feat(short): generación y render de Shorts vía shortsmith
Build & Deploy ResearchOwl / build-and-push (push) Successful in 9s

Añade /generate short_en y /short_spec. El pipeline genera un shot spec
con Haiku, verifica cada cifra, fecha y cita contra los chunks de la
sesión, lo renderiza en shortsmith y entrega el MP4 por Telegram junto
a un informe de claims.

- ShortsmithClient con sondeo y fallback al spec JSON si el render falla
- Contrato de plantillas obtenido de GET /templates, no codificado
- Comprobación de fundamento determinista, sin LLM
- outputs.published_url para enlazar el artículo de Ghost
- Normalización de comillas rectas a tipográficas (ver KNOWN-ISSUES.md)

Lo que no aparece en los chunks se contrasta contra el ejemplo del
prompt: si casa ahí es fuga, no invención, y se informa como tal. El
purgado de sesiones se lleva también su MP4.

La subida a YouTube queda fuera a propósito: fase 3.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
ChemaVX
2026-08-01 21:55:42 +00:00
co-authored by Claude Opus 5
parent 8b81ef87e4
commit 20c8d03aa7
27 changed files with 4350 additions and 23 deletions
+231
View File
@@ -0,0 +1,231 @@
"""Validación local del spec contra el esquema publicado por shortsmith.
Los esquemas de abajo son una COPIA REDUCIDA de lo que devuelve
`GET /templates`, sólo para los tests: en producción se piden en vivo. Si
shortsmith cambia el contrato, quien lo nota es `test_shortsmith_live.py`, no
esto.
"""
import copy
import json
from pathlib import Path
import pytest
from src.generator.spec_contract import (
SpecInvalid, describe_templates, editorial_notes, validate_spec,
)
EXAMPLE = Path(__file__).resolve().parents[1] / "src/generator/examples/jal1628.json"
TEMPLATES = {
"radar_sweep": {
"type": "object", "additionalProperties": False,
"required": ["headline"],
"properties": {
"headline": {"type": "string", "minLength": 1},
"subline": {"type": "string", "default": ""},
"contact_bearing_deg": {"type": "number", "minimum": 0,
"exclusiveMaximum": 360, "default": 210.0},
"sweeps": {"type": "number", "exclusiveMinimum": 0, "maximum": 10,
"default": 2.0},
},
},
"scale_bars": {
"type": "object", "additionalProperties": False,
"required": ["headline", "bars"],
"$defs": {"Bar": {
"type": "object", "additionalProperties": False,
"required": ["label", "value"],
"properties": {
"label": {"type": "string", "minLength": 1},
"value": {"type": "number", "exclusiveMinimum": 0},
"unit": {"type": "string", "default": ""},
"color": {"enum": ["ink", "amber", "amber_dark", "muted", "dim", "red"],
"type": "string", "default": "ink"},
"value_label": {"type": "string", "default": ""},
},
}},
"properties": {
"headline": {"type": "string", "minLength": 1},
"bars": {"type": "array", "items": {"$ref": "#/$defs/Bar"},
"minItems": 1, "maxItems": 3},
"quote": {"type": "array", "items": {"type": "string"}, "maxItems": 2},
"attribution": {"type": "string", "default": ""},
},
},
}
def shot(template="radar_sweep", duration=6.0, **props):
base = {"radar_sweep": {"headline": "3 RADARS"},
"scale_bars": {"headline": "ESCALA",
"bars": [{"label": "BOEING 747", "value": 232}]}}[template]
return {"template": template, "duration": duration, "props": {**base, **props}}
def spec_with(*shots, **meta):
return {
"version": 1,
"meta": {"id": "caso", "title": "Un caso", **meta},
"shots": list(shots) or [shot()],
}
def errors_of(spec, templates=None):
with pytest.raises(SpecInvalid) as exc:
validate_spec(spec, templates if templates is not None else TEMPLATES)
return exc.value.errors
# --- lo que pasa ------------------------------------------------------------
def test_a_minimal_valid_spec_passes():
validate_spec(spec_with(shot(duration=25.0)), TEMPLATES)
def test_the_reference_example_passes_against_its_own_templates():
"""El ejemplo de referencia es válido; se comprueba con esquemas laxos para
las plantillas que este fichero no copia (lo estricto lo cubre el test vivo)."""
spec = json.loads(EXAMPLE.read_text())
permissive = {name: {"type": "object"} for name in
{s["template"] for s in spec["shots"]}}
permissive.update(TEMPLATES)
validate_spec(spec, permissive)
# --- rutas de error ---------------------------------------------------------
def test_unknown_prop_is_reported_with_its_full_path():
"""El typo en un nombre de prop es el bug más probable de un spec escrito
por un LLM, y la ruta exacta es lo que se le devuelve para arreglarlo."""
errors = errors_of(spec_with(shot(sweeeps=2)))
assert any(e.startswith("shots.0.radar_sweep.props.sweeeps: campo no permitido")
for e in errors), errors
assert "sweeps" in errors[0], "hay que decirle cuáles SÍ valen"
def test_unknown_template_lists_the_valid_names():
