Files
cayce-ops/tests/test_spanish_negations.py
cayce f5b026070b
ci / lint-test-leaks (pull_request) Canceled after 0s
audit-4: classifier understands Spanish negations (veto unchanged)
Merchants write in Spanish; negations like nunca, lamentablemente or
no podemos must veto approval exactly like their English counterparts.
Previously an all-Spanish rejection mail could fall through to OTHER,
and a mixed mail with the approval word in English approved despite a
Spanish negation.

- negation list adds: nunca, jamas, tampoco, ningun/ninguna, nadie,
  nada, no podemos, no es posible, no aceptamos, rechaz*, descartad*,
  lamentablemente, no ha sido aprobad*, no procede
- new Spanish REJECTION rule (rechaz*, solicitud denegada, no cumple
  los requisitos) and Spanish APPROVAL rule (aprob*, aceptad*,
  bienvenid*, encantados de trabajar)
- veto rule unchanged: any negation anywhere -> needs_review
- tests: 15 new (12 veto cases incl. 2 mixed-language, pure-Spanish
  approval still approves, Spanish rejection classifies rejection)

Gate: ruff 0 · 96 unit + 1 PG integration · gitleaks clean.
2026-10-28 19:59:44 +00:00

81 lines
2.8 KiB
Python

"""Spanish negation tests (round-3 point 4): merchants write in Spanish;
negations like 'nunca', 'lamentablemente' or 'no podemos' must veto
`approval` exactly like their English counterparts. Veto rule unchanged:
when in doubt -> needs_review."""
from __future__ import annotations
import pytest
from cayceops.components.maild import classify as clf
from cayceops.models import MailClassification
APPROVAL_ONLY = MailClassification.APPROVAL
def _never_approval(cfg_factory, text: str) -> None:
kind, _ = clf.classify(text, cfg_factory())
assert kind is not APPROVAL_ONLY, f"{text!r} classified as APPROVAL"
def test_english_baseline_still_works(cfg):
config = cfg()
kind, _ = clf.classify("Your application was approved, welcome to the program", config)
assert kind is APPROVAL_ONLY
@pytest.mark.parametrize(
"text",
[
# 1. rejection stem
"Lamentamos informarle que su solicitud fue rechazada",
# 2. nunca
"Nunca aceptamos negocios de criptomonedas",
# 3. jamás
"Jamás hemos trabajado con affiliates externos",
# 4. tampoco
"No podemos aceptar su sitio, tampoco podemos ofrecerle otro acuerdo",
# 5. ningún/ninguna
"En este momento no tenemos ningún hueco para nuevos partners",
# 6. no podemos (multi-word)
"Su propuesta es interesante pero no podemos proceder",
# 7. no es posible (multi-word)
"Gracias por escribir, pero no es posible colaborar este trimestre",
# 8. lamentablemente
"Lamentablemente su aplicación no ha sido aprobada",
# 9. no aceptamos
"Por política interna no aceptamos sitios de viajes",
# 10. mixed spanish/english: negation in spanish, approval word in english
"Thanks for reaching out! Lamentablemente we cannot approve your site",
# 11. mixed: approval in spanish, negation in english
"Apreciamos su interés, but we are not accepting new partners",
# 12. nadie / nada
"Aquí nadie decidiría eso, así que no hay nada que aprobar",
],
)
def test_spanish_and_mixed_negations_veto_approval(cfg, text):
_never_approval(cfg, text)
def test_spanish_pure_approval_still_approves(cfg):
"""A clean Spanish approval WITHOUT any negation must still classify
approval — the veto must not over-fire."""
config = cfg()
kind, confidence = clf.classify(
"Su solicitud fue aprobada. Bienvenido al programa, estamos encantados "
"de trabajar con ustedes.",
config,
)
assert kind is APPROVAL_ONLY
assert confidence >= 0.5
def test_spanish_rejection_classifies_rejection(cfg):
config = cfg()
kind, conf = clf.classify(
"Lamentamos informarle que su solicitud fue rechazada por el comité",
config,
)
assert kind is MailClassification.REJECTION
assert conf >= 0.9