ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.Host.Tests/HealthCheckTests.cs

using System.Linq;
using Microsoft.AspNetCore.Mvc.Testing;
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.ScadaBridge.Host.Health;

namespace ZB.MOM.WW.ScadaBridge.Host.Tests;

/// <summary>
/// WP-12: Tests for the three-tier health endpoints after adopting the shared
/// ZB.MOM.WW.Health probes. Verifies that /health/ready, /health/active and the new
/// /healthz tier are mapped, and that the readiness/active tier split is now carried by
/// the canonical <see cref="ZbHealthTags"/> (Ready for database + akka-cluster, Active for
/// active-node) rather than by check-name predicates. These are pure route/tag assertions
/// — they require no database, LDAP, or formed Akka cluster.
/// </summary>
[Collection(HostBootCollection.Name)]
public class HealthCheckTests : IDisposable
{
    private readonly List<IDisposable> _disposables = new();

    public HealthCheckTests()
    {
        // Host-003: connection strings are externalised; supply them via env vars.
        _disposables.Add(new CentralDbTestEnvironment());
    }

    public void Dispose()
    {
        foreach (var d in _disposables)
        {
            try { d.Dispose(); } catch { /* best effort */ }
        }
    }

    private WebApplicationFactory<Program> CreateCentralFactory()
    {
        var factory = new WebApplicationFactory<Program>()
            .WithWebHostBuilder(builder =>
            {
                builder.ConfigureAppConfiguration((context, config) =>
                {
                    config.AddInMemoryCollection(new Dictionary<string, string?>
                    {
                        ["ScadaBridge:Node:NodeName"] = "central-a",
                        ["ScadaBridge:Node:NodeHostname"] = "localhost",
                        ["ScadaBridge:Node:RemotingPort"] = "0",
                        ["ScadaBridge:Cluster:SeedNodes:0"] = "akka.tcp://scadabridge@localhost:2551",
                        ["ScadaBridge:Cluster:SeedNodes:1"] = "akka.tcp://scadabridge@localhost:2552",
                        ["ScadaBridge:Database:SkipMigrations"] = "true",
                    });
                });
                builder.UseSetting("ScadaBridge:Node:Role", "Central");
                builder.UseSetting("ScadaBridge:Database:SkipMigrations", "true");
            });
        _disposables.Add(factory);
        return factory;
    }

    private static IEnumerable<HealthCheckRegistration> Registrations(WebApplicationFactory<Program> factory) =>
        factory.Services.GetRequiredService<IOptions<HealthCheckServiceOptions>>().Value.Registrations;

    [Fact]
    public async Task HealthReady_Endpoint_IsMapped()
    {
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();
            var client = factory.CreateClient();
            _disposables.Add(client);

            var response = await client.GetAsync("/health/ready");

            // The endpoint exists and returns a status code. With test infrastructure
            // (no real DB / cluster) the readiness checks may report Unhealthy, so we
            // accept either 200 (Healthy/Degraded) or 503 (Unhealthy) — never 404.
            Assert.NotEqual(System.Net.HttpStatusCode.NotFound, response.StatusCode);
            Assert.True(
                response.StatusCode == System.Net.HttpStatusCode.OK ||
                response.StatusCode == System.Net.HttpStatusCode.ServiceUnavailable,
                $"Expected 200 or 503, got {(int)response.StatusCode}");
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }

    [Fact]
    public async Task HealthActive_Endpoint_IsMapped()
    {
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();
            var client = factory.CreateClient();
            _disposables.Add(client);

            var response = await client.GetAsync("/health/active");

            Assert.NotEqual(System.Net.HttpStatusCode.NotFound, response.StatusCode);
            Assert.True(
                response.StatusCode == System.Net.HttpStatusCode.OK ||
                response.StatusCode == System.Net.HttpStatusCode.ServiceUnavailable,
                $"Expected 200 or 503, got {(int)response.StatusCode}");
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }

    [Fact]
    public async Task Healthz_LivenessEndpoint_IsMappedAndReturns200()
    {
        // New tier added by adopting the shared library: /healthz runs no checks, so it
        // returns 200 as long as the process is up — independent of DB / cluster state.
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();
            var client = factory.CreateClient();
            _disposables.Add(client);

            var response = await client.GetAsync("/healthz");

