ProductsSelected73°

Claude Code now wraps up tasks gracefully at the 5-hour limit

Why we picked it

Half-finished edits that fail to compile were the biggest pain point of running long Claude Code sessions, and the weekly-limit deduction is a trade-off worth knowing before you rely on it. Developers running overnight refactors or background agents should factor the once-a-week Pro cap into how they schedule heavy tasks. Note that web, desktop and Claude Code share one quota pool, so wrapping up on one surface eats into another.

Claude Code will find a graceful stopping point when a task hits the 5-hour rolling usage limit, instead of cutting off mid-edit and leaving a half-finished multi-file change.

Body

The wrap-up consumes a small fixed allowance drawn from the weekly limit.Pro subscribers can use this finish allowance once per week, while Max and Team Premium seats can use it every time the 5-hour limit is hit.

Further continuation requires enabling extra usage, billed at standard API prices.The change benefits users who run long autonomous tasks such as large refactors overnight.

Original · 宝玉

Claude Code 任务做到一半撞上 5 小时限额时,会先找个合适的地方停下,不再改代码改到一半就直接断掉。收尾用的是一小笔固定额度,从你的每周额度里扣。 Claude 的付费订阅有两道限额。一道是滚动计算的 5 小时窗口,从你发出第一条消息开始计时,管短时间内能用多少。另一道是每周总量上限。网页版、桌面端和 Claude Code 共用一个额度池,在哪儿用都算。 以前 5 小时额度一用完,Claude Code 当场就停。如果它正在做一个跨多个文件的改动,停下来时可能 5 个文件只改了 3 个,代码连编译都过不了。几个小时后额度恢复,你得先弄清楚它停在哪、改了哪些,才能接着往下做。 受益最大的是让 Claude Code 长时间自己干活的人,比如开个大重构然后去开会,或者睡前丢给它一个长任务。以前回来可能面对一个改了一半的代码仓库,现在它会尽量把手头能收尾的部分收掉,停在一个方便接着干的位置。 推送初期的规则是:Pro 用户每周能用一次收尾额度,Max 和 Team 高级席位(Team Premium)每次撞上 5 小时限额都能用。收尾之后还想继续,可以开启额外用量(extra usage),超出部分按 API 标准价格另外计费。 ClaudeDevs @ClaudeDevs Claude Code will now try to find a graceful stopping point when you hit your 5-hour limit mid-task, instead of cutting off mid-edit. It gets a small, fixed allowance pulled from your weekly limit to wrap up what it can.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude Code, Anthropic, usage limits, coding assistants.

Source attribution: curated from 宝玉 (@dotey).