Files
lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests/NodeManagerAlarmSourceFieldsTests.cs
T
Joseph Doherty db751d12a5
v2-ci / build (pull_request) Successful in 4m49s
v2-ci / unit-tests (pull_request) Failing after 3h11m25s
feat(alarms): condition Quality tracks source connectivity (#477)
Part 9 ConditionType.Quality was never assigned; default(StatusCode)==Good
so every native + scripted condition reported Good unconditionally — a
comms-lost device still showed a healthy, inactive, Good condition (a
wrong-VALUE bug, distinct from the null-value #473/#475). Clients (and HMIs
bucketing on IsGood) could not tell "genuinely inactive" from "lost contact".

Layer 1 — make Quality a real, plumbed field:
- AlarmConditionSnapshot gains OpcUaQuality Quality (default Good).
- MaterialiseAlarmCondition sets it (native BadWaitingForInitialData, scripted Good).
- WriteAlarmCondition projects snapshot.Quality; the delta-gate gains a Quality
  member so a quality-bucket change fires a Part 9 event.

Layer 2 — drive native quality from driver connectivity (a comms-lost driver
emits no alarm transitions, and an alarm-bearing raw tag has no value variable,
so quality can't come from either existing channel):
- DriverInstanceActor Tells parent ConnectivityChanged on Connected/Reconnecting.
- DriverHostActor fans it to every native condition the driver owns as
  OpcUaPublishActor.AlarmQualityUpdate (Good on connect, Bad on disconnect).
- New dedicated IOpcUaAddressSpaceSink.WriteAlarmQuality sets ONLY Quality and
  fires only on a bucket change — never touches Active/Acked/Retain (an active
  alarm that loses comms stays active). Not a full-snapshot re-projection, so it
  can't clobber severity/message and works for a never-fired condition.
  Forwarded through DeferredAddressSpaceSink (F10b trap; auto-verified by the
  reflection forwarding guard). Ungated by redundancy role; no /alerts row.

Scripted conditions stay Good; worst-of-input quality deferred to #478 (Layer 3).

Tests: node-level (materialise/project/no-clobber/unknown-node no-op),
NativeAlarmProjector, DriverInstanceActor connectivity emission, DriverHostActor
fan-out, OpcUaPublishActor routing, and the wire-level guard
(Condition_event_Quality_tracks_source_connectivity_on_the_wire) — RED-verified
against a simulated pre-fix always-Good server. Existing DriverInstanceActor
parent probes ignore the new ConnectivityChanged.

Docs: docs/AlarmTracking.md §"Condition source-data Quality (#477)";
design doc docs/plans/2026-07-17-alarm-condition-quality-477-design.md.
2026-07-17 15:10:04 -04:00

355 lines
18 KiB
C#

using Microsoft.Extensions.Logging.Abstractions;
using Opc.Ua;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
namespace ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests;
/// <summary>
/// Issue #473 — every materialised Part 9 condition must carry the mandatory <c>BaseEventType</c>
/// identity fields <c>EventType</c> / <c>SourceNode</c> / <c>SourceName</c>. The SDK does NOT synthesise
/// them on this path: <see cref="NodeState.Create"/> initialises from the type's embedded definition,
/// which declares all three as mandatory children with NO default value, and the auto-filling
/// <see cref="BaseEventState.Initialize(ISystemContext, NodeState, EventSeverity, LocalizedText)"/>
/// overload (which would set SourceNode/SourceName from a source node) is only used for transient
/// events. <c>ReportEvent</c> and <c>InstanceStateSnapshot</c> copy the children verbatim and synthesise
/// nothing — so a field left null at materialise arrives null on the wire on EVERY condition event.