            Assert.Equal(System.Net.HttpStatusCode.OK, response.StatusCode);
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }

    [Fact]
    public void ReadyTier_Carries_Database_And_AkkaCluster()
    {
        // Host-001 regression guard: readiness reflects cluster membership + DB connectivity
        // only (REQ-HOST-4a), NOT cluster leadership. The split is now carried by the Ready tag
        // rather than a check-name predicate: database + akka-cluster are Ready-tagged, and the
        // leader-only active-node check is NOT — so a fully operational standby central node
        // still reports ready on /health/ready.
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();

            var registrations = Registrations(factory).ToDictionary(r => r.Name);

            Assert.True(registrations.ContainsKey("database"), "Expected a 'database' health check.");
            Assert.True(registrations.ContainsKey("akka-cluster"), "Expected an 'akka-cluster' health check.");

            Assert.Contains(ZbHealthTags.Ready, registrations["database"].Tags);
            Assert.Contains(ZbHealthTags.Ready, registrations["akka-cluster"].Tags);

            // M2.14 (#28): readiness ALSO reflects "required cluster singletons running"
            // (REQ-HOST-4a). The Central-only required-singletons check is Ready-tagged so
            // it gates /health/ready alongside database + akka-cluster, but is leadership-
            // agnostic (it does NOT carry the Active tag), so a ready standby stays ready.
            Assert.True(registrations.ContainsKey("required-singletons"),
                "Expected a 'required-singletons' health check.");
            Assert.Contains(ZbHealthTags.Ready, registrations["required-singletons"].Tags);
            Assert.DoesNotContain(ZbHealthTags.Active, registrations["required-singletons"].Tags);

            // The leader-only active-node check must NOT be on the readiness tier.
            Assert.DoesNotContain(ZbHealthTags.Ready, registrations["active-node"].Tags);
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }

    [Fact]
    public void ActiveTier_Carries_ActiveNode_And_Database()
    {
        // Review 01 [High]: /health/active = oldest Up member AND database reachable, so a
        // DB-dead active node is pulled from Traefik rotation. active-node + database carry
        // the Active tag; akka-cluster does not (readiness-only).
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();

            var registrations = Registrations(factory).ToDictionary(r => r.Name);

            Assert.True(registrations.ContainsKey("active-node"), "Expected an 'active-node' health check.");
            Assert.Contains(ZbHealthTags.Active, registrations["active-node"].Tags);

            // Database gates active too (DB-dead active node must drop out of rotation).
            Assert.Contains(ZbHealthTags.Active, registrations["database"].Tags);
            Assert.DoesNotContain(ZbHealthTags.Active, registrations["akka-cluster"].Tags);
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }

    [Fact]
    public void ActiveNodeCheck_IsHostLocalOldestNodeCheck()
    {
        // The shared package's ActiveNodeHealthCheck is LEADER-based (review 01 [High]):
        // during a partition both nodes think they lead and Traefik serves both. The
        // active-node check must be the host-local oldest-member check instead.
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();

            var active = Registrations(factory).Single(r => r.Name == "active-node");
            Assert.Contains(ZbHealthTags.Active, active.Tags);

            var check = active.Factory(factory.Services);
            Assert.IsType<OldestNodeActiveHealthCheck>(check);
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }

    [Fact]
    public void DatabaseCheck_AlsoGatesActive()
    {
        // Review 01 [High] recommendation: /health/active should require Ready
        // (DB reachable) in addition to singleton-host status, so a DB-dead
        // active node is pulled from Traefik rotation.
        var previousEnv = Environment.GetEnvironmentVariable("DOTNET_ENVIRONMENT");
        try
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", "Central");
            var factory = CreateCentralFactory();

            var registrations = Registrations(factory).ToDictionary(r => r.Name);
            var db = registrations["database"];
            Assert.Contains(ZbHealthTags.Ready, db.Tags);
            Assert.Contains(ZbHealthTags.Active, db.Tags);
        }
        finally
        {
            Environment.SetEnvironmentVariable("DOTNET_ENVIRONMENT", previousEnv);
        }
    }
}