voice-cat/clients/apple/VoiceCat.iOS/IosAudioRouter.cs

using AVFoundation;
using Foundation;
using ObjCRuntime;
using UIKit;

namespace VoiceCat.iOS;

internal enum IosAudioPreset { VoiceChat, StereoMicrophone, MonoMicrophone, Advanced }
internal enum IosBluetoothMode { HfpVoice, BuiltInMicA2dp, BuiltInMicSpeaker }
internal enum IosMicMode { Standard, Raw }
internal sealed record IosAudioPort(string Id, string Name, string Type);
internal sealed record IosAudioDataSource(string Id, string Name, IReadOnlyList<AVAudioDataSourcePolarPattern> Patterns);

internal sealed class IosAudioRouter
{
    private static readonly NativeHandle SupportedPolarPatternsSelector = Selector.GetHandle("supportedPolarPatterns");
    private static readonly NativeHandle SetPreferredPolarPatternSelector = Selector.GetHandle("setPreferredPolarPattern:error:");
    internal static IosAudioRouter Shared { get; } = new();
    private readonly NSUserDefaults defaults = NSUserDefaults.StandardUserDefaults;
    private bool applying;
    private System.Threading.Timer? watchdog;
    private long lastRenderCallbacks = -1;
    private int watchdogMisses;
    private bool watchdogTicking;
    private bool interrupted;
    internal event Action? Changed;
    internal IosAudioPreset Preset { get; private set; } = IosAudioPreset.VoiceChat;
    internal IosBluetoothMode BluetoothMode { get; private set; } = IosBluetoothMode.HfpVoice;
    internal IosMicMode MicMode { get; private set; } = IosMicMode.Standard;
    internal bool ForceSpeaker { get; private set; }
    internal bool VoiceProcessing { get; private set; } = true;
    internal bool AutomaticGainControl { get; private set; } = true;
    internal int CaptureChannels { get; private set; } = 1;
    internal string? SelectedInputId { get; private set; }
    internal string? SelectedDataSourceId { get; private set; }
    internal AVAudioDataSourcePolarPattern SelectedPolarPattern { get; private set; } = AVAudioDataSourcePolarPattern.Unknown;
    internal IReadOnlyList<IosAudioPort> Inputs { get; private set; } = [];
    internal IReadOnlyList<IosAudioPort> Outputs { get; private set; } = [];
    internal bool VoiceProcessingAvailable => CaptureChannels == 1 && MicMode == IosMicMode.Standard && BluetoothMode != IosBluetoothMode.BuiltInMicA2dp;
    internal bool UsesVoiceProcessing => VoiceProcessing && VoiceProcessingAvailable;

    private IosAudioRouter()
    {
        NSNotificationCenter.DefaultCenter.AddObserver(AVAudioSession.RouteChangeNotification, HandleRouteChange);
        NSNotificationCenter.DefaultCenter.AddObserver(AVAudioSession.InterruptionNotification, HandleInterruption);
        NSNotificationCenter.DefaultCenter.AddObserver(AVAudioSession.MediaServicesWereResetNotification, _ => Recover("media services reset"));
    }

    internal void Load()
    {
        if (Enum.TryParse(defaults.StringForKey("cat.voice.audio.preset"), true, out IosAudioPreset preset)) Preset = preset;
        if (Enum.TryParse(defaults.StringForKey("cat.voice.audio.bluetoothMode"), true, out IosBluetoothMode bluetooth)) BluetoothMode = bluetooth;
        if (Enum.TryParse(defaults.StringForKey("cat.voice.audio.micMode"), true, out IosMicMode mic)) MicMode = mic;
        ForceSpeaker = defaults.BoolForKey("cat.voice.audio.forceSpeaker");
        // Older voice-chat selections saved an automatic speaker override. Drop that
        // preference for the named preset so an existing install can follow HFP again.
        if (Preset == IosAudioPreset.VoiceChat) ForceSpeaker = false;
        VoiceProcessing = defaults.ValueForKey(new NSString("cat.voice.audio.voiceProcessing")) is null || defaults.BoolForKey("cat.voice.audio.voiceProcessing");
        AutomaticGainControl = defaults.ValueForKey(new NSString("cat.voice.audio.agc")) is null || defaults.BoolForKey("cat.voice.audio.agc");
        CaptureChannels = defaults.IntForKey("cat.voice.audio.captureChannels") == 2 ? 2 : Preset == IosAudioPreset.StereoMicrophone ? 2 : 1;
        SelectedInputId = defaults.StringForKey("cat.voice.audio.inputPortId"); SelectedDataSourceId = defaults.StringForKey("cat.voice.audio.dataSourceId");
        if (Preset == IosAudioPreset.VoiceChat) { SelectedInputId = null; SelectedDataSourceId = null; }
        if (Enum.TryParse(defaults.StringForKey("cat.voice.audio.polarPattern"), true, out AVAudioDataSourcePolarPattern pattern)) SelectedPolarPattern = pattern;
        RefreshRoutes();
    }

