lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/Drivers/DriverHostActorPrimaryRoleSourceTests.cs

using Akka.Actor;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Redundancy;
using ZB.MOM.WW.OtOpcUa.Commons.Types;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
using ZB.MOM.WW.OtOpcUa.Runtime.Drivers;
using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;

namespace ZB.MOM.WW.OtOpcUa.Runtime.Tests.Drivers;

/// <summary>
///     Review R1 m2 (Gitea #597) — the Primary data-plane verdict published to <see cref="IDriverPrimaryRoleSource"/>
///     (read by the native-ack gate and the Sparkplug primary-host claim) mirrors the host's own live gate from the
///     moment the host starts, not only from the first redundancy snapshot.
/// </summary>
/// <remarks>
///     <c>RedundancyRoleView</c> is seeded with the single-node verdict (allow). Before this fix nothing published to
///     it until a snapshot arrived, so on a pair both nodes accepted a native ack through the whole boot window while
///     <c>DriverHostActor</c> — which evaluates the driver member count live — denied the upstream route on the
///     non-Primary. Assertions are on what was PUBLISHED: the seed already reads <c>true</c>, so a current-value
///     assertion of the single-node case would pass with no publish at all.
/// </remarks>
public sealed class DriverHostActorPrimaryRoleSourceTests : RuntimeActorTestBase
{
    private static readonly NodeId TestNode = NodeId.Parse("driver-primary-source-test");
    private static readonly TimeSpan Timeout = TimeSpan.FromSeconds(5);

    /// <summary>On a pair, an unknown role publishes DENY at start — before any snapshot. The later Primary snapshot
    /// is the positive control: the source is wired, and the deny was the verdict, not a missing publish.</summary>
    [Fact]
    public void A_paired_host_publishes_deny_before_the_first_snapshot()
    {
        var source = new RecordingPrimaryRoleSource();
        var host = SpawnHost(source, () => 2);

        AwaitAssert(() => source.Published.ShouldBe([false]), duration: Timeout);

        host.Tell(Snapshot(RedundancyRole.Primary));
        AwaitAssert(() => source.Published.ShouldBe([false, true]), duration: Timeout);
    }

    /// <summary>A single-driver node keeps the allow posture — it is published, not merely seeded.</summary>
    [Fact]
    public void A_single_node_host_publishes_allow_at_start()
    {
        var source = new RecordingPrimaryRoleSource();
        SpawnHost(source, () => 1);

        AwaitAssert(() => source.Published.ShouldBe([true]), duration: Timeout);
    }

    /// <summary>A driver peer coming Up while the role is still unknown flips the published verdict to deny, with no
    /// snapshot involved — the membership re-publish path.</summary>
    [Fact]
    public void A_peer_joining_before_any_snapshot_flips_the_published_verdict_to_deny()
    {
        var source = new RecordingPrimaryRoleSource();
        var members = 1;
        var host = SpawnHost(source, () => Volatile.Read(ref members));
        AwaitAssert(() => source.Published.ShouldBe([true]), duration: Timeout);

        Volatile.Write(ref members, 2);
        host.Tell(DriverHostActor.RepublishPrimaryVerdict.Instance);

        AwaitAssert(() => source.Published.ShouldBe([true, false]), duration: Timeout);
    }

    /// <summary>
    ///     Review R6 MINOR-3 — the same flip driven by a real cluster MEMBER EVENT rather than a direct
    ///     <see cref="DriverHostActor.RepublishPrimaryVerdict"/> tell, so it fails if the host's
    ///     <c>Cluster.Subscribe(… IMemberEvent)</c> or its <c>IMemberEvent</c> handler is deleted. The event is published
    ///     on the ActorSystem EventStream, which is exactly how the cluster's domain-event publisher delivers it to a
    ///     <c>Cluster.Subscribe</c> subscriber — and to nothing else. Re-published inside the wait because the
    ///     subscription is registered asynchronously by the publisher actor after <c>PreStart</c>.
    /// </summary>
    [Fact]
    public void A_cluster_member_event_flips_the_published_verdict_without_a_direct_republish()
    {
        var source = new RecordingPrimaryRoleSource();
        var members = 1;
        SpawnHost(source, () => Volatile.Read(ref members));
        AwaitAssert(() => source.Published.ShouldBe([true]), duration: Timeout);

        Volatile.Write(ref members, 2);
        var memberUp = new Akka.Cluster.ClusterEvent.MemberUp(Akka.Cluster.Cluster.Get(Sys).SelfMember);
        AwaitAssert(() =>
        {
            Sys.EventStream.Publish(memberUp);
            source.Published.ShouldBe([true, false]);
        }, duration: Timeout, interval: TimeSpan.FromMilliseconds(100));
    }

    private IActorRef SpawnHost(IDriverPrimaryRoleSource source, Func<int> driverMemberCount) =>
        Sys.ActorOf(DriverHostActor.Props(
            NewInMemoryDbFactory(),
            TestNode,
            ackRouter: null,
            driverMemberCountProvider: driverMemberCount,
            primaryRoleSource: source));

    private static RedundancyStateChanged Snapshot(RedundancyRole role) =>
        new(
            [
                new NodeRedundancyState(TestNode, role,
                    IsClusterLeader: role == RedundancyRole.Primary,
                    IsDriverPrimary: role == RedundancyRole.Primary,
                    AsOfUtc: DateTime.UtcNow),
            ],
            CorrelationId.NewId());

    /// <summary>Remembers every published verdict, so tests assert on the actor's action, not on the seed.</summary>
    private sealed class RecordingPrimaryRoleSource : IDriverPrimaryRoleSource
    {
        private readonly List<bool> _published = [];
        private readonly Lock _gate = new();

        /// <summary>Every value published so far, in order.</summary>
        public IReadOnlyList<bool> Published
        {
            get { lock (_gate) return _published.ToArray(); }
        }

        public bool ShouldActAsPrimary
        {
            get { lock (_gate) return _published.Count == 0 || _published[^1]; }
        }

        public void PublishPrimaryRole(bool shouldActAsPrimary)
        {
            lock (_gate) _published.Add(shouldActAsPrimary);
        }
    }
}