Skip to content

armgit / codex

Public Imported from GitHub
0

Lightweight coding agent that runs in your terminal

Rust

Default Guardian v2 async classification to conversation mode (#53733)

felixxia-oai4d82d36ccf07
diff --git a/codex-rs/app-server/tests/suite/v2/guardian_v2.rs b/codex-rs/app-server/tests/suite/v2/guardian_v2.rs
index 90849f482d..2f77ce8dfb 100644
--- a/codex-rs/app-server/tests/suite/v2/guardian_v2.rs
+++ b/codex-rs/app-server/tests/suite/v2/guardian_v2.rs
@@ -919,9 +919,12 @@ async fn guardian_v2_routes_scoped_tool_approvals(
} else {
"prompt"
};
- let classifier_mode = match classifier_mode {
- codex_protocol::openai_models::AsyncClassifierMode::Snapshot => "snapshot",
- codex_protocol::openai_models::AsyncClassifierMode::Conversation => "conversation",
+ // Exercise the default conversation path and the explicit snapshot rollback.
+ let classifier_config = match classifier_mode {
+ codex_protocol::openai_models::AsyncClassifierMode::Snapshot => {
+ "\nasync_classifier_mode = \"snapshot\""
+ }
+ codex_protocol::openai_models::AsyncClassifierMode::Conversation => "",
};
let mut mock_config = MockResponsesConfig::new(&responses_url)
.with_model(MODEL)
@@ -932,7 +935,7 @@ async fn guardian_v2_routes_scoped_tool_approvals(
analytics_server.uri(),
))
.with_extra_config(&format!(
- "[mcp_servers.{server_name}]\nurl = \"{mcp_server_url}/mcp\"\ndefault_tools_approval_mode = \"{tool_approval_mode}\"\n\n[analytics]\nenabled = true\n\n[otel]\nmetrics_exporter = {{ otlp-http = {{ endpoint = \"{responses_url}/metrics\", protocol = \"json\" }} }}\n\n[features.guardianv2]\nenabled = true\nasync_classifier_mode = \"{classifier_mode}\"{guardian_scope_config}"
+ "[mcp_servers.{server_name}]\nurl = \"{mcp_server_url}/mcp\"\ndefault_tools_approval_mode = \"{tool_approval_mode}\"\n\n[analytics]\nenabled = true\n\n[otel]\nmetrics_exporter = {{ otlp-http = {{ endpoint = \"{responses_url}/metrics\", protocol = \"json\" }} }}\n\n[features.guardianv2]\nenabled = true{classifier_config}{guardian_scope_config}"
))
.enable_feature(Feature::GuardianApproval);
if lifecycle.has_user_input() || lifecycle.has_root_user_input() {
@@ -1259,7 +1262,8 @@ async fn guardian_v2_routes_scoped_tool_approvals(
| ThreadLifecycle::RootUserRestriction
| ThreadLifecycle::RootRestrictionDuringClassification
) {
- let retention_allowed = classifier_mode == "conversation"
+ let retention_allowed = classifier_mode
+ == codex_protocol::openai_models::AsyncClassifierMode::Conversation
&& !fail_after_classification
&& !matches!(risk, GuardianRisk::InvalidResponse)
&& !late_root_restriction;
@@ -1553,7 +1557,7 @@ async fn guardian_v2_routes_scoped_tool_approvals(
.filter_map(|item| item["id"].as_str())
.filter(|id| id.starts_with("luna-score-message-"))
.collect::<Vec<_>>();
- if classifier_mode == "conversation"
+ if classifier_mode == codex_protocol::openai_models::AsyncClassifierMode::Conversation
&& !fail_after_classification
&& let Some(latest) = retained_ids.last()
{
@@ -1907,7 +1911,7 @@ async fn guardian_v2_routes_scoped_tool_approvals(
}
let post_authorization_change_sample =
wait_for_luna_request(responses_state.as_ref(), /*index*/ 2).await?;
- if classifier_mode == "conversation"
