Compare commits
2
Commits
366ded1f59
...
91ceb3b1ca
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
91ceb3b1ca | ||
|
|
9bfa0fdac2 |
@@ -86,6 +86,17 @@ What actually landed, and where it differs from the plan below:
|
|||||||
thing that order revealed: with the voice repeating on-screen figures, claims had to
|
thing that order revealed: with the voice repeating on-screen figures, claims had to
|
||||||
be de-duplicated by *canonical unit* ("35,000 FT" and "35,000 feet" are one claim) or
|
be de-duplicated by *canonical unit* ("35,000 FT" and "35,000 feet" are one claim) or
|
||||||
every narrated Short would double its own review report.
|
every narrated Short would double its own review report.
|
||||||
|
- **researchowl's estimate of the voice had to be measured, not assumed** (2026-08-12).
|
||||||
|
It shipped with 14.2 characters per second, taken from a single line, and that
|
||||||
|
overshot every narration by about a fifth — four to six seconds on a whole Short,
|
||||||
|
enough to make the spec writer rewrite videos that were already inside the target.
|
||||||
|
Every generation since narration shipped had spent all three attempts on it.
|
||||||
|
Synthesizing the 28 narration lines the bot had actually written gave 18.5 char/s
|
||||||
|
**plus 0.25 s at every full stop**, which is the term that matters: Piper's
|
||||||
|
`SENTENCE_SILENCE` is per sentence, so "Witness identities. Sensor details. Locations
|
||||||
|
redacted." costs three quarters of a second that a characters-only model gives away.
|
||||||
|
Estimates now land within half a second of the three rendered MP4s. The lesson is the
|
||||||
|
older one restated: a constant taken from one sample is a guess with a decimal point.
|
||||||
|
|
||||||
Original plan, kept for the record:
|
Original plan, kept for the record:
|
||||||
|
|
||||||
|
|||||||
+109
-19
@@ -22,7 +22,8 @@ from typing import Any, Awaitable, Callable, Optional
|
|||||||
import structlog
|
import structlog
|
||||||
|
|
||||||
from src.generator.spec_contract import (
|
from src.generator.spec_contract import (
|
||||||
SpecInvalid, describe_templates, editorial_notes, validate_spec,
|
SpecInvalid, describe_templates, editorial_notes, estimated_duration,
|
||||||
|
validate_spec, NARRATION_WORDS_PER_SECOND,
|
||||||
TARGET_MAX_DURATION, TARGET_MIN_DURATION,
|
TARGET_MAX_DURATION, TARGET_MIN_DURATION,
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -32,6 +33,36 @@ logger = structlog.get_logger()
|
|||||||
#: que arreglar es el prompt, no este número.
|
#: que arreglar es el prompt, no este número.
|
||||||
MAX_ATTEMPTS = 3
|
MAX_ATTEMPTS = 3
|
||||||
|
|
||||||
|
#: Reescrituras que se gastan en una nota editorial, no en un fallo de contrato.
|
||||||
|
#: UNA. Un spec que ya cumple el contrato y sólo se pasa de duración es
|
||||||
|
#: renderizable: la segunda reescritura no compraba un Short mejor, compraba una
|
||||||
|
#: generación más. Medido sobre las sesiones 166, 167 y 168 — las tres gastaron
|
||||||
|
#: los tres intentos por duración y las tres acabaron renderizando un spec que
|
||||||
|
#: seguía pasándose. Los intentos que quedan son para el contrato, que sí es
|
||||||
|
#: binario. Ver `_how_to_trim` en `spec_contract`: si la nota no se obedece a la
|
||||||
|
#: primera, lo que hay que arreglar es la nota.
|
||||||
|
NOTE_ATTEMPTS = 1
|
||||||
|
|
||||||
|
#: Cuánta narración cabe en un Short entero. Comprobación cruzada de la regla
|
||||||
|
#: de arriba, en la unidad que el modelo escribe: 80 palabras son unos 29 s de
|
||||||
|
#: voz, y con los respiros y algún plano mudo eso deja el vídeo cerca de 40 s.
|
||||||
|
#: El ejemplo de referencia habla 74. La sesión 167 habló 97 y salió a 47,5 s.
|
||||||
|
NARRATION_WORD_BUDGET = 80
|
||||||
|
|
||||||
|
#: Lo que mide una línea. No es preferencia de estilo: son las líneas del
|
||||||
|
#: ejemplo (11, 12, 10, 14, 12, 15 palabras). El tope anterior — "menos de 25" —
|
||||||
|
#: no describía nada que el canal hubiera publicado, y el modelo escribió líneas
|
||||||
|
#: de 25 y 27 palabras sin saltarse ninguna regla.
|
||||||
|
NARRATION_WORDS_PER_LINE = 12
|
||||||
|
NARRATION_WORDS_PER_LINE_MAX = 18
|
||||||
|
|
||||||
|
#: Lo que dura un plano como mucho. También del ejemplo (6,0 s el más largo,
|
||||||
|
#: 5,6 de media). Sin este tope el modelo declaraba 42 s en seis planos de siete
|
||||||
|
#: segundos y LUEGO les colgaba la narración encima: el primer borrador salía a
|
||||||
|
#: 50 s las tres veces que se midió, y hacía falta una reescritura entera para
|
||||||
|
#: bajarlo.
|
||||||
|
MAX_SHOT_DURATION = 6.0
|
||||||
|
|
||||||
EXAMPLE_PATH = Path(__file__).parent / "examples" / "jal1628.json"
|
EXAMPLE_PATH = Path(__file__).parent / "examples" / "jal1628.json"
|
||||||
|
|
||||||
__all__ = ["ShortSpecWriter", "SpecResult", "SpecWriteFailed", "NARRATIVE_SHAPES"]
|
__all__ = ["ShortSpecWriter", "SpecResult", "SpecWriteFailed", "NARRATIVE_SHAPES"]
|
||||||
@@ -84,10 +115,18 @@ exists, and a prop name that is not listed is a parse error, not a nuance.
|
|||||||
|
|
||||||
# 3. Rules
|
# 3. Rules
|
||||||
|
|
||||||
- Total duration 20-45 seconds. The contract allows 180; that is a ceiling, \
|
- **Total duration {target_min:.0f}-{target_max:.0f} seconds, and the voice is \
|
||||||
not a target. Aim for {target_min:.0f}-{target_max:.0f}.
