Files
breakpilot-compliance/backend-compliance/tests/test_impressum_v3.py
T
Benjamin Admin bd4882e143
CI / detect-changes (push) Successful in 8s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / secret-scan (push) Has been skipped
CI / dep-audit (push) Has been skipped
CI / build-sha-integrity (push) Failing after 4s
CI / validate-canonical-controls (push) Successful in 11s
CI / loc-budget (push) Successful in 14s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Has been skipped
CI / test-go (push) Has been skipped
CI / iace-gt-coverage (push) Has been skipped
CI / test-python-backend (push) Successful in 30s
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped
CI / sbom-scan (push) Has been skipped
feat(agents): Sprint 1.12 Phase 2 — Cookie-Policy v3 + ImpressumAgent v3 finetune
ImpressumAgent v3 (Refactor):
  - v3_engine: laedt direkt alle 75 doc_check_controls['impressum'] ohne
    Sidecar-Filter (Sidecar war zu streng, lieferte nur 3 von 75 MCs).
  - Layer 0 Boost prueft pass+fail_criteria gegen meine 12 Patterns mit
    erweiterten Initial-Seeds (User-Vorgabe 2026-06-09:
    manuelle Initial-Seeds OK, Auto-Learning erweitert zur Laufzeit).
  - ETO-Smoke: 75 DB-MCs · 7 Pattern-Boosts · 24 Boost-Overrides
    (versus 3 DB-MCs vorher).

CookiePolicyAgent v3 (Refactor):
  - cookie_policy/v3_engine.py + cookie_policy/regex_boost.py
  - Laedt direkt alle 381 Cookie-MCs aus doc_check_controls
  - Layer 0 mit 12 eigenen Patterns als Initial-Seed
  - KB-Layer (CMP-Vendor-Cross-Check) bleibt erhalten
  - agent_version='3.0'

Tests: 27/27 gruen (12 v3-impressum, 6 cookie-policy, 9 cross-placement).
Alte v2-cookie-tests umgeschrieben auf v3-Pipeline-Mock.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-09 09:23:12 +02:00

