Files
voice-cat/tests/VoiceCat.Tests/MediaRelayTests.cs
T
Talon f3ac779bf4
Build and test / test (macos-latest) (push) Waiting to run
Build and test / test (ubuntu-24.04) (push) Waiting to run
Build and test / test (windows-latest) (push) Waiting to run
Build and test / apple-client (push) Waiting to run
Survive changing networks and deepen the receive buffer
Media died silently whenever a client's source address changed. The relay bound a
peer's endpoint once and refused to move it, and the client stopped offering its
binding token after the first bind, so a Wi-Fi/cellular handover stranded the
session in both directions. Add an authenticated Rebind media frame: the binding
token travels in the clear for peer lookup only, and the AEAD tag over header and
token plus the peer's existing replay window are what authorize the move, so a
captured rebind cannot be replayed to redirect someone else's downlink. The client
rebuilds its UDP socket instead of retrying on one still pinned to a vanished
interface.

Nothing judged the control connection live: pings were sent and pongs ignored, so a
blackholed TCP path went unnoticed for minutes while the UI showed a live session.
Treat any server traffic as liveness and fail the connection when it stops, which
drives the existing reconnect.

The receive jitter buffer had lost its depth floor, so a channel without FEC or
DRED played out with no buffer at all and ordinary reordering became concealment.
Restore a one-frame floor, observe every arrival rather than only accepted ones —
a shallow buffer was rejecting the late arrivals that should have deepened it —
and allow playout to hold a frame so depth can follow a degrading link. A stalled
consumer now sheds the oldest queued packet instead of refusing the live talkspurt.

Add a deterministic network-impairment simulation covering bursty loss, jitter,
reordering, duplication, outages and a stalled consumer, a handover test against a
real relay, a replay test for the rebind path, and a blackholed control connection
driven through a freezable TCP proxy.
2026-09-24 19:15:16 +02:00

295 lines
16 KiB
C#

using VoiceCat.Transport;
using System.Net;
using System.Net.Sockets;
using VoiceCat.Crypto;
using VoiceCat.Protocol;
using VoiceCat.Server.Transport;
using Voicecat.V1;
using static VoiceCat.Tests.ServerTests;
namespace VoiceCat.Tests;
public sealed class MediaRelayTests
{
[Fact]
public async Task AutomaticModeReportsAuthenticatedSenderUplinkLossWithCap()
{
var clock = new ManualClock();
await using var fixture = new ServerFixture(timeProvider: clock);
Client admin = await ChannelManagementTests.AdminAsync(fixture);
using (var store = new VoiceCat.Server.Data.AccountStore(Path.Combine(fixture.Directory, "voicecat.db")))
{
Channel lobby = store.LoadChannels().Single(channel => channel.Id == 1);
lobby.Audio.PacketLossMode = PacketLossMode.PacketLossAutoFast;
Assert.True(await ChannelManagementTests.ResultAsync(admin, new() { EditChannel = new() { Channel = lobby } }));
}
await using var alice = await VoicePeer.AttachAsync(fixture, admin);
await using var bob = await VoicePeer.ConnectAsync(fixture, "Bob");
StreamAnnounceResult stream = await alice.AnnounceAsync(StreamKind.StreamMic);
await alice.SendAsync(alice.Seal(stream.Ssrc, [1]));
await bob.ReceiveVoiceAsync();
for (int i = 0; i < 99; i++) alice.Seal(stream.Ssrc, [2]);
clock.Advance(TimeSpan.FromSeconds(3));
await alice.SendAsync(alice.Seal(stream.Ssrc, [3]));
