Claude keeps subagents in the foreground only when the very next step needs their answer.
What's wrong with this entry?
The guidance for launching a subagent used to say run it in the foreground whenever you need the result before proceeding. It now limits that to cases where the very next action depends on the result and nothing else could usefully happen in the meantime, and names fire-and-forget work and independent investigations as background cases.
Wanting the result "next" is not enough on its own.
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.234
Another forged control tag is escaped in subagent output
Both mention subagent
-
v2.1.234
Spawned processes get
--flag=valuewhen the value looks like a flagBoth mention subagent
-
v2.1.235
New error for delegating to a subagent without naming one
Both mention subagent