Approved permission prompts not surfaced to Claude in conversation

Summary

When a user approves a permission prompt in Claude Code, Claude has no visibility into what was approved. Claude only sees tool call success/failure — not which permission was prompted or that an approval occurred.

Expected behavior

When a user approves a permission prompt, Claude should receive some signal — either the prompt text, the tool + arguments that triggered it, or a notification that approval happened. This would allow Claude to:

1. Proactively add the permission to settings so it doesn't prompt again
2. Accurately diagnose permission issues rather than guessing

Current behavior

• User sees a permission prompt and approves it
• Claude sees only the tool result (success or error)
• Claude has no awareness that a prompt occurred or what triggered it
• Claude cannot distinguish "this worked because it was already allowed" from "this worked because user just approved it"

Impact

• Users have to manually describe what prompted them
• Claude guesses at root cause instead of diagnosing accurately
• Approved permissions aren't automatically reflected in settings.json

Environment

• Claude Code CLI (VSCode extension)
• macOS

🤖 Filed via Claude Code