/// <para>
/// The contract locked in here (see <c>docs/AlarmTracking.md</c>): the condition node IS the source
/// node — a native-alarm raw tag materialises ONLY a condition (no separate value variable), so
/// <c>SourceNode</c> self-references the condition's own NodeId and <c>SourceName</c> carries the
/// same identifying id string (<c>alarmNodeId</c>: the RawPath for native, the ScriptedAlarmId for
/// scripted), matching <c>ConditionId</c>. The leaf/display name stays on <c>ConditionName</c>, so
/// no information is lost by SourceName carrying the unique id rather than the ambiguous leaf.
/// </para>
/// <para>
/// Issue #475 — the same mechanism leaves the mandatory <c>ConditionType</c> classification fields
/// <c>ConditionClassId</c> / <c>ConditionClassName</c> unset. The contract locked in here: a server that
/// does not model condition classes must still report <c>BaseConditionClassType</c> (Part 9's
/// "no class modelled" value) rather than null. See <c>docs/AlarmTracking.md</c>.
/// </para>
/// </summary>
public sealed class NodeManagerAlarmSourceFieldsTests : IDisposable
{
private static CancellationToken Ct => TestContext.Current.CancellationToken;
private const string RawDeviceFolder = "Plant/Modbus/dev1";
private const string RawAlarmPath = "Plant/Modbus/dev1/HR200";
private readonly string _pkiRoot = Path.Combine(
Path.GetTempPath(),
$"otopcua-alarm-src-fields-{Guid.NewGuid():N}");
/// <summary>A NATIVE condition (Raw realm, ConditionId = RawPath) carries all three identity fields:
/// EventType = its type definition, SourceNode = its own NodeId, SourceName = the RawPath. The leaf name
/// remains on ConditionName so the short name is still available to clients.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Native_condition_carries_EventType_SourceNode_and_SourceName()
{
await using var host = await BootAsync();
var nm = host.Nm;
var rawNs = nm.NamespaceIndexForRealm(AddressSpaceRealm.Raw);
nm.EnsureFolder(RawDeviceFolder, parentNodeId: null, displayName: "dev1", realm: AddressSpaceRealm.Raw);
nm.MaterialiseAlarmCondition(RawAlarmPath, RawDeviceFolder, "HR200", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Raw, isNative: true);
var condition = nm.TryGetAlarmCondition(RawAlarmPath, AddressSpaceRealm.Raw);
condition.ShouldNotBeNull();
// EventType — the concrete condition type, so a client reading the FIELD (not just an OfType
// where-clause) can resolve the type.
condition.EventType.ShouldNotBeNull();
condition.EventType.Value.ShouldBe(ObjectTypeIds.OffNormalAlarmType);
// SourceNode — the condition's own NodeId (it IS the source: no separate value variable exists
// for an alarm-bearing raw tag). Equal to ConditionId.
condition.SourceNode.ShouldNotBeNull();
condition.SourceNode.Value.ShouldBe(new NodeId(RawAlarmPath, rawNs));
// SourceName — the RawPath: unique across devices, matching ConditionId/SourceNode.
condition.SourceName.ShouldNotBeNull();
condition.SourceName.Value.ShouldBe(RawAlarmPath);
// The leaf name is NOT lost — it stays on ConditionName.
condition.ConditionName!.Value.ShouldBe("HR200");
}
/// <summary>A SCRIPTED condition (UNS realm, ConditionId = ScriptedAlarmId) follows the SAME uniform rule:
/// SourceNode = its own NodeId, SourceName = the ScriptedAlarmId. Scripted and native conditions share the
/// materialise path, so neither may regress independently.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Scripted_condition_carries_EventType_SourceNode_and_SourceName()
{
await using var host = await BootAsync();
var nm = host.Nm;
var unsNs = nm.NamespaceIndexForRealm(AddressSpaceRealm.Uns);
nm.EnsureFolder("eq-1", parentNodeId: null, displayName: "Station 1", realm: AddressSpaceRealm.Uns);
nm.MaterialiseAlarmCondition("tank-overflow", "eq-1", "Tank Overflow", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Uns, isNative: false);
var condition = nm.TryGetAlarmCondition("tank-overflow", AddressSpaceRealm.Uns);
condition.ShouldNotBeNull();
condition.EventType!.Value.ShouldBe(ObjectTypeIds.OffNormalAlarmType);
condition.SourceNode!.Value.ShouldBe(new NodeId("tank-overflow", unsNs));
condition.SourceName!.Value.ShouldBe("tank-overflow");
// The human-readable name stays on ConditionName.
