Files
voice-cat/clients/apple/iOS/VoiceCatiOS/SessionState.swift
Talon bba605401d
Some checks failed
Build Linux Binaries / linux/amd64 (push) Has been cancelled
Build Linux Binaries / linux/arm64 (push) Has been cancelled
chore: comment cleanup pass ahead of open-sourcing
Removes leftover debug scaffolding (stray Console.WriteLine/NSLog traces,
dead nick_buf_ptr, a no-op --print-config flag now implemented for real),
fixes stale/misleading comments (channel passwords are no longer a "future
M5+" feature, a wrong cross-reference, a stale TlsContext::close() mention,
an incomplete BanRecord::subject_type doc, and a smoke test pointing at a
build/m1-dev preset that no longer exists), strips internal M1-M5 milestone
jargon from comments now that the roadmap is done, trims comments that just
restated the following line, and consolidates a few "why" explanations that
were duplicated 2-3 times in the same file.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-03 10:20:18 +01:00

554 lines
22 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 voiceSubscribed = false
var selfMuted = false
var selfDeafened = false
var serverMuted = false
var serverDeafened = false
var inputMode: VoiceCatInputMode = .voiceActivation
var vadThreshold: Float = 0.025
var inputGain: Float = 1.0
var inputNoiseReduction: Bool = false
var level: Float = 0.0
var currentDeviceId: String?
var localStreamId: UInt32 = 0
var screenSharing = false
var screenStreamId: 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] = []
/// Back-reference to the app state. Once `SessionState.init` overwrites `client.onEvent`,
/// `AppState.handleConnectEvent` no longer receives per-session events so the
/// `.disconnected` event for a LIVE session arrives here in `handleEvent`, not in AppState.
/// This weak ref lets us hand the disconnect back to AppState (which owns the reconnect
/// state machine) so the auto-reconnect fires. Set by AppState on auth success.
weak var appState: AppState?
// MARK: - Reconnect restore state
//
// When the iOS client auto-reconnects after a network drop, AppState captures the prior
// session's channel + voice/mic state and asks the new SessionState (created on auth success)
// to restore it. We rejoin the channel explicitly (the server auto-placed us in Lobby on
// auth), and on the resulting `.joinResult` we re-arm voice subscription + mute/deafen. The
// drive is here, not in AppState, because once SessionState is created it owns
// `client.onEvent` and AppState no longer sees per-session events.
private struct RestoreRequest {
let channelId: UInt32
let voiceSubscribed: Bool
let micMuted: Bool
let deafened: Bool
}
private var pendingRestore: RestoreRequest?
private var didIssueRestoreJoin = false
/// Host side of iOS screen-audio sharing drains the broadcast extension's App Group ring
/// and feeds the SCREEN_AUDIO stream this session owns. See BroadcastAudioPump.
private let broadcastPump = BroadcastAudioPump()
init(client: VoiceCatClient, selfUserId: UInt32, permissions: Permissions) {
self.client = client
self.selfUserId = selfUserId
self.permissions = permissions
loadAndApplyVoiceSettings()
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 }
}
broadcastPump.onBroadcastStarted = { [weak self] in self?.startScreenShare() }
broadcastPump.onBroadcastFinished = { [weak self] in self?.stopScreenShare() }
broadcastPump.start()
}
deinit {
broadcastPump.stop()
}
// MARK: - Event dispatch
func handleEvent(_ ev: VoiceCatEvent) {
switch ev.type {
case .channelList:
refreshChannels()
syncSelfChannel()
case .userJoined:
// ev.text = nickname, ev.channelId = the channel they joined (per voicecat.h).
if ev.userId != selfUserId && ev.channelId == currentChannelId {
EventFeedback.shared.play(.channelJoin)
EventFeedback.shared.speak("\(ev.text ?? "Someone") joined")
}
refreshUsers()
syncSelfChannel()
case .userLeft:
// Capture the leaving user's prior nickname/channel before refreshUsers() drops them.
if ev.userId != selfUserId,
let gone = users.first(where: { $0.id == ev.userId }),
gone.channelId == currentChannelId {
EventFeedback.shared.play(.channelLeave)
EventFeedback.shared.speak("\(gone.nickname) left")
}
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"
let body = ev.text ?? ""
let isSelf = ev.userId == selfUserId
let isPrivate = ev.textScope == .private
messages.append(ChatMessage(
timestamp: Date(timeIntervalSince1970: Double(ev.timestampUnixMs) / 1000),
senderName: sender,
text: body,
scope: ev.textScope))
EventFeedback.shared.play(isPrivate
? (isSelf ? .pmSent : .pmRecv)
: (isSelf ? .channelSent : .channelRecv))
if !isSelf {
EventFeedback.shared.speak(isPrivate
? "Private message from \(sender): \(body)"
: "\(sender): \(body)")
}
case .talkState:
let talking = ev.u32a != 0
if ev.userId == selfUserId {
EventFeedback.shared.play(talking ? .vaStart : .vaStop)
}
let who = users.first(where: { $0.id == ev.userId })?.nickname ?? "user \(ev.userId)"
addActivity(talking ? "\(who) started talking" : "\(who) stopped talking")
case .streamStarted:
// Our own SCREEN_AUDIO stream is live begin draining the broadcast ring into it,
// in the stream's effective channel mode (downmix to mono if the channel is mono).