+ if classifier_mode == codex_protocol::openai_models::AsyncClassifierMode::Conversation
&& matches!(lifecycle, ThreadLifecycle::RootUserRestriction)
{
let input = post_authorization_change_sample["input"]
diff --git a/codex-rs/core/config.schema.json b/codex-rs/core/config.schema.json
index 4aba1bab6c..fc22ace946 100644
--- a/codex-rs/core/config.schema.json
+++ b/codex-rs/core/config.schema.json
@@ -1960,7 +1960,7 @@
"$ref": "#/definitions/AsyncClassifierMode"
}
],
- "description": "Classifier experiment override. Otherwise use the model default, then snapshots."
+ "description": "Classifier mode override. Otherwise use the model default, then conversation."
},
"classifier_instructions": {
"type": "string"
diff --git a/codex-rs/core/tests/suite/scenarios_guardian_orchestrator_connector.rs b/codex-rs/core/tests/suite/scenarios_guardian_orchestrator_connector.rs
index 545d7b2f45..2f053a57c3 100644
--- a/codex-rs/core/tests/suite/scenarios_guardian_orchestrator_connector.rs
+++ b/codex-rs/core/tests/suite/scenarios_guardian_orchestrator_connector.rs
@@ -94,7 +94,7 @@ async fn host_owned_orchestrator_connector_reaches_guardian_context() -> Result<
.with_pre_build_hook(|home| {
std::fs::write(
home.join("config.toml"),
- "[features.guardianv2]\nenabled = true\n\n[features.guardianv2.review_scope]\ncomputer_use_only = false\n\n[apps._default]\ndefault_tools_approval_mode = \"prompt\"\n",
+ "[features.guardianv2]\nenabled = true\nasync_classifier_mode = \"snapshot\"\n\n[features.guardianv2.review_scope]\ncomputer_use_only = false\n\n[apps._default]\ndefault_tools_approval_mode = \"prompt\"\n",
)
.expect("write Guardian configuration");
})
diff --git a/codex-rs/ext/guardian-v2/src/async_scorer/config_tests.rs b/codex-rs/ext/guardian-v2/src/async_scorer/config_tests.rs
index 3f4cc73fb8..77543cf4a5 100644
--- a/codex-rs/ext/guardian-v2/src/async_scorer/config_tests.rs
+++ b/codex-rs/ext/guardian-v2/src/async_scorer/config_tests.rs
@@ -340,17 +340,23 @@ fn classifier_mode_uses_local_override_then_model_default() {
..Default::default()
})
.unwrap();
- let defaults = GuardianV2ModelConfig {
- async_classifier_mode: Some(AsyncClassifierMode::Conversation),
- ..Default::default()
- };
- assert_eq!(
- config.classifier_mode(Some(&defaults)),
- local.unwrap_or(AsyncClassifierMode::Conversation)
- );
+ for model in [
+ None,
+ Some(AsyncClassifierMode::Snapshot),
+ Some(AsyncClassifierMode::Conversation),
+ ] {
+ let defaults = GuardianV2ModelConfig {
+ async_classifier_mode: model,
+ ..Default::default()
+ };
+ assert_eq!(
+ config.classifier_mode(Some(&defaults)),
+ local.or(model).unwrap_or(AsyncClassifierMode::Conversation)
+ );
+ }
assert_eq!(
config.classifier_mode(/*model_defaults*/ None),
- local.unwrap_or_default()
+ local.unwrap_or(AsyncClassifierMode::Conversation)
);
}
}
diff --git a/codex-rs/ext/guardian-v2/src/async_scorer/decisions_lifecycle_tests.rs b/codex-rs/ext/guardian-v2/src/async_scorer/decisions_lifecycle_tests.rs
index 6c7bb39074..530381a7e0 100644
--- a/codex-rs/ext/guardian-v2/src/async_scorer/decisions_lifecycle_tests.rs
+++ b/codex-rs/ext/guardian-v2/src/async_scorer/decisions_lifecycle_tests.rs