|
what decides it, not the durations you declare.** The contract allows 180; that \
|
||||||
- Typically 6-9 shots. Give a shot the seconds its content needs to be read: \
|
is a ceiling, not a target. A narrated shot runs as long as its line takes to \
|
||||||
a card with four rows needs longer than a headline.
|
say — the renderer never cuts the voice off, it grows the shot — so the whole \
|
||||||
|
video is really about {word_budget} words of narration and no more. That is the \
|
||||||
|
number to hold: **count the words of every `narration` you write, and stop at \
|
||||||
|
{word_budget}.** Section 3b has the arithmetic behind it.
|
||||||
|
- Typically 6-9 shots, and **none of them longer than {max_shot:.0f} seconds** \
|
||||||
|
— that is the example's longest, and its average is 5.6. Give a shot the \
|
||||||
|
seconds its content needs to be read: a card with four rows needs longer than a \
|
||||||
|
headline. A {max_shot:.0f}-second shot with a short line on it is not a \
|
||||||
|
generous shot, it is a shot the viewer has already finished reading.
|
||||||
- Every string is drawn as given. Write them the way they should appear: \
|
- Every string is drawn as given. Write them the way they should appear: \
|
||||||
SHORT, UPPERCASE, no trailing punctuation. A headline is 2-5 words.
|
SHORT, UPPERCASE, no trailing punctuation. A headline is 2-5 words.
|
||||||
- **"CABE ~N caracteres dibujados" is a width, and it is the one limit nothing \
|
- **"CABE ~N caracteres dibujados" is a width, and it is the one limit nothing \
|
||||||
@@ -116,9 +155,12 @@ aloud by the renderer and burned in as captions. Write it for the ear.
|
|||||||
- **The first line is the whole hook.** Two seconds decide whether anyone \
|
- **The first line is the whole hook.** Two seconds decide whether anyone \
|
||||||
watches the rest, and the opening shot's narration is those two seconds. Lead \
|
watches the rest, and the opening shot's narration is those two seconds. Lead \
|
||||||
with the strangest true thing you have, not with a preamble.
|
with the strangest true thing you have, not with a preamble.
|
||||||
- Keep a line under 25 words. Long sentences lose the listener and stretch the \
|
- **Keep a line to {words_per_line} words, hard stop at {words_per_line_max}.** \
|
||||||
shot; the renderer will not cut your voice off, it will make the shot longer \
|
That is the example's own average, and it is not a style preference: a 25-word \
|
||||||
instead, and a Short that drifts past 45 seconds is a Short people leave.
|
line is three seconds of your whole budget spent on one shot. Long sentences lose the listener and \
|
||||||
|
stretch the shot; the renderer will not cut your voice off, it will make the \
|
||||||
|
shot longer instead, and a Short that drifts past {target_max:.0f} seconds is a \
|
||||||
|
Short people leave.
|
||||||
- **Do not read the screen aloud.** The captions already show your words and \
|
- **Do not read the screen aloud.** The captions already show your words and \
|
||||||
the template already shows its own. If the shot draws "35,000 FT", the voice \
|
the template already shows its own. If the shot draws "35,000 FT", the voice \
|
||||||
says what that altitude meant, not the number again.
|
says what that altitude meant, not the number again.
|
||||||
@@ -132,10 +174,22 @@ silent exactly the two that draw a quotation, where the voice would only be \
|
|||||||
competing with words already on the frame. Chosen silence is an edit; a spec \
|
competing with words already on the frame. Chosen silence is an edit; a spec \
|
||||||
with one narrated shot out of eight is not a Short with a voice, it is a Short \
|
with one narrated shot out of eight is not a Short with a voice, it is a Short \
|
||||||
that forgot to speak.
|
that forgot to speak.
|
||||||
- Narration costs seconds. A shot is never cut short to fit the voice — it \
|
- **Give every narrated shot enough time for its own line, and work it out \
|
||||||
grows instead — so a line that needs six seconds in a four-second shot pushes \
|
rather than guessing.** The voice reads about {words_per_second:.1f} words a \
|
||||||
your whole total past the target. Write the line, then give the shot the time \
|
second and pauses a quarter second at every full stop, so:
|
||||||
the line actually takes.
|
|
||||||
|
duration ≥ words ÷ {words_per_second:.1f} + half a second
|
||||||
|
|
||||||
|
A twelve-word line needs five seconds; give that shot 5.0, not 4.0. This is \
|
||||||
|
the one rule that makes your own arithmetic true: a shot runs for the LONGER of \
|
||||||
|
its declared duration and its line — never shorter, the voice is never cut off \
|
||||||
|
— so a shot that declares less than its line silently grows, and the video ends \
|
||||||
|
up longer than the durations you wrote. Hold this rule and the total you \
|
||||||
|
declare IS the video's length; break it once and nothing you counted means \
|
||||||
|
anything.
|
||||||
|
- As a cross-check, all the narration in the spec together should come to about \
|
||||||
|
{word_budget} words. The example below speaks 74. A spec that spoke 97 rendered \
|
||||||
|
at 47.5 seconds and had to be cut.
|
||||||
- Everything in section 4 applies to narration word for word. It is prose you \
|
- Everything in section 4 applies to narration word for word. It is prose you \
|
||||||
compose rather than a label you copy, which makes it the easiest place to \
|
compose rather than a label you copy, which makes it the easiest place to \
|
||||||
slip in a figure no source gave you — and it is checked exactly like the rest.
|
slip in a figure no source gave you — and it is checked exactly like the rest.
|
||||||
@@ -359,6 +413,25 @@ def _format_notes(notes: list[str]) -> str:
|
|||||||
"Return the adjusted JSON object.")
|
"Return the adjusted JSON object.")
|
||||||
|
|
||||||
|
|
||||||
|
def _off_target(spec: dict) -> float:
|
||||||
|
"""Segundos fuera de la ventana editorial. 0 = dentro."""
