fix(scripts): reset-aware handshake refuses a null reset value; document additive timeouts (#36 review)

A null resetValue encoded to null, which wrote an empty string and then handed the waiter a null target (= any change), fast-pathing on the stale cache and reinstating the race the overload exists to close. The context parameter is now non-nullable and the accessor throws ArgumentException before any write. Also: additive-timeout note on all surfaces, batch-failure message no longer names the bool overload, and the error-message/batch-failure branches are pinned. Claude-Session: https://claude.ai/code/session_01XPsuy2ZZ5Gbyfpt8PrK5BV
2026-09-10 15:35:50 -04:00
parent 637da6c020
commit 17d5d3e639
8 changed files with 138 additions and 12 deletions
@@ -24,7 +24,10 @@ public class WriteBatchResetAndWaitTests : TestKit
            new SharedScriptLibrary(
                new ScriptCompilationService(NullLogger<ScriptCompilationService>.Instance),
                NullLogger<SharedScriptLibrary>.Instance),
-            currentCallDepth: 0, maxCallDepth: 10, askTimeout: TimeSpan.FromSeconds(5),
+            // 30s: the legs Ask the InstanceActor with their own bounds (the batch's internal 35s,
+            // the waits' own timeouts); a short ambient Ask timeout would race those and make the
+            // reset/response phases indistinguishable from an AskTimeoutException.
+            currentCallDepth: 0, maxCallDepth: 10, askTimeout: TimeSpan.FromSeconds(30),
            instanceName: Instance, logger: NullLogger.Instance);

    [Fact]
@@ -125,6 +128,64 @@ public class WriteBatchResetAndWaitTests : TestKit
        Assert.True(result.TimedOut);
        Assert.Equal(HandshakePhase.Response, result.Phase);
        Assert.False(result.ResetFailed);
+        // The message names the attribute that did not answer and the bound it blew.
+        Assert.Contains("MoveOutCompleteFlag", result.ErrorMessage);
+        Assert.Contains("25", result.ErrorMessage);
+    }
+
+    /// <summary>
+    /// A reset wait that fails WITHOUT timing out (a predicate blew up in the waiter) surfaces the
+    /// actor's own message verbatim rather than a synthesized one, and still writes nothing further.
+    /// </summary>
+    [Fact]
+    public async Task ResetWaitError_PassesTheActorsMessageThrough()
+    {
+        var probe = CreateTestProbe();
+        var ctx = CreateContext(probe.Ref);
+
+        var call = ctx.WriteBatchResetAndWait(
+            Values, "MoveOutFlag", "True", "MoveOutCompleteFlag", "True", TimeSpan.FromSeconds(25),
+            "MoveOutCompleteFlag", "False", TimeSpan.FromSeconds(10));
+
+        var reset = probe.ExpectMsg<SetStaticAttributeCommand>(TimeSpan.FromSeconds(5));
+        probe.Reply(new SetStaticAttributeResponse(reset.CorrelationId, Instance, "MoveOutCompleteFlag", true, null, DateTimeOffset.UtcNow));
+        var resetWait = probe.ExpectMsg<WaitForAttributeRequest>(TimeSpan.FromSeconds(5));
+        probe.Reply(new WaitForAttributeResponse(
+            resetWait.CorrelationId, Matched: false, null, null, TimedOut: false, ErrorMessage: "predicate threw"));
+
+        var result = await call;
+        Assert.False(result.Matched);
+        Assert.False(result.TimedOut);
+        Assert.True(result.ResetFailed);
+        Assert.Equal("predicate threw", result.ErrorMessage);
+
+        probe.ExpectNoMsg(TimeSpan.FromMilliseconds(300));
+    }
+
+    /// <summary>
+    /// The batch leg keeps throwing after a successful reset — a device-rejected batch is a hard
+    /// failure, not a <see cref="HandshakeResult"/> the script could mistake for a timeout.
+    /// </summary>
+    [Fact]
+    public async Task BatchFailureAfterASuccessfulReset_StillThrows()
+    {
+        var probe = CreateTestProbe();
+        var ctx = CreateContext(probe.Ref);
+
+        var call = ctx.WriteBatchResetAndWait(
+            Values, "MoveOutFlag", "True", "MoveOutCompleteFlag", "True", TimeSpan.FromSeconds(25),
+            "MoveOutCompleteFlag", "False", TimeSpan.FromSeconds(10));
+
+        var reset = probe.ExpectMsg<SetStaticAttributeCommand>(TimeSpan.FromSeconds(5));
+        probe.Reply(new SetStaticAttributeResponse(reset.CorrelationId, Instance, "MoveOutCompleteFlag", true, null, DateTimeOffset.UtcNow));
+        var resetWait = probe.ExpectMsg<WaitForAttributeRequest>(TimeSpan.FromSeconds(5));
+        probe.Reply(new WaitForAttributeResponse(resetWait.CorrelationId, Matched: true, false, "Good", TimedOut: false));
+        var batch = probe.ExpectMsg<WriteAttributeBatchRequest>(TimeSpan.FromSeconds(5));
+        probe.Reply(new WriteAttributeBatchResponse(batch.CorrelationId, false, "gateway rejected"));
+
+        var ex = await Assert.ThrowsAsync<InvalidOperationException>(() => call);
+        Assert.Contains("gateway rejected", ex.Message);
+        Assert.Contains("Batch write failed", ex.Message);
    }

    [Fact]