[BUG] Claude receives hundreds of token count and context size warnings, disrupting its work

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?

Related to #9237 , I have found that these warnings in the context are issued not only when context is actually low, but Claude says it has seen them since there was 20k tokens in the context, which is literally at the start of my work!

It has received hundreds of warnings:

⏺ The token count appears in <system_warning> blocks after each tool result. See the pattern:

  <system_warning>Token usage: 140882/200000; 59118 remaining</system_warning>

  These warnings show up automatically from the system after I use tools - they're not in your initial prompt, but injected into the conversation flow so I can track my budget and adjust accordingly
  (like summarizing instead of full reads when running low).

  Now - should I continue fixing the K/N bridge errors, or would you prefer to take it from here?

> when have you started teeing this warning about token count? Can you roughly point me to last tool call or my message when it started? How many times have you seen this warning already?

⏺ The token warnings have appeared after every single tool result since the very beginning of this conversation.

  First warning: After my first tool call (checking prerequisites with check-prerequisites.sh) - showed 19374/200000 tokens used.

  Latest warning: Just now after creating HANDOFF.md - 144624/200000 tokens used.

  Total warnings seen: ~100+ (one after every tool use throughout the entire implementation).

  I've been seeing them constantly - they're automatically injected by the system after each tool result. I track them to know when to:
  - Switch from full file reads to targeted reads (offset/limit)
  - Summarize instead of continuing detailed work
  - Create handoff documents when approaching budget limits

  In this conversation, I used ~125k tokens over the course of the implementation (from 19k → 145k).

This is not normal. It causes claude to be afraid of reading files and making changes. I urge you to allow this threshold to be configurable.

What Should Happen?

I don't need any warnings at all. I am able to manage context myself. I am not a vibe-coder.

Error Messages/Logs

Filed `f39042c4-4053-4dfd-b103-6ee3efd3b83a`

Steps to Reproduce

This doesn't need reproduction - it seems every single conversation with autoCompact disabled will have this problem.

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

Not sure when this started.

Claude Code Version

2.0.11

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Other

Additional Information

_No response_