feat: adopt shared ZB.MOM.WW.Health probes (preserve tiers + OtOpcUaCompat policy)

sql_login.txt holds DB creds and the Host pki/ dir is the runtime OPC UA
certificate store (private keys + issued/trusted certs); neither belongs
in source control, and ignoring them prevents an accidental git add .

.gitignore

@@ -42,3 +42,9 @@ config_cache*.db
 
 # Client CLI/UI runtime scratch (last-connected endpoint cache)
 session.dat
+
+# Secrets / local credentials — never commit
+sql_login.txt
+
+# OPC UA certificate store (runtime PKI: own/trusted/issued/rejected certs + keys)
+src/Server/ZB.MOM.WW.OtOpcUa.Host/pki/

Directory.Packages.props

@@ -96,6 +96,9 @@
     <PackageVersion Include="xunit" Version="2.9.2" />
     <PackageVersion Include="xunit.runner.visualstudio" Version="3.0.2" />
     <PackageVersion Include="xunit.v3" Version="1.1.0" />
+    <PackageVersion Include="ZB.MOM.WW.Health" Version="0.1.0" />
+    <PackageVersion Include="ZB.MOM.WW.Health.Akka" Version="0.1.0" />
+    <PackageVersion Include="ZB.MOM.WW.Health.EntityFrameworkCore" Version="0.1.0" />
     <PackageVersion Include="ZB.MOM.WW.MxGateway.Client" Version="0.1.0" />
     <PackageVersion Include="ZB.MOM.WW.MxGateway.Contracts" Version="0.1.0" />
   </ItemGroup>

NuGet.config

@@ -3,5 +3,18 @@
   <packageSources>
     <add key="nuget.org" value="https://api.nuget.org/v3/index.json" protocolVersion="3" />
     <add key="local-mxgw" value="./nuget-packages" />
+    <add key="dohertj2-gitea" value="https://gitea.dohertylan.com/api/packages/dohertj2/nuget/index.json" />
   </packageSources>
+  <packageSourceMapping>
+    <packageSource key="nuget.org">
+      <package pattern="*" />
+    </packageSource>
+    <packageSource key="local-mxgw">
+      <package pattern="ZB.MOM.WW.MxGateway.*" />
+    </packageSource>
+    <packageSource key="dohertj2-gitea">
+      <package pattern="ZB.MOM.WW.Health" />
+      <package pattern="ZB.MOM.WW.Health.*" />
+    </packageSource>
+  </packageSourceMapping>
 </configuration>