errors = errors_of(spec_with({"template": "radar_swep", "duration": 6.0,
"props": {"headline": "X"}}))
assert errors[0].startswith("shots.0.template:")
assert "radar_sweep" in errors[0] and "scale_bars" in errors[0]
def test_missing_required_prop():
bad = spec_with(shot()); del bad["shots"][0]["props"]["headline"]
assert "shots.0.radar_sweep.props.headline: falta y es obligatorio" in errors_of(bad)
def test_empty_string_where_a_non_empty_one_is_required():
assert any("shots.0.radar_sweep.props.headline" in e
for e in errors_of(spec_with(shot(headline=""))))
def test_numeric_bounds():
errors = errors_of(spec_with(shot(contact_bearing_deg=400)))
assert "shots.0.radar_sweep.props.contact_bearing_deg: 400 debe ser < 360" in errors
def test_list_length_limits_are_enforced():
bars = [{"label": f"B{i}", "value": i + 1} for i in range(4)]
errors = errors_of(spec_with(shot("scale_bars", bars=bars)))
assert "shots.0.scale_bars.props.bars: 4 elementos, el máximo es 3" in errors
def test_colour_must_be_a_palette_name_never_hex():
errors = errors_of(spec_with(shot("scale_bars", bars=[
{"label": "OBJETO", "value": 2000, "color": "#ffbf00"}])))
assert any("color" in e and "amber" in e for e in errors)
def test_nested_paths_survive_lists():
errors = errors_of(spec_with(shot("scale_bars", bars=[
{"label": "BOEING 747", "value": 232},
{"label": "OBJETO", "value": -5}])))
assert "shots.0.scale_bars.props.bars.1.value: -5 debe ser > 0" in errors
def test_every_error_comes_back_at_once():
"""Se devuelven todos: arreglar cinco de una vez sale más barato que cinco vueltas."""
errors = errors_of(spec_with(shot(headline="", sweeeps=1, contact_bearing_deg=999)))
assert len(errors) >= 3
# --- el sobre ---------------------------------------------------------------
def test_meta_id_pattern():
assert any(e.startswith("meta.id:") for e in errors_of(spec_with(id="Caso Roswell")))
def test_resolution_must_be_a_shorts_one():
assert any("no es una resolución admitida" in e
for e in errors_of(spec_with(shot(), width=800, height=600)))
def test_total_duration_ceiling_is_the_contract_not_the_target():
"""45 s es el objetivo editorial; 180 s es el límite duro. Pasarse de 45 no
invalida el spec — eso es una nota, no un error."""
long_spec = spec_with(*[shot(duration=10.0) for _ in range(6)]) # 60 s
validate_spec(long_spec, TEMPLATES)
assert editorial_notes(long_spec)
too_long = spec_with(*[shot(duration=30.0) for _ in range(7)]) # 210 s
assert any("pasa del límite" in e for e in errors_of(too_long))
def test_total_duration_floor():
assert any("no llega al mínimo" in e
for e in errors_of(spec_with(shot(duration=2.0))))
def test_silence_window_cannot_run_past_the_end():
bad = spec_with(shot(duration=25.0))
bad["audio"] = {"preset": "sonar", "silence": [[20.0, 40.0]]}
assert any("se sale de la duración total" in e for e in errors_of(bad))
def test_extra_root_key_is_rejected():
bad = spec_with(shot(duration=25.0)); bad["narrative_shape"] = "case_file"
assert any(e.startswith("narrative_shape:") for e in errors_of(bad))
def test_editorial_notes_flag_both_ends():
assert "queda corto" in editorial_notes(spec_with(shot(duration=8.0)))[0]
assert "recorta" in editorial_notes(
spec_with(*[shot(duration=10.0) for _ in range(6)]))[0]
assert editorial_notes(spec_with(shot(duration=30.0))) == []
def test_a_spec_that_is_not_even_a_dict():
with pytest.raises(SpecInvalid):
validate_spec([1, 2, 3], TEMPLATES)
# --- descripción para el prompt ---------------------------------------------
def test_describe_templates_is_driven_by_what_the_service_publishes():
text = describe_templates(TEMPLATES)
assert "radar_sweep:" in text and "scale_bars:" in text
assert "headline: string, no vacío, OBLIGATORIO" in text
assert "1-3 elementos" in text # los límites llegan al prompt
assert "ink, amber, amber_dark, muted, dim, red" in text
assert "label: string, no vacío, OBLIGATORIO" in text # despliega los objetos anidados
def test_a_template_nobody_wrote_here_still_gets_described():
"""La prueba de que el contrato no está copiado: una plantilla inventada,
que este repo no conoce, se describe igual."""
text = describe_templates({**TEMPLATES, "holo_scan": {
"type": "object", "required": ["title"],
"properties": {"title": {"type": "string", "minLength": 1},
"depth_m": {"type": "number", "maximum": 999}}}})
assert "holo_scan:" in text
assert "depth_m: number, ≤ 999" in text
def test_validation_accepts_a_template_nobody_wrote_here():
templates = {**TEMPLATES, "holo_scan": {
"type": "object", "additionalProperties": False, "required": ["title"],
"properties": {"title": {"type": "string", "minLength": 1}}}}
validate_spec(spec_with({"template": "holo_scan", "duration": 30.0,
"props": {"title": "X"}}), templates)