Files
DodoSSH/tests/DodoSSH.Client.Terminal.Tests/TerminalDataPlaneTests.cs
T
jaap-jan ef12e8cc99
ci / build and test (pull_request) Successful in 2m30s
ci / android head (pull_request) Successful in 3m19s
ci / desktop nightly (pull_request) Skipped
ci / api image (pull_request) Successful in 21s
Stop the data plane's tests racing the socket they just connected
CI went red on the run that added the renderer tests, and not on anything they
assert: TerminalDataPlaneTests.Output_ReachesTheRenderer read the output frame
where it expected the session's opening one, having lost a race that has been
in the helper since it was written.

Connected and attached are two different moments. ClientWebSocket.ConnectAsync
completes on the 101, which UpgradeAsync writes before it has a WebSocket to
attach — it builds one from the stream and swaps it in a few instructions
later, on the accept thread. SendAsync drops anything sent in between, which is
the transport's documented contract rather than a bug: there is nowhere to put
a frame for a renderer that is not there, and queueing it is the unbounded
growth the credit window exists to prevent. So a helper that returned on the
handshake and let its caller send immediately was betting on thread scheduling,
every run, on every test in the file.

It only started losing now because that assembly grew nine tests and a
JavaScript engine to run them in, which is more work in parallel with a window
measured in instructions. The race is older than the branch that exposed it.

ConnectAsync now waits for the plane's own SocketAttached, subscribed before
the connection because the event can be over before ConnectAsync returns, and
bounded so a socket that never attaches fails the helper instead of hanging the
suite in a later receive. TerminalWorkspaceTests.ConnectRendererAsync has the
same exposure through OpenSessionAsync's opening frame and now waits on
WaitForRendererAsync, with a note on why that is enough for the reattach tests
and what would stop being enough.

◆ NOTHING IN src CHANGED, AND THAT IS THE CONCLUSION RATHER THAN THE SHORTCUT.
Production waits for exactly this moment already — every path that opens a
session goes through TerminalWorkspace.WaitForRendererAsync, which resolves
from the same few lines that raise the event this helper now waits on. Only the
tests skipped the gate the application does not.

Verified by widening the window rather than by hunting the flake: a 100ms delay
inserted between the 101 and the attach, in a throwaway tree, hangs the old
helper outright — both frames dropped, the test blocked in receive — and passes
89/89 with this one. Green three times over on the CI platform besides
(Alpine, musl, Release, dotnet/sdk:10.0-alpine).
2026-08-14 15:44:03 +02:00

543 lines
20 KiB
C#

using System.Globalization;
using System.Net;
using System.Net.WebSockets;
using System.Text;
using DodoSSH.Client.Ssh;
namespace DodoSSH.Client.Terminal.Tests;
/// <summary>
/// The loopback transport end to end, with a real WebSocket client.
/// </summary>
/// <remarks>
/// Uses <see cref="ClientWebSocket"/> against the real listener rather than a stubbed transport,
/// because the hand-rolled HTTP upgrade is the part that could be subtly wrong — and a handshake that
/// no real client accepts would pass any test that skipped it.
/// </remarks>
public sealed class TerminalDataPlaneTests : IAsyncDisposable
{
private const uint SessionId = 3;
private static readonly byte[] PageTemplate = Encoding.UTF8.GetBytes(
$"<html><body data-token=\"{TerminalDataPlane.TokenPlaceholder}\" "
+ $"data-socket=\"{TerminalDataPlane.SocketUrlPlaceholder}\"></body></html>");
private readonly TerminalDataPlane plane = new(new InMemoryTerminalAssetProvider(
new Dictionary<string, TerminalAsset>(StringComparer.Ordinal)
{
[TerminalDataPlane.PagePath] = new("text/html; charset=utf-8", PageTemplate),
["/xterm.js"] = new("text/javascript; charset=utf-8", "console.log(1)"u8.ToArray()),
}));
private readonly CancellationTokenSource lifetime = new();
private Task? server;
/// <inheritdoc />
public async ValueTask DisposeAsync()
{
await lifetime.CancelAsync();
await plane.DisposeAsync();
if (server is not null)
{
try
{
await server;
}
catch (OperationCanceledException)
{
// Expected: the accept loop is stopped by cancelling it.
