mirror of
https://github.com/openai/codex.git
synced 2026-11-07 20:30:33 +00:00
Support direct Guardian review of recorded MCP calls (#59735)
## What changed Extend `guardian_review` to assess recorded MCP tool calls using the current tool catalog, bindings, and approval policy without executing the call or remembering an approval. Return no assessment when policy or a remembered approval skips review, and reject tools blocked by app configuration. ## Testing Add a scenario test that compares direct and live MCP review inputs, verifies that neither dispatches the tool, and checks that the current app approval policy can skip review. GitOrigin-RevId: 05746dd0804a0f96d7946468701d5222171ff64f
This commit is contained in:
@@ -1775,7 +1775,7 @@ pub struct ThreadGuardianReviewParams {
|
||||
#[ts(export_to = "v2/")]
|
||||
pub struct ThreadGuardianReviewResponse {
|
||||
pub call_id: String,
|
||||
/// Null when exec policy skips approval.
|
||||
/// Null when current policy or a remembered approval skips review.
|
||||
pub assessment: Option<ThreadGuardianAssessment>,
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user