fix(agents): Impressum+Cookie delegieren MC-Laden ans Main Tool — Scope-Filter + Maßnahmen
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 / sbom-scan (push) Has been skipped
CI / build-sha-integrity (push) Failing after 4s
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 / dep-audit (push) Has been skipped
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

Regression: Der v3-Agent-Pfad baute eine parallele MC-Pipeline
(_load_impressum_mcs / _load_cookie_mcs, Roh-SELECT) und lief damit an
allen Schutzmechanismen der Engine vorbei → GOV/Branchen-MCs als HIGH bei
OEM/Zulieferer, fremde MCs (Bestellbestätigung), und action=check_question
(Fragen statt Maßnahmen im Frontend).

- Agent delegiert MC-Laden an rag_document_checker._load_controls
  (P72-Scope, check_type='text', fits_doc_type/scope_requires).
- Subtraktives Sektor-Gate (SECTOR_PREFIXES) + Themen-Gate am Agent-Rand.
- action = konkrete Maßnahme (Imperativ) statt check_question.
- rag_document_checker: from __future__ import annotations (3.9-Import).
- mcs: Name-Pattern erkennt "Aktiengesellschaft" (OEM-Impressums).
- Tote GT-/Semantic-/Routes-Tests wiederbelebt (v3-Mismatch +
  agent.cascade-Patch-Target). Alle 72 Specialist-Tests grün.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-06-09 11:30:16 +02:00
parent bd4882e143
commit 389e6de0c7
13 changed files with 641 additions and 135 deletions
@@ -13,6 +13,7 @@ from compliance.services.specialist_agents._semantic_validator import (
standard_label,
validate_present,
)
from tests.fixtures.impressum_groundtruth import make_mc
def _run(coro):
@@ -91,10 +92,33 @@ def test_semantic_demotion_high_to_low(monkeypatch):
"compliance.services.specialist_agents._semantic_validator.cascade",
_fake_cascade,
)
# Agent delegiert MC-Laden ans Main Tool → _load_controls mocken.
# control_id == field_id 'kontakt_telefon', damit der Semantic-Demote
# das Finding ueber die LLM-Antwort zuordnet.
async def _fake_load(doc_type, db_url, limit, business_scope=None):
return [make_mc("kontakt_telefon",
["Telefon Telefonnummer Rufnummer"],
severity="HIGH")]
monkeypatch.setattr(
"compliance.services.specialist_agents.impressum.agent.cascade",
_fake_cascade,
"compliance.services.rag_document_checker._load_controls",
_fake_load,
)
async def _no_match(*a, **kw):
return set()
monkeypatch.setattr(
"compliance.services.mc_embedding_matcher.embedding_match",
_no_match, raising=False,
)
async def _no_embed(*a, **kw):
return None
monkeypatch.setattr(
"compliance.services.mc_embedding_matcher.ensure_mc_embeddings",
_no_embed, raising=False,
)
# Text OHNE Telefon-Label → MC matched nicht → HIGH-Finding
text = (
"Beispiel GmbH\nMusterstr. 1\n12345 Berlin\n"