merge(r2): PLAN-R2-07 UI/Management/Security

docker-env2/central-node-a/appsettings.Central.json

@@ -35,7 +35,12 @@
       "JwtExpiryMinutes": 15,
       "IdleTimeoutMinutes": 30,
       "RequireHttpsCookie": false,
-      "CookieName": "ZB.MOM.WW.ScadaBridge.Auth.env2"
+      "CookieName": "ZB.MOM.WW.ScadaBridge.Auth.env2",
+      "ForwardedHeaders": {
+        "_comment": "Traefik fronts this node on the external scadabridge-net docker network. Trust X-Forwarded-For from the docker bridge address pool so LoginThrottle keys on the real client IP (arch-review R2 N2). Narrow to the Traefik container IP if the network is pinned.",
+        "Enabled": true,
+        "KnownNetworks": [ "172.16.0.0/12" ]
+      }
     },
     "Communication": {
       "DeploymentTimeout": "00:02:00",

docker-env2/central-node-b/appsettings.Central.json

@@ -35,7 +35,12 @@
       "JwtExpiryMinutes": 15,
       "IdleTimeoutMinutes": 30,
       "RequireHttpsCookie": false,
-      "CookieName": "ZB.MOM.WW.ScadaBridge.Auth.env2"
+      "CookieName": "ZB.MOM.WW.ScadaBridge.Auth.env2",
+      "ForwardedHeaders": {
+        "_comment": "Traefik fronts this node on the external scadabridge-net docker network. Trust X-Forwarded-For from the docker bridge address pool so LoginThrottle keys on the real client IP (arch-review R2 N2). Narrow to the Traefik container IP if the network is pinned.",
+        "Enabled": true,
+        "KnownNetworks": [ "172.16.0.0/12" ]
+      }
     },
     "Communication": {
       "DeploymentTimeout": "00:02:00",

docker/central-node-a/appsettings.Central.json

@@ -38,7 +38,12 @@
       "JwtSigningKey": "scadabridge-dev-jwt-signing-key-must-be-at-least-32-characters-long",
       "JwtExpiryMinutes": 15,
       "IdleTimeoutMinutes": 30,
-      "RequireHttpsCookie": false
+      "RequireHttpsCookie": false,
+      "ForwardedHeaders": {
+        "_comment": "Traefik fronts this node on the external scadabridge-net docker network. Trust X-Forwarded-For from the docker bridge address pool so LoginThrottle keys on the real client IP (arch-review R2 N2). Narrow to the Traefik container IP if the network is pinned.",
+        "Enabled": true,
+        "KnownNetworks": [ "172.16.0.0/12" ]
+      }
     },
     "Communication": {
       "DeploymentTimeout": "00:02:00",

docker/central-node-b/appsettings.Central.json

@@ -38,7 +38,12 @@
       "JwtSigningKey": "scadabridge-dev-jwt-signing-key-must-be-at-least-32-characters-long",
       "JwtExpiryMinutes": 15,
       "IdleTimeoutMinutes": 30,
-      "RequireHttpsCookie": false
+      "RequireHttpsCookie": false,
+      "ForwardedHeaders": {
+        "_comment": "Traefik fronts this node on the external scadabridge-net docker network. Trust X-Forwarded-For from the docker bridge address pool so LoginThrottle keys on the real client IP (arch-review R2 N2). Narrow to the Traefik container IP if the network is pinned.",
+        "Enabled": true,
+        "KnownNetworks": [ "172.16.0.0/12" ]
+      }
     },
     "Communication": {
       "DeploymentTimeout": "00:02:00",

docs/requirements/Component-CentralUI.md

@@ -191,7 +191,7 @@ Per-leaf alarm rendering (leaf nodes are individual conditions for native alarms
 - **Live updates** — the page is driven by a **transient, per-site central live alarm cache** (`ISiteAlarmLiveCache`, owned by the Communication component; see [Component-Communication](Component-Communication.md)). On site select the page subscribes to the cache; the cache runs one shared, reference-counted per-site aggregator that **seeds** from the snapshot fan-out and then stays warm on a single **site-wide, alarm-only** `SubscribeSite` gRPC stream (seed-then-stream, dedup by `(InstanceUniqueName, AlarmName, SourceReference)`). Applied deltas raise an in-process change event (mirroring `IDeploymentStatusNotifier`) that the Blazor circuit pushes to the browser via `StateHasChanged()` — no new SignalR hub. `AlarmSummaryService.BuildFromLiveAlarms` rebuilds the roll-up + rows from the cache's current alarm set. The cache is **purely in-memory on the active central node** — there is still **no persisted central alarm store**; on a NodeA↔NodeB failover the new active node re-seeds from scratch.
 - **View** — roll-up tiles (total active, worst severity, unacked count, per-`AlarmKind` counts) plus a flat, sortable, filterable table. Filters cover instance, `AlarmKind` (Computed / NativeOpcUa / NativeMxAccess), state, acked/unacked, severity threshold, and name search.
 - **Read-only** — there are no ack / shelve / suppress controls (native alarms remain read-only by design).
-- **Refresh** — manual refresh button plus the 15s poll timer (mirroring the Health dashboard), now retained as a **fallback + `NotReporting` authority** behind the live cache: when the cache reports `IsLive`, the page renders live-cache state; when a stream is unhealthy or a site has not yet seeded, the poll keeps the page fresh so a stream failure never blanks it. (Aggregated live stream **delivered 2026-07-10** — see `docs/plans/2026-07-10-aggregated-live-alarm-stream-plan.md`.)
+- **Refresh** — manual refresh button plus the 15s poll timer (mirroring the Health dashboard), now retained as a **fallback + `NotReporting` authority** behind the live cache: when the cache reports `IsLive`, the page renders live-cache state; when a stream is unhealthy, **the aggregator has died (deathwatch resets `IsLive`)**, or a site has not yet seeded, the poll keeps the page fresh so a stream failure never blanks it. When live, the poll updates only the `NotReporting` list and leaves the row set to the delta path, so a slow fan-out can never momentarily revert a fresher live delta (R2 N5). (Aggregated live stream **delivered 2026-07-10** — see `docs/plans/2026-07-10-aggregated-live-alarm-stream-plan.md`.)
 - **Reuse** — the alarm badge/formatter markup is factored out of Debug View into a shared `AlarmStateBadges` component consumed by both Debug View and this page.
 
 ### Parked Message Management (Deployment Role)

docs/requirements/Component-Security.md

@@ -138,7 +138,7 @@ Set in a local or docker-dev environment via the environment variable `ScadaBrid
   - Approve or reject a pending secured write from the Secured Writes page — the *approving* half of the two-person write workflow.
 - **Purpose**: The approving counterpart to **Operator**. Separation of duties is enforced **server-side**: the ManagementActor rejects any approval where the approving user equals the submitting Operator (no self-approval), so the two roles must be held by distinct principals for a write to execute. (See Component-ManagementService.md and Component-CentralUI.md.)
 
-> **Two-person secured-write workflow.** `Operator` and `Verifier` are deliberately separate global roles so a single principal cannot both initiate and approve a write through the MxAccess Gateway. Both are coarse global roles like the others; any site scoping is layered on at the LDAP-mapping level.
+> **Two-person secured-write workflow.** `Operator` and `Verifier` are deliberately separate global roles so a single principal cannot both initiate and approve a write through the MxAccess Gateway. Both are coarse global roles like the others. **Site scoping from the LDAP mapping is enforced server-side on every secured-write command** (arch-review R2 N3): submit checks the target site, approve/reject check the row's site (before the TTL/self-approval/CAS chain), and the list constrains a scoped caller to their permitted sites — mirroring the deployment commands' `EnforceSiteScope` rule. Administrators and system-wide principals (empty permitted-site set) are unrestricted.
 >
 > **Deployment-configuration hazard — never grant one principal both roles.** The whole control collapses if the same identity (or LDAP group) maps to *both* `Operator` and `Verifier`: server-side no-self-approval blocks approving the *exact* write you submitted, but a dual-role principal can still trivially pair-approve with a second submission, so a single compromised or careless account regains unilateral write. Keep `SCADA-Operators` and `SCADA-Verifiers` group membership disjoint. The dev `DisableLogin` caveat is the extreme of this: with `DisableLogin` on, the auto-login principal holds **all** roles, so the two-person flow cannot be exercised end-to-end by a single identity — which is exactly why `DisableLogin=true` is refused outside Development (see the `DisableLoginGuard` note above). No-self-approval is covered by handler tests; real two-person use requires two real, distinct-role identities.
 >
@@ -205,7 +205,8 @@ Role checks are expressed as named ASP.NET Core authorization policies (in `Auth
 
 To blunt online password-spray and brute-force against the directory, every LDAP-bind surface consults a shared in-memory throttle (`LoginThrottle`, a `ZB.MOM.WW.ScadaBridge.Security` singleton) before attempting a bind, and records the bind outcome afterwards.
 
