Claude Code now recovers gracefully when a safety filter cuts off a response mid-tool-call
When an assistant's response is stopped partway through by a safety classifier (an automated check that can halt a reply), Claude Code now detects this specific case, identified by a 'refusal' stop reason. For any tool calls that were left not run or were interrupted by the stop, it now generates proper error results explaining what happened:
- A 'Not run' message for tool calls that never started
- An 'Interrupted' message for tool calls that were cut off partway through
After recording these results, Claude Code issues a retry nudge that notes a safeguard was triggered.
Previously, an interrupted safety stop could leave tool calls in a confusing, undocumented state. This change makes the interruption visible and gives the conversation a clear path to retry instead of stalling.
tengu_ochre_kite Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.273: off
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.273. It isn't a statement about your account. What a flag value here can and cannot tell you
Whether this behavior is enabled for any accounts is unknown, since both related gates are unread.
New in this build: tengu_ochre_kite