Resuming a subagent that is already running now errors instead of starting a duplicate.
What's wrong with this entry?
Asking to resume a subagent that is already running, or already mid-resume, throws instead of quietly starting a second copy. Completion, failure and kill each now publish a settled event, flagging whether messages were left stranded.
- Failures reading the state a resume needs are classified, so a transient read error surfaces as its own error type rather than a generic failure.
is already running or being resumed
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