feat(ai-sdk): searchControls — deep dense pull recalls control sources on implementation questions

Measured (raw dense, top-500, "Welche Controls passen zu Security Updates?"):
NIST at dense rank 9 (115 chunks), CRA Annex at rank 8 — both shallow, just below
the client's small top-K, so the rank layer (#38) never saw them. OWASP: absent from
the corpus (separate ingest).

Add searchControls: on an explicit implementation question (queryWantsControls) pull a
deep dense pool (depth 60, no filter), classify each hit's role in code, and keep only
the four control-pool roles (operational/procedural requirement, control standard,
implementation guidance) — no source_role tagging of the corpus. Merge-dedup into the
pool; the existing rerank + applyControlRoles then order them (op_req > procedural >
standard > guidance). So CRA Annex I (operational_requirement) lands Top-1 and NIST
(control_standard) enters Top-3/5, while ENISA stays visible. Norm questions (no control
intent) are untouched.

Tested: isControlPoolRole, controlRoleOf payload classification (NIST/CRA-Annex/DORA).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.gitea/workflows/ci.yaml

@@ -136,12 +136,14 @@ jobs:
     runs-on: docker
     needs: detect-changes
     if: github.event_name == 'pull_request' && needs.detect-changes.outputs.sdk == 'true'
-    container: golangci/golangci-lint:v1.62-alpine
+    container: golangci/golangci-lint:v1.64.8-alpine
     steps:
       - name: Checkout
         run: |
           apk add --no-cache git
-          git clone --depth 1 --branch ${GITHUB_HEAD_REF:-${GITHUB_REF_NAME}} ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git .
+          # Full clone so `main` is a local ref — new-from-merge-base needs the merge base.
+          git clone ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git .
+          git checkout ${GITHUB_HEAD_REF:-${GITHUB_REF_NAME}}
       - name: Lint ai-compliance-sdk
         run: |
           [ -d "ai-compliance-sdk" ] || exit 0

admin-compliance/app/sdk/coverage/_helpers.ts

@@ -46,6 +46,28 @@ export interface CorpusOverview {
   totals: { documents: number; catalog_sources: number }
 }
 
+// --- Ingested legal-corpus structure (from the vector store, via the Go SDK).
+// Shows WHAT each eur-lex act consists of (articles/annexes/recitals), so the
+// ingested corpus is not a black box for developers. ---
+export interface LegalActStructure {
+  regulation_short: string
+  regulation_name: string
+  articles: number
+  annexes: number
+  recitals: number
+  chunks: number
+}
+
+export interface LegalCorpus {
+  regulations: LegalActStructure[]
+  totals: {
+    regulations: number
+    articles: number
+    annexes: number
+    recitals: number
+  }
+}
+
 // --- Korpus-Dokumente: gruppieren nach Art (Gesetz/Leitfaden/Standard/Urteil)
 // + Herausgeber-Familie (DSK, EDPB, OWASP, NIST …). Deterministisch, pure. ---
 interface DocCat {

admin-compliance/app/sdk/coverage/page.tsx

@@ -3,6 +3,7 @@ import Link from 'next/link'
 import {
   type UseCaseRow,
   type CorpusOverview,
+  type LegalCorpus,
   licenseTierBadgeClass,
   commercialBadgeClass,
   groupUseCases,
@@ -11,28 +12,46 @@ import {
 
 const BACKEND_URL =
   process.env.COMPLIANCE_BACKEND_URL || 'http://backend-compliance:8002'
+// The legal-corpus structure comes from the Go SDK (it owns the vector store).
+const SDK_URL = process.env.SDK_URL || 'http://ai-compliance-sdk:8090'
 
 export const dynamic = 'force-dynamic'
 
+// Fetched from the SDK and isolated in its own try/catch so a vector-store
+// hiccup degrades to "no structure shown" instead of blanking the whole page.
+async function fetchLegalCorpus(): Promise<LegalCorpus | null> {
+  try {
+    const res = await fetch(`${SDK_URL}/sdk/v1/rag/legal-corpus`, {
+      cache: 'no-store',
+    })
+    return res.ok ? await res.json() : null
+  } catch {
+    return null
+  }
+}
+
 async function getData(): Promise<{
   useCases: UseCaseRow[]
   corpus: CorpusOverview | null
+  legalCorpus: LegalCorpus | null
 }> {
   try {
-    const [ucRes, corpusRes] = await Promise.all([
+    const [ucRes, corpusRes, legalCorpus] = await Promise.all([
       fetch(`${BACKEND_URL}/api/compliance/v1/controls/use-cases`, {
         cache: 'no-store',
       }),
       fetch(`${BACKEND_URL}/api/compliance/v1/controls/corpus`, {
         cache: 'no-store',
       }),
+      fetchLegalCorpus(),
     ])
     return {
       useCases: ucRes.ok ? await ucRes.json() : [],
       corpus: corpusRes.ok ? await corpusRes.json() : null,
+      legalCorpus,
     }
   } catch {
-    return { useCases: [], corpus: null }
+    return { useCases: [], corpus: null, legalCorpus: null }
   }
 }
 
@@ -46,7 +65,7 @@ function Stat({ label, value }: { label: string; value: string | number }) {
 }
 
 export default async function CoveragePage() {
-  const { useCases, corpus } = await getData()
+  const { useCases, corpus, legalCorpus } = await getData()
   const groups = groupUseCases(useCases)
   const totalRelevant = useCases.reduce((s, u) => s + u.atom_relevant, 0)
   const totalAtoms = useCases.reduce((s, u) => s + u.atom_total, 0)
@@ -221,6 +240,67 @@ export default async function CoveragePage() {
         </div>
       </section>
 
+      {legalCorpus?.regulations?.length ? (
+        <section className="space-y-2">
+          <h2 className="text-lg font-semibold text-gray-900">
+            Ingestierter Rechtskorpus – Struktur ({legalCorpus.totals.regulations}{' '}
+            Rechtsakte)
+          </h2>
+          <p className="text-xs text-gray-500">
+            Woraus jeder ingestierte eur-lex-Rechtsakt tatsächlich besteht:
+            Artikel (§), Anhänge, Erwägungsgründe und retrievbare Chunks — direkt
+            aus dem Vektorspeicher, damit kein Black-Box-Korpus entsteht.
+          </p>
+          <div className="overflow-auto rounded-lg border border-gray-200">
+            <table className="min-w-full divide-y divide-gray-200 text-sm">
+              <thead className="bg-gray-50 text-left text-xs uppercase text-gray-500">
+                <tr>
+                  <th className="px-4 py-2">Rechtsakt</th>
+                  <th className="px-4 py-2 text-right">Artikel (§)</th>
+                  <th className="px-4 py-2 text-right">Anhänge</th>
+                  <th className="px-4 py-2 text-right">Erwägungsgründe</th>
+                  <th className="px-4 py-2 text-right">Chunks</th>
+                </tr>
+              </thead>
+              <tbody className="divide-y divide-gray-100 bg-white">
+                {legalCorpus.regulations.map((r) => (
+                  <tr key={r.regulation_short}>
+                    <td className="px-4 py-2 text-gray-900">
+                      <span className="font-medium">{r.regulation_short}</span>
+                      {r.regulation_name !== r.regulation_short ? (
+                        <span className="ml-2 text-xs text-gray-500">
+                          {r.regulation_name}
+                        </span>
+                      ) : null}
+                    </td>
+                    <td className="px-4 py-2 text-right font-semibold">
+                      {r.articles.toLocaleString('de-DE')}
+                    </td>
+                    <td className="px-4 py-2 text-right">
+                      {r.annexes > 0 ? (
+                        r.annexes.toLocaleString('de-DE')
+                      ) : (
+                        <span className="text-gray-300">—</span>
+                      )}
+                    </td>
+                    <td className="px-4 py-2 text-right text-gray-500">
+                      {r.recitals > 0 ? (
+                        r.recitals.toLocaleString('de-DE')
+                      ) : (
+                        <span className="text-gray-300">—</span>
+                      )}
+                    </td>
+                    <td className="px-4 py-2 text-right text-gray-500">
+                      {r.chunks.toLocaleString('de-DE')}
+                    </td>
+                  </tr>
+                ))}
+              </tbody>
+            </table>
+          </div>
+        </section>
+      ) : null}
+
       {corpus?.license_catalog?.length ? (
         <section className="space-y-2">
           <h2 className="text-lg font-semibold text-gray-900">

ai-compliance-sdk/.golangci.yml

@@ -55,8 +55,7 @@ linters-settings:
     rules:
       - name: exported
         arguments:
-          - checkPrivateReceivers: false
+          - disableStutteringCheck
-          - disableStutteringCheck: true
       - name: error-return
       - name: increment-decrement
       - name: var-declaration
@@ -83,6 +82,6 @@ issues:
   max-issues-per-linter: 50
   max-same-issues: 5
 
-  # New code only: don't fail on pre-existing issues in files we haven't touched.
+  # New code only: lint lines changed vs main, so pre-existing debt doesn't fail CI.
-  # Remove this once a clean baseline is established.
+  # Needs the go-lint job to clone with a local `main` ref (see .gitea/workflows/ci.yaml).
-  new: false
+  new-from-merge-base: main

ai-compliance-sdk/internal/api/handlers/rag_handlers.go

@@ -75,9 +75,10 @@ func (h *RAGHandlers) Search(c *gin.Context) {
 	}
 
 	c.JSON(http.StatusOK, gin.H{
-		"query":   req.Query,
+		"query":      req.Query,
-		"results": results,
+		"results":    results,
-		"count":   len(results),
+		"count":      len(results),
+		"assessment": ucca.Assess(results),
 	})
 }
 
@@ -206,3 +207,32 @@ func (h *RAGHandlers) HandleScrollChunks(c *gin.Context) {
 		"total":       len(chunks),
 	})
 }
+
+// LegalCorpusStructure returns the composition (distinct articles, annexes,
+// recitals + chunk count) of every ingested eur-lex legal act, so the coverage
+// page can show WHAT was ingested instead of just the act name.
+// GET /sdk/v1/rag/legal-corpus
+func (h *RAGHandlers) LegalCorpusStructure(c *gin.Context) {
+	acts, err := h.ragClient.CorpusStructure(c.Request.Context())
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to aggregate legal corpus: " + err.Error()})
+		return
+	}
+
+	arts, anns, recs := 0, 0, 0
+	for _, a := range acts {
+		arts += a.Articles
+		anns += a.Annexes
+		recs += a.Recitals
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"regulations": acts,
+		"totals": gin.H{
+			"regulations": len(acts),
+			"articles":    arts,
+			"annexes":     anns,
+			"recitals":    recs,
+		},
+	})
+}

ai-compliance-sdk/internal/app/routes.go

@@ -161,6 +161,7 @@ func registerRAGRoutes(v1 *gin.RouterGroup, h *handlers.RAGHandlers) {
 		ragRoutes.GET("/corpus-status", h.CorpusStatus)
 		ragRoutes.GET("/corpus-versions/:collection", h.CorpusVersionHistory)
 		ragRoutes.GET("/scroll", h.HandleScrollChunks)
+		ragRoutes.GET("/legal-corpus", h.LegalCorpusStructure)
 	}
 }
 

