Files
voice-cat/clients/apple/iOS/VoiceCatiOS/AppState.swift
Talon b14cf2a4e8
Some checks failed
Build Linux Binaries / linux/amd64 (push) Has been cancelled
Build Linux Binaries / linux/arm64 (push) Has been cancelled
fix(ios): stop core opening a second mic device — dual capture/crackle
On iOS the remote end heard the mic twice and crackly (BT headset + internal
mic in Voice Chat; mono + stereo copies of the internal mic in Stereo Mic).

Root cause is an io-thread ordering race. `ensure_audio_running()` only set
`external_capture` when a MIC stream already existed, but it also runs from
`sync_remote_streams` on the post-auth `ServerStateSnapshot` — before the user
joins voice. With `external_playback_` still false and no MIC stream,
`AudioEngine::start()` opened a real miniaudio capture device that stayed open
all session (later calls early-return on running()), racing the AVAudioEngine
input tap fed via `vc_stream_feed_pcm`. `on_capture_frame` then encoded+sent
both paths — the mic transmitted twice, the two unsynchronized capture clocks
producing the crackle.

- core (ensure_audio_running): force `external_capture = true` whenever
  `external_playback_` is set, so iOS unified mode never opens a hardware
  capture device. No-op on desktop.
- ios (AppState): move `setExternalPlayback(true)` before `connect()`, so the
  flag is set before the io thread processes any message — closing the race.

Verified on device: remote end hears the iOS mic once and clean in both Voice
Chat (+ BT) and Stereo Mic.
2026-06-23 17:47:49 +02:00