    internal void SelectPreset(IosAudioPreset preset)
    {
        Preset = preset;
        if (preset != IosAudioPreset.Advanced)
        {
            CaptureChannels = preset == IosAudioPreset.StereoMicrophone ? 2 : 1; MicMode = IosMicMode.Standard;
            BluetoothMode = preset == IosAudioPreset.VoiceChat ? IosBluetoothMode.HfpVoice : IosBluetoothMode.BuiltInMicA2dp;
            if (preset is IosAudioPreset.StereoMicrophone or IosAudioPreset.MonoMicrophone)
                SelectedInputId = AVAudioSession.SharedInstance().AvailableInputs?.FirstOrDefault(value => value.PortType == AVAudioSession.PortBuiltInMic)?.UID;
            else SelectedInputId = null;
            // Named presets never carry an Advanced capsule selection across transitions.
            // Stereo derives its data source below; mono/voice chat must clear a stale stereo one.
            SelectedDataSourceId = null; SelectedPolarPattern = AVAudioDataSourcePolarPattern.Unknown;
            // HFP needs to remain free to follow a connected headset. A speaker route can
            // still be requested explicitly with the Speaker output control.
            if (preset == IosAudioPreset.VoiceChat) ForceSpeaker = false;
        }
        SaveAndReconfigure();
    }

    internal void SetForceSpeaker(bool value) { ForceSpeaker = value; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }
    internal void SetVoiceProcessing(bool value) { VoiceProcessing = value; SaveAndReconfigure(); }
    internal void SetAutomaticGainControl(bool value) { AutomaticGainControl = value; SaveAndReconfigure(); }
    internal void SetCaptureChannels(int value) { CaptureChannels = value == 2 ? 2 : 1; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }
    internal void SetBluetoothMode(IosBluetoothMode value) { BluetoothMode = value; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }
    internal void SetMicMode(IosMicMode value) { MicMode = value; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }
    internal void SelectInput(string? id) { SelectedInputId = string.IsNullOrEmpty(id) ? null : id; SelectedDataSourceId = null; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }
    internal void SelectDataSource(string? id) { SelectedDataSourceId = string.IsNullOrEmpty(id) ? null : id; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }
    internal void SelectPolarPattern(AVAudioDataSourcePolarPattern pattern) { SelectedPolarPattern = pattern; Preset = IosAudioPreset.Advanced; SaveAndReconfigure(); }

    internal IReadOnlyList<IosAudioDataSource> DataSources()
    {
        AVAudioSessionPortDescription? port = AVAudioSession.SharedInstance().AvailableInputs?.FirstOrDefault(value => value.UID == SelectedInputId);
        return port?.DataSources?.Select(value => new IosAudioDataSource(value.DataSourceID.ToString(), value.DataSourceName,
            value.SupportedPolarPatterns?.ToArray() ?? [])).ToArray() ?? [];
    }

    internal void RefreshRoutes()
    {
        AVAudioSession session = AVAudioSession.SharedInstance();
        Inputs = session.AvailableInputs?.Select(value => new IosAudioPort(value.UID, value.PortName, value.PortType.ToString())).ToArray() ?? [];
        Outputs = session.CurrentRoute.Outputs.Select(value => new IosAudioPort(value.UID, value.PortName, value.PortType.ToString())).ToArray();
        // A route reported by iOS is not an explicit user input choice. Capturing it here
        // can pin the built-in mic after a speaker fallback and displace a Bluetooth HFP route
        // on the next graph rebuild.
        Changed?.Invoke();
    }