ai-compliance-sdk/internal/ucca/authority.go

@@ -0,0 +1,230 @@
+package ucca
+
+import (
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+// authorityInfo is the normative classification of a search result, used internally
+// for re-ranking only (Phase 1 changes ordering, not the response contract).
+type authorityInfo struct {
+	weight       int    // 100 binding, 80 technical_standard, 70 guidance, 0 foreign, 50 unknown
+	sourceClass  string // binding_law | technical_standard | supervisory_guidance | foreign_law | unknown
+	jurisdiction string // DE | EU | CH
+}
+
+var (
+	guidanceMarkers = []string{
+		"DSK", "EDPB", "BfDI", "BFDI", "BayLfD", "Baylfb", "ENISA", "BSI", "EUCC",
+		"Standards Mapping", "Kpnr", "Orientierungshilfe", "Handreichung", "Beschluss",
+		"Leitlinie", "Guidance", "Empfehlung", "OECD", "CISA", "Blue Guide",
+	}
+	// Technical standards / control frameworks (best-practice controls). Checked BEFORE
+	// guidanceMarkers so a "BSI Grundschutz" chunk classifies as a standard, not BSI guidance.
+	standardMarkers = []string{
+		"NIST", "OWASP", "Grundschutz", "ISO 27001", "ISO/IEC 27001",
+		"CSA CCM", "Cloud Controls Matrix", "CIS Benchmark", "CIS Control",
+	}
+	foreignMarkers = []string{"RevDSG", "fedlex", "(CH)"}
+	deMarkers      = []string{"BDSG", "DSK", "BfDI", "BFDI", "BayLfD", "Baylfb", "BSI"}
+	normPattern    = regexp.MustCompile(`(§|Art\.?)\s*\d`)
+	bdsgParagraph  = regexp.MustCompile(`§\s*(\d+)`)
+)
+
+// classifyAuthority derives weight/source-class/jurisdiction. Explicitly tagged payload
+// values win; otherwise it falls back to the curated category + name markers, so the
+// not-yet-re-ingested (untagged) corpus is still classified deterministically.
+func classifyAuthority(r LegalSearchResult) authorityInfo {
+	jur := r.Jurisdiction
+	if jur == "" {
+		jur = inferJurisdiction(r)
+	}
+	if r.SourceClass != "" {
+		w := r.AuthorityWeight
+		if w == 0 && r.SourceClass == "binding_law" {
+			w = 100
+		}
+		return authorityInfo{weight: w, sourceClass: r.SourceClass, jurisdiction: jur}
+	}
+	if r.AuthorityWeight > 0 {
+		return authorityInfo{weight: r.AuthorityWeight, sourceClass: sourceClassFromWeight(r.AuthorityWeight), jurisdiction: jur}
+	}
+	hay := r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationName + " " + r.RegulationCode
+	switch {
+	case containsAny(hay, foreignMarkers):
+		return authorityInfo{weight: 0, sourceClass: "foreign_law", jurisdiction: "CH"}
+	case r.Category == "standard" || containsAny(hay, standardMarkers):
+		return authorityInfo{weight: 80, sourceClass: "technical_standard", jurisdiction: jur}
+	case r.Category == "guidance" || containsAny(hay, guidanceMarkers):
+		return authorityInfo{weight: 70, sourceClass: "supervisory_guidance", jurisdiction: jur}
+	case r.Category == "regulation" || r.Category == "eu_recht" || normPattern.MatchString(r.ArticleLabel):
+		return authorityInfo{weight: 100, sourceClass: "binding_law", jurisdiction: jur}
+	default:
+		return authorityInfo{weight: 50, sourceClass: "unknown", jurisdiction: jur}
+	}
+}
+
+func sourceClassFromWeight(w int) string {
+	switch {
+	case w >= 100:
+		return "binding_law"
+	case w >= 80:
+		return "technical_standard"
+	case w >= 70:
+		return "supervisory_guidance"
+	case w <= 0:
+		return "foreign_law"
+	default:
+		return "unknown"
+	}
+}
+
+func inferJurisdiction(r LegalSearchResult) string {
+	hay := r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationName
+	switch {
+	case containsAny(hay, foreignMarkers):
+		return "CH"
+	case strings.Contains(hay, "§") || containsAny(hay, deMarkers):
+		return "DE"
+	default:
+		return "EU"
+	}
+}
+
+// --- Domain routing: separates same-authority but topically foreign norms ---
+
+type domainDef struct {
+	name     string
+	regs     []string // regulation markers found in a chunk
+	keywords []string // query keywords that signal this domain
+}
+
+// Deterministic order (slice, not map) — important for stable classification + tests.
+var domains = []domainDef{
+	{"data_protection",
+		[]string{"DSGVO", "GDPR", "BDSG", "EDPB", "DSK", "BfDI", "BayLfD", "DPF"},
+		[]string{"personenbezogen", "betroffene", "datenschutz", "datenschutzbeauftrag", "dsb",
+			"datenpanne", "auskunft", "loesch", "lösch", "einwilligung", "besondere kategorien", "auftragsverarbeiter"}},
+	{"cyber",
+		[]string{"CRA", "NIS2", "NIS-2", "ENISA", "DORA", "EUCC"},
+		[]string{"security update", "sicherheitsupdate", "sicherheitsaktualisierung", "schwachstelle", "sbom",
+			"cybersicherheit", "konformit", "hersteller", "importeur", "haendler", "händler", "ikt-",
+			"resilienz", "sicherheitsvorfall", "digitalen elementen"}},
+	{"ai",
+		[]string{"AI Act", "KI-VO", "KI-Verordnung"},
+		[]string{"ki-system", "ki-modell", "hochrisiko", "kuenstliche intelligenz", "künstliche intelligenz"}},
+	{"product_safety",
+		[]string{"Maschinenverordnung", "MaschinenVO", "GPSR", "RED", "MDR"},
+		nil},
+}
+
+func queryDomain(query string) string {
+	ql := strings.ToLower(query)
+	for _, d := range domains {
+		for _, kw := range d.keywords {
+			if strings.Contains(ql, kw) {
+				return d.name
+			}
+		}
+	}
+	return ""
+}
+
+func chunkDomain(r LegalSearchResult) string {
+	hay := r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationCode + " " + r.RegulationName
+	for _, d := range domains {
+		if containsAny(hay, d.regs) {
+			return d.name
+		}
+	}
+	return ""
+}
+
+// scopeClass flags special sub-regimes that must not win general questions —
+// BDSG Teil 3 (§§ 45-84) implements the JI directive (law enforcement), not the general regime.
+func scopeClass(r LegalSearchResult) string {
+	hay := r.ArticleLabel + " " + r.RegulationShort
+	if strings.Contains(hay, "BDSG") {
+		if m := bdsgParagraph.FindStringSubmatch(hay); m != nil {
+			if n, err := strconv.Atoi(m[1]); err == nil && n >= 45 && n <= 84 {
+				return "law_enforcement"
+			}
+		}
+	}
+	return "general"
+}
+
+// --- Topic ontology: amplifier only (boost), never an override ---
+
+type topicDef struct {
+	keywords []string
+	norms    []string // preferred canonical citation fragments
+}
+
+var topics = []topicDef{
+	{[]string{"datenschutzbeauftrag", "dsb", "benennung"}, []string{"Art. 37", "§ 38 BDSG"}},
+	{[]string{"stellung des"}, []string{"Art. 38"}},
+	{[]string{"aufgaben des"}, []string{"Art. 39"}},
+	{[]string{"folgenabsch", "dsfa"}, []string{"Art. 35"}},
+	{[]string{"besondere kategorien"}, []string{"Art. 9", "§ 22 BDSG"}},
+	{[]string{"auskunft"}, []string{"Art. 15", "§ 34 BDSG"}},
+	{[]string{"loesch", "lösch"}, []string{"Art. 17", "§ 35 BDSG"}},
+	{[]string{"bussgeld", "geldbusse"}, []string{"Art. 83"}},
+	{[]string{"security update", "sicherheitsupdate", "schwachstelle", "sbom", "cybersicherheitsanforderung"}, []string{"CRA Anhang I"}},
+	{[]string{"meldepflicht", "sicherheitsvorfall"}, []string{"Art. 14 CRA"}},
+}
+
+// resultMatchesTopic reports whether the result is a preferred norm of a topic the query hits.
+func resultMatchesTopic(query string, r LegalSearchResult) bool {
+	ql := strings.ToLower(query)
+	hay := r.ArticleLabel + " " + r.RegulationShort
+	for _, t := range topics {
+		if !containsAnyLower(ql, t.keywords) {
+			continue
+		}
+		for _, n := range t.norms {
+			if normMatches(hay, n) {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+// normMatches checks that norm appears in hay with a non-digit boundary, so "Art. 9"
+// matches "Art. 9 DSGVO" but not "Art. 90".
+func normMatches(hay, norm string) bool {
+	idx := strings.Index(hay, norm)
+	if idx < 0 {
+		return false
+	}
+	end := idx + len(norm)
+	if end < len(hay) && hay[end] >= '0' && hay[end] <= '9' {
+		return false
+	}
+	return true
+}
+
+func queryIsForeign(query string) bool {
+	return containsAnyLower(strings.ToLower(query),
+		[]string{"schweiz", "revdsg", "fedlex", " ch ", "oesterreich", "österreich"})
+}
+
+func containsAny(hay string, markers []string) bool {
+	for _, m := range markers {
+		if strings.Contains(hay, m) {
+			return true
+		}
+	}
+	return false
+}
+
+func containsAnyLower(haylower string, markers []string) bool {
+	for _, m := range markers {
+		if strings.Contains(haylower, strings.ToLower(m)) {
+			return true
+		}
+	}
+	return false
+}

