fix(dcl): treat OPC UA BadResourceUnavailable as transient Bad; Bad+null keeps last-known value (ScadaBridge#112)

OtOpcUa's out-of-process script runner publishes 0x80040000 with a null value.
- OpcUaDataConnection: logs entry/recovery once per tag, names the symbolic
  status in read errors; never a disconnect (not in the reconnect status set).
- InstanceActor: a Bad update with no value is a quality-only transition
  (keep value, quality Bad, stream publish, no script/alarm/waiter re-eval),
  matching the connection-drop rule. Bad with a value is unchanged.

Claude-Session: https://claude.ai/code/session_01GT67AEHd2Acv1YPwGfXEoV
This commit is contained in:
Joseph Doherty
2026-11-10 04:38:05 -05:00
parent 533414a16d
commit 08fe5acfe4
5 changed files with 322 additions and 2 deletions
@@ -0,0 +1,134 @@
using System.Collections.Concurrent;
using System.Reflection;
using Microsoft.Extensions.Logging;
using NSubstitute;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Protocol;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;
using ZB.MOM.WW.ScadaBridge.DataConnectionLayer.Actors;
using ZB.MOM.WW.ScadaBridge.DataConnectionLayer.Adapters;
namespace ZB.MOM.WW.ScadaBridge.DataConnectionLayer.Tests.Adapters;
/// <summary>
/// ScadaBridge#112: OtOpcUa's out-of-process script runner publishes
/// <c>BadResourceUnavailable</c> (0x80040000) — with a null value — on script-computed nodes
/// when its worker died or is not ready. The OPC UA adapter must treat it as a plain, transient
/// Bad quality on the tag: no disconnect, no subscription teardown, distinct log lines on entry
/// and recovery, and a read error that names the status.
/// </summary>
public class OpcUaResourceUnavailableTests
{
private const uint BadResourceUnavailable = 0x80040000u;
private const string Tag = "nsu=https://zb.com/otopcua/uns;s=Line1.Pump.Calc";
private sealed class CapturingLogger : ILogger<OpcUaDataConnection>
{
public ConcurrentQueue<(LogLevel Level, string Message)> Entries { get; } = new();
public IDisposable? BeginScope<TState>(TState state) where TState : notnull => null;
public bool IsEnabled(LogLevel logLevel) => true;
public void Log<TState>(LogLevel logLevel, EventId eventId, TState state, Exception? exception,
Func<TState, Exception?, string> formatter) => Entries.Enqueue((logLevel, formatter(state, exception)));
}
/// <summary>
/// Good / BadResourceUnavailable(null) / Good on a monitored item maps to Good / Bad / Good
/// tag quality, never raises Disconnected, never removes the subscription, and logs the
/// unavailable entry once (not per notification) plus one recovery line.
/// </summary>
[Fact]
public async Task Subscription_GoodResourceUnavailableGood_IsTransientBadQuality_NotAConnectionFault()
{
var client = Substitute.For<IOpcUaClient>();
var factory = Substitute.For<IOpcUaClientFactory>();
factory.Create().Returns(client);
client.IsConnected.Returns(true);
Action<string, object?, DateTime, uint>? publish = null;
client.CreateSubscriptionAsync(Tag, Arg.Do<Action<string, object?, DateTime, uint>>(cb => publish = cb),
Arg.Any<CancellationToken>())
.Returns("sub-1");
var logger = new CapturingLogger();
var adapter = new OpcUaDataConnection(factory, logger);
var disconnected = 0;
adapter.Disconnected += () => Interlocked.Increment(ref disconnected);
await adapter.ConnectAsync(new Dictionary<string, string>());
var received = new List<TagValue>();
await adapter.SubscribeAsync(Tag, (_, v) => received.Add(v));
Assert.NotNull(publish);
publish!(Tag, 42.0, DateTime.UtcNow, 0u);
publish(Tag, null, DateTime.UtcNow, BadResourceUnavailable);
