lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/Health/PeerProbeSupervisorTests.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.Runtime.Health;
using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;

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

/// <summary>
/// Tests for <see cref="PeerProbeSupervisor"/>: it maintains exactly one peer-OPC-UA-probe child
/// per OTHER, non-Detached driver node named in the latest <see cref="RedundancyStateChanged"/>
/// snapshot, spawning/stopping children as the topology changes.
/// </summary>
public sealed class PeerProbeSupervisorTests : RuntimeActorTestBase
{
    private static readonly NodeId Local = NodeId.Parse("local:4053");
    private static readonly NodeId Peer = NodeId.Parse("peer:4053");
    private static readonly NodeId Adm = NodeId.Parse("adm:4053");

    /// <summary>No-op child actor stub so we can count children without real TCP probes.</summary>
    private sealed class NoopActor : ReceiveActor { }

    private static Props NoopProps() => Akka.Actor.Props.Create(() => new NoopActor());

    /// <summary>
    /// No-op child stub that records its own <see cref="ActorBase.Self"/> into a shared list on
    /// start, in spawn order — lets a test grab a specific (e.g. the FIRST, old-generation) child
    /// ref so it can deliver a synthetic <see cref="Terminated"/> for it.
    /// </summary>
    private sealed class RecordingNoopActor : ReceiveActor
    {
        public RecordingNoopActor(List<IActorRef> spawned) => spawned.Add(Self);
    }

    private static Props RecordingProps(List<IActorRef> spawned) =>
        Akka.Actor.Props.Create(() => new RecordingNoopActor(spawned));

    private static NodeRedundancyState State(NodeId id, RedundancyRole role) =>
        new(id, role, IsClusterLeader: false, IsDriverPrimary: false, DateTime.UtcNow);

    private static RedundancyStateChanged Snapshot(params NodeRedundancyState[] nodes) =>
        new(nodes, CorrelationId.NewId());

    /// <summary>Verifies one child is spawned per non-self, non-Detached peer — self and Detached
    /// nodes are excluded.</summary>
    [Fact]
    public void Spawns_one_child_per_non_self_non_detached_peer()
    {
        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));

        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary),
            State(Adm, RedundancyRole.Detached)));

        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
    }

    /// <summary>Verifies the child for a departed peer is stopped when the next snapshot omits it.</summary>
    [Fact]
    public void Stops_child_for_departed_peer()
    {
        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));

        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);

        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(0),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
    }

    /// <summary>Verifies a single-node snapshot (just the local node) spawns no children — the local node
    /// is never its own probe peer. Established against a following two-node snapshot as a positive
    /// control, so the count of 1 (rather than 2) is what carries the "no local child" claim.</summary>
    [Fact]
    public void Single_node_snapshot_spawns_no_children()
    {
        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));

        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));

        // POSITIVE CONTROL (#501). This is an ABSENCE assertion, and ChildCount is 0 before the snapshot
        // above has been processed at all — so asserting it directly passes at t=0 and proves nothing
        // (AwaitAssert returns on its first success, spending none of its duration). Unlike the other
        // ChildCount.ShouldBe(0) waits in this class, there is no preceding ShouldBe(1) to make it a
        // transition.
        //
        // Follow with a snapshot that DOES spawn exactly one child. The supervisor processes its mailbox
        // in order, so once the count reaches 1 the single-node snapshot has provably been handled — and
        // had it spawned a child for the local node, the count would be 2.
        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary)));

        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
    }

    /// <summary>Verifies a previously-removed peer is respawned when it re-appears, without an
    /// "actor name not unique" collision on the sanitized child name.</summary>
    [Fact]
    public void Re_adding_a_previously_removed_peer_respawns_it()
    {
        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));

        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);

        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(0),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);

        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
    }

    /// <summary>Locks in the stale-Terminated guard: when an OLD (already-replaced) child's
    /// <see cref="Terminated"/> for a peer arrives AFTER a NEW child for the SAME peer was spawned,
    /// the fresh child must NOT be evicted (removal is keyed by current-child ref-equality, not by
    /// peer key). Without this guard a late stale Terminated would silently drop a live probe.</summary>
    [Fact]
    public void Stale_terminated_for_old_child_does_not_evict_fresh_peer_child()
    {
        var spawned = new List<IActorRef>();
        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
            PeerProbeSupervisor.PropsForTests(Local, _ => RecordingProps(spawned)));

        // First add of the peer -> child #0 (the OLD ref).
        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
        AwaitAssert(() => spawned.Count.ShouldBe(1), duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
        var oldRef = spawned[0];

        // Drop the peer -> child #0 stopped, ChildCount back to 0.
        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(0),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);

        // Re-add the SAME peer -> a NEW child #1 (the FRESH ref) is spawned.
        sup.Tell(Snapshot(
            State(Local, RedundancyRole.Primary),
            State(Peer, RedundancyRole.Secondary)));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
        AwaitAssert(() => spawned.Count.ShouldBe(2), duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);

        // Now deliver a STALE Terminated for the OLD ref. The current child for Peer is the fresh
        // child #1, so ref-equality finds no match and the supervisor must leave ChildCount at 1.
        sup.Tell(new Terminated(oldRef, existenceConfirmed: true, addressTerminated: false));
        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
            duration: PresenceBudget, cancellationToken: TestContext.Current.CancellationToken);
    }
}