Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SessionsArea: what it touches
Internal ChangesKind: in v2.1.293,
Internal ChangesSection of the release
What
When Claude Code runs as a remote session, it now looks back through the conversation at each prompt you queued while it was still working. It sorts each one by whether the model replied to it: stopped, open, unread, finished or left. The result goes into its usage reporting. A log entry about permission requests left without an owner also carries more detail.
Why
This is reporting groundwork for remote sessions. It does not change what you see or how prompts are handled.
