feat(short): narración — el grounding la cubre, el contrato la admite y el prompt la guía

El comprobador va primero, antes que el campo (fase 2 §12): la narración es
prosa que el modelo redacta, no una etiqueta que copia, y es donde se cuela
una cifra sin fuente. De paso, la huella de una cifra pasa a ser número +
unidad canónica: con la voz repitiendo la pantalla, '35,000 FT' y '35,000
feet' son el mismo dato y contarlos dos veces inflaría el informe del que
depende la revisión humana.

editorial_notes estima la duración CON la voz: la declarada es un suelo y sin
esto el modelo escribiría 40 s de shots, les colgaría narración y se enteraría
del Short de 65 s cuando ya está pagado.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

README.md

@@ -99,6 +99,16 @@ for case files, `pulse` for debunks, `static` for document drops. The model
 picks one to match the narrative shape, and the cheapest way to audition them
 is the edit loop — change `audio.preset` in the spec file and re-send it.
 
+**Narration:** a shot may carry a `narration` line. shortsmith speaks it and
+burns the words in as captions, and **the grounding check reads it like
+everything else** — narration is prose the model composes rather than a label it
+copies, which makes it the easiest place for an unsourced figure to appear.
+Timing works the other way round from the rest of the spec: a shot's declared
+`duration` becomes a floor, and the shot grows if the line needs longer, so the
+claims report also carries how much the video stretched. The prompt tells the
+model to lead with the hook, keep lines under 25 words, and never read the
+screen aloud — the captions already show the words.
+
 Full spec of the phase: `docs/shortsmith-phase2-spec.md`.
 
 ## YouTube (`/upload_short`)