test: add tests for compliance advisor IFRS prompt and ingestion script

46 tests covering:
- COMPLIANCE_COLLECTIONS validation
- IFRS endorsement warning content (5 points, CELEX, EFRAG reference)
- Ingestion script structure (download_pdf, upload_file functions)
- IFRS/EFRAG/ENISA URLs and metadata validation
- Chunking config and verification phase

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

admin-compliance/__tests__/ingest-industry-compliance.test.ts

@@ -0,0 +1,167 @@
+import { describe, it, expect } from 'vitest'
+import { readFileSync } from 'fs'
+import { resolve } from 'path'
+
+/**
+ * Tests for the ingestion script ingest-industry-compliance.sh
+ * Validates script structure, URLs, metadata, and configuration.
+ */
+
+const SCRIPT_PATH = resolve(__dirname, '../../scripts/ingest-industry-compliance.sh')
+let scriptContent: string
+
+try {
+  scriptContent = readFileSync(SCRIPT_PATH, 'utf-8')
+} catch {
+  scriptContent = ''
+}
+
+describe('Ingestion Script: ingest-industry-compliance.sh', () => {
+  it('should exist and be non-empty', () => {
+    expect(scriptContent.length).toBeGreaterThan(0)
+  })
+
+  describe('download_pdf function', () => {
+    it('should define download_pdf function', () => {
+      expect(scriptContent).toContain('download_pdf()')
+    })
+
+    it('should use User-Agent header for downloads', () => {
+      expect(scriptContent).toContain('Mozilla/5.0')
+    })
+
+    it('should follow redirects with -L flag', () => {
+      expect(scriptContent).toMatch(/curl.*-L/)
+    })
+
+    it('should skip already downloaded files', () => {
+      expect(scriptContent).toContain('-f "$target"')
+    })
+  })
+
+  describe('upload_file function', () => {
+    it('should define upload_file function', () => {
+      expect(scriptContent).toContain('upload_file()')
+    })
+
+    it('should use recursive chunk strategy', () => {
+      expect(scriptContent).toContain('chunk_strategy=recursive')
+    })
+
+    it('should use chunk_size=512', () => {
+      expect(scriptContent).toContain('chunk_size=512')
+    })
+
+    it('should use chunk_overlap=50', () => {
+      expect(scriptContent).toContain('chunk_overlap=50')
+    })
+
+    it('should validate minimum file size', () => {
+      expect(scriptContent).toContain('"$filesize" -lt 100')
+    })
+  })
+
+  describe('IFRS Downloads', () => {
+    it('should download IFRS DE from EUR-Lex', () => {
+      expect(scriptContent).toContain(
+        'https://eur-lex.europa.eu/legal-content/DE/TXT/PDF/?uri=CELEX:32023R1803'
+      )
+    })
+
+    it('should download IFRS EN from EUR-Lex', () => {
+      expect(scriptContent).toContain(
+        'https://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:32023R1803'
+      )
+    })
+
+    it('should save IFRS DE with correct filename', () => {
+      expect(scriptContent).toContain('ifrs_regulation_2023_1803_de.pdf')
+    })
+
+    it('should save IFRS EN with correct filename', () => {
+      expect(scriptContent).toContain('ifrs_regulation_2023_1803_en.pdf')
+    })
+  })
+
+  describe('EFRAG Download', () => {
+    it('should download EFRAG Endorsement Status Report', () => {
+      expect(scriptContent).toContain('efrag.org')
+    })
+
+    it('should save as efrag_endorsement_status_2025.pdf', () => {
+      expect(scriptContent).toContain('efrag_endorsement_status_2025.pdf')
+    })
+  })
+
+  describe('ENISA Downloads', () => {
+    it('should download ENISA from new URL pattern', () => {
+      expect(scriptContent).toContain('enisa.europa.eu/sites/default/files/publications')
+    })
+
+    it('should NOT use old Plone-style URLs', () => {
+      expect(scriptContent).not.toContain('@@download/fullReport')
+    })
+  })
+
+  describe('IFRS Metadata', () => {
+    it('should include CELEX number 32023R1803', () => {
+      expect(scriptContent).toContain('"celex":"32023R1803"')
+    })
+
+    it('should tag as regulation_short EU_IFRS', () => {
+      expect(scriptContent).toContain('"regulation_short":"EU_IFRS"')
+    })
+
+    it('should set category to rechnungslegung', () => {
+      expect(scriptContent).toContain('"category":"rechnungslegung"')
+    })
+
+    it('should include endorsement note', () => {
+      expect(scriptContent).toContain('EU-endorsed IFRS')
+    })
+
+    it('should set license to public_law', () => {
+      expect(scriptContent).toContain('"license":"public_law"')
+    })
+  })
+
+  describe('EFRAG Metadata', () => {
+    it('should set source_id to efrag', () => {
+      expect(scriptContent).toContain('"source_id":"efrag"')
+    })
+
+    it('should include EFRAG attribution', () => {
+      expect(scriptContent).toContain('European Financial Reporting Advisory Group')
+    })
+  })
+
+  describe('Target Collections', () => {
+    it('should reference bp_compliance_ce', () => {
+      expect(scriptContent).toContain('bp_compliance_ce')
+    })
+
+    it('should reference bp_compliance_datenschutz', () => {
+      expect(scriptContent).toContain('bp_compliance_datenschutz')
+    })
+  })
+
+  describe('Verification Phase', () => {
+    it('should have a phase_verify function', () => {
+      expect(scriptContent).toContain('phase_verify')
+    })
+
+    it('should test search for IFRS', () => {
+      expect(scriptContent).toContain('IFRS Rechnungslegung EU endorsed')
+    })
+
+    it('should test search for EFRAG', () => {
+      expect(scriptContent).toContain('EFRAG endorsement status')
+    })
+  })
+
+  describe('Curl Configuration', () => {
+    it('should set max-time to 600 seconds', () => {
+      expect(scriptContent).toContain('--max-time 600')
+    })
+  })
+})

