[BUG] When filing the issue, include the details you shared here: the consistent ~13% discrepancy occurring in the last 24 hours before weekly reset. That pattern is useful for debugging.

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?

my real usage is 63%. but here it shows 76%. Usage (←/→ or tab to cycle)

Current session
0% used
Resets 7:59pm (Asia/Karachi)

Current week (all models)
██████████████████████████████████████ 76% used
Resets 4:59pm (Asia/Karachi)

Extra usage
███████████████████▋ 39% used
$19.56 / $50.00 spent · Resets Mar 1 (Asia/Karachi). this mistake is repeat every week in last 24hour before expiration.

When filing the issue, include the details you shared here: the consistent ~13% discrepancy occurring in the last 24
hours before weekly reset. That pattern is useful for debugging.

What Should Happen?

my real usage is 63%. but here it shows 76%. Usage (←/→ or tab to cycle)

Current session
0% used
Resets 7:59pm (Asia/Karachi)

Current week (all models)
██████████████████████████████████████ 76% used
Resets 4:59pm (Asia/Karachi)

Extra usage
███████████████████▋ 39% used
$19.56 / $50.00 spent · Resets Mar 1 (Asia/Karachi). this mistake is repeat every week in last 24hour before expiration.

When filing the issue, include the details you shared here: the consistent ~13% discrepancy occurring in the last 24
hours before weekly reset. That pattern is useful for debugging.

Error Messages/Logs

Steps to Reproduce

my real usage is 63%. but here it shows 76%. Usage (←/→ or tab to cycle)

Current session
0% used
Resets 7:59pm (Asia/Karachi)

Current week (all models)
██████████████████████████████████████ 76% used
Resets 4:59pm (Asia/Karachi)

Extra usage
███████████████████▋ 39% used
$19.56 / $50.00 spent · Resets Mar 1 (Asia/Karachi). this mistake is repeat every week in last 24hour before expiration.

When filing the issue, include the details you shared here: the consistent ~13% discrepancy occurring in the last 24
hours before weekly reset. That pattern is useful for debugging.

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

v2.1.37

Platform

Anthropic API

Operating System

Other Linux

Terminal/Shell

WSL (Windows Subsystem for Linux)

Additional Information

_No response_