From 2383978a2c1f99997f2960c522be7b984485cb89 Mon Sep 17 00:00:00 2001
From: Michael Bolin <mbolin@openai.com>
Date: Fri, 13 Feb 2026 09:51:22 -0800
Subject: [PATCH] fix: reduce flakiness of
 compact_resume_after_second_compaction_preserves_history (#11663)

## Why
`compact_resume_after_second_compaction_preserves_history` has been
intermittently flaky in Windows CI.

The test had two one-shot request matchers in the second compact/resume
phase that could overlap, and it waited for the first `Warning` event
after compaction. In practice, that made the test sensitive to
platform/config-specific prompt shape and unrelated warning timing.

## What Changed
- Hardened the second compaction matcher in
`codex-rs/core/tests/suite/compact_resume_fork.rs` so it accepts
expected compact-request variants while explicitly excluding the
`AFTER_SECOND_RESUME` payload.
- Updated `compact_conversation()` to wait for the specific compaction
warning (`COMPACT_WARNING_MESSAGE`) rather than any `Warning` event.
- Added an inline comment explaining why the matcher is intentionally
broad but disjoint from the follow-up resume matcher.

## Test Plan
- `cargo test -p codex-core --test all
suite::compact_resume_fork::compact_resume_after_second_compaction_preserves_history
-- --exact`
- Repeated the same test in a loop (40 runs) to check for local
nondeterminism.
---
 .../core/tests/suite/compact_resume_fork.rs     | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/codex-rs/core/tests/suite/compact_resume_fork.rs b/codex-rs/core/tests/suite/compact_resume_fork.rs
index ff90d4baf..fc77a2621 100644
--- a/codex-rs/core/tests/suite/compact_resume_fork.rs
+++ b/codex-rs/core/tests/suite/compact_resume_fork.rs
@@ -932,9 +932,16 @@ async fn mount_second_compact_flow(server: &MockServer) -> Vec<ResponseMock> {
     ]);
     let sse7 = sse(vec![ev_completed("r7")]);
 
+    // Keep this matcher broad enough to survive prompt-shape differences across
+    // platforms/config (history may include either marker text or compact prompt
+    // fragments), but explicitly exclude the final resume turn so these two
+    // one-shot mocks cannot race for the same request.
     let match_second_compact = |req: &wiremock::Request| {
         let body = std::str::from_utf8(&req.body).unwrap_or("");
-        body.contains("AFTER_FORK")
+        (body.contains("AFTER_FORK")
+            || body_contains_text(body, SUMMARIZATION_PROMPT)
+            || body.contains(&json_fragment(FIRST_REPLY)))
+            && !body.contains(&format!("\"text\":\"{AFTER_SECOND_RESUME}\""))
     };
     let second_compact = mount_sse_once_match(server, match_second_compact, sse6).await;
 
@@ -984,7 +991,13 @@ async fn compact_conversation(conversation: &Arc<CodexThread>) {
         .submit(Op::Compact)
         .await
         .expect("compact conversation");
-    let warning_event = wait_for_event(conversation, |ev| matches!(ev, EventMsg::Warning(_))).await;
+    let warning_event = wait_for_event(conversation, |ev| {
+        matches!(
+            ev,
+            EventMsg::Warning(WarningEvent { message }) if message == COMPACT_WARNING_MESSAGE
+        )
+    })
+    .await;
     let EventMsg::Warning(WarningEvent { message }) = warning_event else {
         panic!("expected warning event after compact");
     };