feat: Browser-Matrix C2 + B11 AI-Retention + Impressum-Specialist-Agent + B1 Mobile Playwright
Task #15 Stage 1.c-e — Browser-Matrix Backend-Integration: - _phase_c2_browser_matrix.py: ruft consent-tester /scan-matrix wenn env BROWSER_MATRIX=true, fuellt state["browser_matrix"] + state["browser_aggregate"] + state["browser_matrix_html"] - V2-Mail-Block: 🌐 Browser-Matrix Tabelle (Profile · Score · Sub-Scores PC/RR/BD · Bewertung) mit Worst-of-Header - Orchestrator ruft run_phase_c2 nach run_phase_c KNOWN: Stage 1.b (consent_scanner browser_profile-Param) bleibt zurueckgestellt (Datei in loc-exception, Hook-Patch verweigert). Stage 1.a-Shim laeuft im consent-tester — alle Profile aktuell auf Chromium, echte Engine-Diversitaet kommt mit 1.b. Task #17 TH-RETENTION-002 als B11 ai_retention_granularity_check: - Erkennt AI-Provider-Kontext (vertex/openai/anthropic/etc) - In +-800-char-Window: prueft ≥2 Datenkategorien aus Standard-Liste (Texteingaben/IP/Geraet/Session/Fehlerprotokoll/Zeitstempel) - Wenn 1 pauschale Speicherdauer + ≥2 Kategorien aber kein per-Kategorie-Differential → LOW - Smoke: Elli-Mock-DSE trifft LOW "AI-Speicherdauer pauschal" Task #18 Specialist-Agents Phase-1-Prototyp: - compliance/services/specialist_agents/__init__.py mit Architektur-Doku - impressum_agent.py: 9 Pflichtangaben § 5 TMG + § 1 DL-InfoV als Pattern-Registry (Name, Email, Telefon, HR, USt-IdNr, Vertretungsberechtigt, Aufsichtsbehoerde, Berufsangaben, OS-Link) - business_scope-aware (OS-Link nur fuer ecommerce, Aufsichtsbehoerde nur fuer regulated_profession/financial/insurance) - Phase-1 ist Pattern-Match-only (kein LLM), demonstriert die Schnittstelle. Phase 2 ersetzt Pattern durch System-Prompt + KB. - Smoke: minimal-Impressum triggert 4 Findings korrekt Task #7 B1 Playwright Mobile-Verifikation: - consent-tester/services/mobile_reachability_scanner.py: echte WebKit-launch + p.devices['iPhone 15'] preset + de-DE locale + Europe/Berlin timezone - Footer-Anchor-Suche via locator("footer >> text=/.../i") fuer 13 Reopen-Phrasen - Tap-Target-Boundingbox-Messung (Apple HIG / WCAG ≥44x44) - Click-Behavior: DOM-Modal-Snapshot vor/nach, erkennt CMP-Open - Output: has_anchor, anchor_text, tap_target_px, click_opens_cmp, engine_meta, screenshot_b64 (Footer-Crop wenn kein Anchor) - consent-tester/routes_mobile.py POST /scan-mobile-reachability - Backend _b1_wiring erweitert: ruft Mobile-Endpoint zuerst, Fallback auf statischen HTTP-Fetch. Mobile-Daten enrichen finding.mobile_playwright + Severity-Bump bei tap-target<44 / click-doesnt-open-CMP. KNOWN: WebKit-System-Libs sind im Dockerfile ergaenzt (Stage 1.a- Commit), greifen aber erst nach CI/CD-Rebuild des consent-tester. Bis dahin faellt B1 sauber auf statischen Fetch zurueck. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
@@ -0,0 +1,116 @@
|
||||
"""B11 — AI-Retention-Granularity-Check (TH-RETENTION-002).
|
||||
|
||||
DSGVO Art. 13 Abs. 2 lit. a + DSK-Empfehlung: pro Datenkategorie
|
||||
eine spezifische Speicherdauer. Eine pauschale Angabe wie
|
||||
"6 Monate für alle Daten" reicht nicht.
|
||||
|
||||
GT-Pattern Elli:
|
||||
Vertex-AI-Chatbot speichert "IT- und pseudonymisierte
|
||||
Nutzungsdaten" pauschal 6 Monate. Keine Abstufung nach
|
||||
Datenkategorie (Texteingaben / IP / Geräteinformationen /
|
||||
Session-ID / Fehlerprotokolle).
