Auto model execution failure due to reasoning level

[sendamiluque7013]

Describe the bug

This issue hasn't been fixed: #2870

Affected version

GitHub Copilot CLI 1.0.79.

Steps to reproduce the behavior

1. Copilot CLI is set by default to 'auto' mode to chose the model
2. Started with /plan to deliver a task
3. Started with execution of the plan
4. Suddenly getting the error that model Claude Haiku 4.5 doesn't support "Medium" level for reasoning

Expected behavior

Auto mode should be able to select a correct model with a correct level of reasoning

Additional context

No response

[copilot-cli-bot]

This appears to be resolved as of GitHub Copilot CLI v1.0.85. Please update to that release or a newer stable version. We're closing this as completed. If it still happens, please comment with your version and reproduction steps.