ScadaBridge/src/ZB.MOM.WW.ScadaBridge.AuditLog/Central/HeadExport/AuditChainHeadExportStatus.cs

using System.Diagnostics.Metrics;
using ZB.MOM.WW.ScadaBridge.Commons.Observability;

namespace ZB.MOM.WW.ScadaBridge.AuditLog.Central.HeadExport;

/// <summary>
/// Health signal of the off-box chain-head export (ScadaBridge#115). Updated by
/// <see cref="AuditChainHeadExportService"/> on every tick; read by the Host's
/// <c>audit-chain-head-export</c> /health/ready check. A sink that stays down used to be a
/// log line only, silently stopping the external anchor.
/// </summary>
public sealed class AuditChainHeadExportStatus
{
    private static readonly Meter Meter = new(ScadaBridgeTelemetry.MeterName);

    private static readonly Counter<long> FailuresCounter =
        Meter.CreateCounter<long>("scadabridge.audit.chain_head_export.failures", unit: "1",
            description: "AuditLog chain-head export ticks that failed to read or write the heads (sink offline / unreachable); retried next tick.");

    private readonly object _gate = new();
    private long _totalFailures;
    private int _consecutiveFailures;
    private DateTime? _lastSuccessUtc;
    private DateTime? _lastFailureUtc;
    private string? _lastError;
    private DateTime? _startedUtc;

    /// <summary>Whether the export is running at all (false = disabled, nothing to report).</summary>
    public bool Enabled { get; private set; }

    /// <summary>Minutes between export ticks (for the staleness test).</summary>
    public int IntervalMinutes { get; private set; } = 60;

    /// <summary>Total failed ticks since process start.</summary>
    public long TotalFailures { get { lock (_gate) { return _totalFailures; } } }

    /// <summary>Failed ticks since the last success.</summary>
    public int ConsecutiveFailures { get { lock (_gate) { return _consecutiveFailures; } } }

    /// <summary>UTC time of the last successful tick, or null.</summary>
    public DateTime? LastSuccessUtc { get { lock (_gate) { return _lastSuccessUtc; } } }

    /// <summary>UTC time of the last failed tick, or null.</summary>
    public DateTime? LastFailureUtc { get { lock (_gate) { return _lastFailureUtc; } } }

    /// <summary>Message of the last failure (never a secret: the exception message only), or null.</summary>
    public string? LastError { get { lock (_gate) { return _lastError; } } }

    /// <summary>UTC time the export loop started, or null.</summary>
    public DateTime? StartedUtc { get { lock (_gate) { return _startedUtc; } } }

    /// <summary>Marks the export as running.</summary>
    /// <param name="intervalMinutes">Tick interval.</param>
    /// <param name="nowUtc">Start time.</param>
    public void MarkStarted(int intervalMinutes, DateTime nowUtc)
    {
        lock (_gate)
        {
            Enabled = true;
            IntervalMinutes = intervalMinutes;
            _startedUtc = nowUtc;
        }
    }

    /// <summary>Records a successful tick.</summary>
    /// <param name="nowUtc">Time of the tick.</param>
    public void RecordSuccess(DateTime nowUtc)
    {
        lock (_gate)
        {
            _consecutiveFailures = 0;
            _lastSuccessUtc = nowUtc;
        }
    }

    /// <summary>Records a failed tick and bumps the failure counter metric.</summary>
    /// <param name="nowUtc">Time of the tick.</param>
    /// <param name="error">The failure message.</param>
    public void RecordFailure(DateTime nowUtc, string error)
    {
        lock (_gate)
        {
            _totalFailures++;
            _consecutiveFailures++;
            _lastFailureUtc = nowUtc;
            _lastError = error;
        }

        FailuresCounter.Add(1);
    }
}