-- **Scope — every LDAP-bind surface**: the Central UI interactive login (`POST /auth/login`) and CLI token issue (`POST /auth/token`), plus the HTTP-Basic management/CLI surfaces fronted by `ManagementAuthenticator` — `POST /management`, the audit REST endpoints, and the debug-stream hub. No bind happens outside these paths, so throttling coverage is complete. The dev/test `DisableLogin` bypass sits **above** the throttle: a login-disabled deployment never binds, so it is never throttled.
-- **Key and window**: counters are keyed per `{username}|{IP}` pair (lower-cased username; remote IP from the connection). A fixed window of `LoginFailureWindowMinutes` (default 5) opens on the first failure; reaching `MaxLoginFailuresPerWindow` failures (default 5) within it locks that key out for `LoginLockoutMinutes` (default 5). A successful bind clears the key; an expired window resets the count. Setting `MaxLoginFailuresPerWindow` to `0` disables throttling entirely.
+- **Scope — every LDAP-bind surface**: the Central UI interactive login (`POST /auth/login`) and CLI token issue (`POST /auth/token`), plus the HTTP-Basic management/CLI surfaces fronted by `ManagementAuthenticator` — `POST /management`, the audit REST endpoints, **and the debug-stream hub (`DebugStreamHub.OnConnectedAsync` delegates its whole credential path to `ManagementAuthenticator.AuthenticateAsync`, closing the round-2 N1 gap where the hub bound LDAP directly and bypassed the throttle)**. No bind happens outside these paths. The dev/test `DisableLogin` bypass sits **above** the throttle: a login-disabled deployment never binds, so it is never throttled.
+- **Key and window**: counters are keyed per `{username}|{IP}` pair (lower-cased username; the IP half is the **forwarded-header-resolved client IP** when `ScadaBridge:Security:ForwardedHeaders` names a trusted proxy, otherwise the raw connection peer). A fixed window of `LoginFailureWindowMinutes` (default 5) opens on the first failure; reaching `MaxLoginFailuresPerWindow` failures (default 5) within it locks that key out for `LoginLockoutMinutes` (default 5). A successful bind clears the key; an expired window resets the count. Setting `MaxLoginFailuresPerWindow` to `0` disables throttling entirely.
+- **Proxy topologies and the username-lockout DoS.** The key is deliberately `{username}|{IP}`, not `{username}` alone: keying on username alone would let any network-adjacent actor lock any operator out of a SCADA control surface with five wrong passwords, repeatable indefinitely. That isolation only exists when the throttle sees real client IPs — behind a proxy **without** ForwardedHeaders trust, all clients collapse onto the proxy's IP and the DoS returns. Mitigations: (a) the shipped Traefik topologies enable trusted-proxy ForwardedHeaders (so per-IP isolation is real in the documented deployment); (b) the lockout window is short by default (`LoginLockoutMinutes` = 5) and never touches the directory account itself; (c) residual risk — an attacker spraying from their *own* IP locking out a victim username *at that IP only* — is the throttle working as designed. A success-path bypass ("a correct password unlocks") was considered and rejected: it would let an attacker who has the password bypass the lockout entirely, and it converts the throttle into a password oracle during the lockout window.
 - **Behaviour when locked**: the surface refuses the bind without contacting LDAP. The Basic-Auth surfaces (`ManagementAuthenticator`) and `POST /auth/token` return HTTP `429` with `code = "AUTH_THROTTLED"`; `POST /auth/login` redirects to `/login` with a "Too many failed attempts. Try again later." message.
 - **Best-effort, per-node**: the throttle is in-memory with no external state. The two central nodes maintain independent counters (a spray hitting both simply burns its budget on each). Memory is bounded — writes prune expired keys and cap the tracked-key count. This is a rate-limit guard, not an account-lockout policy; it never disables the directory account itself.

src/ZB.MOM.WW.ScadaBridge.CentralUI/Components/Pages/Monitoring/AlarmSummary.razor

@@ -291,9 +291,27 @@
         try
         {
             var result = await AlarmSummaryService.GetSiteAlarmsAsync(siteId);
-            _rows = result.Alarms;
+            // Stale-site guard (arch-review R2 N4): the operator may have switched sites
+            // while this fan-out was in flight — drop the result rather than labeling
+            // site A's alarms under site B's picker. Mirrors OnLiveAlarmsChanged (:374).
+            if (_selectedSiteId != siteId)
+            {
+                return;
+            }
+
+            // _notReporting is the poll's unique authority — the alarm-only live cache
+            // cannot compute it — so it is always refreshed.
             _notReporting = result.NotReportingInstances;
-            _rollup = AlarmSummaryService.ComputeRollup(_rows);
+
+            // While the cache is live, the live deltas own the row set: a poll whose fan-out
+            // started BEFORE a delta must not land after it and momentarily revert the alarm
+            // state (arch-review R2 N5). When not live (pre-seed / degraded stream / dead
+            // aggregator — see R2 N6), the poll remains the full-rebuild safety net.
+            if (!LiveAlarmCache.IsLive(siteId))
+            {
+                _rows = result.Alarms;
+                _rollup = AlarmSummaryService.ComputeRollup(_rows);
+            }
             RecomputeVisibleRows();
         }
         catch
@@ -341,10 +359,11 @@
     //     aggregated alarm set changes. We rebuild _rows/_rollup/_visibleRows from the
     //     immutable live snapshot — but deliberately DO NOT touch _notReporting, since
     //     the alarm-only live cache can't compute it.
-    //   • The 15s poll (RefreshAsync) still runs untouched: it is the authority for
-    //     _notReporting and the safety net when the cache is not live (pre-seed or a
-    //     degraded/failed stream — IsLive == false). When live, the poll simply
-    //     re-affirms the same snapshot; the live path just makes updates arrive sooner.
+    //   • The 15s poll (RefreshAsync) is the authority for _notReporting and the
+    //     full-rebuild safety net ONLY while the cache is not live (pre-seed or a
+    //     degraded/failed stream — IsLive == false); when live it deliberately leaves
+    //     _rows to the delta path, so a slow fan-out can never revert a fresher live
+    //     delta (arch-review R2 N5).
     //   • Both paths mutate shared state only via the Blazor dispatcher (the poll via
     //     its InvokeAsync callback, the live delta via OnLiveChanged's InvokeAsync), so
     //     they are serialized and never race. Each rebuild is an idempotent snapshot, so
@@ -363,15 +382,20 @@
         _liveSubscription = null;
     }
 
+    // N7: set BEFORE teardown so a live callback racing Dispose is dropped both
+    // before the InvokeAsync marshal and inside it (mirrors DebugView.razor).
+    private volatile bool _disposed;
+
     // Raised on the aggregator's thread — marshal onto the circuit before touching state.
     private void OnLiveAlarmsChanged(int siteId)
     {
+        if (_disposed) return;
         _ = InvokeAsync(() =>
         {
             // Drop stale callbacks for a site we've since navigated away from, and
             // let the poll drive until the aggregator has actually seeded (so we never
             // clobber a good poll snapshot with an empty pre-seed list).
-            if (_selectedSiteId != siteId || !LiveAlarmCache.IsLive(siteId))
+            if (_disposed || _selectedSiteId != siteId || !LiveAlarmCache.IsLive(siteId))
             {
                 return;
             }
@@ -506,6 +530,7 @@
 
     public void Dispose()
     {
+        _disposed = true;
         StopTimer();
         DisposeLiveSubscription();
     }

src/ZB.MOM.WW.ScadaBridge.Commons/Interfaces/Repositories/ISecuredWriteRepository.cs

@@ -46,6 +46,11 @@ public interface ISecuredWriteRepository
     /// <param name="siteId">Site id filter; <c>null</c> matches every site.</param>
     /// <param name="skip">Number of rows to skip (offset paging).</param>
     /// <param name="take">Maximum number of rows to return.</param>
+    /// <param name="permittedSiteIds">When non-null, only rows whose <c>SiteId</c> (site
+    /// identifier) is in the set match; <c>null</c> matches every site. Applied IN ADDITION
+    /// to <paramref name="siteId"/>. Used by the ManagementActor to constrain an unfiltered
+    /// list to a site-scoped caller's permitted sites at the query level (arch-review R2 N3),
+    /// so paging and totals stay correct.</param>
     /// <param name="ct">Cancellation token.</param>
     /// <returns>A task that resolves to a page of matching rows, newest submission first.</returns>
     Task<IReadOnlyList<PendingSecuredWrite>> QueryAsync(
@@ -53,6 +58,7 @@ public interface ISecuredWriteRepository
         string? siteId,
         int skip,
         int take,
+        IReadOnlyCollection<string>? permittedSiteIds = null,
         CancellationToken ct = default);
 
     /// <summary>
@@ -106,7 +112,16 @@ public interface ISecuredWriteRepository
     /// </summary>
     /// <param name="status">Status filter; <c>null</c> matches every status.</param>
     /// <param name="siteId">Site id filter; <c>null</c> matches every site.</param>
+    /// <param name="permittedSiteIds">When non-null, only rows whose <c>SiteId</c> (site
+    /// identifier) is in the set match; <c>null</c> matches every site. Applied IN ADDITION
+    /// to <paramref name="siteId"/>. Used by the ManagementActor to constrain an unfiltered
+    /// list to a site-scoped caller's permitted sites at the query level (arch-review R2 N3),
+    /// so paging and totals stay correct.</param>
     /// <param name="ct">Cancellation token.</param>
     /// <returns>A task that resolves to the count of matching rows.</returns>
-    Task<int> CountAsync(string? status, string? siteId, CancellationToken ct = default);
+    Task<int> CountAsync(
+        string? status,
+        string? siteId,
+        IReadOnlyCollection<string>? permittedSiteIds = null,
+        CancellationToken ct = default);
 }

src/ZB.MOM.WW.ScadaBridge.Communication/ISiteAlarmLiveCache.cs

@@ -60,6 +60,6 @@ public interface ISiteAlarmLiveCache
     /// cache is authoritative.
     /// </summary>
     /// <param name="siteId">The numeric site id.</param>
-    /// <returns><c>true</c> once the site's aggregator has seeded and published at least once.</returns>
+    /// <returns><c>true</c> while a <b>living</b> aggregator has seeded and published; reverts to false if the aggregator terminates (R2 N6) — a frozen snapshot is never reported as live.</returns>
     bool IsLive(int siteId);
 }

src/ZB.MOM.WW.ScadaBridge.Communication/SiteAlarmLiveCacheService.cs

@@ -239,6 +239,14 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
                     TimeSpan.FromSeconds(60))); // stability window — former StabilityWindow static default
 
                 entry.Actor = system.ActorOf(props, $"site-alarm-aggregator-{entry.SiteId}-{Guid.NewGuid():N}");
+
+                var aggregator = entry.Actor;
+                // Deathwatch (arch-review R2 N6): if the aggregator terminates for any reason,
+                // liveness must reset — a dead feed must never keep IsLive == true, or the page
+                // grafts a frozen snapshot over fresh poll data for up to 15 s.
+                system.ActorOf(Props.Create(() => new AggregatorTerminationWatcher(
+                    aggregator!, () => OnAggregatorTerminated(entry.SiteId, aggregator!))));
+
                 entry.StartRetryTimer?.Dispose();
                 entry.StartRetryTimer = null;
                 _logger.LogInformation("Started live alarm aggregator for site {SiteId} ({SiteIdentifier})",
@@ -421,6 +429,57 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
         }
     }
 