condition.ConditionName!.Value.ShouldBe("Tank Overflow");
}
/// <summary>EventType tracks the ACTUAL materialised type, not a hardcoded constant: an unknown alarm type
/// falls back to the base <see cref="AlarmConditionState"/> and its EventType must report that base type
/// rather than a subtype the node does not have.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task EventType_reflects_the_fallback_base_type_for_an_unknown_alarm_type()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder("eq-2", parentNodeId: null, displayName: "Station 2", realm: AddressSpaceRealm.Uns);
nm.MaterialiseAlarmCondition("alm-x", "eq-2", "Generic", "LimitAlarm", 500,
realm: AddressSpaceRealm.Uns, isNative: false);
var condition = nm.TryGetAlarmCondition("alm-x", AddressSpaceRealm.Uns);
condition.ShouldNotBeNull();
condition.GetType().ShouldBe(typeof(AlarmConditionState)); // base-type fallback
condition.EventType!.Value.ShouldBe(ObjectTypeIds.AlarmConditionType);
}
/// <summary>The identity fields survive a re-materialise that DROPS and re-creates the node (the native↔scripted
/// kind-swap path), so a redeploy can never leave a condition emitting null identity.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Identity_fields_survive_a_kind_swap_rematerialise()
{
await using var host = await BootAsync();
var nm = host.Nm;
var unsNs = nm.NamespaceIndexForRealm(AddressSpaceRealm.Uns);
nm.EnsureFolder("eq-3", parentNodeId: null, displayName: "Station 3", realm: AddressSpaceRealm.Uns);
nm.MaterialiseAlarmCondition("alm-swap", "eq-3", "Swap", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Uns, isNative: false);
// Kind swap (scripted → native) drops the prior instance and re-creates it.
nm.MaterialiseAlarmCondition("alm-swap", "eq-3", "Swap", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Uns, isNative: true);
var condition = nm.TryGetAlarmCondition("alm-swap", AddressSpaceRealm.Uns);
condition.ShouldNotBeNull();
condition.EventType!.Value.ShouldBe(ObjectTypeIds.OffNormalAlarmType);
condition.SourceNode!.Value.ShouldBe(new NodeId("alm-swap", unsNs));
condition.SourceName!.Value.ShouldBe("alm-swap");
}
/// <summary>#475 — a NATIVE condition (Raw realm) carries the mandatory ConditionType classification fields.
/// We do not model condition classes, so Part 9's "no class modelled" value — BaseConditionClassType — is the
/// conformant answer; the point is that it is a resolvable class NodeId a client can bucket on rather than a
/// null that drops the alarm into an unclassified bin.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Native_condition_carries_ConditionClassId_and_ConditionClassName()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder(RawDeviceFolder, parentNodeId: null, displayName: "dev1", realm: AddressSpaceRealm.Raw);
nm.MaterialiseAlarmCondition(RawAlarmPath, RawDeviceFolder, "HR200", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Raw, isNative: true);
var condition = nm.TryGetAlarmCondition(RawAlarmPath, AddressSpaceRealm.Raw);
condition.ShouldNotBeNull();
condition.ConditionClassId.ShouldNotBeNull();
condition.ConditionClassId.Value.ShouldBe(ObjectTypeIds.BaseConditionClassType);
condition.ConditionClassName.ShouldNotBeNull();
condition.ConditionClassName.Value.ShouldNotBeNull();
condition.ConditionClassName.Value.Text.ShouldBe("BaseConditionClass");
}
/// <summary>#475 — a SCRIPTED condition (UNS realm) carries the SAME classification fields: native and scripted
