lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Host.Tests/Health/ScriptRunnerHealthCheckTests.cs

using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Diagnostics.HealthChecks;
using Microsoft.Extensions.Options;
using Shouldly;
using Xunit;
using ZB.MOM.WW.Health;
using ZB.MOM.WW.OtOpcUa.Core.Scripting.OutOfProcess;
using ZB.MOM.WW.OtOpcUa.Host.Health;

namespace ZB.MOM.WW.OtOpcUa.Host.Tests.Health;

/// <summary>
///     lmxopcua#780 design §10, owner decision §14 #12: the script runner is a READY-tier component that is degraded but
///     still ready when its circuit is open — a sick runner must never fail readiness (on a redundant pair that would move
///     ServiceLevel to the peer over a script problem while OPC UA still serves driver data).
/// </summary>
public sealed class ScriptRunnerHealthCheckTests
{
    private static ScriptWorkerShardStatus Shard(string label, bool up, double? downSeconds = null)
        => new(label, label == "iso", up, downSeconds is { } s ? TimeSpan.FromSeconds(s) : null, up ? 1234 : null, up ? 0 : 3, 0, 0, 0);

    private static ScriptRunnerStatus Status(ScriptRunnerState state, params ScriptWorkerShardStatus[] shards)
        => new(state, shards, SuspectCount: 0, QuarantinedCount: 0, PeCacheEnabled: true);

    [Fact]
    public void In_process_is_healthy()
        => ScriptRunnerHealthDecision.Evaluate(null).Status.ShouldBe(HealthStatus.Healthy);

    [Fact]
    public void Ready_is_healthy()
        => ScriptRunnerHealthDecision.Evaluate(Status(ScriptRunnerState.Ready, Shard("0", true), Shard("1", true))).Status
            .ShouldBe(HealthStatus.Healthy);

    [Fact]
    public void A_shard_down_is_degraded_and_names_it()
    {
        var (status, description, data) = ScriptRunnerHealthDecision.Evaluate(
            Status(ScriptRunnerState.Degraded, Shard("0", true), Shard("1", false, 4)));
        status.ShouldBe(HealthStatus.Degraded);
        description.ShouldContain("ScriptWorker 1 down");
        data["shard.1"].ShouldBe("down 4 s (3 failure(s))");
        data["state"].ShouldBe("Degraded");
    }

    /// <summary>★ decision 12: the circuit-open runner is Degraded — never Unhealthy, so /health/ready stays 200.</summary>
    [Fact]
    public void An_open_circuit_is_degraded_never_unhealthy()
    {
        var (status, description, _) = ScriptRunnerHealthDecision.Evaluate(
            Status(ScriptRunnerState.Unavailable, Shard("0", false, 200), Shard("1", false, 200)));
        status.ShouldBe(HealthStatus.Degraded);
        description.ShouldContain("circuit open");
    }

    [Theory]
    [InlineData(false, false)]
    [InlineData(true, true)]
    public async Task It_is_registered_on_the_ready_tier_only_on_driver_nodes(bool hasDriver, bool registered)
    {
        var registrations = new ServiceCollection()
            .AddOtOpcUaHealth(hasAdmin: true, hasDriver: hasDriver)
            .BuildServiceProvider()
            .GetRequiredService<IOptions<HealthCheckServiceOptions>>()
            .Value.Registrations
            .Where(r => r.Name == ScriptRunnerHealthCheck.Name)
            .ToList();
        if (!registered)
        {
            registrations.ShouldBeEmpty();
            return;
        }
        var registration = registrations.ShouldHaveSingleItem();
        registration.Tags.ShouldBe([ZbHealthTags.Ready]);
        // A node without a runner selection (in-process, or a harness) resolves it as Healthy.
        var check = registration.Factory(new ServiceCollection().BuildServiceProvider()).ShouldBeOfType<ScriptRunnerHealthCheck>();
        (await check.CheckHealthAsync(new HealthCheckContext { Registration = registration }, CancellationToken.None))
            .Status.ShouldBe(HealthStatus.Healthy);
    }

    [Theory]
    [InlineData(ScriptRunnerState.Ready)]
    [InlineData(ScriptRunnerState.Degraded)]
    [InlineData(ScriptRunnerState.Unavailable)]
    public void Shadow_is_healthy_whatever_its_worker_pool_does(ScriptRunnerState shadowState)
    {
        // lmxopcua#780 P2: under Shadow every published value is in process — the shadow pool must never move readiness.
        var stats = new ZB.MOM.WW.OtOpcUa.Core.Scripting.ScriptShadowStats(10, 7, 3, 1, 2, 1, 0);
        var (status, description, data) = ScriptRunnerHealthDecision.Evaluate(
            null, (Status(shadowState, Shard("0", shadowState == ScriptRunnerState.Ready, 200)), stats));
        status.ShouldBe(HealthStatus.Healthy);
        description.ShouldContain("Shadow");
        description.ShouldContain("3 mismatch(es)");
        data["mode"].ShouldBe("Shadow");
        data["shadow.state"].ShouldBe(shadowState.ToString());
        data["shadow.mismatched"].ShouldBe(3L);
        data["shadow.dropped"].ShouldBe(3L);
    }
}