Resolve all 33 medium-severity architecture review findings

Second slice of the 2026-09-09 whole-system review remediation (docs/plans/2026-09-09-arch-review.md §10), on top of the High slice 146a1323. Runtime/devices: SR-2 alarm on-trigger integration scope; SR-3 correlated NativeAlarmActor subscribe retry; SR-4 immutable audited DB target; SR-5 ordered InstanceActor stop/flush; SR-12 rehydration fence; SR-13 S&F gate recheck per delivery; DC-4 no OPC UA security downgrade; DC-5 alarm snapshot for every new subscriber; ORCH-1 sync-dispose joins the pump. Management/UI: MG-2 site scope on audit tree + Flow Debugger Replay; MG-3 stale-probe memo removed; MG-4 server-owned bulk-deploy deadline; UI-5 sandbox runs in a killable child process (new CentralUI.SandboxWorker project); UI-14 bounded sandbox output/IPC. Edge/audit: EI-1 relay audit ownership; EI-2 SkipBodyCapture suppresses error text; EI-3/EI-11 error-field redaction + caps; EI-4 single relay deadline, pre-execution-only retry; EI-5 authenticated relay provenance; EI-10 body cap before audit read. Persistence/contracts: DL-1 global Instance.UniqueName unique index + conflict translation; DL-2 DataConnection protocol config encrypted at rest (migration 20260909203046_EnforceGlobalInstanceNamesAndProtectProtocolConfiguration — coordinated central upgrade, old binaries cannot read protected rows); DL-3 bounded Replay paging; DL-6 cross-site Overwrite of a deployed instance rejected; XC-4 proto descriptor contract test. Config/hygiene: XC-1 central listener isolation by local port; XC-2/XC-3 inert SMTP + cron keys removed from rig settings; CM-2 env2 bootstrap guard enabled; DC-6 deploy site exit code; DC-7 notifier retries only explicit standby rejection; XC-5 ClusterClient purged from docs. Gates recorded in the report: build 0/0, 9 397 passed / 0 failed, rig redeployed on all eight nodes with the migration applied. 46 Low findings remain open.
2026-09-09 22:05:30 -04:00
parent 146a13238f
commit 9a87d7a328
136 changed files with 5441 additions and 648 deletions
@@ -430,7 +430,7 @@ public class AuditLogIngestActorCombinedTelemetryTests : TestKit, IClassFixture<
    /// </summary>
    private sealed class BatchFailingAuditRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        private readonly IAuditLogRepository _inner;
@@ -458,7 +458,7 @@ public class AuditLogIngestActorCombinedTelemetryTests : TestKit, IClassFixture<
            TimeSpan window, DateTime? nowUtc = null, CancellationToken ct = default) =>
            _inner.GetKpiSnapshotAsync(window, nowUtc, ct);
        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            _inner.GetExecutionTreeAsync(executionId, ct);
        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
            _inner.GetDistinctSourceNodesAsync(ct);
@@ -382,7 +382,7 @@ public class AuditLogIngestActorTests : TestKit, IClassFixture<MsSqlMigrationFix
    /// </summary>
    private sealed class TokenRecordingRepository : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        public CancellationToken? BatchToken { get; private set; }
@@ -427,7 +427,7 @@ public class AuditLogIngestActorTests : TestKit, IClassFixture<MsSqlMigrationFix
            throw new NotSupportedException();

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            throw new NotSupportedException();

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -441,7 +441,7 @@ public class AuditLogIngestActorTests : TestKit, IClassFixture<MsSqlMigrationFix
    /// </summary>
    private sealed class ThrowingRepository : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        private readonly IAuditLogRepository _inner;
@@ -486,7 +486,7 @@ public class AuditLogIngestActorTests : TestKit, IClassFixture<MsSqlMigrationFix
            _inner.GetKpiSnapshotAsync(window, nowUtc, ct);

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            _inner.GetExecutionTreeAsync(executionId, ct);

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -45,7 +45,7 @@ public class AuditLogPurgeActorTests : TestKit, IClassFixture<MsSqlMigrationFixt
    /// </summary>
    private sealed class RecordingRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        public List<DateTime> ThresholdQueries { get; } = new();
@@ -112,7 +112,7 @@ public class AuditLogPurgeActorTests : TestKit, IClassFixture<MsSqlMigrationFixt
            Task.FromResult(new ZB.MOM.WW.ScadaBridge.Commons.Types.AuditLogKpiSnapshot(0L, 0L, 0L, nowUtc ?? DateTime.UtcNow));

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            Task.FromResult<IReadOnlyList<ExecutionTreeNode>>(Array.Empty<ExecutionTreeNode>());

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -37,7 +37,7 @@ public class CentralAuditWriteFailuresTests : TestKit
    /// </summary>
    private sealed class ThrowingRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        public Task InsertIfNotExistsAsync(AuditEvent evt, CancellationToken ct = default) =>
@@ -61,7 +61,7 @@ public class CentralAuditWriteFailuresTests : TestKit
            Task.FromResult(new ZB.MOM.WW.ScadaBridge.Commons.Types.AuditLogKpiSnapshot(0L, 0L, 0L, nowUtc ?? DateTime.UtcNow));

