[MODEL] opus responses are very verbose

Preflight Checklist

• [x] I have searched existing issues for similar behavior reports
• [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Other unexpected behavior

What You Asked Claude to Do

"Default conversational verbosity is high enough that we built a local opt-out (a custom output style). There's no built-in concise style among Proactive/Explanatory/Learning — Explanatory even goes the other direction."
"Code-comment verbosity specifically: the CLI already has a good, precise rule for this ('only write a comment to state a constraint the code can't show'), but on the model/gate path we're on, it's replaced by the vaguer 'match the surrounding comment density' — which has little effect on new or sparsely-commented files."

What Claude Actually Did

in general the response we've been receiving from the opus model have been highly verbose - causing our engineers to tailor requests to respond in a more concise way. ITs fair to say this has been more noticed over the last 2 weeks

Expected Behavior

respond more concisely???

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Yes, every time with the same prompt

Steps to Reproduce

_No response_

Claude Model

Opus

Relevant Conversation

Impact

Low - Minor inconvenience

Claude Code Version

2.1.224 (Claude Code)

Platform

Anthropic API

Additional Context

_No response_