test(site-runtime): pin #36 — reset-aware handshake holds the batch until the reset echo lands

Claude-Session: https://claude.ai/code/session_01XPsuy2ZZ5Gbyfpt8PrK5BV

tests/ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests/Actors/HandshakeResetEchoTests.cs

@@ -0,0 +1,166 @@
+using Akka.Actor;
+using Akka.TestKit;
+using Akka.TestKit.Xunit2;
+using Microsoft.Extensions.Logging.Abstractions;
+using System.Text.Json;
+using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Protocol;
+using ZB.MOM.WW.ScadaBridge.Commons.Messages.DataConnection;
+using ZB.MOM.WW.ScadaBridge.Commons.Types;
+using ZB.MOM.WW.ScadaBridge.Commons.Types.Flattening;
+using ZB.MOM.WW.ScadaBridge.SiteRuntime.Actors;
+using ZB.MOM.WW.ScadaBridge.SiteRuntime.Persistence;
+using ZB.MOM.WW.ScadaBridge.SiteRuntime.Scripts;
+using ZB.MOM.WW.ScadaBridge.TestSupport;
+
+namespace ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests.Actors;
+
+/// <summary>
+/// Gitea #36 end-to-end over the REAL <see cref="InstanceActor"/> waiter and DCL ingest path:
+/// the cache still holds the previous run's <c>CompleteFlag = True</c>, the script's reset
+/// write has NOT echoed back yet. The legacy overload fast-paths on the stale value (the
+/// defect, pinned as documentation); the reset-aware overload holds the batch + trigger until
+/// the reset echo lands, then matches only on the device's fresh <c>True</c>.
+/// </summary>
+public class HandshakeResetEchoTests : TestKit, IDisposable
+{
+    private const string Conn = "PLC";
+    private const string TriggerTag = "ns=3;s=MoveOutFlag";
+    private const string CompleteTag = "ns=3;s=MoveOutCompleteFlag";
+    private const string BatchTag = "ns=3;s=MoveOutBatchID";
+
+    private readonly SiteStorageService _storage;
+    private readonly ScriptCompilationService _compilationService;
+    private readonly SharedScriptLibrary _sharedScriptLibrary;
+    private readonly TestLocalDb _localDb;
+
+    public HandshakeResetEchoTests()
+    {
+        _localDb = TestLocalDb.CreateTemp("handshake-reset-echo");
+        _storage = new SiteStorageService(_localDb.Db, NullLogger<SiteStorageService>.Instance);
+        _storage.InitializeAsync().GetAwaiter().GetResult();
+        _compilationService = new ScriptCompilationService(NullLogger<ScriptCompilationService>.Instance);
+        _sharedScriptLibrary = new SharedScriptLibrary(_compilationService, NullLogger<SharedScriptLibrary>.Instance);
+    }
+
+    void IDisposable.Dispose()
+    {
+        // TestKit teardown first, so no in-flight actor can reach a disposed ILocalDb;
+        // then dispose the database before deleting — the master connection anchors the WAL.
+        Shutdown();
+        var path = _localDb.Path;
+        _localDb.Dispose();
+        TestLocalDb.DeleteFiles(path);
+    }
+
+    private static FlattenedConfiguration Config() => new()
+    {
+        InstanceUniqueName = "Z28061",
+        Attributes =
+        [
+            new ResolvedAttribute { CanonicalName = "MoveOutFlag", Value = "false", DataType = "Boolean", DataSourceReference = TriggerTag, BoundDataConnectionName = Conn },
+            new ResolvedAttribute { CanonicalName = "MoveOutCompleteFlag", Value = "false", DataType = "Boolean", DataSourceReference = CompleteTag, BoundDataConnectionName = Conn },
+            new ResolvedAttribute { CanonicalName = "MoveOutBatchID", Value = "0", DataType = "Int32", DataSourceReference = BatchTag, BoundDataConnectionName = Conn },
+        ]
+    };
+
+    private (IActorRef Actor, TestProbe Dcl, ScriptRuntimeContext Ctx) Boot()
+    {
+        var dcl = CreateTestProbe();
+        var actor = ActorOf(Props.Create(() => new InstanceActor(
+            "Z28061", JsonSerializer.Serialize(Config()), _storage, _compilationService, _sharedScriptLibrary,
+            null, new SiteRuntimeOptions(), NullLogger<InstanceActor>.Instance, dcl.Ref)));
+        dcl.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(5));
+
+        // The previous run's completion is still in the cache: codec "True", exactly what the
+        // response wait targets.
+        actor.Tell(new TagValueUpdate(Conn, CompleteTag, true, QualityCode.Good, DateTimeOffset.UtcNow));
+
