1. Email report now renders as styled HTML (matching frontend design):
- Progress bars (green=completeness, blue=correctness)
- Hierarchical L1→L2 check display
- Red hint boxes under failed checks explaining what to fix
- Matched text evidence for passed checks
2. Section splitter deduplicates: two "Social Media" headings on the
same page are merged into one section instead of creating duplicates.
3. Extracted report builder to agent_doc_check_report.py (175 LOC)
to keep routes file under 500 LOC (386 LOC).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fixes based on manual verification of all 30 failed checks:
1. Cookie table: recognize "folgende cookies" + column headers as text
2. Cookie names: add JSESSIONID, cookieinfo, et_id, BT_* patterns
3. Essential justified: match "sitzung zuordnen", "betrieb der website"
4. Social bookmarks: recognize as 2-click alternative
5. DSFA plural: "kanaelen" now matches alongside "kanal"
6. Section splitter: skip-headings no longer lose subsequent text
(Risikoabwaegung section was cut from DSFA, losing risk scores)
7. Cookie legal basis: accept Art. 6(1)(f) in cookie context
Reduces false positives from 7 to ~1-2 for IHK Konstanz test case.
Ground truth table: zeroclaw/docs/ground-truth-ihk-konstanz.md
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>
'Datenschutzfolgeabschätzung...Social Media' was matching as social_media
(Art. 26) instead of dsfa (Art. 35) because the social_media pattern
'datenschutz.*social media' matched first.
Fixed: DSFA patterns checked before social_media patterns.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
8 false positives from generic canonical_controls. Regex checks (9+5)
are accurate. Re-enable when ~80 specific doc-check controls exist.
See INSTRUCTION-master-controls-for-doc-check.md
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Complete rewrite of rag_document_checker.py:
- Queries canonical_controls table (294K controls, 10K data_protection)
- Filters by category + title keywords per document type
- Uses test_procedure field as actual check instructions
- Regex pre-check extracts key terms from procedure → fast match
- LLM fallback only for regex misses (saves tokens)
- /no_think prefix for direct JSON output
SQL approach advantages:
- Structured data with test_procedure, pass_criteria, fail_criteria
- Category filtering (data_protection, compliance, governance)
- No Qdrant API key issues
- Controls are actual check criteria, not general legal texts
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Current 144K controls are general legal texts, not specific check criteria.
RAG integration code stays (rag_document_checker.py), just disabled in
the doc-check endpoint. Re-enable when G1-G4 block is complete and
25K Master Controls with Decision Trace are available.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New module: rag_document_checker.py
- Searches RAG (Qdrant) for controls relevant to document type
- Filters by regulation (DSGVO Art.13, TDDDG §25, BGB §355 etc.)
- LLM (Qwen 3.5:35b) verifies each control against document text
- Returns fulfilled/missing with evidence text + severity
- Supports: DSI, Cookie, Impressum, Widerruf, AGB, DSFA, AVV, Loeschkonzept
Integration in doc-check endpoint:
- Regex checklist runs first (fast, deterministic)
- RAG checks run after (semantic, catches what regex misses)
- Both results combined in single response
LLM prompt returns JSON: {fulfilled, evidence, issue, severity}
Think-tags stripped, JSON extracted from response.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Only Cookie and Widerruf sections are checked as separate documents.
Social Media, DSFA, Betroffenenrechte, Dienste von Drittanbietern are
part of the parent DSI and no longer generate false findings.
