From 6ce7f01be83b264ab0113e181beeb409c0eb438e Mon Sep 17 00:00:00 2001
From: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
Date: Fri, 27 Feb 2026 20:14:52 +0000
Subject: [PATCH] Fix epoch race condition causing unit tests to hang on
 net10.0 and net472

The HasUnprocessedMessages guard (previous commit) correctly prevents
spurious workflow_invoke Activity creation on timeout wake-ups, but
exposed a latent race in the epoch-based signal filtering.

The race: when the run loop processes messages quickly and calls
Interlocked.Increment(ref _completionEpoch) before the consumer calls
TakeEventStreamAsync, the consumer reads the already-incremented epoch
and sets myEpoch = epoch + 1. This causes the consumer to skip the
valid InternalHaltSignal (its epoch < myEpoch) and block forever
waiting for a signal that will never arrive (since the guard prevents
spurious signal generation).

Fix: read _completionEpoch without +1. The +1 was originally needed to
filter stale signals from timeout-driven spurious loop iterations, but
those no longer exist thanks to the HasUnprocessedMessages guard.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 .../Execution/StreamingRunEventStream.cs                  | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/dotnet/src/Microsoft.Agents.AI.Workflows/Execution/StreamingRunEventStream.cs b/dotnet/src/Microsoft.Agents.AI.Workflows/Execution/StreamingRunEventStream.cs
index dabfb8a54b..189ec0d5a4 100644
--- a/dotnet/src/Microsoft.Agents.AI.Workflows/Execution/StreamingRunEventStream.cs
+++ b/dotnet/src/Microsoft.Agents.AI.Workflows/Execution/StreamingRunEventStream.cs
@@ -206,8 +206,12 @@ internal sealed class StreamingRunEventStream : IRunEventStream
         bool blockOnPendingRequest,
         [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {
-        // Get the current epoch - we'll only respond to completion signals from this epoch or later
-        int myEpoch = Volatile.Read(ref this._completionEpoch) + 1;
+        // Get the current epoch - we'll only respond to completion signals from this epoch or later.
+        // Note: We read the current value (not +1) because the HasUnprocessedMessages guard in the
+        // run loop prevents spurious completion signals, so there are no stale signals to filter.
+        // Using +1 would race with the run loop's Interlocked.Increment, causing the consumer to
+        // skip the valid signal when the run loop finishes before TakeEventStreamAsync starts.
+        int myEpoch = Volatile.Read(ref this._completionEpoch);
 
         // Use custom async enumerable to avoid exceptions on cancellation.
         NonThrowingChannelReaderAsyncEnumerable<WorkflowEvent> eventStream = new(this._eventChannel.Reader);