}
}
lifetime.Dispose();
}
// ---- Serving the page ----
[Fact]
public async Task ThePage_IsServedWithTheTokenAndSocketUrlSubstituted()
{
// Substituted at serve time rather than written into the file, so the token never touches disk
// and never appears in a URL that a log or a browser history could keep.
Start();
using var client = new HttpClient();
var body = await client.GetStringAsync(plane.PageUrl, TestContext.Current.CancellationToken);
body.ShouldContain(plane.Token);
body.ShouldContain(
string.Create(CultureInfo.InvariantCulture, $"ws://127.0.0.1:{plane.Port}/socket"));
body.ShouldNotContain(TerminalDataPlane.TokenPlaceholder);
body.ShouldNotContain(TerminalDataPlane.SocketUrlPlaceholder);
}
[Fact]
public async Task ThePage_IsNotCached()
{
// It carries a connection token.
Start();
using var client = new HttpClient();
using var response = await client.GetAsync(plane.PageUrl, TestContext.Current.CancellationToken);
response.Headers.CacheControl!.NoStore.ShouldBeTrue();
}
[Fact]
public async Task AnUnknownPath_Is404()
{
Start();
using var client = new HttpClient();
using var response = await client.GetAsync(
new Uri($"http://127.0.0.1:{plane.Port}/nope"),
TestContext.Current.CancellationToken);
response.StatusCode.ShouldBe(HttpStatusCode.NotFound);
}
// ---- Attaching ----
[Fact]
public async Task TheRenderer_Attaches()
{
Start();
using var socket = await ConnectAsync();
socket.State.ShouldBe(WebSocketState.Open);
socket.SubProtocol.ShouldBe(TerminalDataPlane.SubProtocol);
await plane.RendererAttached;
}
[Fact]
public async Task AConnectionWithoutTheToken_IsRejected()
{
Start();
await Should.ThrowAsync<WebSocketException>(async () =>
await ConnectAsync(token: null));
}
[Fact]
public async Task AConnectionWithTheWrongToken_IsRejected()
{
Start();
await Should.ThrowAsync<WebSocketException>(async () =>
await ConnectAsync(token: "not-the-token"));
}
[Fact]
public async Task AConnectionFromAnotherOrigin_IsRejected()
{
// The threat this actually addresses: a page open in the user's browser can attempt WebSocket
// connections to loopback ports, and would otherwise reach a terminal.
Start();
await Should.ThrowAsync<WebSocketException>(async () =>
await ConnectAsync(origin: "https://evil.example"));
}
/// <remarks>
/// The truth this replaced: a second valid attach used to be a 409, on the theory that one renderer
/// lives for the whole process. Android's WebView does not honour that theory — its renderer process is
/// routinely killed and the page reloads with a fresh socket — so a second valid attach is now a
/// takeover. This asserts both halves: the newcomer gets the connection, and the displaced socket
/// actually goes rather than lingering as a phantom nothing is reading from.
/// </remarks>
[Fact]
public async Task ASecondRenderer_TakesOver_AndTheFirstSocketIsDropped()
{
Start();
using var first = await ConnectAsync();
first.State.ShouldBe(WebSocketState.Open);
using var second = await ConnectAsync();
second.State.ShouldBe(WebSocketState.Open);
// The first socket was aborted rather than closed gracefully — Abort skips the close handshake
// entirely, so there is no Close frame for this side to see coming. What a receive on it sees
// instead is the connection simply gone, which the client surfaces as an exception rather than as
// a state that quietly flips on its own; nothing here reads from the socket otherwise, so the
// state alone would not move.
