fix(worker): forget write-completion entries for dropped ack item handles

Add MxAccessWriteCompletionCache.Remove and RemoveServer and call them
from AlarmAckWriter when it drops an item (dirty re-add, LRU eviction,
failed AddItem/Advise/Write) and when it tears down its registration, so
the cache no longer keeps one entry per dropped handle for the life of
the worker.

Fixes #165

Claude-Session: https://claude.ai/code/session_016J6isfcgqy4SB2RK3ZvFvT

docs/MxAccessWorkerInstanceDesign.md

@@ -351,6 +351,17 @@ native client correlating by handle has the identical ambiguity). The exposure
 is bounded: `statuses` is an enrichment field, and `Hresult`/`ProtocolStatus`
 stay acceptance-only regardless of which completion (if any) was attributed.
 
+**The alarm ack writer narrows the window for acknowledgements.**
+`AlarmAckWriter` registers its own MXAccess server with its own
+`MxAccessWriteCompletionCache` and reuses one advised `AckMsg` item per alarm
+(least-recently-used, capped at 256). After an ack ends unconfirmed it marks the
+item dirty, and the next ack to that alarm removes and re-adds the item so the
+write waits on a fresh item handle the stale completion cannot match. Every
+drop of an item (dirty re-add, eviction, or a failed `AddItem`/`Advise`/`Write`)
+also removes that handle's completion entry, and tearing down the registration
+removes every entry for its server handle, so the cache does not grow by one
+entry per dropped handle for the life of the worker.
+
 ## Live alarm watch-list replacement
 
 An auto-mode `SubscribeAlarms` with `fallback_enabled = true` always builds a

src/ZB.MOM.WW.MxGateway.Worker.Tests/MxAccess/AlarmAckWriterTests.cs

@@ -333,6 +333,76 @@ public sealed class AlarmAckWriterTests
         Assert.Empty(server.RemovedItemHandles);
     }
 
+    [Fact]
+    public void Acknowledge_AfterDirtyReAdd_ForgetsDroppedHandleCompletion()
+    {
+        RecordingAckServer server = new RecordingAckServer { AuthenticateResult = 5 };
+        MxAccessWriteCompletionCache cache = new MxAccessWriteCompletionCache();
+        using AlarmAckWriter writer = new AlarmAckWriter(server, cache, () => { }, TimeSpan.FromMilliseconds(20), "MxGateway");
+
+        writer.Acknowledge("T.A.AckMsg", "one", Alice()); // handle 100, Unconfirmed
+        cache.Record(7, 100, Rows(MxStatusCategory.Ok, 0)); // its late completion
+        Assert.Equal(1, cache.Count);
+        server.OnWrite = (handle, item) => cache.Record(handle, item, Rows(MxStatusCategory.Ok, 0));
+
+        AlarmAckResult second = writer.Acknowledge("T.A.AckMsg", "two", Alice()); // drops 100, adds 101
+
+        Assert.Equal(AlarmAckOutcome.Applied, second.Outcome);
+        Assert.Equal(1, cache.Count);
+        Assert.Equal(0UL, cache.CurrentVersion(7, 100));
+        Assert.Equal(1UL, cache.CurrentVersion(7, 101));
+    }
+
+    [Fact]
+    public void Acknowledge_PastCacheCap_ForgetsEvictedHandleCompletion()
+    {
+        RecordingAckServer server = new RecordingAckServer { AuthenticateResult = 5 };
+        MxAccessWriteCompletionCache cache = new MxAccessWriteCompletionCache();
+        server.OnWrite = (handle, item) => cache.Record(handle, item, Rows(MxStatusCategory.Ok, 0));
+        using AlarmAckWriter writer = new AlarmAckWriter(server, cache, () => { }, TimeSpan.FromSeconds(1), "MxGateway", maxCachedItems: 2);
+
+        writer.Acknowledge("A.X.AckMsg", "1", Alice()); // handle 100
+        writer.Acknowledge("B.X.AckMsg", "2", Alice()); // handle 101
+        Assert.Equal(2, cache.Count);
+        writer.Acknowledge("C.X.AckMsg", "3", Alice()); // handle 102, evicts A (100)
+
+        Assert.Equal(2, cache.Count);
+        Assert.Equal(0UL, cache.CurrentVersion(7, 100));
+    }
+
+    [Fact]
+    public void Dispose_ForgetsServerCompletions()
+    {
+        RecordingAckServer server = new RecordingAckServer { AuthenticateResult = 5 };
+        MxAccessWriteCompletionCache cache = new MxAccessWriteCompletionCache();
+        server.OnWrite = (handle, item) => cache.Record(handle, item, Rows(MxStatusCategory.Ok, 0));
+        AlarmAckWriter writer = new AlarmAckWriter(server, cache, () => { }, TimeSpan.FromSeconds(1), "MxGateway");
+        writer.Acknowledge("A.X.AckMsg", "1", Alice());
+        writer.Acknowledge("B.X.AckMsg", "2", Alice());
+        cache.Record(8, 100, Rows(MxStatusCategory.Ok, 0)); // another server's entry survives
+
+        writer.Dispose();
+
+        Assert.Equal(1, cache.Count);
+        Assert.Equal(1UL, cache.CurrentVersion(8, 100));
+    }
+
+    [Fact]
+    public void Acknowledge_WhenWriteDisconnected_ForgetsServerCompletions()
+    {
+        RecordingAckServer server = new RecordingAckServer { AuthenticateResult = 5 };
+        MxAccessWriteCompletionCache cache = new MxAccessWriteCompletionCache();
+        server.OnWrite = (handle, item) => cache.Record(handle, item, Rows(MxStatusCategory.Ok, 0));
+        using AlarmAckWriter writer = new AlarmAckWriter(server, cache, () => { }, TimeSpan.FromSeconds(1), "MxGateway");
+        writer.Acknowledge("A.X.AckMsg", "1", Alice()); // handle 100 recorded
+        server.WriteException = new COMException("x", unchecked((int)0x80010108));
+
+        writer.Acknowledge("A.X.AckMsg", "2", Alice());
+
+        Assert.Contains("Unregister", server.Operations);
+        Assert.Equal(0, cache.Count);
+    }
+
     [Fact]
     public void Acknowledge_WhenNonOkCompletionHasNoDetail_ReturnsMinusOne()
     {

