DodoSSH/tests/DodoSSH.SystemTests/M1VerticalSliceTests.cs

using System.Text;
using DodoSSH.Client.Domain;
using DodoSSH.Client.Session;
using DodoSSH.Client.Ssh;
using DodoSSH.Client.Storage;
using DodoSSH.Contracts;
using DodoSSH.Crypto;

namespace DodoSSH.SystemTests;

/// <summary>
/// M1's definition of done: sign in, enroll, unlock, create a host, sync, read it on a second machine,
/// and open a shell on it.
/// </summary>
/// <remarks>
/// <para>
/// Nothing is stubbed. A real Keycloak issues the tokens and signs the key binding, a real API stores the
/// ciphertext in a real PostgreSQL, real DSH1 crypto seals and opens it, and a real <c>sshd</c> answers at
/// the end. Every other suite substitutes at least one of those, and each substitution is a place where a
/// misreading of the protocol can be consistent on both sides and still wrong in production — which is
/// exactly what this found the first time it ran.
/// </para>
/// <para>
/// One test rather than several, because the steps are not independent: you cannot unlock without having
/// enrolled, and enrollment happens once per account. Splitting them would mean sharing mutable state
/// between tests or repeating a minute of setup per assertion.
/// </para>
/// </remarks>
public sealed class M1VerticalSliceTests(DevStack stack) : IClassFixture<DevStack>, IAsyncDisposable
{
    private const string Passphrase = "an end to end passphrase";

    /// <remarks>
    /// 64 MiB is the floor <c>EnrollmentLimits</c> enforces, and this suite has to respect it — the other
    /// client suites use 8 MiB because their in-memory servers have no policy, and a real one rejects that
    /// outright. Worth knowing rather than discovering: the reduction those suites take for speed is only
    /// available because nothing is checking, and the difference is a 400 rather than a slow test.
    /// </remarks>
    private static readonly Argon2Profile ServerFloorProfile =
        Argon2Profile.FromStoredParameters(memoryKibibytes: 64 * 1024, passes: 3, parallelism: 1);

    private readonly List<string> directories = [];

    /// <inheritdoc />
    public ValueTask DisposeAsync()
    {
        foreach (var directory in directories.Where(Directory.Exists))
        {
            Directory.Delete(directory, recursive: true);
        }

        return ValueTask.CompletedTask;
    }

    [Fact]
    public async Task TheWholeSlice()
    {
        // The realm file's own account, deliberately — see DevStack.RealmUser. A runtime-minted one hid a
        // sign-in failure that only the committed configuration had.
        var account = DevStack.RealmUser;
        var browser = new ScriptedBrowser(account.Username, account.Password);

        using var connection = await ServerConnection
            .SignInAsync(stack.ApiBaseUrl, browser, TimeProvider.System, Token);

        AssertDiscoveredFromTheServer(connection);

        using var laptopCache = await OpenCacheAsync();
        await EnrollAsync(connection, laptopCache, browser);

        var laptop = await UnlockAsync(laptopCache);
        await using var laptopSession = laptop;

        var host = BuildHost();
        var entityId = await laptop.Hosts.CreateAsync(laptop.ActiveVaultId, host, Token);

        var pushed = await laptop.SyncAsync(connection.Sync, Token);
        pushed.Pushed.ShouldBe(1);
        pushed.NeedsAttention.ShouldBeFalse();

        await AssertTheServerCannotSeeTheAddressAsync(connection, entityId);

        var seen = await ReadOnASecondMachineAsync(connection, host, entityId);

        await AssertUnlocksOfflineAsync(laptopCache);

        await OpenAShellAsync(seen);
    }

    // ---- Steps ----

    /// <remarks>
    /// The user typed one server URL. Everything about the identity provider — the authority, the client
    /// id, the scopes — came back from the server, which is the whole onboarding story.
    /// </remarks>
    private void AssertDiscoveredFromTheServer(ServerConnection connection)
    {
        connection.Configuration.Oidc.Authority.ToString()
            .ShouldStartWith(stack.Authority.ToString());

        connection.Configuration.Oidc.ClientId.ShouldBe("dodossh-desktop");