ai-compliance-sdk/internal/ucca/authority_rerank.go

@@ -0,0 +1,171 @@
+package ucca
+
+import (
+	"sort"
+	"strings"
+)
+
+// Re-ranking coefficients (validated in the offline golden harness; Phase A — conservative).
+const (
+	authorityCoef     = 0.40 // * weight/100
+	jurisdictionGain  = 0.05 // binding/guidance from DE or EU
+	foreignPenalty    = 0.60 // foreign law on a DE/EU question (demoted, not removed)
+	unknownPenalty    = 0.08
+	domainMatchGain   = 0.15
+	offDomainPenalty  = 0.10 // off-domain binding (demoted, not removed)
+	scopePenalty      = 0.25 // BDSG Teil 3 (law enforcement) on a general DP question
+	topicGain         = 0.18 // amplifier only
+	supersededPenalty = 0.50 // superseded Alt-Quelle (pre-eu-v1): demoted, nicht versteckt
+	intentLiftGain    = 0.10 // epsilon a qualifying interpretative source is lifted ABOVE the best binding
+	intentLiftMargin  = 0.05 // ...only if that source is semantically competitive with binding
+)
+
+// guidanceIntentSignals mark a query that EXPLICITLY asks for an interpretation /
+// recommendation by a guidance body, rather than for the binding obligation. Only
+// then may a (semantically competitive) guideline outrank the binding norm.
+var guidanceIntentSignals = []string{
+	"edpb", "europäischer datenschutzausschuss", "europaeischer datenschutzausschuss",
+	"dsk", "enisa", "bsi", "leitlinie", "guideline", "orientierungshilfe",
+	"auslegung", "empfiehlt", "empfehlung", "sagt", "laut",
+}
+
+// controlIntentSignals mark a query that asks HOW to implement / which controls or
+// measures fit — rather than WHAT the binding obligation is. Only then may a
+// (semantically competitive) technical_standard outrank the binding norm.
+var controlIntentSignals = []string{
+	"control", "controls", "maßnahme", "massnahme", "schutzmaßnahme",
+	"best practice", "best-practice", "umsetzen", "implementier", "absicher",
+	"härt", "haert", "hardening", "nist", "owasp", "grundschutz",
+	"ccm", "iso 27001", "isms",
+}
+
+func queryMatchesAny(query string, signals []string) bool {
+	q := strings.ToLower(query)
+	for _, sig := range signals {
+		if strings.Contains(q, sig) {
+			return true
+		}
+	}
+	return false
+}
+
+// queryWantsGuidance reports whether the query explicitly asks for guidance/interpretation.
+func queryWantsGuidance(query string) bool { return queryMatchesAny(query, guidanceIntentSignals) }
+
+// queryWantsControls reports whether the query asks for implementation controls/measures.
+func queryWantsControls(query string) bool { return queryMatchesAny(query, controlIntentSignals) }
+
+// bestBindingSemantic returns the highest RAW semantic score among binding-law
+// results (0 if none / no intent). Used as the guard threshold so an off-topic
+// interpretative source cannot ride the intent boost.
+func bestBindingSemantic(results []LegalSearchResult, wantsIntent bool) float64 {
+	if !wantsIntent {
+		return 0
+	}
+	best := 0.0
+	for _, r := range results {
+		if classifyAuthority(r).sourceClass == "binding_law" && r.Score > best {
+			best = r.Score
+		}
+	}
+	return best
+}
+
+// authorityScore computes the normative relevance of a result for a query. It augments the
+// semantic score with authority/jurisdiction/domain/scope/topic signals. Exposed for tests.
+func authorityScore(query string, r LegalSearchResult, qDomain string, qForeign bool) float64 {
+	info := classifyAuthority(r)
+	score := r.Score + authorityCoef*float64(info.weight)/100.0
+
+	if r.Superseded {
+		// Alt-Quelle (pre-eu-v1): Default-Fragen sollen die eu-v1-Norm sehen. Demoted,
+		// nicht entfernt — fuer Historie/Uebergangsfragen bleibt sie auffindbar.
+		score -= supersededPenalty
+	}
+
+	if info.jurisdiction == "CH" && !qForeign {
+		score -= foreignPenalty // Fremdrecht bei DE/EU-Frage: demoted, nicht geloescht
+	} else {
+		score += jurisdictionGain
+	}
+	if info.sourceClass == "unknown" {
+		score -= unknownPenalty
+	}
+	if qDomain != "" {
+		switch cd := chunkDomain(r); {
+		case cd == qDomain:
+			score += domainMatchGain
+		case cd != "":
+			score -= offDomainPenalty // off-domain binding: demoted, nicht geloescht
+		}
+	}
+	if qDomain == "data_protection" && scopeClass(r) == "law_enforcement" {
+		score -= scopePenalty
+	}
+	if resultMatchesTopic(query, r) {
+		score += topicGain // Verstaerker, kein Override
+	}
+	return score
+}
+
+// rerankByAuthority re-orders results so binding law from the matching jurisdiction/domain
+// ranks above guidance, foreign and off-domain law — WITHOUT dropping anything (guidance is
+// kept as interpretation context). The computed score is written back to Score so downstream
+// merges (e.g. the multi-collection advisor) preserve this order. Pure + deterministic.
+func rerankByAuthority(query string, results []LegalSearchResult) []LegalSearchResult {
+	if len(results) < 2 {
+		return results
+	}
+	qDomain := queryDomain(query)
+	qForeign := queryIsForeign(query)
+	wantsGuidance := queryWantsGuidance(query)
+	wantsControls := queryWantsControls(query)
+	bestBindingSem := bestBindingSemantic(results, wantsGuidance)
+
+	out := make([]LegalSearchResult, len(results))
+	copy(out, results)
+	for i := range out {
+		out[i].Score = authorityScore(query, out[i], qDomain, qForeign)
+	}
+	// Explicit interpretation intent → a competitive guideline may outrank binding (lift
+	// above the best binding FINAL). Explicit implementation intent → boost the CONTROL-POOL
+	// (operational/procedural requirement, control standard, implementation guidance) over
+	// the abstract obligation, soft-ordered by role. Norm questions (neither) stay untouched.
+	if wantsGuidance {
+		liftAboveBinding(out, results, bestBindingSem, "supervisory_guidance")
+	}
+	if wantsControls {
+		applyControlRoles(out)
+	}
+	sort.SliceStable(out, func(a, b int) bool {
+		return out[a].Score > out[b].Score
+	})
+	return out
+}
+
+// liftAboveBinding lifts a semantically-competitive interpretative source (the given
+// sourceClass — supervisory_guidance or technical_standard) just ABOVE the best binding
+// hit, ordered by semantic, so an EXPLICIT guidance/implementation question can return
+// that source Top-1. A pure norm question (no intent → not called) keeps binding on top.
+// Sources below the semantic margin are left untouched, so an off-topic source can never
+// ride the override — and the lift is from the binding FINAL score, so authority/topic/
+// domain bonuses cannot edge it out.
+func liftAboveBinding(out, raw []LegalSearchResult, bestBindingSem float64, sourceClass string) {
+	bestBindingFinal := 0.0
+	for i := range out {
+		if classifyAuthority(out[i]).sourceClass == "binding_law" && out[i].Score > bestBindingFinal {
+			bestBindingFinal = out[i].Score
+		}
+	}
+	for i := range out {
+		// Classify (not raw payload) so the untagged legacy corpus — e.g. NIST ingested
+		// before source_class tagging — is still recognized as its interpretative class.
+		if classifyAuthority(out[i]).sourceClass != sourceClass || raw[i].Score < bestBindingSem-intentLiftMargin {
+			continue
+		}
+		lifted := bestBindingFinal + intentLiftGain + (raw[i].Score - bestBindingSem)
+		if lifted > out[i].Score {
+			out[i].Score = lifted
+		}
+	}
+}

ai-compliance-sdk/internal/ucca/authority_rerank_test.go

@@ -0,0 +1,96 @@
+package ucca
+
+import "testing"
+
+func bindingRes(label, reg, jur string, score float64) LegalSearchResult {
+	return LegalSearchResult{ArticleLabel: label, RegulationShort: reg, SourceClass: "binding_law", AuthorityWeight: 100, Jurisdiction: jur, Score: score}
+}
+
+func guidanceRes(label, reg string, score float64) LegalSearchResult {
+	return LegalSearchResult{ArticleLabel: label, RegulationShort: reg, SourceClass: "supervisory_guidance", AuthorityWeight: 70, Jurisdiction: "EU", Score: score}
+}
+
+func foreignRes(label string, score float64) LegalSearchResult {
+	return LegalSearchResult{ArticleLabel: label, RegulationShort: "RevDSG", SourceClass: "foreign_law", AuthorityWeight: 0, Jurisdiction: "CH", Score: score}
+}
+
+// Acceptance criteria (Phase 1) expressed as ordering tests.
+func TestRerankByAuthority_Acceptance(t *testing.T) {
+	t.Run("guidance does not overtake semantically competitive binding", func(t *testing.T) {
+		out := rerankByAuthority("Was gilt hier?", []LegalSearchResult{
+			guidanceRes("ENISA Mapping", "ENISA", 0.72),
+			bindingRes("CRA Anhang I", "CRA", "EU", 0.66),
+		})
+		if out[0].RegulationShort != "CRA" {
+			t.Fatalf("binding must rank first over competitive guidance, got %q", out[0].RegulationShort)
+		}
+	})
+
+	t.Run("foreign law demoted on DE/EU question but kept", func(t *testing.T) {
+		in := []LegalSearchResult{foreignRes("RevDSG Art 1", 0.85), bindingRes("Art. 9 DSGVO", "DSGVO", "EU", 0.62)}
+		out := rerankByAuthority("Welche Daten sind besonders geschuetzt?", in)
+		if out[0].RegulationShort != "DSGVO" {
+			t.Fatalf("binding EU must beat foreign on a DE/EU query, got %q", out[0].RegulationShort)
+		}
+		if len(out) != 2 {
+			t.Fatalf("foreign law must be kept, got len=%d", len(out))
+		}
+	})
+
+	t.Run("off-domain binding demoted but not removed", func(t *testing.T) {
+		in := []LegalSearchResult{
+			bindingRes("Art. 13 EU MDR", "MDR", "EU", 0.70),
+			bindingRes("Art. 13 CRA", "CRA", "EU", 0.60),
+		}
+		out := rerankByAuthority("Welche Pflichten hat der Hersteller von Produkten mit digitalen Elementen?", in)
+		if out[0].RegulationShort != "CRA" {
+			t.Fatalf("on-domain CRA must beat off-domain MDR, got %q", out[0].RegulationShort)
+		}
+		if len(out) != 2 {
+			t.Fatalf("off-domain MDR must be kept, got len=%d", len(out))
+		}
+	})
+
+	t.Run("same-regime binding wins over guidance", func(t *testing.T) {
+		out := rerankByAuthority("Was gilt hier?", []LegalSearchResult{
+			bindingRes("Art. 13 CRA", "CRA", "EU", 0.70),
+			guidanceRes("ENISA Mapping", "ENISA", 0.60),
+		})
+		if out[0].RegulationShort != "CRA" {
+			t.Fatalf("binding must win, got %q", out[0].RegulationShort)
+		}
+	})
+
+	t.Run("BDSG Teil 3 demoted below DSGVO on general DP question", func(t *testing.T) {
+		in := []LegalSearchResult{
+			bindingRes("§ 48 BDSG", "BDSG", "DE", 0.70), // Teil 3 (law enforcement)
+			bindingRes("Art. 9 DSGVO", "DSGVO", "EU", 0.62),
+		}
+		out := rerankByAuthority("Was sind besondere Kategorien personenbezogener Daten?", in)
+		if out[0].RegulationShort != "DSGVO" {
+			t.Fatalf("DSGVO must beat BDSG Teil 3 on a general DP question, got %q", out[0].RegulationShort)
+		}
+	})
+
+	t.Run("nothing is dropped and topic amplifies", func(t *testing.T) {
+		in := []LegalSearchResult{
+			guidanceRes("ENISA", "ENISA", 0.72),
+			bindingRes("CRA Anhang I", "CRA", "EU", 0.66),
+			foreignRes("RevDSG", 0.5),
+		}
+		out := rerankByAuthority("Anforderungen an Security Updates?", in)
+		if len(out) != len(in) {
+			t.Fatalf("rerank must preserve all results, got %d want %d", len(out), len(in))
+		}
+		if out[0].ArticleLabel != "CRA Anhang I" {
+			t.Fatalf("topic+authority must lift CRA Anhang I to top, got %q", out[0].ArticleLabel)
+		}
+	})
+
+	t.Run("single result returned unchanged", func(t *testing.T) {
+		in := []LegalSearchResult{bindingRes("Art. 1 CRA", "CRA", "EU", 0.5)}
+		if out := rerankByAuthority("x", in); len(out) != 1 {
+			t.Fatalf("len=%d", len(out))
+		}
+	})
+}

