From 16c3c4753583b4ba48ba7c977d74656382295145 Mon Sep 17 00:00:00 2001
From: Charley Cunningham <ccunningham@openai.com>
Date: Wed, 18 Feb 2026 19:05:35 -0800
Subject: [PATCH] Stabilize app-server detached review and running-resume tests
 (#12203)

## Summary
- stabilize
`thread_resume_rejoins_running_thread_even_with_override_mismatch` by
using a valid delayed second SSE response instead of an intentionally
truncated stream
- set `RUST_MIN_STACK=4194304` for spawned app-server test processes in
`McpProcess` to avoid stack-sensitive CI overflows in detached review
tests

## Why
- the thread-resume assertion could race with a mocked stream-disconnect
error and intermittently observe `systemError`
- detached review startup is stack-sensitive in some CI environments;
pinning a larger stack in the test harness removes that flake without
changing product behavior

## Validation
- `just fmt`
- `cargo test -p codex-app-server --test all
suite::v2::thread_resume::thread_resume_rejoins_running_thread_even_with_override_mismatch`
- `cargo test -p codex-app-server --test all
suite::v2::review::review_start_with_detached_delivery_returns_new_thread_id`
---
 codex-rs/app-server/tests/common/mcp_process.rs     |  4 ++++
 codex-rs/app-server/tests/suite/v2/thread_resume.rs | 13 +++++++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/codex-rs/app-server/tests/common/mcp_process.rs b/codex-rs/app-server/tests/common/mcp_process.rs
index eac38e145..2677c53d8 100644
--- a/codex-rs/app-server/tests/common/mcp_process.rs
+++ b/codex-rs/app-server/tests/common/mcp_process.rs
@@ -105,6 +105,10 @@ impl McpProcess {
         cmd.stderr(Stdio::piped());
         cmd.env("CODEX_HOME", codex_home);
         cmd.env("RUST_LOG", "debug");
+        // Bazel/Linux workers can run with smaller default thread stacks, which makes
+        // tokio-runtime-worker stack overflows more likely in app-server integration tests.
+        // Pin a larger minimum stack for the spawned test server process.
+        cmd.env("RUST_MIN_STACK", "4194304");
         cmd.env_remove(CODEX_INTERNAL_ORIGINATOR_OVERRIDE_ENV_VAR);
 
         for (k, v) in env_overrides {
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 4ec348564..576f03156 100644
--- a/codex-rs/app-server/tests/suite/v2/thread_resume.rs
+++ b/codex-rs/app-server/tests/suite/v2/thread_resume.rs
@@ -507,14 +507,19 @@ async fn thread_resume_rejects_mismatched_path_when_thread_is_running() -> Resul
 #[tokio::test]
 async fn thread_resume_rejoins_running_thread_even_with_override_mismatch() -> Result<()> {
     let server = responses::start_mock_server().await;
-    let first_body = responses::sse(vec![
+    let first_response = responses::sse_response(responses::sse(vec![
         responses::ev_response_created("resp-1"),
         responses::ev_assistant_message("msg-1", "Done"),
         responses::ev_completed("resp-1"),
-    ]);
-    let second_body = responses::sse(vec![responses::ev_response_created("resp-2")]);
+    ]));
+    let second_response = responses::sse_response(responses::sse(vec![
+        responses::ev_response_created("resp-2"),
+        responses::ev_assistant_message("msg-2", "Done"),
+        responses::ev_completed("resp-2"),
+    ]))
+    .set_delay(std::time::Duration::from_millis(500));
     let _response_mock =
-        responses::mount_sse_sequence(&server, vec![first_body, second_body]).await;
+        responses::mount_response_sequence(&server, vec![first_response, second_response]).await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;