if ev.userId == selfUserId && ev.streamId == voiceState.screenStreamId {
let sid = voiceState.screenStreamId
let (r, cfg) = client.getStreamAudioConfig(userId: selfUserId, streamId: sid)
let channels: UInt32 = (r == .ok && cfg?.stereo == true) ? 2 : 1
let c = client
broadcastPump.beginFeeding(streamChannels: channels) { pcm, samples, ch in
c.feedPcm(streamId: sid, pcm: pcm, samplesPerChannel: samples, channels: ch)
}
addActivity("Sharing screen audio (\(channels == 2 ? "stereo" : "mono"))")
break
}
if ev.userId != selfUserId {
do {
try AudioSessionManager.shared.ensureSessionActive()
} catch {
addActivity("Audio session activate failed: \(error)")
}
}
AudioSessionManager.shared.logSessionState("stream started (user \(ev.userId))")
addActivity("Stream started (user \(ev.userId))")
case .streamStopped:
if ev.userId == selfUserId {
if ev.streamId == voiceState.localStreamId {
voiceState.localStreamId = 0
voiceState.micActive = false
voiceState.level = 0
}
} else {
addActivity("Stream stopped (user \(ev.userId))")
}
case .voiceState:
let subscribed = ev.u32a != 0
voiceState.voiceSubscribed = subscribed
if subscribed {
doStartMicStream()
} else {
voiceState.micActive = false
voiceState.level = 0
EventFeedback.shared.play(.voiceOff)
}
case .joinResult:
if ev.result == .ok {
currentChannelId = ev.channelId
addActivity("Joined channel")
refreshUsers()
// Reconnect restore: this was our restore-join. Now that the server has
// processed the channel move, re-arm voice subscription (if the user was
// transmitting before the drop) and re-apply the local mute/deafen state.
// The server returns ok even when joining the channel we're already in, so
// this fires reliably for the Lobby-too case.
if didIssueRestoreJoin, let r = pendingRestore, r.channelId == ev.channelId {
didIssueRestoreJoin = false
completeRestore()
}
} else {
addActivity("Join failed: \(ev.result.description)")
// Restore-join failed (channel was deleted, became password-protected or
// full while we were away). Give up on the voice/mute restore cleanly so we
// don't leave dangling state or attempt voice without being in a channel.
if didIssueRestoreJoin {
didIssueRestoreJoin = false
pendingRestore = nil
}
}
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()
case .disconnected:
// Audible cue, then hand the disconnect back to AppState so its reconnect state
// machine fires. This is the ONLY way AppState learns a live session dropped
// after auth success, `SessionState.init` overwrites `client.onEvent`, so
// `AppState.handleConnectEvent` never sees this event. (Without this callback, a
// network drop on a live session would just play the cue and leave the session as a
// zombie the user would have to tap Disconnect manually.)
EventFeedback.shared.play(ev.result == .ok ? .logout : .connectionLost)
EventFeedback.shared.speak(ev.result == .ok ? "Disconnected" : "Connection lost")
appState?.onLiveSessionDisconnected()
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's bootstrap/event-handling sync. 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's handling
/// of UserEvent.UPDATED for the self user.
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 joinVoice() {
AVAudioApplication.requestRecordPermission { [weak self] granted in
DispatchQueue.main.async {
guard let self else { return }
if granted {
let result = self.client.joinVoice()
if result != .ok {
self.addActivity("Failed to join voice: \(result.description)")
}
} 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",
externalFeed: true)
let (result, streamId) = client.startStream(desc)
guard result == .ok else {
addActivity("Failed to start mic: \(result.description)")
return
}
voiceState.micActive = true
voiceState.localStreamId = streamId
EventFeedback.shared.play(.voiceOn)
let channels = IOSAudioRouter.shared.captureChannels.channelCount
if channels != 1 {
client.setCaptureChannels(streamId: streamId, channels: channels)
}
IOSAudioEngine.shared.startMic(streamId: streamId, channels: channels)
}
func leaveVoice() {
if voiceState.screenStreamId != 0 { stopScreenShare() }
client.setPushToTalk(false)
IOSAudioEngine.shared.stopMic()
client.leaveVoice()
}
// MARK: - Reconnect restore
/// Called by `AppState` after a reconnect's auth success to rejoin the prior channel and
/// re-enable the prior voice/mic state. Drives the restore through the `.joinResult` event
/// so we re-arm voice only AFTER the server processed the join joining voice before the
/// channel move would be rejected server-side. `micMuted`/`deafened` are the user's LOCAL
/// mute/deafen state at the moment of the drop; the server resets those on a fresh auth, so
/// we re-push them via `setMute` after the channel is restored.
func requestRestore(channelId: UInt32, voiceSubscribed: Bool,
micMuted: Bool, deafened: Bool) {
pendingRestore = RestoreRequest(channelId: channelId,
voiceSubscribed: voiceSubscribed,
micMuted: micMuted,
deafened: deafened)
didIssueRestoreJoin = false
if channelId != 0 {
// The server auto-placed us in the Lobby on auth; join our prior channel explicitly.
