Claude Pro: 1M context limit breaks active workflows without warning

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?

The recent enforcement of usage credits for 1M context has broken
active work sessions mid-task.

Issues:

• I'm on Claude Pro with minimal usage (13% session, 6% weekly)
• A long conversation hit the 1M context limit mid-work
• /clear and /compact did not resolve the issue
• There was no prior warning before the conversation was cut off
• All accumulated context (hours of work) was lost

This is a recent policy change with no clear communication.
Pro users need either:

1. A warning before hitting the limit so work can be saved
2. A grace period or session continuation for active work
3. Clearer documentation about what Pro actually includes

This is causing real productivity loss for paying users.

What Should Happen?

Claude not runnig

Error Messages/Logs

1M context limit breaks active workflows without warning

Steps to Reproduce

<img width="653" height="132" alt="Image" src="https://github.com/user-attachments/assets/a8360a43-6fde-4456-b508-81a643fffde3" />

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

1.0.110

Claude Code Version

1.0.213

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

VS Code integrated terminal

Additional Information

<img width="427" height="400" alt="Image" src="https://github.com/user-attachments/assets/26118f07-19f0-4727-a92f-950872a6f62e" />

<img width="653" height="132" alt="Image" src="https://github.com/user-attachments/assets/94d223a2-4c3d-4c7f-89bb-3e7bdef1e0c6" />