docs/plans/alarms-d1-smoke-artifact.md

@@ -0,0 +1,106 @@
+# Alarms D.1 — smoke artifact
+
+> **Status (2026-05-29): alarm-source leg VERIFIED. Historian-write leg still
+> pending the Windows sidecar + live AVEVA Historian.**
+>
+> **Re-confirmed 2026-05-31** against the same gateway (`http://10.100.0.48:5120`):
+> the Skip-gated live test passed again, pulling a native `Raise` transition
+> (`Galaxy!TestArea.TestMachine_001.TestAlarm001`, raw sev 500 → OPC UA 750/High,
+> category `TestArea`, operator comment `Test alarm #1`) through the production
+> consumer. Independent re-run, not the original capture.
+>
+> This is the D.1 deliverable called for by `docs/plans/alarms-worker-wiring-plan.md`
+> — captured evidence that a live Galaxy alarm reaches lmxopcua through the native
+> gateway path (not the sub-attribute fallback). It supersedes the "A.2 blocked"
+> banners in `alarms-over-gateway.md` / `alarms-worker-wiring-plan.md`, which were
+> written 2026-04-30 before the gateway's alarm feed was working.
+
+## What was verified
+
+The mxaccessgw gateway **does** serve native MxAccess alarms today, and the lmxopcua
+consumer ingests them with full fidelity — **including operator-comment**, the field
+the 2026-04-30 plan flagged as "the only v1 regression."
+
+Verified from the macOS dev box against the live gateway at `http://10.100.0.48:5120`
+(reachable; `nc -z` succeeds). No acknowledge / no writes were issued — read-only
+`StreamAlarms`.
+
+### 1. Gateway boundary — raw `StreamAlarms` (`ZB.MOM.WW.MxGateway.Client`)
+
+A standalone client streamed the active-alarm snapshot: **20 active alarms**, each
+carrying native metadata. Sample (one of 20):
+
+```json
+{ "alarmFullReference": "Galaxy!TestArea.TestMachine_001.TestAlarm001",
+  "sourceObjectReference": "TestMachine_001.TestAlarm001",
+  "alarmTypeName": "DSC", "severity": 500,
+  "currentState": "ALARM_CONDITION_STATE_ACTIVE", "category": "TestArea",
+  "lastTransitionTimestamp": "2026-05-24T16:04:10.856Z",
+  "operatorComment": "Test alarm #1" }
+```
+
+Followed by the `SnapshotComplete` marker. `operatorComment`, `category`, `severity`,
+`currentState`, and `lastTransitionTimestamp` are all populated.
+
+### 2. lmxopcua consumer — `GatewayGalaxyAlarmFeed` → `GalaxyAlarmTransition`
+
+The Skip-gated live test
+`Runtime/GatewayGalaxyAlarmFeedLiveTests.Live_gateway_delivers_native_alarm_transitions_through_the_consumer`
+wires the real `MxGatewayClient.StreamAlarmsAsync` into the production consumer seam
+and **passes**. Captured output (`D1_SMOKE_OUT`):
+
+```
+# consumer transitions observed: 2+
+Raise  Galaxy!TestArea.TestMachine_001.TestAlarm001 | sev=750(High) raw=500 | cat=TestArea | comment='Test alarm #1' | xitionUtc=2026-05-24T16:04:10.856Z
+Raise  Galaxy!TestArea.TestMachine_003.TestAlarm001 | sev=750(High) raw=500 | cat=TestArea | comment='Test alarm #1' | xitionUtc=2026-05-07T18:14:00.594Z
+```
+
+The consumer preserves `operatorComment` + `category` + transition timestamp and
+applies the OPC UA severity-bucket mapping (`MxAccessSeverityMapper`: raw 500 →
+OPC UA 750, bucket `High`).
+
+### 3. Full chain to the OPC UA Part 9 surface (code-path verified)
+
+`GalaxyDriver.OnAlarmFeedTransition` maps `GalaxyAlarmTransition` →
+`AlarmEventArgs`, carrying `OperatorComment`, `OriginalRaiseTimestampUtc`,
+`AlarmCategory`, and the severity bucket onto `IAlarmSource.OnAlarmEvent`.
+`AlarmEventArgs` already declares those fields — so the **E.7 contract extension is
+done**, not pending. The server's Part-9 condition layer consumes `IAlarmSource`
+via `AlarmSurfaceInvoker` → `GenericDriverNodeManager`. Unit coverage:
+`GalaxyDriverAlarmSourceTests`, `GatewayGalaxyAlarmFeedTests`.
+
+## How to re-run
+
+```bash
+export MXGW_ENDPOINT="http://10.100.0.48:5120"
+export GALAXY_MXGW_API_KEY="<dev key from docker-dev/docker-compose.yml>"
+export D1_SMOKE_OUT="/tmp/d1-consumer-transitions.txt"   # optional capture
+dotnet test tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Tests \
+  --filter "FullyQualifiedName~GatewayGalaxyAlarmFeedLiveTests"
+```
+
+Without the env vars the test `Skip`s, so normal `dotnet test` runs are unaffected.
+
+## Not covered here (still open)
+
+1. **Scripted-alarm historian write-back → AVEVA Historian** (C.1's live leg). The
+   `SdkAlarmHistorianWriteBackend` (real `HistorianAccess.AddStreamedValue` path) is
+   implemented and unit-tested, but its `Live_*` write smoke needs the Windows
+   historian sidecar + a live AVEVA Historian — neither reachable from the macOS dev
+   box. Capture this leg on the Windows parity rig.
+2. **Running-server → OPC UA A&C client round-trip.** This artifact proves the driver
+   consumer end; it does not exercise a full OtOpcUa server surfacing the condition to
+   an OPC UA client, because the docker-dev stack stubs the Galaxy driver on Linux
+   (`DriverInstanceActor.ShouldStub`). Capture on the Windows parity rig (or a Linux
+   host with `ShouldStub` overridden to point the real driver at the gateway).
+
+## Mechanism — true MxAccess alarm-event support
+
+The gateway delivers these alarms via **true MxAccess alarm-event support** in the
+mxaccessgw .NET client — a real alarm-event subscription, **not** the value-driven
+sub-attribute fallback. (Confirmed by the gateway maintainer; the client-side stream
+check above can only observe the resulting feed, which is why this artifact records the
+mechanism here rather than inferring it.) So A.2 is implemented as originally specified:
+`MX_EVENT_FAMILY_ON_ALARM_TRANSITION` carries genuine native alarm-event metadata, and
+the operator-comment / original-raise-time / category fields are first-class — not
+reconstructed from attribute reads.

