[BUG] "PDF too large" error persists and blocks all PDF reading

[jfgordo]

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?

This is a continuation of issue #9789, which was closed as a duplicate but the bug is still occurring as of December 2025.

When Claude Code attempts to open a PDF file that exceeds size or page count thresholds, it displays the error message "⏺ PDF too large. Please double press esc to edit your message and try again."

The issue is that after this error occurs once, Claude Code continues to refuse to read ANY PDF file regardless of how small or large it actually is. Even when asking Claude to help find alternative solutions (e.g., searching for Python tools to parse the PDF), it returns the same "PDF too large" error.

Related closed issues: #9789, #6231, #6197, #8077

What Should Happen?

After displaying the "PDF too large" error for an oversized PDF:

1. Claude Code should be able to read smaller PDFs that are within limits
2. 2. Claude Code should be able to help find alternative solutions (e.g., suggesting Python libraries to parse PDFs) without returning the same error
3. 3. The error state should not persist and affect unrelated requests

Error Messages/Logs

⏺ PDF too large. Please double press esc to edit your message and try again.

This error repeats for any subsequent attempts to read PDFs (regardless of actual file size) and also appears when asking Claude to help find workarounds (e.g., searching for Python tools to parse the PDF instead).

Steps to Reproduce

1. Ask Claude Code to open/read a large PDF file (e.g., several MB in size or many pages)
2. 2. Receive the "PDF too large" error message
3. 3. Try to open a different, smaller PDF file
4. 4. Observe that the same "PDF too large" error appears even for small files
5. 5. Ask Claude to help find Python tools to parse the PDF instead
6. 6. Observe that Claude still returns the "PDF too large" error

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

No response

Claude Code Version

2.0.62 (Claude Code)

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

Using Opus 4.5 with Claude Max subscription.

This bug was originally reported in #9789 and marked as a duplicate of #6231, but the issue persists. Multiple users have confirmed in the comments that the bug is still happening.

[github-actions[bot]]

Found 3 possible duplicate issues:

1. https://github.com/anthropics/claude-code/issues/9789
2. https://github.com/anthropics/claude-code/issues/11527
3. https://github.com/anthropics/claude-code/issues/6231

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

[emkman]

Still happening with v2.0.64 and none of the duplicate issues have been resolved, just closed without a solution.

[paschaldev]

Just experiemced this problem.

File Size: 1.7M Number of pages: 312

[jiaxi98]

When I encounter this issue, I usually use esc to return back to a point where the context has not blow up and ask Claude Code to read the pdf more efficiently. But it would definitely be better if there is an internal mechanism in Claude Code to handle large file input