mirror of
https://github.com/openai/codex.git
synced 2026-05-24 04:54:52 +00:00
Update guardian output schema (#17061)
## Summary - Update guardian output schema to separate risk, authorization, outcome, and rationale. - Feed guardian rationale into rejection messages. - Split the guardian policy into template and tenant-config sections. ## Validation - `cargo test -p codex-core mcp_tool_call` - `env -u CODEX_SANDBOX_NETWORK_DISABLED INSTA_UPDATE=always cargo test -p codex-core guardian::` --------- Co-authored-by: Owen Lin <owen@openai.com>
This commit is contained in:
@@ -2004,6 +2004,7 @@ impl Session {
|
||||
session_telemetry,
|
||||
models_manager: Arc::clone(&models_manager),
|
||||
tool_approvals: Mutex::new(ApprovalStore::default()),
|
||||
guardian_rejection_rationales: Mutex::new(HashMap::new()),
|
||||
skills_manager,
|
||||
plugins_manager: Arc::clone(&plugins_manager),
|
||||
mcp_manager: Arc::clone(&mcp_manager),
|
||||
|
||||
Reference in New Issue
Block a user