190 lines
6.1 KiB
Python

"""Tests für Impressum-Agent v3 (Sprint 1.12).
Mockt rag_document_checker damit Tests offline laufen + prüft die
Layer-0-Boost-Logik isoliert.
"""
from __future__ import annotations
import asyncio
import pytest
from compliance.services.specialist_agents import (
AgentInput,
ImpressumAgent,
Severity,
)
from compliance.services.specialist_agents.impressum.regex_boost import (
BOOST_KEYWORDS,
boost_matches_db_mc,
compute_regex_boosts,
)
TESLA_TEXT = (
"Tesla Germany GmbH\nLudwig-Prandtl-Strasse 25-29\n12526 Berlin\n"
"E-Mail: info@tesla.com\n"
"Telefon: +49 89 1250 16 800\n"
"Management: Elon Musk\n"
"Handelsregister: HRB 218904 B Charlottenburg\n"
"USt-IdNr: DE123456789\n"
)
def _run(coro):
return asyncio.get_event_loop().run_until_complete(coro)
def test_compute_regex_boosts_detects_basic_fields():
hits = compute_regex_boosts(TESLA_TEXT, business_scope=set())
# Tesla hat klassische Pflichtangaben
assert "kontakt_email" in hits
assert "kontakt_telefon" in hits
assert "handelsregister" in hits
assert "ust_id" in hits
assert "vertretungsberechtigte" in hits # "Management"
# KFZ-Auto-Detect → aufsichtsbehoerde wäre relevant aber kein
# Pattern getroffen (KBA nicht genannt)
def test_compute_regex_boosts_short_text_empty():
assert compute_regex_boosts("x", business_scope=set()) == set()
def test_boost_matches_db_mc_finds_telefon():
boosts = {"kontakt_telefon"}
pass_crit = [
"Telefonnummer angeben",
"Erreichbar per Telefon und E-Mail",
]
matched = boost_matches_db_mc(boosts, pass_crit)
assert matched == "kontakt_telefon"
def test_boost_matches_db_mc_returns_none_when_unrelated():
boosts = {"kontakt_telefon"}
pass_crit = [
"Cookie-Banner muss zentriert sein",
]
assert boost_matches_db_mc(boosts, pass_crit) is None
def test_boost_matches_db_mc_uses_fail_criteria():
"""Wörter aus fail_criteria sollen die Zuordnung mit unterstützen."""
boosts = {"name_anbieter"}
pass_crit = ["Sichtbar"]
fail_crit = ["Keine Postadresse angegeben", "Adresse fehlt"]
matched = boost_matches_db_mc(boosts, pass_crit, fail_crit)
assert matched == "name_anbieter"
def test_boost_matches_db_mc_eto_address_case():
"""Konkreter ETO-Fall: AUTH-1954-A07 'Postadresse + Geschäftssitz'."""
boosts = {"name_anbieter"}
pass_crit = [
"Vollständige Postadresse (Straße, Hausnummer, PLZ, Ort, Land)",
"Oder: Eindeutige Angabe des Geschäftssitzes",
"Adresse ist aktuell und korrekt",
]
matched = boost_matches_db_mc(boosts, pass_crit)
assert matched == "name_anbieter"
def test_boost_keywords_cover_all_field_ids():
"""Jedes mcs.py field_id muss in BOOST_KEYWORDS ein Eintrag haben."""
from compliance.services.specialist_agents.impressum.mcs import MCS
for mc in MCS:
assert mc.field_id in BOOST_KEYWORDS, (
f"BOOST_KEYWORDS missing for {mc.field_id}"
)
@pytest.fixture
def mock_v3(monkeypatch):
"""Mockt run_v3_pipeline mit deterministischen Fake-Results."""
async def _fake_pipeline(text, scope, db_url=""):
results = [
{"control_id": "AUTH-1954-A04",
"passed": True,
"label": "Anbieterkennzeichnung dokumentiert",
"severity": "HIGH",
"regulation": "TMG",
"article": "§ 5",
"hint": "",
"matched_text": "Tesla Germany GmbH",
"source": "keyword_match"},
{"control_id": "DATA-2786-A04",
"passed": False,
"label": "Freiwilligkeit der TDDDG-Einwilligungen",
"severity": "MEDIUM",
"regulation": "TDDDG",
"article": "§ 25",
"hint": "Bitte Freiwilligkeit dokumentieren",
"matched_text": "",
"source": ""},
]
telemetry = {
"layer_0_field_hits": 5,
"layer_0_field_ids": ["kontakt_email", "kontakt_telefon",
"handelsregister", "ust_id",
"vertretungsberechtigte"],
"layer_1_pass": 1,
"layer_1_fail": 1,
"layer_0_boost_overrides": 0,
"total_mcs": 2,
}
return results, telemetry
monkeypatch.setattr(
"compliance.services.specialist_agents.impressum.agent.run_v3_pipeline",
_fake_pipeline,
)
async def _no_validator(*a, **kw): return {}
monkeypatch.setattr(
"compliance.services.specialist_agents.impressum.agent.validate_present",
_no_validator,
)
def test_agent_uses_db_mcs(mock_v3):
agent = ImpressumAgent()
out = _run(agent.evaluate(AgentInput(doc_type="impressum",
text=TESLA_TEXT)))
db_mc_findings = [f for f in out.findings
if f.check_id.startswith("DBMC-")]
assert len(db_mc_findings) == 1
assert db_mc_findings[0].check_id == "DBMC-DATA-2786-A04"
assert db_mc_findings[0].severity == Severity.MEDIUM.value
assert "TDDDG" in db_mc_findings[0].norm
def test_agent_emits_boost_coverage(mock_v3):
agent = ImpressumAgent()
out = _run(agent.evaluate(AgentInput(doc_type="impressum",
text=TESLA_TEXT)))
# 2 DB-MCs + 12 Pattern-Boost-Slots = 14 coverage entries
assert out.mc_total >= 14
boost_ok = [c for c in out.mc_coverage
if c.mc_id.startswith("IMP-MC-") and c.status == "ok"]
assert len(boost_ok) == 5 # 5 boost_ids im fake
def test_agent_notes_telemetry(mock_v3):
agent = ImpressumAgent()
out = _run(agent.evaluate(AgentInput(doc_type="impressum",
text=TESLA_TEXT)))
assert "v3-pipeline" in out.notes
assert "Pattern-Boosts" in out.notes
def test_short_text_skipped():
agent = ImpressumAgent()
out = _run(agent.evaluate(AgentInput(doc_type="impressum", text="x")))
assert all(c.status == "skipped" for c in out.mc_coverage)
assert not out.findings
def test_agent_version_is_three():
agent = ImpressumAgent()
assert agent.agent_version == "3.0"