mirror of
https://github.com/openai/codex.git
synced 2026-11-09 20:50:33 +00:00
starr-openai
732b12b1ef
## Why Recent `rust-ci-full` failures were dominated by transient Windows timeout clusters in process-heavy tests such as `suite::resume`, `suite::cli_stream`, `suite::auth_env`, `start_thread_uses_all_default_environments_from_codex_home`, and `connect_stdio_command_initializes_json_rpc_client_on_windows`. The goal here is to make those known flaky paths less likely to fail full CI without relaxing the global nextest timeout policy. ## What changed - Enable one global nextest retry with `retries = 1` so a single transient failure can recover. - Add a `windows_process_heavy` test group with `max-threads = 2` for the recurring Windows subprocess/session-heavy timeout families. - Add Windows-only slow-timeout overrides for that process-heavy group. - Add a narrower Windows-only timeout override for `start_thread_uses_all_default_environments_from_codex_home`, which still exceeded the broader Windows bucket in both Windows full-CI lanes. - Increase the `rust-ci-full` nextest job timeout from `45m` to `60m` so Windows ARM64 still has job-level headroom after retries and targeted per-test timeout increases. - Keep the global `slow-timeout` unchanged at `15s`. ## Validation Validated through `rust-ci-full` GitHub Actions reruns on this PR. Observed improvement on the tuned Windows lanes: - Windows x64 went from `5 timed out` to `0 timed out`. - Windows ARM64 went from `2 timed out` to `0 timed out`. - `start_thread_uses_all_default_environments_from_codex_home` recovered as a flaky pass on Windows ARM64 instead of timing out. The remaining failing tests in those runs were unrelated hard failures outside this nextest timeout tuning.
69 lines
2.9 KiB
TOML
69 lines
2.9 KiB
TOML
[profile.default]
|
|
# Retry once so one transient failure does not fail full-CI outright.
|
|
slow-timeout = { period = "15s", terminate-after = 2 }
|
|
retries = 1
|
|
|
|
[profile.default.junit]
|
|
path = "junit.xml"
|
|
|
|
[test-groups.app_server_protocol_codegen]
|
|
max-threads = 1
|
|
|
|
[test-groups.app_server_integration]
|
|
max-threads = 1
|
|
|
|
[test-groups.core_apply_patch_cli_integration]
|
|
max-threads = 1
|
|
|
|
[test-groups.windows_sandbox_legacy_sessions]
|
|
max-threads = 1
|
|
|
|
[test-groups.windows_process_heavy]
|
|
max-threads = 2
|
|
|
|
[[profile.default.overrides]]
|
|
# Do not add new tests here
|
|
filter = 'test(rmcp_client) | test(humanlike_typing_1000_chars_appears_live_no_placeholder)'
|
|
slow-timeout = { period = "1m", terminate-after = 4 }
|
|
|
|
[[profile.default.overrides]]
|
|
filter = 'test(approval_matrix_covers_all_modes)'
|
|
slow-timeout = { period = "30s", terminate-after = 2 }
|
|
|
|
[[profile.default.overrides]]
|
|
filter = 'package(codex-app-server-protocol) & (test(typescript_schema_fixtures_match_generated) | test(json_schema_fixtures_match_generated) | test(generate_ts_with_experimental_api_retains_experimental_entries) | test(generated_ts_optional_nullable_fields_only_in_params) | test(generate_json_filters_experimental_fields_and_methods))'
|
|
test-group = 'app_server_protocol_codegen'
|
|
|
|
[[profile.default.overrides]]
|
|
# These integration tests spawn a fresh app-server subprocess per case.
|
|
# Keep the library unit tests parallel.
|
|
filter = 'package(codex-app-server) & kind(test)'
|
|
test-group = 'app_server_integration'
|
|
|
|
[[profile.default.overrides]]
|
|
# These tests exercise full Codex turns and apply_patch execution, and they are
|
|
# sensitive to Windows runner process-startup stalls when many cases launch at once.
|
|
filter = 'package(codex-core) & kind(test) & test(apply_patch_cli)'
|
|
test-group = 'core_apply_patch_cli_integration'
|
|
|
|
[[profile.default.overrides]]
|
|
# These tests create restricted-token Windows child processes and private desktops.
|
|
# Serialize them to avoid exhausting Windows session/global desktop resources in CI.
|
|
filter = 'package(codex-windows-sandbox) & test(legacy_)'
|
|
test-group = 'windows_sandbox_legacy_sessions'
|
|
|
|
[[profile.default.overrides]]
|
|
# This Codex-home startup path still exceeded the broader Windows-heavy ceiling
|
|
# in both Windows full-CI lanes after contention was reduced.
|
|
platform = 'cfg(windows)'
|
|
filter = 'test(start_thread_uses_all_default_environments_from_codex_home)'
|
|
slow-timeout = { period = "1m", terminate-after = 2 }
|
|
|
|
[[profile.default.overrides]]
|
|
# These Windows-heavy tests spawn subprocesses, session files, or JSON-RPC
|
|
# clients and have been the dominant source of 30s full-CI timeouts.
|
|
platform = 'cfg(windows)'
|
|
filter = 'test(suite::resume::) | test(suite::cli_stream::) | test(suite::auth_env::) | test(start_thread_uses_all_default_environments_from_codex_home) | test(connect_stdio_command_initializes_json_rpc_client_on_windows)'
|
|
test-group = 'windows_process_heavy'
|
|
slow-timeout = { period = "45s", terminate-after = 2 }
|