From 10bf6008f4d76c56db86cafb2a45c1fc88024aaf Mon Sep 17 00:00:00 2001
From: Ahmed Ibrahim <aibrahim@openai.com>
Date: Mon, 9 Mar 2026 10:41:23 -0700
Subject: [PATCH] Stabilize thread resume replay tests (#13885)

## What changed
- The thread-resume replay tests now use unchecked mock sequencing so
the replay flow can complete before the test asserts.
- They also poll outbound `/responses` request counts and fail
immediately if replay emits an unexpected extra request.

## Why this fixes the flake
- The previous version asserted while the replay machinery was still
mid-flight, so the test was sometimes checking an intermediate state
instead of the completed behavior.
- Strict mock sequencing made that problem worse by forcing the test to
care about exact sub-step timing rather than about the end result.
- Letting replay settle and then asserting on stabilized request counts
makes the test validate the real contract: the replay path finishes and
does not send extra model requests.

## Scope
- Test-only change.
---
 .../tests/suite/v2/thread_resume.rs           | 35 +++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/codex-rs/app-server/tests/suite/v2/thread_resume.rs b/codex-rs/app-server/tests/suite/v2/thread_resume.rs
index e5ed8f57c..7a3c04f57 100644
--- a/codex-rs/app-server/tests/suite/v2/thread_resume.rs
+++ b/codex-rs/app-server/tests/suite/v2/thread_resume.rs
@@ -4,7 +4,6 @@ use app_test_support::create_apply_patch_sse_response;
 use app_test_support::create_fake_rollout_with_text_elements;
 use app_test_support::create_final_assistant_message_sse_response;
 use app_test_support::create_mock_responses_server_repeating_assistant;
-use app_test_support::create_mock_responses_server_sequence;
 use app_test_support::create_mock_responses_server_sequence_unchecked;
 use app_test_support::create_shell_command_sse_response;
 use app_test_support::rollout_path;
@@ -60,6 +59,36 @@ use uuid::Uuid;
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 const CODEX_5_2_INSTRUCTIONS_TEMPLATE_DEFAULT: &str = "You are Codex, a coding agent based on GPT-5. You and the user share the same workspace and collaborate to achieve the user's goals.";
 
+async fn wait_for_responses_request_count(
+    server: &wiremock::MockServer,
+    expected_count: usize,
+) -> Result<()> {
+    timeout(DEFAULT_READ_TIMEOUT, async {
+        loop {
+            let Some(requests) = server.received_requests().await else {
+                anyhow::bail!("wiremock did not record requests");
+            };
+            let responses_request_count = requests
+                .iter()
+                .filter(|request| {
+                    request.method == "POST" && request.url.path().ends_with("/responses")
+                })
+                .count();
+            if responses_request_count == expected_count {
+                return Ok::<(), anyhow::Error>(());
+            }
+            if responses_request_count > expected_count {
+                anyhow::bail!(
+                    "expected exactly {expected_count} /responses requests, got {responses_request_count}"
+                );
+            }
+            tokio::time::sleep(std::time::Duration::from_millis(10)).await;
+        }
+    })
+    .await??;
+    Ok(())
+}
+
 #[tokio::test]
 async fn thread_resume_rejects_unmaterialized_thread() -> Result<()> {
     let server = create_mock_responses_server_repeating_assistant("Done").await;
@@ -982,6 +1011,7 @@ async fn thread_resume_replays_pending_command_execution_request_approval() -> R
         primary.read_stream_until_notification_message("turn/completed"),
     )
     .await??;
+    wait_for_responses_request_count(&server, 3).await?;
 
     Ok(())
 }
@@ -1004,7 +1034,7 @@ async fn thread_resume_replays_pending_file_change_request_approval() -> Result<
         create_apply_patch_sse_response(patch, "patch-call")?,
         create_final_assistant_message_sse_response("done")?,
     ];
-    let server = create_mock_responses_server_sequence(responses).await;
+    let server = create_mock_responses_server_sequence_unchecked(responses).await;
     create_config_toml(&codex_home, &server.uri())?;
 
     let mut primary = McpProcess::new(&codex_home).await?;
@@ -1147,6 +1177,7 @@ async fn thread_resume_replays_pending_file_change_request_approval() -> Result<
         primary.read_stream_until_notification_message("turn/completed"),
     )
     .await??;
+    wait_for_responses_request_count(&server, 3).await?;
 
     Ok(())
 }