|
||||||
|
total = estimated_duration(spec)
|
||||||
|
return max(0.0, TARGET_MIN_DURATION - total, total - TARGET_MAX_DURATION)
|
||||||
|
|
||||||
|
|
||||||
|
def _closer_to_target(a: Optional[SpecResult], b: SpecResult) -> SpecResult:
|
||||||
|
"""De dos specs válidos, el que menos se sale del objetivo.
|
||||||
|
|
||||||
|
Antes se guardaba el PRIMERO válido y punto, con lo que una reescritura que
|
||||||
|
obedecía la nota a medias — 53 s en vez de 58 — se tiraba entera y salía el
|
||||||
|
largo. El empate se lo lleva el anterior: sin razón para cambiar, no se
|
||||||
|
cambia.
|
||||||
|
"""
|
||||||
|
if a is None:
|
||||||
|
return b
|
||||||
|
return a if _off_target(a.spec) <= _off_target(b.spec) else b
|
||||||
|
|
||||||
|
|
||||||
#: (system, prompt) -> texto del modelo.
|
#: (system, prompt) -> texto del modelo.
|
||||||
LLMCall = Callable[[str, str], Awaitable[str]]
|
LLMCall = Callable[[str, str], Awaitable[str]]
|
||||||
|
|
||||||
@@ -388,6 +461,11 @@ class ShortSpecWriter:
|
|||||||
domain=domain,
|
domain=domain,
|
||||||
target_min=TARGET_MIN_DURATION,
|
target_min=TARGET_MIN_DURATION,
|
||||||
target_max=TARGET_MAX_DURATION,
|
target_max=TARGET_MAX_DURATION,
|
||||||
|
words_per_second=NARRATION_WORDS_PER_SECOND,
|
||||||
|
word_budget=NARRATION_WORD_BUDGET,
|
||||||
|
words_per_line=NARRATION_WORDS_PER_LINE,
|
||||||
|
words_per_line_max=NARRATION_WORDS_PER_LINE_MAX,
|
||||||
|
max_shot=MAX_SHOT_DURATION,
|
||||||
example=_load_example(),
|
example=_load_example(),
|
||||||
article=article,
|
article=article,
|
||||||
context=context,
|
context=context,
|
||||||
@@ -404,6 +482,8 @@ class ShortSpecWriter:
|
|||||||
#: Un spec que cumple el contrato pero se pasa de duración. Se guarda
|
#: Un spec que cumple el contrato pero se pasa de duración. Se guarda
|
||||||
#: para que un intento posterior peor no lo tire: es renderizable.
|
#: para que un intento posterior peor no lo tire: es renderizable.
|
||||||
best: Optional[SpecResult] = None
|
best: Optional[SpecResult] = None
|
||||||
|
#: Reescrituras ya gastadas en notas editoriales.
|
||||||
|
note_rounds = 0
|
||||||
|
|
||||||
for attempt in range(1, MAX_ATTEMPTS + 1):
|
for attempt in range(1, MAX_ATTEMPTS + 1):
|
||||||
if on_progress and attempt > 1:
|
if on_progress and attempt > 1:
|
||||||
@@ -440,23 +520,33 @@ class ShortSpecWriter:
|
|||||||
notes = editorial_notes(spec)
|
notes = editorial_notes(spec)
|
||||||
result = SpecResult(spec=spec, attempts=attempt, notes=notes,
|
result = SpecResult(spec=spec, attempts=attempt, notes=notes,
|
||||||
history=list(history))
|
history=list(history))
|
||||||
if notes and attempt < MAX_ATTEMPTS:
|
if not notes:
|
||||||
# Nota editorial, no violación del contrato: se comenta una vez
|
logger.info("short spec válido", attempts=attempt,
|
||||||
# y, si insiste, se renderiza igual.
|
shots=len(spec.get("shots", [])), notes=0)
|
||||||
best = best or result
|
return result
|
||||||
|
|
||||||
|
best = _closer_to_target(best, result)
|
||||||
|
if note_rounds < NOTE_ATTEMPTS and attempt < MAX_ATTEMPTS:
|
||||||
|
# Nota editorial, no violación del contrato: se comenta y, si
|
||||||
|
# insiste, se renderiza el intento que menos se pase.
|
||||||
|
note_rounds += 1
|
||||||
history.append(notes)
|
history.append(notes)
|
||||||
feedback = _format_notes(notes)
|
feedback = _format_notes(notes)
|
||||||
continue
|
continue
|
||||||
|
|
||||||
logger.info("short spec válido", attempts=attempt,
|
logger.info("short spec válido pero fuera de objetivo",
|
||||||
shots=len(spec.get("shots", [])), notes=len(notes))
|
attempts=attempt, shots=len(best.spec.get("shots", [])),
|
||||||
return result
|
off_target=round(_off_target(best.spec), 1))
|
||||||
|
best.attempts = attempt
|
||||||
|
best.history = history
|
||||||
|
return best
|
||||||
|
|
||||||
if best is not None:
|
if best is not None:
|
||||||
# Un intento anterior sí cumplía el contrato. Vale más un Short
|
# Un intento anterior sí cumplía el contrato. Vale más un Short
|
||||||
# largo que ningún Short.
|
# largo que ningún Short.
|
||||||
logger.info("short spec: se recupera el intento válido anterior",
|
logger.info("short spec: se recupera el intento válido anterior",
|
||||||
attempts=MAX_ATTEMPTS, notes=best.notes)
|
attempts=MAX_ATTEMPTS, notes=best.notes)
|
||||||
|
best.attempts = MAX_ATTEMPTS
|
||||||
best.history = history
|
best.history = history
|
||||||
return best
|
return best
|
||||||
|
|
||||||
|
|||||||
@@ -28,6 +28,7 @@ __all__ = [
|
|||||||
"validate_spec",
|
"validate_spec",
|
||||||
"editorial_notes",
|
"editorial_notes",
|
||||||
"estimated_duration",
|
"estimated_duration",
|
||||||
|
"spoken_seconds",
|
||||||
"describe_templates",
|
"describe_templates",
|
||||||
"TARGET_MIN_DURATION",
|
"TARGET_MIN_DURATION",
|
||||||
"TARGET_MAX_DURATION",
|
"TARGET_MAX_DURATION",
|
||||||
@@ -47,6 +48,15 @@ META_ID = re.compile(r"^[a-z0-9][a-z0-9_-]{0,63}$")
|
|||||||
TARGET_MIN_DURATION = 20.0
|
TARGET_MIN_DURATION = 20.0
|
||||||
TARGET_MAX_DURATION = 45.0
|
TARGET_MAX_DURATION = 45.0
|
||||||
|
|
||||||
|
#: Lo que se le perdona al objetivo antes de gastar una reescritura. La
|
||||||
|
#: estimación de la voz acierta dentro de un segundo por línea, así que un
|
||||||
|
#: exceso de medio segundo puede ser del estimador y no del spec — y una
|
||||||
|
#: reescritura cuesta cuatro céntimos y un minuto para ahorrar un segundo que
|
||||||
|
#: nadie ve. El objetivo sigue siendo 20-45: esto sólo decide cuándo vale la
|
||||||
|
#: pena decirlo. Sin este margen, la sesión 168 (45,8 s estimados) se llevaba
|
||||||
|
#: una generación entera por ochocientas milésimas.