docs/plans/alarms-over-gateway.md

@@ -9,24 +9,41 @@
 > the new RPCs; the sub-attribute fallback path keeps Galaxy alarms
 > functional today.
 >
-> ⚠️ **Worker-side native alarm subscription blocked on a dev-rig
-> finding (2026-04-30):** the MXAccess COM Toolkit at
+> ✅ **UPDATE 2026-05-29 — native alarm feed VERIFIED working; the
+> 2026-04-30 "blocked" finding below is superseded.** A live
+> `StreamAlarms` check against the gateway at `10.100.0.48:5120`
+> returned the active-alarm snapshot (20 alarms) with full native
+> metadata — `severity`, `category`, `currentState`,
+> `lastTransitionTimestamp`, **and `operatorComment`** (the field the
+> note below called "the only v1 regression"). The lmxopcua consumer
+> (`GatewayGalaxyAlarmFeed` → `GalaxyAlarmTransition` →
+> `AlarmEventArgs` → `IAlarmSource`) ingests it with full fidelity and
+> the OPC UA severity-bucket mapping applied — proven by the passing
+> Skip-gated live test `GatewayGalaxyAlarmFeedLiveTests`. `AlarmEventArgs`
+> already carries operator-comment / original-raise-time / category, so
+> **E.7 is done too**. See `docs/plans/alarms-d1-smoke-artifact.md` for
+> the captured evidence. The gateway delivers this via **true MxAccess
+> alarm-event support** in the mxaccessgw .NET client (a real
+> alarm-event subscription — **not** the sub-attribute fallback), so A.2
+> is implemented as originally specified. Still open: the scripted-alarm
+> → AVEVA Historian write-back live smoke (C.1's `Live_*` leg) and a full
+> running-server → OPC UA A&C round-trip — both need the Windows parity rig.
+>
+> ⚠️ **[SUPERSEDED — kept for history] Worker-side native alarm
+> subscription blocked on a dev-rig finding (2026-04-30):** the MXAccess
+> COM Toolkit at
 > `C:\Program Files (x86)\ArchestrA\Framework\Bin\ArchestrA.MXAccess.dll`
-> exposes no alarm-event family — only `OnDataChange`,
-> `OnWriteComplete`, `OperationComplete`, `OnBufferedDataChange`.
+> exposed no alarm-event family — only `OnDataChange`,
+> `OnWriteComplete`, `OperationComplete`, `OnBufferedDataChange` — and
 > AVEVA's `aaAlarmManagedClient` / `ArchestrAAlarmsAndEvents.SDK`
-> assemblies are x64-only and incompatible with the worker's x86
-> bitness. **Operator decision needed before
-> `MX_EVENT_FAMILY_ON_ALARM_TRANSITION` carries any events:** either
-> accept the value-driven sub-attribute path as the production
-> architecture (operator-comment fidelity is the only v1 regression)
-> or add an x64 alarm-helper sub-process alongside the worker. See
-> `src/MxGateway.Worker/MxAccess/MxAccessAlarmEventSink.cs` in the
-> mxaccessgw repo for the architectural notes. Live
-> `aahClientManaged` alarm-event write call site
-> (`SdkAlarmHistorianWriteBackend` placeholder from PR C.1) and the
-> D.1 smoke artifact ship once those decisions resolve. The
-> remainder of this document is preserved as the design record.
+> assemblies are x64-only vs. the worker's x86 bitness. The operator
+> decision (accept the value-driven sub-attribute path, or add an x64
+> alarm-helper sub-process) has since been resolved on the gateway side
+> — `MX_EVENT_FAMILY_ON_ALARM_TRANSITION` now carries events (verified
+> above). The C.1 `SdkAlarmHistorianWriteBackend` is **no longer a
+> placeholder** — it writes through the real
+> `HistorianAccess.AddStreamedValue` path (only its live-rig write
+> smoke remains).
 
