[BUG] 2.1.111 on $200 Max auto select xhigh effort on update, auto effort removed

Status Fixed / completed
Reported on v2.1.210
Maintainer reply None cached
Activity 4 comments · opened Apr 16, 2026 · closed Apr 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?

Updated to v2.1.111 on a Max $200 plan. Previously used model 4.6 with medium/auto effort. On selecting Recommended Opus 4.7, effort selected was xhigh instead of medium. Auto effort removed. Placing effort next to max will waste thousands of tokens

What Should Happen?

Effort selection should mirror prior selection in 2.1.210 or medium as a proper default.

Error Messages/Logs

Steps to Reproduce

  1. update Claude CLI
  2. start claude cli
  3. /model select Opus 4.7 (recommended)
  4. type /effort to see effort at xhigh

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.111

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

WSL (Windows Subsystem for Linux)

Additional Information

_No response_

View original on GitHub ↗

4 Comments

yxi8 · 6 months ago

"More effort control: Opus 4.7 introduces a new xhigh (“extra high”) effort level between high and max, giving users finer control over the tradeoff between reasoning and latency on hard problems. In Claude Code, we’ve raised the default effort level to xhigh for all plans. When testing Opus 4.7 for coding and agentic use cases, we recommend starting with high or xhigh effort."

github-actions[bot] · 6 months ago

Found 3 possible duplicate issues:

  1. https://github.com/anthropics/claude-code/issues/49224
  2. https://github.com/anthropics/claude-code/issues/49076
  3. https://github.com/anthropics/claude-code/issues/30726

This issue will be automatically closed as a duplicate in 3 days.

  • If your issue is a duplicate, please close it and 👍 the existing issue instead
  • To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

mk11232 · 6 months ago
"More effort control: Opus 4.7 introduces a new xhigh (“extra high”) effort level between high and max, giving users finer control over the tradeoff between reasoning and latency on hard problems. In Claude Code, we’ve raised the default effort level to xhigh for all plans. When testing Opus 4.7 for coding and agentic use cases, we recommend starting with high or xhigh effort."

I missed that thank you for the update. For my use case, the first test was amazing. However, this is just going to fuel more decreased value in the plans since people don't realize they're on a higher effort than before is all.

github-actions[bot] · 5 months ago

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.