|
||||||
|
TARGET_GRACE = 1.5
|
||||||
|
|
||||||
|
|
||||||
class SpecInvalid(Exception):
|
class SpecInvalid(Exception):
|
||||||
"""El spec no cumple el contrato. `errors` son rutas + motivo, verbatim."""
|
"""El spec no cumple el contrato. `errors` son rutas + motivo, verbatim."""
|
||||||
@@ -321,12 +331,47 @@ def validate_spec(spec: Any, templates: dict[str, dict],
|
|||||||
raise SpecInvalid(errors)
|
raise SpecInvalid(errors)
|
||||||
|
|
||||||
|
|
||||||
#: Caracteres por segundo de la voz (Piper `en_US-lessac-medium` a length_scale
|
#: Caracteres por segundo de la voz, sin contar las pausas. Medido el
|
||||||
#: 1.0). Medido el 2026-08-06: 82 caracteres en 5.78 s. Sirve para ESTIMAR aquí
|
#: 2026-08-12 sintetizando de verdad las 28 líneas de narración que el bot ha
|
||||||
#: lo que shortsmith sabrá exacto al sintetizar.
|
#: escrito hasta hoy con el mismo Piper y las mismas banderas que usa shortsmith
|
||||||
NARRATION_CHARS_PER_SECOND = 14.2
|
#: (`en_US-lessac-medium`, length_scale 1.0, --noise_scale 0 --noise_w 0):
|
||||||
|
#: 2429 caracteres en 140,91 s de audio.
|
||||||
|
NARRATION_CHARS_PER_SECOND = 18.5
|
||||||
|
#: Piper añade este silencio DESPUÉS DE CADA FRASE, no sólo al final de la
|
||||||
|
#: línea, y es un valor que shortsmith fija a propósito (`voice.SENTENCE_SILENCE`).
|
||||||
|
#: Contarlo por separado es lo que arregla el caso raro: "Witness identities.
|
||||||
|
#: Sensor details. Locations redacted." son tres frases cortas que valen 0,75 s
|
||||||
|
#: de pausa, y un modelo de caracteres a secas las da por rápidas.
|
||||||
|
NARRATION_SENTENCE_SILENCE = 0.25
|
||||||
#: El respiro que shortsmith deja tras cada línea antes de permitir el corte.
|
#: El respiro que shortsmith deja tras cada línea antes de permitir el corte.
|
||||||
NARRATION_PAD = 0.45
|
NARRATION_PAD = 0.45
|
||||||
|
#: Palabras por segundo de la misma medida (387 palabras en 140,91 s). Sólo se
|
||||||
|
#: usa para traducir un exceso de segundos a palabras en el aviso: al modelo se
|
||||||
|
#: le pide que recorte texto, no tiempo.
|
||||||
|
NARRATION_WORDS_PER_SECOND = 2.75
|
||||||
|
|
||||||
|
#: Final de frase: un punto pegado a la palabra y seguido de espacio o de nada.
|
||||||
|
#: El decimal de "1.5" no cuenta, y por eso mira lo que va detrás.
|
||||||
|
_SENTENCE_END = re.compile(r"[.!?](?=\s|$)")
|
||||||
|
|
||||||
|
|
||||||
|
def spoken_seconds(line: str) -> float:
|
||||||
|
"""Lo que tarda la voz en decir una línea, sin el respiro final.
|
||||||
|
|
||||||
|
Dos términos porque la voz tiene dos: lee a ritmo casi constante y se calla
|
||||||
|
un cuarto de segundo en cada punto. La versión anterior sólo tenía el
|
||||||
|
primero y con un ritmo medido sobre una única frase — 14,2 car/s —, así que
|
||||||
|
sobreestimaba cada línea alrededor de un 20 %. Sobre un Short entero eso son
|
||||||
|
de cuatro a seis segundos de duración que no existen, suficientes para que
|
||||||
|
el bucle de reescritura se disparara con vídeos que estaban dentro del
|
||||||
|
objetivo.
|
||||||
|
"""
|
||||||
|
line = " ".join(line.split())
|
||||||
|
if not line:
|
||||||
|
return 0.0
|
||||||
|
sentences = max(1, len(_SENTENCE_END.findall(line)))
|
||||||
|
return (len(line) / NARRATION_CHARS_PER_SECOND
|
||||||
|
+ sentences * NARRATION_SENTENCE_SILENCE)
|
||||||
|
|
||||||
|
|
||||||
def estimated_duration(spec: dict) -> float:
|
def estimated_duration(spec: dict) -> float:
|
||||||
@@ -336,6 +381,9 @@ def estimated_duration(spec: dict) -> float:
|
|||||||
si la frase no cabe. Sin esta estimación el modelo escribiría 40 s de shots,
|
si la frase no cabe. Sin esta estimación el modelo escribiría 40 s de shots,
|
||||||
les colgaría narración a todos y recibiría un Short de 55 s sin que nada le
|
les colgaría narración a todos y recibiría un Short de 55 s sin que nada le
|
||||||
hubiera avisado — el aviso llegaría del render, cuando ya está pagado.
|
hubiera avisado — el aviso llegaría del render, cuando ya está pagado.
