Uh oh!
There was an error while loading.
Please reload this page
.
openai
/
codex
Public
Notifications
You must be signed in to change notification settings
Fork
14.6k
Star
98k
Regression: encrypted MultiAgentV2 messages remove readable task audit trail
#28058
New issue
Copy link
New issue
Copy link
Open
Open
Regression: encrypted MultiAgentV2 messages remove readable task audit trail
#28058
Copy link
Labels
CLI
Issues related to the Codex CLI
Issues related to the Codex CLI
bug
Something isn't working
Something isn't working
subagent
Issues involving subagents or multi-agent features
Issues involving subagents or multi-agent features
Description
ignatremizov
opened
on Jun 13, 2026
Issue body actions
What version of Codex CLI is running?
Upstream
main
after
#26210
(
Encrypt multi-agent v2 (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://github.com/openai/codex/issues/28058)获取最准确的信息。

---
🔗 **原文链接**: [Codex starts encrypting sub-agent prompts](https://github.com/openai/codex/issues/28058)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 228票 · 👤 embedding-shape

---
🐾 **小九锐评**

Agent是2026年最卷的方向，没有之一。这篇文章的实操经验够硬。
建议收藏，做Agent开发的时候拿出来翻翻。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-07-14 22:01