+    // ── Deathwatch (R2 N6) ──────────────────────────────────────────────────────
+
+    /// <summary>Watches one aggregator and fires a callback exactly once on Terminated.</summary>
+    private sealed class AggregatorTerminationWatcher : ReceiveActor
+    {
+        public AggregatorTerminationWatcher(IActorRef watched, Action onTerminated)
+        {
+            Context.Watch(watched);
+            Receive<Terminated>(_ =>
+            {
+                onTerminated();
+                Context.Stop(Self);
+            });
+        }
+    }
+
+    /// <summary>
+    /// Terminated hook (R2 N6). A DELIBERATE stop (linger fired, entry already removed
+    /// from _sites) is a no-op — the ReferenceEquals guard also ignores a stale watcher
+    /// firing after a newer aggregator replaced the dead one. A crash-death with live
+    /// viewers resets liveness (IsLive → false, snapshot cleared, so the page's poll is
+    /// authoritative again) and arms the existing bounded start-retry so the feature
+    /// self-heals, mirroring StartAggregatorAsync's transient-failure path.
+    /// </summary>
+    private void OnAggregatorTerminated(int siteId, IActorRef deadActor)
+    {
+        lock (_lock)
+        {
+            if (!_sites.TryGetValue(siteId, out var entry) || !ReferenceEquals(entry.Actor, deadActor))
+                return;
+
+            entry.Actor = null;
+            entry.HasPublished = false;
+            entry.Current = Empty;
+
+            if (entry.Subscribers.Count > 0 && !entry.Starting)
+            {
+                entry.Starting = true;
+                entry.StartRetryTimer?.Dispose();
+                entry.StartRetryTimer = new Timer(
+                    _ => { _ = StartAggregatorAsync(entry); },
+                    state: null,
+                    dueTime: _options.LiveAlarmCacheReconcileInterval,
+                    period: Timeout.InfiniteTimeSpan);
+            }
+        }
+        _logger.LogWarning(
+            "Live alarm aggregator for site {SiteId} terminated unexpectedly; liveness reset " +
+            "(page falls back to polling) and a restart is armed while viewers remain", siteId);
+    }
+
     // ── Nested types ────────────────────────────────────────────────────────────
 
     /// <summary>Per-site bookkeeping. All mutable fields are guarded by the service's <c>_lock</c>.</summary>

src/ZB.MOM.WW.ScadaBridge.ConfigurationDatabase/Repositories/SecuredWriteRepository.cs

@@ -57,6 +57,7 @@ public class SecuredWriteRepository : ISecuredWriteRepository
         string? siteId,
         int skip,
         int take,
+        IReadOnlyCollection<string>? permittedSiteIds = null,
         CancellationToken ct = default)
     {
         IQueryable<PendingSecuredWrite> query = _context.Set<PendingSecuredWrite>()
@@ -72,6 +73,11 @@ public class SecuredWriteRepository : ISecuredWriteRepository
             query = query.Where(p => p.SiteId == siteId);
         }
 
+        if (permittedSiteIds is not null)
+        {
+            query = query.Where(p => permittedSiteIds.Contains(p.SiteId));
+        }
+
         return await query
             .OrderByDescending(p => p.SubmittedAtUtc)
             .ThenByDescending(p => p.Id)
@@ -128,7 +134,11 @@ WHERE Id = {id}
     }
 
     /// <inheritdoc />
-    public async Task<int> CountAsync(string? status, string? siteId, CancellationToken ct = default)
+    public async Task<int> CountAsync(
+        string? status,
+        string? siteId,
+        IReadOnlyCollection<string>? permittedSiteIds = null,
+        CancellationToken ct = default)
     {
         IQueryable<PendingSecuredWrite> query = _context.Set<PendingSecuredWrite>()
             .AsNoTracking();
@@ -143,6 +153,11 @@ WHERE Id = {id}
             query = query.Where(p => p.SiteId == siteId);
         }
 
+        if (permittedSiteIds is not null)
+        {
+            query = query.Where(p => permittedSiteIds.Contains(p.SiteId));
+        }
+
         return await query.CountAsync(ct);
     }
 }

src/ZB.MOM.WW.ScadaBridge.Host/Program.cs

@@ -337,6 +337,18 @@ try
         }
 
         // Middleware pipeline
+
+        // Trusted-proxy forwarded headers (arch-review R2 N2): behind Traefik every client
+        // shares the proxy's IP, collapsing the LoginThrottle's {username}|{ip} keys onto
+        // one address (per-IP isolation gone + cheap username-lockout DoS). When enabled,
+        // X-Forwarded-For from the CONFIGURED proxies only is honored. MUST run first —
+        // everything downstream keys on Connection.RemoteIpAddress.
+        var forwardedOptions = builder.Configuration
+            .GetSection(ZB.MOM.WW.ScadaBridge.Security.ForwardedHeadersSecurityOptions.SectionName)
+            .Get<ZB.MOM.WW.ScadaBridge.Security.ForwardedHeadersSecurityOptions>() ?? new();
+        if (ZB.MOM.WW.ScadaBridge.Security.ForwardedHeadersSetup.Build(forwardedOptions) is { } fho)
+            app.UseForwardedHeaders(fho);
+
         app.UseWebSockets();
         app.UseRouting();
         app.UseAuthentication();

src/ZB.MOM.WW.ScadaBridge.ManagementService/ConfigSecretScrubber.cs

@@ -18,7 +18,7 @@ internal static class ConfigSecretScrubber
     private static readonly string[] SecretNameFragments =
         ["password", "secret", "token", "apikey", "credential", "passphrase"];
 
-    private static bool IsSecretName(string propertyName)
+    internal static bool IsSecretName(string propertyName)
     {
         foreach (var fragment in SecretNameFragments)
         {
@@ -127,6 +127,15 @@ internal static class ConfigSecretScrubber
     /// <param name="incoming">The client-submitted config JSON, possibly containing sentinel values.</param>
     /// <param name="stored">The previously stored config JSON to source real secret values from.</param>
     /// <returns>The incoming JSON with sentinel values replaced by the corresponding stored values.</returns>
+    /// <remarks>
+    /// <b>Array limitation (arch-review R2 N9):</b> sentinel restoration inside arrays
+    /// pairs incoming[i] with stored[i] BY INDEX. A client that reorders an array of
+    /// credentialed objects while round-tripping sentinels grafts the wrong stored
+    /// secret into each slot — a silent misconfiguration (never a disclosure). Clients
+    /// must not reorder arrays that carry sentinels (the CLI round-trip does not);
+    /// key-based matching is a possible future refinement if a config type ever nests
+    /// credentialed arrays.
+    /// </remarks>
     public static string? MergeSentinels(string? incoming, string? stored)
     {
         if (string.IsNullOrEmpty(incoming))

src/ZB.MOM.WW.ScadaBridge.ManagementService/DebugStreamHub.cs

@@ -1,4 +1,3 @@
-using System.Text;
 using Microsoft.AspNetCore.SignalR;
 using Microsoft.Extensions.DependencyInjection;
 using Microsoft.Extensions.Logging;
@@ -6,7 +5,6 @@ using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Repositories;
 using ZB.MOM.WW.ScadaBridge.Commons.Messages.DebugView;
 using ZB.MOM.WW.ScadaBridge.Commons.Messages.Streaming;
 using ZB.MOM.WW.ScadaBridge.Communication;
-using ZB.MOM.WW.Auth.Abstractions.Ldap;
 using ZB.MOM.WW.ScadaBridge.Security;
 
 namespace ZB.MOM.WW.ScadaBridge.ManagementService;
@@ -75,73 +73,35 @@ public class DebugStreamHub : Hub
             return;
         }
 
-        // Dev/test: when login is disabled, auto-authenticate the debug stream as the configured
-        // dev user (ALL roles incl. Deployer, system-wide) — mirroring the cookie/management
-        // bypass so the CLI debug stream is usable in a login-disabled (e.g. no-LDAP) deployment.
-        // See ManagementAuthenticator.
-        var bypassUser = ManagementAuthenticator.TryDisableLoginUser(httpContext);
-        if (bypassUser is not null)
+        // Authenticate via the SAME shared Basic→LDAP flow as POST /management and the
+        // audit REST (arch-review R2 N1): ManagementAuthenticator applies the DisableLogin
+        // bypass, the LoginThrottle lockout check BEFORE the bind, and RecordFailure/
+        // RecordSuccess bookkeeping — so hub connection attempts can no longer be used as
+        // an unthrottled LDAP-bind oracle, and hub failures feed the shared lockout.
+        var outcome = await ManagementAuthenticator.AuthenticateAsync(httpContext);
+        if (outcome.User is null)
         {
-            Context.Items[RolesKey] = bypassUser.Roles;
-            Context.Items[PermittedSiteIdsKey] = bypassUser.PermittedSiteIds;
-            _logger.LogInformation(
-                "DebugStreamHub connection established for {Username} (login disabled)", bypassUser.Username);
-            await base.OnConnectedAsync();
-            return;
-        }
-
-        // Extract Basic Auth credentials
-        var authHeader = httpContext.Request.Headers.Authorization.ToString();
-        if (string.IsNullOrEmpty(authHeader) || !authHeader.StartsWith("Basic ", StringComparison.OrdinalIgnoreCase))
-        {
-            _logger.LogWarning("DebugStreamHub connection rejected: missing Basic Auth header");
+            _logger.LogWarning("DebugStreamHub connection rejected: authentication failed or throttled");
             Context.Abort();
             return;
         }
+        var user = outcome.User;
 