 Coordinated epic across two repos:
 

docs/plans/alarms-worker-wiring-plan.md

@@ -1,5 +1,18 @@
 # Alarms Worker Wiring Plan
 
+> ✅ **UPDATE 2026-05-29 — the blocker below is RESOLVED on the gateway side; this
+> plan is largely complete.** A live `StreamAlarms` check against `10.100.0.48:5120`
+> returns the active-alarm snapshot with full native metadata **including
+> `operatorComment`**, and the lmxopcua consumer ingests it end-to-end (passing live
+> test `GatewayGalaxyAlarmFeedLiveTests`). So **A.2 / A.3 / A.4** are functionally done
+> at the gateway boundary (the worker now emits native alarm transitions and the client
+> exposes `AcknowledgeAlarm` / `QueryActiveAlarms` RPCs). **C.1** ships real code
+> (`SdkAlarmHistorianWriteBackend` → `HistorianAccess.AddStreamedValue`). **D.1**'s
+> alarm-source leg is captured in `docs/plans/alarms-d1-smoke-artifact.md`. Only two
+> things remain, both needing the Windows parity rig: C.1's live historian-write smoke
+> and a full running-server → OPC UA A&C round-trip. The per-item detail below is kept
+> as the historical record of the original blocked state.
+>
 > **Context**: The alarms-over-gateway epic shipped 19 PRs across the
 > `lmxopcua` and `mxaccessgw` repos (merged 2026-04-30). Contracts are live;
 > the sub-attribute fallback path keeps Galaxy alarms functional today. Four
@@ -16,7 +29,7 @@
 
 ---
 
-## Dev-rig finding that blocks everything (2026-04-30)
+## Dev-rig finding that blocks everything (2026-04-30) — [SUPERSEDED 2026-05-29]
 
 During PR A.2 work the following was discovered on the dev box:
 
@@ -318,16 +331,20 @@ fallback as production).
 
 ## Summary of blocks
 
-| Item | Blocked by | Estimated effort once unblocked |
-|------|-----------|--------------------------------|
-| A.2 | Architectural decision (x64 alarm-helper vs. sub-attribute fallback as production) | 2–3 days implementation; 1 day tests |
-| A.3 | A.2 delivering WorkerEvent bodies | 1–2 days |
-| A.4 | A.2 (active-alarm query needs AlarmClient session) | 1 day |
-| C.1 | aahClientManaged SDK access (available on dev box); NOT blocked by A.2 | 1–2 days |
-| D.1 | A.2 + A.3 + C.1 all passing on parity rig | 0.5 day (smoke + artifact capture) |
+> **Resolved as of 2026-05-29** — see the update banner at the top and
+> `docs/plans/alarms-d1-smoke-artifact.md`. Original status table kept for history.
 
-C.1 can proceed in parallel with A.2 / A.3 since the sidecar's `aahClientManaged`
-is x64 and does not share the worker bitness constraint.
+| Item | Status (2026-05-29) | Original block |
+|------|--------------------|----------------|
+| A.2 | ✅ **True MxAccess alarm-event support** in the gateway client (real alarm-event subscription, not the sub-attribute fallback); verified via live `StreamAlarms` with operator-comment fidelity | Architectural decision (x64 alarm-helper vs. sub-attribute fallback) |
+| A.3 | ✅ Dispatch + `AcknowledgeAlarm` RPC present on the client surface | A.2 delivering WorkerEvent bodies |
+| A.4 | ✅ `QueryActiveAlarms` RPC present on the client surface | A.2 (active-alarm query needs AlarmClient session) |
+| C.1 | ✅ Code shipped (`AddStreamedValue` path); ⏳ live historian-write smoke needs the Windows rig | aahClientManaged SDK access |
+| D.1 | ◑ Alarm-source leg captured (`alarms-d1-smoke-artifact.md`); ⏳ historian-write leg + full server→A&C round-trip need the Windows rig | A.2 + A.3 + C.1 all passing on parity rig |
+
+The gateway delivers operator-comment fidelity through **true MxAccess alarm-event
+support** in the mxaccessgw .NET client — a real alarm-event subscription, not the
+value-driven sub-attribute path. The sub-attribute fallback is now legacy.
 
