feat(platform): live-wire AGB v2 + DSE v3 + Architektur-Tab (#29)
CI / detect-changes (push) Successful in 7s
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 / sbom-scan (push) Has been skipped
CI / build-sha-integrity (push) Successful in 9s
CI / validate-canonical-controls (push) Successful in 12s
CI / loc-budget (push) Successful in 24s
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) Successful in 3m11s
CI / test-go (push) Has been skipped
CI / iace-gt-coverage (push) Has been skipped
CI / test-python-backend (push) Successful in 24s
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped

AGB v2 (decision_method routing, 71%FP->~0) + DSE v3 (4-layer, recovered from container) + Architektur-Tab into /sdk/agent live path. Incl CI robustness (detect-changes.sh + PR-head checkout) + security (hardcoded Qdrant key removed, gitleaks allowlist).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit was merged in pull request #29.
This commit is contained in:
2026-06-21 12:58:26 +00:00
parent 6b9c7984b4
commit 38a347a82a
44 changed files with 3861 additions and 104 deletions
@@ -1,12 +1,27 @@
"""AGBAgent — kuratierte §§-305-ff-BGB-Checkliste (ChecklistAgent-Subclass)."""
from __future__ import annotations
"""AGBAgent (v2, routed). Embedding/LLM offline-gestubbt → kein Netzwerk."""
import asyncio
import pytest
import compliance.services.specialist_agents.agb._pipeline as pipeline
from compliance.services.checkers.base import CheckResult
from compliance.services.specialist_agents import REGISTRY, AgentInput
class _Stub:
def __init__(self, present):
self._p = present
async def check(self, ctrl, doc):
return CheckResult(present=self._p)
@pytest.fixture(autouse=True)
def _offline(monkeypatch):
monkeypatch.setattr(pipeline, "_EMB", _Stub(None))
monkeypatch.setattr(pipeline, "_LLM", _Stub(None))
def _run(text: str):
return asyncio.run(
REGISTRY.get("agb").evaluate(AgentInput(doc_type="agb", text=text)))
@@ -0,0 +1,62 @@
"""AGB routed-Pipeline: Gate, Reference-/Embedding-Rescue, LLM-skip, Re-Tiering.
Embedding + LLM offline-gestubbt → deterministisch, kein Netzwerk (Reference = echtes Regex)."""
import asyncio
from types import SimpleNamespace
import pytest
import compliance.services.specialist_agents.agb._pipeline as pipeline
from compliance.services.checkers.base import CheckResult
from compliance.services.specialist_agents._base import AgentInput
from compliance.services.specialist_agents.agb.agent import AGBAgent
class _Stub:
def __init__(self, present):
self._p = present
async def check(self, ctrl, doc):
return CheckResult(present=self._p)
@pytest.fixture(autouse=True)
def _offline(monkeypatch):
monkeypatch.setattr(pipeline, "_EMB", _Stub(None))
monkeypatch.setattr(pipeline, "_LLM", _Stub(None))
def _routed(field_ids, text, context=None):
findings = [SimpleNamespace(field_id=fid) for fid in field_ids]
return asyncio.run(pipeline.run_routed(findings, text, context or {}))
def test_gate_termination_na_for_oneoff_shop():
text = "Widerrufsbelehrung: Sie koennen binnen 14 Tagen widerrufen. " * 5
kept, resolved, gated = _routed(["termination", "termination_form"], text)
assert set(gated) == {"termination", "termination_form"}
assert kept == []
def test_reference_rescues_data_protection():
text = "Einzelheiten zur Verarbeitung in unserer Datenschutzerklaerung. " * 5
kept, resolved, gated = _routed(["data_protection"], text)
assert "data_protection" in resolved and kept == []
def test_embedding_rescue_resolves(monkeypatch):
monkeypatch.setattr(pipeline, "_EMB", _Stub(True))
kept, resolved, gated = _routed(["scope"], "x" * 200)
assert "scope" in resolved
def test_llm_skipped_keeps_finding():
kept, resolved, gated = _routed(["delivery_timeframe"], "x" * 200, {"skip_llm": True})
assert [f.field_id for f in kept] == ["delivery_timeframe"] and resolved == []
def test_evaluate_retiers_low_out_of_findings():
text = ("Allgemeine Geschaeftsbedingungen. Vertragsschluss durch Bestellung. "
"Haftung beschraenkt. Gerichtsstand Muenchen. ") * 6
out = asyncio.run(AGBAgent().evaluate(AgentInput(doc_type="agb", text=text)))
assert out.agent == "agb" and out.agent_version == "2.0"
assert all(f.severity in ("HIGH", "MEDIUM") for f in out.findings)
@@ -0,0 +1,14 @@
"""AGB muss im LIVE-Pfad verdrahtet sein (_TOPIC_AGENTS), nicht nur per Snapshot."""