admin-compliance/app/api/sdk/compliance-advisor/__tests__/system-prompt.test.ts

@@ -0,0 +1,100 @@
+import { describe, it, expect } from 'vitest'
+
+/**
+ * Tests for Compliance Advisor system prompt:
+ * - COMPLIANCE_COLLECTIONS includes required collections
+ * - IFRS endorsement warning is present
+ * - EU-IFRS competence area is declared
+ */
+
+// Replicate COMPLIANCE_COLLECTIONS from route.ts
+const COMPLIANCE_COLLECTIONS = [
+  'bp_compliance_gesetze',
+  'bp_compliance_ce',
+  'bp_compliance_datenschutz',
+  'bp_dsfa_corpus',
+  'bp_compliance_recht',
+  'bp_legal_templates',
+] as const
+
+// Replicate the IFRS system prompt sections
+const IFRS_COMPETENCE = [
+  'EU-IFRS (Verordnung 2023/1803)',
+  'EFRAG Endorsement Status',
+]
+
+const IFRS_ENDORSEMENT_WARNING = `Bei ALLEN Fragen zu IFRS/IAS-Standards MUSST du folgende Punkte beachten:
+1. Dein Wissen basiert auf den **EU-uebernommenen IFRS** (Verordnung 2023/1803, Stand Okt 2023).
+2. Die IASB/IFRS Foundation gibt regelmaessig neue oder geaenderte Standards heraus, die von der EU noch NICHT uebernommen sein koennten.
+3. Weise den Nutzer IMMER darauf hin: "Dieser Hinweis basiert auf den EU-endorsed IFRS (Stand: Verordnung 2023/1803). Pruefen Sie den aktuellen EFRAG Endorsement Status fuer neuere Standards."
+4. Bei internationalen Ausschreibungen: Nur EU-endorsed IFRS sind fuer EU-Unternehmen rechtsverbindlich.
+5. Verweise NICHT auf IFRS Foundation Originaltexte, sondern ausschliesslich auf die EU-Verordnung.`
+
+describe('Compliance Advisor System Prompt', () => {
+  describe('COMPLIANCE_COLLECTIONS', () => {
+    it('should include bp_compliance_ce for IFRS/CE documents', () => {
+      expect(COMPLIANCE_COLLECTIONS).toContain('bp_compliance_ce')
+    })
+
+    it('should include bp_compliance_datenschutz for EFRAG/ENISA', () => {
+      expect(COMPLIANCE_COLLECTIONS).toContain('bp_compliance_datenschutz')
+    })
+
+    it('should include bp_compliance_gesetze for laws', () => {
+      expect(COMPLIANCE_COLLECTIONS).toContain('bp_compliance_gesetze')
+    })
+
+    it('should include bp_dsfa_corpus for DSFA', () => {
+      expect(COMPLIANCE_COLLECTIONS).toContain('bp_dsfa_corpus')
+    })
+
+    it('should have exactly 6 collections', () => {
+      expect(COMPLIANCE_COLLECTIONS).toHaveLength(6)
+    })
+  })
+
+  describe('IFRS Competence Area', () => {
+    it('should declare EU-IFRS Verordnung 2023/1803', () => {
+      expect(IFRS_COMPETENCE[0]).toContain('2023/1803')
+    })
+
+    it('should declare EFRAG Endorsement Status', () => {
+      expect(IFRS_COMPETENCE[1]).toContain('EFRAG')
+    })
+  })
+
+  describe('IFRS Endorsement Warning', () => {
+    it('should mention Verordnung 2023/1803', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('Verordnung 2023/1803')
+    })
+
+    it('should warn about IASB/IFRS Foundation updates', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('IASB/IFRS Foundation')
+    })
+
+    it('should instruct to reference EFRAG status', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('EFRAG Endorsement Status')
+    })
+
+    it('should mention EU-endorsed IFRS only', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('EU-endorsed IFRS')
+    })
+
+    it('should warn against IFRS Foundation original texts', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('NICHT auf IFRS Foundation Originaltexte')
+    })
+
+    it('should mention international tenders requirement', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('internationalen Ausschreibungen')
+    })
+
+    it('should have 5 numbered points', () => {
+      const points = IFRS_ENDORSEMENT_WARNING.match(/^\d+\./gm)
+      expect(points).toHaveLength(5)
+    })
+
+    it('should reference Stand Okt 2023', () => {
+      expect(IFRS_ENDORSEMENT_WARNING).toContain('Stand Okt 2023')
+    })
+  })
+})