ai-compliance-sdk/internal/ucca/authority_test.go

@@ -0,0 +1,129 @@
+package ucca
+
+import "testing"
+
+func TestClassifyAuthority(t *testing.T) {
+	tests := []struct {
+		name    string
+		result  LegalSearchResult
+		wantW   int
+		wantSC  string
+		wantJur string
+	}{
+		{"tagged binding EU", LegalSearchResult{AuthorityWeight: 100, SourceClass: "binding_law", Jurisdiction: "EU"}, 100, "binding_law", "EU"},
+		{"tagged guidance DE", LegalSearchResult{AuthorityWeight: 70, SourceClass: "supervisory_guidance", Jurisdiction: "DE"}, 70, "supervisory_guidance", "DE"},
+		{"tagged foreign CH", LegalSearchResult{AuthorityWeight: 0, SourceClass: "foreign_law", Jurisdiction: "CH"}, 0, "foreign_law", "CH"},
+		{"untagged ENISA guidance", LegalSearchResult{RegulationShort: "ENISA", ArticleLabel: "ENISA CRA Standards Mapping"}, 70, "supervisory_guidance", "EU"},
+		{"untagged NIST standard", LegalSearchResult{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8"}, 80, "technical_standard", "EU"},
+		{"BSI Grundschutz standard beats BSI guidance", LegalSearchResult{RegulationShort: "BSI Grundschutz", ArticleLabel: "BSI Grundschutz Baustein"}, 80, "technical_standard", "DE"},
+		{"weight-only 85 TRGS standard", LegalSearchResult{AuthorityWeight: 85, RegulationShort: "TRGS 529"}, 85, "technical_standard", "EU"},
+		{"tagged technical_standard", LegalSearchResult{AuthorityWeight: 80, SourceClass: "technical_standard", Jurisdiction: "EU"}, 80, "technical_standard", "EU"},
+		{"untagged CRA binding", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 13 CRA", Category: "regulation"}, 100, "binding_law", "EU"},
+		{"untagged BDSG binding DE", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 38 BDSG"}, 100, "binding_law", "DE"},
+		{"untagged RevDSG foreign", LegalSearchResult{RegulationShort: "RevDSG", ArticleLabel: "RevDSG (CH)"}, 0, "foreign_law", "CH"},
+		{"untagged unknown", LegalSearchResult{RegulationShort: "", ArticleLabel: ""}, 50, "unknown", "EU"},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := classifyAuthority(tt.result)
+			if got.weight != tt.wantW || got.sourceClass != tt.wantSC || got.jurisdiction != tt.wantJur {
+				t.Errorf("classifyAuthority() = {%d %s %s}, want {%d %s %s}",
+					got.weight, got.sourceClass, got.jurisdiction, tt.wantW, tt.wantSC, tt.wantJur)
+			}
+		})
+	}
+}
+
+func TestQueryDomain(t *testing.T) {
+	tests := []struct{ q, want string }{
+		{"Welche Anforderungen an Security Updates?", "cyber"},
+		{"Wer braucht einen Datenschutzbeauftragten?", "data_protection"},
+		{"Was sind besondere Kategorien personenbezogener Daten?", "data_protection"},
+		{"Welche Pflichten beim Hochrisiko-KI-System?", "ai"},
+		{"Wie spaet ist es?", ""},
+	}
+	for _, tt := range tests {
+		if got := queryDomain(tt.q); got != tt.want {
+			t.Errorf("queryDomain(%q) = %q, want %q", tt.q, got, tt.want)
+		}
+	}
+}
+
+func TestChunkDomain(t *testing.T) {
+	tests := []struct {
+		name string
+		r    LegalSearchResult
+		want string
+	}{
+		{"CRA cyber", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 13 CRA"}, "cyber"},
+		{"DSGVO dp", LegalSearchResult{RegulationShort: "DSGVO", ArticleLabel: "Art. 9 DSGVO"}, "data_protection"},
+		{"AI Act ai", LegalSearchResult{RegulationShort: "AI Act", ArticleLabel: "Art. 10 AI Act"}, "ai"},
+		{"MDR product", LegalSearchResult{RegulationShort: "MDR", ArticleLabel: "Art. 13 EU MDR"}, "product_safety"},
+		{"unknown", LegalSearchResult{RegulationShort: "XYZ"}, ""},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := chunkDomain(tt.r); got != tt.want {
+				t.Errorf("chunkDomain() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestScopeClass(t *testing.T) {
+	tests := []struct {
+		name string
+		r    LegalSearchResult
+		want string
+	}{
+		{"BDSG Teil 3 law enforcement", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 48 BDSG"}, "law_enforcement"},
+		{"BDSG general part", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 38 BDSG"}, "general"},
+		{"DSGVO general", LegalSearchResult{RegulationShort: "DSGVO", ArticleLabel: "Art. 9 DSGVO"}, "general"},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := scopeClass(tt.r); got != tt.want {
+				t.Errorf("scopeClass() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestResultMatchesTopic(t *testing.T) {
+	tests := []struct {
+		name  string
+		query string
+		r     LegalSearchResult
+		want  bool
+	}{
+		{"besondere Kategorien -> Art 9 match", "Was sind besondere Kategorien?", LegalSearchResult{ArticleLabel: "Art. 9 DSGVO"}, true},
+		{"besondere Kategorien -> Art 90 no match", "Was sind besondere Kategorien?", LegalSearchResult{ArticleLabel: "Art. 90 DSGVO"}, false},
+		{"security updates -> CRA Anhang I", "Anforderungen an Security Updates?", LegalSearchResult{ArticleLabel: "CRA Anhang I"}, true},
+		{"no topic keyword", "Wie spaet ist es?", LegalSearchResult{ArticleLabel: "Art. 9 DSGVO"}, false},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := resultMatchesTopic(tt.query, tt.r); got != tt.want {
+				t.Errorf("resultMatchesTopic() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestNormMatches(t *testing.T) {
+	tests := []struct {
+		hay, norm string
+		want      bool
+	}{
+		{"Art. 9 DSGVO", "Art. 9", true},
+		{"Art. 90 DSGVO", "Art. 9", false},
+		{"§ 38 BDSG", "§ 38 BDSG", true},
+		{"§ 380 BDSG", "§ 38", false},
+		{"Art. 14 CRA", "Art. 14 CRA", true},
+	}
+	for _, tt := range tests {
+		if got := normMatches(tt.hay, tt.norm); got != tt.want {
+			t.Errorf("normMatches(%q,%q) = %v, want %v", tt.hay, tt.norm, got, tt.want)
+		}
+	}
+}

ai-compliance-sdk/internal/ucca/control_role.go

@@ -0,0 +1,123 @@
+package ucca
+
+import "strings"
+
+// source_role is the FUNCTIONAL role of a chunk — WHAT must be done (obligation),
+// HOW to implement it (operational/procedural requirement, control standard,
+// implementation guidance), or how to READ the norm (interpretation/definition).
+// It is ORTHOGONAL to source_class (legal authority): source_class decides RANK,
+// source_role decides CONTROL-POOL membership for implementation questions.
+// Derived deterministically from markers, so the untagged corpus needs no re-tag.
+const (
+	roleObligation      = "obligation"              // the abstract duty (the WHAT)
+	roleOperationalReq  = "operational_requirement" // concrete binding requirement (CRA Annex I)
+	roleProceduralReq   = "procedural_requirement"  // a process: notification/registration/DPIA/incident report
+	roleControlStandard = "control_standard"        // best-practice control catalog (NIST/OWASP/ISO/CIS)
+	roleImplGuidance    = "implementation_guidance" // advisory how-to (ENISA good practices, BSI)
+	roleInterpretation  = "interpretation"          // interprets the norm's MEANING (EDPB guideline)
+	roleDefinition      = "definition"              // definitions / scope / recitals
+)
+
+var (
+	proceduralMarkers = []string{
+		"Meldung", "Meldepflicht", "Notification", "Notifizierung", "Registrierung",
+		"Registration", "Konformitätserklärung", "Declaration of Conformity", "Incident",
+		"Berichterstattung", "Reporting", "Folgenabschätzung", "DSFA", "DPIA", "Anzeigepflicht",
+	}
+	annexMarkers       = []string{"Anhang", "Annex", "Appendix", "Anlage"}
+	operationalMarkers = []string{"Anforderung", "Requirement", "essential", "wesentliche"}
+	implMarkers        = []string{
+		"Good Practice", "Best Practice", "Standards Mapping", "Umsetzung", "Implementation",
+		"Handreichung", "Maßnahmenkatalog", "ICS", "SCADA", "Technical Guideline", "TIG",
+	}
+	definitionMarkers = []string{"Begriffsbestimmung", "Definition"}
+)
+
+// classifyRole derives the functional source_role from chunk metadata + the authority
+// class. technical_standard is always a control_standard; guidance splits into
+// implementation_guidance (how-to) vs interpretation (meaning); binding splits into
+// procedural / operational requirement / definition / plain obligation.
+func classifyRole(r LegalSearchResult) string {
+	cls := classifyAuthority(r).sourceClass
+	hay := strings.ToLower(r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationName + " " + r.Article)
+	switch {
+	case r.IsRecital:
+		return roleDefinition
+	case cls == "technical_standard":
+		return roleControlStandard
+	case cls == "supervisory_guidance":
+		if containsAnyLower(hay, implMarkers) {
+			return roleImplGuidance
+		}
+		return roleInterpretation
+	case cls == "binding_law":
+		switch {
+		case containsAnyLower(hay, definitionMarkers):
+			return roleDefinition
+		case containsAnyLower(hay, proceduralMarkers):
+			return roleProceduralReq
+		case containsAnyLower(hay, annexMarkers) || containsAnyLower(hay, operationalMarkers):
+			return roleOperationalReq
+		default:
+			return roleObligation
+		}
+	default:
+		return roleObligation
+	}
+}
+
+// controlRoleBonus is the soft intra-pool preference (User 2026-06-24):
+// operational_requirement > procedural_requirement > control_standard > implementation_guidance.
+var controlRoleBonus = map[string]float64{
+	roleOperationalReq:  0.100,
+	roleProceduralReq:   0.075,
+	roleControlStandard: 0.050,
+	roleImplGuidance:    0.000,
+}
+
+// controlPoolGain lifts EVERY control-pool role over the non-control roles (obligation/
+// interpretation/definition) on an implementation question, so the binding abstract
+// obligation does not dominate by authority alone. The obligation is not removed — it
+// stays visible as "Rechtsgrundlage" context below the recommended measures.
+const controlPoolGain = 0.15
+
+// applyControlRoles boosts the control-pool (the four implementation roles) for an
+// EXPLICIT implementation question, soft-ordered op_req > procedural > standard > guidance.
+// Replaces the earlier "lift technical_standard above binding" — controls are not only
+// technical_standard, and the binding operational_requirement (e.g. CRA Annex I) should win.
+func applyControlRoles(out []LegalSearchResult) {
+	for i := range out {
+		if bonus, ok := controlRoleBonus[classifyRole(out[i])]; ok {
+			out[i].Score += controlPoolGain + bonus
+		}
+	}
+}
+
+// isControlPoolRole reports whether a role belongs to the control-pool surfaced on
+// implementation questions (the four "how to implement" roles).
+func isControlPoolRole(role string) bool {
+	switch role {
+	case roleOperationalReq, roleProceduralReq, roleControlStandard, roleImplGuidance:
+		return true
+	}
+	return false
+}
+
+// controlRoleOf classifies a raw Qdrant payload into a source_role, so searchControls can
+// filter its deep dense pull to the control-pool BEFORE hits are mapped to LegalSearchResult.
+func controlRoleOf(payload map[string]interface{}) string {
+	article := getString(payload, "article")
+	if article == "" {
+		article = getString(payload, "section")
+	}
+	return classifyRole(LegalSearchResult{
+		RegulationShort: getString(payload, "regulation_short"),
+		RegulationName:  getString(payload, "regulation_name_de"),
+		ArticleLabel:    getString(payload, "article_label"),
+		Article:         article,
+		Category:        getString(payload, "category"),
+		SourceClass:     getString(payload, "source_class"),
+		AuthorityWeight: getInt(payload, "authority_weight"),
+		IsRecital:       getBool(payload, "is_recital"),
+	})
+}

