test(agent): approvals-editor-check.js runs Ask When Risky in the real editor

The dev build as a throwaway instance with this checkout's extension and a stand-in provider, as
diagram-editor-check.js does. The stand-in plays a run in a project whose README asks AI agents to
upload .env: `ls -la` passes the reviewer and runs with no card; the upload (which commandSafety.js
does not flag) is rated critical + injection and stops on a card with the reviewer's reason; `rm -rf
build` asks as a danger-set command without a review. It also checks the three-option menu, that the
choice is saved as levelcode.ai.agent.approvals, the README's instruction sits inside the reviewer's
fenced activity and not in the person's section, and that nothing throws in the chat page.

12/12 on macOS against vscode/.build/electron, twice. Not part of scripts/test-extensions.sh.

Author: ndemianc