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.
This commit is contained in:
Joseph Doherty
2026-09-09 22:05:30 -04:00
parent 146a13238f
commit 9a87d7a328
136 changed files with 5441 additions and 648 deletions
@@ -101,7 +101,7 @@ public class MxGatewayBatchSeamTests
}
[Fact]
public async Task AlarmStream_OpensOnTheLongestCommonPrefix_AndOnlyRestartsForAnEscapingSource()
public async Task AlarmStream_UsesLongestCommonPrefix_AndRefreshesEveryNewSource()
{
var fake = new FakeMxGatewayClient();
var adapter = NewAdapter(fake);
@@ -119,15 +119,15 @@ public class MxGatewayBatchSeamTests
await WaitForPrefixCountAsync(fake, 2);
Assert.Equal("Area1.Tank", fake.AlarmStreamPrefixes[1]);
// A source ALREADY covered by the live prefix must NOT restart the stream.
// A covered new source still needs its standing-state snapshot.
await adapter.SubscribeAlarmsAsync("Area1.Tank3.Sub", null, NoTransition);
await Task.Delay(100);
Assert.Equal(2, fake.AlarmStreamPrefixes.Count);
await WaitForPrefixCountAsync(fake, 3);
Assert.Equal("Area1.Tank", fake.AlarmStreamPrefixes[2]);
// A source outside the prefix widens it again — here down to gateway-wide.
await adapter.SubscribeAlarmsAsync("Zone9.Pump", null, NoTransition);
await WaitForPrefixCountAsync(fake, 3);
Assert.Null(fake.AlarmStreamPrefixes[2]); // "" → gateway-wide
await WaitForPrefixCountAsync(fake, 4);
Assert.Null(fake.AlarmStreamPrefixes[3]); // "" → gateway-wide
}
[Fact]
@@ -25,6 +25,46 @@ public class MxGatewayDataConnectionAlarmReconnectTests
["ApiKey"] = "key",
};
[Fact]
public async Task DC5_EachTransportRefreshHasItsOwnConnectionWideEpoch()
{
var clients = new List<PerInstanceFakeMxGatewayClient>();
var adapter = new MxGatewayDataConnection(new RecordingFactory(clients), NullLogger<MxGatewayDataConnection>.Instance);
var received = new System.Collections.Concurrent.ConcurrentQueue<NativeAlarmTransition>();
await adapter.ConnectAsync(Details());
await adapter.SubscribeAlarmsAsync("Area1", null, received.Enqueue);
await WaitUntilAsync(() => clients[0].AlarmStreamOpens.Count == 1);
clients[0].EmitAlarm(MakeTransition(AlarmTransitionKind.SnapshotComplete));
clients[0].EmitAlarm(MakeTransition(AlarmTransitionKind.SnapshotStart));
clients[0].EmitAlarm(MakeTransition(AlarmTransitionKind.SnapshotComplete));
var starts = received.Where(t => t.Kind == AlarmTransitionKind.SnapshotStart).ToArray();
var ends = received.Where(t => t.Kind == AlarmTransitionKind.SnapshotComplete).ToArray();
Assert.Equal(2, starts.Length);
Assert.Equal(2, ends.Length);
Assert.NotNull(starts[0].SnapshotId);
Assert.NotEqual(starts[0].SnapshotId, starts[1].SnapshotId);
Assert.Equal(starts[0].SnapshotId, ends[0].SnapshotId);
Assert.Equal(starts[1].SnapshotId, ends[1].SnapshotId);
Assert.All(starts, t => Assert.Null(t.SnapshotSourceReference));
await adapter.DisconnectAsync();
}
[Fact]
public async Task DC5_CoveredNewSourceRequestsFreshStandingSnapshot()
{
var clients = new List<PerInstanceFakeMxGatewayClient>();
var adapter = new MxGatewayDataConnection(new RecordingFactory(clients), NullLogger<MxGatewayDataConnection>.Instance);
await adapter.ConnectAsync(Details());
await adapter.SubscribeAlarmsAsync("Area1", null, _ => { });
await WaitUntilAsync(() => clients[0].AlarmStreamOpens.Count == 1);
await adapter.SubscribeAlarmsAsync("Area1.Tank1", null, _ => { });
await WaitUntilAsync(() => clients[0].AlarmStreamOpens.Count == 2);
Assert.True(clients[0].AlarmStreamTokens[0].IsCancellationRequested);
await adapter.DisconnectAsync();
}
[Fact]
public async Task Reconnect_ThenSubscribeAlarms_OpensNewStreamOnNewClient()
{
@@ -78,7 +118,7 @@ public class MxGatewayDataConnectionAlarmReconnectTests
var received = new List<NativeAlarmTransition>();
await adapter.ConnectAsync(Details());
await adapter.SubscribeAlarmsAsync("Area1.Tank1", null, t => received.Add(t));
await adapter.SubscribeAlarmsAsync("Area1.Tank1", null, t => { if (t.Kind != AlarmTransitionKind.SnapshotStart) received.Add(t); });
await WaitUntilAsync(() => clients[0].AlarmStreamOpens.Count == 1);
// Prove the feed works pre-reconnect.
@@ -86,7 +126,7 @@ public class MxGatewayDataConnectionAlarmReconnectTests
await WaitUntilAsync(() => received.Count == 1);
await adapter.ConnectAsync(Details()); // reconnect
await adapter.SubscribeAlarmsAsync("Area1.Tank1", null, t => received.Add(t));
await adapter.SubscribeAlarmsAsync("Area1.Tank1", null, t => { if (t.Kind != AlarmTransitionKind.SnapshotStart) received.Add(t); });
await WaitUntilAsync(() => clients[1].AlarmStreamOpens.Count == 1);
// A transition on the OLD (disposed, orphaned) client must never reach the
@@ -0,0 +1,23 @@
using Opc.Ua;
using ZB.MOM.WW.ScadaBridge.DataConnectionLayer.Adapters;
namespace ZB.MOM.WW.ScadaBridge.DataConnectionLayer.Tests.Adapters;
public class OpcUaSecurityDowngradeTests
{
[Theory]
[InlineData(false)]
[InlineData(true)]
public void DC4_RequestedProtectionNeverFallsBackToNone(bool discoveryFails)
{
Assert.Throws<InvalidOperationException>(() => RealOpcUaClient.DiscoverEndpoint("opc.tcp://test:4840",
MessageSecurityMode.SignAndEncrypt, () => discoveryFails
? throw new Exception("discovery unavailable")
: new EndpointDescriptionCollection { new("opc.tcp://test:4840") { SecurityMode = MessageSecurityMode.None } }));
}
[Fact]
public void DC4_ExactRequestedModeIsSelected()
{
var encrypted = new EndpointDescription("opc.tcp://test:4840") { SecurityMode = MessageSecurityMode.SignAndEncrypt };
Assert.Same(encrypted, RealOpcUaClient.DiscoverEndpoint("opc.tcp://test:4840", MessageSecurityMode.SignAndEncrypt,
() => new EndpointDescriptionCollection { new("opc.tcp://test:4840"), encrypted }));
}
}