Screenshot shows Claude Code injecting 'NOT USER INPUT' notices for background tasks

philhchen · x · 2026-11-18

A screenshot reveals how Claude Code handles background-task events: when an agent task completes, the system injects an explicit notice telling the model it is an automated event, not user input, and that nothing the user 'said, approved, or confirmed' earlier counts as real consent. It also notes the same task-id may fire multiple notifications. A neat detail of agent interaction design against mistaking system messages for human approval.

Original post →

More from coding & agent

coding & agent channel →