From c4af304c7710059237133e6c597d25abd35428bd Mon Sep 17 00:00:00 2001
From: Celia Chen <celia@openai.com>
Date: Thu, 8 Jan 2026 10:17:05 -0800
Subject: [PATCH] [fix] app server flaky thread/resume tests (#8870)

Fix flakiness of CI tests:
https://github.com/openai/codex/actions/runs/20350530276/job/58473691443?pr=8282

This PR does two things:
1. test with responses API instead of chat completions API in
thread_resume tests;
2. have a new responses API fixture that mocks out arbitrary numbers of
responses API calls (including no calls) and have the same repeated
response.

Tested by CI
---
 codex-rs/app-server/tests/common/lib.rs        |  1 +
 .../tests/common/mock_model_server.rs          | 18 ++++++++++++++++++
 .../app-server/tests/suite/v2/thread_resume.rs | 12 ++++++------
 3 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/codex-rs/app-server/tests/common/lib.rs b/codex-rs/app-server/tests/common/lib.rs
index f3950595b..38beab779 100644
--- a/codex-rs/app-server/tests/common/lib.rs
+++ b/codex-rs/app-server/tests/common/lib.rs
@@ -20,6 +20,7 @@ pub use core_test_support::test_tmp_path_buf;
 pub use mcp_process::McpProcess;
 pub use mock_model_server::create_mock_chat_completions_server;
 pub use mock_model_server::create_mock_chat_completions_server_unchecked;
+pub use mock_model_server::create_mock_responses_server_repeating_assistant;
 pub use models_cache::write_models_cache;
 pub use models_cache::write_models_cache_with_models;
 pub use responses::create_apply_patch_sse_response;
diff --git a/codex-rs/app-server/tests/common/mock_model_server.rs b/codex-rs/app-server/tests/common/mock_model_server.rs
index 08765338a..77fa6b201 100644
--- a/codex-rs/app-server/tests/common/mock_model_server.rs
+++ b/codex-rs/app-server/tests/common/mock_model_server.rs
@@ -1,12 +1,14 @@
 use std::sync::atomic::AtomicUsize;
 use std::sync::atomic::Ordering;
 
+use core_test_support::responses;
 use wiremock::Mock;
 use wiremock::MockServer;
 use wiremock::Respond;
 use wiremock::ResponseTemplate;
 use wiremock::matchers::method;
 use wiremock::matchers::path;
+use wiremock::matchers::path_regex;
 
 /// Create a mock server that will provide the responses, in order, for
 /// requests to the `/v1/chat/completions` endpoint.
@@ -64,3 +66,19 @@ impl Respond for SeqResponder {
         }
     }
 }
+
+/// Create a mock responses API server that returns the same assistant message for every request.
+pub async fn create_mock_responses_server_repeating_assistant(message: &str) -> MockServer {
+    let server = responses::start_mock_server().await;
+    let body = responses::sse(vec![
+        responses::ev_response_created("resp-1"),
+        responses::ev_assistant_message("msg-1", message),
+        responses::ev_completed("resp-1"),
+    ]);
+    Mock::given(method("POST"))
+        .and(path_regex(".*/responses$"))
+        .respond_with(responses::sse_response(body))
+        .mount(&server)
+        .await;
+    server
+}
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 be8562e2f..483095a98 100644
--- a/codex-rs/app-server/tests/suite/v2/thread_resume.rs
+++ b/codex-rs/app-server/tests/suite/v2/thread_resume.rs
@@ -1,7 +1,7 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
 use app_test_support::create_fake_rollout;
-use app_test_support::create_mock_chat_completions_server;
+use app_test_support::create_mock_responses_server_repeating_assistant;
 use app_test_support::to_response;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
@@ -23,7 +23,7 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
 
 #[tokio::test]
 async fn thread_resume_returns_original_thread() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
 
@@ -66,7 +66,7 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
 
 #[tokio::test]
 async fn thread_resume_returns_rollout_history() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
 
@@ -130,7 +130,7 @@ async fn thread_resume_returns_rollout_history() -> Result<()> {
 
 #[tokio::test]
 async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
 
@@ -174,7 +174,7 @@ async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
 
 #[tokio::test]
 async fn thread_resume_supports_history_and_overrides() -> Result<()> {
-    let server = create_mock_chat_completions_server(vec![]).await;
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
 
@@ -247,7 +247,7 @@ model_provider = "mock_provider"
 [model_providers.mock_provider]
 name = "Mock provider for test"
 base_url = "{server_uri}/v1"
-wire_api = "chat"
+wire_api = "responses"
 request_max_retries = 0
 stream_max_retries = 0
 "#