# NousResearch/hermes-agent · PDF files misread as text by read_file tool

## Open now

- 1 issue, 2 PRs open on GitHub.
- #43059: read_file reads PDFs as text (.pdf excluded from BINARY_EXTENSIONS; content sniff samples only first 1000 bytes = ASCII header) → ~100KB dump exceeds context → compression-reset loop
- PR #43064: fix(tools): add .pdf to BINARY_EXTENSIONS to prevent read_file from dumping raw PDF bytes
- PR #43124: fix(tools): treat PDFs as binary in read_file (#43059)

A bug where read_file treats PDF files as plain text rather than binary, causing large raw-byte dumps that exceed context limits. The fix adds .pdf to BINARY_EXTENSIONS to prevent this behavior.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 0 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.67`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #43059: read_file reads PDFs as text (.pdf excluded from BINARY_EXTENSIONS; content sniff samples only first 1000 bytes = ASCII header) → ~100KB dump exceeds context → compression-reset loop

## Prior & competing PRs

- **#43064: fix(tools): add .pdf to BINARY_EXTENSIONS to prevent read_file from dumping raw PDF bytes**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#43124`
  - files: `tests/tools/test_file_operations_edge_cases.py`, `tools/binary_extensions.py`
- **#43124: fix(tools): treat PDFs as binary in read_file (#43059)**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `tests/tools/test_file_operations_edge_cases.py`, `tests/tools/test_file_tools.py`, `tools/binary_extensions.py`, `tools/file_operations.py`

## Fix status

- No merged fix on record.
- Subsystem: `agent`