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:
@@ -27,4 +27,14 @@ public sealed class EventOptions
|
||||
/// bounds the buffer).
|
||||
/// </summary>
|
||||
public double ReplayRetentionSeconds { get; init; } = 300;
|
||||
|
||||
/// <summary>
|
||||
/// Gets the maximum <c>total_length</c> a sparse-array write may declare before the
|
||||
/// gateway rejects it with <c>InvalidArgument</c>, enforced in
|
||||
/// <see cref="Sessions.SparseArrayExpander"/> before the full array is materialized.
|
||||
/// Guards against a single write forcing a multi-GB allocation. The default of
|
||||
/// 1,000,000 elements is far above any realistic MXAccess array write yet well below
|
||||
/// the frame-size ceiling.
|
||||
/// </summary>
|
||||
public int MaxSparseArrayLength { get; init; } = 1_000_000;
|
||||
}
|
||||
|
||||
@@ -181,6 +181,10 @@ public sealed class GatewayOptionsValidator : OptionsValidatorBase<GatewayOption
|
||||
options.DetachGraceSeconds,
|
||||
"MxGateway:Sessions:DetachGraceSeconds must be zero or greater (0 disables detach-grace retention).",
|
||||
builder);
|
||||
AddIfNegative(
|
||||
options.FaultedGraceSeconds,
|
||||
"MxGateway:Sessions:FaultedGraceSeconds must be zero or greater (0 reaps a faulted session on the next sweep).",
|
||||
builder);
|
||||
AddIfNegative(
|
||||
options.WorkerReadyWaitTimeoutMs,
|
||||
"MxGateway:Sessions:WorkerReadyWaitTimeoutMs must be greater than or equal to zero.",
|
||||
@@ -214,6 +218,10 @@ public sealed class GatewayOptionsValidator : OptionsValidatorBase<GatewayOption
|
||||
builder.RequireThat(
|
||||
options.ReplayRetentionSeconds >= 0,
|
||||
"MxGateway:Events:ReplayRetentionSeconds must be greater than or equal to zero.");
|
||||
|
||||
builder.RequireThat(
|
||||
options.MaxSparseArrayLength >= 1 && options.MaxSparseArrayLength <= Array.MaxLength,
|
||||
$"MxGateway:Events:MaxSparseArrayLength must be between 1 and {Array.MaxLength}.");
|
||||
}
|
||||
|
||||
private static void ValidateDashboard(DashboardOptions options, ValidationBuilder builder)
|
||||
|
||||
@@ -45,6 +45,18 @@ public sealed class SessionOptions
|
||||
/// </remarks>
|
||||
public int DetachGraceSeconds { get; init; } = 30;
|
||||
|
||||
/// <summary>
|
||||
/// Gets the grace period, in seconds, that a faulted session is retained before the
|
||||
/// lease monitor reaps it (killing its worker and freeing the session slot). A faulted
|
||||
/// session is otherwise permanently unusable — every command fails the readiness check —
|
||||
/// yet without this sweep it pins a session slot and a live x86 worker until its normal
|
||||
/// lease expires (up to <see cref="DefaultLeaseSeconds"/>). A value of <c>0</c> (the
|
||||
/// default) reaps a faulted session on the next sweep cycle, bounding the blast radius; a
|
||||
/// positive value keeps the faulted session observable via <c>GetSessionStatus</c> for the
|
||||
/// grace window before it is reclaimed. Must be greater than or equal to zero.
|
||||
/// </summary>
|
||||
public int FaultedGraceSeconds { get; init; }
|
||||
|
||||
/// <summary>
|
||||
/// Gets a value indicating whether multiple event subscribers are allowed per session.
|
||||
/// </summary>
|
||||
|
||||
Reference in New Issue
Block a user