PacketLossUpdate update = (await admin.ReadUntilAsync(envelope => envelope.PacketLossUpdate is not null)).PacketLossUpdate;
Assert.Equal(1U, update.ChannelId);
Assert.Equal(99U, update.MeasuredPercent);
Assert.Equal(30U, update.AppliedPercent);
}
[Fact]
public async Task DisconnectInvalidatesBothBindingAndActiveStreams()
{
await using var fixture = new ServerFixture();
await using var alice = await VoicePeer.ConnectAsync(fixture, "Alice");
await using var bob = await VoicePeer.ConnectAsync(fixture, "Bob");
var stream = await alice.AnnounceAsync(StreamKind.StreamMic);
alice.Client.Send(new() { Disconnect = new() });
await bob.Client.ReadUntilAsync(e => e.UserEvent?.Kind == UserEvent.Types.Kind.Left && e.UserEvent.LeftId == alice.Client.Authentication!.Self.Id);
await alice.SendAsync(alice.Seal(stream.Ssrc, [1]));
await bob.AssertNoVoiceAsync();
}
[Fact]
public async Task AnnounceRequiresSubscriptionAndUsesAuthoritativeMusicSettings()
{
await using var fixture = new ServerFixture();
await using var client = await fixture.ConnectAsync();
await client.LoginAsync("Alice");
client.Send(new() { StreamAnnounce = new() { Kind = StreamKind.StreamMic } });
Assert.False((await client.ReadUntilAsync(e => e.StreamAnnounceResult is not null)).StreamAnnounceResult.Ok);
client.Send(new() { SubscribeVoice = new() });
await client.ReadUntilAsync(e => e.VoiceSubscriptionResult is not null);
client.Send(new() { JoinChannel = new() { ChannelId = 2 } });
await client.ReadUntilAsync(e => e.JoinChannelResult is not null);
client.Send(new() { RequestId = 21, StreamAnnounce = new() { Kind = StreamKind.StreamScreenAudio, RequestedAudio = new() { SampleRate = 8000, BitrateBps = 64000 } } });
var announced = await client.ReadUntilAsync(e => e.StreamAnnounceResult is not null);
Assert.Equal(21UL, announced.RequestId);
Assert.True(announced.StreamAnnounceResult.Ok);
Assert.Equal(64000U, announced.StreamAnnounceResult.EffectiveAudio.BitrateBps);
Assert.Equal(48000U, announced.StreamAnnounceResult.EffectiveAudio.SampleRate);
Assert.Equal(ChannelMode.ModeStereo, announced.StreamAnnounceResult.EffectiveAudio.Mode);
client.Send(new() { StreamAnnounce = new() { Kind = (StreamKind)99 } });
Assert.False((await client.ReadUntilAsync(e => e.StreamAnnounceResult is not null)).StreamAnnounceResult.Ok);
}
[Fact]
public async Task EncryptedOpusIsResealedWithRecipientCountersAcrossMultipleStreamsAndSenders()
{
await using var fixture = new ServerFixture();
await using var alice = await VoicePeer.ConnectAsync(fixture, "Alice");
await using var bob = await VoicePeer.ConnectAsync(fixture, "Bob");
await using var carol = await VoicePeer.ConnectAsync(fixture, "Carol");
StreamAnnounceResult mic = await alice.AnnounceAsync(StreamKind.StreamMic);
StreamAnnounceResult screen = await alice.AnnounceAsync(StreamKind.StreamScreenAudio);
StreamAnnounceResult other = await carol.AnnounceAsync(StreamKind.StreamMic);
Assert.NotEqual(mic.StreamId, screen.StreamId);
Assert.NotEqual(mic.Ssrc, screen.Ssrc);
Assert.Equal(48000U, screen.EffectiveAudio.SampleRate);
Assert.Equal(24000U, screen.EffectiveAudio.BitrateBps);
using var encoder = new Codec.OpusEncoder(new());
short[] samples = Enumerable.Range(0, 960).Select(i => (short)(8000 * Math.Sin(i * 0.1))).ToArray();
byte[] payload = new byte[4000];
int length = encoder.Encode(samples, payload);
payload = payload[..length];
foreach (var (sender, stream) in new[] { (alice, mic), (carol, other), (alice, screen) })
