feat: Multi-URL Document Check with full checklist visibility

New "Dokumenten-Pruefung" tab in Compliance Agent:
- User adds multiple URLs with document type (DSI, AGB, Impressum, Cookie, Widerruf)
- Each document loaded via Playwright, accordions expanded, text extracted
- Checked against type-specific legal checklist
- Optional: Cookie banner check via checkbox

Checklisten-UX (solves "100% looks like nothing was checked"):
- All checks shown per document: green checkmark + matched text excerpt
- Red X for missing fields with legal reference
- Builds user trust: "9 Punkte geprueft, alle bestanden"
- Expandable per document with completeness bar

New checklists:
- Impressum: §5 TMG (6 fields: name, address, contact, register, VAT, representative)
- Cookie-Richtlinie: §25 TDDDG (5 fields: types, purposes, retention, third-party, opt-out)

Backend:
- POST /agent/doc-check — async with polling (same pattern as /scan)
- DocCheckResult includes checks[] with passed/failed + matched_text
- dsi_document_checker returns all_checks in SCORE finding
- Email report shows per-document checklist

Files: agent_doc_check_routes.py (280 LOC), DocCheckTab.tsx (248 LOC),
ChecklistView.tsx (130 LOC), dsi_document_checker.py (+70 LOC)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-05-06 10:08:40 +02:00
parent 254dbab566
commit 4c68caac4e
7 changed files with 770 additions and 8 deletions
@@ -163,6 +163,36 @@ AGB_CHECKLIST = [
"patterns": [r"gerichtsstand", r"anwendbares\s+recht", r"jurisdiction", r"governing\s+law"]},
]
# §5 TMG / §18 MStV Impressum requirements
IMPRESSUM_CHECKLIST = [
{"id": "name", "label": "Name des Anbieters",
"patterns": [r"(?:gmbh|ag|e\.v\.|ohg|kg|gbr|ug|mbh|inc|ltd)", r"firma", r"unternehmen"]},
{"id": "address", "label": "Anschrift",
"patterns": [r"(?:str(?:asse|\.)|weg|platz|allee)\s*\d", r"d-\d{5}", r"\d{5}\s+\w+"]},
{"id": "contact", "label": "Kontaktdaten (E-Mail + Telefon)",
"patterns": [r"(?:e-?mail|mail).*@", r"telefon|phone|tel\.", r"\+?\d[\d\s/\-]{8,}"]},
{"id": "register", "label": "Handelsregister / Registernummer",
"patterns": [r"(?:handelsregister|hrb|hra|registergericht|amtsgericht)", r"register.*(?:nr|nummer)"]},
{"id": "vat", "label": "USt-IdNr.",
"patterns": [r"ust.*id", r"umsatzsteuer.*identifikation", r"vat.*id", r"de\s*\d{9}"]},
{"id": "representative", "label": "Vertretungsberechtigte",
"patterns": [r"vertretungsberechtigt", r"geschäftsführ", r"vorstand", r"inhaber"]},
]
# §25 TDDDG Cookie policy requirements
COOKIE_CHECKLIST = [
{"id": "cookie_types", "label": "Arten der Cookies",
"patterns": [r"(?:notwendig|essentiell|funktional|statistik|marketing|tracking)", r"cookie.*(?:art|typ|kategori)"]},
{"id": "purposes", "label": "Zwecke der Cookies",
"patterns": [r"zweck.*cookie", r"cookie.*zweck", r"(?:wofuer|wozu|warum).*cookie"]},
{"id": "retention", "label": "Speicherdauer der Cookies",
"patterns": [r"(?:speicherdauer|laufzeit|gueltigk|ablauf).*cookie", r"cookie.*(?:\d+\s+(?:tag|monat|jahr)|session)"]},
{"id": "third_party", "label": "Drittanbieter-Cookies",
"patterns": [r"drittanbieter", r"third.?party", r"(?:google|facebook|meta|microsoft).*cookie"]},
{"id": "opt_out", "label": "Widerspruchsmoeglichkeit",
"patterns": [r"(?:widerspruch|opt.?out|ablehnen|deaktivieren).*cookie", r"cookie.*(?:ablehnen|deaktivieren|loeschen)"]},
]
def check_document_completeness(
text: str,
@@ -215,15 +245,36 @@ def check_document_completeness(
elif doc_type in ("agb", "terms", "nutzungsbedingungen"):
checklist = AGB_CHECKLIST
label = "§305ff BGB"
elif doc_type in ("impressum", "imprint"):
checklist = IMPRESSUM_CHECKLIST
label = "§5 TMG / §18 MStV"
elif doc_type in ("cookie",):
checklist = COOKIE_CHECKLIST
label = "§25 TDDDG"
else:
checklist = ART13_CHECKLIST # Default: check as DSE
label = "Art. 13 DSGVO"
present = 0
total = len(checklist)
all_checks: list[dict] = []
for check in checklist:
found = any(re.search(p, text_lower) for p in check["patterns"])
if not found:
match = None
for p in check["patterns"]:
m = re.search(p, text_lower)
if m:
match = m
break
passed = match is not None
matched_text = ""
if match:
start = max(0, match.start() - 30)
end = min(len(text_lower), match.end() + 30)
matched_text = text_lower[start:end].strip()
present += 1
else:
findings.append({
"code": f"DSI-MISSING-{check['id'].upper()}",
"severity": check.get("severity", "MEDIUM"),
@@ -236,8 +287,14 @@ def check_document_completeness(
"doc_type": doc_type,
"check_id": check["id"],
})
else:
present += 1
all_checks.append({
"id": check["id"],
"label": check["label"],
"passed": passed,
"severity": check.get("severity", "MEDIUM"),
"matched_text": matched_text,
})
# Always add summary finding (even at 100% — needed for completeness tracking)
if total > 0:
@@ -252,6 +309,7 @@ def check_document_completeness(
"doc_title": doc_title,
"doc_url": doc_url,
"doc_type": doc_type,
"all_checks": all_checks,
})
return findings