fix(notifications): park corrupt buffered notification payloads instead of silently discarding as delivered (supersedes StoreAndForward-018)

This commit is contained in:
Joseph Doherty
2026-07-08 20:48:16 -04:00
parent 05a71a0260
commit c3a8576863
3 changed files with 30 additions and 22 deletions
@@ -20,6 +20,10 @@ namespace ZB.MOM.WW.ScadaBridge.StoreAndForward;
/// <item><description>ack not <c>Accepted</c>, or the Ask times out / fails →
/// <see cref="DeliverAsync"/> throws; the S&amp;F engine treats any thrown
/// exception as transient and retries the forward at the fixed interval.</description></item>
/// <item><description>the buffered payload is corrupt (undeserialisable / null) →
/// <see cref="DeliverAsync"/> returns <c>false</c> (the handler contract's
/// permanent-failure signal); the engine parks the row so the payload is preserved
/// for operator forensics. Supersedes StoreAndForward-018's silent discard.</description></item>
/// </list>
///
/// The forward travels over the ClusterClient command/control transport: the handler
@@ -51,8 +55,8 @@ public sealed class NotificationForwarder
/// </param>
/// <param name="logger">
/// Optional logger. A corrupt buffered payload is logged at
/// Warning before being discarded so an operator has a forensic trail of the row
/// that vanished from the buffer.
/// Warning before the row is parked so an operator has a forensic trail pointing at
/// the preserved parked row.
/// </param>
public NotificationForwarder(
IActorRef siteCommunicationActor,
@@ -69,21 +73,26 @@ public sealed class NotificationForwarder
/// <summary>
/// Store-and-Forward delivery handler entry point — matches the
/// <c>Func&lt;StoreAndForwardMessage, Task&lt;bool&gt;&gt;</c> handler contract.
/// Returns <c>true</c> when central accepts the notification; throws on a
/// non-accepted ack or an Ask timeout/failure so the engine retries.
/// Returns <c>true</c> when central accepts the notification; returns <c>false</c>
/// when the buffered payload is corrupt (permanent failure engine parks the row);
/// throws on a non-accepted ack or an Ask timeout/failure so the engine retries.
/// </summary>
/// <param name="message">The buffered store-and-forward message to deliver to central.</param>
/// <returns>A task that resolves to <c>true</c> when central accepts (or the payload is corrupt and discarded); throws on a transient forward failure so the engine retries.</returns>
/// <returns>A task that resolves to <c>true</c> when central accepts; <c>false</c> when the payload is corrupt (the engine parks the row for forensics); throws on a transient forward failure so the engine retries.</returns>
public async Task<bool> DeliverAsync(StoreAndForwardMessage message)
{
if (!TryBuildSubmit(message, out var submit))
{
_logger.LogWarning(
"Discarding corrupt buffered notification {NotificationId} (payload is not deserialisable as NotificationSubmit). " +
"Payload preview: {PayloadPreview}",
"Parking corrupt buffered notification {NotificationId} (payload is not deserialisable as NotificationSubmit); " +
"the row is preserved for operator forensics. Payload preview: {PayloadPreview}",
message.Id,
PreviewPayload(message.PayloadJson));
return true;
// false = permanent failure by the delivery-handler contract → the
// engine parks the row (payload preserved, operator can inspect or
// discard). Supersedes StoreAndForward-018's silent discard, which
// reported the notification as delivered while losing it entirely.
return false;
}
// The reply may legitimately be a non-accepted ack, so it is not requested as