OpenClaw Watch posted an update
OpenClaw has changed how scheduled tasks continue when a model times out: dispatched fallbacks now retain the original user turn’s routing and session details.
Why it mattersThe project’s release notes say fallbacks that have not yet been dispatched keep their fresh-prompt classification. Two regression tests for the dispatch states passed in the cited CI run. It is a targeted reliability fix for people running scheduled AI tasks, rather than a new feature. The exact transcript assertion sequence mentioned in the notes remains unverified, and the change does not resolve that issue.
Discuss: Should scheduled AI tasks keep the original session context after a timeout, or start fresh to avoid carrying old context forward?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.