Photo → Scanned PDF

Phone photos of documents → scanner-look PDF. The pipeline that works, and the failure modes that ship wrong PDFs if skipped.

photos ──► rectify (photo_to_scan.py --raw)
       ──► ORDER BY CONTENT, detect colored paper   ← agent eyes, not filenames
       ──► enhance: noteshrink (white batch with -g │ colored pages separately,
                                after white-balance pre-pass)
       ──► assemble_pdf.py → A4 PDF
       ──► make_contact_sheet.py → READ IT, verify EVERY page   ← mandatory

Division of labor: scripts carry execution; you (the agent) carry the two judgment steps — content-based page ordering, and whole-document verification. Neither can be automated away: filenames lie about order, and per-page spot checks miss wrong-slot bugs.