    internal void Apply(bool configureInput)
    {
        if (applying) return; applying = true;
        try
        {
            AVAudioSession session = AVAudioSession.SharedInstance(); AVAudioSessionCategoryOptions options = AVAudioSessionCategoryOptions.MixWithOthers;
            if (BluetoothMode == IosBluetoothMode.HfpVoice) options |= AVAudioSessionCategoryOptions.AllowBluetooth | AVAudioSessionCategoryOptions.AllowBluetoothA2DP | AVAudioSessionCategoryOptions.AllowAirPlay;
            if (BluetoothMode == IosBluetoothMode.BuiltInMicA2dp) options |= AVAudioSessionCategoryOptions.AllowBluetoothA2DP | AVAudioSessionCategoryOptions.AllowAirPlay;
            if (BluetoothMode == IosBluetoothMode.BuiltInMicSpeaker || ForceSpeaker && BluetoothMode != IosBluetoothMode.BuiltInMicA2dp) options |= AVAudioSessionCategoryOptions.DefaultToSpeaker;
            AVAudioSessionMode mode = CaptureChannels == 2 ? AVAudioSessionMode.Default : MicMode == IosMicMode.Raw ? AVAudioSessionMode.Measurement
                : BluetoothMode == IosBluetoothMode.BuiltInMicA2dp ? AVAudioSessionMode.VideoRecording : AVAudioSessionMode.VoiceChat;
            if (!session.SetCategory(AVAudioSessionCategory.PlayAndRecord, mode, options, out NSError? categoryError)) throw new InvalidOperationException(categoryError.LocalizedDescription);
            session.SetPreferredSampleRate(48_000, out _); session.SetPreferredIOBufferDuration(0.02, out _);
            if (configureInput) ApplyInputSelection(session);
            if (!session.SetActive(true, AVAudioSessionSetActiveOptions.NotifyOthersOnDeactivation, out NSError? activeError)) throw new InvalidOperationException(activeError.LocalizedDescription);
            Console.Error.WriteLine($"VC_ROUTE preset={Preset} requestedCh={CaptureChannels} sessionCh={session.InputNumberOfChannels} " +
                $"preferred={session.PreferredInput?.PortName ?? "default"} dataSource={session.InputDataSource?.DataSourceName ?? "default"} " +
                $"pattern={session.InputDataSource?.SelectedPolarPattern.ToString() ?? "default"}");
            // The speaker port override forces both input and output to built-in hardware,
            // even with a headset connected. DefaultToSpeaker is an explicit speaker choice
            // only; the voice-chat preset leaves it off so HFP can follow the headset.
            RefreshRoutes();
            ResetWatchdog(); EnsureWatchdog();
        }
        finally { applying = false; }
    }

    private void ApplyInputSelection(AVAudioSession session)
    {
        AVAudioSessionPortDescription? port = session.AvailableInputs?.FirstOrDefault(value => value.UID == SelectedInputId);
        if (CaptureChannels == 2) port ??= session.AvailableInputs?.FirstOrDefault(value => value.PortType == AVAudioSession.PortBuiltInMic);
        if (port is null) { if (CaptureChannels == 1) ClearStereoPolarPattern(session); return; }
        if (CaptureChannels == 2)
        {
            // Polar-pattern discovery alone is insufficient on current iPhones: until a stereo
            // orientation is requested, the built-in port can expose only its mono Bottom source
            // and AVAudioEngine consequently binds a one-channel input node. This is Apple's
            // dedicated switch for built-in stereo recording. Portrait matches this portrait UI;
            // it also gives Core Audio an unambiguous left/right mapping before graph creation.
            if (!session.SetPreferredInputOrientation(AVAudioStereoOrientation.Portrait, out NSError? orientationError))
                throw new InvalidOperationException(orientationError?.LocalizedDescription ?? "Could not set the stereo microphone orientation.");
        }
        AVAudioSessionDataSourceDescription? source = CaptureChannels == 2
            ? port.DataSources?.FirstOrDefault(SupportsStereoPolarPattern)
            : port.DataSources?.FirstOrDefault(value => value.DataSourceID.ToString() == SelectedDataSourceId);
        if (CaptureChannels == 1 && source is null) ClearStereoPolarPattern(session);
        if (source is not null)
        {
            if (!port.SetPreferredDataSource(source, out NSError? portError)) throw new InvalidOperationException(portError.LocalizedDescription);
            if (CaptureChannels == 2) SetStereoPolarPattern(source);
            else if (SelectedPolarPattern != AVAudioDataSourcePolarPattern.Unknown &&
                !source.SetPreferredPolarPattern(SelectedPolarPattern, out NSError? patternError))
                throw new InvalidOperationException(patternError.LocalizedDescription);
        }
        if (!session.SetPreferredInput(port, out NSError? inputError)) throw new InvalidOperationException(inputError.LocalizedDescription);
        // The working Swift client deliberately does not call
        // SetPreferredInputNumberOfChannels: doing so disrupts stereo + A2DP routing. The stereo
        // capsule and polar pattern above cause the input node to expose its two-channel format.
        if (CaptureChannels == 2 && source is not null &&
            !session.SetInputDataSource(source, out NSError? sourceError))
            throw new InvalidOperationException(sourceError.LocalizedDescription);
        Console.Error.WriteLine($"VC_ROUTE_SELECT port={port.PortName} source={source?.DataSourceName ?? "none"} " +
            $"stereoPattern={source is not null && SupportsStereoPolarPattern(source)} " +
            $"patterns={string.Join(',', source?.SupportedPolarPatterns?.Select(value => value.ToString()) ?? [])}");
    }

