{"version":"2.1.239","anchor":"permission-prompts-from-remote-agents-can-no-longer-create-p","canonical_anchor":"permission-prompts-from-remote-agents-can-no-longer-create-p","heading":"Permission prompts from remote agents can no longer create permanent allow rules","tier":"notice","area":"Permissions","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.239\/e\/permission-prompts-from-remote-agents-can-no-longer-create-p","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.239","markdown":"### Permission prompts from remote agents can no longer create permanent allow rules\n\nPermission requests from remote agents can only be approved once, never remembered.\n\n**What**\n\nWhen a permission request comes from a remote agent, Claude Code will not offer to remember the decision. The always-allow option is suppressed and the usual rule suggestions are hidden, the same way they are for requests capped by an organisation policy. Approvals from remote agents are one-time only.\n\n**Details**\n\n- Two separate guards: one on the computation that decides whether an always-allow choice is available, one in the suggestion UI.\n- Local requests are unaffected and still offer persistent rules.\n\n**Evidence**\n\n`e.requestSource?.type === \"remote-agent\"`\n\n- Area: Permissions\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 4\/5"}