[BUG]

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 Claude Code HUD displays a usage percentage that is approximately 6x higher than the actual usage shown on the claude.ai usage dashboard.

Observed Behavior:

• HUD shows: ████░░░░░░ 38%
• claude.ai dashboard shows:
• Current session: 6% used (resets in ~2 hours)
• Weekly all models: 9% used
• Sonnet: 0% used

Expected Behavior:
HUD usage percentage should roughly match the session usage shown on claude.ai (6%), not show 38%.

Environment:

• Claude Code version: 2.1.17
• Model: claude-opus-4-5-20251101
• Platform: Windows 10/11
• Plan: MAX

What Should Happen?

Either calibrate the local estimation to better match actual API usage, or fetch real usage data from the API if available.

Error Messages/Logs

Steps to Reproduce

<img width="1438" height="702" alt="Image" src="https://github.com/user-attachments/assets/ea30de79-00b6-4bcd-9d19-08f25fa92514" />
<img width="1426" height="157" alt="Image" src="https://github.com/user-attachments/assets/a9cfb650-b1ba-4886-ae99-6ce1dd3a0a7f" />

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.17

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_