    // Microsoft.iOS 27 exposes AVAudioSessionPolarPatternStereo as an NSString constant but its
    // AVAudioDataSourcePolarPattern smart enum still has no Stereo member. Reading the native
    // NSArray and setting the native NSString avoids silently mapping Stereo to Unknown.
    private static bool SupportsStereoPolarPattern(AVAudioSessionDataSourceDescription source)
    {
        NativeHandle handle = NativeMethods.GetObject(source.Handle, SupportedPolarPatternsSelector);
        NSArray? patterns = Runtime.GetNSObject<NSArray>(handle);
        if (patterns is null) return false;
        for (nuint index = 0; index < patterns.Count; index++)
            if (patterns.GetItem<NSString>(index)?.IsEqualTo(AVAudioSession.PolarPatternStereo.Handle) == true) return true;
        return false;
    }

    private static void SetStereoPolarPattern(AVAudioSessionDataSourceDescription source)
    {
        NativeHandle error = NativeHandle.Zero;
        if (NativeMethods.SetObject(source.Handle, SetPreferredPolarPatternSelector,
            AVAudioSession.PolarPatternStereo.Handle, ref error) == 0)
            throw new InvalidOperationException(Runtime.GetNSObject<NSError>(error)?.LocalizedDescription ?? "Could not enable stereo microphone capture.");
    }

    private static class NativeMethods
    {
        [System.Runtime.InteropServices.DllImport("/usr/lib/libobjc.dylib", EntryPoint = "objc_msgSend")]
        internal static extern NativeHandle GetObject(NativeHandle receiver, NativeHandle selector);

        [System.Runtime.InteropServices.DllImport("/usr/lib/libobjc.dylib", EntryPoint = "objc_msgSend")]
        internal static extern byte SetObject(NativeHandle receiver, NativeHandle selector, NativeHandle value, ref NativeHandle error);
    }

    private static void ClearStereoPolarPattern(AVAudioSession session)
    {
        session.SetPreferredInputOrientation(AVAudioStereoOrientation.None, out _);
        AVAudioSessionPortDescription? builtIn = session.AvailableInputs?.FirstOrDefault(value => value.PortType == AVAudioSession.PortBuiltInMic);
        if (builtIn is null) return;
        foreach (AVAudioSessionDataSourceDescription source in builtIn.DataSources ?? [])
            if (source.SelectedPolarPattern == AVAudioDataSourcePolarPattern.Unknown && SupportsStereoPolarPattern(source))
                source.SetPreferredPolarPattern(AVAudioDataSourcePolarPattern.Unknown, out _);
    }

    private void SaveAndReconfigure()
    {
        defaults.SetString(Preset.ToString(), "cat.voice.audio.preset"); defaults.SetString(BluetoothMode.ToString(), "cat.voice.audio.bluetoothMode");
        defaults.SetString(MicMode.ToString(), "cat.voice.audio.micMode"); defaults.SetBool(ForceSpeaker, "cat.voice.audio.forceSpeaker");
        defaults.SetBool(VoiceProcessing, "cat.voice.audio.voiceProcessing"); defaults.SetBool(AutomaticGainControl, "cat.voice.audio.agc"); defaults.SetInt(CaptureChannels, "cat.voice.audio.captureChannels");
        Set("cat.voice.audio.inputPortId", SelectedInputId); Set("cat.voice.audio.dataSourceId", SelectedDataSourceId); defaults.SetString(SelectedPolarPattern.ToString(), "cat.voice.audio.polarPattern"); defaults.Synchronize();
        if (IosAudioEngine.Shared.IsConnected) IosAudioEngine.Shared.Reconfigure(); Changed?.Invoke();
    }

