Merge feat/telemetry-followons: telemetry follow-ons for OtOpcUa

Serilog.AspNetCore/Extensions.Hosting/Settings.Configuration aligned to 10.0.0;
config-driven OTLP exporter opt-in (default Prometheus; also makes recorded
spans exportable when OTLP is configured).

.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

@@ -79,11 +79,11 @@
     <PackageVersion Include="OpenTelemetry.Extensions.Hosting" Version="1.15.3" />
     <PackageVersion Include="Polly.Core" Version="8.6.6" />
     <PackageVersion Include="S7netplus" Version="0.20.0" />
-    <PackageVersion Include="Serilog" Version="4.3.0" />
+    <PackageVersion Include="Serilog" Version="4.3.1" />
-    <PackageVersion Include="Serilog.AspNetCore" Version="9.0.0" />
+    <PackageVersion Include="Serilog.AspNetCore" Version="10.0.0" />
-    <PackageVersion Include="Serilog.Extensions.Hosting" Version="9.0.0" />
+    <PackageVersion Include="Serilog.Extensions.Hosting" Version="10.0.0" />
     <PackageVersion Include="Serilog.Formatting.Compact" Version="3.0.0" />
-    <PackageVersion Include="Serilog.Settings.Configuration" Version="9.0.0" />
+    <PackageVersion Include="Serilog.Settings.Configuration" Version="10.0.0" />
     <PackageVersion Include="Serilog.Sinks.Console" Version="6.0.0" />
     <PackageVersion Include="Serilog.Sinks.File" Version="7.0.0" />
     <PackageVersion Include="Shouldly" Version="4.3.0" />
@@ -96,6 +96,11 @@
     <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.Telemetry" Version="0.1.0" />
+    <PackageVersion Include="ZB.MOM.WW.Telemetry.Serilog" 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

@@ -1,7 +1,23 @@
 <?xml version="1.0" encoding="utf-8"?>
 <configuration>
   <packageSources>
+    <clear />
     <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.*" />
+      <package pattern="ZB.MOM.WW.Telemetry" />
+      <package pattern="ZB.MOM.WW.Telemetry.*" />
+    </packageSource>
+  </packageSourceMapping>
 </configuration>

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

@@ -3,6 +3,12 @@
 > **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"

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
+    /// Registers the shared ZB.MOM.WW health probes. Tier semantics preserved: configdb + akka on
-    /// probes. Mirrors ScadaLink's three-tier pattern: <c>ready</c> = boot ok; <c>active</c> =
+    /// ready+active; admin-leader on active only.
-    /// fully serving traffic; <c>healthz</c> = bare process liveness.
     /// </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" })
+            .AddTypeActivatedCheck<DatabaseHealthCheck<OtOpcUaConfigDbContext>>(
-            .AddCheck<AkkaClusterHealthCheck>("akka", tags: new[] { "ready", "active" })
+                "configdb",
-            .AddCheck<AdminRoleLeaderHealthCheck>("admin-leader", tags: new[] { "active" });
+                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
+        app.MapZbHealth();
-        // 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();
         return app;
     }
 }

src/Server/ZB.MOM.WW.OtOpcUa.Host/Observability/ObservabilityExtensions.cs

@@ -1,6 +1,6 @@
-using OpenTelemetry.Metrics;
+using Microsoft.Extensions.Configuration;
-using OpenTelemetry.Trace;
 using ZB.MOM.WW.OtOpcUa.Commons.Observability;
+using ZB.MOM.WW.Telemetry;
 
 namespace ZB.MOM.WW.OtOpcUa.Host.Observability;
 