 ---
 

src/Server/ZB.MOM.WW.OtOpcUa.Host/Health/AdminRoleLeaderHealthCheck.cs

@@ -1,39 +0,0 @@
-using Microsoft.Extensions.Diagnostics.HealthChecks;
-using ZB.MOM.WW.OtOpcUa.Commons.Interfaces;
-
-namespace ZB.MOM.WW.OtOpcUa.Host.Health;
-
-/// <summary>
-/// Reports Healthy on the admin-role leader, Degraded on a non-leader admin member. Used by
-/// the <c>/health/active</c> endpoint so external load balancers can route admin-singleton
-/// traffic to the current leader (cookie sessions still work on either node — DataProtection
-/// keys are shared).
-/// </summary>
-public sealed class AdminRoleLeaderHealthCheck : IHealthCheck
-{
-    private readonly IClusterRoleInfo _roleInfo;
-
-    /// <summary>Initializes a new instance of the AdminRoleLeaderHealthCheck class.</summary>
-    /// <param name="roleInfo">The cluster role information provider.</param>
-    public AdminRoleLeaderHealthCheck(IClusterRoleInfo roleInfo)
-    {
-        _roleInfo = roleInfo;
-    }
-
-    /// <summary>Checks the health status of the admin role leader.</summary>
-    /// <param name="context">The health check context.</param>
-    /// <param name="cancellationToken">The cancellation token.</param>
-    /// <returns>A task representing the health check operation.</returns>
-    public Task<HealthCheckResult> CheckHealthAsync(HealthCheckContext context, CancellationToken cancellationToken = default)
-    {
-        if (!_roleInfo.HasRole("admin"))
-            return Task.FromResult(HealthCheckResult.Healthy("Node does not carry admin role"));
-
-        var leader = _roleInfo.RoleLeader("admin");
-        var isLeader = leader is not null && leader.Value.Equals(_roleInfo.LocalNode);
-
-        return Task.FromResult(isLeader
-            ? HealthCheckResult.Healthy($"Admin leader ({_roleInfo.LocalNode})")
-            : HealthCheckResult.Degraded($"Admin member but not leader (leader={leader?.Value ?? "<unknown>"})"));
-    }
-}

src/Server/ZB.MOM.WW.OtOpcUa.Host/Health/AkkaClusterHealthCheck.cs

@@ -1,35 +0,0 @@
-using Akka.Actor;
-using Akka.Cluster;
-using Microsoft.Extensions.Diagnostics.HealthChecks;
-
-namespace ZB.MOM.WW.OtOpcUa.Host.Health;
-
-public sealed class AkkaClusterHealthCheck : IHealthCheck
-{
-    private readonly ActorSystem _system;
-
-    /// <summary>
-    /// Initializes a new instance of the AkkaClusterHealthCheck class.
-    /// </summary>
-    /// <param name="system">The Akka actor system to check cluster health for.</param>
-    public AkkaClusterHealthCheck(ActorSystem system)
-    {
-        _system = system;
-    }
-
-    /// <summary>
-    /// Checks the health of the Akka cluster asynchronously.
-    /// </summary>
-    /// <param name="context">The health check context.</param>
-    /// <param name="cancellationToken">Cancellation token.</param>
-    public Task<HealthCheckResult> CheckHealthAsync(HealthCheckContext context, CancellationToken cancellationToken = default)
-    {
-        var cluster = Akka.Cluster.Cluster.Get(_system);
-        var selfUp = cluster.State.Members.Any(m =>
-            m.Address == cluster.SelfAddress && m.Status == MemberStatus.Up);
-
-        return Task.FromResult(selfUp
-            ? HealthCheckResult.Healthy($"Self Up; {cluster.State.Members.Count} member(s)")
-            : HealthCheckResult.Degraded("Self not yet Up in cluster"));
-    }
-}

