[BUG] Using the same prompt and model at different times results in higher token consumption during later executions.

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?

Version information:

Identifier: anthropic.claude-code
Version: 2.1.107
Last Updated: 2 hours ago
Size: 241.01 MB

What Should Happen?

Version information:

Identifier: anthropic.claude-code
Version: 2.1.107
Last Updated: 2 hours ago
Size: 241.01 MB

Error Messages/Logs

Steps to Reproduce

Version information:

Identifier: anthropic.claude-code
Version: 2.1.107
Last Updated: 2 hours ago
Size: 241.01 MB

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.107

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_