from compliance.api.agent_check._agent_outputs import _TOPIC_AGENTS
def test_agb_wired_into_live_topic_agents():
assert _TOPIC_AGENTS.get("agb") == "agb"
def test_dse_wired_into_live_topic_agents():
assert _TOPIC_AGENTS.get("dse") == "dse"
def test_impressum_still_wired():
assert _TOPIC_AGENTS.get("impressum") == "impressum"
@@ -0,0 +1,83 @@
"""Unit-Tests der Prüfer-Library. Embedding + LLM gemockt → kein Netzwerk."""
import asyncio
import compliance.services.llm_cascade as cascade_mod
import compliance.services.mc_embedding_matcher as emb_mod
from compliance.services.checkers.base import (
ControlSpec,
DecisionMethod,
DocContext,
VerificationMethod,
)
from compliance.services.checkers.embedding_checker import EmbeddingChecker
from compliance.services.checkers.llm_checker import LLMChecker
from compliance.services.checkers.reference_checker import ReferenceChecker
def _run(coro):
return asyncio.run(coro)
def test_reference_present_and_absent():
rc = ReferenceChecker()
spec = ControlSpec("data_protection", VerificationMethod.REFERENCE,
DecisionMethod.LINK_RESOLVER,
patterns=[r"datenschutz(erkl|bestimmung|hinweis)"])
r = _run(rc.check(spec, DocContext(
text="Details in unserer Datenschutzerklaerung: https://x.de/datenschutz")))
assert r.present is True
assert r.detail.get("link", "").startswith("https://")
r2 = _run(rc.check(spec, DocContext(text="Keine Angabe zum Datenschutz-Thema.")))
assert r2.present is False
def test_embedding_threshold(monkeypatch):
monkeypatch.setattr(emb_mod, "DIM", 3, raising=False)
monkeypatch.setattr(emb_mod, "_chunk_text", lambda t: [t], raising=False)
async def _embed(texts):
return [[1.0, 0.0, 0.0] for _ in texts]
monkeypatch.setattr(emb_mod, "_embed_texts", _embed, raising=False)
ec = EmbeddingChecker()
spec = ControlSpec("scope_t", VerificationMethod.CONTENT, DecisionMethod.EMBEDDING,
paraphrases=["Geltungsbereich"], embed_threshold=0.58)
monkeypatch.setattr(emb_mod, "_cosine", lambda a, b: 0.90, raising=False)
r = _run(ec.check(spec, DocContext(text="x" * 200)))
assert r.present is True and r.confidence >= 0.58
monkeypatch.setattr(emb_mod, "_cosine", lambda a, b: 0.20, raising=False)
r2 = _run(ec.check(spec, DocContext(text="x" * 200)))
assert r2.present is False
def test_embedding_offline_returns_none(monkeypatch):
async def _boom(texts):
raise ConnectionError("embedding-service down")
monkeypatch.setattr(emb_mod, "_embed_texts", _boom, raising=False)
ec = EmbeddingChecker()
spec = ControlSpec("scope_off", VerificationMethod.CONTENT, DecisionMethod.EMBEDDING,
paraphrases=["x"], embed_threshold=0.6)
r = _run(ec.check(spec, DocContext(text="y" * 200)))
assert r.present is None # fail-safe
def test_llm_present_and_absent(monkeypatch):
lc = LLMChecker()
spec = ControlSpec("delivery_timeframe", VerificationMethod.CONTENT, DecisionMethod.LLM,
topic_regex=r"liefer", question="Konkrete Lieferfrist?")