{
byte[] packet = sender.Seal(stream.Ssrc, payload, 960, VoiceFrameFlags.Marker | VoiceFrameFlags.FecPresent);
await sender.SendAsync(packet);
var received = await bob.ReceiveVoiceAsync();
Assert.Equal(payload, received.Payload);
Assert.Equal(stream.Ssrc, received.Header.Ssrc);
Assert.Equal(960U, received.Header.Timestamp);
Assert.Equal(VoiceFrameFlags.Marker | VoiceFrameFlags.FecPresent, received.Header.Flags);
}
Assert.Equal(2UL, bob.LastSequence);
}
[Fact]
public async Task ReplayForgeryAndSpoofedStreamsAreDroppedWithoutBreakingValidMedia()
{
await using var fixture = new ServerFixture();
await using var alice = await VoicePeer.ConnectAsync(fixture, "Alice");
await using var bob = await VoicePeer.ConnectAsync(fixture, "Bob");
StreamAnnounceResult stream = await alice.AnnounceAsync(StreamKind.StreamMic);
byte[] packet = alice.Seal(stream.Ssrc, [1, 2, 3]);
await alice.SendAsync(packet);
Assert.Equal(new byte[] { 1, 2, 3 }, (await bob.ReceiveVoiceAsync()).Payload);
await alice.SendAsync(packet);
byte[] forged = alice.Seal(stream.Ssrc, [4]);
forged[^1] ^= 1;
await alice.SendAsync(forged);
await alice.SendAsync(alice.Seal(stream.Ssrc + 1000, [5]));
await alice.SendAsync([1]);
await alice.SendAsync(alice.Seal(stream.Ssrc, [6]));
Assert.Equal(new byte[] { 6 }, (await bob.ReceiveVoiceAsync()).Payload);
Assert.Equal(1UL, bob.LastSequence);
}
[Fact]
public async Task SubscriptionChannelMovementAndStreamStopIsolateMedia()
{
await using var fixture = new ServerFixture();
await using var alice = await VoicePeer.ConnectAsync(fixture, "Alice");
await using var bob = await VoicePeer.ConnectAsync(fixture, "Bob");
var mic = await alice.AnnounceAsync(StreamKind.StreamMic);
await bob.SubscribeAsync(false);
await alice.SendAsync(alice.Seal(mic.Ssrc, [1]));
await bob.AssertNoVoiceAsync();
await bob.SubscribeAsync(true);
bob.Client.Send(new() { JoinChannel = new() { ChannelId = 2 } });
Assert.True((await bob.Client.ReadUntilAsync(e => e.JoinChannelResult is not null)).JoinChannelResult.Ok);
await alice.SendAsync(alice.Seal(mic.Ssrc, [2]));
await bob.AssertNoVoiceAsync();
bob.Client.Send(new() { JoinChannel = new() { ChannelId = 1 } });
await bob.Client.ReadUntilAsync(e => e.JoinChannelResult is not null);
alice.Client.Send(new() { StreamStop = new() { StreamId = mic.StreamId } });
await alice.Client.ReadUntilAsync(e => e.UserEvent?.User?.Id == alice.Client.Authentication!.Self.Id && e.UserEvent.User.Streams.Count == 0);
await alice.SendAsync(alice.Seal(mic.Ssrc, [3]));
await bob.AssertNoVoiceAsync();
var replacement = await alice.AnnounceAsync(StreamKind.StreamMic);
await alice.SendAsync(alice.Seal(replacement.Ssrc, [4]));
Assert.Equal(new byte[] { 4 }, (await bob.ReceiveVoiceAsync()).Payload);
}
[Fact]
public async Task BadTokensCannotBindAndExistingBindingCannotBeStolen()
{
await using var fixture = new ServerFixture();
await using var alice = await VoicePeer.ConnectAsync(fixture, "Alice");
using var rogue = new Socket(AddressFamily.InterNetwork, SocketType.Dgram, ProtocolType.Udp);
rogue.Bind(new IPEndPoint(IPAddress.Loopback, 0));
byte[] binding = new byte[VoiceFrameHeader.Size + 16];
new VoiceFrameHeader(MediaFrameType.UdpBinding, 0, 0, 0, 0, 0).Write(binding);
await rogue.SendToAsync(binding, SocketFlags.None, fixture.Server.MediaEndPoint);
alice.Client.Authentication!.UdpToken.Span.CopyTo(binding.AsSpan(VoiceFrameHeader.Size));