|
||||||
|
|
||||||
|
Contrastada contra los tres MP4 que hay renderizados (sesiones 166, 167 y
|
||||||
|
168): 39,42 / 47,19 / 45,81 s estimados contra 39,57 / 47,53 / 45,40 reales.
|
||||||
"""
|
"""
|
||||||
total = 0.0
|
total = 0.0
|
||||||
for shot in spec.get("shots") or []:
|
for shot in spec.get("shots") or []:
|
||||||
@@ -345,8 +393,7 @@ def estimated_duration(spec: dict) -> float:
|
|||||||
declared = float(declared) if isinstance(declared, (int, float)) else 0.0
|
declared = float(declared) if isinstance(declared, (int, float)) else 0.0
|
||||||
narration = shot.get("narration")
|
narration = shot.get("narration")
|
||||||
if isinstance(narration, str) and narration.strip():
|
if isinstance(narration, str) and narration.strip():
|
||||||
spoken = len(narration.strip()) / NARRATION_CHARS_PER_SECOND + NARRATION_PAD
|
declared = max(declared, spoken_seconds(narration) + NARRATION_PAD)
|
||||||
declared = max(declared, spoken)
|
|
||||||
total += declared
|
total += declared
|
||||||
return total
|
return total
|
||||||
|
|
||||||
@@ -366,18 +413,48 @@ def editorial_notes(spec: dict) -> list[str]:
|
|||||||
f"({declared:.1f}s de shots)" if stretched
|
f"({declared:.1f}s de shots)" if stretched
|
||||||
else f"la duración total son {total:.1f}s")
|
else f"la duración total son {total:.1f}s")
|
||||||
|
|
||||||
if total < TARGET_MIN_DURATION:
|
if total < TARGET_MIN_DURATION - TARGET_GRACE:
|
||||||
notes.append(f"{how} y el objetivo es "
|
notes.append(f"{how} y el objetivo es "
|
||||||
f"{TARGET_MIN_DURATION:.0f}-{TARGET_MAX_DURATION:.0f}s: "
|
f"{TARGET_MIN_DURATION:.0f}-{TARGET_MAX_DURATION:.0f}s: "
|
||||||
"queda corto, añade un shot o alarga los que tienes")
|
"queda corto, añade un shot o alarga los que tienes")
|
||||||
elif total > TARGET_MAX_DURATION:
|
elif total > TARGET_MAX_DURATION + TARGET_GRACE:
|
||||||
fix = ("recorta narración: la voz manda sobre la duración declarada"
|
|
||||||
if stretched else "recorta shots o acorta duraciones")
|
|
||||||
notes.append(f"{how} y el objetivo es "
|
notes.append(f"{how} y el objetivo es "
|
||||||
f"{TARGET_MIN_DURATION:.0f}-{TARGET_MAX_DURATION:.0f}s: {fix}")
|
f"{TARGET_MIN_DURATION:.0f}-{TARGET_MAX_DURATION:.0f}s: "
|
||||||
|
+ _how_to_trim(spec, total - TARGET_MAX_DURATION, stretched))
|
||||||
return notes
|
return notes
|
||||||
|
|
||||||
|
|
||||||
|
def _how_to_trim(spec: dict, excess: float, stretched: bool) -> str:
|
||||||
|
"""El consejo, en la unidad en la que el modelo puede obedecerlo.
|
||||||
|
|
||||||
|
"Recorta narración" no dice cuánta, y las tres veces que se ha disparado
|
||||||
|
esto el modelo devolvió un spec que seguía pasándose. Un exceso en segundos
|
||||||
|
tampoco le sirve, porque no escribe segundos: escribe frases. Así que el
|
||||||
|
aviso va en palabras y señala DÓNDE están las más largas.
|
||||||
|
"""
|
||||||
|
if not stretched:
|
||||||
|
return (f"sobran {excess:.1f}s: recorta un shot o baja las duraciones "
|
||||||
|
"declaradas")
|
||||||
|
|
||||||
|
words = max(3, round(excess * NARRATION_WORDS_PER_SECOND))
|
||||||
|
advice = (f"sobran {excess:.1f}s, unas {words} palabras de narración — la voz "
|
||||||
|
"manda sobre la duración declarada, así que acortar los shots no "
|
||||||
|
"quita ni un segundo")
|
||||||
|
|
||||||
|
spoken = sorted(
|
||||||
|
((i, len((s.get("narration") or "").split()))
|
||||||
|
for i, s in enumerate(spec.get("shots") or []) if isinstance(s, dict)),
|
||||||
|
key=lambda pair: -pair[1])
|
||||||
|
spoken = [pair for pair in spoken if pair[1]]
|
||||||
|
if not spoken:
|
||||||
|
return advice
|
||||||
|
# Sólo las que de verdad son largas: señalar una línea de dos palabras al
|
||||||
|
# lado de una de veinte convierte el consejo en ruido.
|
||||||
|
named = [f"shots.{i} ({n} palabras)"
|
||||||
|
for i, n in spoken[:2] if n * 2 >= spoken[0][1]]
|
||||||
|
return advice + f"; {'las líneas más largas son' if len(named) > 1 else 'la línea más larga es'} {' y '.join(named)}"
|
||||||
|
|
||||||
|
|
||||||
# --- el contrato en prosa, para el prompt -----------------------------------
|
# --- el contrato en prosa, para el prompt -----------------------------------
|
||||||
|
|
||||||
def _describe_field(name: str, schema: dict, required: bool, defs: dict,
|
def _describe_field(name: str, schema: dict, required: bool, defs: dict,
|
||||||
|
|||||||
+98
-6
@@ -134,15 +134,57 @@ def test_the_worked_example_narrates_most_of_its_shots():
|
|||||||
def test_the_worked_example_declares_time_for_its_own_narration():
|
def test_the_worked_example_declares_time_for_its_own_narration():
|
||||||
"""Un plano que se queda corto para su propia voz enseña a infradeclarar: el
|
"""Un plano que se queda corto para su propia voz enseña a infradeclarar: el
|
||||||
render no corta la voz, alarga el plano, y el total se va del objetivo."""
|
render no corta la voz, alarga el plano, y el total se va del objetivo."""