src/ZB.MOM.WW.MxGateway.Worker.Tests/MxAccess/MxAccessWriteCompletionCacheTests.cs

@@ -183,6 +183,39 @@ public sealed class MxAccessWriteCompletionCacheTests
         Assert.Equal(77, Assert.Single(statuses).Detail);
     }
 
+    /// <summary>Verifies that Remove forgets only the given handle pair.</summary>
+    [Fact]
+    public void Remove_ForgetsOnlyThatHandlePair()
+    {
+        MxAccessWriteCompletionCache cache = new();
+        cache.Record(7, 21, BuildStatuses(detail: 1));
+        cache.Record(7, 22, BuildStatuses(detail: 2));
+
+        cache.Remove(7, 21);
+        cache.Remove(7, 99); // unknown pair is a no-op
+
+        Assert.Equal(1, cache.Count);
+        Assert.Equal(0UL, cache.CurrentVersion(7, 21));
+        Assert.Equal(1UL, cache.CurrentVersion(7, 22));
+    }
+
+    /// <summary>Verifies that RemoveServer forgets every pair of that server and no other.</summary>
+    [Fact]
+    public void RemoveServer_ForgetsOnlyThatServersPairs()
+    {
+        MxAccessWriteCompletionCache cache = new();
+        cache.Record(7, 21, BuildStatuses(detail: 1));
+        cache.Record(7, -5, BuildStatuses(detail: 2));
+        cache.Record(8, 21, BuildStatuses(detail: 3));
+        cache.Record(-7, 21, BuildStatuses(detail: 4));
+
+        cache.RemoveServer(7);
+
+        Assert.Equal(2, cache.Count);
+        Assert.Equal(1UL, cache.CurrentVersion(8, 21));
+        Assert.Equal(1UL, cache.CurrentVersion(-7, 21));
+    }
+
     private static RepeatedField<MxStatusProxy> BuildStatuses(int detail)
     {
         return new RepeatedField<MxStatusProxy>

src/ZB.MOM.WW.MxGateway.Worker/MxAccess/AlarmAckWriter.cs

@@ -303,6 +303,9 @@ public sealed class AlarmAckWriter : IAlarmAckWriter
             try { mx.Unregister(serverHandle); } catch { /* best effort */ }
         }
 
+        // The registration is gone, so no completion can arrive for its handles.
+        completionCache.RemoveServer(serverHandle);
+
         itemHandles.Clear();
         itemLru.Clear();
         server = null;
@@ -335,6 +338,10 @@ public sealed class AlarmAckWriter : IAlarmAckWriter
         itemLru.Remove(node);
         try { mx.UnAdvise(serverHandle, node.Value.Handle); } catch { /* best effort */ }
         try { mx.RemoveItem(serverHandle, node.Value.Handle); } catch { /* best effort */ }
+
+        // Without this the completion cache keeps one entry per dropped handle
+        // (each Unconfirmed re-add and each eviction) for the worker's life.
+        completionCache.Remove(serverHandle, node.Value.Handle);
     }
 
     private IMxAccessServer EnsureRegistered()

src/ZB.MOM.WW.MxGateway.Worker/MxAccess/MxAccessWriteCompletionCache.cs

@@ -184,6 +184,57 @@ public sealed class MxAccessWriteCompletionCache
         }
     }
 
+    /// <summary>
+    ///     Forgets the completion entry of a handle pair whose MXAccess item was
+    ///     removed, so a long-lived writer that drops and re-adds items does not
+    ///     keep one entry per dropped handle for the life of the worker.
+    /// </summary>
+    /// <param name="serverHandle">MXAccess server handle.</param>
+    /// <param name="itemHandle">MXAccess item handle that was removed.</param>
+    public void Remove(
+        int serverHandle,
+        int itemHandle)
+    {
+        lock (syncRoot)
+        {
+            entries.Remove(CreateItemKey(serverHandle, itemHandle));
+        }
+    }
+
+    /// <summary>Forgets every completion entry recorded under a server handle that was unregistered.</summary>
+    /// <param name="serverHandle">MXAccess server handle that was unregistered.</param>
+    public void RemoveServer(int serverHandle)
+    {
+        lock (syncRoot)
+        {
+            List<long> stale = new();
+            foreach (long key in entries.Keys)
+            {
+                if ((int)(key >> 32) == serverHandle)
+                {
+                    stale.Add(key);
+                }
+            }
+
+            foreach (long key in stale)
+            {
+                entries.Remove(key);
+            }
+        }
+    }
+
+    /// <summary>Gets the number of handle pairs with a recorded completion (test seam).</summary>
+    internal int Count
+    {
+        get
+        {
+            lock (syncRoot)
+            {
+                return entries.Count;
+            }
+        }
+    }
+
     private static long CreateItemKey(
         int serverHandle,
         int itemHandle)