feat(batch-agent): add E2E evaluation harness with Langfuse integration

- eval/mock_executor.py: intercepts execute_on_client, serves fixture
  files from disk, records all mutations (insert/update/delete)
- eval/config.py: YAML fixture loader with prompt variants, expected
  results, seed records, model overrides
- eval/scorer.py: FieldMatchScorer (fuzzy title match, per-field
  accuracy, precision/recall/F1) + LLMJudgeScorer (semantic eval)
- eval/langfuse_eval.py: sync fixtures to Langfuse datasets, create
  dataset runs, post scores, link traces to runs
- eval/runner.py: orchestrates fixture → mock → agent pipeline →
  scoring → Langfuse reporting
- eval/cli.py: CLI (python -m eval run/list/sync) with --models,
  --variants, --fixture, --no-judge flags
- eval/fixtures/: example Italian freelance scenario with 3 prompt
  variants (baseline, detailed_italian, minimal)

services/batch-agent/eval/fixtures/sample_files/invoices/meeting_ecommerce.md

@@ -0,0 +1,25 @@
+# Meeting Notes - Kickoff Progetto E-Commerce
+
+**Data:** 10 Marzo 2026
+**Partecipanti:** Marco R., Giulia T., Cliente (FashionStore srl)
+
+## Decisioni prese
+
+1. **Piattaforma**: Next.js + Stripe per i pagamenti
+2. **Timeline**: MVP pronto entro 30 aprile 2026
+3. **Budget**: €12.000 totale, €4.000 anticipo già ricevuto
+
+## Action items
+
+- [ ] Marco: preparare wireframe homepage entro 14 marzo — ALTA PRIORITÀ
+- [ ] Giulia: setup progetto Next.js e configurare CI/CD — media priorità
+- [ ] Marco: ricerca plugin Stripe per gestione abbonamenti — bassa priorità
+- [x] Giulia: inviare contratto firmato al cliente — COMPLETATO
+
+## Note aggiuntive
+
+Il cliente vuole un design minimalista, ispirato a Zara.com.
+Colori primari: nero, bianco, oro.
+Font: Inter per body, Playfair Display per headings.
+
+Prossimo meeting: 24 marzo 2026 ore 15:00.