[FEATURE] Print reasoning process in noninteractive mode

Resolved 💬 3 comments Opened Nov 25, 2025 by ShuangLiu1992 Closed Jan 27, 2026

Preflight Checklist

  • [x] I have searched existing requests and this feature hasn't been requested yet
  • [x] This is a single feature request (not multiple features)

Problem Statement

I need to log and understand and debug why claude code is behaving in certain ways with different prompts, ideally with reasoning process, but currently in noninteractive it's impossible to observe such information

Proposed Solution

have a flag to turn on logging reasoning process with --output-json

Alternative Solutions

_No response_

Priority

Critical - Blocking my work

Feature Category

CLI commands and flags

Use Case Example

_No response_

Additional Context

_No response_

View original on GitHub ↗

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