c28c5329587e10f1031a328c56f8a654b32d9ad1
6 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
c28c532958 |
feat(ai-sdk): demote superseded pre-eu-v1 sources in authority rerank
CI / detect-changes (pull_request) Successful in 18s
CI / branch-name (pull_request) Successful in 1s
CI / guardrail-integrity (pull_request) Successful in 14s
CI / secret-scan (pull_request) Successful in 16s
CI / dep-audit (pull_request) Failing after 1m3s
CI / sbom-scan (pull_request) Failing after 1m8s
CI / build-sha-integrity (pull_request) Successful in 16s
CI / validate-canonical-controls (pull_request) Successful in 14s
CI / loc-budget (pull_request) Successful in 24s
CI / go-lint (pull_request) Successful in 57s
CI / python-lint (pull_request) Failing after 20s
CI / nodejs-lint (pull_request) Failing after 1m13s
CI / nodejs-build (pull_request) Successful in 3m9s
CI / test-go (pull_request) Successful in 1m3s
CI / iace-gt-coverage (pull_request) Successful in 26s
CI / test-python-backend (pull_request) Successful in 36s
CI / test-python-document-crawler (pull_request) Successful in 20s
CI / test-python-dsms-gateway (pull_request) Successful in 18s
The old pre-eu-v1 corpus chunks (un-annotated CRA/AI Act/DORA/NIS2/DSGVO duplicates + the old Machinery Directive and its guide) are tagged status=superseded / use_for_primary=false in the vector store. Honor that in the rerank: a superseded result takes a fixed penalty so the eu-v1 norm wins default questions, while the old source stays in the pool (demoted, not hidden) and remains findable for history / transition questions. Verified on dev: "CRA Sicherheitsupdates" now returns CRA Anhang I (eu-v1) at #1 instead of an un-annotated old chunk; MaschinenVO outranks the old Machinery Directive/guide; superseded chunks remain retrievable lower down. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
|
989d9f6f91 |
feat(ai-sdk): citation-graph assessment + opt-in graph expansion (Phase 2)
CI / detect-changes (pull_request) Successful in 14s
CI / branch-name (pull_request) Successful in 1s
CI / guardrail-integrity (pull_request) Successful in 16s
CI / secret-scan (pull_request) Successful in 18s
CI / dep-audit (pull_request) Failing after 1m2s
CI / sbom-scan (pull_request) Failing after 1m10s
CI / build-sha-integrity (pull_request) Successful in 13s
CI / validate-canonical-controls (pull_request) Successful in 14s
CI / loc-budget (pull_request) Successful in 23s
CI / go-lint (pull_request) Successful in 50s
CI / python-lint (pull_request) Failing after 18s
CI / nodejs-lint (pull_request) Failing after 1m8s
CI / nodejs-build (pull_request) Successful in 3m7s
CI / test-go (pull_request) Successful in 1m6s
CI / iace-gt-coverage (pull_request) Successful in 26s
CI / test-python-backend (pull_request) Successful in 33s
CI / test-python-document-crawler (pull_request) Successful in 21s
CI / test-python-dsms-gateway (pull_request) Successful in 21s
Add an `assessment` object to the legal RAG search response: primary norm, connected norms (from the citation graph references_out/in of the primary), cross_regime, human_review_flag, a norm-level winner_margin and a short reasoning string. The margin is computed over DISTINCT norms, so a long article split into several chunks no longer fabricates uncertainty. The per-result schema stays frozen — graph fields are internal (json:"-"). Also wire optional citation-graph expansion (RAG_GRAPH_EXPANSION=true, default off): top hits pull their referenced norms into the candidate pool via the precise edge (e.g. Art. 13 CRA -> Anhang I). Measured to add no rank gain over the existing binding-law augmentation, with +1 Qdrant call per search and reverse-edge fan-out risk, so it ships off-by-default as a recall safety net. The graph EXPLAINS retrieval (assessment), it does not expand it by default. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
|
a1f425d43a |
feat(ai-sdk): authority-aware re-ranking for legal RAG (Phase 1) (#31)
CI / detect-changes (push) Successful in 8s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / secret-scan (push) Has been skipped
CI / dep-audit (push) Has been skipped
CI / sbom-scan (push) Has been skipped
CI / build-sha-integrity (push) Successful in 5s
CI / validate-canonical-controls (push) Successful in 4s
CI / loc-budget (push) Successful in 28s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Has been skipped
CI / test-go (push) Successful in 58s
CI / iace-gt-coverage (push) Successful in 16s
CI / test-python-backend (push) Has been skipped
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped
|
||
|
|
017c9b3c12 |
feat(advisor): Legal-RAG Zitier-Metadaten — ai-sdk + Advisor/Drafting lesen article_label
ai-sdk (legal_rag_client/scroll/types) liest die gepinnten Spec-Felder
article_label/regulation_code/article/paragraph/sub/citation_style/is_recital
mit Fallback auf alt-ingestierte Chunks (regulation_id, section); neuer getBool-Helfer.
