{"version":"2.1.293","anchor":"resumed-subagent-run-flag-documented-for-sendmessage-waits","canonical_anchor":"resumed-subagent-run-flag-documented-for-sendmessage-waits","heading":"SDK output describes resumed subagent runs that a tool call waits for","tier":"internal","area":"Agents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293\/e\/resumed-subagent-run-flag-documented-for-sendmessage-waits","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293","markdown":"### SDK output describes resumed subagent runs that a tool call waits for\n\nSDK output now describes a resumed subagent run that the resuming tool call waits on, with its report returned in that call's result\n\n**Unclear.** The name of the new field is not shown, nor whether Claude Code actually sends it yet.\n\n**What**\n\nThe Agent SDK's output format, which programs that drive Claude Code read, has a new description for one kind of run. It covers a subagent (a helper agent Claude starts to handle part of a task) that is resumed by a tool call, where the tool call waits for it to finish. `SendMessage` works this way when background tasks are turned off.\n\nFor such a run:\n\n- the run has ended once the resuming tool call returns or fails\n\n- the subagent's report is placed in that tool call's result\n\n- the run's `task_started` event names the tool call in its `tool_use_id`\n\nThe description is marked as internal.\n\n**Why**\n\nPrograms built on the SDK get a way to recognise these resumed runs and know that the waiting tool call's result holds their report.\n\n- Area: Agents\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}