[BUG] in CLI, tray shows wrong model

Resolved 💬 3 comments Opened Mar 12, 2026 by DDavis-i3Verticals Closed Mar 16, 2026

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?

❯ why then I do alt-p to select the model it says I'm on Haiku, but the tray says
5% until auto-compact · /model opus[1m]

● The tray showing "opus" might indicate fast mode is enabled. According to the system info I have:

Fast mode for Claude Code uses the same Claude Opus 4.6 model with faster output. It does NOT switch to a different model.

So you're still on Haiku—fast mode just adds faster output. Check if fast mode is toggled on (you can toggle with /fast).

If that's not it and there's a genuine mismatch between what alt-p shows vs the tray display, that sounds like a UI bug in Claude Code worth reporting at https://github.com/anthropics/claude-code/issues.

Either way—should I proceed with committing the test fixes, or would you like me to do something else first?

❯ /fast off
⎿ Fast mode OFF

❯ what model do you show I am using?

● According to my system info, you're using Haiku 4.5 (claude-haiku-4-5-20251001).

────────────────────────────────────────────────────────────────────────
❯ 
────────────────────────────────────────────────────────────────────────
? for shortcuts 5% until auto-compact · /model opus[1m]

What Should Happen?

tray display should correctly show what model is in use.

Error Messages/Logs

Steps to Reproduce

switching model with alt-p should update tray value, it does not.

Claude Model

Not sure / Multiple models

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.74 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

PowerShell

Additional Information

_No response_

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