-        string username, password;
-        try
+        // Role check — Deployer role required (unchanged policy).
+        if (!user.Roles.Contains(Roles.Deployer))
         {
-            var decoded = Encoding.UTF8.GetString(Convert.FromBase64String(authHeader["Basic ".Length..]));
-            var colon = decoded.IndexOf(':');
-            if (colon < 0) throw new FormatException();
-            username = decoded[..colon];
-            password = decoded[(colon + 1)..];
-        }
-        catch
-        {
-            _logger.LogWarning("DebugStreamHub connection rejected: malformed Basic Auth");
-            Context.Abort();
-            return;
-        }
-
-        // LDAP authentication
-        var ldapAuth = httpContext.RequestServices.GetRequiredService<ILdapAuthService>();
-        var authResult = await ldapAuth.AuthenticateAsync(username, password, Context.ConnectionAborted);
-        if (!authResult.Succeeded)
-        {
-            _logger.LogWarning("DebugStreamHub connection rejected: LDAP auth failed for {Username}", username);
-            Context.Abort();
-            return;
-        }
-
-        // Role check — Deployer role required
-        var roleMapper = httpContext.RequestServices.GetRequiredService<RoleMapper>();
-        var mappingResult = await roleMapper.MapGroupsToRolesAsync(authResult.Groups, Context.ConnectionAborted);
-
-        if (!mappingResult.Roles.Contains(Roles.Deployer))
-        {
-            _logger.LogWarning("DebugStreamHub connection rejected: {Username} lacks Deployer role", username);
+            _logger.LogWarning("DebugStreamHub connection rejected: {Username} lacks Deployer role", user.Username);
             Context.Abort();
             return;
         }
 
         // Persist the resolved identity on the connection so per-instance site-scope
-        // enforcement can be applied to SubscribeInstance calls.
-        Context.Items[RolesKey] = mappingResult.Roles.ToArray();
-        Context.Items[PermittedSiteIdsKey] = mappingResult.PermittedSiteIds.ToArray();
+        // enforcement can be applied to SubscribeInstance calls. PermittedSiteIds is the
+        // authenticator's normalized form (empty == system-wide), same as every other surface.
+        Context.Items[RolesKey] = user.Roles;
+        Context.Items[PermittedSiteIdsKey] = user.PermittedSiteIds;
 
-        _logger.LogInformation("DebugStreamHub connection established for {Username}", username);
+        _logger.LogInformation("DebugStreamHub connection established for {Username}", user.Username);
         await base.OnConnectedAsync();
     }
 

src/ZB.MOM.WW.ScadaBridge.ManagementService/ManagementActor.cs

@@ -467,7 +467,7 @@ public class ManagementActor : ReceiveActor
             SubmitSecuredWriteCommand cmd => await HandleSubmitSecuredWrite(sp, cmd, user),
             ApproveSecuredWriteCommand cmd => await HandleApproveSecuredWrite(sp, cmd, user),
             RejectSecuredWriteCommand cmd => await HandleRejectSecuredWrite(sp, cmd, user),
-            ListSecuredWritesCommand cmd => await HandleListSecuredWrites(sp, cmd),
+            ListSecuredWritesCommand cmd => await HandleListSecuredWrites(sp, cmd, user),
 
             // Transport bundle operations
             ExportBundleCommand cmd => await HandleExportBundle(sp, cmd, user.Username),
@@ -1247,6 +1247,11 @@ public class ManagementActor : ReceiveActor
         var site = await siteRepo.GetSiteByIdentifierAsync(cmd.SiteId)
             ?? throw new ManagementCommandException($"Site '{cmd.SiteId}' not found.");
 
+        // Site scope (arch-review R2 N3): an LDAP-mapping-scoped Operator may only
+        // submit device writes to their permitted sites — same rule C2 applies to
+        // DeployArtifacts, on a higher-consequence path. Checked before the row exists.
+        EnforceSiteScope(user, site.Id);
+
         var connections = await siteRepo.GetDataConnectionsBySiteIdAsync(site.Id);
         var conn = connections.FirstOrDefault(c =>
             string.Equals(c.Name, cmd.ConnectionName, StringComparison.Ordinal))
@@ -1293,6 +1298,11 @@ public class ManagementActor : ReceiveActor
             throw new ManagementCommandException(
                 $"Secured write {cmd.Id} is '{row.Status}', not Pending; it cannot be approved.");
 
+        // Site scope (arch-review R2 N3): the approving Verifier must be permitted on
+        // the row's target site — checked BEFORE the TTL/self-approval/CAS chain so an
+        // out-of-scope verifier can neither consume the Pending transition nor relay.
+        await EnforceSiteScopeForIdentifier(sp, user, row.SiteId);
+
         // Server-side TTL: a Pending write older than the configured age is transitioned
         // to Expired and can never be approved — the stale setpoint is never relayed
         // (arch-review S2). Checked BEFORE the self-approval/CAS so an overdue row never
@@ -1450,6 +1460,10 @@ public class ManagementActor : ReceiveActor
             throw new ManagementCommandException(
                 $"Secured write {cmd.Id} is '{entity.Status}', not Pending; it cannot be rejected.");
 
+        // Site scope (arch-review R2 N3): the rejecting Verifier must be permitted on
+        // the row's target site — checked BEFORE the TTL/self-approval chain.
+        await EnforceSiteScopeForIdentifier(sp, user, entity.SiteId);
+
         // Server-side TTL: an overdue Pending write expires here too, so a reject on a
         // stale row deterministically reports the expiry rather than recording a
         // human decision (arch-review S2).
@@ -1479,16 +1493,36 @@ public class ManagementActor : ReceiveActor
     }
 
     private static async Task<object?> HandleListSecuredWrites(
-        IServiceProvider sp, ListSecuredWritesCommand cmd)
+        IServiceProvider sp, ListSecuredWritesCommand cmd, AuthenticatedUser user)
     {
+        // Site scoping (arch-review R2 N3): an explicit SiteId filter is scope-checked
+        // like every other identifier-keyed command; an UNFILTERED list from a
+        // site-scoped non-admin caller is constrained to their permitted sites at the
+        // query level (rows AND totalCount both scoped — see ISecuredWriteRepository).
+        IReadOnlyCollection<string>? permittedIdentifiers = null;
+        if (cmd.SiteId is not null)
+        {
+            await EnforceSiteScopeForIdentifier(sp, user, cmd.SiteId);
+        }
+        else if (user.PermittedSiteIds.Length > 0
+            && !user.Roles.Contains(Roles.Administrator, StringComparer.OrdinalIgnoreCase))
+        {
+            var siteRepo = sp.GetRequiredService<ISiteRepository>();
+            var permitted = new HashSet<string>(user.PermittedSiteIds);
+            permittedIdentifiers = (await siteRepo.GetAllSitesAsync())
+                .Where(s => permitted.Contains(s.Id.ToString()))
+                .Select(s => s.SiteIdentifier)
+                .ToList();
+        }
+
         var repo = sp.GetRequiredService<ISecuredWriteRepository>();
 
         // Offset paging (arch-review P3): clamp untrusted paging inputs so a crafted
         // command can neither request a negative offset nor an unbounded page.
         var take = Math.Clamp(cmd.Take, 1, 500);
         var skip = Math.Max(0, cmd.Skip);
-        var rows = await repo.QueryAsync(cmd.Status, cmd.SiteId, skip, take);
-        var totalCount = await repo.CountAsync(cmd.Status, cmd.SiteId);
+        var rows = await repo.QueryAsync(cmd.Status, cmd.SiteId, skip, take, permittedIdentifiers);
+        var totalCount = await repo.CountAsync(cmd.Status, cmd.SiteId, permittedIdentifiers);
 
         // Opportunistic expiry sweep (arch-review S2): every time the list is read, walk
         // the page and expire any overdue Pending row. TryExpireIfStaleAsync self-filters

src/ZB.MOM.WW.ScadaBridge.Security/ForwardedHeadersSetup.cs

@@ -0,0 +1,64 @@
+using Microsoft.AspNetCore.Builder;
+using Microsoft.AspNetCore.HttpOverrides;
+using System.Net;
+
+namespace ZB.MOM.WW.ScadaBridge.Security;
+
+/// <summary>
+/// Config shape for trusted-proxy forwarded-header handling
+/// (<c>ScadaBridge:Security:ForwardedHeaders</c>). Disabled by default: a deployment
+/// with no reverse proxy must NOT honor X-Forwarded-For (a client could spoof its
+/// throttle key). The documented Traefik topologies enable it with the docker
+/// network range so LoginThrottle keys on the REAL client IP (arch-review R2 N2).
+/// </summary>
+public sealed class ForwardedHeadersSecurityOptions
+{
+    /// <summary>Configuration section binding this options class.</summary>
+    public const string SectionName = "ScadaBridge:Security:ForwardedHeaders";
+
+    /// <summary>Whether X-Forwarded-For from trusted proxies is honored.</summary>
+    public bool Enabled { get; set; }
+
+    /// <summary>Exact proxy IPs allowed to supply X-Forwarded-For.</summary>
+    public string[] KnownProxies { get; set; } = [];
+
+    /// <summary>CIDR networks allowed to supply X-Forwarded-For (e.g. "172.16.0.0/12").</summary>
+    public string[] KnownNetworks { get; set; } = [];
+}
+
+/// <summary>
+/// Builds the <see cref="ForwardedHeadersOptions"/> for <c>app.UseForwardedHeaders</c>.
+/// Pure and fail-fast: malformed entries throw at startup rather than silently
+/// trusting nothing/everything. Defaults (loopback) are CLEARED — only the
+/// explicitly configured proxies/networks are trusted, and ForwardLimit=1 means
+/// only the entry the trusted proxy itself appended is honored.
+/// </summary>
+public static class ForwardedHeadersSetup
+{
+    /// <summary>
+    /// Builds the forwarded-headers options, or <see langword="null"/> when disabled.
+    /// </summary>
+    /// <param name="options">The bound <see cref="ForwardedHeadersSecurityOptions"/>.</param>
+    /// <returns>The configured <see cref="ForwardedHeadersOptions"/>, or <see langword="null"/> when disabled.</returns>
+    public static ForwardedHeadersOptions? Build(ForwardedHeadersSecurityOptions options)
+    {
+        if (!options.Enabled) return null;
+        var built = new ForwardedHeadersOptions
+        {
+            ForwardedHeaders = ForwardedHeaders.XForwardedFor | ForwardedHeaders.XForwardedProto,
+            ForwardLimit = 1,
+        };
+        built.KnownProxies.Clear();
+        // KnownIPNetworks (System.Net.IPNetwork) is the net10 successor to the now-deprecated
+        // KnownNetworks; UseForwardedHeaders reads it identically.
+        built.KnownIPNetworks.Clear();
+        foreach (var proxy in options.KnownProxies)
+            built.KnownProxies.Add(IPAddress.Parse(proxy));
+        foreach (var network in options.KnownNetworks)
+        {
+            var parts = network.Split('/');
+            built.KnownIPNetworks.Add(new(IPAddress.Parse(parts[0]), int.Parse(parts[1])));
+        }
+        return built;
+    }
+}

src/ZB.MOM.WW.ScadaBridge.Security/LoginThrottle.cs

@@ -41,6 +41,18 @@ public sealed class LoginThrottle
     /// </summary>
     public const int MaxTrackedKeys = 10_000;
 
