Usage allowance shared across two separate Anthropic accounts in parallel VS Code Claude Code sessions

Resolved 💬 3 comments Opened Apr 28, 2026 by stoneyp96 Closed May 31, 2026

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?

<html>
<body>
<!--StartFragment--><p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(191, 191, 191); font-family: -apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(25, 26, 27); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><strong>Observed behavior:</strong>
Usage on Account A is reflected in Account B's "Account &amp; Usage" panel and vice versa. Three captures taken minutes apart show:</p>
  | Account A (Max) | Account B (Pro)
-- | -- | --
Session (5hr) | 68% | 67% → 68%
Weekly (7 day) | 94% | 94%

<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(191, 191, 191); font-family: -apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(25, 26, 27); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Both accounts show identical weekly percentages (94%) despite Pro and Max having different absolute limits — the only way this stays in lockstep is if one shared counter is feeding both UI panels, or if work executed under one account is being attributed to the other.

Regardess of current stats towards your usage, both accounts share the attributed usage towards limits.</p><!--EndFragment-->
</body>
</html>

What Should Happen?

Expected behavior:
Each account's usage should be tracked independently against its own plan's limits. Activity in window #1 should not affect Account B's allowance at all.

Impact:

Pro plan exhausts at the same rate as the Max plan it's running alongside, even when only the Max account is being used.
Makes running parallel work across separate accounts (e.g. personal + work) impossible without effectively double-billing the smaller plan.
Combined with the prefix re-billing on session start (which I observed at ~10% per fresh session), the usage burns down faster than expected.

Error Messages/Logs

0 error messages

Steps to Reproduce

Repro steps:

Sign into Account A in VS Code window #1 (Claude Code extension).
Sign into Account B in a separate VS Code window #2 (different extension session, different account).
Run any work in window #1 — observe usage tick up.
Open the "Account & Usage" panel in window #2 — usage on Account B has moved by the same percentage.
Reverse the direction — same result.

Claude Model

Other

Is this a regression?

No, this never worked

Last Working Version

_No response_

Claude Code Version

  • Claude Code VS Code extension: 2.1.121 (win32-x64)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Windows Terminal

Additional Information

<img width="438" height="465" alt="Image" src="https://github.com/user-attachments/assets/e3a6011d-fa9d-4fd5-9e45-1b47fdd90434" />

<img width="436" height="466" alt="Image" src="https://github.com/user-attachments/assets/a68e1ec7-eb59-4067-850a-5dde00c23c8d" />

<img width="433" height="465" alt="Image" src="https://github.com/user-attachments/assets/d89d9bbc-6d88-45af-aced-76a17802ae67" />

View original on GitHub ↗

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