using Microsoft.AspNetCore.Builder; using Microsoft.Extensions.Configuration; using Microsoft.Extensions.DependencyInjection; using Microsoft.Extensions.Diagnostics.HealthChecks; using Microsoft.Extensions.Options; using ZB.MOM.WW.Health; using ZB.MOM.WW.Health.Akka; using ZB.MOM.WW.LocalDb; using ZB.MOM.WW.LocalDb.Registration; using ZB.MOM.WW.ScadaBridge.Commons.Messages.Health; using ZB.MOM.WW.ScadaBridge.HealthMonitoring; using ZB.MOM.WW.ScadaBridge.Host.Health; namespace ZB.MOM.WW.ScadaBridge.Host.Tests; /// /// Site-node health endpoints. Site nodes previously served no health surface at all — only gRPC on /// the HTTP/2 listener and /metrics on the HTTP/1.1 one — so the family overview dashboard /// had no uniform way to probe them. These tests pin the three checks the site now registers and /// the tier each one lands in. /// /// The registration assertions build the REAL container from /// rather than a hand-assembled /// ServiceCollection, for the reason spelled out in : /// this family's wiring defects have consistently been ones that only a container-built graph /// catches. Each registration is additionally ACTIVATED through its factory, so a check that is /// registered but cannot resolve its dependencies fails here instead of at the first live probe. /// /// public class SiteHealthCheckTests : IDisposable { private readonly WebApplication _host; private readonly string _tempDbPath; private readonly string _tempSiteDbPath; private readonly string _tempTrackingDbPath; public SiteHealthCheckTests() { var stamp = Guid.NewGuid(); _tempDbPath = Path.Combine(Path.GetTempPath(), $"scadabridge_health_localdb_{stamp}.db"); _tempSiteDbPath = Path.Combine(Path.GetTempPath(), $"scadabridge_health_site_{stamp}.db"); _tempTrackingDbPath = Path.Combine(Path.GetTempPath(), $"scadabridge_health_track_{stamp}.db"); var builder = WebApplication.CreateBuilder(); builder.Configuration.Sources.Clear(); builder.Configuration.AddInMemoryCollection(new Dictionary { ["ScadaBridge:Node:Role"] = "Site", ["ScadaBridge:Node:NodeName"] = "node-a", ["ScadaBridge:Node:NodeHostname"] = "test-site", ["ScadaBridge:Node:SiteId"] = "TestSite", ["ScadaBridge:Node:RemotingPort"] = "0", ["ScadaBridge:Node:GrpcPort"] = "0", ["ScadaBridge:Database:SiteDbPath"] = _tempSiteDbPath, ["ScadaBridge:OperationTracking:ConnectionString"] = $"Data Source={_tempTrackingDbPath}", ["ScadaBridge:Cluster:SeedNodes:0"] = "akka.tcp://scadabridge@localhost:2551", ["ScadaBridge:Cluster:SeedNodes:1"] = "akka.tcp://scadabridge@localhost:2552", ["LocalDb:Path"] = _tempDbPath, }); builder.Services.AddGrpc(); builder.Services.AddSingleton(); SiteServiceRegistration.Configure(builder.Services, builder.Configuration); AkkaHostedServiceRemover.RemoveAkkaHostedServiceOnly(builder.Services); _host = builder.Build(); } public void Dispose() { (_host as IDisposable)?.Dispose(); foreach (var path in new[] { _tempDbPath, _tempSiteDbPath, _tempTrackingDbPath }) { try { File.Delete(path); } catch { /* best effort */ } } GC.SuppressFinalize(this); } private IReadOnlyList Registrations => _host.Services.GetRequiredService>().Value.Registrations.ToList(); [Fact] public void Site_RegistersExactlyTheThreeSiteChecks() { // Exact-set, not "contains": an extra check silently changes what /health/ready means for // every consumer, and a site node inheriting a central-only probe is precisely the mistake // this asserts against. Assert.Equal( new[] { "active-node", "akka-cluster", "localdb" }, Registrations.Select(r => r.Name).OrderBy(n => n, StringComparer.Ordinal).ToArray()); } [Theory] [InlineData("akka-cluster", ZbHealthTags.Ready)] [InlineData("localdb", ZbHealthTags.Ready)] [InlineData("active-node", ZbHealthTags.Active)] public void Site_ChecksCarryTheirIntendedTier(string name, string expectedTag) { var registration = Assert.Single(Registrations, r => r.Name == name); // Exactly one tier tag each: MapZbHealth selects by tag, so a check tagged both Ready and // Active would put standby-ness into readiness and drop the standby out of readiness too. Assert.Equal(new[] { expectedTag }, registration.Tags.ToArray()); } [Theory] [InlineData("akka-cluster", typeof(AkkaClusterHealthCheck))] [InlineData("localdb", typeof(SiteLocalDbHealthCheck))] [InlineData("active-node", typeof(SitePairActiveNodeHealthCheck))] public void Site_ChecksActivateToTheIntendedType(string name, Type expected) { var registration = Assert.Single(Registrations, r => r.Name == name); // Running the factory is the point: a type-activated check whose constructor dependencies // are not registered on site would throw here rather than on the first probe in production. var check = registration.Factory(_host.Services); Assert.IsType(expected, check); } [Fact] public void Site_ActiveNodeCheck_IsNotCentralsRoleLessOldestCheck() { // Central's OldestNodeActiveHealthCheck calls SelfIsOldest(cluster) with no role argument. // On a mesh carrying more than one site's members that computes "oldest" across the wrong // member set, so a site node could report Active purely for being the oldest member overall. var check = Assert.Single(Registrations, r => r.Name == "active-node").Factory(_host.Services); Assert.IsNotType(check); } [Theory] [InlineData("database")] [InlineData("required-singletons")] public void Site_DoesNotRegisterCentralOnlyChecks(string centralOnlyName) { // Positive control first: if the harness ever stopped registering health checks at all, // every "is absent" assertion below would pass vacuously and this test would be worthless. Assert.Contains(Registrations, r => r.Name == "akka-cluster"); Assert.DoesNotContain(Registrations, r => r.Name == centralOnlyName); } [Fact] public async Task Site_LocalDbCheck_ReportsHealthyAgainstTheRealSiteDatabase() { // Behaviour, not wiring: the probe runs against the consolidated site database this // composition actually built, so a check that resolves but cannot query fails here. var check = (SiteLocalDbHealthCheck)Assert.Single(Registrations, r => r.Name == "localdb") .Factory(_host.Services); var result = await check.CheckHealthAsync(NewContext("localdb", check)); Assert.Equal(HealthStatus.Healthy, result.Status); } [Fact] public async Task Site_LocalDbCheck_EnrichesWithReplicationStateWithoutFailingOnDefaultOff() { // Replication ships default-OFF, so the unreplicated steady state must stay Healthy while // still surfacing the state as data — enrichment must never become a verdict. var check = (SiteLocalDbHealthCheck)Assert.Single(Registrations, r => r.Name == "localdb") .Factory(_host.Services); var result = await check.CheckHealthAsync(NewContext("localdb", check)); Assert.Equal(HealthStatus.Healthy, result.Status); Assert.False(Assert.IsType(result.Data["replicationConnected"])); Assert.Equal(0L, Assert.IsType(result.Data["replicationOplogBacklog"])); } [Fact] public async Task Site_LocalDbCheck_ReportsUnhealthyWhenTheStoreIsUnreachable() { var check = new SiteLocalDbHealthCheck(new ThrowingLocalDb()); var result = await check.CheckHealthAsync(NewContext("localdb", check)); Assert.Equal(HealthStatus.Unhealthy, result.Status); } [Theory] [InlineData(true, HealthStatus.Healthy)] [InlineData(false, HealthStatus.Unhealthy)] public async Task Site_ActiveNodeCheck_SplitsPrimaryFromStandby(bool selfIsPrimary, HealthStatus expected) { // 200 on the primary / 503 on the standby is the same contract central publishes, so a // consumer reads one active-node meaning fleet-wide. var check = new SitePairActiveNodeHealthCheck(new StubNodeProvider(selfIsPrimary)); var result = await check.CheckHealthAsync(NewContext("active-node", check)); Assert.Equal(expected, result.Status); } private static HealthCheckContext NewContext(string name, IHealthCheck check) => new() { Registration = new HealthCheckRegistration(name, check, HealthStatus.Unhealthy, tags: null), }; private sealed class StubNodeProvider(bool selfIsPrimary) : IClusterNodeProvider { public bool SelfIsPrimary { get; } = selfIsPrimary; public IReadOnlyList GetClusterNodes() => []; } private sealed class ThrowingLocalDb : ILocalDb { public Task ExecuteAsync(string sql, object? parameters = null, CancellationToken ct = default) => throw new InvalidOperationException("store unreachable"); public Task> QueryAsync( string sql, Func map, object? parameters = null, CancellationToken ct = default) => throw new InvalidOperationException("store unreachable"); public Task BeginTransactionAsync(CancellationToken ct = default) => throw new InvalidOperationException("store unreachable"); public Microsoft.Data.Sqlite.SqliteConnection CreateConnection() => throw new InvalidOperationException("store unreachable"); public ReplicatedTable RegisterReplicated(string tableName) => throw new InvalidOperationException("store unreachable"); public IReadOnlyDictionary ReplicatedTables => throw new InvalidOperationException("store unreachable"); } }