valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix flaky windows test (#3564)

Browse Source 
There are exactly 4 types of flaky tests in Windows x86 right now:

1. `review_input_isolated_from_parent_history` => Times out waiting for
closing events
2. `review_does_not_emit_agent_message_on_structured_output` => Times
out waiting for closing events
3. `auto_compact_runs_after_token_limit_hit` => Times out waiting for
closing events
4. `auto_compact_runs_after_token_limit_hit` => Also has a problem where
auto compact should add a third request, but receives 4 requests.

1, 2, and 3 seem to be solved with increasing threads on windows runner
from 2 -> 4.

Don't know yet why # 4 is happening, but probably also because of
WireMock issues on windows causing races.
This commit is contained in:
dedrisian-oai
2025-09-14 16:20:25 -07:00
committed by GitHub
parent 51f88fd04a
commit b2f6fc3b9a
2 changed files with 41 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
codex-rs/core/tests/suite/review.rs
View File

@@ -118,7 +118,9 @@ async fn review_op_emits_lifecycle_and_review_output() {
/// When the model returns plain text that is not JSON, ensure the child
/// lifecycle still occurs and the plain text is surfaced via
/// ExitedReviewMode(Some(..)) as the overall_explanation.
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
// Windows CI only: bump to 4 workers to prevent SSE/event starvation and test timeouts.
#[cfg_attr(windows, tokio::test(flavor = "multi_thread", worker_threads = 4))]
#[cfg_attr(not(windows), tokio::test(flavor = "multi_thread", worker_threads = 2))]
async fn review_op_with_plain_text_emits_review_fallback() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
@@ -168,7 +170,9 @@ async fn review_op_with_plain_text_emits_review_fallback() {
/// When the model returns structured JSON in a review, ensure no AgentMessage
/// is emitted; the UI consumes the structured result via ExitedReviewMode.
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
// Windows CI only: bump to 4 workers to prevent SSE/event starvation and test timeouts.
#[cfg_attr(windows, tokio::test(flavor = "multi_thread", worker_threads = 4))]
#[cfg_attr(not(windows), tokio::test(flavor = "multi_thread", worker_threads = 2))]
async fn review_does_not_emit_agent_message_on_structured_output() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
@@ -293,7 +297,9 @@ async fn review_uses_custom_review_model_from_config() {
/// When a review session begins, it must not prepend prior chat history from
/// the parent session. The request `input` should contain only the review
/// prompt from the user.
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
// Windows CI only: bump to 4 workers to prevent SSE/event starvation and test timeouts.
#[cfg_attr(windows, tokio::test(flavor = "multi_thread", worker_threads = 4))]
#[cfg_attr(not(windows), tokio::test(flavor = "multi_thread", worker_threads = 2))]
async fn review_input_isolated_from_parent_history() {
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(