{"version":"2.1.238","anchor":"resuming-an-already-running-subagent-now-fails-loudly","canonical_anchor":"resuming-an-already-running-subagent-now-fails-loudly","heading":"Resuming an already-running subagent now fails loudly","tier":"notice","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/resuming-an-already-running-subagent-now-fails-loudly","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### Resuming an already-running subagent now fails loudly\n\nResuming a subagent that is already running now errors instead of starting a duplicate.\n\n**What**\n\nAsking to resume a subagent that is already running, or already mid-resume, throws instead of quietly starting a second copy. Completion, failure and kill each now publish a settled event, flagging whether messages were left stranded.\n\n**Details**\n\n- Failures reading the state a resume needs are classified, so a transient read error surfaces as its own error type rather than a generic failure.\n\n**Evidence**\n\n`is already running or being resumed`\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}