Three coupled pieces of work, all landing the same PoC:
1. Backend gap-review endpoint (Task #7)
- internal/api/handlers/iace_handler_gap_review.go:
POST /projects/:id/llm-gap-review
feeds Limits-Form + current hazards + current mitigations to
the configured LLM (Qwen / Claude / OpenAI via ProviderRegistry),
parses a JSON suggestion list, filter+stamps confidence, falls
back to a static checklist when LLM is unavailable.
- Adopt step is NOT in this endpoint by design — the user clicks
Adopt in the frontend which calls the existing CreateHazard /
CreateMitigation handlers so provenance flows through the normal
audit trail.
2. Frontend modal + button (Task #8)
- app/sdk/iace/[projectId]/hazards/_components/LLMGapReviewModal.tsx:
reusable modal that POSTs the gap-review endpoint, renders
suggestions with Adopt/Reject UX, shows confidence + norm refs,
source-stamp llm_gap_review vs fallback_static.
- hazards/page.tsx: indigo "KI-Gap-Review" button next to the
existing "Eigene Gefaehrdung" button + modal mount.
3. Tech-File sources appendix (Task #29 — Stufe 4)
- internal/iace/document_export_sources.go: new pdfSourcesAppendix
method appended to ExportPDF. Groups cited norms by license rule
(R1 OSHA/EU-Recht / R3 BreakPilot patterns / R3 DIN-EN-ISO
identifier-only) and emits the legally required statement that
pauschal Impressum-Hinweise nicht ausreichen.
- extractCitedNorms() scans hazard/mitigation text for EN/ISO/IEC/
DIN identifiers in a narrow grammar so prose isn't turned into
spurious citations.
Bonus refactor:
- internal/app/routes.go reached the 500-LOC hard cap when the new
llm-gap-review route was added. Extracted registerIACERoutes into
routes_iace.go (136 LOC). Same wiring, no behaviour change.
Three of the four Attribution-Renderer stages (1, 2, 4) now produce
real output. Stufe 3 ships as <SourceBadge> + <LicenseModuleBanner>
already (commits dfac940 + b9e3eea earlier in this branch).
The PoC is intentionally conservative: every LLM-Suggestion stays
unverbindlich until a human clicks Adopt, and Adopt goes through the
existing normal CreateHazard/CreateMitigation flow (not yet wired in
this commit — separate iteration). The endpoint, modal and provenance
chain are in place for the next iteration to wire Adopt → write path.
- Erklaerteil-Template fuer Risikobeurteilungen (risk_assessment_template.go)
in PDF-Export, Markdown-Export und Frontend ReportPrintView eingebaut
- Ground Truth Benchmark-System: Datenmodell, Fuzzy-Matching-Engine,
3 API Endpoints (import-gt, benchmark, benchmark/summary)
- Frontend Benchmark-Tab mit Score-Cards, Kategorie-Breakdown,
Hazard-Vergleichstabelle (Zugeordnet/Fehlend/Extra), Business Impact
- Erster Benchmark: 13.3% Coverage (Baseline) gegen 60 GT-Eintraege
- Dedup-Fix: seenCat[cat] -> seenCatZone[cat+zone] erlaubt mehrere
Gefaehrdungen pro Kategorie an verschiedenen Gefahrenstellen
- Komponenten-spezifische Hazard-Namen und Zone-basierte Zuordnung
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Each of the four oversized files (training/store.go 1569 LOC, ucca/rules.go 1231 LOC,
ucca_handlers.go 1135 LOC, document_export.go 1101 LOC) is split by logical group
into same-package files, all under the 500-line hard cap. Zero behavior changes,
no renamed exported symbols. Also fixed pre-existing hazard_library split (missing
functions and duplicate UUID keys from a prior session).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Benjamin Admin