// `vc_join_channel` is idempotent server-side (joining the channel you're already in
// returns ok), so this is safe even if the prior channel was the Lobby.
client.joinChannel(channelId)
didIssueRestoreJoin = true
} else {
// No prior channel go straight to the voice/mute restore. (voiceSubscribed with
// channelId == 0 is contradictory; `completeRestore` further guards on
// currentChannelId != 0 before subscribing to voice.)
completeRestore()
}
}
/// Finish the restore after the channel is in place (or there was no channel to restore):
/// re-subscribe to voice if the user was transmitting, and re-apply the local mute/deafen
/// state. Safe to call once per `pendingRestore`; clears it.
private func completeRestore() {
guard let r = pendingRestore else { return }
if r.voiceSubscribed && currentChannelId != 0 {
joinVoice()
}
setMute(r.micMuted, deafened: r.deafened)
addActivity("Restored to channel \(currentChannelId)"
+ (r.voiceSubscribed ? " with voice" : ""))
pendingRestore = nil
}
// MARK: - Screen audio share
/// Called when the broadcast extension becomes active. Announces the SCREEN_AUDIO stream;
/// feeding begins on the resulting `.streamStarted` event (see handleEvent). The actual
/// system-audio capture happens in the ReplayKit upload extension (a separate process).
private func startScreenShare() {
guard voiceState.screenStreamId == 0 else { return }
guard currentChannelId != 0 else {
addActivity("Screen audio ignored — join a channel first")
return
}
let (result, streamId) = client.startStream(
StreamDescriptor(kind: .screenAudio, deviceId: nil, label: "Screen audio"))
if result == .ok {
voiceState.screenStreamId = streamId
voiceState.screenSharing = true
addActivity("Screen audio share starting…")
} else {
addActivity("Failed to start screen audio: \(result.description)")
}
}
/// Called when the broadcast ends (or on disconnect). Stops feeding and the stream.
private func stopScreenShare() {
broadcastPump.endFeeding()
if voiceState.screenStreamId != 0 {
client.stopStream(voiceState.screenStreamId)
voiceState.screenStreamId = 0
}
if voiceState.screenSharing {
voiceState.screenSharing = false
addActivity("Stopped sharing screen audio")
}
}
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
UserDefaults.standard.set(Int(mode.rawValue), forKey: DefaultsKey.inputMode)
}
func setVadThreshold(_ threshold: Float) {
client.setVadThreshold(threshold)
voiceState.vadThreshold = threshold
UserDefaults.standard.set(threshold, forKey: DefaultsKey.vadThreshold)
}
func setInputGain(_ gain: Float) {
client.setInputGain(gain)
voiceState.inputGain = gain
UserDefaults.standard.set(gain, forKey: DefaultsKey.inputGain)
}
func setInputNoiseReduction(_ on: Bool) {
client.setInputNoiseReduction(on)
voiceState.inputNoiseReduction = on
UserDefaults.standard.set(on, forKey: DefaultsKey.inputNoiseReduction)
}
// MARK: - Persisted input settings
private enum DefaultsKey {
static let inputMode = "voice.inputMode"
static let vadThreshold = "voice.vadThreshold"
static let inputGain = "voice.inputGain"
static let inputNoiseReduction = "voice.inputNoiseReduction"
}
/// Restore the saved input mode / VAD threshold / mic gain and push them into the core so a
/// relaunch keeps the user's transmission settings instead of resetting to VAD defaults.
private func loadAndApplyVoiceSettings() {
let d = UserDefaults.standard
if d.object(forKey: DefaultsKey.inputMode) != nil {
let raw = UInt32(d.integer(forKey: DefaultsKey.inputMode))
voiceState.inputMode = VoiceCatInputMode(rawValue: raw) ?? .voiceActivation
}
if d.object(forKey: DefaultsKey.vadThreshold) != nil {
voiceState.vadThreshold = d.float(forKey: DefaultsKey.vadThreshold)
}
if d.object(forKey: DefaultsKey.inputGain) != nil {
voiceState.inputGain = d.float(forKey: DefaultsKey.inputGain)
}
if d.object(forKey: DefaultsKey.inputNoiseReduction) != nil {
voiceState.inputNoiseReduction = d.bool(forKey: DefaultsKey.inputNoiseReduction)
}
client.setInputMode(voiceState.inputMode)
client.setVadThreshold(voiceState.vadThreshold)
client.setInputGain(voiceState.inputGain)
client.setInputNoiseReduction(voiceState.inputNoiseReduction)
}
private var pttEngaged = false
func setPushToTalk(_ active: Bool) {
client.setPushToTalk(active)
// Play the PTT cue only on the press transition (the gesture fires repeatedly while held).
if active && !pttEngaged { EventFeedback.shared.play(.ptt) }
pttEngaged = 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(_ info: ChannelEdit) {
client.createChannel(info)
}
func editChannel(_ info: ChannelEdit) {
client.editChannel(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)
}
}