var firstBuffer = new byte[16];
await Should.ThrowAsync<Exception>(async () =>
await first.ReceiveAsync(firstBuffer.AsMemory(), TestContext.Current.CancellationToken));
await using var session = new FakeShellSession(bytesToProduce: 64);
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
var run = pump.RunAsync(TestContext.Current.CancellationToken);
var opened = await ReceiveAsync(second);
opened.Opcode.ShouldBe((byte)TerminalServerOpcode.SessionOpened);
var output = await ReceiveAsync(second);
output.Opcode.ShouldBe((byte)TerminalServerOpcode.Output);
output.Payload.Length.ShouldBe(64);
await SendAsync(
second,
(byte)TerminalClientOpcode.Acknowledge,
TerminalFrame.CreateAcknowledgementPayload((uint)output.Payload.Length));
await run;
}
/// <remarks>
/// <para>
/// The other half of the takeover: a renderer process that dies without a close handshake — which is
/// what a killed Android WebView actually does, no FIN, nothing — must not fault the send path. A
/// faulted send would propagate into <see cref="TerminalSessionPump"/>'s flush loop and freeze a live
/// session; see <see cref="TerminalDataPlane.SendAsync"/>'s remark for why. Disposing the client socket
/// abruptly, with no close handshake sent, is the closest this harness gets to that: the server-side
/// socket is left believing itself open until it actually tries to write to it.
/// </para>
/// <para>
/// Driven straight through <see cref="TerminalDataPlane.SendAsync"/> rather than through a pump, because
/// a pump adds nothing here — the point is entirely about the transport's own contract, and a session
/// layered on top would only leave it unclear whether a passing test proved the transport never threw or
/// merely that the frames never happened to need a live socket.
/// </para>
/// </remarks>
[Fact]
public async Task SendAsync_DoesNotThrow_WhenTheAttachedRendererDiedWithoutClosing_AndAFreshAttachStillReceives()
{
Start();
var first = await ConnectAsync();
first.State.ShouldBe(WebSocketState.Open);
first.Dispose();
// Whether this particular send lands on the OS's send buffer before the peer's absence is noticed,
// or fails immediately, is not the point — either way it must not throw.
await Should.NotThrowAsync(async () =>
await plane.SendAsync(
TerminalFrame.Create((byte)TerminalServerOpcode.Output, SessionId, "before"u8.ToArray()),
TestContext.Current.CancellationToken));
using var second = await ConnectAsync();
await Should.NotThrowAsync(async () =>
await plane.SendAsync(
TerminalFrame.Create((byte)TerminalServerOpcode.Output, SessionId, "after"u8.ToArray()),
TestContext.Current.CancellationToken));
var output = await ReceiveAsync(second);
output.Opcode.ShouldBe((byte)TerminalServerOpcode.Output);
Encoding.UTF8.GetString(output.Payload).ShouldBe("after");
}
// ---- Frames ----
[Fact]
public async Task Output_ReachesTheRenderer()
{
Start();
using var socket = await ConnectAsync();
await using var session = new FakeShellSession(bytesToProduce: 128);
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
var run = pump.RunAsync(TestContext.Current.CancellationToken);
// SessionOpened first, then the output.
var opened = await ReceiveAsync(socket);
opened.Opcode.ShouldBe((byte)TerminalServerOpcode.SessionOpened);
opened.SessionId.ShouldBe(SessionId);
var output = await ReceiveAsync(socket);
output.Opcode.ShouldBe((byte)TerminalServerOpcode.Output);
output.Payload.Length.ShouldBe(128);
// Acknowledge it, exactly as the page does from term.write's callback.