Added PLAN-rag-document-check.md for Phase 2:
- RAG-based checks with document-type-specific Controls
- DSFA checklist (Art. 35 + Landes-Listen)
- AVV checklist (Art. 28)
- Reference detection (sub-doc → parent doc)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a single URL contains multiple document sections (e.g. IHK DSI page
with Cookies, Social Media, Dienste von Drittanbietern), the system now:
1. Extracts full page text (main document check as before)
2. Splits text at heading boundaries (short uppercase lines)
3. Classifies each section: Cookie→cookie checklist, Social Media→DSI etc.
4. Runs type-specific checklist per section
5. Returns all results: main doc + sub-sections
Section type detection via SECTION_TYPE_MAP patterns:
- 'Cookie*' → §25 TDDDG checklist
- 'Dienste von Drittanbietern' → DSI checklist
- 'Social Media' → DSI checklist (Art. 26 joint controllership)
- 'Widerrufsrecht' → §355 BGB checklist
- 'Impressum' → §5 TMG checklist
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>
Two fixes:
1. consent-tester: full_text truncation raised from 10,000 to 50,000 chars
(IHK Internetangebot has ~50K chars, Beschwerderecht was after 10K cutoff)
2. Backend: dse_text now combines Playwright HTML + ALL DSI discovery texts
for mandatory content checking. Previously only used first 8K chars from
one source, missing Verantwortlicher/DSB that were in DSI documents.
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>
Fundamental fix: scans now run asynchronously with progress polling.
Backend:
- POST /scan starts background task, returns scan_id immediately
- GET /scan/{scan_id} returns status + progress + result when done
- 7 progress steps shown: Website scan, DSI discovery, DSE analysis,
SOLL/IST comparison, corrections, report, email
- In-memory job store (dict with scan_id → status/result)
- No timeout limits on scan duration
Frontend:
- POST starts scan, receives scan_id
- Polls GET every 5 seconds (max 120 attempts = 10 min)
- Shows live progress message during scan
- Displays result when completed, error when failed
Proxy:
- POST timeout reduced to 30s (just starts the job)
- GET timeout 10s (just status check)
- No more 504/connection-dropped errors
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bug 1: max_pages was hardcoded to 15 in backend call — raised to 50
Bug 2: DSI documents checked against text_preview (500 chars) — now uses
full_text (10,000 chars) for Art. 13 mandatory field checks
Bug 3: DSE text not found when Playwright misses DSE page — now falls
back to DSI Discovery full_text as second source
Bug 4: Backend timeout 120s too short for 50 pages — raised to 300s
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
NameError: name 're' is not defined at line 146 — the import was
accidentally removed when extracting helper functions to agent_scan_helpers.py.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
NameError: name 're' is not defined at line 146 — the import was
accidentally removed when extracting helper functions to agent_scan_helpers.py.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New DSRArt11Service: handles rejection with proper legal basis,
automated email notification to requester explaining Art. 11
- POST /dsr/{id}/reject-art11 endpoint
- ActionButtons.tsx: "Nicht identifizierbar (Art. 11)" button
shown when identity is not yet verified
- Also fixes: DSR export type-cast rollback handling
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- DSRExportService: aggregates all CMP data about a user from
Banner Consents, Einwilligungen, Audit Trail, DSR History
- GET /dsr/{id}/export-user-data?format=json|csv|pdf endpoint
- PDF: A4 reportlab with 4 sections (Consents, Einwilligungen,
Audit-Trail, DSR-Anfragen) + cover page
- CSV: BOM-encoded for Excel with flattened data rows
- JSON: structured export with all data categories
- ActionButtons.tsx: PDF/JSON/CSV export buttons now functional
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Migration 115: compliance_role_training_mapping table (org roles → training codes)
- TrainingLinkService: queries training_modules/matrix/assignments to find gaps
per person and role. Gracefully degrades when Go training tables don't exist yet.
- document_review_routes: 2 new endpoints (training-requirements, training-gaps)
- _notify_approval() now checks training gaps and sends emails to persons
with outstanding modules, linking to /sdk/training/learner
[migration-approved]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Migration 111: 3 new tables (org_roles, document_reviews, document_role_mapping)
with seed data mapping all 71 doc types to 7 compliance roles
- org_role_routes.py: CRUD for roles, seed defaults, test email, mapping API
- document_review_routes.py: Review lifecycle (create→send→approve/reject)
with approval notification to all affected roles
- Migration 112: SOP template (ISO 9001 structure, 21 placeholders)
- Added standard_operating_procedure to TemplateType, doc-labels, presets
[migration-approved]
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fundamental architecture fix: data processing happens through APIs/scripts/
cookies — NOT through visible page text. A news site about healthcare does
NOT process health data.