+    /// <summary>Amortization cadence: a full prune sweep runs every Nth failure write
+    /// (plus immediately whenever the map exceeds <see cref="MaxTrackedKeys"/>), so a
+    /// spray does not pay an O(n) scan — and a possible full sort — on every failed
+    /// request (arch-review R2 N8). Lockout SEMANTICS are unaffected: IsLockedOut reads
+    /// window/lockout expiry directly and never depends on pruning.</summary>
+    internal const int PruneEveryNFailures = 64;
+
+    /// <summary>Diagnostics/test accessor: number of currently tracked keys.</summary>
+    internal int TrackedKeyCount => _entries.Count;
+
+    private int _failureWrites;
+
     private readonly TimeProvider _clock;
     private readonly IOptions<SecurityOptions> _options;
 
@@ -118,7 +130,13 @@ public sealed class LoginThrottle
                 return Arm(existing with { Count = existing.Count + 1 }, opts, now, lockout);
             });
 
-        Prune(now);
+        // Amortized prune (R2 N8): every Nth failure, or immediately when over the hard
+        // cap — the cap is the memory-safety invariant and must never wait for the cadence.
+        if (Interlocked.Increment(ref _failureWrites) % PruneEveryNFailures == 0
+            || _entries.Count > MaxTrackedKeys)
+        {
+            Prune(now);
+        }
     }
 
     /// <summary>

tests/ZB.MOM.WW.ScadaBridge.CentralUI.Tests/Monitoring/AlarmSummaryRenderTests.cs

@@ -208,6 +208,100 @@ public class AlarmSummaryRenderTests : BunitContext
         Assert.True(_liveCache.DisposeCount >= 1);
     }
 
+    // ── arch-review R2 N4: stale-site poll guard ───────────────────────────────
+
+    [Fact]
+    public void InFlightPollForPreviousSite_DoesNotOverwriteNewSitesRows()
+    {
+        // Site 1's fan-out hangs on a TCS; site 2 answers immediately (arch-review R2 N4).
+        var site1Tcs = new TaskCompletionSource<AlarmSummaryResult>();
+        _summary.GetSiteAlarmsAsync(1, Arg.Any<CancellationToken>()).Returns(site1Tcs.Task);
+        _summary.GetSiteAlarmsAsync(2, Arg.Any<CancellationToken>()).Returns(Task.FromResult(
+            new AlarmSummaryResult(
+                new List<AlarmSummaryRow>
+                {
+                    new("Site2Instance", new AlarmStateChanged("Site2Instance", "S2-alarm", AlarmState.Active, 100, DateTimeOffset.UtcNow)),
+                },
+                Array.Empty<string>())));
+
+        var cut = Render<AlarmSummaryPage>();
+        cut.Find("[data-test='alarm-summary-site']").Change("1"); // poll in flight, hung
+        cut.Find("[data-test='alarm-summary-site']").Change("2"); // site 2 renders
+        cut.WaitForAssertion(() => Assert.Equal("Site2Instance", FirstRowInstance(cut)));
+
+        // The stale site-1 fan-out now completes — it must be dropped, not rendered.
+        site1Tcs.SetResult(new AlarmSummaryResult(
+            new List<AlarmSummaryRow>
+            {
+                new("StaleSite1", new AlarmStateChanged("StaleSite1", "S1-alarm", AlarmState.Active, 999, DateTimeOffset.UtcNow)),
+            },
+            new[] { "StaleNotReporting" }));
+
+        cut.WaitForAssertion(() =>
+        {
+            Assert.Equal("Site2Instance", FirstRowInstance(cut));
+            Assert.DoesNotContain("StaleNotReporting", cut.Markup);
+        });
+    }
+
+    // ── arch-review R2 N5: while live, the poll updates only _notReporting ──────
+
+    [Fact]
+    public void PollWhileLive_UpdatesNotReportingOnly_DoesNotRegressLiveRows()
+    {
+        // Poll snapshot = Zeta/Alpha (constructor stub) + a not-reporting instance.
+        _summary.GetSiteAlarmsAsync(Arg.Any<int>(), Arg.Any<CancellationToken>())
+            .Returns(ci => Task.FromResult(new AlarmSummaryResult(
+                new List<AlarmSummaryRow>
+                {
+                    new("Zeta", new AlarmStateChanged("Zeta", "Z-alarm", AlarmState.Active, 900, DateTimeOffset.UtcNow)),
+                },
+                new[] { "OfflineInstance" })));
+
+        var cut = RenderWithSiteSelected();
+
+        // Go live with a fresher delta: Gamma only (arch-review R2 N5).
+        _liveCache.PushAlarms(new List<AlarmStateChanged>
+        {
+            new("Gamma", "G-alarm", AlarmState.Active, 300, DateTimeOffset.UtcNow),
+        });
+        cut.WaitForAssertion(() => Assert.Equal("Gamma", FirstRowInstance(cut)));
+
+        // A poll now completes: it owns _notReporting but must NOT rebuild the rows.
+        cut.Find("[data-test='alarm-summary-refresh']").Click();
+
+        cut.WaitForAssertion(() =>
+        {
+            Assert.Contains("OfflineInstance", cut.Markup);            // notReporting refreshed
+            Assert.Equal("Gamma", FirstRowInstance(cut));              // live rows NOT regressed
+            Assert.Single(cut.FindAll("tr[data-test='alarm-summary-row']"));
+        });
+    }
+
+    // ── arch-review R2 N7: disposal guard on the live callback ─────────────────
+
+    [Fact]
+    public void LiveCallbackRacingDispose_IsDropped_NoRebuildNoThrow()
+    {
+        var cut = RenderWithSiteSelected();
+        _liveCache.PushAlarms(new List<AlarmStateChanged>
+        {
+            new("Gamma", "G-alarm", AlarmState.Active, 300, DateTimeOffset.UtcNow),
+        });
+        cut.WaitForAssertion(() => Assert.Equal("Gamma", FirstRowInstance(cut)));
+
+        // Snapshot the callback BEFORE disposal — this models a delta thread that
+        // already read the delegate when Dispose ran (arch-review R2 N7).
+        var inFlight = _liveCache.CapturedCallback!;
+        cut.Instance.Dispose();
+
+        _liveCache.PushAlarms(new List<AlarmStateChanged>()); // mutate the fake's snapshot
+        var ex = Record.Exception(inFlight);
+        Assert.Null(ex);
+        // The disposed page must not have re-applied the (now empty) live snapshot.
+        Assert.Equal("Gamma", FirstRowInstance(cut));
+    }
+
     /// <summary>
     /// Controllable in-memory fake of <see cref="ISiteAlarmLiveCache"/>: records
     /// subscribe/dispose counts and lets a test push a live snapshot (which flips
@@ -223,6 +317,7 @@ public class AlarmSummaryRenderTests : BunitContext
         public int SubscribeCount { get; private set; }
         public int DisposeCount { get; private set; }
         public int? LastSubscribedSite { get; private set; }
+        public Action? CapturedCallback => _onChanged;
 
         public IDisposable Subscribe(int siteId, Action onChanged)
         {

tests/ZB.MOM.WW.ScadaBridge.Communication.Tests/SiteAlarmLiveCacheServiceTests.cs

@@ -302,4 +302,40 @@ public class SiteAlarmLiveCacheServiceTests : TestKit
         AwaitCondition(() => service.IsLive(3), TimeSpan.FromSeconds(5));
         Assert.True(factory.GetOrCreateCount >= 1); // a client was created for the single endpoint
     }
+
+    // ── R2 T10: deathwatch un-sticks IsLive on aggregator death (N6) ──
+
+    [Fact]
+    public async Task Aggregator_Death_Resets_IsLive_And_Clears_The_Snapshot()
+    {
+        var service = CreateService(TimeSpan.FromMinutes(5), out _);
+        using var sub = service.Subscribe(SiteId, () => { });
+        AwaitAssert(() => Assert.True(service.IsLive(SiteId)), TimeSpan.FromSeconds(10));
+
+        // Kill the aggregator out from under the service (crash-death, NOT a linger stop).
+        var aggregator = await Sys.ActorSelection($"/user/site-alarm-aggregator-{SiteId}-*")
+            .ResolveOne(TimeSpan.FromSeconds(5));
+        Sys.Stop(aggregator);
+
+        AwaitAssert(() =>
+        {
+            Assert.False(service.IsLive(SiteId));          // sticky no more (R2 N6)
+            Assert.Empty(service.GetCurrentAlarms(SiteId)); // frozen snapshot never grafted
+        }, TimeSpan.FromSeconds(10));
+    }
+
+    [Fact]
+    public void Linger_Stop_Does_Not_Resurrect_The_Aggregator()
+    {
+        // Last viewer leaves, linger fires, entry removed: the deathwatch on the
+        // deliberately-stopped actor must be a no-op (entry gone), not a restart.
+        var service = CreateService(TimeSpan.FromMilliseconds(50), out var factory);
+        var sub = service.Subscribe(SiteId, () => { });
+        AwaitAssert(() => Assert.True(service.IsLive(SiteId)), TimeSpan.FromSeconds(10));
+        sub.Dispose();
+        AwaitAssert(() => Assert.False(service.IsLive(SiteId)), TimeSpan.FromSeconds(10));
+        var startsAfterStop = factory.GetOrCreateCount;
+        Thread.Sleep(300);
+        Assert.Equal(startsAfterStop, factory.GetOrCreateCount); // no self-heal restart fired
+    }
 }

tests/ZB.MOM.WW.ScadaBridge.ConfigurationDatabase.Tests/SecuredWriteRepositoryTests.cs