|
||||
|
||||
Heuristik:
|
||||
1. AI-Kontext erkennen (vertex ai / openai / claude / etc.)
|
||||
2. In ±600-char-Window prüfen:
|
||||
- Existiert eine Speicherdauer-Aussage? (parse_duration_to_days)
|
||||
- Werden ≥2 Datenkategorien aus AI-Standardliste genannt?
|
||||
(Texteingaben, IP, Geräteinformationen, Session, Fehlerprotokolle)
|
||||
- Wenn 1 Speicherdauer + ≥2 Kategorien aber kein
|
||||
per-Kategorie-Differential → LOW
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
|
||||
from .retention_comparator import parse_duration_to_days
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
_AI_PROVIDERS = (
|
||||
"vertex ai", "google vertex", "openai", "gpt-3", "gpt-4", "chatgpt",
|
||||
"anthropic", "claude.ai", "claude-3", "mistral ai",
|
||||
"ki-assistent", "ki assistent", "ai assistant",
|
||||
)
|
||||
|
||||
|
||||
_AI_DATA_CATEGORIES = (
|
||||
"texteingab", # Texteingaben / Texteingabe
|
||||
"chatverlauf", "chatverläuf",
|
||||
"ip-adress",
|
||||
"geräteinform", "geraeteinform", "device-info",
|
||||
"session-id", "sitzungs-id",
|
||||
"browserversion", "user-agent",
|
||||
"fehlerprotokoll",
|
||||
"zeitstempel",
|
||||
)
|
||||
|
||||
|
||||
def _per_category_phrases() -> tuple[str, ...]:
|
||||
"""Patterns indicating per-category retention is mentioned."""
|
||||
return (
|
||||
"pro datenkategorie",
|
||||
"je datenkategorie",
|
||||
"unterschiedlich je",
|
||||
"abhängig vom datentyp",
|
||||
"abhaengig vom datentyp",
|
||||
"differenziert nach",
|
||||
"pro kategorie",
|
||||
)
|
||||
|
||||
|
||||
def check_ai_retention_granularity(state: dict) -> list[dict]:
|
||||
doc_texts = state.get("doc_texts") or {}
|
||||
dse = (doc_texts.get("dse") or "").lower()
|
||||
if not dse:
|
||||
return []
|
||||
findings: list[dict] = []
|
||||
for ai_kw in _AI_PROVIDERS:
|
||||
idx = dse.find(ai_kw)
|
||||
if idx < 0:
|
||||
continue
|
||||
window = dse[max(0, idx - 800): idx + 800]
|
||||
if not window:
|
||||
continue
|
||||
categories_found = [c for c in _AI_DATA_CATEGORIES if c in window]
|
||||
if len(categories_found) < 2:
|
||||
continue
|
||||
# Per-category retention phrase already present? then OK
|
||||
if any(p in window for p in _per_category_phrases()):
|
||||
return []
|
||||
# Retention-claim in window? parse duration
|
||||
m = re.search(
|
||||
r"(\d+(?:[.,]\d+)?\s*(?:tage?|monat\w*|jahre?|"
|
||||
r"day|month|year))", window,
|
||||
)
|
||||
if not m:
|
||||
continue
|
||||
days, kind = parse_duration_to_days(m.group(1))
|
||||
if days is None:
|
||||
continue
|
||||
findings.append({
|
||||
"check_id": "TH-RETENTION-GRANULARITY-001",
|
||||
"severity": "LOW",
|
||||
"severity_reason": "incomplete",
|
||||
"title": (
|
||||
"AI-Speicherdauer pauschal — pro Datenkategorie "
|
||||
"differenzieren empfohlen"
|
||||
),
|
||||
"norm": "DSGVO Art. 13 Abs. 2 lit. a + DSK-OH AI",
|
||||
"ai_provider": ai_kw,
|
||||
"retention_days": int(days),
|
||||
"categories_detected": categories_found,
|
||||
"action": (
|
||||
f"Für '{ai_kw}'-Kontext separate Speicherdauern je "
|
||||
f"Datenkategorie angeben (Texteingaben / IP / "
|
||||
f"Geräteinformationen / Session). Aktuell pauschal "
|
||||
f"{int(days)} Tage."