src/Server/ZB.MOM.WW.OtOpcUa.Host/Health/DatabaseHealthCheck.cs

@@ -1,38 +0,0 @@
-using Microsoft.EntityFrameworkCore;
-using Microsoft.Extensions.Diagnostics.HealthChecks;
-using ZB.MOM.WW.OtOpcUa.Configuration;
-
-namespace ZB.MOM.WW.OtOpcUa.Host.Health;
-
-public sealed class DatabaseHealthCheck : IHealthCheck
-{
-    private readonly IDbContextFactory<OtOpcUaConfigDbContext> _dbFactory;
-
-    /// <summary>
-    /// Initializes a new instance of the <see cref="DatabaseHealthCheck"/> class.
-    /// </summary>
-    /// <param name="dbFactory">The database context factory for the config database.</param>
-    public DatabaseHealthCheck(IDbContextFactory<OtOpcUaConfigDbContext> dbFactory)
-    {
-        _dbFactory = dbFactory;
-    }
-
-    /// <summary>
-    /// Checks the health of the configuration database.
-    /// </summary>
-    /// <param name="context">The health check context.</param>
-    /// <param name="cancellationToken">Cancellation token.</param>
-    public async Task<HealthCheckResult> CheckHealthAsync(HealthCheckContext context, CancellationToken cancellationToken = default)
-    {
-        try
-        {
-            await using var db = await _dbFactory.CreateDbContextAsync(cancellationToken);
-            await db.Deployments.AsNoTracking().Take(1).ToListAsync(cancellationToken);
-            return HealthCheckResult.Healthy("ConfigDb reachable");
-        }
-        catch (Exception ex)
-        {
-            return HealthCheckResult.Unhealthy("ConfigDb unreachable", ex);
-        }
-    }
-}

src/Server/ZB.MOM.WW.OtOpcUa.Host/Health/HealthEndpoints.cs

@@ -1,25 +1,40 @@
-using Microsoft.AspNetCore.Builder;
-using Microsoft.AspNetCore.Diagnostics.HealthChecks;
 using Microsoft.AspNetCore.Routing;
+using Microsoft.EntityFrameworkCore;
 using Microsoft.Extensions.DependencyInjection;
-using Microsoft.Extensions.Diagnostics.HealthChecks;
+using ZB.MOM.WW.Health;
+using ZB.MOM.WW.Health.Akka;
+using ZB.MOM.WW.Health.EntityFrameworkCore;
+using ZB.MOM.WW.OtOpcUa.Configuration;
 
 namespace ZB.MOM.WW.OtOpcUa.Host.Health;
 
 public static class HealthEndpoints
 {
     /// <summary>
-    /// Registers the standard ASP.NET Core health-check infrastructure plus the OtOpcUa-specific
-    /// probes. Mirrors ScadaLink's three-tier pattern: <c>ready</c> = boot ok; <c>active</c> =
-    /// fully serving traffic; <c>healthz</c> = bare process liveness.
+    /// Registers the shared ZB.MOM.WW health probes. Tier semantics preserved: configdb + akka on
+    /// ready+active; admin-leader on active only.
     /// </summary>
-    /// <param name="services">The service collection to register health checks with.</param>
     public static IServiceCollection AddOtOpcUaHealth(this IServiceCollection services)
     {
         services.AddHealthChecks()
-            .AddCheck<DatabaseHealthCheck>("configdb", tags: new[] { "ready", "active" })
-            .AddCheck<AkkaClusterHealthCheck>("akka", tags: new[] { "ready", "active" })
-            .AddCheck<AdminRoleLeaderHealthCheck>("admin-leader", tags: new[] { "active" });
+            .AddTypeActivatedCheck<DatabaseHealthCheck<OtOpcUaConfigDbContext>>(
+                "configdb",
+                failureStatus: null,
+                tags: new[] { ZbHealthTags.Ready, ZbHealthTags.Active },
+                args: new DatabaseHealthCheckOptions<OtOpcUaConfigDbContext>
+                {
+                    ProbeQuery = static (db, ct) => db.Deployments.AsNoTracking().Take(1).ToListAsync(ct),
+                })
+            .AddTypeActivatedCheck<AkkaClusterHealthCheck>(
+                "akka",
+                failureStatus: null,
+                tags: new[] { ZbHealthTags.Ready, ZbHealthTags.Active },
+                args: AkkaClusterStatusPolicy.OtOpcUaCompat)
+            .AddTypeActivatedCheck<ActiveNodeHealthCheck>(
+                "admin-leader",
+                failureStatus: null,
+                tags: new[] { ZbHealthTags.Active },
+                args: "admin");
         return services;
     }
 