    private void Set(string key, string? value) { if (value is null) defaults.RemoveObject(key); else defaults.SetString(value, key); }
    internal void Deactivate()
    {
        watchdog?.Dispose(); watchdog = null; ResetWatchdog();
        AVAudioSession.SharedInstance().SetActive(false, AVAudioSessionSetActiveOptions.NotifyOthersOnDeactivation, out _);
    }
    internal void EnsureAudio(string reason)
    {
        if (!IosAudioEngine.Shared.IsConnected || interrupted) return;
        try { IosAudioEngine.Shared.EnsureRunning(); }
        catch (Exception exception) { System.Diagnostics.Debug.WriteLine($"Audio recovery ({reason}) failed: {exception}"); }
    }

    internal void Recover(string reason, bool force = true)
    {
        RefreshRoutes();
        if (!IosAudioEngine.Shared.IsConnected || interrupted) return;
        UIApplication.SharedApplication.BeginInvokeOnMainThread(() =>
        {
            try { IosAudioEngine.Shared.Reconfigure(force); }
            catch (Exception exception) { System.Diagnostics.Debug.WriteLine($"Audio recovery ({reason}) failed: {exception}"); }
        });
    }

    // The render callback is the only clock for the device-clocked pipeline, so a graph that
    // stops while the app is backgrounded freezes capture, mix and send with no notification to
    // recover from. Poll for that and rebuild; a failed rebuild is retried on the next tick.
    private void EnsureWatchdog()
    {
        watchdog ??= new System.Threading.Timer(_ => UIApplication.SharedApplication.BeginInvokeOnMainThread(TickWatchdog),
            null, TimeSpan.FromSeconds(1), TimeSpan.FromSeconds(1));
    }

    private void ResetWatchdog() { lastRenderCallbacks = -1; watchdogMisses = 0; }

    // An interruption that ends while the app is suspended never delivers its Ended notification,
    // so foregrounding still has to check. It must not rebuild unconditionally though: the `audio`
    // background mode keeps the session and graph live across a backgrounding, so the graph is
    // almost always healthy here and a rebuild costs a visible glitch plus, on Bluetooth, an HFP
    // renegotiation. Ensure it is running, and only reconfigure when it actually stopped.
    internal void ResumeForeground()
    {
        interrupted = false; ResetWatchdog(); RefreshRoutes();
        if (IosAudioEngine.Shared.IsConnected && !IosAudioEngine.Shared.IsRunning) Recover("foreground");
        else EnsureAudio("foreground");
    }

    private void TickWatchdog()
    {
        if (watchdogTicking) return;
        watchdogTicking = true;
        try
        {
            if (!IosAudioEngine.Shared.IsConnected || interrupted || applying) { ResetWatchdog(); return; }
            long callbacks = IosAudioEngine.Shared.RenderCallbacks;
            bool stalled = !IosAudioEngine.Shared.IsRunning || callbacks == lastRenderCallbacks;
            lastRenderCallbacks = callbacks;
            if (!stalled) { watchdogMisses = 0; return; }
            // One missed tick can be a route change already rebuilding the graph.
            if (++watchdogMisses < 2) return;
            ResetWatchdog();
            try { IosAudioEngine.Shared.Reconfigure(); }
            catch (Exception exception) { System.Diagnostics.Debug.WriteLine($"Audio watchdog rebuild failed: {exception}"); }
        }
        finally { watchdogTicking = false; }
    }
    private void HandleRouteChange(NSNotification note)
    {
        NSNumber? value = note.UserInfo?[new NSString("AVAudioSessionRouteChangeReasonKey")] as NSNumber;
        AVAudioSessionRouteChangeReason reason = (AVAudioSessionRouteChangeReason)(value?.UInt32Value ?? 0);
        RefreshRoutes();
        if (reason is AVAudioSessionRouteChangeReason.CategoryChange
            or AVAudioSessionRouteChangeReason.Override
            or AVAudioSessionRouteChangeReason.RouteConfigurationChange)
            return;
        Recover($"route change ({reason})");
    }
    private void HandleInterruption(NSNotification note)
    {
        NSNumber? type = note.UserInfo?[new NSString("AVAudioSessionInterruptionTypeKey")] as NSNumber;
        AVAudioSessionInterruptionType interruption = (AVAudioSessionInterruptionType)(type?.UInt32Value ?? 0);
        // The system stops the graph on Began and SetActive fails until the interruption clears,
        // so suppress recovery until Ended and let the watchdog retry if that rebuild fails.
        if (interruption == AVAudioSessionInterruptionType.Began) { interrupted = true; ResetWatchdog(); return; }
        if (interruption != AVAudioSessionInterruptionType.Ended) return;
        interrupted = false; ResetWatchdog(); Recover("interruption ended");
    }
}