{"version":"2.1.307","anchor":"fork-subagent-directive-tool-result-text-now-depends-on-whic","canonical_anchor":"fork-subagent-directive-tool-result-text-now-depends-on-whic","heading":"Forked subagents see different stand-in results for each sibling tool call","tier":"internal","area":"Subagents","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307\/e\/fork-subagent-directive-tool-result-text-now-depends-on-whic","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307","markdown":"### Forked subagents see different stand-in results for each sibling tool call\n\nWhen a subagent is forked from a message with several tool calls, each call now gets stand-in result text that depends on which call and which tool it is\n\n**What**\n\nA subagent is a helper Claude starts to work on part of a task. A forked subagent starts with a copy of the conversation so far. When the message it is forked from contains several tool calls (requests by Claude to run a tool), Claude Code fills in a stand-in result for each one. That stand-in text now depends on which call is the one doing the forking and which tool each call uses. Before, every call got the same stand-in text.\n\n**Why**\n\nIt can change what a forked subagent is told about the other tool calls in the message it started from.\n\n- Area: Subagents\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}