Commit Graph

3 Commits

Author SHA1 Message Date
Benjamin Admin 0148d55304 feat(iace): overnight NASA NTRS failure-knowledge harvester
Unattended, bounded (MAX_DOCS), resumable pipeline: NTRS lessons-learned →
public-reuse licence gate → download PDF → pdftotext / abstract / vision-OCR
fallback → Ollama tuple extraction → results.jsonl + bp_iace_failure_kb,
tagged verified=false + provenance for morning review. Never touches the
curated Go set.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-13 00:36:44 +02:00
Benjamin Admin 755ea44343 feat(iace): refresh architecture tab + data-flow diagram + E1 ingest script
- architecture.go: DataSources now reflect the real ingested set (ESAW 2023,
  BLS CFOI, OSHA OTM, PRISM, cobot CC-BY, HSE) with their RAG collections;
  risk stage cites BLS + the searchable RAG layer; matrix stage now mentions
  the distance-benchmark dimension.
- Architektur & Datenfluss tab: new DataFlowDiagram — 4 lanes (input →
  knowledge/RAG-evidence → deterministic engine → outputs) with live counts.
- scripts/ingest_iace_kb.sh: idempotent E1 ingest — creates the 2 collections
  and uploads the 6 datasources docs against a configurable RAG_URL (for prod
  Qdrant), with retry.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-12 09:18:03 +02:00
Benjamin Admin 005a2ed711 feat(iace): generic cross-domain leak gates + norm vocab reconciliation
- Domain-gate ~15 foreign machine classes (pool, amusement, paint booth,
  tank farm, reactor, lathe/chips, saw, film/carton, robot, mobile cab,
  asbestos, playground swing) in pattern_domain_gates.go so ungated hazard
  patterns stop leaking into unrelated machines; matching emit keywords
  added in keyword_dictionary.go (gate+emit share one vocabulary).
- Extend the cross-domain precision guard to 6 machine classes (press,
  cobot, motor, welding + the 2 GTs) with per-case homeDomains, so a
  machine's own domain terms are never flagged. GT coverage stays 100%.
- Reconcile the fine-grained norm machine-type vocabulary (455 keys) with
  the 68 canonical dropdown keys via canonicalMachineType() family folding
  in matchNorm — welding 0->17, robotics_cobot 0->6, press 8->13,
  circular_saw 1->35 machine-specific C-norms. Pattern gating left strict.
- Fix initialize?force=true summary index-shift that mislabeled counts
  (reported matched-patterns as "hazards"); now uses named step vars.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-10 22:29:10 +02:00