Adds a curated database of safety-relevant features for the major
manufacturers across mechanical/plant engineering, written entirely in
own words with norm anchors. No verbatim manufacturer texts — therefore
no copyright issue:
- Markennennung (§ 23 MarkenG nominative use) is permitted.
- Fakten ueber Produkt-Sicherheitsfunktionen are not protected by § 2
UrhG (only Werke, not facts).
- NormReferences contain only the identifiers (e.g. "EN ISO 13849-1
PLd Kat.3"), never the norm text itself.
Coverage (52 entries across 12 categories):
Industrieroboter (10): FANUC DCS, KUKA SafeOperation, ABB SafeMove,
Yaskawa FSU, Staeubli CS9, Kawasaki Cubic-S, Mitsubishi MELFA,
Universal Robots PolyScope, Doosan PRS, Comau SafeNet
CNC/WZM (8): DMG MORI, Mazak, TRUMPF, Okuma, Hermle, Heidenhain
SPLC, GROB, Heller
Pneumatik (4): Festo, SMC, AVENTICS, Parker
Hydraulik (3): Bosch Rexroth, HAWE, HYDAC
Safety-PLC / Sicherheitstechnik (8): PILZ, SICK, Schmersal, Euchner,
Leuze, Phoenix Contact, Banner, Wieland
Standard-PLC (5): Siemens, Beckhoff, Rockwell, Schneider, B&R
Pressen (3): Schuler, Bruderer, AIDA
Spritzguss (3): Arburg, KraussMaffei, ENGEL
Verpackung (2): Krones, Bosch Packaging/Syntegon
Laser/Schweissen (3): Bystronic, Amada, Fronius
Foerdertechnik (2): Interroll, SEW EURODRIVE
Engine integration:
- LookupManufacturerFeaturesInText() scans the project narrative for
any of the manufacturer aliases (case-insensitive, umlaut-tolerant).
- Init-Handler appends matched feature clarifications to the relevant
hazard's "Mit Anlagenbauer zu klaeren:" block — for the right
HazardCategory only (e.g. FANUC DCS only on mechanical_hazard).
- For a Bremse project narrative mentioning "Fanuc Robodrill", the
engine now adds clarification questions like "Ist DCS am Roboter
konfiguriert?" to relevant mechanical hazards automatically.
Tests: 7 new pin tests — manufacturer count, norm prefixes, FANUC/KUKA
detection in narrative, umlaut robustness (Staeubli vs Staubli).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
ai-compliance-sdk
Go/Gin service providing AI-Act compliance analysis: iACE impact assessments, UCCA rules engine, hazard library, training/academy, audit, escalation, portfolio, RBAC, RAG, whistleblower, workshop.
Port: 8090 → exposed 8093 (container: bp-compliance-ai-sdk)
Stack: Go 1.24, Gin, pgx, Postgres.
Architecture
Clean-arch refactor is complete:
cmd/server/main.go # Thin entrypoint, 7 LOC — wiring in internal/app/
internal/
├── app/
│ ├── app.go # Server initialization + lifecycle
│ └── routes.go # Route registration
├── api/handlers/ # 8 sub-resource handler files:
│ │ # iace_handler_projects, hazards, mitigations,
│ │ # techfile, monitoring, refdata, rag, components
├── iace/ # Store split into 7 files:
│ │ # store_projects, components, hazards,
│ │ # hazard_library, mitigations, evidence, audit
│ └── hazard_library/ # Split into 10 category files
└── ...
See ../AGENTS.go.md for the full convention.
Linting (Phase 5): .golangci.yml added — run golangci-lint run --timeout 5m ./....
Run locally
cd ai-compliance-sdk
go mod download
export COMPLIANCE_DATABASE_URL=...
go run ./cmd/server
Tests
go test -race -cover ./...
golangci-lint run --timeout 5m ./...
Co-located *_test.go, table-driven. Repo layer uses testcontainers-go (or the compose Postgres) — no SQL mocks.
Public API surface
Handlers under internal/api/handlers/ (8 sub-resource files). Health at GET /health. iACE, UCCA, training, academy, portfolio, escalation, audit, rag, whistleblower, workshop subresources. Every route is a contract.
Environment
| Var | Purpose |
|---|---|
COMPLIANCE_DATABASE_URL |
Postgres DSN |
LLM_GATEWAY_URL |
LLM router for rag/iACE |
QDRANT_URL |
Vector search |
Don't touch
DB schema. Hand-rolled migrations elsewhere own it.