[BUG] Stop hook feedback with no output creates an infinite loop

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?

even when the hook exits 0 with no stdout/stderr, the runner sends "No stderr output" back as a
conversational turn, which triggers another Stop event.

What Should Happen?

When a Stop hook exits 0 with no stdout/stderr, Claude Code should silently do nothing — no feedback message, no new turn. The stop
should proceed normally

Expected: Hook exits 0 with no output → no feedback message, no new turn, stop completes silently.

Actual: A "No stderr output" feedback message is synthesized and injected as a conversational turn, creating an infinite loop.

Error Messages/Logs

Steps to Reproduce

Reproduction steps:

1. Add a Stop hook to ~/.claude/settings.json:

{
"hooks": {
"Stop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "python3 -c \"import sys; sys.exit(0)\"",
"timeout": 5
}
]
}
]
}
}

1. Start a new Claude Code session
2. Send any message, e.g. say hello
3. After Claude responds, observe the hook feedback appearing:

Stop hook feedback:
[python3 -c "import sys; sys.exit(0)"]: No stderr output

1. This feedback is treated as a new user turn → triggers another response → triggers another Stop → infinite loop. Only way to break

out is Ctrl+C or Escape.

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.92

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Other

Additional Information

_No response_