await SendAsync(
socket,
(byte)TerminalClientOpcode.Acknowledge,
TerminalFrame.CreateAcknowledgementPayload((uint)output.Payload.Length));
await run;
}
[Fact]
public async Task Input_ReachesTheRemote()
{
Start();
using var socket = await ConnectAsync();
await using var session = new FakeShellSession();
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
await SendAsync(socket, (byte)TerminalClientOpcode.Input, "whoami\r"u8.ToArray());
await WaitUntilAsync(() => session.Written.Length > 0);
Encoding.UTF8.GetString(session.Written).ShouldBe("whoami\r");
}
[Fact]
public async Task AResize_ReachesTheRemote()
{
Start();
using var socket = await ConnectAsync();
await using var session = new FakeShellSession();
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
await SendAsync(
socket,
(byte)TerminalClientOpcode.Resize,
TerminalFrame.CreateResizePayload(new TerminalSize(132, 43, 1320, 1075)));
await WaitUntilAsync(() => session.ResizeCount > 0);
session.LastResize.ShouldBe(new TerminalSize(132, 43, 1320, 1075));
}
[Fact]
public async Task AnAcknowledgement_ReturnsCredit()
{
Start();
using var socket = await ConnectAsync();
await using var session = new FakeShellSession();
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
pump.Credits.TryReserve(1024);
pump.Credits.Outstanding.ShouldBe(1024);
await SendAsync(
socket,
(byte)TerminalClientOpcode.Acknowledge,
TerminalFrame.CreateAcknowledgementPayload(1024));
await WaitUntilAsync(() => pump.Credits.Outstanding == 0);
}
/// <remarks>
/// The point of this one is the <em>absence</em> of a registered session. Every other client frame is
/// about a terminal and is dropped once its session has gone; a text-size chord is about the person
/// reading, and the page sends whichever id it had to hand — often one whose shell has just ended,
/// which is exactly when somebody may be squinting at the message it left behind. Dispatching this
/// opcode before the session lookup is what makes that work.
/// </remarks>
[Fact]
public async Task AFontSizeStep_IsHeardWithNoSessionRegistered()
{
Start();
using var socket = await ConnectAsync();
var steps = new List<int>();
plane.FontSizeStepRequested += (_, e) => steps.Add(e.Step);
await SendAsync(
socket,
(byte)TerminalClientOpcode.FontSizeStep,
TerminalFrame.CreateFontSizeStepPayload(-1),
sessionId: 0);
await WaitUntilAsync(() => steps.Count > 0);
steps[0].ShouldBe(-1);
}
[Fact]
public async Task AFrameForAnUnregisteredSession_IsIgnored()
{
// Ordinary during teardown: the page can still have frames in flight for a session that just
// ended. Dropping them must not disturb anything else.
Start();
using var socket = await ConnectAsync();
await using var session = new FakeShellSession();
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
// A session id that is never registered. Using the registered one and relying on ordering
// would be a race: frames are dispatched on the receive loop, so the orphan can land after
// registration and legitimately be delivered.
await SendAsync(socket, (byte)TerminalClientOpcode.Input, "orphan"u8.ToArray(), sessionId: 999);
await SendAsync(socket, (byte)TerminalClientOpcode.Input, "real"u8.ToArray());
await WaitUntilAsync(() => session.Written.Length > 0);
Encoding.UTF8.GetString(session.Written).ShouldBe("real");
}
[Fact]
public async Task AMalformedFrame_IsIgnored()
{
Start();
using var socket = await ConnectAsync();
// Shorter than the header.
await socket.SendAsync(
new byte[] { 1, 2 },
WebSocketMessageType.Binary,
endOfMessage: true,
TestContext.Current.CancellationToken);
await using var session = new FakeShellSession();
await using var pump = CreatePump(session);
plane.Register(SessionId, pump);
await SendAsync(socket, (byte)TerminalClientOpcode.Input, "still here"u8.ToArray());
await WaitUntilAsync(() => session.Written.Length > 0);
Encoding.UTF8.GetString(session.Written).ShouldBe("still here");
}
// ---- Helpers ----
private void Start() => server = plane.RunAsync(lifetime.Token);
private TerminalSessionPump CreatePump(FakeShellSession session) =>
new(
SessionId,
session,
plane,
TimeProvider.System,
new TerminalPumpOptions { FlushInterval = TimeSpan.FromMilliseconds(10) });
/// <summary>
/// Opens a renderer's socket and returns once the plane is actually holding it.