@@ -27,21 +42,7 @@ public static class HealthEndpoints
     /// <param name="app">The endpoint route builder.</param>
     public static IEndpointRouteBuilder MapOtOpcUaHealth(this IEndpointRouteBuilder app)
     {
-        // AllowAnonymous on all three — Traefik / k8s liveness probes / load-balancers
-        // hit these without credentials. Without it the AddOtOpcUaAuth fallback policy
-        // 401s every probe and Traefik marks every backend unhealthy.
-        app.MapHealthChecks("/health/ready", new HealthCheckOptions
-        {
-            Predicate = c => c.Tags.Contains("ready"),
-        }).AllowAnonymous();
-        app.MapHealthChecks("/health/active", new HealthCheckOptions
-        {
-            Predicate = c => c.Tags.Contains("active"),
-        }).AllowAnonymous();
-        app.MapHealthChecks("/healthz", new HealthCheckOptions
-        {
-            Predicate = _ => false, // process-liveness only — no probes run.
-        }).AllowAnonymous();
+        app.MapZbHealth();
         return app;
     }
 }

src/Server/ZB.MOM.WW.OtOpcUa.Host/ZB.MOM.WW.OtOpcUa.Host.csproj

@@ -27,6 +27,9 @@
         </PackageReference>
         <PackageReference Include="OpenTelemetry.Extensions.Hosting"/>
         <PackageReference Include="OpenTelemetry.Exporter.Prometheus.AspNetCore"/>
+        <PackageReference Include="ZB.MOM.WW.Health" />
+        <PackageReference Include="ZB.MOM.WW.Health.Akka" />
+        <PackageReference Include="ZB.MOM.WW.Health.EntityFrameworkCore" />
     </ItemGroup>
 
     <ItemGroup>

tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Tests/Runtime/GatewayGalaxyAlarmFeedLiveTests.cs

