fix(archreview): gateway core P0 remediation (GWC-01/02/03, TST-02, TST-12)

Interlocking changes across the gateway server (shared GatewaySession.cs /
SessionManager.cs), committed together:

- GWC-01 (Critical): alarm monitor now attaches as an internal
  (non-counted) distributor subscriber instead of a second raw drain of the
  single worker event channel; WorkerClient._events -> SingleReader with a
  claimed-once guard so a future dual-consumer regression throws loudly.
- GWC-02 (High): faulted sessions are swept in CloseExpiredLeasesAsync
  (IsFaultedReapable + FaultedReason); new FaultedGraceSeconds (default 0).
- GWC-03 (High): configurable MaxSparseArrayLength (default 1_000_000)
  enforced before allocation.
- TST-02 (High, security): StreamEvents attach now enforces the opening key
  id -> PermissionDenied on owner mismatch.
- TST-12 (Medium): CLAUDE.md retention-defaults sentence corrected.

Verified: NonWindows build clean; targeted tests 135/135 on macOS, plus
WorkerClientTests 18/18 on the Windows host.
This commit is contained in:
Joseph Doherty
2026-07-09 05:51:57 -04:00
parent 31eec41456
commit 20392cf246
30 changed files with 632 additions and 48 deletions
@@ -975,6 +975,68 @@ public sealed class SessionManagerTests
Assert.Equal(0, workerClient.ShutdownCount);
}
/// <summary>
/// A faulted session is reaped by the lease sweep (default <c>FaultedGraceSeconds=0</c>)
/// even though its normal lease is still far in the future, tearing down its worker and
/// freeing the slot, while a healthy leased session in the same manager is untouched.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task CloseExpiredLeasesAsync_ReapsFaultedSession()
{
FakeWorkerClient faultedClient = new();
FakeWorkerClient healthyClient = new();
QueueingSessionWorkerClientFactory factory = new(faultedClient, healthyClient);
SessionManager manager = CreateManager(factory);
GatewaySession faultedSession = await manager.OpenSessionAsync(CreateOpenRequest(), "client-1", ownerKeyId: null, CancellationToken.None);
GatewaySession healthySession = await manager.OpenSessionAsync(CreateOpenRequest(), "client-2", ownerKeyId: null, CancellationToken.None);
DateTimeOffset now = DateTimeOffset.UtcNow;
// Both leases are far in the future, so only the fault can reap the faulted session.
faultedSession.ExtendLease(now.AddMinutes(30));
healthySession.ExtendLease(now.AddMinutes(30));
faultedSession.MarkFaulted("test fault");
int closedCount = await manager.CloseExpiredLeasesAsync(now, CancellationToken.None);
Assert.Equal(1, closedCount);
Assert.Equal(SessionState.Closed, faultedSession.State);
Assert.Equal(1, faultedClient.ShutdownCount);
Assert.Equal(SessionState.Ready, healthySession.State);
Assert.Equal(0, healthyClient.ShutdownCount);
}
/// <summary>
/// With a positive <c>FaultedGraceSeconds</c>, a faulted session stays observable until
/// the grace window elapses, then the next sweep reaps it.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task CloseExpiredLeasesAsync_RespectsFaultedGraceWindow()
{
FakeWorkerClient workerClient = new();
FakeTimeProvider clock = new(DateTimeOffset.UtcNow);
SessionManager manager = CreateManager(
new FakeSessionWorkerClientFactory(workerClient),
options: CreateOptions(defaultLeaseSeconds: 1800, faultedGraceSeconds: 30),
timeProvider: clock);
GatewaySession session = await manager.OpenSessionAsync(CreateOpenRequest(), "client-1", ownerKeyId: null, CancellationToken.None);
session.MarkFaulted("test fault");
// Before the grace window elapses: the faulted session is retained (still observable).
clock.Advance(TimeSpan.FromSeconds(29));
int closedBefore = await manager.CloseExpiredLeasesAsync(clock.GetUtcNow(), CancellationToken.None);
Assert.Equal(0, closedBefore);
Assert.Equal(SessionState.Faulted, session.State);
// After the grace window elapses: the sweep reaps it.
clock.Advance(TimeSpan.FromSeconds(1));
int closedAfter = await manager.CloseExpiredLeasesAsync(clock.GetUtcNow(), CancellationToken.None);
Assert.Equal(1, closedAfter);
Assert.Equal(SessionState.Closed, session.State);
Assert.Equal(1, workerClient.ShutdownCount);
}
/// <summary>Verifies that shutdown closes all registered sessions.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
@@ -1023,7 +1085,8 @@ public sealed class SessionManagerTests
int maxSessions = 64,
int defaultLeaseSeconds = 1800,
int detachGraceSeconds = 0,
int workerReadyWaitTimeoutMs = 0)
int workerReadyWaitTimeoutMs = 0,
int faultedGraceSeconds = 0)
{
return new GatewayOptions
{
@@ -1034,6 +1097,7 @@ public sealed class SessionManagerTests
DefaultLeaseSeconds = defaultLeaseSeconds,
DetachGraceSeconds = detachGraceSeconds,
WorkerReadyWaitTimeoutMs = workerReadyWaitTimeoutMs,
FaultedGraceSeconds = faultedGraceSeconds,
},
Worker = new WorkerOptions
{