202 lines
7.7 KiB
Swift

import Foundation
import VoiceCatCore
struct PendingIdentity: Identifiable {
let id = UUID()
let displayText: String
let tofuStatus: VoiceCatTofuStatus
}
@Observable
@MainActor
final class AppState {
var servers: [SavedServer] = ServerListStore.shared.load()
var session: SessionState?
// Connect-flow state
var isConnecting = false
var connectStatus = ""
var showAddServer = false
var editingServer: SavedServer?
var showPasswordPrompt = false
var pendingIdentity: PendingIdentity?
private var connectingClient: VoiceCatClient?
private(set) var connectingServer: SavedServer?
private var identityHandled = false
// MARK: - Server list management
func addServer(_ server: SavedServer, password: String?) {
if let pw = password, !pw.isEmpty {
ServerListStore.shared.savePassword(pw, tag: server.keychainTag)
}
servers.append(server)
ServerListStore.shared.save(servers)
}
func updateServer(_ server: SavedServer, password: String?) {
if let pw = password, !pw.isEmpty {
ServerListStore.shared.savePassword(pw, tag: server.keychainTag)
}
if let idx = servers.firstIndex(where: { $0.id == server.id }) {
servers[idx] = server
}
ServerListStore.shared.save(servers)
}
func removeServer(_ server: SavedServer) {
ServerListStore.shared.deletePassword(tag: server.keychainTag)
servers.removeAll(where: { $0.id == server.id })
ServerListStore.shared.save(servers)
}
// MARK: - Connect flow
func connectTo(_ server: SavedServer) {
guard !isConnecting else { return }
isConnecting = true
connectStatus = "Connecting…"
connectingServer = server
identityHandled = false
let config = VoiceCatConfig(
clientName: "VoiceCat-iOS",
clientVersion: "0.0.1",
logLevel: .info,
tofuStorePath: ServerListStore.shared.tofuStorePath)
let client = VoiceCatClient(config: config)
connectingClient = client
client.onEvent = { [weak self] ev in
Task { @MainActor [weak self] in self?.handleConnectEvent(ev, server: server) }
}
// Put the core into external-playback mode BEFORE connect, so the flag is set on the
// io thread before any message is processed. The server sends AuthResult immediately
// followed by ServerStateSnapshot; handle_server_state runs ensure_audio_running() on
// the io thread, and if external_playback_ were still false at that point the core
// would open a hardware miniaudio playback+capture device (see the matching fix in
// vc_client::ensure_audio_running). Setting it here before connect guarantees the
// unified external path is in effect from the first frame. setExternalPlayback only
// flips an atomic + forwards to the engine's setter; both are safe pre-connect.
client.setExternalPlayback(true)
client.connect(host: server.host, port: server.port)
// Auth is queued immediately the core serialises it behind TLS + TOFU.
switch server.authMode {
case .guest:
let nick = (server.nickname?.isEmpty == false) ? server.nickname! : "iOS User"
client.authenticateGuest(nick)
case .password:
let savedPw = ServerListStore.shared.loadPassword(tag: server.keychainTag)
if let pw = savedPw, !pw.isEmpty {
client.authenticateUser(server.savedUsername, password: pw)
} else {
showPasswordPrompt = true
}
}
}
func disconnect() {
session?.stopMicStream()
session?.client.disconnect()
IOSAudioEngine.shared.stop()
AudioSessionManager.shared.deactivateSession()
session = nil
connectingClient?.disconnect()
connectingClient = nil
connectingServer = nil
isConnecting = false
connectStatus = ""
showPasswordPrompt = false
pendingIdentity = nil
}
// MARK: - Auth actions (called from prompt sheets)
func authenticateUser(username: String, password: String) {
connectingClient?.authenticateUser(username, password: password)
showPasswordPrompt = false
}
func confirmServerIdentity(accept: Bool) {
connectingClient?.confirmServerIdentity(accept: accept)
pendingIdentity = nil
if !accept { cancelConnect() }
}
func cancelConnect() {
connectingClient?.disconnect()
connectingClient = nil
connectingServer = nil
isConnecting = false
connectStatus = ""
showPasswordPrompt = false
pendingIdentity = nil
}
// MARK: - Connect event handler
private func handleConnectEvent(_ ev: VoiceCatEvent, server: SavedServer) {
switch ev.type {
case .connectionState:
switch ev.connectionState {
case .connecting: connectStatus = "Connecting…"
case .tlsHandshake: connectStatus = "TLS handshake…"
case .authenticating: connectStatus = "Authenticating…"
case .verifyingIdentity: connectStatus = "Verifying server identity…"
case .connected: connectStatus = "Connected"
default: break
}
case .serverIdentity:
guard !identityHandled else { break }
let tofuStatus = ev.tofuStatus ?? .firstConnect
if tofuStatus == .matched {
connectingClient?.confirmServerIdentity(accept: true)
} else {
identityHandled = true
let displayText = connectingClient?.getServerIdentityDisplay() ?? ""
pendingIdentity = PendingIdentity(displayText: displayText, tofuStatus: tofuStatus)
}
case .authResult:
if ev.result == .ok {
guard let client = connectingClient else { break }
let perms = client.getPermissions()
let newSession = SessionState(client: client, selfUserId: ev.userId, permissions: perms)
connectingClient = nil
isConnecting = false
connectStatus = ""
showPasswordPrompt = false
self.session = newSession
EventFeedback.shared.play(.login)
EventFeedback.shared.speak("Connected")
// External-playback mode was enabled before connect() so the core never opens a
// miniaudio device on iOS (the single ordering rule of the unified audio path).
// Now activate the session and start the engine in listening mode so remote audio
// plays the moment someone talks, even before we join voice (no "can't hear anyone").
do {
try AudioSessionManager.shared.ensureSessionActive()
} catch {
print("Audio session activate on connect failed: \(error)")
}
IOSAudioEngine.shared.startListening(client: client)
} else {
connectStatus = "Auth failed: \(ev.result.description)"
showPasswordPrompt = true
}
case .disconnected:
if session == nil { cancelConnect() }
else {
IOSAudioEngine.shared.stop()
AudioSessionManager.shared.deactivateSession()
session = nil; isConnecting = false
}
case .error:
connectStatus = ev.text ?? "Unknown error"
if session == nil { isConnecting = false }
default:
break
}
}
}