Files
breakpilot-compliance/zeroclaw
Benjamin Admin 8af9584d09
CI / detect-changes (pull_request) Failing after 5s
CI / branch-name (pull_request) Successful in 2s
CI / guardrail-integrity (pull_request) Failing after 4s
CI / secret-scan (pull_request) Failing after 4s
CI / dep-audit (pull_request) Failing after 2s
CI / sbom-scan (pull_request) Failing after 2s
CI / build-sha-integrity (pull_request) Failing after 3s
CI / validate-canonical-controls (pull_request) Failing after 3s
CI / loc-budget (pull_request) Has been skipped
CI / go-lint (pull_request) Has been skipped
CI / python-lint (pull_request) Has been skipped
CI / nodejs-lint (pull_request) Has been skipped
CI / nodejs-build (pull_request) Has been skipped
CI / test-go (pull_request) Has been skipped
CI / iace-gt-coverage (pull_request) Has been skipped
CI / test-python-backend (pull_request) Has been skipped
CI / test-python-document-crawler (pull_request) Has been skipped
CI / test-python-dsms-gateway (pull_request) Has been skipped
test(dse): adopt canonical v3 tests + criteria/GT/validation
Replace the reconstructed test_dse_agent.py with the canonical version and add
the companion unit tests (classification_gate, embedding_recall) covering the
recovered v3 modules. Include the curated DSE criteria backup + changelog
(legal-note rationale per control), the v1 validation writeup, and the
multi-company DSE ground-truth fulltexts (elli/eto/mercedes/safetykon) used
for threshold calibration.

18 DSE tests green offline (DB/embedding/LLM stubbed).

dev-only, no deploy.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-21 12:35:16 +02:00
..

ZeroClaw Compliance Agent Demo

Autonomer Compliance-Agent der Web-Dokumente (Cookie-Banner, Datenschutzerklaerungen) analysiert und die Ergebnisse an die zustaendige Rolle weiterleitet.

Architektur

ZeroClaw Agent (Rust, Mac Mini)
  │
  ├── LLM: Qwen 3.5:35b-a3b (Ollama, localhost:11434)
  │
  ├── Compliance SDK (Go/Gin, localhost:8093)
  │   ├── /sdk/v1/llm/chat         → Dokumentklassifizierung
  │   ├── /sdk/v1/ucca/assess      → Risikobewertung
  │   └── /sdk/v1/ucca/escalations → Eskalation + Rollenzuweisung
  │
  ├── Backend (Python/FastAPI, localhost:8002)
  │   └── /api/compliance/agent/notify → Email-Benachrichtigung
  │
  └── Mailpit (SMTP localhost:1025, Web localhost:8025)
      └── Fiktive Email-Zustellung

Voraussetzungen

  • ZeroClaw v0.7.3+ (brew install zeroclaw)
  • Ollama mit qwen3.5:35b-a3b Modell
  • Alle Compliance-Services laufen (SDK, Backend, Mailpit)

Demo ausfuehren

# 1. ZeroClaw mit Ollama verbinden (einmalig)
zeroclaw onboard --quick --provider ollama --model qwen3.5:35b-a3b

# 2. SOP ausfuehren
zeroclaw agent -m "Analysiere die Datenschutzerklaerung von https://www.google.com/intl/de/policies/privacy/"

# 3. Ergebnis pruefen
open http://localhost:8025  # Mailpit Web-UI

E2E Test

bash zeroclaw/tests/test_sop_workflow.sh

SOP-Workflow (6 Schritte)

  1. Fetch — URL holen, HTML strippen
  2. Classify — Dokumenttyp bestimmen (privacy_policy, cookie_banner, etc.)
  3. Assess — DSGVO-Risikobewertung via UCCA
  4. Summarize — Manager-Report auf Deutsch
  5. Assign — Zustaendige Rolle bestimmen (E0-E3 Mapping)
  6. Notify — Email an DSB/Teamleitung senden