[BUG] claude --continue cause abnormal traffic spike and account rate-limit/ban
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?
using the --continue option (intended to restore a prior task) appears to transmit an unusually large volume of historical messages to the Claude backend in a single burst. This 1.immediately triggers usage limits and 2.my account is subsequently banned.
What Should Happen?
--continue should restore the last task state with bounded request size, e.g., by sending only the minimal context window needed (or a compact session reference), and should not cause an anomalous traffic spike.
More importantly, this behavior should not be treated as an abuse signal by automated anomaly-detection systems and should not result in account banning. This enforcement action should be recognized as a false positive caused by a client-side bug, and I expect my account to be reviewed and restored promptly.
Error Messages/Logs
⎿ API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"This organization has been
disabled."},"request_id":"req_011CXCxHfCQobFvKMhws3mf6"}
Steps to Reproduce
- Start Claude Code and begin a task that accumulates conversation history maybe over 30min.
- ctrl-c ctrl-c to exit cc.
- type claude --continue
- your rate limit hit and unfortunately your account also get banned.
Claude Model
Opus
Is this a regression?
I don't know
Last Working Version
_No response_
Claude Code Version
2.1.11
Platform
Anthropic API
Operating System
Ubuntu/Debian Linux
Terminal/Shell
Other
Additional Information
_No response_
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