feat(health.akka): cluster health check with configurable status policy

2026-06-01 06:47:29 -04:00
parent 1ab2f32e8e
commit 25dd328280
4 changed files with 315 additions and 0 deletions
@@ -0,0 +1,51 @@
+using Akka.Actor;
+using Akka.Cluster;
+using Microsoft.Extensions.DependencyInjection;
+using Microsoft.Extensions.Diagnostics.HealthChecks;
+
+namespace ZB.MOM.WW.Health.Akka;
+
+/// <summary>
+/// Health check that maps the local node's Akka cluster membership status to a
+/// <see cref="HealthStatus"/> through a configurable <see cref="AkkaClusterStatusPolicy"/>.
+/// Register to the <see cref="ZbHealthTags.Ready"/> tag (recommended <c>[ready, active]</c>).
+/// </summary>
+/// <remarks>
+/// The <see cref="ActorSystem"/> is resolved lazily from the service provider. If it is not yet
+/// available — e.g. during startup before Akka is initialised — the check returns
+/// <see cref="HealthStatus.Degraded"/> rather than throwing, so it is safe to register before Akka
+/// is fully up.
+/// </remarks>
+public sealed class AkkaClusterHealthCheck : IHealthCheck
+{
+    private readonly IServiceProvider _serviceProvider;
+    private readonly AkkaClusterStatusPolicy _policy;
+
+    /// <summary>Initializes a new <see cref="AkkaClusterHealthCheck"/>.</summary>
+    /// <param name="serviceProvider">
+    /// The application service provider. The <see cref="ActorSystem"/> is resolved lazily so the
+    /// check is startup-safe: if no <see cref="ActorSystem"/> is registered yet the result is Degraded.
+    /// </param>
+    /// <param name="policy">The status-to-health mapping policy to apply.</param>
+    public AkkaClusterHealthCheck(IServiceProvider serviceProvider, AkkaClusterStatusPolicy policy)
+    {
+        _serviceProvider = serviceProvider ?? throw new ArgumentNullException(nameof(serviceProvider));
+        _policy = policy ?? throw new ArgumentNullException(nameof(policy));
+    }
+
+    /// <inheritdoc />
+    public Task<HealthCheckResult> CheckHealthAsync(
+        HealthCheckContext context,
+        CancellationToken cancellationToken = default)
+    {
+        var system = _serviceProvider.GetService<ActorSystem>();
+        if (system is null)
+            return Task.FromResult(HealthCheckResult.Degraded("ActorSystem not yet available."));
+
+        var status = Cluster.Get(system).SelfMember.Status;
+        var health = _policy.Evaluate(status);
+        var description = $"Akka cluster member status: {status}";
+
+        return Task.FromResult(new HealthCheckResult(health, description));
+    }
+}