Before: Qwen reads website text → guesses "health_data: true" (WRONG)
After: Google Analytics detected → tracking: true (CORRECT, deterministic)
New flow: detect services from HTML → map service categories to flags →
feed flags into UCCA assessment. No LLM needed for flag extraction.
SERVICE_TO_FLAGS maps categories: tracking→tracking, marketing→marketing+
third_party_sharing, payment→payment_data, heatmap→profiling, etc.
SPECIFIC_SERVICE_FLAGS for Klarna (Art.22), Stripe (US transfer), etc.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Dockerfile: install Playwright AS appuser (not root) so chromium
binary is accessible at runtime. Was causing 500 error.
2. DSE service matching: text-search fallback when LLM extraction fails.
If "etracker" appears in DSE text, mark as documented even without
LLM parsing the service list.
3. CMP skip: consent managers in category "cmp" skipped (not just "other"
with id "cmp").
NOT DEPLOYED — RAG pipeline is running.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New /website-scan endpoint in consent-tester service:
- Real browser renders JavaScript (finds dynamic content)
- Clicks navigation menus (discovers hidden sub-pages like IHK DSB page)
- Follows links within DSE to find regional privacy policies
- Collects rendered HTML for each page (after JS execution)
Backend integration:
- agent_scan_routes tries Playwright first, falls back to httpx
- DSE text and HTML extracted from Playwright-rendered pages
- Service detection runs on rendered HTML (catches JS-loaded scripts)
Also fixes:
- GA regex: G-[A-Z0-9]{8,12} prevents CSS class false positives
- etracker added to service registry
- External page scanning blocked (same-domain only)
- CSS/JS/image files excluded from page list
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase 6: PDF export via WeasyPrint — POST /agent/scans/pdf generates
printable compliance report with findings table, service comparison,
risk badge, and legal disclaimer.
Phase 7: Recurring scans — POST /agent/monitored-urls to add URLs,
POST /agent/run-scheduled triggers all enabled scans (cron/ZeroClaw).
In-memory storage with DB upgrade path.
Phase 8: Multi-website compare — POST /agent/compare with 2-5 URLs,
parallel scanning, comparison table (risk, findings, services, compliance
features per site).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Migration 086: compliance_agent_scans table (findings, services, corrections)
- agent_history_routes.py: POST /scans (save), GET /scans (list), GET /scans/{id}
- Scan results survive page reloads and can be reviewed later
- Phase 10 (Playwright website scanner) added to product roadmap
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- dse_parser.py: HTML → structured sections (heading, number, content, parent)
Uses heading hierarchy (h1-h4) with regex fallback
- dse_matcher.py: matches detected services against DSE sections
Exact name → provider → category matching with insertion point suggestion
- agent_scan_routes: TextReference model in findings (original text,
section, paragraph, correction type, insert_after)
Enables showing: "Google Analytics not found in DSE, insert after
Section 2.4 Cookies und Tracking"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase 0: Qwen extracts 14 structured intake flags (personal_data,
marketing, profiling, ai_usage, etc.) instead of keyword matching.
Fallback to keywords if LLM unavailable. Flags feed into UCCA for
accurate scoring.
Phase 1: Control relevance filter removes false positives.
C_TRANSPARENCY only recommended if AI/ML keywords found in text.
7 control rules with keyword lists + intake flag fallback.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Summary now renders as styled HTML (table layout, colored risk badge,
warning banners) instead of plaintext in <div>
- Tab info text explains scope: "Analysiert nur die eingegebene URL" vs
"Scannt automatisch 5-10 Unterseiten"
- Scan history with findings count badge and page count
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>
SDK LLM chat returns empty content due to Qwen think-mode. Direct Ollama
/api/generate call with stream:false gets the full response including
think tags which we strip.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Benjamin Admin