clone/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-04-26 15:45:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

[fix] app server flaky send_messages test (#8874)

Browse Source 
Fix flakiness of CI test:
https://github.com/openai/codex/actions/runs/20350530276/job/58473691434?pr=8282

This PR does two things:
1. move the flakiness test to use responses API instead of chat
completion API
2. make mcp_process agnostic to the order of
responses/notifications/requests that come in, by buffering messages not
read
This commit is contained in:
Celia Chen
2026-01-08 12:41:21 -08:00
committed by GitHub
parent a70f5b0b3c
commit 051bf81df9
4 changed files with 103 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
codex-rs/app-server/tests/suite/send_message.rs
View File

@@ -1,7 +1,5 @@
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::to_response;
use codex_app_server_protocol::AddConversationListenerParams;
use codex_app_server_protocol::AddConversationSubscriptionResponse;
@@ -17,6 +15,7 @@ use codex_protocol::ThreadId;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ResponseItem;
use codex_protocol::protocol::RawResponseItemEvent;
use core_test_support::responses;
use pretty_assertions::assert_eq;
use std::path::Path;
use tempfile::TempDir;
@@ -26,13 +25,21 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
#[tokio::test]
async fn test_send_message_success() -> Result<()> {
// Spin up a mock completions server that immediately ends the Codex turn.
// Spin up a mock responses server that immediately ends the Codex turn.
// Two Codex turns hit the mock model (session start + send-user-message). Provide two SSE responses.
let responses = vec![
create_final_assistant_message_sse_response("Done")?,
create_final_assistant_message_sse_response("Done")?,
];
let server = create_mock_chat_completions_server(responses).await;
let server = responses::start_mock_server().await;
let body1 = responses::sse(vec![
responses::ev_response_created("resp-1"),
responses::ev_assistant_message("msg-1", "Done"),
responses::ev_completed("resp-1"),
]);
let body2 = responses::sse(vec![
responses::ev_response_created("resp-2"),
responses::ev_assistant_message("msg-2", "Done"),
responses::ev_completed("resp-2"),
]);
let _response_mock1 = responses::mount_sse_once(&server, body1).await;
let _response_mock2 = responses::mount_sse_once(&server, body2).await;
// Create a temporary Codex home with config pointing at the mock server.
let codex_home = TempDir::new()?;
@@ -135,8 +142,13 @@ async fn send_message(
#[tokio::test]
async fn test_send_message_raw_notifications_opt_in() -> Result<()> {
let responses = vec![create_final_assistant_message_sse_response("Done")?];
let server = create_mock_chat_completions_server(responses).await;
let server = responses::start_mock_server().await;
let body = responses::sse(vec![
responses::ev_response_created("resp-1"),
responses::ev_assistant_message("msg-1", "Done"),
responses::ev_completed("resp-1"),
]);
let _response_mock = responses::mount_sse_once(&server, body).await;
let codex_home = TempDir::new()?;
create_config_toml(codex_home.path(), &server.uri())?;
@@ -259,7 +271,7 @@ 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
"#
@@ -269,6 +281,7 @@ stream_max_retries = 0
#[expect(clippy::expect_used)]
async fn read_raw_response_item(mcp: &mut McpProcess, conversation_id: ThreadId) -> ResponseItem {
// TODO: Switch to rawResponseItem/completed once we migrate to app server v2 in codex web.
loop {
let raw_notification: JSONRPCNotification = timeout(
DEFAULT_READ_TIMEOUT,