[BUG] Limit hits message became my compacted context

Resolved 💬 3 comments Opened Aug 18, 2025 by liori Closed Jan 6, 2026

Environment

  • Platform (select one):
  • [X] Anthropic API
  • [ ] AWS Bedrock
  • [ ] Google Vertex AI
  • [ ] Other: <!-- specify -->
  • Claude CLI version: 1.0.72 (Claude Code)
  • Operating System: Debian 12
  • Terminal: mate-terminal

Bug Description

This one's funny. I managed to hit account limits just after /compact message, resulting in:

> This session is being continued from a previous conversation that ran out of context. The conversation is summarized below:
  Claude AI usage limit reached|1755482400.

Steps to Reproduce

  1. Approach account limits
  2. Type /compact

Expected Behavior

Compaction does not happen. Error message about limits is printed out.

Actual Behavior

Compaction is considered successful, with the error message as its full content.

View original on GitHub ↗

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