{"version":"2.1.234","anchor":"stream-schema-explains-multi-block-assistant-messages","canonical_anchor":"stream-schema-explains-multi-block-assistant-messages","heading":"Stream schema explains multi-block assistant messages","tier":"notice","area":"Streaming Output","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234\/e\/stream-schema-explains-multi-block-assistant-messages","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.234","markdown":"### Stream schema explains multi-block assistant messages\n\nStream output docs now explain why one reply arrives as several messages sharing an id.\n\n**What**\n\nThe assistant-message schema now states that one message is emitted per completed content block, that consecutive messages can share the same `message.id`, that `stop_reason` is null and usage is not final on those, and that `parent_tool_use_id` is set inside a subagent.\n\n**Evidence**\n\n`the turn's stop reason and total usage arrive on the result message`\n\n- Area: Streaming Output\n- Names: `parent_tool_use_id`, `stop_reason`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}