Attachments
Attachments inline into the message at send time. The most common surprises are size caps and file types Loach can’t decode.
“File too large” when dropping a file
The composer refuses the file.
There’s a 20 MB cap per file. Split large logs, or paste the relevant section as text instead.
The PDF came in empty or with garbled text
The model says it can’t see the document, even though you attached a PDF.
Loach extracts text from PDFs, but scanned PDFs (image pages with no text layer) have no text to extract. Run the PDF through an OCR tool first, or paste the relevant pages as plain text.
The DOCX won’t attach
The file picker rejects the document.
Only .docx is supported, not legacy .doc. Open the file in Word or LibreOffice and Save As → Word Document (.docx).
A long document shows a “content truncated” footer
A long PDF or text file was attached but only part of it reached the model.
Per-file cap is 200,000 characters; total inlined content per message is 500,000 characters. Either:
- Trim the document to the parts you actually need, or
- Send several focused messages, each with a different excerpt.
Images don’t seem to be working
You attached a PNG/JPEG but the model can’t describe it.
The model needs vision capability. In the Models tab, the tile shows a “vision” badge when supported. Switch to a vision-capable model (Llava, Llama 3.2 Vision, GPT-4o, etc.) and re-send.