+        var ctx = new ScriptRuntimeContext(
+            actor, _sharedScriptLibrary, currentCallDepth: 0, maxCallDepth: 10,
+            askTimeout: TimeSpan.FromSeconds(5), instanceName: "Z28061", logger: NullLogger.Instance);
+        return (actor, dcl, ctx);
+    }
+
+    private static IReadOnlyDictionary<string, string?> Values(int batchId)
+        => new Dictionary<string, string?> { ["MoveOutBatchID"] = AttributeValueCodec.Encode(batchId) };
+
+    /// <summary>The defect, as documentation: the legacy overload answers from the stale cache.</summary>
+    [Fact]
+    public async Task LegacyOverload_FastPathsOnThePreviousRunsCachedTrue()
+    {
+        var (_, dcl, ctx) = Boot();
+
+        var call = ctx.WriteBatchAndWait(
+            Values(28950), "MoveOutFlag", AttributeValueCodec.Encode(true),
+            "MoveOutCompleteFlag", AttributeValueCodec.Encode(true), TimeSpan.FromSeconds(5));
+
+        var batch = dcl.ExpectMsg<WriteTagBatchRequest>(TimeSpan.FromSeconds(5));
+        dcl.Reply(new WriteTagBatchResponse(batch.CorrelationId, true, null, DateTimeOffset.UtcNow));
+
+        // No device update at all — and the wait still "matches".
+        Assert.True(await call);
+    }
+
+    [Fact]
+    public async Task ResetAwareOverload_HoldsTheBatchUntilTheResetEchoes_ThenMatchesTheFreshTrue()
+    {
+        var (actor, dcl, ctx) = Boot();
+
+        var call = ctx.WriteBatchResetAndWait(
+            Values(28950), "MoveOutFlag", AttributeValueCodec.Encode(true),
+            "MoveOutCompleteFlag", AttributeValueCodec.Encode(true), TimeSpan.FromSeconds(10),
+            "MoveOutCompleteFlag", AttributeValueCodec.Encode(false), TimeSpan.FromSeconds(10));
+
+        // Leg 1 reaches the device as a plain tag write; the DCL acks it but the device has
+        // not echoed anything yet.
+        var reset = dcl.ExpectMsg<WriteTagRequest>(TimeSpan.FromSeconds(5));
+        Assert.Equal(CompleteTag, reset.TagPath);
+        dcl.Reply(new WriteTagResponse(reset.CorrelationId, true, null, DateTimeOffset.UtcNow));
+
+        // The cache still says True → the reset wait must NOT fast-path, and no batch may go out.
+        dcl.ExpectNoMsg(TimeSpan.FromMilliseconds(500));
+        Assert.False(call.IsCompleted);
+
+        // The device echoes the reset.
+        actor.Tell(new TagValueUpdate(Conn, CompleteTag, false, QualityCode.Good, DateTimeOffset.UtcNow));
+
+        // Only now the batch + trigger.
+        var batch = dcl.ExpectMsg<WriteTagBatchRequest>(TimeSpan.FromSeconds(5));
+        Assert.Equal(TriggerTag, batch.TriggerTagPath);
+        Assert.Equal(AttributeValueCodec.Encode(true), AttributeValueCodec.Encode(batch.TriggerValue));
+        Assert.True(batch.Values.ContainsKey(BatchTag));
+        dcl.Reply(new WriteTagBatchResponse(batch.CorrelationId, true, null, DateTimeOffset.UtcNow));
+
+        // Still pending: the cache now holds False.
+        Assert.False(call.IsCompleted);
+
+        // The device completes THIS request.
+        actor.Tell(new TagValueUpdate(Conn, CompleteTag, true, QualityCode.Good, DateTimeOffset.UtcNow));
+
+        var result = await call;
+        Assert.True(result.Matched);
+        Assert.Equal(HandshakePhase.Response, result.Phase);
+        Assert.Equal(true, result.Value);
+        Assert.Equal("Good", result.Quality);
+    }
+
+    [Fact]
+    public async Task ResetAwareOverload_NoEcho_TimesOutInResetPhase_AndNeverWritesTheBatch()
+    {
+        var (_, dcl, ctx) = Boot();
+
+        var call = ctx.WriteBatchResetAndWait(
+            Values(28950), "MoveOutFlag", AttributeValueCodec.Encode(true),
+            "MoveOutCompleteFlag", AttributeValueCodec.Encode(true), TimeSpan.FromSeconds(10),
+            "MoveOutCompleteFlag", AttributeValueCodec.Encode(false), TimeSpan.FromMilliseconds(700));
+
+        var reset = dcl.ExpectMsg<WriteTagRequest>(TimeSpan.FromSeconds(5));
+        dcl.Reply(new WriteTagResponse(reset.CorrelationId, true, null, DateTimeOffset.UtcNow));
+
+        var result = await call;
+        Assert.False(result.Matched);
+        Assert.True(result.TimedOut);
+        Assert.True(result.ResetFailed);
+        dcl.ExpectNoMsg(TimeSpan.FromMilliseconds(300));
+    }
+}