@@ -0,0 +1,82 @@
+using ZB.MOM.WW.MxGateway.Client;
+using Shouldly;
+using Xunit;
+using ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Runtime;
+
+namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Tests.Runtime;
+
+/// <summary>
+///     D.1 smoke (alarm-source leg): drives the REAL gateway <c>StreamAlarms</c> feed through the
+///     production lmxopcua consumer (<see cref="GatewayGalaxyAlarmFeed"/>) and asserts native alarm
+///     transitions — with operator comment, category, original raise time, and the mapped OPC UA
+///     severity bucket preserved — reach the driver-side boundary that feeds
+///     <c>IAlarmSource.OnAlarmEvent</c>.
+///     <para>
+///     Skip-gated: runs only when <c>MXGW_ENDPOINT</c> + <c>GALAXY_MXGW_API_KEY</c> are set to a
+///     reachable gateway. Captured 2026-05-29 against <c>10.100.0.48:5120</c> — see
+///     <c>docs/plans/alarms-d1-smoke-artifact.md</c>. Set <c>D1_SMOKE_OUT</c> to dump the observed
+///     transitions to a file for artifact capture.
+///     </para>
+/// </summary>
+[Trait("Category", "Integration")]
+public sealed class GatewayGalaxyAlarmFeedLiveTests
+{
+    [Fact]
+    public async Task Live_gateway_delivers_native_alarm_transitions_through_the_consumer()
+    {
+        var endpoint = Environment.GetEnvironmentVariable("MXGW_ENDPOINT");
+        var apiKey = Environment.GetEnvironmentVariable("GALAXY_MXGW_API_KEY");
+        if (string.IsNullOrWhiteSpace(endpoint) || string.IsNullOrWhiteSpace(apiKey))
+            Assert.Skip("Set MXGW_ENDPOINT + GALAXY_MXGW_API_KEY to run the live gateway alarm-feed smoke.");
+
+        var client = MxGatewayClient.Create(new MxGatewayClientOptions
+        {
+            Endpoint = new Uri(endpoint!, UriKind.Absolute),
+            ApiKey = apiKey!,
+            UseTls = false,
+            ConnectTimeout = TimeSpan.FromSeconds(10),
+            DefaultCallTimeout = TimeSpan.FromSeconds(30),
+            StreamTimeout = TimeSpan.FromSeconds(30),
+        });
+
+        var observed = new List<GalaxyAlarmTransition>();
+        var gotOne = new TaskCompletionSource<bool>(TaskCreationOptions.RunContinuationsAsynchronously);
+
+        // Wire the live client's StreamAlarms method group into the production consumer seam.
+        await using var feed = new GatewayGalaxyAlarmFeed(client.StreamAlarmsAsync, clientName: "D1Smoke");
+        feed.OnAlarmTransition += (_, t) =>
+        {
+            lock (observed) { observed.Add(t); }
+            gotOne.TrySetResult(true);
+        };
+        feed.Start();
+
+        // The stream opens with the active-alarm snapshot, so we expect ≥1 transition promptly.
+        await Task.WhenAny(gotOne.Task, Task.Delay(TimeSpan.FromSeconds(20), TestContext.Current.CancellationToken));
+
+        List<GalaxyAlarmTransition> snapshot;
+        lock (observed) snapshot = observed.ToList();
+
+        snapshot.ShouldNotBeEmpty(
+            "Live gateway should deliver at least the active-alarm snapshot through the lmxopcua consumer.");
+        var first = snapshot[0];
+        first.AlarmFullReference.ShouldNotBeNullOrWhiteSpace();
+        first.OpcUaSeverity.ShouldBeGreaterThan(0); // severity bucket mapping applied by the consumer
+
+        foreach (var t in snapshot.Take(8))
+            TestContext.Current.SendDiagnosticMessage(
+                $"{t.TransitionKind,-11} {t.AlarmFullReference}  sev={t.OpcUaSeverity}({t.SeverityBucket})  cat={t.Category}  comment='{t.OperatorComment}'");
+        TestContext.Current.SendDiagnosticMessage($"TOTAL consumer transitions observed: {snapshot.Count}");
+
+        // Deterministic artifact capture (only when D1_SMOKE_OUT is set).
+        var outPath = Environment.GetEnvironmentVariable("D1_SMOKE_OUT");
+        if (!string.IsNullOrWhiteSpace(outPath))
+        {
+            var lines = snapshot.Take(50).Select(t =>
+                $"{t.TransitionKind,-11} {t.AlarmFullReference} | sev={t.OpcUaSeverity}({t.SeverityBucket}) raw={t.RawMxAccessSeverity} | cat={t.Category} | comment='{t.OperatorComment}' | xitionUtc={t.TransitionTimestampUtc:o}");
+            await File.WriteAllLinesAsync(outPath!,
+                new[] { $"# consumer transitions observed: {snapshot.Count}" }.Concat(lines),
+                TestContext.Current.CancellationToken);
+        }
+    }
+}

tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Tests/ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Tests.csproj

@@ -25,6 +25,9 @@
 
     <ItemGroup>
         <PackageReference Include="ZB.MOM.WW.MxGateway.Contracts" />
+        <!-- Client package: only the Skip-gated live alarm-feed smoke (GatewayGalaxyAlarmFeedLiveTests)
+             constructs a real MxGatewayClient. Unit tests use the fake stream-factory seam. -->
+        <PackageReference Include="ZB.MOM.WW.MxGateway.Client" />
     </ItemGroup>
 
 </Project>