@@ -164,6 +164,72 @@ public class SecuredWriteRepositoryTests : IClassFixture<MsSqlMigrationFixture>
         Assert.Equal(0, await repo.CountAsync(status: "Executed", siteId: siteId));
     }
 
+    [SkippableFact]
+    public async Task QueryAsync_PermittedSiteIds_ReturnsOnlyPermittedRows()
+    {
+        Skip.IfNot(_fixture.Available, _fixture.SkipReason);
+
+        // Distinct per-run site identifiers stand in for "SITE1"/"SITE2"/"SITE3" so the
+        // permitted-set filter is asserted deterministically against a shared MSSQL.
+        var site1 = NewSiteId();
+        var site2 = NewSiteId();
+        var site3 = NewSiteId();
+        await using var context = CreateContext();
+        var repo = new SecuredWriteRepository(context);
+
+        await repo.AddAsync(NewRow(site1, status: "Pending"));
+        await repo.AddAsync(NewRow(site1, status: "Pending"));
+        await repo.AddAsync(NewRow(site2, status: "Pending"));
+        await repo.AddAsync(NewRow(site3, status: "Pending"));
+
+        var rows = await repo.QueryAsync(status: null, siteId: null, skip: 0, take: 100,
+            permittedSiteIds: new[] { site1, site3 });
+        Assert.Equal(3, rows.Count);
+        Assert.DoesNotContain(rows, r => r.SiteId == site2);
+    }
+
+    [SkippableFact]
+    public async Task CountAsync_PermittedSiteIds_CountsOnlyPermittedRows()
+    {
+        Skip.IfNot(_fixture.Available, _fixture.SkipReason);
+
+        var site1 = NewSiteId();
+        var site2 = NewSiteId();
+        var site3 = NewSiteId();
+        await using var context = CreateContext();
+        var repo = new SecuredWriteRepository(context);
+
+        await repo.AddAsync(NewRow(site1, status: "Pending"));
+        await repo.AddAsync(NewRow(site1, status: "Pending"));
+        await repo.AddAsync(NewRow(site2, status: "Pending"));
+        await repo.AddAsync(NewRow(site3, status: "Pending"));
+
+        var count = await repo.CountAsync(status: null, siteId: null,
+            permittedSiteIds: new[] { site1, site3 });
+        Assert.Equal(3, count);
+    }
+
+    [SkippableFact]
+    public async Task QueryAsync_NullPermittedSiteIds_IsUnfiltered_BackCompat()
+    {
+        Skip.IfNot(_fixture.Available, _fixture.SkipReason);
+
+        // 4 rows on a single unique site; null permittedSiteIds must not filter them
+        // out — exactly today's behavior.
+        var siteId = NewSiteId();
+        await using var context = CreateContext();
+        var repo = new SecuredWriteRepository(context);
+
+        await repo.AddAsync(NewRow(siteId, status: "Pending"));
+        await repo.AddAsync(NewRow(siteId, status: "Pending"));
+        await repo.AddAsync(NewRow(siteId, status: "Executed"));
+        await repo.AddAsync(NewRow(siteId, status: "Rejected"));
+
+        var rows = await repo.QueryAsync(status: null, siteId: siteId, skip: 0, take: 100,
+            permittedSiteIds: null);
+        Assert.Equal(4, rows.Count);
+    }
+
     // --- helpers ------------------------------------------------------------
 
     private ScadaBridgeDbContext CreateContext()

tests/ZB.MOM.WW.ScadaBridge.ManagementService.Tests/ConfigSecretScrubberTests.cs

@@ -42,4 +42,47 @@ public class ConfigSecretScrubberTests
         Assert.Contains("\"real\"", merged);
         Assert.DoesNotContain(ConfigSecretScrubber.Sentinel, merged);
     }
+
+    // ── arch-review R2 N9: frozen scrubber fragment coverage ───────────────────
+
+    // Frozen non-secret allowlist (arch-review R2 N9), mirroring RequiredRoleMatrixTests:
+    // every string-typed property on the DataConnections config types must EITHER match
+    // the scrubber's secret fragments (it gets elided) OR be listed here after a
+    // deliberate "this is not a secret" decision. A new string property with neither
+    // fails EveryConfigStringProperty_IsScrubbedOrDeliberatelyNonSecret, so a future
+    // "SigningKey"/"Pin" cannot silently leak through List/Get/audit.
+    private static readonly Dictionary<Type, string[]> KnownNonSecretStringProperties = new()
+    {
+        [typeof(ZB.MOM.WW.ScadaBridge.Commons.Types.DataConnections.OpcUaEndpointConfig)] = ["EndpointUrl", "SubscriptionDisplayName"],
+        [typeof(ZB.MOM.WW.ScadaBridge.Commons.Types.DataConnections.OpcUaUserIdentityConfig)] = ["Username", "CertificatePath"],
+        [typeof(ZB.MOM.WW.ScadaBridge.Commons.Types.DataConnections.MxGatewayEndpointConfig)] = ["Endpoint", "ClientName", "CaFile", "ServerName"],
+        [typeof(ZB.MOM.WW.ScadaBridge.Commons.Types.DataConnections.OpcUaHeartbeatConfig)] = ["TagPath"],
+        [typeof(ZB.MOM.WW.ScadaBridge.Commons.Types.DataConnections.OpcUaDeadbandConfig)] = [],
+    };
+
+    [Fact]
+    public void EveryConfigStringProperty_IsScrubbedOrDeliberatelyNonSecret()
+    {
+        foreach (var (type, allowlist) in KnownNonSecretStringProperties)
+        {
+            var stringProps = type.GetProperties(System.Reflection.BindingFlags.Public | System.Reflection.BindingFlags.Instance)
+                .Where(p => p.PropertyType == typeof(string))
+                .Select(p => p.Name);
+            foreach (var name in stringProps)
+            {
+                var scrubbed = ConfigSecretScrubber.IsSecretName(name);
+                var allowlisted = allowlist.Contains(name);
+                Assert.True(scrubbed ^ allowlisted,
+                    $"{type.Name}.{name}: must be EITHER fragment-scrubbed OR explicitly " +
+                    "allowlisted as non-secret (and never both) — see arch-review R2 N9.");
+            }
+        }
+    }
+
+    [Theory]
+    [InlineData("Password")]
+    [InlineData("CertificatePassword")]
+    [InlineData("ApiKey")]
+    public void KnownSecretProperties_MatchTheFragmentList(string name)
+        => Assert.True(ConfigSecretScrubber.IsSecretName(name));
 }

tests/ZB.MOM.WW.ScadaBridge.ManagementService.Tests/DebugStreamHubTests.cs

@@ -1,4 +1,19 @@
+using System.Net;
+using System.Text;
+using Microsoft.AspNetCore.Http;
+using Microsoft.AspNetCore.Http.Connections.Features;
+using Microsoft.AspNetCore.Http.Features;
+using Microsoft.AspNetCore.SignalR;
+using Microsoft.Extensions.DependencyInjection;
+using Microsoft.Extensions.Logging.Abstractions;
+using Microsoft.Extensions.Options;
+using NSubstitute;
+using ZB.MOM.WW.Auth.Abstractions.Ldap;
+using ZB.MOM.WW.ScadaBridge.Communication;
+using ZB.MOM.WW.ScadaBridge.Communication.Grpc;
 using ZB.MOM.WW.ScadaBridge.ManagementService;
+using ZB.MOM.WW.ScadaBridge.Security;
+using ZB.MOM.WW.ScadaBridge.Security.Auth;
 
 namespace ZB.MOM.WW.ScadaBridge.ManagementService.Tests;
 