|
||||
),
|
||||
})
|
||||
break # one per DSE is enough
|
||||
if findings:
|
||||
logger.info("B11 AI-retention-granularity: %d findings", len(findings))
|
||||
return findings
|
||||
@@ -44,8 +44,10 @@ def compose_v2(state: dict) -> str:
|
||||
state.get("vendor_consistency_html", ""),
|
||||
# B5 — AI-Act Art. 50 Transparenzpflicht
|
||||
state.get("ai_act_html", ""),
|
||||
# B6/B7/B8 — DPO-cross-doc + Doc-Staleness + CMP-fingerprint
|
||||
# B6/B7/B8/B9/B10 — DPO + Staleness + CMP + MultiEntity + Transfer
|
||||
state.get("extra_findings_html", ""),
|
||||
# Browser-Matrix (Stage 1.c)
|
||||
state.get("browser_matrix_html", ""),
|
||||
# All legacy build_*_html() wrapped in V2 sections — preserves
|
||||
# every information block from the old renderer (Exec Summary,
|
||||
# Banner-Screenshot, VVT, Redundancy, Solutions, Diff, etc.)
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
"""Doc-Type Specialist-Agents — Phase 1 Prototyp.
|
||||
|
||||
Architektur:
|
||||
- Pro Doc-Type ein Spezialist-Agent mit System-Prompt (Domänenwissen)
|
||||
+ Knowledge-Base (anonymisierte Patterns/Statistiken aus
|
||||
Multi-Mandanten-Daten)
|
||||
- Jeder Agent liefert strukturierte Findings → enriched state
|
||||
- Ein Cross-Doc-Router-Agent prüft ob Absätze falsch zugeordnet sind
|
||||
("Cookie-Inhalt steht in AGB statt Cookie-Richtlinie")
|
||||
|
||||
Phase 1: Impressum-Agent als Prototyp (Pattern-Match-only, ohne LLM).
|
||||
Phase 2: DSE-Agent + Cross-Doc-Router (LLM-gestützt).
|
||||
Phase 3+: Weitere Doc-Types + Continuous Learning der KB.
|
||||
|
||||
Privacy: KB enthält NIEMALS Roh-Mandantendaten. Anonymisierung +
|
||||
Aggregation Pflicht (NER-Maskierung vor KB-Speicher).
|
||||
"""
|
||||
@@ -0,0 +1,159 @@
|
||||
"""Impressum-Specialist-Agent Phase-1 Prototyp.
|
||||
|
||||
Pattern-Match-only (kein LLM). Demonstriert die Architektur:
|
||||
- Knowledge-Base mit § 5 TMG/DDG-Pflichtangaben
|
||||
- Pattern-Library für Erkennung
|
||||
- strukturierte Findings mit Norm + Action
|
||||
|
||||
Phase 2 wird denselben Output produzieren, aber LLM-gestützt mit
|
||||
Domain-spezifischem System-Prompt + Cross-Customer-KB.
|
||||
|
||||
KB-Beispiel-Einträge:
|
||||
- HR-Format DE: HR[BA] <Nr> <Stadt>
|
||||
- USt-IdNr-Format DE: DE\\d{9}
|
||||
- Aufsichtsbehörden-Liste (Branchen)
|
||||
- DSB-Adressformat
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# Pflichtangaben nach § 5 TMG + § 1 DL-InfoV
|
||||
PFLICHTANGABEN = {
|
||||
"name_anbieter": {
|
||||
"label": "Name + Anschrift des Anbieters",
|
||||
"norm": "§ 5 Abs. 1 Nr. 1 TMG",
|
||||
"patterns": [
|
||||
re.compile(r"\b(?:Anbieter|Diensteanbieter|"
|
||||
r"Verantwortlich(?:er Anbieter)?)\s*[:.\s]",
|
||||
re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "HIGH",
|
||||
},
|
||||
"kontakt_email": {
|
||||
"label": "Email-Adresse",
|
||||
"norm": "§ 5 Abs. 1 Nr. 2 TMG",
|
||||
"patterns": [
|
||||
re.compile(r"\b[\w.+-]+@[\w-]+\.[a-z]{2,}\b", re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "HIGH",
|
||||
},
|
||||
"kontakt_telefon": {
|
||||
"label": "Telefon",
|
||||
"norm": "§ 5 Abs. 1 Nr. 2 TMG",
|
||||
"patterns": [
|
||||
re.compile(r"(?:Tel(?:efon)?|Phone)\.?\s*[:.\s]\s*[\+\d][\d\s/\-()]{5,}",
|
||||
re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "MEDIUM",
|
||||
},
|
||||
"handelsregister": {
|
||||
"label": "Handelsregister-Eintrag",
|
||||
"norm": "§ 5 Abs. 1 Nr. 4 TMG",
|
||||
"patterns": [
|
||||
re.compile(r"\bHR[BA]\s+\d", re.IGNORECASE),
|
||||
