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/core/src/config_loader/tests.rs

@@ -636,7 +636,7 @@ allowed_approval_policies = ["on-request"]
                 rules: None,
                 enforce_residency: None,
                 network: None,
-                guardian_developer_instructions: None,
+                guardian_policy_config: None,
             }))
         }),
     )
@@ -688,7 +688,7 @@ allowed_approval_policies = ["on-request"]
             rules: None,
             enforce_residency: None,
             network: None,
-            guardian_developer_instructions: None,
+            guardian_policy_config: None,
         },
     );
     load_requirements_toml(&mut config_requirements_toml, &requirements_file).await?;
@@ -729,7 +729,7 @@ async fn load_config_layers_includes_cloud_requirements() -> anyhow::Result<()>
         rules: None,
         enforce_residency: None,
         network: None,
-        guardian_developer_instructions: None,
+        guardian_policy_config: None,
     };
     let expected = requirements.clone();
     let cloud_requirements = CloudRequirementsLoader::new(async move { Ok(Some(requirements)) });