fix(deploy): persist which nodes never acked on a deploy timeout (lmxopcua#784)

In the normal timeout branch (some acks landed) the deployment row was set to TimedOut with a null FailureReason, so GET /api/deployments/{id} could not say which node to fix; only the central log named it. The branch now persists a reason naming the silent nodes ("Timed out waiting for acks (n/m landed). No ack from: ..."), bounded to 20 named nodes plus a count of the rest, and still backstopped by the 2048-char Truncate. Tests: the reason names the silent node and not the acked one; on a 25-node silence it names 20, counts 5 and fits the column. Mutation-checked: dropping the SetFailureReason fails both, dropping the bound fails the second. Claude-Session: https://claude.ai/code/session_01GT67AEHd2Acv1YPwGfXEoV
2026-11-09 21:16:53 -05:00
parent 43f61eba2e
commit 80118a01c5
3 changed files with 97 additions and 1 deletions
@@ -111,6 +111,74 @@ public sealed class ConfigPublishCoordinatorTimeoutTests : ControlPlaneActorTest
        }, duration: TimeSpan.FromSeconds(3));
    }

+    /// <summary>
+    ///     lmxopcua#784 — a deployment that timed out with SOME acks landed must persist WHY: the status API
+    ///     returned TimedOut with a null reason, and only the central log named the silent node. The reason
+    ///     names the node(s) that never acked and not the one that did.
+    /// </summary>
+    [Fact]
+    public void Timeout_with_some_acks_landed_persists_a_reason_naming_the_silent_nodes()
+    {
+        var dbFactory = NewInMemoryDbFactory();
+        var deploymentId = SeedDispatchingDeployment(dbFactory, status: DeploymentStatus.AwaitingApplyAcks);
+        SeedNodeRows(dbFactory, deploymentId, applied: new[] { "site-a-1:4053" }, applying: new[] { "site-b-1:4053" });
+
+        var actor = Sys.ActorOf(ConfigPublishCoordinator.Props(dbFactory, TimeSpan.FromMinutes(5)));
+        actor.Tell(new ConfigPublishCoordinator.DeadlineElapsed(deploymentId));
+
+        AwaitAssert(() =>
+        {
+            using var db = dbFactory.CreateDbContext();
+            var row = db.Deployments.Single();
+            row.Status.ShouldBe(DeploymentStatus.TimedOut);
+            row.FailureReason.ShouldNotBeNull();
+            row.FailureReason.ShouldContain("No ack from: site-b-1:4053.");
+            row.FailureReason.ShouldContain("(1/2 landed)");
+            row.FailureReason.ShouldNotContain("site-a-1");
+        }, duration: TimeSpan.FromSeconds(3));
+    }
+
+    /// <summary>lmxopcua#784 — the timeout reason stays bounded on a large fleet: it names 20 nodes and counts the rest.</summary>
+    [Fact]
+    public void Timeout_reason_is_bounded_when_many_nodes_are_silent()
+    {
+        var dbFactory = NewInMemoryDbFactory();
+        var deploymentId = SeedDispatchingDeployment(dbFactory, status: DeploymentStatus.AwaitingApplyAcks);
+        var silent = Enumerable.Range(0, 25).Select(i => $"node-{i:D2}-with-a-fairly-long-host-name:4053").ToArray();
+        SeedNodeRows(dbFactory, deploymentId, applied: new[] { "acked-node:4053" }, applying: silent);
+
+        var actor = Sys.ActorOf(ConfigPublishCoordinator.Props(dbFactory, TimeSpan.FromMinutes(5)));
+        actor.Tell(new ConfigPublishCoordinator.DeadlineElapsed(deploymentId));
+
+        AwaitAssert(() =>
+        {
+            using var db = dbFactory.CreateDbContext();
+            var reason = db.Deployments.Single().FailureReason;
+            reason.ShouldNotBeNull();
+            reason.ShouldContain("node-19-with-a-fairly-long-host-name:4053");
+            reason.ShouldNotContain("node-20-");
+            reason.ShouldContain("(and 5 more)");
+            reason.Length.ShouldBeLessThanOrEqualTo(2048);
+        }, duration: TimeSpan.FromSeconds(3));
+    }
+
+    private static void SeedNodeRows(
+        IDbContextFactory<OtOpcUaConfigDbContext> dbFactory, DeploymentId deploymentId, string[] applied, string[] applying)
+    {
+        using var db = dbFactory.CreateDbContext();
+        foreach (var n in applied)
+            db.NodeDeploymentStates.Add(new Configuration.Entities.NodeDeploymentState
+            {
+                NodeId = n, DeploymentId = deploymentId.Value, Status = NodeDeploymentStatus.Applied,
+            });
+        foreach (var n in applying)
+            db.NodeDeploymentStates.Add(new Configuration.Entities.NodeDeploymentState
+            {
+                NodeId = n, DeploymentId = deploymentId.Value, Status = NodeDeploymentStatus.Applying,
+            });
+        db.SaveChanges();
+    }
+
    private static DeploymentId SeedDispatchingDeployment(
        IDbContextFactory<OtOpcUaConfigDbContext> dbFactory,
        DeploymentStatus status = DeploymentStatus.Dispatching)