@@ -63,4 +78,83 @@ public class DebugStreamHubTests
 
         Assert.True(allowed);
     }
+
+    // --- OnConnectedAsync delegates to ManagementAuthenticator (arch-review R2 N1) ------------
+
+    private readonly ILdapAuthService _ldap = Substitute.For<ILdapAuthService>();
+    private readonly ServiceProvider _provider;
+    private readonly LoginThrottle _throttle;
+
+    public DebugStreamHubTests()
+    {
+        var services = new ServiceCollection();
+        services.AddSingleton<IOptions<AuthDisableLoginOptions>>(
+            Options.Create(new AuthDisableLoginOptions { DisableLogin = false }));
+        services.AddSingleton<IOptions<SecurityOptions>>(Options.Create(new SecurityOptions()));
+        services.AddSingleton(TimeProvider.System);
+        services.AddSingleton<LoginThrottle>();
+        services.AddSingleton(_ldap);
+        services.AddLogging();
+        _provider = services.BuildServiceProvider();
+        _throttle = _provider.GetRequiredService<LoginThrottle>();
+    }
+
+    private async Task<TestHubCallerContext> ConnectAsync(string username, string password)
+    {
+        var http = new DefaultHttpContext { RequestServices = _provider };
+        var creds = Convert.ToBase64String(Encoding.UTF8.GetBytes($"{username}:{password}"));
+        http.Request.Headers.Authorization = $"Basic {creds}";
+        http.Connection.RemoteIpAddress = IPAddress.Parse("10.0.0.1");
+
+        var debugStreamService = new DebugStreamService(
+            new CommunicationService(Options.Create(new CommunicationOptions()), NullLogger<CommunicationService>.Instance),
+            new ServiceCollection().BuildServiceProvider(),
+            new SiteStreamGrpcClientFactory(NullLoggerFactory.Instance),
+            NullLogger<DebugStreamService>.Instance);
+        var hubContext = Substitute.For<IHubContext<DebugStreamHub>>();
+        var hub = new DebugStreamHub(debugStreamService, hubContext, NullLogger<DebugStreamHub>.Instance);
+
+        var ctx = new TestHubCallerContext(http);
+        hub.Context = ctx;
+        await hub.OnConnectedAsync();
+        return ctx;
+    }
+
+    [Fact]
+    public async Task OnConnectedAsync_FailedBinds_FeedTheSharedLoginThrottle()
+    {
+        // 5 failed hub connects for alice@10.0.0.1 must arm the same lockout the
+        // /management and /auth surfaces consult (arch-review R2 N1).
+        _ldap.AuthenticateAsync(Arg.Any<string>(), Arg.Any<string>(), Arg.Any<CancellationToken>())
+            .Returns(LdapAuthResult.Fail(LdapAuthFailure.BadCredentials));
+        for (var i = 0; i < 5; i++) await ConnectAsync("alice", "wrong"); // each Aborted
+        Assert.True(_throttle.IsLockedOut("alice", "10.0.0.1"));
+    }
+
+    [Fact]
+    public async Task OnConnectedAsync_LockedOutKey_AbortsWithoutContactingLdap()
+    {
+        for (var i = 0; i < 5; i++) _throttle.RecordFailure("alice", "10.0.0.1");
+        _ldap.ClearReceivedCalls();
+        var ctx = await ConnectAsync("alice", "whatever");
+        Assert.True(ctx.Aborted);
+        await _ldap.DidNotReceiveWithAnyArgs().AuthenticateAsync(default!, default!, default);
+    }
+
+    private sealed class TestHubCallerContext : HubCallerContext
+    {
+        private readonly FeatureCollection _features = new();
+        public TestHubCallerContext(HttpContext http) =>
+            _features.Set<IHttpContextFeature>(new TestHttpContextFeature { HttpContext = http });
+        public bool Aborted { get; private set; }
+        public override string ConnectionId => "test-conn";
+        public override string? UserIdentifier => null;
+        public override System.Security.Claims.ClaimsPrincipal? User => null;
+        public override IDictionary<object, object?> Items { get; } = new Dictionary<object, object?>();
+        public override IFeatureCollection Features => _features;
+        public override CancellationToken ConnectionAborted => CancellationToken.None;
+        public override void Abort() => Aborted = true;
+
+        private sealed class TestHttpContextFeature : IHttpContextFeature { public HttpContext? HttpContext { get; set; } }
+    }
 }

tests/ZB.MOM.WW.ScadaBridge.ManagementService.Tests/ManagementActorTests.cs

@@ -145,7 +145,7 @@ public class ManagementActorTests : TestKit, IDisposable
         var securedWriteRepo = Substitute.For<ISecuredWriteRepository>();
         securedWriteRepo.QueryAsync(
                 Arg.Any<string?>(), Arg.Any<string?>(), Arg.Any<int>(), Arg.Any<int>(),
-                Arg.Any<CancellationToken>())
+                Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
             .Returns(Task.FromResult<IReadOnlyList<PendingSecuredWrite>>(
                 Array.Empty<PendingSecuredWrite>()));
         _services.AddScoped(_ => securedWriteRepo);

tests/ZB.MOM.WW.ScadaBridge.ManagementService.Tests/SecuredWriteHandlerTests.cs

@@ -151,6 +151,9 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
         new(new AuthenticatedUser(username, username, roles, Array.Empty<string>()),
             command, Guid.NewGuid().ToString("N"));
 
+    private static ManagementEnvelope ScopedEnvelope(object command, string username, string[] permittedSiteIds, params string[] roles) =>
+        new(new AuthenticatedUser(username, username, roles, permittedSiteIds), command, Guid.NewGuid().ToString("N"));
+
     void IDisposable.Dispose() => Shutdown();
 
     /// <summary>Wires a site whose single connection uses the given protocol.</summary>
@@ -346,7 +349,7 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
     [Fact]
     public void List_FiltersByStatusAndSite()
     {
-        _securedWriteRepo.QueryAsync("Pending", "SITE1", 0, 200, Arg.Any<CancellationToken>())
+        _securedWriteRepo.QueryAsync("Pending", "SITE1", 0, 200, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
             .Returns(new List<PendingSecuredWrite>
             {
                 new()
@@ -369,13 +372,13 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
         Assert.Equal(envelope.CorrelationId, response.CorrelationId);
         Assert.Contains("\"id\":3", response.JsonData);
         Assert.Contains("alice", response.JsonData);
-        _securedWriteRepo.Received(1).QueryAsync("Pending", "SITE1", 0, 200, Arg.Any<CancellationToken>());
+        _securedWriteRepo.Received(1).QueryAsync("Pending", "SITE1", 0, 200, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>());
     }
 
     [Fact]
     public void List_NoFilters_PassesNullsToRepository()
     {
-        _securedWriteRepo.QueryAsync(null, null, 0, 200, Arg.Any<CancellationToken>())
+        _securedWriteRepo.QueryAsync(null, null, 0, 200, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
             .Returns(new List<PendingSecuredWrite>());
 
         var actor = CreateActor();
@@ -385,7 +388,49 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
         actor.Tell(envelope);
 
         ExpectMsg<ManagementSuccess>(TimeSpan.FromSeconds(5));
-        _securedWriteRepo.Received(1).QueryAsync(null, null, 0, 200, Arg.Any<CancellationToken>());
+        _securedWriteRepo.Received(1).QueryAsync(null, null, 0, 200, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>());
+    }
+
+    [Fact]
+    public void List_SiteScopedReader_ExplicitOutOfScopeSiteFilter_Unauthorized()
+    {
+        SeedSiteWithConnection(1, "SITE1", "Gw1", "MxGateway");
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(new ListSecuredWritesCommand(null, "SITE1"), "bob", ["3"], "Verifier"));
+        ExpectMsg<ManagementUnauthorized>(TimeSpan.FromSeconds(5));
+    }
+
+    [Fact]
+    public void List_SiteScopedReader_Unfiltered_QueriesOnlyPermittedIdentifiers()
+    {
+        _siteRepo.GetAllSitesAsync(Arg.Any<CancellationToken>()).Returns(new List<Site>
+        {
+            new("Site1", "SITE1") { Id = 1 },
+            new("Site3", "SITE3") { Id = 3 },
+        });
+        _securedWriteRepo.QueryAsync(null, null, 0, 200,
+                Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
+            .Returns(new List<PendingSecuredWrite>());
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(new ListSecuredWritesCommand(null, null), "bob", ["3"], "Verifier"));
+        ExpectMsg<ManagementSuccess>(TimeSpan.FromSeconds(5));
+        _securedWriteRepo.Received(1).QueryAsync(null, null, 0, 200,
+            Arg.Is<IReadOnlyCollection<string>?>(s => s != null && s.Single() == "SITE3"),
+            Arg.Any<CancellationToken>());
+    }
+
+    [Fact]
+    public void List_SystemWideReader_PassesNullPermittedFilter()
+    {
+        _securedWriteRepo.QueryAsync(null, null, 0, 200,
+                Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
+            .Returns(new List<PendingSecuredWrite>());
+        var actor = CreateActor();
+        actor.Tell(Envelope(new ListSecuredWritesCommand(null, null), "carol", "Operator"));
+        ExpectMsg<ManagementSuccess>(TimeSpan.FromSeconds(5));
+        _securedWriteRepo.Received(1).QueryAsync(null, null, 0, 200,
+            Arg.Is<IReadOnlyCollection<string>?>(s => s == null),
+            Arg.Any<CancellationToken>());
     }
 
     // ------------------------------------------------------------------------
@@ -620,16 +665,16 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
     [Fact]
     public void List_WithSkipTake_ForwardsPagingAndReturnsTotalCount()
     {
-        _securedWriteRepo.QueryAsync(null, null, 10, 25, Arg.Any<CancellationToken>())
+        _securedWriteRepo.QueryAsync(null, null, 10, 25, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
             .Returns(new List<PendingSecuredWrite>());
-        _securedWriteRepo.CountAsync(null, null, Arg.Any<CancellationToken>()).Returns(87);
+        _securedWriteRepo.CountAsync(null, null, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>()).Returns(87);
 
         var actor = CreateActor();
         actor.Tell(Envelope(new ListSecuredWritesCommand(null, null, Skip: 10, Take: 25), "carol", "Operator"));
 
         var resp = ExpectMsg<ManagementSuccess>(TimeSpan.FromSeconds(5));
-        _securedWriteRepo.Received(1).QueryAsync(null, null, 10, 25, Arg.Any<CancellationToken>());
-        _securedWriteRepo.Received(1).CountAsync(null, null, Arg.Any<CancellationToken>());
+        _securedWriteRepo.Received(1).QueryAsync(null, null, 10, 25, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>());
+        _securedWriteRepo.Received(1).CountAsync(null, null, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>());
         Assert.Contains("\"totalCount\":87", resp.JsonData);
     }
 