await rogue.SendToAsync(binding, SocketFlags.None, fixture.Server.MediaEndPoint);
byte[] keepalive = new byte[VoiceFrameHeader.Size];
new VoiceFrameHeader(MediaFrameType.Keepalive, 0, 0, 0, 0, 0).Write(keepalive);
await rogue.SendToAsync(keepalive, SocketFlags.None, fixture.Server.MediaEndPoint);
using var timeout = new CancellationTokenSource(200);
await Assert.ThrowsAnyAsync<OperationCanceledException>(async () => await rogue.ReceiveAsync(new byte[100], SocketFlags.None, timeout.Token));
await alice.SendAsync(keepalive);
Assert.Equal(keepalive, await alice.ReceivePacketAsync());
}
internal sealed class VoicePeer : IAsyncDisposable
{
public Client Client { get; }
private Socket udp = new(AddressFamily.InterNetwork, SocketType.Dgram, ProtocolType.Udp);
private readonly IPEndPoint endpoint;
private readonly MediaSessionCrypto crypto;
public ulong LastSequence { get; private set; }
private VoicePeer(Client client, IPEndPoint endpoint, MediaSessionCrypto crypto)
{
Client = client; this.endpoint = endpoint; this.crypto = crypto;
udp.Bind(new IPEndPoint(IPAddress.Loopback, 0));
}
public static async Task<VoicePeer> ConnectAsync(ServerFixture fixture, string nickname)
{
Client client = await fixture.ConnectAsync();
await client.LoginAsync(nickname);
return await AttachAsync(fixture, client);
}
internal static async Task<VoicePeer> AttachAsync(ServerFixture fixture, Client client)
{
var peer = new VoicePeer(client, fixture.Server.MediaEndPoint, await client.TakeMediaCryptoAsync());
client.Send(new() { UdpBinding = new() { UdpToken = client.Authentication!.UdpToken } });
Assert.True((await client.ReadUntilAsync(e => e.UdpBinding is not null)).UdpBinding.Ack);
byte[] binding = new byte[VoiceFrameHeader.Size + 16];
new VoiceFrameHeader(MediaFrameType.UdpBinding, 0, 0, 0, 0, 0).Write(binding);
client.Authentication.UdpToken.Span.CopyTo(binding.AsSpan(VoiceFrameHeader.Size));
await peer.SendAsync(binding);
byte[] keepalive = new byte[VoiceFrameHeader.Size];
new VoiceFrameHeader(MediaFrameType.Keepalive, 0, 0, 0, 0, 0).Write(keepalive);
await peer.SendAsync(keepalive);
Assert.Equal(keepalive, await peer.ReceivePacketAsync());
await peer.SubscribeAsync(true);
return peer;
}
public async Task SubscribeAsync(bool subscribed)
{
Client.Send(subscribed ? new() { SubscribeVoice = new() } : new() { UnsubscribeVoice = new() });
var result = (await Client.ReadUntilAsync(e => e.VoiceSubscriptionResult is not null)).VoiceSubscriptionResult;
Assert.True(result.Ok); Assert.Equal(subscribed, result.Subscribed);
}
public async Task<StreamAnnounceResult> AnnounceAsync(StreamKind kind)
{
Client.Send(new() { StreamAnnounce = new() { Kind = kind, RequestedAudio = new() { SampleRate = 8000, BitrateBps = 900000 } } });
var result = (await Client.ReadUntilAsync(e => e.StreamAnnounceResult is not null)).StreamAnnounceResult;
Assert.True(result.Ok, result.Error);
return result;
}
public byte[] Seal(uint ssrc, byte[] payload, uint timestamp = 0, VoiceFrameFlags flags = 0)
{
byte[] packet = new byte[VoiceFrameHeader.Size + payload.Length + 16];
crypto.Encryptor.Encrypt(new(MediaFrameType.Voice, flags, 0, ssrc, 0, timestamp), payload, packet);
return packet;
}
public async Task SendAsync(byte[] packet) => await udp.SendToAsync(packet, SocketFlags.None, endpoint, Client.Timeout.Token);
// Models a Wi-Fi/cellular handover: the peer keeps its TLS control session but its media
// source address changes, then it re-offers its UDP binding token from the new address.