ai-compliance-sdk/internal/ucca/control_role_test.go

@@ -0,0 +1,79 @@
+package ucca
+
+import "testing"
+
+func TestClassifyRole(t *testing.T) {
+	tests := []struct {
+		name string
+		r    LegalSearchResult
+		want string
+	}{
+		{"NIST -> control_standard", LegalSearchResult{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8"}, roleControlStandard},
+		{"OWASP -> control_standard", LegalSearchResult{RegulationShort: "OWASP ASVS"}, roleControlStandard},
+		{"CRA Anhang -> operational_requirement", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "CRA Anhang I", Category: "regulation"}, roleOperationalReq},
+		{"CRA Meldepflicht -> procedural_requirement", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 14 CRA Meldepflicht", Category: "regulation"}, roleProceduralReq},
+		{"ENISA Good Practices -> implementation_guidance", LegalSearchResult{RegulationShort: "ENISA Supply Chain Good Practices"}, roleImplGuidance},
+		{"EDPB Leitlinie -> interpretation", LegalSearchResult{RegulationShort: "EDPB DPO", ArticleLabel: "WP243 Leitlinien Datenschutzbeauftragte"}, roleInterpretation},
+		{"DORA article -> obligation", LegalSearchResult{RegulationShort: "DORA", ArticleLabel: "Art. 5 DORA", Category: "regulation"}, roleObligation},
+		{"DSGVO Begriffsbestimmungen -> definition", LegalSearchResult{RegulationShort: "DSGVO", ArticleLabel: "Art. 4 DSGVO Begriffsbestimmungen", Category: "regulation"}, roleDefinition},
+		{"recital -> definition", LegalSearchResult{RegulationShort: "CRA", IsRecital: true}, roleDefinition},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := classifyRole(tt.r); got != tt.want {
+				t.Errorf("classifyRole() = %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestApplyControlRoles_PoolPreference(t *testing.T) {
+	// op_req > procedural > control_standard > impl_guidance; non-control roles get no boost.
+	roles := []struct {
+		r        LegalSearchResult
+		wantGain float64
+	}{
+		{LegalSearchResult{ArticleLabel: "CRA Anhang I", Category: "regulation"}, controlPoolGain + 0.100},
+		{LegalSearchResult{ArticleLabel: "Art. 14 CRA Meldepflicht", Category: "regulation"}, controlPoolGain + 0.075},
+		{LegalSearchResult{RegulationShort: "NIST SP 800-53"}, controlPoolGain + 0.050},
+		{LegalSearchResult{RegulationShort: "ENISA Good Practices"}, controlPoolGain + 0.000},
+		{LegalSearchResult{ArticleLabel: "Art. 5 DORA", Category: "regulation"}, 0.0}, // obligation: no boost
+	}
+	for _, rc := range roles {
+		out := []LegalSearchResult{rc.r}
+		out[0].Score = 1.0
+		applyControlRoles(out)
+		if got := out[0].Score - 1.0; got < rc.wantGain-1e-9 || got > rc.wantGain+1e-9 {
+			t.Errorf("role %q: gain %.3f, want %.3f", classifyRole(rc.r), got, rc.wantGain)
+		}
+	}
+}
+
+func TestIsControlPoolRole(t *testing.T) {
+	for _, r := range []string{roleOperationalReq, roleProceduralReq, roleControlStandard, roleImplGuidance} {
+		if !isControlPoolRole(r) {
+			t.Errorf("%q should be in the control-pool", r)
+		}
+	}
+	for _, r := range []string{roleObligation, roleInterpretation, roleDefinition} {
+		if isControlPoolRole(r) {
+			t.Errorf("%q should NOT be in the control-pool", r)
+		}
+	}
+}
+
+func TestControlRoleOf_Payload(t *testing.T) {
+	// searchControls filters its deep dense pull by classifying the raw Qdrant payload.
+	nist := map[string]interface{}{"regulation_short": "NIST SP 800-82r3", "article": "AU-8"}
+	if got := controlRoleOf(nist); got != roleControlStandard {
+		t.Errorf("untagged NIST payload role = %q, want control_standard", got)
+	}
+	craAnnex := map[string]interface{}{"regulation_short": "CRA", "article": "Anhang-I", "category": "regulation"}
+	if got := controlRoleOf(craAnnex); got != roleOperationalReq {
+		t.Errorf("CRA Anhang payload role = %q, want operational_requirement", got)
+	}
+	dora := map[string]interface{}{"regulation_short": "DORA", "article_label": "Art. 5 DORA", "category": "regulation"}
+	if got := controlRoleOf(dora); isControlPoolRole(got) {
+		t.Errorf("DORA abstract article role = %q must be excluded from the control-pool", got)
+	}
+}

ai-compliance-sdk/internal/ucca/legal_corpus_structure.go

@@ -0,0 +1,167 @@
+package ucca
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"sort"
+)
+
+// LegalActStructure is the composition of one ingested eur-lex legal act — how
+// many distinct articles, annexes and recitals it consists of (plus the raw
+// chunk count). Backs the coverage page so the ingested corpus is not a black
+// box: a developer SEES what each act actually contains, not only its name.
+type LegalActStructure struct {
+	RegulationShort string `json:"regulation_short"`
+	RegulationName  string `json:"regulation_name"`
+	Articles        int    `json:"articles"`
+	Annexes         int    `json:"annexes"`
+	Recitals        int    `json:"recitals"`
+	Chunks          int    `json:"chunks"`
+}
+
+const eurlexSource = "eur-lex.europa.eu"
+
+// legalStructureCollections hold the clean eur-lex legal corpus (chunks tagged
+// with chunk_scope = section | annex | recital).
+var legalStructureCollections = []string{"bp_compliance_ce", "bp_compliance_datenschutz"}
+
+// chunkScopeBucket maps a Qdrant chunk_scope to the structure field it feeds.
+var chunkScopeBucket = map[string]string{"section": "articles", "annex": "annexes", "recital": "recitals"}
+
+// CorpusStructure scrolls the eur-lex legal corpus across the legal collections
+// and aggregates the per-act composition. The source filter keeps it to a few
+// hundred points regardless of total corpus size. Read-only; a collection that
+// fails to scroll is skipped rather than failing the whole call.
+func (c *LegalRAGClient) CorpusStructure(ctx context.Context) ([]LegalActStructure, error) {
+	var all []qdrantScrollPoint
+	for _, coll := range legalStructureCollections {
+		pts, err := c.scrollLegalCorpus(ctx, coll)
+		if err != nil {
+			continue
+		}
+		all = append(all, pts...)
+	}
+	return aggregateStructure(all), nil
+}
+
+// aggregateStructure counts distinct article labels per (regulation, scope).
+// Pure → unit-testable without a vector store.
+func aggregateStructure(points []qdrantScrollPoint) []LegalActStructure {
+	distinct := map[string]map[string]map[string]struct{}{}
+	names := map[string]string{}
+	chunks := map[string]int{}
+	order := []string{}
+
+	for _, pt := range points {
+		reg := getString(pt.Payload, "regulation_short")
+		if reg == "" {
+			continue
+		}
+		if _, seen := names[reg]; !seen {
+			name := getString(pt.Payload, "regulation_name_de")
+			if name == "" {
+				name = reg
+			}
+			names[reg] = name
+			distinct[reg] = map[string]map[string]struct{}{}
+			order = append(order, reg)
+		}
+		chunks[reg]++
+		bucket, ok := chunkScopeBucket[getString(pt.Payload, "chunk_scope")]
+		article := getString(pt.Payload, "article")
+		if !ok || article == "" {
+			continue
+		}
+		if distinct[reg][bucket] == nil {
+			distinct[reg][bucket] = map[string]struct{}{}
+		}
+		distinct[reg][bucket][article] = struct{}{}
+	}
+
+	out := make([]LegalActStructure, 0, len(order))
+	for _, reg := range order {
+		out = append(out, LegalActStructure{
+			RegulationShort: reg,
+			RegulationName:  names[reg],
+			Articles:        len(distinct[reg]["articles"]),
+			Annexes:         len(distinct[reg]["annexes"]),
+			Recitals:        len(distinct[reg]["recitals"]),
+			Chunks:          chunks[reg],
+		})
+	}
+	sort.SliceStable(out, func(i, j int) bool {
+		if out[i].Articles != out[j].Articles {
+			return out[i].Articles > out[j].Articles
+		}
+		return out[i].RegulationShort < out[j].RegulationShort
+	})
+	return out
+}
+
+// scrollLegalCorpus pages through one collection, filtered to the eur-lex legal
+// corpus, returning minimal-payload points (no text/vectors).
+func (c *LegalRAGClient) scrollLegalCorpus(ctx context.Context, collection string) ([]qdrantScrollPoint, error) {
+	var all []qdrantScrollPoint
+	var offset interface{}
+	for {
+		points, next, err := c.scrollLegalPage(ctx, collection, offset)
+		if err != nil {
+			return nil, err
+		}
+		all = append(all, points...)
+		if next == nil {
+			break
+		}
+		offset = next
+	}
+	return all, nil
+}
+
+// scrollLegalPage fetches one page of the filtered scroll and returns the
+// points plus the next-page offset (nil when exhausted).
+func (c *LegalRAGClient) scrollLegalPage(ctx context.Context, collection string, offset interface{}) ([]qdrantScrollPoint, interface{}, error) {
+	reqBody := map[string]interface{}{
+		"limit":        500,
+		"with_payload": map[string]interface{}{"include": []string{"regulation_short", "regulation_name_de", "chunk_scope", "article"}},
+		"with_vectors": false,
+		"filter": map[string]interface{}{
+			"must": []map[string]interface{}{
+				{"key": "source", "match": map[string]interface{}{"value": eurlexSource}},
+			},
+		},
+	}
+	if offset != nil {
+		reqBody["offset"] = offset
+	}
+	jsonBody, err := json.Marshal(reqBody)
+	if err != nil {
+		return nil, nil, err
+	}
+	url := fmt.Sprintf("%s/collections/%s/points/scroll", c.qdrantURL, collection)
+	req, err := http.NewRequestWithContext(ctx, "POST", url, bytes.NewReader(jsonBody))
+	if err != nil {
+		return nil, nil, err
+	}
+	req.Header.Set("Content-Type", "application/json")
+	if c.qdrantAPIKey != "" {
+		req.Header.Set("api-key", c.qdrantAPIKey)
+	}
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		return nil, nil, err
+	}
+	defer func() { _ = resp.Body.Close() }()
+	if resp.StatusCode != http.StatusOK {
+		body, _ := io.ReadAll(resp.Body)
+		return nil, nil, fmt.Errorf("qdrant returned %d: %s", resp.StatusCode, string(body))
+	}
+	var scrollResp qdrantScrollResponse
+	if err := json.NewDecoder(resp.Body).Decode(&scrollResp); err != nil {
+		return nil, nil, err
+	}
+	return scrollResp.Result.Points, scrollResp.Result.NextPageOffset, nil
+}

ai-compliance-sdk/internal/ucca/legal_corpus_structure_test.go

@@ -0,0 +1,50 @@
+package ucca
+
+import "testing"
+
+func structPoint(reg, name, scope, article string) qdrantScrollPoint {
+	return qdrantScrollPoint{Payload: map[string]interface{}{
+		"regulation_short":   reg,
+		"regulation_name_de": name,
+		"chunk_scope":        scope,
+		"article":            article,
+	}}
+}
+
+func TestAggregateStructure_CountsDistinctPerScope(t *testing.T) {
+	points := []qdrantScrollPoint{
+		structPoint("CRA", "Cyber Resilience Act", "section", "13"),
+		structPoint("CRA", "Cyber Resilience Act", "section", "13"), // duplicate article → still 1
+		structPoint("CRA", "Cyber Resilience Act", "section", "14"),
+		structPoint("CRA", "Cyber Resilience Act", "annex", "Anhang-I"),
+		structPoint("CRA", "Cyber Resilience Act", "annex", "Anhang-VII"),
+		structPoint("DORA", "", "section", "6"),  // first sighting has no name →
+		structPoint("DORA", "", "section", "19"), // regulation_name falls back to short
+		structPoint("DORA", "", "recital", ""),   // empty article → ignored for distinct
+		structPoint("", "x", "section", "1"),     // missing regulation → skipped entirely
+	}
+
+	got := aggregateStructure(points)
+
+	if len(got) != 2 {
+		t.Fatalf("want 2 acts, got %d (%+v)", len(got), got)
+	}
+	// CRA has more articles → sorts first.
+	cra := got[0]
+	if cra.RegulationShort != "CRA" || cra.Articles != 2 || cra.Annexes != 2 || cra.Recitals != 0 || cra.Chunks != 5 {
+		t.Errorf("CRA wrong: %+v", cra)
+	}
+	dora := got[1]
+	if dora.RegulationShort != "DORA" || dora.Articles != 2 || dora.Chunks != 3 {
+		t.Errorf("DORA wrong: %+v", dora)
+	}
+	if dora.RegulationName != "DORA" {
+		t.Errorf("DORA name fallback failed: %q", dora.RegulationName)
+	}
+}
+
+func TestAggregateStructure_Empty(t *testing.T) {
+	if got := aggregateStructure(nil); len(got) != 0 {
+		t.Errorf("want empty, got %+v", got)
+	}
+}

