Lacuna/Labs
photo-pre-publish-pass
green
#231 / 601

NAME

photo-pre-publish-pass — Full vision pass before publish.

SYNOPSIS

id photo-pre-publish-pass tier green section §8. Green — cloud assist + web search + vision (46 baseline, 152 post-matrix) trigger event (pre-publish) tools photo-dim-detect, photo-blur-detect, photo-watermark-detect source new

DESCRIPTION

Vision model via Flash reads the photo and answers one yes/no question (is it dim? blurred? watermarked?). Cheap per call; runs before publish.

Full vision pass before publish.

MECHANISM

INPUToperator / ctxTRANSFORMverb callOUTPUTrender / done

not-yet-implemented — no cart file at curator-web/src/scheme/carts/…/photo-pre-publish-pass.sks

EXAMPLES

Example forthcoming — docs/automations/examples.json entry editable in place.

TIER

green
cloud assist / web search / image understanding · sub-cent / call

FITNESS

Ready

Fits any shop today — this one has no sample-size floor.

SEE ALSO

HISTORY

canonical source: curator/docs/AUTOMATIONS-CANONICAL.md · §8-green-cloud-assist-web-search-vision-46-baseline-152-post-matrix
last regenerated: 2026-06-05 20:31 UTC (mechanical — edits land in the MD or sidecars, not here)

KNOWN BUGS

(none recorded — flag in AUTOMATIONS-CANONICAL.md or open an issue against the cart file)