        // Server:PublicBaseUrl, which is what a client behind a proxy would follow. Worth asserting
        // because it is configuration the server states about itself and nothing else would notice it
        // being wrong.
        connection.Configuration.ApiBaseUrl.ShouldBe(stack.ApiBaseUrl);

        connection.Meta.SyncProtocolVersion.ShouldBe(1);
        connection.Meta.CryptoSpecVersion.ShouldBe(1);
    }

    private async Task EnrollAsync(
        ServerConnection connection,
        ClientCacheFactory caches,
        ScriptedBrowser browser)
    {
        var provisioner = new AccountProvisioner(
            connection.Account, connection.KeyBinding, caches, TimeProvider.System, ServerFloorProfile);

        var before = await provisioner.RefreshAsync(ServerUrl, Token);
        before.Status.ShouldBe(ProvisionStatus.EnrollmentRequired);

        var enrolled = await provisioner.EnrollAsync(
            ServerUrl, Passphrase, "e2e-laptop", "Personal", Token);

        enrolled.Status.ShouldBe(ProvisionStatus.Ready);
        enrolled.RecoveryCode.ShouldNotBeNullOrWhiteSpace();

        // Two sign-ins, not one. The second is the identity-provider key binding: an authorization whose
        // nonce is the key statement's hash, whose ID token the server verified against Keycloak's JWKS
        // before accepting the key. That is what stops a compromised DodoSSH server fabricating a key for
        // someone who never enrolled — see ADR 0001 — and it is invisible unless something counts.
        browser.SignInCount.ShouldBe(
            2, "enrollment must obtain an identity-provider signature over the published key");
    }

    /// <remarks>
    /// Asserted against what the server hands back, not against the local mirror. With relay off the
    /// address stays inside the ciphertext; ADR 0004 is the only reason it would ever be otherwise.
    /// </remarks>
    private static async Task AssertTheServerCannotSeeTheAddressAsync(
        ServerConnection connection,
        Guid entityId)
    {
        var vaultId = (await connection.Account.GetMeAsync(Token)).Vaults.Single().VaultId;

        var page = await connection.Sync.SyncPullAsync(
            vaultId, new SyncPullRequest(null, 100, [SyncEntityType.Host]), Token);

        var change = page.Changes.Single(c => c.EntityId == entityId);

        change.PlaintextFields.ShouldNotBeNull();
        change.PlaintextFields.RelayEnabled.ShouldBeFalse();
        change.PlaintextFields.Hostname.ShouldBeNull("the address must not leave the payload");
        change.PlaintextFields.Port.ShouldBeNull();

        // What it does hold is opaque, and it carries its data key as the specification requires.
        change.Payload.ShouldNotBeNull();
        change.Payload.WrappedDataKey.ShouldNotBeEmpty();
        change.Payload.DataKeyId.ShouldNotBe(Guid.Empty);
    }

    private async Task<HostSecret> ReadOnASecondMachineAsync(
        ServerConnection connection,
        HostSecret expected,
        Guid entityId)
    {
        using var desktopCache = await OpenCacheAsync();

        var provisioner = new AccountProvisioner(
            connection.Account, connection.KeyBinding, desktopCache, TimeProvider.System, ServerFloorProfile);

        // Already enrolled, so this only caches what an offline unlock will need.
        (await provisioner.RefreshAsync(ServerUrl, Token)).Status
            .ShouldBe(ProvisionStatus.Ready);

        var desktop = await UnlockAsync(desktopCache);
        await using var session = desktop;

        var pulled = await desktop.SyncAsync(connection.Sync, Token);
        pulled.Pulled.ShouldBe(1);

        var listing = await desktop.Hosts.ListAsync(desktop.ActiveVaultId, Token);
        var seen = listing.Hosts.ShouldHaveSingleItem();

        seen.EntityId.ShouldBe(entityId);
        seen.HasUnsyncedChanges.ShouldBeFalse();

        // The decrypted host survived a round trip through a server that could read none of it — including
        // the directives, which merge per name and therefore have to come back in canonical form.
        seen.Host.ShouldBe(expected);

        return seen.Host;
    }

    private static async Task AssertUnlocksOfflineAsync(ClientCacheFactory caches)
    {
        // Nothing here touches the network: the salt, the parameters and the wrapped bundle are local.
        var offline = await new SessionOpener(caches, TimeProvider.System).UnlockAsync(Passphrase, Token);

        offline.IsUnlocked.ShouldBeTrue(offline.Message);
        await offline.Session!.DisposeAsync();
    }

