{"version":"2.1.290","anchor":"subagent-permission-prompts-tagged-with-requestsource-subage","canonical_anchor":"subagent-permission-prompts-tagged-with-requestsource-subage","heading":"Permission requests from background subagents are now labelled as coming from a subagent","tier":"notice","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.290\/e\/subagent-permission-prompts-tagged-with-requestsource-subage","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.290","markdown":"### Permission requests from background subagents are now labelled as coming from a subagent\n\nWhen a background subagent asks for permission, the request is now labelled as coming from a subagent\n\n**Unclear.** It is not clear when the label is applied or whether anything on screen shows it yet.\n\n**What**\n\nA subagent is a separate helper that Claude Code starts to work on part of a task, sometimes in the background while you do something else. When a background subagent needs your permission to do something, such as run a command or edit a file, Claude Code asks you first. Those permission requests now carry a label saying they came from a subagent. The labelling already existed for other kinds of request; this extends it to background subagents.\n\n**Why**\n\nThe label gives Claude Code what it needs to show you that a permission request came from a subagent rather than from the main conversation. That makes it easier to tell which part of the work is asking.\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}