User Reports Claude Code Feature Sending Erroneous Messages Across Sessions
A user says a newly added Claude Code feature frequently sends messages to other active sessions, often incorrectly and with little practical value. The feature is reportedly enabled by default, but its disable setting remains unclear.
A user has reported that the latest Claude Code release introduced a feature capable of sending messages to other running sessions. According to the post, the feature often makes incorrect decisions about when to send a message, creating distraction and consuming additional tokens.
The claim is currently supported mainly by the original social-media post and a reposted account. No clear version number, official changelog entry, or reproducible test has been provided. A follow-up post appears to point toward a possible setting, but the available material does not establish the exact control or whether it fully disables the behavior.
Other material included with the report discusses adaptive thinking, default effort levels, usage analysis, and a separate reasoning-history bug. Those reports do not directly verify the cross-session messaging claim, so this should be treated as an unconfirmed user complaint rather than an established product defect.
Source evidence
An update on recent Claude Code quality reportsanthropic.com · supportingThe implementation had a bug. Instead of clearing thinking history once, it cleared it on every turn for the rest of the session. After a session crossed the idle threshold once, each request for the rest of that process told the API to keep only the most recent block of reasoning and discard everything before it. This compounded: if you sent a follow-up message while Claude was in the middle of a tool use, that started a new turn under the broken flag, so even the reasoning from the current turn was dropped. Claude would continue executing, but increasingly without memory of why it had chosen to do what it was doing. This surfaced as the forgetfulness, repetition, and odd tool choices people reported. [...] As part of the investigation, we back-tested Code Review against the offending pull requests using Opus 4.7. When provided the code repositories necessary to gather complete context, Opus 4.7 found the bug, while Opus 4.6 didn't. To prevent this from happening again, we are now lan
“Claude Code更新废了”！热议Issue：思考深度下降67%，已无法胜任复杂的工程任务 – 量子位qbitai.com · supporting第一个变更发生在2月9日，Opus 4.6发布，引入了自适应思考（adaptive thinking）。 以前的Claude Code用的是固定思考预算，adaptive thinking模式下，模型会自主决定推理的深度和时长。 Boris说，这种方式总体上比固定思考预算效果更好。如果你还是喜欢老方式，也可以通过环境变量CLAUDE\_CODE\_DISABLE\_ADAPTIVE\_THINKING关闭这个功能。 第二个变更发生在3月3日，Opus 4.6默认启用Medium effort模式。 团队发现，effort=85是“intelligence-latency/cost曲线”上的一个甜蜜点 。在这个设置下，模型能在保持高智能表现的同时，显著提升token效率、降低响应延迟。 针对此改动，团队加了弹窗提示，让用户知情并有机会选择关闭。 有些用户希望模型能进行更深层的思考，可以通过/effort指令或在settings.json中手动将值设为high。 不过呢，即便Boris表示已经提示大伙儿了，还是有很多人刚刚才发现这个问题。 > 在输出质量断崖式下跌之前，我完全不知道默认effort已经被改成了Medium。为了纠正这些问题，我大概花了一整天的工作时间。现在我会确保把effort设为最高，从那以后就再也没出现过糟糕的对话了。能否给我一个“永远拼尽全力”的模式？ 以及很多网友并不买账： > 问题远不止是默认思考等级被改成了中等这么简单，我同意其他人说的，哪怕把effort调到最高，模型“急于完成任务”的摆烂行为也明显变多了。 参考链接： 版权所有，未经授权不得以任何形式转载及使用，违者必究。 Claude Code [西风](#) [...] < img id="wx\_img" src=" width="400" height="400"> # “Claude Code更新废了”！热议Issue：思考深度下降67%，已无法胜任复杂的工程任务 西风 2026-04-07 14:13:01 来源：量子位 > 西风 发自 凹非寺 > > 量子位 | 公众号 QbitAI 在官方仓库贴脸开大，热议Issue指出：Claude Code已经更新“废了”。 关键在于，能力退化的时间线可追溯到2月份，和新功能
Claude Code 更新了 /usage 的功能 會顯示當前 session 更詳細的資訊 把 cost 花費的部分也一併顯示 下面還會分析你的 token 使用的模式 - sub-agent 花很兇，建議多用便宜的模型去執行 - 上下文超過 150k 的對話佔比很高，記得常常開新對話 如果覺得自己的 token 燒很快 可以用這功能觀察一下自己的使用情境囉threads.com · supporting# Thread 16.7K views darrell_tw_'s profile picture darrell\_tw\_ Claude Code 更新了 /usage 的功能 會顯示當前 session 更詳細的資訊 把 cost 花費的部分也一併顯示 下面還會分析你的 token 使用的模式 - sub-agent 花很兇，建議多用便宜的模型去執行 - 上下文超過 150k 的對話佔比很高，記得常常開新對話 如果覺得自己的 token 燒很快 可以用這功能觀察一下自己的使用情境囉 Translate 216 6 19 Log in or sign up for ThreadsSee what people are talking about and join the conversation. Log in with username instead
宝玉on X: "Claude Code 最新版本上线了一个特别讨厌的功能x.com · supportingClaude Code 最新版本上线了一个特别讨厌的功能，频繁的给其他正在运行的session 发消息！还老是搞错，除了浪费token 并没有太大价值…… 默认打开我都
宝玉on X: "应该是这个选项" / Xx.com · supportingClaude Code 最新版本上线了一个特别讨厌的功能，频繁的给其他正在运行的session 发消息！还老是搞错，除了浪费token 并没有太大价值…… 默认打开我都没
Claude Code 新会话消息功能浪费令牌 - XNewsxnews.xgrowing.ai · supportingClaude Code 最新版本会频繁向其他正在运行的会话发送消息，且经常错误发送，消耗令牌却价值甚微。该功能默认启用，作者尚未找到关闭它的位置。