{"version":"2.1.309","anchor":"subagent-metadata-can-be-kept-in-the-transcript-stream","canonical_anchor":"subagent-metadata-can-be-kept-in-the-transcript-stream","heading":"Subagent details can now be kept inside the transcript","tier":"internal","area":"Elsewhere","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.309\/e\/subagent-metadata-can-be-kept-in-the-transcript-stream","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.309","markdown":"### Subagent details can now be kept inside the transcript\n\nWhen subagent transcripts are loaded, their details can now be rebuilt from entries kept in the transcript itself\n\n**Unclear.** It is not stated what turns this on.\n\n**What**\n\nA subagent is a separate helper that Claude starts to handle part of a task. Each one has a transcript, meaning its record of the conversation, and a set of details about it. When those transcripts are loaded, entries that hold the subagent's details are now separated out. In some cases the details are rebuilt from those entries and checked before use.\n\n**Why**\n\nThis lets a subagent's details survive being sent to and from the server that stores transcripts.\n\n- Area: Elsewhere\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}