publish(Tag, null, DateTime.UtcNow, BadResourceUnavailable); // repeated: no second log line
publish(Tag, 43.0, DateTime.UtcNow, 0u);
Assert.Equal(
new[] { QualityCode.Good, QualityCode.Bad, QualityCode.Bad, QualityCode.Good },
received.Select(v => v.Quality).ToArray());
Assert.Null(received[1].Value);
Assert.Equal(43.0, received[3].Value);
Assert.Equal(0, disconnected);
Assert.Equal(ConnectionHealth.Connected, adapter.Status);
await client.DidNotReceiveWithAnyArgs().RemoveSubscriptionAsync(default!, default);
await client.DidNotReceiveWithAnyArgs().DisconnectAsync(default);
var unavailable = logger.Entries.Where(e => e.Message.Contains("reports BadResourceUnavailable")).ToList();
var recovered = logger.Entries.Where(e => e.Message.Contains("recovered") && e.Message.Contains(Tag)).ToList();
Assert.Single(unavailable);
Assert.Contains(Tag, unavailable[0].Message);
Assert.Single(recovered);
}
/// <summary>A read that returns BadResourceUnavailable fails the read without a disconnect and
/// names the symbolic status so it reads as a transient source-side condition.</summary>
[Fact]
public async Task Read_ResourceUnavailable_FailsReadWithNamedStatus_NoDisconnect()
{
var client = Substitute.For<IOpcUaClient>();
var factory = Substitute.For<IOpcUaClientFactory>();
factory.Create().Returns(client);
client.IsConnected.Returns(true);
client.ReadValueAsync(Tag, Arg.Any<CancellationToken>())
.Returns(((object?)null, DateTime.UtcNow, BadResourceUnavailable));
var adapter = new OpcUaDataConnection(factory, new CapturingLogger());
var disconnected = 0;
adapter.Disconnected += () => disconnected++;
await adapter.ConnectAsync(new Dictionary<string, string>());
var result = await adapter.ReadAsync(Tag);
Assert.False(result.Success);
Assert.Contains("0x80040000", result.ErrorMessage);
Assert.Contains("BadResourceUnavailable", result.ErrorMessage);
Assert.Contains("temporarily unable", result.ErrorMessage);
Assert.Equal(0, disconnected);
Assert.Equal(ConnectionHealth.Connected, adapter.Status);
}
/// <summary>Other Bad reads still get the symbolic name but not the transient wording.</summary>
[Fact]
public void DescribeBadRead_OtherCodes_NamedWithoutTransientWording()
{
var text = OpcUaDataConnection.DescribeBadRead(0x80340000u);
Assert.Contains("BadNodeIdUnknown", text);
Assert.DoesNotContain("temporarily", text);
}
/// <summary>
/// BadResourceUnavailable is a per-node status: the DataConnectionActor must never classify it
/// as a session/secure-channel failure, which would drive a reconnect and a subscription rebuild.
/// </summary>
[Fact]
public void ResourceUnavailable_IsNotConnectionLevelStatus()
{
var method = typeof(DataConnectionActor).GetMethod("IsConnectionLevelStatus",
BindingFlags.NonPublic | BindingFlags.Static);
Assert.NotNull(method);
Assert.False((bool)method!.Invoke(null, new object[] { BadResourceUnavailable })!);
// Positive control: a genuine session code IS connection-level.
Assert.True((bool)method.Invoke(null, new object[] { 0x80250000u /* BadSessionIdInvalid */ })!);
}
}
@@ -768,6 +768,92 @@ public class InstanceActorTests : TestKit, IDisposable
Assert.Equal(1450, response.Value);
}
/// <summary>
/// ScadaBridge#112: a Bad-quality update that carries NO value (OtOpcUa sends a null Value
/// with every Bad status, e.g. BadResourceUnavailable from its out-of-process script runner)
/// is a quality-only transition — the last-known value survives, quality goes Bad, waiters
/// and children are not re-evaluated against a null that never existed, and the next Good
/// update recovers the attribute. Pins the Good / Bad(null) / Good sequence.
