[BUG] "PDF too large" error incorrectly triggered on plain text (.txt) files in VS Code extension

Resolved 💬 1 comment Opened May 10, 2026 by ross-satchell Closed Jun 9, 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?

The error message "PDF too large (max 100 pages, 20MB). Try reading the file a different way (e.g., extract text with pdftotext)" is being incorrectly triggered when uploading or referencing plain text files. The file in question was a .txt file converted from a PDF using pdftotext, not a PDF itself.

What Should Happen?

It should read the txt file uploaded and extract data

Error Messages/Logs

PDF too large (max 100 pages, 20MB). Try reading the file a different way (e.g., extract text with pdftotext).

Steps to Reproduce

Take a PDF datasheet and extract a section using pdftk:

pdftk input.pdf cat 405-419 output extract.pdf

Convert to text using pdftotext:

pdftotext extract.pdf extract.txt

Upload extract.txt to Claude Code in VS Code and submit a prompt referencing it
Also attempted referencing the file by absolute path in the prompt — same error
Also attempted renaming to adc_burst.txt and re-uploading — same error

Claude Model

Sonnet (default)

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.138

Platform

Anthropic API

Operating System

Ubuntu/Debian Linux

Terminal/Shell

VS Code integrated terminal

Additional Information

_No response_

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