@@ -17,7 +17,7 @@ async fn decisions_disagreement_failures_and_disabled_flag_preserve_baseline() -
] {
let server = responses::start_mock_server().await;
let fixture = GuardianFailureFixture::with_config(&format!(
- "[features]\nguardianv2_decisions_comparison = {enabled}\n"
+ "[features]\nguardianv2_decisions_comparison = {enabled}\n[features.guardianv2]\nasync_classifier_mode = \"snapshot\"\n"
))
.await?;
let test = &fixture.test;
@@ -181,7 +181,11 @@ async fn decisions_disagreement_failures_and_disabled_flag_preserve_baseline() -
#[tokio::test]
async fn guardian_budget_rejects_both_backends_before_sending() -> Result<()> {
skip_if_no_network!(Ok(()));
- let fixture = GuardianFailureFixture::new().await?;
+ // This test replaces the snapshot sampler to force the Responses budget failure.
+ let fixture = GuardianFailureFixture::with_config(
+ "[features.guardianv2]\nenabled = true\nasync_classifier_mode = \"snapshot\"\n",
+ )
+ .await?;
let server = responses::start_mock_server().await;
let store = fixture.test.codex.thread_extension_data();
let mut config = fixture.test.config.clone();
diff --git a/codex-rs/ext/guardian-v2/src/async_scorer/extension_tests.rs b/codex-rs/ext/guardian-v2/src/async_scorer/extension_tests.rs
index 1cb6c10055..ba624f70e2 100644
--- a/codex-rs/ext/guardian-v2/src/async_scorer/extension_tests.rs
+++ b/codex-rs/ext/guardian-v2/src/async_scorer/extension_tests.rs
@@ -2092,7 +2092,7 @@ async fn contributor_samples_tool_calls_with_the_existing_luna_pool() -> Result<
conversation_history,
r#"{"path":"README.md"}"#,
Some(TEST_GUARDIAN_POLICY),
- "[features.guardianv2.transcript]\nmax_message_entry_tokens = 100\nmax_message_transcript_tokens = 100\n",
+ "[features.guardianv2]\nasync_classifier_mode = \"snapshot\"\n[features.guardianv2.transcript]\nmax_message_entry_tokens = 100\nmax_message_transcript_tokens = 100\n",
/*model_defaults*/ None,
)
.await?;
diff --git a/codex-rs/features/src/feature_configs.rs b/codex-rs/features/src/feature_configs.rs
index e3ae224609..69d581e957 100644
--- a/codex-rs/features/src/feature_configs.rs
+++ b/codex-rs/features/src/feature_configs.rs
@@ -152,7 +152,7 @@ pub struct GuardianV2ConfigToml {
/// Transcript encoding for synchronous Guardian review and asynchronous scoring. Defaults to line.
#[serde(skip_serializing_if = "Option::is_none")]
pub transcript_mode: Option<codex_protocol::TranscriptFormat>,
- /// Classifier experiment override. Otherwise use the model default, then snapshots.
+ /// Classifier mode override. Otherwise use the model default, then conversation.
#[serde(skip_serializing_if = "Option::is_none")]
pub async_classifier_mode: Option<codex_protocol::openai_models::AsyncClassifierMode>,
/// Reset retained async history when the next request exceeds this token estimate.
diff --git a/codex-rs/protocol/src/openai_models/guardian_v2.rs b/codex-rs/protocol/src/openai_models/guardian_v2.rs
index c13a0dca9b..6a80d8dce2 100644
--- a/codex-rs/protocol/src/openai_models/guardian_v2.rs
+++ b/codex-rs/protocol/src/openai_models/guardian_v2.rs
@@ -10,8 +10,8 @@ use super::ReasoningEffort;
#[serde(rename_all = "snake_case")]
#[ts(rename_all = "snake_case")]
pub enum AsyncClassifierMode {
- #[default]
Snapshot,
+ #[default]
Conversation,
}