[BUG] Abnormal Usage Consumption on Claude Code Session Resume — Possible Bug

[kokemizawa]

Preflight Checklist

• I have searched existing issues and this hasn't been reported yet
• This is a single bug report (please file separate reports for different bugs)
• I am using the latest version of Claude Code

What's Wrong?

Hi Anthropic Support,

I'm reporting what appears to be a bug related to Claude Code session resumption that caused abnormal usage limit consumption.

Account: Max plan ($100/month)
Date of incident: March 23–24, 2026
Platform: Claude Code via Dispatch (macOS)

Issue:
When resuming a large Claude Code session (project: claude-business, containing multiple CLAUDE.md files and Notion cache layer implementation in progress), my usage limit reached 80% with NO user input — simply by launching the session. Within 45 minutes of minimal interaction, usage hit 100%.

Evidence from ccusage:
I ran npx ccusage@latest session --since 20260323 --breakdown and found the following:

• Session: claude-bu... (claude-business project)
• Model: opus-4-6
• Input tokens: 27,169
• Output tokens: 652,069
• Estimated cost: $342.74
• This single session consumed 97% of all token usage across all sessions

The 652,069 output tokens were generated without corresponding user prompts. I did not instruct Claude to produce this volume of output. It appears the session resume process triggered excessive, unintended token generation.

Relevant update:
I noticed that a Claude Code update released on the same day includes the fix: "Improved memory usage and startup time when resuming large sessions." This strongly suggests that the behavior I experienced was a known issue that has since been patched.

Request:
Could you please investigate whether this was indeed a bug in the session resume logic prior to the fix? If confirmed, I would appreciate a restoration of the usage credits consumed by this unintended behavior.

I have screenshots of the ccusage breakdown report available if needed.

Thank you for your time.

Best regards,
Yuki Kokemizawa
Seiyokoke-en (西予苔園)

What Should Happen?

Session resume should not generate output tokens without user input. Expected behavior: launching a session consumes only the tokens needed to load context (CLAUDE.md, project files), not 652k output tokens.

Error Messages/Logs

ccusage output (session --since 20260323 --breakdown):
Session: claude-bu... (claude-business)
Model: opus-4-6
Input: 27,169 tokens
Output: 652,069 tokens
Cost: $342.74
All other sessions combined: $9.94

Steps to Reproduce

1. Have a large Claude Code project with multiple CLAUDE.md files and active MCP connections
2. Run a session with Opus model, perform substantial work (Notion cache layer implementation)
3. End session
4. Resume/relaunch the same session
5. Usage limit immediately jumps to 80%+ with no user input

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

2.1.81

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

Same-day Claude Code update includes fix: "Improved memory usage and startup time when resuming large sessions" - this strongly suggests the behavior was a known bug.

Attaching ccusage breakdown screenshots.

I would appreciate restoration of usage credits consumed by this unintended behavior.

[github-actions]

Found 2 possible duplicate issues:

1. [BUG] Chrome MCP screenshots accumulate in context, causing extreme token drain on session resume (17% of Max plan for 5 trivial turns) #27869
2. [BUG] /resume crashes with "_.reduce is not a function" on large sessions (~2.7 MB, 1015 entries) #36539

This issue will be automatically closed as a duplicate in 3 days.

• If your issue is a duplicate, please close it and 👍 the existing issue instead
• To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

[kokemizawa]

This is related but not a direct duplicate. My case involves Notion MCP cache layer + multiple CLAUDE.md files (not Chrome MCP screenshots). The root cause may be the same — accumulated MCP context causing token drain on session resume — but the reproduction path is different. Keeping this open as an additional data point for the engineering team.

[gex581990]

I've been dealing with the same thing for 3 days on multiple accounts on multiple platforms. Claude code has been useless. Just has been in a failure loop racking up usage. My one account used its weekly amount just from one message from me, the rest was Claude code failing over and over again, timing out, and trying again. I haven't gotten a legit reply. It's seriously crazy we are paying for their failed connections like it's some kind of usage on the user end we have control of. Why do we get charged for their failure?

[MertHaddad]

I have been experiencing the same issue as well!

[TheMysteryPanda]

Same here. Claude is pretty much useless at the moment. I'm currently at a 25€ plan only and it uses my "current session usage" within 187 tokens while it was "thinking" for 20 minutes straight...

[gex581990]

Now I'm getting session limit hit restrictions at 60 percent session limit and 30 percent weekly limit. Claude is so busted right now it's insane

[erikc96]

Anthropic's silence on this is pretty damning

[Astro-Han]

@kokemizawa yeah, the resume spike is brutal. The whole context gets re-sent when you load the session, so if you've got MCP caches and multiple CLAUDE.md files piled up, that's a massive token hit before you even type anything.

@gex581990 the failure loop makes it worse. Every retry re-sends the full context again, so a few failed turns can eat more quota than an hour of actual work. Paying for retries you didn't ask for is... not great.

I built a small statusline that tracks burn rate live, mostly because I got tired of guessing: https://github.com/Astro-Han/claude-lens

With the resume issue you can literally see the usage jump the moment the session loads. At least lets you decide whether to kill it and start fresh before it eats more.

[sophiaashi]

Adding another data point — seeing the same abnormal consumption after session resume. Usage jumps even when the resumed session is doing lightweight work.

What helped my workflow: routing the routine stuff (file ops, grep, test reruns) through cheaper models automatically so my Claude quota only gets used for actual reasoning. Brought my effective daily consumption down enough that I stop hitting walls.

Not a fix for the underlying bug, but keeps you productive: https://dev.to/sophiaashi/claude-code-rate-limit-on-max-plan-the-workaround-developers-are-actually-using-in-2026-16g2

[alighierikz]

Can confirm. DISPATCH IS BUGGED. Bloats context and burns tokens.

Today i had claude code sessions spawn by opening the tab, it re-read message from 2 days ago. Probebly lag due to a giant 3 days context window. Burned 20% session limit by opening the dispatch tab.

The root of the problem is by design. The dispatch session growing over time.

"Instead of starting a new session for each task, you have a single persistent thread with Claude. This thread doesn't reset—Claude retains context from previous tasks, so you can pick up where you left off."

As far i know. You cannot reset, clear, delete or create a new dispatch session. Its a cowork session in the cloud, the only way to delete it is contact privacy@anthropic.com?

Here my top 5:

Modell	Input	Output	Cache Create	Cache Read	Total	Cost
opus-4-6	9,239	315,742	5,288,554	383,860,527	389,474,062	$279.37
opus-4-6	997	154,285	861,267	158,210,081	159,226,630	$99.59
opus-4-6	889	66,502	973,940	128,765,225	129,806,556	$78.77
opus-4-6, haiku-4-5-20251001	47,276	52,590	1,194,160	8,928,380	10,222,406	$5.89
sonnet-4-6	126	32,227	136,449	10,683,804	10,852,606	$4.20

How did i input 9k or 49k tokens? Im way to lazy for that, my input is like "yes, fix that", "docs that", "change this".
Must be a session reload that gets interpreted as user input.

[jwon0101]

Same here. Is it only related to the Max Plan?