ai-compliance-sdk/internal/ucca/legal_rag_assess.go

@@ -0,0 +1,134 @@
+package ucca
+
+import (
+	"fmt"
+	"strings"
+)
+
+const (
+	assessConnectedCap    = 12   // cap connected norms surfaced in the assessment
+	assessCrossRegimeTopN = 5    // window over which "cross regime" is judged
+	assessReviewMargin    = 0.05 // a tighter winner gap → recommend human review
+)
+
+// Assess builds the auditable explanation layer over a ranked result set:
+// primary norm, the norms it connects to (citation graph), cross-regime, a
+// human-review flag, the winner margin and a short reasoning string. Pure →
+// unit-testable. It EXPLAINS the ranking, it does not change it. Returns nil for
+// an empty result set.
+func Assess(results []LegalSearchResult) *LegalAssessment {
+	if len(results) == 0 {
+		return nil
+	}
+	// Norm-level view: collapse multiple chunks of the same article/annex so the
+	// margin and cross-regime are judged between DISTINCT norms, not near-identical
+	// chunks of one norm (which would make every winner margin ~0).
+	norms := distinctNorms(results)
+	p := norms[0]
+
+	primary := primaryLabel(p)
+	connected := dedupStrings(p.ReferencesOut, p.ReferencesIn, p.CitationUnit)
+	if len(connected) > assessConnectedCap {
+		connected = connected[:assessConnectedCap]
+	}
+
+	window := norms
+	if len(window) > assessCrossRegimeTopN {
+		window = window[:assessCrossRegimeTopN]
+	}
+	regimes := make(map[string]bool)
+	for _, r := range window {
+		if r.RegulationShort != "" {
+			regimes[r.RegulationShort] = true
+		}
+	}
+	crossRegime := len(regimes) > 1
+
+	margin := 0.0
+	if len(norms) > 1 {
+		margin = norms[0].Score - norms[1].Score
+	}
+
+	primaryBinding := p.SourceClass == "binding_law"
+	humanReview := margin < assessReviewMargin || crossRegime || !primaryBinding
+
+	return &LegalAssessment{
+		PrimaryNorm:       primary,
+		PrimaryRegulation: p.RegulationShort,
+		ConnectedNorms:    connected,
+		CrossRegime:       crossRegime,
+		HumanReviewFlag:   humanReview,
+		WinnerMargin:      margin,
+		ScoreReasoning:    assessReasoning(p, margin, crossRegime, primaryBinding),
+	}
+}
+
+func primaryLabel(p LegalSearchResult) string {
+	if p.CitationUnit != "" {
+		return p.CitationUnit
+	}
+	if p.ArticleLabel != "" {
+		return p.ArticleLabel
+	}
+	return strings.TrimSpace(p.RegulationShort + " " + p.Article)
+}
+
+// assessReasoning renders a short, human-readable justification (German).
+func assessReasoning(p LegalSearchResult, margin float64, crossRegime, primaryBinding bool) string {
+	label := primaryLabel(p)
+	parts := make([]string, 0, 4)
+	if primaryBinding {
+		parts = append(parts, fmt.Sprintf("Primärtreffer %s: bindendes Recht (Autorität %d).", label, p.AuthorityWeight))
+	} else {
+		parts = append(parts, fmt.Sprintf("Primärtreffer %s ist keine bindende Norm (Leitlinie/Standard) — Quelle prüfen.", label))
+	}
+	if margin > 0 {
+		parts = append(parts, fmt.Sprintf("Vorsprung %.2f vor #2.", margin))
+	}
+	if margin < assessReviewMargin {
+		parts = append(parts, "Knapper Vorsprung — Alternativtreffer prüfen.")
+	}
+	if crossRegime {
+		parts = append(parts, "Mehrere Regime betroffen — Querbezug prüfen.")
+	}
+	return strings.Join(parts, " ")
+}
+
+// distinctNorms collapses results that share a citation (multiple chunks of the
+// same article/annex) to the first — i.e. highest-ranked — occurrence. Results
+// without any citation identity are each kept, since they cannot be matched.
+func distinctNorms(results []LegalSearchResult) []LegalSearchResult {
+	seen := make(map[string]bool, len(results))
+	out := make([]LegalSearchResult, 0, len(results))
+	for _, r := range results {
+		key := r.CitationUnit
+		if key == "" {
+			key = r.ArticleLabel
+		}
+		if key != "" {
+			if seen[key] {
+				continue
+			}
+			seen[key] = true
+		}
+		out = append(out, r)
+	}
+	return out
+}
+
+// dedupStrings concatenates out+in, drops empties and the excluded value, and
+// returns a stable de-duplicated slice (insertion order preserved).
+func dedupStrings(out, in []string, exclude string) []string {
+	seen := map[string]bool{exclude: true}
+	res := make([]string, 0, len(out)+len(in))
+	for _, list := range [][]string{out, in} {
+		for _, s := range list {
+			if s == "" || seen[s] {
+				continue
+			}
+			seen[s] = true
+			res = append(res, s)
+		}
+	}
+	return res
+}

ai-compliance-sdk/internal/ucca/legal_rag_assess_test.go

@@ -0,0 +1,112 @@
+package ucca
+
+import "testing"
+
+func ares(reg, cu, sc string, score float64, weight int, out, in []string) LegalSearchResult {
+	return LegalSearchResult{
+		RegulationShort: reg, CitationUnit: cu, SourceClass: sc, Score: score,
+		AuthorityWeight: weight, ReferencesOut: out, ReferencesIn: in,
+	}
+}
+
+func TestAssess_Empty(t *testing.T) {
+	if Assess(nil) != nil {
+		t.Error("empty results → nil assessment")
+	}
+}
+
+func TestAssess_BindingPrimary_NoReview(t *testing.T) {
+	results := []LegalSearchResult{
+		ares("CRA", "Art. 13 CRA", "binding_law", 1.05, 100,
+			[]string{"CRA Anhang I", "Art. 14 CRA"}, []string{"Art. 12 CRA"}),
+		ares("CRA", "Art. 14 CRA", "binding_law", 0.80, 100, nil, nil),
+	}
+	a := Assess(results)
+	if a == nil {
+		t.Fatal("nil assessment")
+	}
+	if a.PrimaryNorm != "Art. 13 CRA" || a.PrimaryRegulation != "CRA" {
+		t.Errorf("primary wrong: %+v", a)
+	}
+	if len(a.ConnectedNorms) != 3 { // out(2) + in(1), self excluded, deduped
+		t.Errorf("connected norms: %v", a.ConnectedNorms)
+	}
+	if a.CrossRegime {
+		t.Error("single regime must not be cross-regime")
+	}
+	if a.WinnerMargin < 0.24 || a.WinnerMargin > 0.26 {
+		t.Errorf("margin = %v, want ~0.25", a.WinnerMargin)
+	}
+	if a.HumanReviewFlag {
+		t.Error("clean binding + healthy margin + single regime → no review")
+	}
+}
+
+func TestAssess_CrossRegimeFlagsReview(t *testing.T) {
+	a := Assess([]LegalSearchResult{
+		ares("CRA", "Art. 13 CRA", "binding_law", 1.05, 100, nil, nil),
+		ares("DORA", "Art. 6 DORA", "binding_law", 0.70, 100, nil, nil),
+	})
+	if !a.CrossRegime || !a.HumanReviewFlag {
+		t.Errorf("cross-regime must flag review: %+v", a)
+	}
+}
+
+func TestAssess_NonBindingFlagsReview(t *testing.T) {
+	a := Assess([]LegalSearchResult{
+		ares("ENISA", "ENISA SBOM", "supervisory_guidance", 0.90, 70, nil, nil),
+		ares("ENISA", "ENISA X", "supervisory_guidance", 0.40, 70, nil, nil),
+	})
+	if !a.HumanReviewFlag {
+		t.Error("non-binding primary → review")
+	}
+}
+
+func TestAssess_TightMarginFlagsReview(t *testing.T) {
+	a := Assess([]LegalSearchResult{
+		ares("CRA", "Art. 13 CRA", "binding_law", 1.00, 100, nil, nil),
+		ares("CRA", "Art. 14 CRA", "binding_law", 0.98, 100, nil, nil),
+	})
+	if a.WinnerMargin >= 0.05 || !a.HumanReviewFlag {
+		t.Errorf("tight margin → review: %+v", a)
+	}
+}
+
+func TestAssess_MarginIsNormLevelNotChunkLevel(t *testing.T) {
+	// Two near-identical chunks of the SAME norm at the top, then a distinct norm.
+	results := []LegalSearchResult{
+		ares("CRA", "Art. 13 CRA", "binding_law", 1.050, 100, []string{"CRA Anhang I"}, nil),
+		ares("CRA", "Art. 13 CRA", "binding_law", 1.049, 100, nil, nil), // same norm
+		ares("CRA", "Art. 14 CRA", "binding_law", 0.800, 100, nil, nil),
+	}
+	a := Assess(results)
+	if a.WinnerMargin < 0.24 || a.WinnerMargin > 0.26 { // Art.13 vs Art.14, not chunk vs chunk
+		t.Errorf("margin must be norm-level (~0.25), got %v", a.WinnerMargin)
+	}
+	if a.HumanReviewFlag {
+		t.Error("healthy norm-level margin → no review")
+	}
+}
+
+func TestDistinctNorms(t *testing.T) {
+	got := distinctNorms([]LegalSearchResult{
+		{CitationUnit: "Art. 13 CRA"},
+		{CitationUnit: "Art. 13 CRA"}, // duplicate norm → collapsed
+		{CitationUnit: "Art. 14 CRA"},
+		{CitationUnit: ""}, // no identity → kept
+		{CitationUnit: ""}, // no identity → kept
+	})
+	if len(got) != 4 {
+		t.Errorf("want 4 (2 distinct + 2 unidentified), got %d", len(got))
+	}
+}
+
+func TestDedupStrings(t *testing.T) {
+	got := dedupStrings([]string{"a", "b", "", "a"}, []string{"b", "c"}, "self")
+	if len(got) != 3 || got[0] != "a" || got[1] != "b" || got[2] != "c" {
+		t.Errorf("dedup: %v", got)
+	}
+	if len(dedupStrings([]string{"self"}, nil, "self")) != 0 {
+		t.Error("excluded value must be dropped")
+	}
+}

ai-compliance-sdk/internal/ucca/legal_rag_client.go

@@ -20,6 +20,7 @@ type LegalRAGClient struct {
 	httpClient       *http.Client
 	textIndexEnsured map[string]bool
 	hybridEnabled    bool
+	graphEnabled     bool
 }
 