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            Task.FromResult<IReadOnlyList<ExecutionTreeNode>>(Array.Empty<ExecutionTreeNode>());

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -68,7 +68,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
    /// </summary>
    private sealed class RecordingRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        public List<AuditEvent> Inserted { get; } = new();
@@ -109,7 +109,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
            Task.FromResult(new ZB.MOM.WW.ScadaBridge.Commons.Types.AuditLogKpiSnapshot(0L, 0L, 0L, nowUtc ?? DateTime.UtcNow));

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            Task.FromResult<IReadOnlyList<ExecutionTreeNode>>(Array.Empty<ExecutionTreeNode>());

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -124,7 +124,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
    /// </summary>
    private sealed class PoisonInsertRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        private readonly Guid _poisonId;
@@ -175,7 +175,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
            Task.FromResult(new ZB.MOM.WW.ScadaBridge.Commons.Types.AuditLogKpiSnapshot(0L, 0L, 0L, nowUtc ?? DateTime.UtcNow));

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            Task.FromResult<IReadOnlyList<ExecutionTreeNode>>(Array.Empty<ExecutionTreeNode>());

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -198,7 +198,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
    /// </summary>
    private sealed class AlwaysFailUnlessSyntheticRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        public List<AuditEvent> Inserted { get; } = new();
@@ -241,7 +241,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
            Task.FromResult(new ZB.MOM.WW.ScadaBridge.Commons.Types.AuditLogKpiSnapshot(0L, 0L, 0L, nowUtc ?? DateTime.UtcNow));

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default) =>
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null) =>
            Task.FromResult<IReadOnlyList<ExecutionTreeNode>>(Array.Empty<ExecutionTreeNode>());

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default) =>
@@ -612,7 +612,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
    /// <summary>Repository whose every insert throws, so the retry hold-back path is taken.</summary>
    private sealed class AlwaysThrowingRepo : IAuditLogRepository
    {
-        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default)
+        public Task<IReadOnlyList<AuditEvent>> GetTraceEventsAsync(Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException("GetTraceEventsAsync is not exercised by this test double.");

        public Task InsertIfNotExistsAsync(AuditEvent evt, CancellationToken ct = default) =>
@@ -644,7 +644,7 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
            => throw new NotSupportedException();

        public Task<IReadOnlyList<ExecutionTreeNode>> GetExecutionTreeAsync(
-            Guid executionId, CancellationToken ct = default)
+            Guid executionId, CancellationToken ct = default, IReadOnlyList<string>? permittedSiteIds = null)
            => throw new NotSupportedException();

        public Task<IReadOnlyList<string>> GetDistinctSourceNodesAsync(CancellationToken ct = default)
@@ -20,6 +20,34 @@ namespace ZB.MOM.WW.ScadaBridge.AuditLog.Tests.Redaction;
 /// </summary>
 public class ScadaBridgeAuditRedactorTests
 {
+    [Theory]
+    [InlineData(false)]
+    [InlineData(true)]
+    public void EI11_ErrorMessage_AllFieldsRedactedAndCapped(bool perTarget)
+    {
+        var opts = new AuditLogOptions { ErrorCapBytes = 128 };
+        if (perTarget) opts.PerTargetOverrides["target"] = new PerTargetRedactionOverride { AdditionalBodyRedactors = ["SECRET123"] };
+        else opts.GlobalBodyRedactors = ["SECRET123"];
+        var evt = NewEvent(status: AuditStatus.Failed, outcome: AuditOutcome.Failure, target: "target", errorDetail: "SECRET123", request: "SECRET123", response: "SECRET123", extra: "SECRET123");
+        evt = evt with { DetailsJson = AuditDetailsCodec.Serialize(Details(evt) with { ErrorMessage = "SECRET123" + new string('x', 1000) }) };
+        var result = Redactor(opts).Apply(evt);
+        Assert.DoesNotContain("SECRET123", result.DetailsJson!);
+        Assert.True(Encoding.UTF8.GetByteCount(Details(result).ErrorMessage!) <= 128);
+    }
+
+    [Fact]
+    public void EI3_SqlParameterPolicy_DoesNotPersistExceptionEchoedValues()
+    {
+        var opts = new AuditLogOptions();
+        opts.PerTargetOverrides["PrimaryDb"] = new PerTargetRedactionOverride { RedactSqlParamsMatching = "^@token$" };
+        var evt = NewEvent(channel: AuditChannel.DbOutbound, status: AuditStatus.Failed, outcome: AuditOutcome.Failure,
+            target: "PrimaryDb.Query", request: "{\"parameters\":{\"@token\":\"SECRET123\"}}", errorDetail: "SqlException duplicate key value is (SECRET123)");
+        evt = evt with { DetailsJson = AuditDetailsCodec.Serialize(Details(evt) with { ErrorMessage = "duplicate key SECRET123" }) };
+        var result = Redactor(opts).Apply(evt);
+        Assert.DoesNotContain("SECRET123", result.DetailsJson!);
+        Assert.Equal("Failed", Details(result).Status);
+    }
+
    private static ScadaBridgeAuditRedactor Redactor(
        AuditLogOptions? opts = null,
        IAuditRedactionFailureCounter? counter = null) =>