doc = DocContext(text=("1. Lieferung\nDie Ware wird innerhalb von 2 Werktagen "
"geliefert.\n") * 4)
async def _erfuellt(system, user, **kw):
return {"text": '{"verdict":"ERFUELLT","zitat":"2 Werktagen","begruendung":"x"}',
"source": "qwen", "confidence": 0.7}
monkeypatch.setattr(cascade_mod, "call_with_cascade", _erfuellt, raising=False)
assert _run(lc.check(spec, doc)).present is True
async def _fehlt(system, user, **kw):
return {"text": '{"verdict":"FEHLT"}', "source": "qwen"}
monkeypatch.setattr(cascade_mod, "call_with_cascade", _fehlt, raising=False)
assert _run(lc.check(spec, doc)).present is False
@@ -1,65 +1,153 @@
"""DSEAgent — kuratierte Art-13/14-Checkliste (kein Library-Firehose)."""
"""DSE-Agent v3 — DB-Controls (doc_check_controls) via run_v3_pipeline +
kuratierter Art-13-Regex-Boost (Layer 0). Volle Parität zu impressum/cookie.
Die Tests prüfen die deterministischen Bausteine (regex_boost/mcs) ohne DB und
den Agent-Pfad mit gemocktem run_v3_pipeline (CI hat keine DB).
"""
from __future__ import annotations
import asyncio
import compliance.services.specialist_agents.dse.agent as dse_agent
from compliance.services.specialist_agents import REGISTRY, AgentInput
from compliance.services.specialist_agents.dse.mcs import MCS, MC_IDS
from compliance.services.specialist_agents.dse.regex_boost import (
boost_matches_db_mc,
compute_regex_boosts,
criteria_on_topic,
)
_DSE_SAMPLE = (
"Datenschutzerklaerung. Verantwortlich im Sinne der DSGVO ist die Muster "
"GmbH, Musterstrasse 1, 12345 Berlin. E-Mail: info@muster.de. "
"Datenschutzbeauftragter: dsb@muster.de. Zwecke der Verarbeitung und "
"Rechtsgrundlage Art. 6 Abs. 1 lit. f berechtigtes Interesse. Empfaenger "
"Ihrer Daten sind Auftragsverarbeiter. Speicherdauer der Daten richtet "
"sich nach Aufbewahrungsfristen. Sie haben das Recht auf Auskunft, das "
"Recht auf Berichtigung, das Recht auf Loeschung sowie ein "
"Widerspruchsrecht. Beschwerde bei der Aufsichtsbehoerde moeglich. Stand: "
"Januar 2026. ") * 3
def _run(text: str):
return asyncio.run(
REGISTRY.get("dse").evaluate(AgentInput(doc_type="dse", text=text)))
# ── Registrierung ────────────────────────────────────────────────────────
def test_dse_agent_registered():
assert REGISTRY.get("dse") is not None
agent = REGISTRY.get("dse")
assert agent is not None
assert agent.agent_version == "3.0"
assert agent.doc_type == "dse"
def test_dse_detects_core_obligations():
text = (
"Datenschutzerklaerung. Verantwortlich im Sinne der DSGVO ist die "
"Muster GmbH, Musterstrasse 1, 12345 Berlin. E-Mail: info@muster.de. "
"Datenschutzbeauftragter: dsb@muster.de. Zwecke der Verarbeitung und "
"Rechtsgrundlage Art. 6 Abs. 1. Empfaenger Ihrer Daten. Speicherdauer "
"der Daten. Ihre Rechte: Auskunft, Loeschung, Widerspruch, Beschwerde "
"bei der Aufsichtsbehoerde. ") * 3
out = _run(text)
assert out.agent == "dse"
# 10 L1-Pflichtangaben immer + L2-Details deren Parent vorhanden ist
# (fehlende Parents → L2 übersprungen, kein 'na'-Rauschen).
assert 10 <= out.mc_total <= 33
ok = [c.label for c in out.mc_coverage if c.status == "ok"]
assert any("Verantwortlich" in lbl for lbl in ok)
assert any("Rechtsgrundlage" in lbl for lbl in ok)
def test_owned_mc_ids_match_checklist():
