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
@@ -9,6 +9,8 @@ from unittest.mock import AsyncMock, patch
import pytest
from fastapi.testclient import TestClient
from tests.fixtures.impressum_groundtruth import make_mc
@pytest.fixture
def app(tmp_path, monkeypatch):
@@ -69,9 +71,37 @@ def test_run_result_after_text_input(client, monkeypatch):
# Skip LLM
async def _no_cascade(*a, **kw): return None, []
monkeypatch.setattr(
"compliance.services.specialist_agents.impressum.agent.cascade",
"compliance.services.specialist_agents._semantic_validator.cascade",
_no_cascade,
)
# Agent delegiert MC-Laden ans Main Tool → _load_controls mocken.
# Tesla nennt 'Management' (engl.) statt deutschem GF-Label → das
# label_korrekt-MC schlaegt fehl → erwartetes Finding.
async def _fake_load(doc_type, db_url, limit, business_scope=None):
# pass_criteria nur mit label_korrekt-eigenen Keywords (deutsche/
# Bezeichnung/Rechtsform) — NICHT 'Geschäftsführer/Vorstand', sonst
# boostet das aktive vertretungsberechtigte-Feld (Tesla: 'Management')
# das MC faelschlich auf PASS.
return [make_mc(
"vertretungsberechtigte_label_korrekt",
["deutsche Bezeichnung Rechtsform Pflicht angeben"],
)]
monkeypatch.setattr(
"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,
)
r = client.post("/api/v1/specialist-agent/test/start",
json={"agent_id": "impressum",
"raw_texts": [
@@ -103,7 +133,7 @@ def test_run_result_after_text_input(client, monkeypatch):
def test_artifacts_listing(client, monkeypatch):
async def _no_cascade(*a, **kw): return None, []
monkeypatch.setattr(
"compliance.services.specialist_agents.impressum.agent.cascade",
"compliance.services.specialist_agents._semantic_validator.cascade",
_no_cascade,
)
r = client.post("/api/v1/specialist-agent/test/start",