mirror of
https://github.com/openai/codex.git
synced 2026-05-15 00:32:51 +00:00
## Summary Restricts behavior of `is_known_safe_command` only to modes where it is explicitly part of the documented behavior: - when `environment_lacks_sandbox_protections` - in `AskForApproval::UnlessTrusted` Notably, as a result of this, escalations for commands that pass `is_known_safe_commands` are no longer auto-approved in AskForApproval::OnRequest or AskForApproval::Granular. ## Testing - [x] Updated unit tests - [x] Updated approvals scenario tests. --------- Co-authored-by: Codex <noreply@openai.com>