lmxopcua/src/Server/ZB.MOM.WW.OtOpcUa.Host/Health/ScriptRunnerHealthCheck.cs

using Microsoft.Extensions.Diagnostics.HealthChecks;
using ZB.MOM.WW.OtOpcUa.Core.Scripting.OutOfProcess;
using ZB.MOM.WW.OtOpcUa.Host.Configuration;

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

/// <summary>
///     Pure decision function for the script-runner probe (lmxopcua#780 design §10, owner decision §14 #12), factored
///     out of <see cref="ScriptRunnerHealthCheck"/> so the matrix is table-testable without worker processes.
/// </summary>
public static class ScriptRunnerHealthDecision
{
    /// <summary>
    ///     Maps the runner's status to a health status. <b>Never Unhealthy:</b> a sick script runner does not stop the
    ///     node serving driver data over OPC UA, so it must not fail readiness — on a redundant pair that would shift
    ///     ServiceLevel to the peer over a script problem. Degraded is still ready (200) but visible.
    /// </summary>
    /// <param name="status">The out-of-process runner's status, or null when every seam runs in process.</param>
    /// <returns>The status, a description and the per-shard data.</returns>
    public static (HealthStatus Status, string Description, IReadOnlyDictionary<string, object> Data) Evaluate(ScriptRunnerStatus? status)
    {
        if (status is null)
            return (HealthStatus.Healthy, "Scripts run in process (Scripting:Runner=InProcess).", new Dictionary<string, object>());

        var data = new Dictionary<string, object>(StringComparer.Ordinal)
        {
            ["state"] = status.State.ToString(),
            ["suspects"] = status.SuspectCount,
            ["quarantined"] = status.QuarantinedCount,
            ["peCache"] = status.PeCacheEnabled,
        };
        foreach (var shard in status.Shards)
        {
            data[$"shard.{shard.Label}"] = shard.Up
                ? $"up pid {shard.Pid}, {shard.InFlight} in flight"
                : shard.DownFor is { } downFor ? $"down {downFor.TotalSeconds:F0} s ({shard.ConsecutiveFailures} failure(s))" : "not started";
        }

        var down = status.Shards.Where(s => s.DownFor is not null).Select(s => s.Label).ToArray();
        return status.State switch
        {
            ScriptRunnerState.Ready => (HealthStatus.Healthy, "Out-of-process script runner ready.", data),
            ScriptRunnerState.Degraded => (HealthStatus.Degraded,
                $"Out-of-process script runner degraded: ScriptWorker {string.Join(", ", down)} down; scripts placed there report BadResourceUnavailable until it restarts.",
                data),
            _ => (HealthStatus.Degraded,
                "Out-of-process script runner unavailable (circuit open): every ScriptWorker shard is down; every compiled script reports BadResourceUnavailable. OPC UA keeps serving driver data.",
                data),
        };
    }
}

/// <summary>The script-runner readiness component: Healthy, or Degraded-but-ready (see <see cref="ScriptRunnerHealthDecision"/>).</summary>
/// <param name="selection">The node's runner selection; null on nodes that never register one.</param>
public sealed class ScriptRunnerHealthCheck(ScriptRunnerSelection? selection) : IHealthCheck
{
    /// <summary>The check's registration name.</summary>
    public const string Name = "script-runner";

    /// <inheritdoc />
    public Task<HealthCheckResult> CheckHealthAsync(HealthCheckContext context, CancellationToken cancellationToken = default)
    {
        var (status, description, data) = ScriptRunnerHealthDecision.Evaluate(selection?.Status());
        return Task.FromResult(status == HealthStatus.Healthy
            ? HealthCheckResult.Healthy(description, data)
            : HealthCheckResult.Degraded(description, data: data));
    }
}