/// </summary>
/// <remarks>
/// <para>
/// <b>Connected and attached are two different moments, and the gap between them is where this used to
/// flake.</b> <c>ClientWebSocket.ConnectAsync</c> completes on the 101, which
/// <see cref="TerminalDataPlane.UpgradeAsync"/> writes before it has a <see cref="WebSocket"/> to
/// attach — it builds one from the stream and swaps it in a few instructions later, on the accept
/// thread. A frame sent in between is dropped, by design rather than by accident: the transport has
/// nowhere to put a frame for a renderer that is not there, and queueing it is the unbounded growth the
/// credit window exists to prevent.
/// </para>
/// <para>
/// So a test that connected and immediately expected a frame was racing that window on every run. It
/// lost one on CI — <c>Output_ReachesTheRenderer</c> read the output frame first and asked why it was
/// not the session's opening one, the opening one having been dropped a moment earlier — which is a
/// scheduling accident on a loaded machine and says nothing whatever about the transport.
/// </para>
/// <para>
/// Production does not race it and needs no change: everything that opens a session waits on
/// <c>TerminalWorkspace.WaitForRendererAsync</c> first, and that resolves from the same few lines this
/// event is raised from.
/// </para>
/// <para>
/// Subscribed before the connection rather than after it, because the event is raised on the accept
/// thread and can be over before <c>ConnectAsync</c> has returned here. Bounded, so that a socket that
/// never attaches fails this helper rather than hanging the suite in a later receive.
/// </para>
/// </remarks>
private async Task<ClientWebSocket> ConnectAsync(
string? token = "",
string? origin = null)
{
var socket = new ClientWebSocket();
socket.Options.AddSubProtocol(TerminalDataPlane.SubProtocol);
if (token is not null)
{
socket.Options.AddSubProtocol($"token.{(token.Length == 0 ? plane.Token : token)}");
}
socket.Options.SetRequestHeader(
"Origin",
origin ?? string.Create(CultureInfo.InvariantCulture, $"http://127.0.0.1:{plane.Port}"));
var attached = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
void OnAttached(object? sender, EventArgs e) => attached.TrySetResult();
plane.SocketAttached += OnAttached;
try
{
await socket.ConnectAsync(
new Uri($"ws://127.0.0.1:{plane.Port}{TerminalDataPlane.SocketPath}"),
TestContext.Current.CancellationToken);
await attached.Task.WaitAsync(
TimeSpan.FromSeconds(5),
TestContext.Current.CancellationToken);
}
catch
{
socket.Dispose();
throw;
}
finally
{
plane.SocketAttached -= OnAttached;
}
return socket;
}
private static async Task SendAsync(
ClientWebSocket socket,
byte opcode,
byte[] payload,
uint sessionId = SessionId) =>
await socket.SendAsync(
TerminalFrame.Create(opcode, sessionId, payload),
WebSocketMessageType.Binary,
endOfMessage: true,
TestContext.Current.CancellationToken);
private static async Task<(byte Opcode, uint SessionId, byte[] Payload)> ReceiveAsync(
ClientWebSocket socket)
{
var buffer = new byte[64 * 1024];
var result = await socket.ReceiveAsync(
buffer.AsMemory(),
TestContext.Current.CancellationToken);
TerminalFrame.TryRead(buffer.AsSpan(0, result.Count), out var opcode, out var sessionId, out var payload)
.ShouldBeTrue();
return (opcode, sessionId, payload.ToArray());
}
/// <remarks>
/// Polls rather than awaiting a signal: inbound frames are dispatched on the transport's receive
/// loop, which has no completion for the caller to await. The bound keeps a genuine failure a
/// failure rather than a hang.
/// </remarks>
private static async Task WaitUntilAsync(Func<bool> condition)
{
var deadline = TimeProvider.System.GetUtcNow() + TimeSpan.FromSeconds(5);
while (TimeProvider.System.GetUtcNow() < deadline)
{
if (condition())
{
return;
}
await Task.Delay(10, TestContext.Current.CancellationToken);
}
throw new TimeoutException("The expected state was not reached within 5 seconds.");
}
}