/// share the materialise path, so neither may regress independently.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Scripted_condition_carries_ConditionClassId_and_ConditionClassName()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder("eq-4", parentNodeId: null, displayName: "Station 4", realm: AddressSpaceRealm.Uns);
nm.MaterialiseAlarmCondition("tank-dry", "eq-4", "Tank Dry", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Uns, isNative: false);
var condition = nm.TryGetAlarmCondition("tank-dry", AddressSpaceRealm.Uns);
condition.ShouldNotBeNull();
condition.ConditionClassId!.Value.ShouldBe(ObjectTypeIds.BaseConditionClassType);
condition.ConditionClassName!.Value.Text.ShouldBe("BaseConditionClass");
}
/// <summary>#477 — a freshly materialised NATIVE condition reports BadWaitingForInitialData quality (not the
/// accidentally-Good default), matching the value-variable "no driver data yet" convention. Its quality only
/// becomes Good once its driver's connectivity confirms it (Layer 2).</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Native_condition_materialises_with_waiting_for_initial_data_quality()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder(RawDeviceFolder, parentNodeId: null, displayName: "dev1", realm: AddressSpaceRealm.Raw);
nm.MaterialiseAlarmCondition(RawAlarmPath, RawDeviceFolder, "HR200", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Raw, isNative: true);
var condition = nm.TryGetAlarmCondition(RawAlarmPath, AddressSpaceRealm.Raw);
condition.ShouldNotBeNull();
condition.Quality.ShouldNotBeNull();
condition.Quality.Value.ShouldBe((StatusCode)StatusCodes.BadWaitingForInitialData);
StatusCode.IsGood(condition.Quality.Value).ShouldBeFalse();
}
/// <summary>#477 — a SCRIPTED condition is script-computed and always "live" in v1, so it materialises Good.
/// (Scripted worst-of-input quality is deferred to Layer 3.)</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task Scripted_condition_materialises_with_good_quality()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder("eq-q1", parentNodeId: null, displayName: "Station Q1", realm: AddressSpaceRealm.Uns);
nm.MaterialiseAlarmCondition("scripted-q", "eq-q1", "Scripted Q", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Uns, isNative: false);
var condition = nm.TryGetAlarmCondition("scripted-q", AddressSpaceRealm.Uns);
condition.ShouldNotBeNull();
condition.Quality.ShouldNotBeNull();
StatusCode.IsGood(condition.Quality.Value).ShouldBeTrue();
}
/// <summary>#477 — WriteAlarmCondition projects the snapshot's Quality onto the live condition node, so a
/// Bad-quality snapshot (comms-lost source) makes the condition report non-Good.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task WriteAlarmCondition_projects_snapshot_quality_onto_the_condition()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder(RawDeviceFolder, parentNodeId: null, displayName: "dev1", realm: AddressSpaceRealm.Raw);
nm.MaterialiseAlarmCondition(RawAlarmPath, RawDeviceFolder, "HR200", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Raw, isNative: true);
// A comms-lost snapshot: the alarm state is unchanged but Quality is Bad.
var badSnapshot = new AlarmConditionSnapshot(
Active: false, Acknowledged: true, Confirmed: true, Enabled: true,
Shelving: AlarmShelvingKind.Unshelved, Severity: 700, Message: "HR200",
Quality: OpcUaQuality.Bad);
nm.WriteAlarmCondition(RawAlarmPath, badSnapshot, DateTime.UtcNow, AddressSpaceRealm.Raw);
var condition = nm.TryGetAlarmCondition(RawAlarmPath, AddressSpaceRealm.Raw);
condition.ShouldNotBeNull();
StatusCode.IsBad(condition.Quality.Value).ShouldBeTrue();
// Recover: a Good snapshot restores Good quality.