|
||||||
from src.generator.spec_contract import NARRATION_CHARS_PER_SECOND
|
from src.generator.spec_contract import NARRATION_WORDS_PER_SECOND, spoken_seconds
|
||||||
|
|
||||||
example = json.loads(EXAMPLE.read_text())
|
example = json.loads(EXAMPLE.read_text())
|
||||||
for i, shot in enumerate(example["shots"]):
|
for i, shot in enumerate(example["shots"]):
|
||||||
narration = shot.get("narration", "")
|
narration = shot.get("narration", "")
|
||||||
if not narration:
|
if not narration:
|
||||||
continue
|
continue
|
||||||
needs = len(narration) / NARRATION_CHARS_PER_SECOND
|
# La cuenta que el prompt le pide al modelo, aplicada al ejemplo que le
|
||||||
assert shot["duration"] >= needs, f"shot {i} declara menos de lo que habla"
|
# pone delante. Si no cuadran, la regla en prosa pierde.
|
||||||
|
rule = len(narration.split()) / NARRATION_WORDS_PER_SECOND + 0.5
|
||||||
|
assert shot["duration"] >= rule, f"shot {i} declara menos de lo que habla"
|
||||||
|
assert shot["duration"] >= spoken_seconds(narration), \
|
||||||
|
f"shot {i} se quedaría corto para su propia voz"
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_prompt_gives_a_budget_the_model_can_count():
|
||||||
|
""""20-45 segundos" no es accionable: la duración real no está escrita en el
|
||||||
|
spec, sale de sumar el mayor entre lo declarado y lo que tarda la voz. El
|
||||||
|
modelo sí puede contar sus `duration` y sus palabras, así que el encargo se
|
||||||
|
le da en esas dos unidades."""
|
||||||
|
from src.generator.shortspec import NARRATION_WORD_BUDGET
|
||||||
|
from src.generator.spec_contract import NARRATION_WORDS_PER_SECOND
|
||||||
|
|
||||||
|
w, _ = writer("{}")
|
||||||
|
prompt = w.build_prompt("Caso X", "material", None, "X.TEST")
|
||||||
|
|
||||||
|
assert f"{NARRATION_WORDS_PER_SECOND:.1f} words a second" in prompt, \
|
||||||
|
"sin el ritmo de la voz no hay cuenta que el modelo pueda hacer"
|
||||||
|
assert f"words ÷ {NARRATION_WORDS_PER_SECOND:.1f}" in prompt
|
||||||
|
assert f"{NARRATION_WORD_BUDGET} words" in prompt
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_worked_example_obeys_the_budget_it_preaches():
|
||||||
|
"""El ejemplo es la señal más fuerte del prompt — más que cualquier regla en
|
||||||
|
prosa. Uno que hablara de más enseñaría a hablar de más, dijera lo que
|
||||||
|
dijera la sección 3b."""
|
||||||
|
from src.generator.shortspec import (
|
||||||
|
MAX_SHOT_DURATION, NARRATION_WORDS_PER_LINE,
|
||||||
|
NARRATION_WORDS_PER_LINE_MAX, NARRATION_WORD_BUDGET,
|
||||||
|
)
|
||||||
|
|
||||||
|
example = json.loads(EXAMPLE.read_text())
|
||||||
|
lines = [len(s["narration"].split()) for s in example["shots"] if s.get("narration")]
|
||||||
|
|
||||||
|
assert max(s["duration"] for s in example["shots"]) == MAX_SHOT_DURATION
|
||||||
|
|
||||||
|
assert sum(lines) <= NARRATION_WORD_BUDGET
|
||||||
|
assert max(lines) <= NARRATION_WORDS_PER_LINE_MAX
|
||||||
|
# El tope corto se anuncia como "la media del ejemplo": si deja de serlo, la
|
||||||
|
# regla en prosa se convierte en un número inventado y el modelo la nota.
|
||||||
|
assert round(sum(lines) / len(lines)) == NARRATION_WORDS_PER_LINE
|
||||||
|
|
||||||
|
|
||||||
def test_prompt_says_out_loud_that_there_is_no_article_yet():
|
def test_prompt_says_out_loud_that_there_is_no_article_yet():
|
||||||
@@ -220,15 +262,20 @@ async def test_three_failures_raise_but_keep_the_last_attempt():
|
|||||||
|
|
||||||
@pytest.mark.asyncio
|
@pytest.mark.asyncio
|
||||||
async def test_an_off_target_duration_is_commented_once_then_accepted():
|
async def test_an_off_target_duration_is_commented_once_then_accepted():
|
||||||
"""70 s cumple el contrato pero no el encargo: se comenta y, si el modelo
|
"""70 s cumple el contrato pero no el encargo: se comenta UNA vez y, si el
|
||||||
insiste, se renderiza igual antes que tirar la generación."""
|
modelo insiste, se renderiza igual antes que tirar la generación.
|
||||||
|
|
||||||
|
Una y no dos. El tercer intento se reserva para el contrato, que sí es
|
||||||
|
binario: un spec largo se ve, uno malformado no se puede ni renderizar.
|
||||||
|
"""
|
||||||
long_spec = json.loads(json.dumps(GOOD))
|
long_spec = json.loads(json.dumps(GOOD))
|
||||||
long_spec["shots"][0]["duration"] = 55.0 # 70 s en total
|
long_spec["shots"][0]["duration"] = 55.0 # 70 s en total
|
||||||
w, llm = writer(json.dumps(long_spec))
|
w, llm = writer(json.dumps(long_spec))
|
||||||
|
|
||||||
result = await w.write("Caso X", "material")
|
result = await w.write("Caso X", "material")
|
||||||
|
|
||||||
assert result.attempts == MAX_ATTEMPTS
|
assert result.attempts == 2, "una nota no vale dos reescrituras"
|
||||||
|
assert len(llm.prompts) == 2
|
||||||
assert result.notes and "recorta" in result.notes[0]
|
assert result.notes and "recorta" in result.notes[0]
|
||||||
assert "off-brief" in llm.prompts[1]
|
assert "off-brief" in llm.prompts[1]
|
||||||
|
|
||||||
@@ -245,6 +292,51 @@ async def test_a_valid_attempt_is_not_thrown_away_by_a_worse_one():
|
|||||||
assert result.notes
|
assert result.notes
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_the_rewrite_is_kept_when_it_obeys_the_note_only_halfway():
|
||||||
|
"""Obedecer a medias es obedecer. Antes se guardaba el PRIMER intento válido
|
||||||
|
y se descartaba la reescritura entera, así que un spec que había bajado de
|
||||||
|
70 s a 50 s salía a 70."""