@@ -652,7 +697,7 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
             ValueJson = "false", ValueType = "Boolean", Status = "Pending",
             OperatorUser = "alice", SubmittedAtUtc = DateTime.UtcNow.AddHours(-25) // TTL default 24h
         };
-        _securedWriteRepo.QueryAsync(null, null, 0, 200, Arg.Any<CancellationToken>())
+        _securedWriteRepo.QueryAsync(null, null, 0, 200, Arg.Any<IReadOnlyCollection<string>?>(), Arg.Any<CancellationToken>())
             .Returns(new List<PendingSecuredWrite> { fresh, stale });
         _securedWriteRepo.TryMarkExpiredAsync(2, Arg.Any<DateTime>(), Arg.Any<CancellationToken>())
             .Returns(true);
@@ -899,4 +944,86 @@ public class SecuredWriteHandlerTests : TestKit, IDisposable
         var execute = SingleOfKind(captured, AuditKind.SecuredWriteExecute);
         Assert.Equal(ZB.MOM.WW.Audit.AuditOutcome.Failure, execute.Outcome);
     }
+
+    // ------------------------------------------------------------------------
+    // Site scope on submit / approve / reject (arch-review R2 N3)
+    // ------------------------------------------------------------------------
+
+    [Fact]
+    public void Submit_SiteScopedOperator_OutOfScopeSite_Unauthorized_NoRowInserted()
+    {
+        SeedSiteWithConnection(1, "SITE1", "Gw1", "MxGateway");
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(
+            new SubmitSecuredWriteCommand("SITE1", "Gw1", "Tag.A", "true", "Boolean", "go"),
+            "alice", ["3"], "Operator"));
+        ExpectMsg<ManagementUnauthorized>(TimeSpan.FromSeconds(5));
+        _securedWriteRepo.DidNotReceiveWithAnyArgs().AddAsync(default!, default);
+    }
+
+    [Fact]
+    public void Submit_SiteScopedOperator_InScopeSite_Succeeds()
+    {
+        SeedSiteWithConnection(1, "SITE1", "Gw1", "MxGateway");
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(
+            new SubmitSecuredWriteCommand("SITE1", "Gw1", "Tag.A", "true", "Boolean", "go"),
+            "alice", ["1"], "Operator"));
+        ExpectMsg<ManagementSuccess>(TimeSpan.FromSeconds(5));
+    }
+
+    [Fact]
+    public void Approve_SiteScopedVerifier_OutOfScopeSite_Unauthorized_NeverRelays()
+    {
+        SeedSiteWithConnection(1, "SITE1", "Gw1", "MxGateway");
+        _securedWriteRepo.GetAsync(42, Arg.Any<CancellationToken>()).Returns(new PendingSecuredWrite
+        {
+            Id = 42, SiteId = "SITE1", ConnectionName = "Gw1", TagPath = "Tag.A",
+            ValueJson = "true", ValueType = "Boolean", Status = "Pending",
+            OperatorUser = "alice", SubmittedAtUtc = DateTime.UtcNow,
+        });
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(new ApproveSecuredWriteCommand(42, "ok"), "bob", ["3"], "Verifier"));
+        ExpectMsg<ManagementUnauthorized>(TimeSpan.FromSeconds(5));
+        _securedWriteRepo.DidNotReceiveWithAnyArgs().TryMarkApprovedAsync(default, default!, default, default, default);
+        Assert.Equal(0, _comms.CallCount); // the device write is NEVER relayed
+    }
+
+    [Fact]
+    public void Reject_SiteScopedVerifier_OutOfScopeSite_Unauthorized()
+    {
+        SeedSiteWithConnection(1, "SITE1", "Gw1", "MxGateway");
+        _securedWriteRepo.GetAsync(42, Arg.Any<CancellationToken>()).Returns(new PendingSecuredWrite
+        {
+            Id = 42, SiteId = "SITE1", ConnectionName = "Gw1", TagPath = "Tag.A",
+            ValueJson = "true", ValueType = "Boolean", Status = "Pending",
+            OperatorUser = "alice", SubmittedAtUtc = DateTime.UtcNow,
+        });
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(new RejectSecuredWriteCommand(42, "no"), "bob", ["3"], "Verifier"));
+        ExpectMsg<ManagementUnauthorized>(TimeSpan.FromSeconds(5));
+        _securedWriteRepo.DidNotReceiveWithAnyArgs().UpdateAsync(default!, default);
+    }
+
+    [Fact]
+    public void Approve_ScopedAdministrator_BypassesSiteScope()
+    {
+        // A scoped Verifier who is ALSO an Administrator bypasses site scope
+        // (EnforceSiteScope admin bypass, ManagementActor.cs:499) — the approve
+        // proceeds past the scope gate rather than returning ManagementUnauthorized.
+        SeedSiteWithConnection(1, "SITE1", "Gw1", "MxGateway");
+        _securedWriteRepo.GetAsync(42, Arg.Any<CancellationToken>()).Returns(new PendingSecuredWrite
+        {
+            Id = 42, SiteId = "SITE1", ConnectionName = "Gw1", TagPath = "Tag.A",
+            ValueJson = "true", ValueType = "Boolean", Status = "Pending",
+            OperatorUser = "alice", SubmittedAtUtc = DateTime.UtcNow,
+        });
+        _securedWriteRepo.TryMarkApprovedAsync(
+                42, Arg.Any<string>(), Arg.Any<string?>(), Arg.Any<DateTime>(), Arg.Any<CancellationToken>())
+            .Returns(true);
+        var actor = CreateActor();
+        actor.Tell(ScopedEnvelope(new ApproveSecuredWriteCommand(42, "ok"), "carol", ["3"], "Verifier", "Administrator"));
+        var response = ExpectMsg<object>(TimeSpan.FromSeconds(5));
+        Assert.IsNotType<ManagementUnauthorized>(response);
+    }
 }

tests/ZB.MOM.WW.ScadaBridge.Security.Tests/ForwardedHeadersSetupTests.cs

@@ -0,0 +1,36 @@
+using Microsoft.AspNetCore.HttpOverrides;
+using ZB.MOM.WW.ScadaBridge.Security;
+using Xunit;
+
+namespace ZB.MOM.WW.ScadaBridge.Security.Tests;
+
+public class ForwardedHeadersSetupTests
+{
+    [Fact]
+    public void Build_Disabled_ReturnsNull()
+        => Assert.Null(ForwardedHeadersSetup.Build(new ForwardedHeadersSecurityOptions { Enabled = false }));
+
+    [Fact]
+    public void Build_Enabled_ParsesProxiesAndNetworks_AndClearsDefaults()
+    {
+        var built = ForwardedHeadersSetup.Build(new ForwardedHeadersSecurityOptions
+        {
+            Enabled = true,
+            KnownProxies = ["10.5.0.9"],
+            KnownNetworks = ["172.16.0.0/12"],
+        })!;
+        Assert.Equal(ForwardedHeaders.XForwardedFor | ForwardedHeaders.XForwardedProto, built.ForwardedHeaders);
+        Assert.Equal(1, built.ForwardLimit);
+        Assert.Single(built.KnownProxies);                       // ONLY the configured proxy —
+        Assert.DoesNotContain(System.Net.IPAddress.IPv6Loopback, // the loopback default is cleared
+            built.KnownProxies);
+        Assert.Single(built.KnownIPNetworks); // net10 successor to the deprecated KnownNetworks
+    }
+
+    [Theory]
+    [InlineData("not-an-ip", "172.16.0.0/12")]
+    [InlineData("10.5.0.9", "not-a-cidr")]
+    public void Build_MalformedEntry_ThrowsAtStartup(string proxy, string network)
+        => Assert.ThrowsAny<Exception>(() => ForwardedHeadersSetup.Build(
+            new ForwardedHeadersSecurityOptions { Enabled = true, KnownProxies = [proxy], KnownNetworks = [network] }));
+}

tests/ZB.MOM.WW.ScadaBridge.Security.Tests/LoginThrottleTests.cs

@@ -25,6 +25,12 @@ public class LoginThrottleTests
     private static LoginThrottle Create(TimeProvider clock, SecurityOptions? options = null) =>
         new(clock, Options.Create(options ?? new SecurityOptions()));
 
+    private static (LoginThrottle throttle, TestTimeProvider clock) Create()
+    {
+        var clock = new TestTimeProvider(Start);
+        return (Create(clock), clock);
+    }
+
     [Fact]
     public void FiveFailuresInWindow_LocksOut_ThenWindowExpiryUnlocks()
     {
@@ -34,7 +40,7 @@ public class LoginThrottleTests
         for (var i = 0; i < 5; i++) throttle.RecordFailure("alice", "10.0.0.1");
 
         Assert.True(throttle.IsLockedOut("alice", "10.0.0.1"));
-        Assert.False(throttle.IsLockedOut("alice", "10.0.0.2"));  // per username+IP key
+        Assert.False(throttle.IsLockedOut("alice", "10.0.0.2"));  // per username+IP key — real isolation in production requires the trusted-proxy ForwardedHeaders config (R2 N2); without it all clients share the proxy IP
         Assert.False(throttle.IsLockedOut("bob", "10.0.0.1"));
 
         clock.Advance(TimeSpan.FromMinutes(6));                    // lockout window passed
@@ -110,4 +116,29 @@ public class LoginThrottleTests
 
         Assert.False(throttle.IsLockedOut("alice", "10.0.0.1"));
     }
+
+    // ── arch-review R2 N8: amortized prune ─────────────────────────────────────
+
+    [Fact]
+    public void KeySpray_MapStaysBounded_AtTheHardCap()
+    {
+        var (throttle, _) = Create(); // existing helper: throttle over a fake clock
+        // Spray far past the cap: the over-cap eviction must run on EVERY write once
+        // the cap is exceeded, regardless of the amortized cadence (arch-review R2 N8).
+        for (var i = 0; i < LoginThrottle.MaxTrackedKeys + 500; i++)
+            throttle.RecordFailure($"user{i}", "10.0.0.1");
+        Assert.True(throttle.TrackedKeyCount <= LoginThrottle.MaxTrackedKeys);
+    }
+
+    [Fact]
+    public void ExpiredEntries_AreEventuallySwept_OnTheAmortizedCadence()
+    {
+        var (throttle, clock) = Create();
+        throttle.RecordFailure("stale", "10.0.0.1");
+        clock.Advance(TimeSpan.FromMinutes(10)); // window fully expired
+        for (var i = 0; i < LoginThrottle.PruneEveryNFailures; i++)
+            throttle.RecordFailure($"fresh{i}", "10.0.0.1"); // cadence tick fires within these
+        Assert.False(throttle.IsLockedOut("stale", "10.0.0.1"));
+        Assert.True(throttle.TrackedKeyCount <= LoginThrottle.PruneEveryNFailures); // "stale" swept
+    }
 }