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
parent f6a3c31b60
commit db751d12a5
30 changed files with 752 additions and 7 deletions
@@ -196,6 +196,120 @@ public sealed class NodeManagerAlarmSourceFieldsTests : IDisposable
        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