@@ -15,16 +15,25 @@ public static class ObservabilityExtensions
 {
     /// <summary>Adds OtOpcUa observability (metrics and tracing) to the service collection.</summary>
     /// <param name="services">The service collection to add observability services to.</param>
-    public static IServiceCollection AddOtOpcUaObservability(this IServiceCollection services)
+    /// <param name="configuration">
+    /// Configuration read for the opt-in OTLP exporter. <c>OtOpcUa:Telemetry:Exporter</c>
+    /// (parsed case-insensitively to <see cref="ZbExporter"/>) switches to OTLP when set to
+    /// <c>Otlp</c>; <c>OtOpcUa:Telemetry:OtlpEndpoint</c> sets the OTLP endpoint. With no
+    /// config the exporter stays Prometheus (the default).
+    /// </param>
+    public static IServiceCollection AddOtOpcUaObservability(this IServiceCollection services, IConfiguration configuration)
     {
-        services.AddOpenTelemetry()
+        return services.AddZbTelemetry(o =>
-            .WithMetrics(b => b
+        {
-                .AddMeter(OtOpcUaTelemetry.MeterName)
+            o.ServiceName = "otopcua";
-                .AddPrometheusExporter())
+            o.Meters = [OtOpcUaTelemetry.MeterName];
-            .WithTracing(b => b
+            o.ActivitySources = [OtOpcUaTelemetry.ActivitySourceName];
-                .AddSource(OtOpcUaTelemetry.ActivitySourceName));
+            if (Enum.TryParse<ZbExporter>(configuration["OtOpcUa:Telemetry:Exporter"], ignoreCase: true, out var exporter))
-
+                o.Exporter = exporter;
-        return services;
+            var otlp = configuration["OtOpcUa:Telemetry:OtlpEndpoint"];
+            if (!string.IsNullOrWhiteSpace(otlp))
+                o.OtlpEndpoint = otlp;
+        });
     }
 
     /// <summary>
@@ -35,7 +44,7 @@ public static class ObservabilityExtensions
     /// <param name="app">The endpoint route builder.</param>
     public static IEndpointRouteBuilder MapOtOpcUaMetrics(this IEndpointRouteBuilder app)
     {
-        app.MapPrometheusScrapingEndpoint("/metrics");
+        app.MapZbMetrics();
         return app;
     }
 }

src/Server/ZB.MOM.WW.OtOpcUa.Host/Program.cs

@@ -20,6 +20,7 @@ using ZB.MOM.WW.OtOpcUa.Runtime;
 using ZB.MOM.WW.OtOpcUa.Security;
 using ZB.MOM.WW.OtOpcUa.Security.Endpoints;
 using ZB.MOM.WW.OtOpcUa.Security.Ldap;
+using ZB.MOM.WW.Telemetry.Serilog;
 
 // Roles drive the entire conditional wiring below — see ZB.MOM.WW.OtOpcUa.Cluster.RoleParser.
 var roles = RoleParser.Parse(Environment.GetEnvironmentVariable("OTOPCUA_ROLES"));
@@ -45,11 +46,10 @@ var roleSuffix = roles.Length == 0 ? null : string.Join('-', roles.OrderBy(r =>
 if (roleSuffix is not null)
     builder.Configuration.AddJsonFile($"appsettings.{roleSuffix}.json", optional: true, reloadOnChange: true);
 
-// Serilog — rolling daily file sink per CLAUDE.md. Console for local dev.
+// Serilog — shared ZB.MOM.WW.Telemetry bootstrap. Sinks (Console + rolling daily file)
-builder.Host.UseSerilog((ctx, lc) => lc
+// now live in appsettings.json (ReadFrom.Configuration); AddZbSerilog layers in the
-    .ReadFrom.Configuration(ctx.Configuration)
+// shared NodeHostname / TraceContext / Redaction enrichers and trace correlation.
-    .WriteTo.Console()
+builder.AddZbSerilog(o => o.ServiceName = "otopcua");
-    .WriteTo.File("logs/otopcua-.log", rollingInterval: RollingInterval.Day));
 
 // Windows-service registration is handled at install time by scripts/install/Install-Services.ps1
 // (Task 62) rather than in-process, so the binary stays cross-platform-compilable.
@@ -135,7 +135,7 @@ if (hasAdmin)
 }
 
 builder.Services.AddOtOpcUaHealth();
-builder.Services.AddOtOpcUaObservability();
+builder.Services.AddOtOpcUaObservability(builder.Configuration);
 
 var app = builder.Build();
 app.UseSerilogRequestLogging();

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

@@ -27,6 +27,11 @@
         </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" />
+        <PackageReference Include="ZB.MOM.WW.Telemetry" />
+        <PackageReference Include="ZB.MOM.WW.Telemetry.Serilog" />
     </ItemGroup>
 
     <ItemGroup>

src/Server/ZB.MOM.WW.OtOpcUa.Host/appsettings.json

@@ -1 +1,9 @@
-{}
+{
+  "Serilog": {
+    "Using": [ "Serilog.Sinks.Console", "Serilog.Sinks.File" ],
+    "WriteTo": [
+      { "Name": "Console" },
+      { "Name": "File", "Args": { "path": "logs/otopcua-.log", "rollingInterval": "Day" } }
+    ]
+  }
+}