Background task results can no longer fake harness messages by closing the reminder wrapper early.
What's wrong with this entry?
Automated background-task events delivered on your turn are now wrapped in a <system-reminder> envelope, and any closing tag inside the payload is escaped to </system-reminder> so content coming back from a task cannot close the reminder early and start speaking as the harness.
- The escape is a case-insensitive global replace over the payload before wrapping.
- The subagent prompt was updated to match: worker results arrive as user-role messages containing
<task-notification>XML, delivered as harness input inside a reminder, and the model is told never to reproduce them in its own output. - The multi-agent example transcript now shows the nesting too.
- Active on this build wherever task notifications are delivered.
Worker results arrive as user-role messages containing \<task-notification>\ XML, delivered as harness input, normally inside a \<system-reminder>\ that opens with, <task-notification>
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.
-
v2.1.235
Several finished background tasks now report as one line
Both mention background task
-
v2.1.236
Background-task notices no longer look like user approval
Both mention background task
-
v2.1.236
Fleet view and the prompt input rebuilt on explicit stores
Both mention background task