mirror of
https://github.com/openai/codex.git
synced 2026-11-12 21:20:34 +00:00
swastik-oai
3934ae926a
## 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
17 lines
746 B
Rust
17 lines
746 B
Rust
//! Host adapter types and assessment results for synchronous Guardian review.
|
|
//! The extension supplies agent startup and owns the reviewer pool and its lifecycle.
|
|
|
|
pub use crate::guardian::GuardianReviewSession;
|
|
pub use crate::guardian::GuardianReviewState;
|
|
pub use crate::guardian::PreparedGuardianContext;
|
|
pub use crate::guardian::prepare_review_prewarm;
|
|
pub use crate::mcp_tool_call::conversation_history::conversation_history_tools;
|
|
|
|
/// The result of checking a recorded call without executing it.
|
|
#[derive(Debug, PartialEq, Eq)]
|
|
pub struct GuardianReviewResult {
|
|
pub call_id: String,
|
|
/// Absent when current policy or a remembered approval skips review.
|
|
pub assessment: Option<codex_guardian_reviewer::GuardianAssessment>,
|
|
}
|