Advisor + Drafting-Engine bilden die Quellenzeile primaer aus article_label
("BDSG § 38 Abs. 1"), sonst aus den strukturierten Feldern. 17 Tests gruen, tsc sauber.
Vertrag: docs-src/development/rag_reingest_spec.md (§2/§7). Deploy an den Re-Ingest
gekoppelt — neue Felder sind bis dahin leer (graceful Fallback).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|
|
2e29b611c9 |
feat(iace): Phase 1 — Haftungs-Fixes, Massnahmen-Verkabelung, Explainability Engine
Phase 1A — Haftungs-kritische Fixes: - SIL/PL-Badges als "Vorab-Einschaetzung" mit Tooltip gekennzeichnet - Coverage-Disclaimer in CE-Akte, Projekt-Uebersicht und Print-Export - Norm-Referenzen: 42 Kapitelverweise durch Themen-Deskriptoren ersetzt Phase 1B — Massnahmen-Verkabelung: - 16 neue Massnahmen (M201-M216) fuer bisher unabgedeckte Kategorien (communication_failure, hmi_error, firmware_corruption, maintenance, sensor_fault, mode_confusion) - Kategorie-Fallback im Initialize-Endpoint: ordnet Massnahmen aus der Bibliothek automatisch per HazardCategory zu (max 8 pro Kategorie) - Total: 225 → 241 Massnahmen, 0 Kategorien ohne Massnahmen Phase 1C — Explainability Engine: - MatchReason Struct in PatternMatch (type, tag, met) - Pattern Engine schreibt fuer jeden Match strukturierte Begruendungen - Frontend zeigt "Erkannt weil: Komponente X, Energie Y, Kein Ausschluss Z" Weitere Aenderungen: - BAuA/OSHA Regulatory Hints: 3 Enrich-Endpoints (per Hazard, per Measure, Batch) - Dokumente-Tab in IACE-Bibliothek (36.708 Chunks aus Qdrant) - Varianten-UX: Basis-Projekt-Summary auf Varianten-Seite - Projekt-Initialisierung: POST /initialize kettet Parse→Komponenten→Patterns→Hazards→Massnahmen→Normen - 18 pre-existing TS-Fehler gefixt, Route-Konflikt behoben - Component-Library + Measures-Library Tests aktualisiert Tests: Go alle bestanden, TS 0 Fehler, Playwright 141+ bestanden Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
c293d76e6b |
refactor(go/ucca): split policy_engine, legal_rag, ai_act, nis2, financial_policy, dsgvo_module
Split 6 oversized files (719–882 LOC each) into focused files under 500 LOC: - policy_engine.go → types, loader, eval, gen (4 files) - legal_rag.go → types, client, http, context, scroll (5 files) - ai_act_module.go → module, yaml, obligations (3 files) - nis2_module.go → module, yaml, obligations + shared obligation_yaml_types.go (3+1 files) - financial_policy.go → types, engine (2 files) - dsgvo_module.go → module, yaml, obligations (3 files) All in package ucca, zero exported symbol renames, go test ./internal/ucca/... passes. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |