {
currentChannelId = ev.channelId
addActivity("Joined channel")
refreshUsers()
} else {
addActivity("Join failed: \(ev.result.description)")
}
case .error:
addActivity("Error: \(ev.text ?? ev.result.description)")
case .genericResult:
if ev.result != .ok {
addActivity("Operation failed: \(ev.result.description)")
}
case .accountList:
accounts = client.listAccounts()
default:
break
}
}
private func addActivity(_ text: String) {
activityLog.append(ActivityEntry(timestamp: Date(), text: text))
if activityLog.count > 500 { activityLog.removeFirst() }
}
// MARK: - Self-channel / server-mute sync
/// Sync currentChannelId from the self user's channelId in the user list. Mirrors macOS
/// MainWindowController.swift:461,491,522. The server auto-places every authed user into
/// the Lobby (channel 1) on connect, but without this sync currentChannelId stays 0 and
/// the mic button (gated on currentChannelId == 0) stays permanently dimmed.
private func syncSelfChannel() {
if let me = users.first(where: { $0.id == selfUserId }) {
currentChannelId = me.channelId
}
}
/// Apply server-side mute/deafen state mirrors macOS MainWindowController.swift:693-700.
/// iOS was previously ignoring server mute/deafen entirely.
private func applyServerMuteState(muted: Bool, deafened: Bool) {
if muted && !voiceState.serverMuted { addActivity("You have been server-muted") }
if deafened && !voiceState.serverDeafened { addActivity("You have been server-deafened") }
if !muted && voiceState.serverMuted { addActivity("Server mute cleared") }
if !deafened && voiceState.serverDeafened { addActivity("Server deafen cleared") }
voiceState.serverMuted = muted
voiceState.serverDeafened = deafened
}
// MARK: - Data refresh
func refreshChannels() { channels = client.listChannels() }
func refreshUsers() { users = client.listUsers() }
func refreshDevices() { devices = client.listDevices(.input) }
// MARK: - Voice controls
func joinChannel(_ channelId: UInt32, password: String = "") {
client.joinChannel(channelId, password: password.isEmpty ? nil : password)
}
func leaveChannel() {
client.leaveChannel()
currentChannelId = 0
}
func startMicStream() {
AVAudioApplication.requestRecordPermission { [weak self] granted in
DispatchQueue.main.async {
guard let self else { return }
if granted {
self.doStartMicStream()
} else {
self.addActivity("Microphone permission denied — grant in Settings > Privacy > Microphone")
}
}
}
}
private func doStartMicStream() {
do {
try AudioSessionManager.shared.ensureSessionActive()
} catch {
addActivity("AVAudioSession activate failed: \(error)")
return
}
let desc = StreamDescriptor(kind: .mic, deviceId: voiceState.currentDeviceId, label: "Mic")
let (result, streamId) = client.startStream(desc)
if result == .ok {
voiceState.micActive = true
voiceState.localStreamId = streamId
// Publish the active mic stream ID so IOSAudioRouter can reset the core's capture
// channel count when the user switches monostereo (selectCaptureChannels /
// applyPreset). Without this, switching stereomono leaves the LocalStream's
// capture_channels field at 2 and the next engine start still opens stereo.
AudioSessionManager.shared.activeMicStreamId = streamId
// Store the user's capture channel selection before the server acknowledges
// the stream. The engine hasn't started yet at this point (it starts when
// handle_stream_announce_result fires), so vc_set_capture_channels just
// stores the value no restart. ensure_audio_running() picks it up when
// the stream is confirmed and opens the device with the right channel count.
let channels = IOSAudioRouter.shared.captureChannels.channelCount
if channels != 1 {
client.setCaptureChannels(streamId: streamId, channels: channels)
}
} else {
addActivity("Failed to start mic: \(result.description)")
}
}
func stopMicStream() {
if voiceState.localStreamId != 0 {
client.stopStream(voiceState.localStreamId)
voiceState.localStreamId = 0
AudioSessionManager.shared.activeMicStreamId = nil
}
voiceState.micActive = false
voiceState.level = 0
// Do NOT deactivate the AVAudioSession here the user may still want to hear
// remote audio (other people talking). The session is deactivated only when
// disconnecting from the server (see AppState.disconnect / .disconnected event).
}
func setMute(_ muted: Bool, deafened: Bool) {
client.setSelfMute(micMuted: muted, deafened: deafened)
voiceState.selfMuted = muted
voiceState.selfDeafened = deafened
}
func setInputMode(_ mode: VoiceCatInputMode) {
client.setInputMode(mode)
voiceState.inputMode = mode
}
func setVadThreshold(_ threshold: Float) {
client.setVadThreshold(threshold)
voiceState.vadThreshold = threshold
}
func setPushToTalk(_ active: Bool) {
client.setPushToTalk(active)
}
// MARK: - Text
func sendText(_ text: String, scope: VoiceCatTextScope, targetId: UInt32 = 0) {
client.sendText(scope: scope, targetId: targetId, text: text)
}
// MARK: - Admin
func kickUser(_ userId: UInt32, reason: String) {
client.kickUser(userId, reason: reason.isEmpty ? nil : reason)
}
func banUser(_ userId: UInt32, reason: String, expiresUnixMs: UInt64) {
client.banUser(userId, reason: reason.isEmpty ? nil : reason, expiresUnixMs: expiresUnixMs)
}
func moveUser(_ userId: UInt32, toChannel channelId: UInt32) {
client.moveUser(userId, toChannel: channelId)
}
func setPermissions(_ userId: UInt32, perms: Permissions) {
client.setPermission(userId, perms: perms)
}
func setServerMute(_ userId: UInt32, muted: Bool, deafened: Bool) {
client.setServerMute(userId, muted: muted, deafened: deafened)
}
func createChannel(name: String, topic: String) {
let info = ChannelEdit(id: 0, parentId: 0, name: name, topic: topic,
passwordProtected: false, password: nil,
maxUsers: 0, sortOrder: 0, audio: AudioConfig())
client.createChannel(info)
}
func deleteChannel(_ channelId: UInt32) {
client.deleteChannel(channelId)
}
func fetchAccountList() {
client.requestAccountList()
}
func createAccount(username: String, password: String) {
client.createAccount(username, password: password)
}
func deleteAccount(username: String) {
client.deleteAccount(username)
}
func resetPassword(username: String, newPassword: String) {
client.resetPassword(username, newPassword: newPassword)
}
}