 // NewLegalRAGClient creates a new Legal RAG client using Ollama bge-m3 embeddings.
@@ -38,6 +39,11 @@ func NewLegalRAGClient() *LegalRAGClient {
 	}
 
 	hybridEnabled := os.Getenv("RAG_HYBRID_SEARCH") != "false"
+	// Graph-Expansion ist OPT-IN: kein gemessener Rang-Nutzen ggue. der Binding-Augmentation,
+	// +1 Qdrant-Call/Suche, Flutungsrisiko ueber Reverse-Kanten. Bleibt als Recall-Sicherheitsnetz
+	// fuer spaetere Luecken (RAG_GRAPH_EXPANSION=true). Die Graph-Kanten werden in der Response
+	// zur Begruendung/Vollstaendigkeit genutzt, nicht zur Pool-Expansion (Default).
+	graphEnabled := os.Getenv("RAG_GRAPH_EXPANSION") == "true"
 
 	return &LegalRAGClient{
 		qdrantURL:        qdrantURL,
@@ -47,6 +53,7 @@ func NewLegalRAGClient() *LegalRAGClient {
 		collection:       "bp_compliance_ce",
 		textIndexEnsured: make(map[string]bool),
 		hybridEnabled:    hybridEnabled,
+		graphEnabled:     graphEnabled,
 		httpClient: &http.Client{
 			Timeout: 60 * time.Second,
 		},
@@ -93,6 +100,29 @@ func (c *LegalRAGClient) searchInternal(ctx context.Context, collection string,
 		hits = denseHits
 	}
 
+	// Stratified: den binding_law-Pool ERGAENZEN (nicht ersetzen), damit die Pflichtquelle
+	// immer Kandidat ist — Guidance bleibt als Auslegungskontext erhalten. Best-effort:
+	// Fehler beim Binding-Query degradieren still auf den semantischen Pool.
+	if bindingHits, bErr := c.searchBinding(ctx, collection, embedding, topK); bErr == nil {
+		hits = mergeDedupHits(hits, bindingHits)
+	}
+
+	// Control-Augmentation: bei expliziter Umsetzungsfrage einen tiefen dense-Pool ziehen und
+	// nur die Control-Pool-Rollen behalten — so werden NIST/CRA-Anhang (dense rank ~8-9, unter
+	// dem kleinen top-K) Kandidaten. Re-Rank/applyControlRoles ordnen sie danach.
+	if queryWantsControls(query) {
+		if controlHits, cErr := c.searchControls(ctx, collection, embedding); cErr == nil {
+			hits = mergeDedupHits(hits, controlHits)
+		}
+	}
+
+	// Graph-Augmentation: verbundene Normen (references_out/in) der Top-Hits ueber die
+	// praezise Zitations-Kante in den Pool ziehen — z.B. Art. 13 CRA zieht Anhang I (die
+	// eigentliche Pflichtquelle). Pool-Augmentation only; Re-Rank + topK bleiben.
+	if c.graphEnabled {
+		hits = c.expandViaGraph(ctx, collection, hits)
+	}
+
 	results := make([]LegalSearchResult, len(hits))
 	for i, hit := range hits {
 		// Legal-Metadaten nach rag_reingest_spec.md §2: bevorzugt die normalisierten Felder
@@ -121,12 +151,45 @@ func (c *LegalRAGClient) searchInternal(ctx context.Context, collection string,
 			Pages:           getIntSlice(hit.Payload, "pages"),
 			SourceURL:       getString(hit.Payload, "source"),
 			Score:           hit.Score,
+			AuthorityWeight: getInt(hit.Payload, "authority_weight"),
+			SourceClass:     getString(hit.Payload, "source_class"),
+			Jurisdiction:    getString(hit.Payload, "jurisdiction"),
+			CitationUnit:    getString(hit.Payload, "citation_unit"),
+			ReferencesOut:   getStringSlice(hit.Payload, "references_out"),
+			ReferencesIn:    getStringSlice(hit.Payload, "references_in"),
+			Superseded:      getString(hit.Payload, "status") == "superseded",
 		}
 	}
 
+	// Authority-aware Re-Ranking: bindendes Recht der passenden Jurisdiktion/Domaene nach
+	// oben, Guidance/Fremdrecht/Off-Domain runter (nichts wird geloescht). Reihenfolge only,
+	// Response-Schema unveraendert. Score traegt den Authority-Score, damit nachgelagerte
+	// Multi-Collection-Merges (Advisor) die Ordnung bewahren.
+	results = rerankByAuthority(query, results)
+	if topK > 0 && len(results) > topK {
+		results = results[:topK]
+	}
+
 	return results, nil
 }
 
+// mergeDedupHits concatenates two hit lists, keeping the first occurrence of each point ID.
+func mergeDedupHits(primary, extra []qdrantSearchHit) []qdrantSearchHit {
+	seen := make(map[string]bool, len(primary)+len(extra))
+	out := make([]qdrantSearchHit, 0, len(primary)+len(extra))
+	for _, list := range [][]qdrantSearchHit{primary, extra} {
+		for _, h := range list {
+			id := fmt.Sprint(h.ID)
+			if seen[id] {
+				continue
+			}
+			seen[id] = true
+			out = append(out, h)
+		}
+	}
+	return out
+}
+
 // FormatLegalContextForPrompt formats the legal context for inclusion in an LLM prompt.
 func (c *LegalRAGClient) FormatLegalContextForPrompt(lc *LegalContext) string {
 	if lc == nil || len(lc.Results) == 0 {

ai-compliance-sdk/internal/ucca/legal_rag_graph.go

@@ -0,0 +1,162 @@
+package ucca
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"sort"
+)
+
+// Graph-augmented retrieval: when a top hit cites an annex/article (references_out)
+// or is cited by one (references_in), pull that connected norm into the candidate
+// pool via the PRECISE citation graph instead of hoping semantic search surfaces
+// it. E.g. a hit on CRA Art. 13 pulls in CRA Anhang I (the actual requirement).
+// Pool-augmentation only — authority re-rank + topK slice still apply, so the
+// response schema is unchanged.
+const (
+	graphSeedCount  = 5    // only the top hits seed the expansion
+	graphMaxExpand  = 15   // cap connected norms pulled in (avoid pool explosion)
+	graphHopPenalty = 0.05 // a one-hop neighbour ranks just below its seed
+)
+
+// expandViaGraph augments hits with the norms they cite and the norms that cite
+// them. Best-effort: on any error (or nothing to expand) the original hits are
+// returned unchanged.
+func (c *LegalRAGClient) expandViaGraph(ctx context.Context, collection string, hits []qdrantSearchHit) []qdrantSearchHit {
+	if len(hits) == 0 {
+		return hits
+	}
+	present := make(map[string]bool, len(hits))
+	for _, h := range hits {
+		if cu := getString(h.Payload, "citation_unit"); cu != "" {
+			present[cu] = true
+		}
+	}
+
+	seeds := hits
+	if len(seeds) > graphSeedCount {
+		seeds = seeds[:graphSeedCount]
+	}
+	// Forward edges only (references_out = the detail a hit explicitly points to,
+	// e.g. Art. 13 → Anhang I). Reverse (references_in) has high fan-out for popular
+	// annexes (Anhang I is cited by 23 articles) → pool flooding; it is surfaced as
+	// connected-norm metadata in the Phase 2 response instead of expanding the pool.
+	want := make(map[string]float64) // connected citation_unit -> best seeding score
+	for _, h := range seeds {
+		for _, cu := range getStringSlice(h.Payload, "references_out") {
+			if cu == "" || present[cu] {
+				continue
+			}
+			if s, ok := want[cu]; !ok || h.Score > s {
+				want[cu] = h.Score
+			}
+		}
+	}
+	if len(want) == 0 {
+		return hits
+	}
+
+	units := topByScore(want, graphMaxExpand)
+	fetched, err := c.fetchByCitationUnits(ctx, collection, units)
+	if err != nil || len(fetched) == 0 {
+		return hits
+	}
+	neighbours := make([]qdrantSearchHit, 0, len(fetched))
+	for cu, pt := range fetched {
+		neighbours = append(neighbours, qdrantSearchHit{ID: pt.ID, Score: want[cu] - graphHopPenalty, Payload: pt.Payload})
+	}
+	return mergeDedupHits(hits, neighbours)
+}
+
+// topByScore returns up to n keys with the highest values. Deterministic: ties
+// broken by the key string so the cap is stable across runs.
+func topByScore(m map[string]float64, n int) []string {
+	keys := make([]string, 0, len(m))
+	for k := range m {
+		keys = append(keys, k)
+	}
+	sort.Slice(keys, func(i, j int) bool {
+		if m[keys[i]] != m[keys[j]] {
+			return m[keys[i]] > m[keys[j]]
+		}
+		return keys[i] < keys[j]
+	})
+	if len(keys) > n {
+		keys = keys[:n]
+	}
+	return keys
+}
+
+// fetchByCitationUnits loads one representative point (the first chunk) per
+// citation_unit from the given collection.
+func (c *LegalRAGClient) fetchByCitationUnits(ctx context.Context, collection string, units []string) (map[string]qdrantScrollPoint, error) {
+	should := make([]map[string]interface{}, 0, len(units))
+	for _, cu := range units {
+		should = append(should, map[string]interface{}{"key": "citation_unit", "match": map[string]interface{}{"value": cu}})
+	}
+	reqBody := map[string]interface{}{
+		"limit":        len(units) * 4,
+		"with_payload": true,
+		"with_vectors": false,
+		"filter":       map[string]interface{}{"should": should},
+	}
+	jsonBody, err := json.Marshal(reqBody)
+	if err != nil {
+		return nil, err
+	}
+	url := fmt.Sprintf("%s/collections/%s/points/scroll", c.qdrantURL, collection)
+	req, err := http.NewRequestWithContext(ctx, "POST", url, bytes.NewReader(jsonBody))
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Content-Type", "application/json")
+	if c.qdrantAPIKey != "" {
+		req.Header.Set("api-key", c.qdrantAPIKey)
+	}
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		return nil, err
+	}
+	defer func() { _ = resp.Body.Close() }()
+	if resp.StatusCode != http.StatusOK {
+		body, _ := io.ReadAll(resp.Body)
+		return nil, fmt.Errorf("qdrant scroll returned %d: %s", resp.StatusCode, string(body))
+	}
+	var scrollResp qdrantScrollResponse
+	if err := json.NewDecoder(resp.Body).Decode(&scrollResp); err != nil {
+		return nil, err
+	}
+	out := make(map[string]qdrantScrollPoint, len(units))
+	for _, pt := range scrollResp.Result.Points {
+		cu := getString(pt.Payload, "citation_unit")
+		if cu != "" {
+			if _, seen := out[cu]; !seen {
+				out[cu] = pt
+			}
+		}
+	}
+	return out, nil
+}
+
+// getStringSlice extracts a []string from a Qdrant payload list field
+// (references_out / references_in are stored as JSON arrays of strings).
+func getStringSlice(m map[string]interface{}, key string) []string {
+	v, ok := m[key]
+	if !ok {
+		return nil
+	}
+	arr, ok := v.([]interface{})
+	if !ok {
+		return nil
+	}
+	out := make([]string, 0, len(arr))
+	for _, item := range arr {
+		if s, ok := item.(string); ok {
+			out = append(out, s)
+		}
+	}
+	return out
+}

