Changes to sandbox command assessment feature based on initial experiment feedback (#6091)

* Removed sandbox risk categories; feedback indicates that these are not
that useful and "less is more"
* Tweaked the assessment prompt to generate terser answers
* Fixed bug in orchestrator that prevents this feature from being
exposed in the extension

codex-rs/protocol/src/protocol.rs

@@ -37,7 +37,6 @@ use ts_rs::TS;
 pub use crate::approvals::ApplyPatchApprovalRequestEvent;
 pub use crate::approvals::ExecApprovalRequestEvent;
 pub use crate::approvals::SandboxCommandAssessment;
-pub use crate::approvals::SandboxRiskCategory;
 pub use crate::approvals::SandboxRiskLevel;
 
 /// Open/close tags for special user-input blocks. Used across crates to avoid