/// </summary>
[Fact]
public void InstanceActor_BadQualityWithNullValue_KeepsLastKnownValue_AndRecoversOnGood()
{
const string tag = "nsu=https://zb.com/otopcua/uns;s=Line1.Pump.Calc";
var config = new FlattenedConfiguration
{
InstanceUniqueName = "Pump-BadNull",
Attributes =
[
new ResolvedAttribute
{
CanonicalName = "Calc", Value = "0", DataType = "Int32",
DataSourceReference = tag, BoundDataConnectionName = "OtOpcUa"
}
]
};
var dcl = CreateTestProbe();
var actor = CreateInstanceActorWithDcl("Pump-BadNull", config, dcl);
actor.Tell(new TagValueUpdate("OtOpcUa", tag, 1450, QualityCode.Good, DateTimeOffset.UtcNow));
// A waiter that would fire if the stored value were ever nulled.
actor.Tell(new WaitForAttributeRequest(
"wfa-null", "Pump-BadNull", "Calc",
null, v => v is null, TimeSpan.FromSeconds(30), DateTimeOffset.UtcNow));
ExpectNoMsg(TimeSpan.FromMilliseconds(200));
// Source goes BadResourceUnavailable: Bad quality, null value.
actor.Tell(new TagValueUpdate("OtOpcUa", tag, null, QualityCode.Bad, DateTimeOffset.UtcNow));
ExpectNoMsg(TimeSpan.FromMilliseconds(300));
actor.Tell(new GetAttributeRequest("corr-bad", "Pump-BadNull", "Calc", DateTimeOffset.UtcNow));
var bad = ExpectMsg<GetAttributeResponse>(TimeSpan.FromSeconds(5));
Assert.True(bad.Found);
Assert.Equal("Bad", bad.Quality);
Assert.Equal(1450, bad.Value);
// Next good evaluation recovers.
actor.Tell(new TagValueUpdate("OtOpcUa", tag, 1500, QualityCode.Good, DateTimeOffset.UtcNow));
actor.Tell(new GetAttributeRequest("corr-good", "Pump-BadNull", "Calc", DateTimeOffset.UtcNow));
var good = ExpectMsg<GetAttributeResponse>(TimeSpan.FromSeconds(5));
Assert.Equal("Good", good.Quality);
Assert.Equal(1500, good.Value);
}
/// <summary>
/// Guard for ScadaBridge#112: a Bad update that DOES carry a value keeps the historical
/// behaviour — the carried value is stored with Bad quality.
/// </summary>
[Fact]
public void InstanceActor_BadQualityWithValue_StoresCarriedValue()
{
const string tag = "ns=3;s=Pump.BadWithValue";
var config = new FlattenedConfiguration
{
InstanceUniqueName = "Pump-BadValue",
Attributes =
[
new ResolvedAttribute
{
CanonicalName = "Speed", Value = "0", DataType = "Int32",
DataSourceReference = tag, BoundDataConnectionName = "PLC"
}
]
};
var dcl = CreateTestProbe();
var actor = CreateInstanceActorWithDcl("Pump-BadValue", config, dcl);
actor.Tell(new TagValueUpdate("PLC", tag, 1450, QualityCode.Good, DateTimeOffset.UtcNow));
actor.Tell(new TagValueUpdate("PLC", tag, 1300, QualityCode.Bad, DateTimeOffset.UtcNow));
actor.Tell(new GetAttributeRequest("corr-bv", "Pump-BadValue", "Speed", DateTimeOffset.UtcNow));
var response = ExpectMsg<GetAttributeResponse>(TimeSpan.FromSeconds(5));
Assert.Equal("Bad", response.Quality);
Assert.Equal(1300, response.Value);
}
/// <summary>
/// MV (C1 fix): a WRITE to a data-sourced <c>DataType.List</c> attribute must
/// send the DCL a TYPED collection (so OPC UA writes an array node), NOT the