mirror of
https://github.com/openai/codex.git
synced 2026-11-08 20:40:33 +00:00
felixxia-oai
4b1cf9a4c9
## What changed - Always use the retained conversation backend for asynchronous classification; keep snapshot sampling test-only. - Accept legacy `async_classifier_mode` values in configuration and model metadata but ignore them. Emit a startup warning when `[features.guardianv2].async_classifier_mode` is configured. - Ignore legacy classifier mode differences when checking model-switch compatibility, and fail closed if the conversation backend is missing. ## Testing Update coverage for legacy configuration warnings, model-switch compatibility, retained approval-review context, and conversation-based scoring. GitOrigin-RevId: 5e8bb7e4e6e7d1589572f38bfe2498c9fa6825a0
37 lines
2.1 KiB
Rust
37 lines
2.1 KiB
Rust
use super::*;
|
|
use codex_protocol::openai_models::AsyncClassifierMode;
|
|
use test_case::test_case;
|
|
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::New, ModelReviewRequirement::Optional; "low")]
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::ReviewContinuations, ModelReviewRequirement::Optional; "retained_sync_review_delivered_once")]
|
|
#[test_case(GuardianRisk::High, ThreadLifecycle::ReviewContinuations, ModelReviewRequirement::Optional; "new_sync_review_appended")]
|
|
#[test_case(GuardianRisk::LowWithStreamFailure, ThreadLifecycle::ReviewContinuations, ModelReviewRequirement::Optional; "sync_review_restored_after_failed_stream")]
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::RootUserRestriction, ModelReviewRequirement::Optional; "new_user_instruction_resets_conversation")]
|
|
#[test_case(GuardianRisk::LowWithStreamFailure, ThreadLifecycle::New, ModelReviewRequirement::Optional; "failure_after_early_score")]
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::RootRestrictionDuringClassification, ModelReviewRequirement::Optional; "authorization_changed_during_classification")]
|
|
#[test_case(GuardianRisk::High, ThreadLifecycle::New, ModelReviewRequirement::Optional; "high")]
|
|
#[test_case(GuardianRisk::InvalidResponse, ThreadLifecycle::New, ModelReviewRequirement::Optional; "failed")]
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::Resume, ModelReviewRequirement::Optional; "resume")]
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::Fork, ModelReviewRequirement::Optional; "fork")]
|
|
#[test_case(GuardianRisk::Low, ThreadLifecycle::New, ModelReviewRequirement::Required; "mandatory_review")]
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
|
async fn conversation_classifier_preserves_approval_matrix(
|
|
risk: GuardianRisk,
|
|
lifecycle: ThreadLifecycle,
|
|
requirement: ModelReviewRequirement,
|
|
) -> Result<()> {
|
|
skip_if_no_network!(Ok(()));
|
|
guardian_v2_routes_scoped_tool_approvals(
|
|
risk,
|
|
lifecycle,
|
|
requirement,
|
|
ReviewOutcome::Allow,
|
|
TranscriptContent::Normal,
|
|
GuardianToolScope::AllTools,
|
|
/*sensitive_action*/ None,
|
|
AsyncClassifierMode::Conversation,
|
|
)
|
|
.await?;
|
|
Ok(())
|
|
}
|