# owned_mc_ids = die Boost-Pattern-IDs (aus ART13_CHECKLIST gehoben).
assert MC_IDS == tuple(m.mc_id for m in MCS)
assert len(MC_IDS) >= 10 # mind. die 10 L1-Pflichtfelder + L2
def test_dse_missing_obligations_are_findings():
out = _run("Lorem ipsum dolor sit amet consectetur adipiscing elit. " * 6)
assert out.findings
assert any(f.severity == "HIGH" for f in out.findings)
# ── Layer-0 Regex-Boost (deterministisch, ohne DB) ───────────────────────
def test_regex_boost_detects_core_fields():
boosts = compute_regex_boosts(_DSE_SAMPLE)
# Die zentralen Art-13-Felder müssen erkannt werden.
for field in ("controller", "legal_basis", "rights", "complaint",
"retention", "dse_version_date"):
assert field in boosts, f"{field} nicht erkannt: {sorted(boosts)}"
def test_regex_boost_empty_on_short_text():
assert compute_regex_boosts("zu kurz") == set()
def test_criteria_on_topic_accepts_dse_rejects_foreign():
dse_crit = ["Rechtsgrundlage gemäß Art. 6 DSGVO benannt",
"Speicherdauer und Löschfrist angegeben"]
assert criteria_on_topic(dse_crit) is True
foreign = ["Bestellbestätigung wird per E-Mail versendet",
"Versandkosten werden im Warenkorb angezeigt"]
assert criteria_on_topic(foreign) is False
# leere Kriterien → konservativ on-topic behalten
assert criteria_on_topic([]) is True
def test_boost_matches_db_mc_third_country():
boosts = {"third_country", "controller"}
crit = ["Standardvertragsklauseln für Drittland benannt",
"Geeignete Garantien bei Übermittlung in ein Drittland"]
assert boost_matches_db_mc(boosts, crit) == "third_country"
# ohne passende Boosts → None
assert boost_matches_db_mc(set(), crit) is None
# ── Agent-Pfad mit gemocktem run_v3_pipeline ─────────────────────────────
def _mock_v3(results, telemetry=None):
async def _fake(text, scope, db_url="", skip_embedding=False):
return results, (telemetry or {
"total_mcs": len(results), "layer_0_field_hits": 0,
"layer_0_field_ids": [], "layer_0_boost_overrides": 0,
"sector_dropped": 0, "offtopic_dropped": 0})
return _fake
def _run(text, context=None):
return asyncio.run(REGISTRY.get("dse").evaluate(
AgentInput(doc_type="dse", text=text, context=context or {})))
def test_dse_short_text_skips():
out = _run("zu kurz")
assert out.confidence == 0.0
assert all(c.status == "skipped" for c in out.mc_coverage)
assert out.mc_coverage and all(
c.status == "skipped" for c in out.mc_coverage)
def test_third_country_high_when_applicable_no_na_detail_short_action():
# Text ohne Drittland-Abschnitt + Scan-Kontext drittland=ja:
# - third_country (L1) fehlt → HIGH (nicht weiches MEDIUM)
# - Transfermechanismus (L2) → KEIN 'na' (übersprungen, Parent deckt ab)
# - Titel/Maßnahme kurz (kein 280-Zeichen-Hint als Recommendation-Titel)
text = ("Datenschutz. Verantwortlich ist die Muster GmbH, info@muster.de. "
"Zwecke und Rechtsgrundlage Art. 6. Speicherdauer. Ihre Rechte. ") * 4
out = asyncio.run(REGISTRY.get("dse").evaluate(AgentInput(
doc_type="dse", text=text,
context={"scan_context": {"third_country_transfer": "yes"}})))
tc = [f for f in out.findings if "Drittland" in f.title]
assert tc and tc[0].severity == "HIGH"
assert not any(c.status == "na" and "Transfermechanismus" in c.label
for c in out.mc_coverage)
assert all(len(f.action) < 110 for f in out.findings)
# Detail-Begründung bleibt als evidence erhalten
assert any(f.evidence for f in out.findings)
def test_dse_findings_from_failed_db_mc(monkeypatch):
results = [{
"control_id": "DATA-525-A17", "passed": False, "severity": "HIGH",
"label": "Berechtigte Interessen ausweisen", "regulation": None,
"article": None, "_pass_criteria": ["berechtigtes interesse benannt"],
"matched_text": "", "source": "keyword_match",
}, {
"control_id": "AUTH-2051-A11", "passed": True, "severity": "LOW",
"label": "Prägnante Form", "regulation": None, "article": None,
"_pass_criteria": [], "matched_text": "ok",
}]
monkeypatch.setattr(dse_agent, "run_v3_pipeline", _mock_v3(results))
out = _run(_DSE_SAMPLE, context={"skip_llm": True})
fids = {f.field_id for f in out.findings}
assert "DATA-525-A17" in fids # failed → Finding
assert "AUTH-2051-A11" not in fids # passed → kein Finding
f = next(f for f in out.findings if f.field_id == "DATA-525-A17")
assert f.severity == "HIGH"
assert f.norm == "DSGVO Art. 13/14" # NULL-regulation → Fallback-Norm
assert len(f.action) < 410
def test_dse_third_country_override_to_high(monkeypatch):
