figure 2

DeepSeek Harness plugin: content-aware PDF reading tools for vision models (pdf_scan / pdf_read_page / pdf_render_region). Detects figures (vector+raster), tables, math, and two-column layout per page, then routes text pages to extraction and figure/table

DeepSeek Harness plugin: typeset LaTeX as font-free SVG/PNG images, draw geometry and function figures from a declarative spec, convert formulas or SVG into embeddable images, and assemble documents with those images inserted