var goodSnapshot = badSnapshot with { Quality = OpcUaQuality.Good };
nm.WriteAlarmCondition(RawAlarmPath, goodSnapshot, DateTime.UtcNow, AddressSpaceRealm.Raw);
StatusCode.IsGood(condition.Quality.Value).ShouldBeTrue();
}
/// <summary>#477 Layer 2 — the dedicated connectivity-quality path sets ONLY the condition's Quality
/// (comms lost → Bad, restored → Good) and never clobbers the node's severity / message / alarm state:
/// it is a pure annotation applied out-of-band from any alarm transition.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task WriteAlarmQuality_sets_only_quality_without_touching_state_or_severity()
{
await using var host = await BootAsync();
var nm = host.Nm;
nm.EnsureFolder(RawDeviceFolder, parentNodeId: null, displayName: "dev1", realm: AddressSpaceRealm.Raw);
nm.MaterialiseAlarmCondition(RawAlarmPath, RawDeviceFolder, "HR200", "OffNormalAlarm", 700,
realm: AddressSpaceRealm.Raw, isNative: true);
var condition = nm.TryGetAlarmCondition(RawAlarmPath, AddressSpaceRealm.Raw);
condition.ShouldNotBeNull();
var severityBefore = condition.Severity!.Value;
var messageBefore = condition.Message!.Value?.Text;
// Device comes online → Good.
nm.WriteAlarmQuality(RawAlarmPath, OpcUaQuality.Good, DateTime.UtcNow, AddressSpaceRealm.Raw);
StatusCode.IsGood(condition.Quality!.Value).ShouldBeTrue();
// Device goes comms-lost → Bad, but severity / message / active-ack state are untouched.
nm.WriteAlarmQuality(RawAlarmPath, OpcUaQuality.Bad, DateTime.UtcNow, AddressSpaceRealm.Raw);
StatusCode.IsBad(condition.Quality.Value).ShouldBeTrue();
condition.Severity.Value.ShouldBe(severityBefore);
condition.Message.Value?.Text.ShouldBe(messageBefore);
condition.ActiveState!.Id!.Value.ShouldBeFalse(); // unchanged: annotation only
}
/// <summary>#477 Layer 2 — WriteAlarmQuality on an unknown / unmaterialised node is a safe no-op (never
/// throws), mirroring the other write paths: a mid-rebuild race must not fault a connectivity update.</summary>
[Trait("Category", "Unit")]
[Fact]
public async Task WriteAlarmQuality_is_a_noop_for_an_unknown_condition()
{
await using var host = await BootAsync();
var nm = host.Nm;
Should.NotThrow(() =>
nm.WriteAlarmQuality("no/such/node", OpcUaQuality.Bad, DateTime.UtcNow, AddressSpaceRealm.Raw));
}
/// <summary>A booted server + its node manager, disposed via <c>await using</c> so an assertion failure
/// cannot leak a live server (and its bound port) into the rest of the test run.</summary>
private sealed class BootedServer(OpcUaApplicationHost host, OtOpcUaNodeManager nm) : IAsyncDisposable
{
public OtOpcUaNodeManager Nm { get; } = nm;
public ValueTask DisposeAsync() => host.DisposeAsync();
}
private async Task<BootedServer> BootAsync()
{
var host = new OpcUaApplicationHost(
new OpcUaApplicationHostOptions
{
ApplicationName = "OtOpcUa.AlarmSourceFieldsTest",
ApplicationUri = $"urn:OtOpcUa.AlarmSourceFieldsTest:{Guid.NewGuid():N}",
OpcUaPort = AllocateFreePort(),
PublicHostname = "localhost",
PkiStoreRoot = _pkiRoot,
},
NullLogger<OpcUaApplicationHost>.Instance);
var server = new OtOpcUaSdkServer();
await host.StartAsync(server, Ct);
return new BootedServer(host, server.NodeManager!);
}
private static int AllocateFreePort()
{
using var listener = new System.Net.Sockets.TcpListener(System.Net.IPAddress.Loopback, 0);
listener.Start();
return ((System.Net.IPEndPoint)listener.LocalEndpoint).Port;
}
public void Dispose()
{
if (Directory.Exists(_pkiRoot))
{
try { Directory.Delete(_pkiRoot, recursive: true); }
catch { /* best-effort */ }
}
}
}