Chandler Copeland e7bf5abb9f fix(13): switch to GPT-4o vision — render PDF pages as images for accurate field placement ...

- extractPdfText now renders each page to JPEG via @napi-rs/canvas + pdfjs-dist (108dpi)
- field-placement.ts sends rendered page images to GPT-4o with vision (detail: high)
- AI can now visually identify underlines, signature blocks, date fields, initials boxes
- System prompt focuses on visual cues (blank lines, boxes) not text pattern matching
- Handles multi-field lines: separate fields for signature blank and date blank on same line

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-03-21 17:40:47 -06:00

.planning

docs(13-03): complete AI Auto-place UI wire-up plan — violet button, aiPlacementKey, handleAiAutoPlace

2026-03-21 17:10:01 -06:00

teressa-copeland-homes

fix(13): switch to GPT-4o vision — render PDF pages as images for accurate field placement

2026-03-21 17:40:47 -06:00

Description

No description provided

19 MiB

Languages

TypeScript 97.5%

Shell 1.6%

Dockerfile 0.4%

JavaScript 0.3%

CSS 0.2%