    /// <remarks>
    /// Goes through the real trust-on-first-use path rather than around it. An unknown host key throws, the
    /// caller pins it and retries — which is what the interface does, and the only way to prove the
    /// fingerprint a user would be shown is the one the server actually presented.
    /// </remarks>
    private static async Task OpenAShellAsync(HostSecret host)
    {
        var knownHosts = new InMemoryKnownHostStore();
        var factory = new SshNetConnectionFactory(knownHosts);

        var request = new SshConnectionRequest(
            host.Hostname, host.Port, host.Username!, new SshPasswordCredential(DevStack.SshPassword));

        try
        {
            await using var first = await factory.ConnectAsync(request, Token);
            Assert.Fail("An unseen host key must not be trusted silently.");
        }
        catch (SshHostKeyUnknownException exception)
        {
            exception.Presentation.Fingerprint.ShouldStartWith("SHA256:");
            await knownHosts.TrustAsync(exception.Presentation, Token);
        }

        await using var connection = await factory.ConnectAsync(request, Token);
        await using var shell = await connection.OpenShellAsync(TerminalSize.Default, Token);

        await shell.WriteTextAsync("echo dodossh-e2e-ok\n", Token);

        var output = await ReadUntilEchoedAsync(shell, "dodossh-e2e-ok");

        output.ShouldContain("dodossh-e2e-ok");
    }

    // ---- Helpers ----

    private static CancellationToken Token => TestContext.Current.CancellationToken;

    /// <remarks>
    /// The provisioner takes the URL as a string because it is also the cache's identity — the value an
    /// offline unlock compares against to refuse a cache belonging to another server.
    /// </remarks>
    private string ServerUrl => stack.ApiBaseUrl.ToString();

    private HostSecret BuildHost() =>
        new()
        {
            Label = "e2e-target",
            Hostname = stack.SshHostname,
            Port = stack.SshHostPort,
            Username = DevStack.SshUsername,
            Notes = "created by the end-to-end slice",
            Options = HostOptions.Create([new HostOption("ServerAliveInterval", "30")]),
        };

    private async Task<ClientCacheFactory> OpenCacheAsync()
    {
        var directory = Path.Combine(Path.GetTempPath(), $"dodossh-e2e-{Guid.CreateVersion7():N}");
        Directory.CreateDirectory(directory);
        directories.Add(directory);

        var factory = ClientCacheFactory.ForFile(new ClientPaths(directory).CacheFile);

        try
        {
            await factory.MigrateAsync(Token);
            return factory;
        }
        catch
        {
            factory.Dispose();
            throw;
        }
    }

    private static async Task<VaultSession> UnlockAsync(ClientCacheFactory caches)
    {
        var outcome = await new SessionOpener(caches, TimeProvider.System).UnlockAsync(Passphrase, Token);

        outcome.IsUnlocked.ShouldBeTrue(outcome.Message);
        return outcome.Session!;
    }

    /// <remarks>
    /// Waits for the marker twice — once as the shell echoes the typed command, once as its output — rather
    /// than for a fixed time. The login banner arrives first and its length is not something this test
    /// should have to know.
    /// </remarks>
    private static async Task<string> ReadUntilEchoedAsync(ISshShellSession shell, string marker)
    {
        var text = new StringBuilder();
        var buffer = new byte[8192];

        using var deadline = CancellationTokenSource.CreateLinkedTokenSource(Token);
        deadline.CancelAfter(TimeSpan.FromSeconds(30));

        while (!deadline.IsCancellationRequested)
        {
            var read = await shell.ReadAsync(buffer, deadline.Token);

            if (read == 0)
            {
                break;
            }

            text.Append(Encoding.UTF8.GetString(buffer, 0, read));

            if (Occurrences(text.ToString(), marker) >= 2)
            {
                break;
            }
        }

        return text.ToString();
    }

    private static int Occurrences(string text, string marker)
    {
        var count = 0;
        var index = 0;

        while ((index = text.IndexOf(marker, index, StringComparison.Ordinal)) >= 0)
        {
            count++;
            index += marker.Length;
        }

        return count;
    }
}