# MEDIUM-Drittland-MC → HIGH bei dokumentiertem Transfer (scan_context).
results = [{
"control_id": "DATA-900-A01", "passed": False, "severity": "MEDIUM",
"label": "Drittlandtransfer Schutzgarantien benennen",
"regulation": None, "article": None,
"_pass_criteria": ["standardvertragsklauseln", "drittland garantien"],
"matched_text": "", "source": "keyword_match",
}]
monkeypatch.setattr(dse_agent, "run_v3_pipeline", _mock_v3(results))
out = _run(_DSE_SAMPLE, context={
"skip_llm": True,
"scan_context": {"third_country_transfer": "yes"}})
f = next(f for f in out.findings if f.field_id == "DATA-900-A01")
assert f.severity == "HIGH"
assert f.severity_reason == "db_mc_failed_third_country_transfer"
def test_dse_no_transfer_keeps_medium(monkeypatch):
results = [{
"control_id": "DATA-900-A01", "passed": False, "severity": "MEDIUM",
"label": "Drittlandtransfer Schutzgarantien benennen",
"regulation": None, "article": None,
"_pass_criteria": ["standardvertragsklauseln", "drittland garantien"],
"matched_text": "", "source": "keyword_match",
}]
monkeypatch.setattr(dse_agent, "run_v3_pipeline", _mock_v3(results))
out = _run(_DSE_SAMPLE, context={"skip_llm": True})
f = next(f for f in out.findings if f.field_id == "DATA-900-A01")
assert f.severity == "MEDIUM"
@@ -0,0 +1,59 @@
"""Tests fuer das DSE-Applicability-Gate (_classification_gate).
Deckt die reine Split-Logik (apply_gate) und das defensive Verhalten von
load_dse_gate ohne DB ab. Die DB-Abfrage selbst ist I/O und wird hier nicht
gegen eine echte DB getestet (defensiver Pfad: kein DSN -> leeres Dict)."""
import asyncio
import os
from compliance.services.specialist_agents.dse._classification_gate import (
apply_gate,
load_dse_gate,
)
def test_apply_gate_splits_findings_and_organizational():
controls = [
{"control_id": "AUTH-2051-A02", "title": "Speicherdauer nennen"},
{"control_id": "AUTH-2049-A01", "title": "VVT fuehren"},
]
gate = {
"AUTH-2049-A01": {
"obligation_type": "EVIDENCE",
"check_intent": "DIRECT_EVIDENCE",
"applicable_artifacts": ["VVT", "AUDIT"],
"reference_allowed": "NO",
}
}
kept, organizational = apply_gate(controls, gate)
assert [c["control_id"] for c in kept] == ["AUTH-2051-A02"]
assert len(organizational) == 1
org = organizational[0]
assert org["control_id"] == "AUTH-2049-A01"
assert org["title"] == "VVT fuehren"
assert org["applicable_artifacts"] == ["VVT", "AUDIT"]
assert org["check_intent"] == "DIRECT_EVIDENCE"
def test_apply_gate_empty_gate_keeps_all():
controls = [{"control_id": "X-1"}, {"control_id": "X-2"}]
kept, organizational = apply_gate(controls, {})
assert len(kept) == 2
assert organizational == []
def test_load_dse_gate_without_dsn_is_defensive():
"""Kein DSN + keine Env -> leeres Dict (kein Filter), kein Fehler."""