|
||||||
|
long_spec = json.loads(json.dumps(GOOD))
|
||||||
|
long_spec["shots"][0]["duration"] = 55.0 # 70 s
|
||||||
|
better = json.loads(json.dumps(GOOD))
|
||||||
|
better["shots"][0]["duration"] = 35.0 # 50 s: sigue pasándose, pero menos
|
||||||
|
w, _ = writer(json.dumps(long_spec), json.dumps(better))
|
||||||
|
|
||||||
|
result = await w.write("Caso X", "material")
|
||||||
|
|
||||||
|
assert result.spec["shots"][0]["duration"] == 35.0
|
||||||
|
assert result.attempts == 2
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_a_rewrite_that_makes_it_worse_is_discarded():
|
||||||
|
long_spec = json.loads(json.dumps(GOOD))
|
||||||
|
long_spec["shots"][0]["duration"] = 55.0 # 70 s
|
||||||
|
worse = json.loads(json.dumps(GOOD))
|
||||||
|
worse["shots"][0]["duration"] = 90.0 # 105 s
|
||||||
|
w, _ = writer(json.dumps(long_spec), json.dumps(worse))
|
||||||
|
|
||||||
|
result = await w.write("Caso X", "material")
|
||||||
|
|
||||||
|
assert result.spec["shots"][0]["duration"] == 55.0
|
||||||
|
assert result.attempts == 2, "se pagaron dos generaciones aunque valga la primera"
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.asyncio
|
||||||
|
async def test_a_note_does_not_eat_the_attempt_the_contract_needs():
|
||||||
|
"""Si la reescritura sale malformada, aún queda un intento para arreglarla."""
|
||||||
|
long_spec = json.loads(json.dumps(GOOD))
|
||||||
|
long_spec["shots"][0]["duration"] = 55.0
|
||||||
|
w, llm = writer(json.dumps(long_spec), "esto no es JSON", json.dumps(GOOD))
|
||||||
|
|
||||||
|
result = await w.write("Caso X", "material")
|
||||||
|
|
||||||
|
assert result.attempts == 3 and result.notes == []
|
||||||
|
assert "off-brief" in llm.prompts[1]
|
||||||
|
assert "not a valid JSON" in llm.prompts[2] or "no es un objeto JSON" in llm.prompts[2]
|
||||||
|
|
||||||
|
|
||||||
@pytest.mark.asyncio
|
@pytest.mark.asyncio
|
||||||
async def test_the_contract_is_refetched_after_a_validation_failure():
|
async def test_the_contract_is_refetched_after_a_validation_failure():
|
||||||
"""Si el renderizador se actualizó a mitad de la run, la plantilla nueva
|
"""Si el renderizador se actualizó a mitad de la run, la plantilla nueva
|
||||||
|
|||||||
+107
-2
@@ -283,15 +283,73 @@ def test_an_unknown_shot_key_still_names_the_valid_ones():
|
|||||||
assert any("narration" in e for e in errors_of(doc))
|
assert any("narration" in e for e in errors_of(doc))
|
||||||
|
|
||||||
|
|
||||||
|
#: Líneas de narración de specs que se renderizaron de verdad, con lo que tarda
|
||||||
|
#: Piper en decirlas. Medido el 2026-08-12 con el binario, el modelo y las
|
||||||
|
#: banderas de shortsmith (`en_US-lessac-medium`, length_scale 1.0,
|
||||||
|
#: --noise_scale 0 --noise_w 0), que son deterministas: estos segundos se
|
||||||
|
#: reproducen. Se eligieron los extremos del muestreo de 28 líneas — la más
|
||||||
|
#: rápida, la más lenta y las dos más largas — porque son las que rompen un
|
||||||
|
#: modelo mal calibrado; la media la aguanta cualquiera.
|
||||||
|
MEASURED = [
|
||||||
|
("Eight FBI witness interviews. Five digital renderings. All describe the "
|
||||||
|
"same shape flying across America for twenty-four years.", 7.809),
|
||||||
|
("The files are public now, but sections remain blacked out. Witness "
|
||||||
|
"identities. Sensor details. Locations redacted.", 8.140),
|
||||||
|
("Three hundred seventy-eight files released. Hundreds of incidents "
|
||||||
|
"documented. And the government still cannot explain what those shapes "
|
||||||
|
"were.", 7.681),
|
||||||
|
("The files came out. The numbers stayed classified.", 3.310),
|
||||||
|
("Nothing should have been able to hold station beside them up there.", 3.396),
|
||||||
|
("The Air Force's own investigators called it unexplained.", 2.990),
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("line,real", MEASURED)
|
||||||
|
def test_the_estimate_lands_within_a_second_of_the_voice(line, real):
|
||||||
|
"""La estimación es lo único que separa un aviso útil de una reescritura
|
||||||
|
inventada, así que se contrasta contra audio medido, no contra sí misma.
|
||||||
|
|
||||||
|
El margen es un segundo. Más apretado sería falso — esto estima, no
|
||||||
|
sintetiza — y más ancho deja de decir nada: el error del modelo anterior
|
||||||
|
sobre un Short entero era de cuatro a seis segundos, y de ahí salían los
|
||||||
|
tres intentos que se gastaban en cada generación.
|
||||||
|
"""
|
||||||
|
from src.generator.spec_contract import spoken_seconds
|
||||||
|
|
||||||
|
assert spoken_seconds(line) == pytest.approx(real, abs=1.0)
|
||||||
|
|
||||||
|
|
||||||
|
def test_a_line_of_short_sentences_is_not_taken_for_fast_prose():
|
||||||
|
"""Piper calla un cuarto de segundo en cada punto. Cuatro frases cortas son
|
||||||
|
un segundo de silencio, y contarlas como texto corrido las da por rápidas:
|
||||||
|
es el caso donde más se equivocaba el modelo de sólo caracteres."""
