Claude Code now wraps up tasks gracefully when hitting the 5-hour limit instead of cutting off mid-edit
lydiahallie · x · 2026-09-26
Anthropic shipped one of the most requested Claude Code updates: instead of cutting off mid-edit when users hit the 5-hour usage limit mid-task, Claude Code now tries to find a graceful stopping point.
It uses a small, fixed allowance pulled from the weekly limit to wrap up whatever it can. DevRel lead Lydia Hallie noted the team worked on this for a while, marking a notable improvement to the mid-task interruption experience.
More from coding & agent
- HeyGen guide: turn a week of Slack messages into a video via Claude Cowork + MCP — HeyGen · 2026-09-26
- Claude-generated video explains model-based formal verification and state machines — DavidKPiano · 2026-09-26
- GiviLoop: an open-source workflow where Claude's code review finds one real bug and one false finding gets dismissed — Smart_Ad500 · 2026-09-26
- A four-dimension eval framework for long-horizon agents: outcome, trajectory, experience, governance — sh_reya · 2026-09-26
- Exa launches Agent Ultra, a swarm-of-agents deep research system it claims is SOTA — yoimnotkesku · 2026-09-26
- Databricks launches Unity Gateway CLI to centrally manage models across coding agents — matei_zaharia · 2026-09-26