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>

codex-rs/protocol/src/protocol.rs

@@ -69,6 +69,7 @@ pub use crate::approvals::GuardianAssessmentEvent;
 pub use crate::approvals::GuardianAssessmentStatus;
 pub use crate::approvals::GuardianCommandSource;
 pub use crate::approvals::GuardianRiskLevel;
+pub use crate::approvals::GuardianUserAuthorization;
 pub use crate::approvals::NetworkApprovalContext;
 pub use crate::approvals::NetworkApprovalProtocol;
 pub use crate::approvals::NetworkPolicyAmendment;