Merge R2-03 Virtual-Tag failure quality (arch-review round 2) [PR #430]

Findings 02/S13 (VT failure/timeout degrades node to Bad quality, no stale-Good forever), 02/S12 (evaluator retry-once on disposed-race), 02/P7 (compile-cache clear gated on changed expression set). T11/T12 deferred. STATUS.md conflict resolved additively. Build clean.
2026-07-13 10:20:43 -04:00
parent fea6477f45 6bb91e8d1f
commit 901d4e6ed3
9 changed files with 589 additions and 88 deletions
@@ -357,6 +357,87 @@ public sealed class RoslynVirtualTagEvaluatorTests
        CompiledCacheCount(sut).ShouldBe(0);
    }

+    /// <summary>02/S12 sequential pin: evaluating a compiled expression, clearing the cache, then
+    /// evaluating the SAME source again succeeds both times and leaves the cache with exactly one entry
+    /// (the recompile). This pins the clear-then-recompile contract the T8 retry-loop restructure must
+    /// not regress.</summary>
+    [Fact]
+    public void Evaluate_after_ClearCompiledScripts_recompiles_and_succeeds()
+    {
+        using var sut = new RoslynVirtualTagEvaluator(NullLogger<RoslynVirtualTagEvaluator>.Instance, NoOpScriptRoot());
+        const string expr = "return (int)ctx.GetTag(\"a\").Value + 1;";
+
+        var first = sut.Evaluate("vt-clear", expr, new Dictionary<string, object?> { ["a"] = 1 });
+        first.Success.ShouldBeTrue(first.Reason);
+        CompiledCacheCount(sut).ShouldBe(1);
+
+        sut.ClearCompiledScripts();
+        CompiledCacheCount(sut).ShouldBe(0);
+
+        var second = sut.Evaluate("vt-clear", expr, new Dictionary<string, object?> { ["a"] = 41 });
+        second.Success.ShouldBeTrue(second.Reason);
+        second.Value.ShouldBe(42);
+        CompiledCacheCount(sut).ShouldBe(1);
+    }
+
+    /// <summary>02/S12 concurrent stress repro (RED on current code): while one loop runs many compiled
+    /// (non-passthrough) evaluations of the same expression, a second loop hammers
+    /// <see cref="RoslynVirtualTagEvaluator.ClearCompiledScripts"/> — the apply-boundary clear. On the
+    /// unfixed tree a clear landing between a child's <c>GetOrCompile</c> and the run's disposed-guard
+    /// surfaces an ObjectDisposedException as a <c>Failure("script threw: Cannot access a disposed
+    /// object…")</c>; the fix retries once and every result stays Success. The whole test is WaitAsync-
+    /// bounded so a regression fails fast rather than hanging.</summary>
+    [Fact]
+    public async Task Evaluate_racing_ClearCompiledScripts_never_fails_with_disposed()
+    {
+        // Generous timeout so the wall-clock budget never fires and confounds the race assertion.
+        using var sut = new RoslynVirtualTagEvaluator(
+            NullLogger<RoslynVirtualTagEvaluator>.Instance, NoOpScriptRoot(), TimeSpan.FromSeconds(5));
+        const string expr = "return (int)ctx.GetTag(\"a\").Value + 1;";
+
+        const int loopCount = 12;
+        const int iterations = 400;
+        var failures = new System.Collections.Concurrent.ConcurrentBag<string>();
+        var remaining = loopCount; // number of concurrent evaluation loops still running
+
+        // Many concurrent evaluation loops put the thread pool under enough pressure that the inner
+        // Task.Run hop inside TimedScriptEvaluator is measurably delayed — widening the
+        // fetch→run-disposed-guard window so a clear reliably lands inside SOME in-flight evaluation.
+        // The clear loop clears on a short spin cadence (not back-to-back) so (a) most evaluations hit
+        // the warm cache — keeping compile cost bounded — and (b) at most one clear lands within a
+        // single evaluation, so the single retry the fix adds is sufficient (a back-to-back clear loop
+        // would both compile-swamp the RED run into a timeout and defeat the one-shot retry). Pre-fix a
+        // clear disposing the just-fetched evaluator surfaces as Failure("script threw: Cannot access a
+        // disposed object…"); post-fix the retry re-fetches into the current generation → all Success.
+        var evalLoops = Enumerable.Range(0, loopCount).Select(_ => Task.Run(() =>
+        {
+            for (var i = 0; i < iterations; i++)
+            {
+                var r = sut.Evaluate("vt-race", expr, new Dictionary<string, object?> { ["a"] = i });
+                if (!r.Success)
+                {
+                    failures.Add(r.Reason ?? "<null reason>");
+                }
+            }
+            Interlocked.Decrement(ref remaining);
+        }, TestContext.Current.CancellationToken)).ToArray();
+
+        var clearLoop = Task.Run(() =>
+        {
+            while (Volatile.Read(ref remaining) > 0)
+            {
+                sut.ClearCompiledScripts();
+                Thread.SpinWait(4000); // ~tens of µs between clears — frequent, but not back-to-back
+            }
+        }, TestContext.Current.CancellationToken);
+
+        await Task.WhenAll(evalLoops.Append(clearLoop))
+            .WaitAsync(TimeSpan.FromSeconds(45), TestContext.Current.CancellationToken);
+
+        failures.ShouldBeEmpty(
+            $"every evaluation must succeed despite racing clears; observed: {string.Join(" | ", failures)}");
+    }
+
    /// <summary>Reads the count of the private compiled-script cache via reflection. The cache is a
    /// <c>CompiledScriptCache&lt;,&gt;</c> which exposes a <c>Count</c> property (not <c>ICollection</c>).</summary>
    private static int CompiledCacheCount(RoslynVirtualTagEvaluator sut)