saved = (
os.environ.pop("DATABASE_URL", None),
os.environ.pop("COMPLIANCE_DATABASE_URL", None),
)
try:
result = asyncio.run(load_dse_gate(""))
assert result == {}
finally:
if saved[0] is not None:
os.environ["DATABASE_URL"] = saved[0]
if saved[1] is not None:
os.environ["COMPLIANCE_DATABASE_URL"] = saved[1]
@@ -0,0 +1,67 @@
"""DSE Embedding-Recall — deterministische semantische Schicht (gecacht).
Testet die reine Logik OHNE Embedding-Service: Cache-Treffer-Pfad,
Schwellen-Filter, Kandidaten-Schnitt, Reachability-Guard. Das Einbetten selbst
(Embedding-Service) ist Integration und wird auf macmini/Prod validiert.
"""
from __future__ import annotations
import asyncio
import json
import compliance.services.specialist_agents.dse._embedding_recall as er
_TEXT = ("Datenschutzerklaerung der Muster GmbH. " * 20) # > 100 Zeichen
def _seed_cache(tmp_path, scores: dict[str, float]) -> str:
p = tmp_path / "dse_embed_cache.json"
p.write_text(json.dumps({er._doc_hash(_TEXT): scores}))
return str(p)
def test_doc_hash_deterministic():
# feste Funktion: gleicher Text → gleicher Hash (Reproduzierbarkeit)
assert er._doc_hash(_TEXT) == er._doc_hash(_TEXT)
assert er._doc_hash("a") != er._doc_hash("b")
def test_cache_hit_threshold_filter(tmp_path, monkeypatch):
# Cache-Treffer: kein Embedding-Service nötig. Nur Scores >= Schwelle UND
# in den Kandidaten werden zurückgegeben.
scores = {"DATA-1": 0.71, "DATA-2": 0.60, "AUTH-3": 0.68, "SEC-4": 0.50}
monkeypatch.setenv("DSE_EMBED_CACHE", _seed_cache(tmp_path, scores))
monkeypatch.setattr(er, "_CACHE_PATH", str(tmp_path / "dse_embed_cache.json"))
cands = ["DATA-1", "DATA-2", "AUTH-3", "SEC-4"]
out = asyncio.run(er.embedding_recall(_TEXT, cands, threshold=0.65))
# >=0.65: DATA-1 (0.71), AUTH-3 (0.68). NICHT DATA-2 (0.60), SEC-4 (0.50).
assert out == {"DATA-1", "AUTH-3"}
def test_cache_hit_candidate_intersection(tmp_path, monkeypatch):
# Nur Kandidaten (durchgefallene Controls) zählen — andere ignoriert.
scores = {"DATA-1": 0.90, "DATA-2": 0.90}
monkeypatch.setattr(er, "_CACHE_PATH", str(tmp_path / "c.json"))
(tmp_path / "c.json").write_text(json.dumps({er._doc_hash(_TEXT): scores}))
out = asyncio.run(er.embedding_recall(_TEXT, ["DATA-1"], threshold=0.65))
assert out == {"DATA-1"} # DATA-2 nicht in Kandidaten
def test_empty_inputs():
assert asyncio.run(er.embedding_recall("zu kurz", ["X"])) == set()
assert asyncio.run(er.embedding_recall(_TEXT, [])) == set()
def test_service_down_returns_empty(tmp_path, monkeypatch):
# Kein Cache + Service nicht erreichbar → leer (deterministischer Layer trägt),
# KEIN Hang.
monkeypatch.setattr(er, "_CACHE_PATH", str(tmp_path / "none.json"))
async def _unreachable(timeout=2.0):
return False
monkeypatch.setattr(er, "_embedding_reachable", _unreachable)
out = asyncio.run(er.embedding_recall(_TEXT, ["DATA-1"]))
assert out == set()