[BUG] [BUG] Message to continue an interrupted process sent as me with out authorization.
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
When a Claude Code session is resumed after a usage limit resets, the continuation prompt ("I hit my usage limit while you were working, but it has reset now. Please continue from where you left off.") appears in the transcript as a normal user message — same right-aligned bubble, same timestamp, same copy/edit/share controls as a message the user actually typed. There is no visual indication that this message was system/platform-generated rather than user-authored.
While the attached image simply shows a message requesting the agent to continue, it was truly not typed or sent by me and is the cause for my concern.
<img width="899" height="537" alt="Image" src="https://github.com/user-attachments/assets/a52b1a0d-3a5d-449b-bd8b-0edc8fcb8bed" />
What Should Happen?
If the session resume is triggered by the platform rather than typed by the user, it should be visually distinguishable from genuine user input.
Error Messages/Logs
Steps to Reproduce
Start a Claude Code session (desktop app) and let it run a task long enough to hit a usage limit.
Wait for the usage limit to reset.
The session resumes on its own with a message that reads as if the user typed "I hit my usage limit... please continue from where you left off."
Observe that this message is styled identically to a real user message — bubble alignment, timestamp, and the copy/edit/share icon row.
Claude Model
None
Is this a regression?
Yes, this worked in a previous version
Last Working Version
_No response_
Claude Code Version
Version 2.2553.1 (c38127)
Platform
Anthropic API
Operating System
Windows
Terminal/Shell
Windows Terminal
Additional Information
_No response_