[BUG] CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS Configuration Ignored

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?

The CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS setting defined in ~/.claude/settings.json or .claude/settings.json is not respected by the Read tool for main agents or sub-agents.

Current Behavior

• Configuration is present but ignored
• Files exceeding the token limit are displaying a successful read with total line count
• Only the first 2KB is returned to the agent in the response
• Remaining content is saved to a separate file instead of respecting the configured limit

Impact

• Configuration is unusable; setting has no effect
• Unexpected file reads and persistence bypass user-configured limits

What Should Happen?

• Read tool respects the configured CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS value
• Content truncation/persistence happens at the configured token boundary
• Both main agents and sub-agents honor the setting

Error Messages/Logs

Steps to Reproduce

Example Configuration

{
  "env": {
    "CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS": "75000"
  }
}

Expected behavior: ~225-300k characters (at 3-4 chars/token ratio)

Claude Model

Not sure / Multiple models

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.71 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Windows Terminal

Additional Information

_No response_