Training phase: scripts 09+10, --model flag in 03, gold schema patch

Smoke Signal v1: integrated pipeline wizard tab

Stages 9+10: Codex exporter and validation report

Stages 7+8: LLM normalisation and review workbench

test push

Upload 04_region_detector.py

Update smoke_signal/scripts/03_ocr_bakeoff.py

Create 03_ocr_bakeoff.py

Create 02_profile_pdfs.py

Upload 13 files

Update child-focused public-domain OCR candidate list

Upload 2 files

Update src/codex_extractor.py

Update src/codex_extractor.py

Make sidebar Codex Extractor open Codex tab

Fix tab visibility and single-title works autofill

Restore latest extractor with OCR fallback

Fix Codex tab visibility and catalogue autofill

Upload app.py with huggingface_hub

Upload codex_catalogue.xlsx

Update src/codex_extractor.py

Install tesseract for scanned PDF OCR

Add OCR python dependencies

Add OCR fallback for scanned PDFs

Fix Space build dependency conflict

Pin pydantic for Gradio compatibility

Fix Codex Extractor interaction compatibility

Fix Codex Extractor button binding status output

Fix Codex Extractor button binding/status

Deploy Codex Extractor Gradio app

Deploy Codex Extractor Gradio app

Deploy Codex Extractor Gradio app

Deploy Codex Extractor Gradio app

Deploy Codex Extractor Gradio app

Deploy Codex Extractor Gradio app

initial commit