9 files had conflict markers from the branch merge. All resolved keeping
the feature branch version. Also split agent_scan_routes.py (534→367 LOC)
by extracting Pydantic models to agent_scan_models.py.
[guardrail-change]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Impressum-Check: Toggle activates 75 Impressum MCs via agent
- Banner-Check: Toggle runs additional cookie doc-check (381 MCs)
after the Playwright banner test completes
- Both use the same use_agent flag through doc-check endpoint
Green pill button consistent across all tabs:
'KI-Agent aus' / 'KI-Agent aktiv (X MCs)'
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Green pill button: 'KI-Agent aus' / 'KI-Agent aktiv (1.874 MCs)'
Toggles use_agent flag which is passed through the full chain:
Frontend → DocCheckRequest → _run_doc_check → _check_single_document
→ check_document_with_controls(use_agent=True)
→ ComplianceAgent with tool calling
Default: OFF (deterministic regex). User can enable per scan.
Also works via env var COMPLIANCE_USE_AGENT=true for always-on.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Both DocCheckTab and BannerCheckTab now:
- Store full scan results per history entry in localStorage
- History entries are clickable — loads the saved result immediately
- No need to re-scan to see old results
- Fallback to last result if specific entry not found
- Banner-Check sends HTML email report to mailpit
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. localStorage Persistenz: URL, letztes Ergebnis, Historie (30 Eintraege)
2. Historie: Zeigt URL, Datum, Provider, Violations, Prozent
3. Letztes Ergebnis bleibt nach Tab-Wechsel/Reload sichtbar
4. E-Mail-Report: HTML-formatiert mit Violations + Hints an mailpit
5. Email-Status Anzeige im Frontend
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Explains why companies must buy norms their own employees wrote,
and the 2024 EuGH ruling that harmonised standards are EU law
and must be freely accessible.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The /banner-check endpoint is synchronous (Playwright completes in
<30s and returns result directly). Removed unused async polling loop
that would never match since no scan_id is returned.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Explains current status: no harmonised standards published under
(EU) 2023/1230 yet, ~800 from old directive still valid. Timeline
from June 2023 to January 2027 full application.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
5 FAQ items covering:
- What happens when companies are sued (4 enforcement paths)
- How document checks work (3-step process)
- Which document types are checked (7 types, 138 checks)
- How reliable results are (0 false positives, LLM verification)
- What GDPR violations cost in practice (fine tiers + examples)
Includes EuGH rulings (C-300/21, C-319/20), CNIL fine examples,
and practical cost ranges.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New "Banner-Check" tab with:
- URL input → Playwright 3-phase test (before/reject/accept)
- Shield icon + provider detection
- Progress bar with pass/fail percentage
- 3-phase summary (cookies + scripts per phase)
- Violations (red) and passes (green) in structured list
Backend: new POST /api/compliance/agent/banner-check endpoint
that proxies to consent-tester:8094/scan.
Next step: Upgrade banner checks to L1/L2 format with expert
hints (same quality as document checks).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each check now has a "hint" field explaining what is missing and
what the customer should do to fix it. Hints are shown in the
frontend below failed checks in red text.
Examples:
- "Bei Verarbeitung auf Basis von Art. 6(1)(f) muss dokumentiert
werden, warum Ihr berechtigtes Interesse die Rechte der
Betroffenen ueberwiegt."
- "Die ladungsfaehige Anschrift fehlt. Erforderlich: Strasse,
Hausnummer, PLZ und Ort."
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
L2 checks were hidden behind a second click on L1 items.
Now they render inline below their L1 parent, always visible
when the document card is expanded.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
DSI Dedup (consent-tester):
- Only H1/H2 headings count as documents (not H3/H4 sub-sections)
- Sub-sections (Cookies, Betroffenenrechte, Social Media) are part of
parent document's full text, not separate documents
- Reduces IHK result from 30 to ~11 real documents
Backend (agent_scan_routes):
- ScanFinding gets doc_title field linking each finding to its document
- doc_title set when creating DSI findings for document attribution
Frontend (ScanResult.tsx):
- 3 sections: Services table, Document cards, General findings
- Documents: expandable cards with completeness bar (green/yellow/red)
- Findings grouped under their parent document
- Each card shows: title, word count, findings count, % completeness
- Findings without doc_title go to "Allgemeine Findings" section
Email Summary (agent_scan_helpers):
- Findings listed under their parent document
- General findings in separate section
- No more flat mixed list
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Shows: Impressum link ✓/✗, DSE link ✓/✗, plus violation cards for
wrong DSE consent wording, pre-ticked checkboxes, dark patterns,
missing reject button, no settings re-access.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests each consent category in isolation:
- Phase D: Only "Statistics" enabled → checks if only analytics loads
- Phase E: Only "Marketing" enabled → checks if only ads load
- Phase F: Only "Functional" enabled → checks no tracking loads
CMP-specific category selectors for Cookiebot, OneTrust, Usercentrics,
Didomi. Generic fallback via toggle/checkbox keyword detection.
SERVICE_CATEGORY_MAP maps 35+ services to expected categories.
Violations: "Facebook Pixel loads with only Statistics enabled" = miscategorization.
Frontend: category test results shown below Phase A-C with
per-category violation cards.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Third tab "Cookie-Test" in Compliance Agent:
- Phase A: Before consent (tracking without permission)
- Phase B: After rejection (CRITICAL if tracking persists)
- Phase C: After acceptance (undocumented services)
- CMP badge (Didomi, OneTrust, etc.)
- Violation cards with severity badges and legal references
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Shows for each finding:
- Original text block from DSE (or "missing" indicator)
- Position: section heading, number, parent section, paragraph index
- Correction: insert/append/replace with copy button
Falls back to plain correction view if no text reference available.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Email now lists all scanned URLs with checkmark/cross status.
Frontend shows collapsible "X Seiten gescannt — Details anzeigen".
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Scan public website for cancellation button, imprint, privacy link, cookie consent
- Generate follow-up questions when checks can't be verified without login
- User answers "no" → finding with legal basis is added to results
- Frontend: FollowUpQuestions component with Ja/Nein buttons
- Sidebar: "Compliance Agent" entry added under KI-Compliance
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Benjamin Admin