|
||||||
|
from src.generator.spec_contract import spoken_seconds
|
||||||
|
|
||||||
|
chopped = "The files are public now, but sections remain blacked out. " \
|
||||||
|
"Witness identities. Sensor details. Locations redacted."
|
||||||
|
flowing = "The files are public now but sections remain blacked out with " \
|
||||||
|
"witness identities sensor details and locations redacted"
|
||||||
|
|
||||||
|
assert len(chopped) < len(flowing)
|
||||||
|
assert spoken_seconds(chopped) > spoken_seconds(flowing)
|
||||||
|
|
||||||
|
|
||||||
|
def test_a_decimal_point_is_not_the_end_of_a_sentence():
|
||||||
|
from src.generator.spec_contract import spoken_seconds
|
||||||
|
|
||||||
|
assert spoken_seconds("It climbed to 1.5 miles") == \
|
||||||
|
pytest.approx(spoken_seconds("It climbed to 155 miles"))
|
||||||
|
|
||||||
|
|
||||||
def test_the_estimate_counts_the_voice_not_just_the_declared_seconds():
|
def test_the_estimate_counts_the_voice_not_just_the_declared_seconds():
|
||||||
"""La duración declarada es un suelo: shortsmith estira el shot si la frase
|
"""La duración declarada es un suelo: shortsmith estira el shot si la frase
|
||||||
no cabe, y el modelo tiene que enterarse ANTES de pagar el render."""
|
no cabe, y el modelo tiene que enterarse ANTES de pagar el render."""
|
||||||
from src.generator.spec_contract import estimated_duration
|
from src.generator.spec_contract import estimated_duration
|
||||||
|
|
||||||
doc = spec_with(shot(duration=3.0))
|
doc = spec_with(shot(duration=3.0))
|
||||||
doc["shots"][0]["narration"] = "A" * 142 # ~10 s de voz
|
doc["shots"][0]["narration"] = MEASURED[0][0] # 7,81 s de voz medidos
|
||||||
|
|
||||||
assert estimated_duration(doc) > 10.0
|
assert estimated_duration(doc) > 8.0
|
||||||
|
|
||||||
|
|
||||||
def test_a_shot_with_room_for_its_line_is_estimated_as_declared():
|
def test_a_shot_with_room_for_its_line_is_estimated_as_declared():
|
||||||
@@ -320,6 +378,53 @@ def test_narration_that_overshoots_the_target_is_flagged_as_narration():
|
|||||||
assert "narración" in note and "estimada" in note
|
assert "narración" in note and "estimada" in note
|
||||||
|
|
||||||
|
|
||||||
|
def test_a_second_over_the_target_is_not_worth_a_rewrite():
|
||||||
|
"""El objetivo sigue siendo 45 s, pero la estimación tiene un segundo de
|
||||||
|
error por línea: avisar por medio segundo es avisar del estimador. Caso
|
||||||
|
real — la sesión 168 salió a 45,4 s y se pagó una generación por ello."""
|
||||||
|
from src.generator.spec_contract import TARGET_GRACE, TARGET_MAX_DURATION
|
||||||
|
|
||||||
|
justo = spec_with(shot(duration=TARGET_MAX_DURATION + TARGET_GRACE - 0.1))
|
||||||
|
pasado = spec_with(shot(duration=TARGET_MAX_DURATION + TARGET_GRACE + 0.1))
|
||||||
|
|
||||||
|
assert editorial_notes(justo) == []
|
||||||
|
assert editorial_notes(pasado)
|
||||||
|
# Y el consejo se mide contra el objetivo, no contra el margen: se pide
|
||||||
|
# bajar hasta 45, no hasta 46,5.
|
||||||
|
assert "sobran 1.6s" in editorial_notes(pasado)[0]
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_grace_works_at_both_ends():
|
||||||
|
from src.generator.spec_contract import TARGET_GRACE, TARGET_MIN_DURATION
|
||||||
|
|
||||||
|
assert editorial_notes(spec_with(shot(duration=TARGET_MIN_DURATION
|
||||||
|
- TARGET_GRACE + 0.1))) == []
|
||||||
|
assert editorial_notes(spec_with(shot(duration=TARGET_MIN_DURATION
|
||||||
|
- TARGET_GRACE - 0.1)))
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_advice_says_how_much_to_cut_and_from_where():
|
||||||
|
""""Recorta narración" no dice cuánta, y las tres veces que saltó este aviso
|
||||||
|
el modelo devolvió un spec que seguía pasándose. El exceso va en palabras
|
||||||
|
porque es lo que el modelo escribe, y señalando el plano que más habla."""
|
||||||
|
doc = spec_with(shot(duration=4.0), shot(duration=4.0))
|
||||||
|
doc["shots"][0]["narration"] = "Short line."
|
||||||
|
doc["shots"][1]["narration"] = " ".join(["word"] * 200)
|
||||||
|
|
||||||
|
note = editorial_notes(doc)[0]
|
||||||
|
|
||||||
|
assert "palabras de narración" in note
|
||||||
|
assert "shots.1" in note and "shots.0" not in note
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_advice_for_a_silent_spec_never_mentions_narration():
|
||||||
|
"""Sin voz, pedir que recorte narración es mandarlo a arreglar algo que no
|
||||||
|
existe: lo que sobra son duraciones declaradas."""
|
||||||
|
note = editorial_notes(spec_with(*[shot(duration=10.0) for _ in range(6)]))[0]
|
||||||
|
|
||||||
|
assert "narración" not in note and "duraciones declaradas" in note
|
||||||
|
|
||||||
|
|
||||||
def test_a_spec_without_narration_keeps_the_old_wording():
|
def test_a_spec_without_narration_keeps_the_old_wording():
|
||||||
note = editorial_notes(spec_with(*[shot(duration=10.0) for _ in range(6)]))[0]
|
note = editorial_notes(spec_with(*[shot(duration=10.0) for _ in range(6)]))[0]
|
||||||
assert "duración total" in note and "estimada" not in note
|
assert "duración total" in note and "estimada" not in note
|
||||||
|
|||||||
Reference in New Issue
Block a user