re.compile(r"Handelsregister", re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "HIGH",
|
||||
},
|
||||
"ust_id": {
|
||||
"label": "USt-IdNr",
|
||||
"norm": "§ 5 Abs. 1 Nr. 6 TMG",
|
||||
"patterns": [
|
||||
re.compile(r"\b(?:USt-?Id(?:Nr)?\.?|VAT(?:-?Id)?)\s*[:.\s]",
|
||||
re.IGNORECASE),
|
||||
re.compile(r"\bDE\d{9}\b"),
|
||||
],
|
||||
"severity_if_missing": "MEDIUM",
|
||||
},
|
||||
"vertretungsberechtigte": {
|
||||
"label": "Vertretungsberechtigte Person",
|
||||
"norm": "§ 5 Abs. 1 Nr. 1 TMG (juristische Personen)",
|
||||
"patterns": [
|
||||
re.compile(r"(?:Geschäftsführer|Vertretungsberechtigt|"
|
||||
r"vertreten\s+durch)\s*[:.\s]",
|
||||
re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "HIGH",
|
||||
},
|
||||
"aufsichtsbehoerde": {
|
||||
"label": "Aufsichtsbehörde (regulierte Branchen)",
|
||||
"norm": "§ 5 Abs. 1 Nr. 3 TMG (Branchen-bedingt)",
|
||||
"patterns": [
|
||||
re.compile(r"Aufsichtsbeh(?:ö|oe)rde\s*[:.\s]", re.IGNORECASE),
|
||||
re.compile(r"\bBAFin\b|\bBNetzA\b|\bLKA\b", re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "LOW",
|
||||
},
|
||||
"berufsangaben": {
|
||||
"label": "Berufsbezeichnung + Berufsrechtliche Angaben",
|
||||
"norm": "§ 5 Abs. 1 Nr. 5 TMG (Kammerberufe)",
|
||||
"patterns": [
|
||||
re.compile(r"Berufsbezeichnung|Berufsordnung|Kammer",
|
||||
re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "LOW",
|
||||
},
|
||||
"odr_link": {
|
||||
"label": "OS-Link auf EU-Plattform",
|
||||
"norm": "Art. 14 EU-VO 524/2013 (B2C-Onlineshops)",
|
||||
"patterns": [
|
||||
re.compile(r"ec\.europa\.eu/consumers/odr", re.IGNORECASE),
|
||||
],
|
||||
"severity_if_missing": "MEDIUM",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def evaluate(impressum_text: str,
|
||||
business_scope: set[str] | None = None) -> list[dict]:
|
||||
"""Run Impressum-Agent against the doc text.
|
||||
|
||||
Returns a list of finding dicts; empty when all Pflichtangaben
|
||||
present. `business_scope` controls which optional checks run
|
||||
(e.g. OS-Link only for B2C ecommerce).
|
||||
"""
|
||||
if not impressum_text:
|
||||
return []
|
||||
business_scope = business_scope or set()
|
||||
findings: list[dict] = []
|
||||
for field_id, spec in PFLICHTANGABEN.items():
|
||||
# Skip context-dependent fields when scope doesn't match
|
||||
if field_id == "odr_link" and "ecommerce" not in business_scope:
|
||||
continue
|
||||
if field_id == "aufsichtsbehoerde" and (
|
||||
"regulated_profession" not in business_scope
|
||||
and "financial_services" not in business_scope
|
||||
and "insurance" not in business_scope
|
||||
):
|
||||
continue
|
||||
if field_id == "berufsangaben" and (
|
||||
"regulated_profession" not in business_scope
|
||||
):
|
||||
continue
|
||||
found = any(p.search(impressum_text) for p in spec["patterns"])
|
||||
if found:
|
||||
continue
|
||||
findings.append({
|
||||
"check_id": f"IMPRESSUM-AGENT-{field_id.upper()}",
|
||||
"agent": "impressum_agent_v1",
|
||||
"field_id": field_id,
|
||||
"severity": spec["severity_if_missing"],
|
||||
"severity_reason": "missing",
|
||||
"title": f"Pflichtangabe '{spec['label']}' fehlt im Impressum",
|
||||
"norm": spec["norm"],
|
||||
"action": (
|
||||
f"{spec['label']} im Impressum ergänzen "
|
||||
f"(Pflichtangabe nach {spec['norm']})."
|
||||
),
|
||||
})
|
||||
if findings:
|
||||
logger.info(
|
||||
"impressum_agent: %d findings (kein LLM, KB v1)", len(findings),
|
||||
)
|
||||
return findings
|
||||
Reference in New Issue
Block a user