internal async Task HandoverAsync()
{
udp.Dispose();
udp = new(AddressFamily.InterNetwork, SocketType.Dgram, ProtocolType.Udp);
udp.Bind(new IPEndPoint(IPAddress.Loopback, 0));
byte[] rebind = new byte[MediaEncryptor.RebindSize];
int size = crypto.Encryptor.EncryptRebind(Client.Authentication!.UdpToken.Span, rebind);
await SendAsync(rebind[..size]);
}
// A rebind captured off the wire must not let anyone else claim the peer's downlink.
internal async Task<byte[]> CaptureRebindAsync()
{
byte[] rebind = new byte[MediaEncryptor.RebindSize];
int size = crypto.Encryptor.EncryptRebind(Client.Authentication!.UdpToken.Span, rebind);
await SendAsync(rebind[..size]);
return rebind[..size];
}
// Returns true when the relay echoes a keepalive to the peer's current source address,
// which is the only signal that the server will route downlink media back to it.
internal async Task<bool> KeepaliveEchoesAsync(int timeoutMilliseconds = 1000)
{
byte[] keepalive = new byte[VoiceFrameHeader.Size];
new VoiceFrameHeader(MediaFrameType.Keepalive, 0, 0, 0, 0, 0).Write(keepalive);
await SendAsync(keepalive);
using var timeout = new CancellationTokenSource(timeoutMilliseconds);
try { byte[] buffer = new byte[65535]; await udp.ReceiveAsync(buffer, SocketFlags.None, timeout.Token); return true; }
catch (OperationCanceledException) { return false; }
}
public async Task<byte[]> ReceivePacketAsync()
{
byte[] buffer = new byte[65535];
int size = await udp.ReceiveAsync(buffer, SocketFlags.None, Client.Timeout.Token);
return buffer[..size];
}
public async Task<(VoiceFrameHeader Header, byte[] Payload)> ReceiveVoiceAsync()
{
byte[] packet = await ReceivePacketAsync();
byte[] plain = new byte[65535];
Assert.True(crypto.Decryptor.TryDecrypt(packet, plain, out var header, out int length));
LastSequence = header.Sequence;
return (header, plain[..length]);
}
public async Task AssertNoVoiceAsync()
{
using var timeout = new CancellationTokenSource(200);
await Assert.ThrowsAnyAsync<OperationCanceledException>(async () => await udp.ReceiveAsync(new byte[65535], SocketFlags.None, timeout.Token));
}
public async ValueTask DisposeAsync() { udp.Dispose(); crypto.Dispose(); await Client.DisposeAsync(); }
}
private sealed class ManualClock : TimeProvider
{
private long timestamp;
public override long TimestampFrequency => 1_000;
public override long GetTimestamp() => Volatile.Read(ref timestamp);
internal void Advance(TimeSpan duration) => Interlocked.Add(ref timestamp, (long)duration.TotalMilliseconds);
}
}