feat(auditlog): AuditLogIngestActor + gRPC handler (#23)

This commit is contained in:
Joseph Doherty
2026-05-20 12:48:26 -04:00
parent b679430d13
commit 87cae88f92
6 changed files with 579 additions and 0 deletions

View File

@@ -4,6 +4,9 @@ using Akka.Actor;
using Grpc.Core;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Options;
using ScadaLink.Commons.Entities.Audit;
using ScadaLink.Commons.Messages.Audit;
using ScadaLink.Commons.Types.Enums;
using GrpcStatus = Grpc.Core.Status;
namespace ScadaLink.Communication.Grpc;
@@ -23,6 +26,15 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
private readonly TimeSpan _maxStreamLifetime;
private volatile bool _ready;
private long _actorCounter;
// Audit Log (#23 M2): central-side ingest actor proxy. Set by the host
// after the cluster singleton starts (see Bundle E wiring). When null the
// IngestAuditEvents RPC replies with an empty IngestAck so sites can
// safely retry — wiring-incomplete is treated as transient, never fatal.
private IActorRef? _auditIngestActor;
// Per Bundle D's brief — Ask timeout is 30 s. The ingest actor's repo
// calls are sub-100 ms in steady state; a generous timeout absorbs a slow
// MSSQL connection without surfacing as a gRPC failure on a healthy site.
private static readonly TimeSpan AuditIngestAskTimeout = TimeSpan.FromSeconds(30);
/// <summary>
/// Test-only constructor — kept <c>internal</c> so the DI container sees a
@@ -76,6 +88,19 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
_ready = true;
}
/// <summary>
/// Hands the central-side <c>AuditLogIngestActor</c> proxy to the gRPC
/// server so the <see cref="IngestAuditEvents"/> RPC can route incoming
/// site batches. Audit Log (#23) M2 wiring point — mirrors the way
/// <c>CommunicationService.SetNotificationOutbox</c> takes the Notification
/// Outbox singleton proxy. Bundle E supplies the actor after the cluster
/// singleton starts.
/// </summary>
public void SetAuditIngestActor(IActorRef proxy)
{
_auditIngestActor = proxy;
}
/// <summary>
/// Number of currently active streaming subscriptions. Exposed for diagnostics.
/// </summary>
@@ -168,6 +193,114 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
}
}
/// <summary>
/// Audit Log (#23) M2 site→central push RPC. Decodes a site batch into
/// <see cref="AuditEvent"/> rows, Asks the central <c>AuditLogIngestActor</c>
/// proxy to persist them, and echoes the accepted EventIds back so the site
/// can flip its local rows to <c>Forwarded</c>.
/// </summary>
/// <remarks>
/// <para>
/// The DTO→entity conversion is inlined here (rather than calling the
/// AuditLog mapper) to avoid a project-reference cycle:
/// <c>ScadaLink.AuditLog</c> already references
/// <c>ScadaLink.Communication</c>, so the gRPC server cannot reach back
/// into AuditLog for its mapper. The shape mirrors
/// <c>AuditEventMapper.FromDto</c> in <c>ScadaLink.AuditLog.Telemetry</c>;
/// the two must evolve together.
/// </para>
/// <para>
/// When <see cref="_auditIngestActor"/> is not yet wired (host startup
/// race window), the RPC returns an empty <see cref="IngestAck"/> rather
/// than failing — the site treats the missing ack as a transient outcome
/// and retries on the next drain, which is the desired idempotent
/// behaviour.
/// </para>
/// </remarks>
public override async Task<IngestAck> IngestAuditEvents(
AuditEventBatch request,
ServerCallContext context)
{
// Empty batch is a no-op; reply immediately so the client moves on.
if (request.Events.Count == 0)
{
return new IngestAck();
}
var actor = _auditIngestActor;
if (actor is null)
{
// Wiring incomplete (host startup race). Sites treat an empty
// ack as "nothing was acked, leave rows Pending, retry next
// drain" — exactly the right behaviour during host bring-up.
_logger.LogWarning(
"IngestAuditEvents received {Count} events before SetAuditIngestActor was called; returning empty ack.",
request.Events.Count);
return new IngestAck();
}
// Inlined FromDto. Keep in sync with AuditEventMapper.FromDto in
// ScadaLink.AuditLog.Telemetry — there is no shared mapper because
// doing so would create a project-reference cycle (AuditLog → Communication).
var entities = new List<AuditEvent>(request.Events.Count);
foreach (var dto in request.Events)
{
entities.Add(new AuditEvent
{
EventId = Guid.Parse(dto.EventId),
OccurredAtUtc = DateTime.SpecifyKind(dto.OccurredAtUtc.ToDateTime(), DateTimeKind.Utc),
IngestedAtUtc = null,
Channel = Enum.Parse<AuditChannel>(dto.Channel),
Kind = Enum.Parse<AuditKind>(dto.Kind),
CorrelationId = string.IsNullOrEmpty(dto.CorrelationId) ? null : Guid.Parse(dto.CorrelationId),
SourceSiteId = NullIfEmpty(dto.SourceSiteId),
SourceInstanceId = NullIfEmpty(dto.SourceInstanceId),
SourceScript = NullIfEmpty(dto.SourceScript),
Actor = NullIfEmpty(dto.Actor),
Target = NullIfEmpty(dto.Target),
Status = Enum.Parse<AuditStatus>(dto.Status),
HttpStatus = dto.HttpStatus,
DurationMs = dto.DurationMs,
ErrorMessage = NullIfEmpty(dto.ErrorMessage),
ErrorDetail = NullIfEmpty(dto.ErrorDetail),
RequestSummary = NullIfEmpty(dto.RequestSummary),
ResponseSummary = NullIfEmpty(dto.ResponseSummary),
PayloadTruncated = dto.PayloadTruncated,
Extra = NullIfEmpty(dto.Extra),
ForwardState = null,
});
}
var cmd = new IngestAuditEventsCommand(entities);
IngestAuditEventsReply reply;
try
{
reply = await actor.Ask<IngestAuditEventsReply>(
cmd, AuditIngestAskTimeout, context.CancellationToken);
}
catch (Exception ex)
{
// Audit ingest is best-effort; failing this RPC at the gRPC layer
// would surface as a transport error and force the site to retry
// (which it would do anyway). Logging + an empty ack keeps the
// semantics consistent with the "wiring incomplete" path above.
_logger.LogError(ex,
"AuditLogIngestActor Ask failed for batch of {Count} events; returning empty ack.",
request.Events.Count);
return new IngestAck();
}
var ack = new IngestAck();
foreach (var id in reply.AcceptedEventIds)
{
ack.AcceptedEventIds.Add(id.ToString());
}
return ack;
}
private static string? NullIfEmpty(string? value) =>
string.IsNullOrEmpty(value) ? null : value;
/// <summary>
/// Tracks a single active stream so cleanup only removes its own entry.
/// </summary>