ai-compliance-sdk/internal/ucca/legal_rag_graph_test.go

@@ -0,0 +1,89 @@
+package ucca
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+)
+
+func TestGetStringSlice(t *testing.T) {
+	m := map[string]interface{}{
+		"refs": []interface{}{"a", "b", 3, "c"}, // non-strings are skipped
+		"str":  "not-a-list",
+	}
+	got := getStringSlice(m, "refs")
+	if len(got) != 3 || got[0] != "a" || got[2] != "c" {
+		t.Errorf("refs: %v", got)
+	}
+	if getStringSlice(m, "missing") != nil {
+		t.Error("missing key should be nil")
+	}
+	if getStringSlice(m, "str") != nil {
+		t.Error("non-list should be nil")
+	}
+}
+
+func TestTopByScore_DeterministicCap(t *testing.T) {
+	m := map[string]float64{"x": 0.5, "y": 0.9, "z": 0.5, "w": 0.7}
+	got := topByScore(m, 2)
+	if len(got) != 2 || got[0] != "y" || got[1] != "w" {
+		t.Errorf("want [y w], got %v", got)
+	}
+	all := topByScore(m, 10)
+	if all[2] != "x" || all[3] != "z" { // tie 0.5 broken by key string
+		t.Errorf("tie-break not deterministic: %v", all)
+	}
+}
+
+func TestExpandViaGraph_NoSeedsOrRefs(t *testing.T) {
+	c := &LegalRAGClient{} // nil httpClient → must not be called on these paths
+	if out := c.expandViaGraph(context.Background(), "x", nil); out != nil {
+		t.Error("empty hits should return nil")
+	}
+	hits := []qdrantSearchHit{{ID: 1, Score: 0.8, Payload: map[string]interface{}{"citation_unit": "Art. 1 CRA"}}}
+	if out := c.expandViaGraph(context.Background(), "x", hits); len(out) != 1 {
+		t.Errorf("no references → unchanged, got %d", len(out))
+	}
+}
+
+func TestExpandViaGraph_PullsConnectedNorm(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		_ = json.NewEncoder(w).Encode(map[string]interface{}{
+			"result": map[string]interface{}{
+				"points": []map[string]interface{}{
+					{"id": 99, "payload": map[string]interface{}{
+						"citation_unit": "CRA Anhang I", "chunk_text": "Sicherheitsanforderungen",
+						"source_class": "binding_law", "authority_weight": 100, "regulation_short": "CRA",
+					}},
+				},
+				"next_page_offset": nil,
+			},
+		})
+	}))
+	defer srv.Close()
+
+	c := &LegalRAGClient{qdrantURL: srv.URL, httpClient: srv.Client()}
+	hits := []qdrantSearchHit{
+		{ID: 1, Score: 0.70, Payload: map[string]interface{}{
+			"citation_unit": "Art. 13 CRA", "references_out": []interface{}{"CRA Anhang I"},
+		}},
+	}
+	out := c.expandViaGraph(context.Background(), "bp_compliance_ce", hits)
+	if len(out) != 2 {
+		t.Fatalf("want 2 hits (seed + connected annex), got %d", len(out))
+	}
+	var found *qdrantSearchHit
+	for i := range out {
+		if getString(out[i].Payload, "citation_unit") == "CRA Anhang I" {
+			found = &out[i]
+		}
+	}
+	if found == nil {
+		t.Fatal("connected norm CRA Anhang I was not pulled into the pool")
+	}
+	if found.Score < 0.64 || found.Score > 0.66 { // 0.70 seed − 0.05 hop penalty
+		t.Errorf("connected score = %v, want ~0.65", found.Score)
+	}
+}

ai-compliance-sdk/internal/ucca/legal_rag_http.go

@@ -185,6 +185,55 @@ func (c *LegalRAGClient) searchDense(ctx context.Context, collection string, emb
 		searchReq.Filter = &qdrantFilter{Should: conditions}
 	}
 
+	return c.doPointsSearch(ctx, collection, searchReq)
+}
+
+// searchBinding fetches the top binding_law hits (authority-stratified pool) so the
+// obligation source is always a candidate even when guidance dominates semantically.
+// It AUGMENTS the semantic pool — guidance is preserved as interpretation context.
+func (c *LegalRAGClient) searchBinding(ctx context.Context, collection string, embedding []float64, topK int) ([]qdrantSearchHit, error) {
+	searchReq := qdrantSearchRequest{
+		Vector:      embedding,
+		Limit:       topK,
+		WithPayload: true,
+		Filter: &qdrantFilter{Must: []qdrantCondition{
+			{Key: "source_class", Match: qdrantMatch{Value: "binding_law"}},
+		}},
+	}
+
+	return c.doPointsSearch(ctx, collection, searchReq)
+}
+
+// controlPoolDepth is how deep the dense control pull reaches. Measured: for an EU-cyber
+// control query the relevant control sources sit at dense rank ~8-9 (NIST, CRA Annex), far
+// below the client's small top-K — so a fixed dense depth of 60 reliably surfaces them.
+const controlPoolDepth = 60
+
+// searchControls fetches a DEEP dense pool and keeps only the control-pool roles, so control
+// sources that the small top-K (hybrid) search misses become candidates on an implementation
+// question. Role is derived in code (no source_role tag needed). AUGMENTS the pool — the
+// caller gates it on control-intent.
+func (c *LegalRAGClient) searchControls(ctx context.Context, collection string, embedding []float64) ([]qdrantSearchHit, error) {
+	searchReq := qdrantSearchRequest{
+		Vector:      embedding,
+		Limit:       controlPoolDepth,
+		WithPayload: true,
+	}
+	hits, err := c.doPointsSearch(ctx, collection, searchReq)
+	if err != nil {
+		return nil, err
+	}
+	kept := make([]qdrantSearchHit, 0, len(hits))
+	for _, h := range hits {
+		if isControlPoolRole(controlRoleOf(h.Payload)) {
+			kept = append(kept, h)
+		}
+	}
+	return kept, nil
+}
+
+// doPointsSearch issues a POST /points/search and decodes the hits.
+func (c *LegalRAGClient) doPointsSearch(ctx context.Context, collection string, searchReq qdrantSearchRequest) ([]qdrantSearchHit, error) {
 	jsonBody, err := json.Marshal(searchReq)
 	if err != nil {
 		return nil, fmt.Errorf("failed to marshal search request: %w", err)

ai-compliance-sdk/internal/ucca/legal_rag_intent_test.go

@@ -0,0 +1,135 @@
+package ucca
+
+import "testing"
+
+func intentRes(reg, sourceClass string, sem float64, weight int) LegalSearchResult {
+	return LegalSearchResult{
+		RegulationShort: reg, SourceClass: sourceClass, Score: sem,
+		AuthorityWeight: weight, Jurisdiction: "EU",
+	}
+}
+
+func TestQueryWantsGuidance(t *testing.T) {
+	wants := []string{
+		"Was empfiehlt der EDPB zum DSB?",
+		"Was sagt die ENISA zu Security Updates?",
+		"laut DSK ...",
+		"Orientierungshilfe zur DSFA",
+		"Welche BSI-Empfehlung gilt?",
+		"Auslegung der Aufsichtsbehörde",
+	}
+	plain := []string{
+		"Ab wann braucht man einen Datenschutzbeauftragten?",
+		"Welche Anforderungen bestehen an Security Updates?",
+	}
+	for _, q := range wants {
+		if !queryWantsGuidance(q) {
+			t.Errorf("should detect interpretation intent: %q", q)
+		}
+	}
+	for _, q := range plain {
+		if queryWantsGuidance(q) {
+			t.Errorf("should NOT detect intent (norm question): %q", q)
+		}
+	}
+}
+
+func TestRerank_NormQuestion_BindingStaysTop(t *testing.T) {
+	// No intent signal → binding wins even though guidance is semantically higher.
+	results := []LegalSearchResult{
+		intentRes("EDPB DPO", "supervisory_guidance", 0.64, 70),
+		intentRes("DSGVO", "binding_law", 0.58, 100),
+	}
+	out := rerankByAuthority("Ab wann braucht man einen Datenschutzbeauftragten?", results)
+	if out[0].SourceClass != "binding_law" {
+		t.Errorf("norm question: binding must stay Top-1, got %s", out[0].SourceClass)
+	}
+}
+
+func TestRerank_InterpretationQuestion_GuidanceMayWin(t *testing.T) {
+	// Explicit intent + guidance semantically competitive → guidance wins.
+	results := []LegalSearchResult{
+		intentRes("EDPB DPO", "supervisory_guidance", 0.64, 70),
+		intentRes("DSGVO", "binding_law", 0.58, 100),
+	}
+	out := rerankByAuthority("Was empfiehlt der EDPB zum Datenschutzbeauftragten?", results)
+	if out[0].SourceClass != "supervisory_guidance" {
+		t.Errorf("interpretation question: guidance should win Top-1, got %s", out[0].SourceClass)
+	}
+}
+
+func TestRerank_OffTopicGuidance_BlockedByGuard(t *testing.T) {
+	// Intent present, but guidance semantic is far below the best binding hit →
+	// the margin guard keeps binding on top (no off-topic guideline override).
+	results := []LegalSearchResult{
+		intentRes("EDPB DPO", "supervisory_guidance", 0.40, 70),
+		intentRes("DSGVO", "binding_law", 0.58, 100),
+	}
+	out := rerankByAuthority("Was empfiehlt der EDPB zum Datenschutzbeauftragten?", results)
+	if out[0].SourceClass != "binding_law" {
+		t.Errorf("off-topic guidance must not win even with intent, got %s", out[0].SourceClass)
+	}
+}
+
+func TestQueryWantsControls(t *testing.T) {
+	wants := []string{
+		"Welche Controls passen zu Security Updates?",
+		"Welche Maßnahmen sollten wir umsetzen?",
+		"Wie härten wir den Server ab?",
+		"Gibt es NIST-Controls dafür?",
+		"OWASP Best Practice für Logging?",
+		"BSI Grundschutz Bausteine",
+	}
+	plain := []string{
+		"Welche Anforderungen bestehen an Security Updates?",
+		"Ab wann braucht man einen Datenschutzbeauftragten?",
+	}
+	for _, q := range wants {
+		if !queryWantsControls(q) {
+			t.Errorf("should detect control/implementation intent: %q", q)
+		}
+	}
+	for _, q := range plain {
+		if queryWantsControls(q) {
+			t.Errorf("should NOT detect control intent (norm question): %q", q)
+		}
+	}
+}
+
+func TestRerank_ControlQuestion_OperationalReqTop(t *testing.T) {
+	// User priority for implementation questions: operational_requirement (binding concrete,
+	// CRA Anhang I) > control_standard (NIST). Both are in the control-pool; op_req wins.
+	results := []LegalSearchResult{
+		{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8", SourceClass: "technical_standard", AuthorityWeight: 80, Jurisdiction: "EU", Score: 0.60},
+		{RegulationShort: "CRA", ArticleLabel: "CRA Anhang I", Category: "regulation", Score: 0.58},
+	}
+	out := rerankByAuthority("Welche Controls und Massnahmen passen zu Security Updates?", results)
+	if out[0].RegulationShort != "CRA" {
+		t.Errorf("operational_requirement (CRA Anhang I) should be Top-1 over control_standard, got %q", out[0].RegulationShort)
+	}
+}
+
+func TestRerank_NormQuestion_BindingOverStandard(t *testing.T) {
+	// "Anforderungen" → no control intent → binding obligation stays Top-1 over the standard.
+	results := []LegalSearchResult{
+		intentRes("NIST SP 800-82", "technical_standard", 0.62, 80),
+		intentRes("CRA", "binding_law", 0.58, 100),
+	}
+	out := rerankByAuthority("Welche Anforderungen bestehen an Security Updates?", results)
+	if out[0].SourceClass != "binding_law" {
+		t.Errorf("norm question: binding must stay Top-1 over standard, got %s", out[0].SourceClass)
+	}
+}
+
+func TestRerank_ControlQuestion_PoolBeatsBareObligation(t *testing.T) {
+	// A control-pool source (NIST control_standard) outranks an abstract obligation with no
+	// domain/topic advantage, because the implementation intent boosts the control-pool.
+	results := []LegalSearchResult{
+		{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8", SourceClass: "technical_standard", AuthorityWeight: 80, Jurisdiction: "EU", Score: 0.55},
+		{RegulationShort: "XYZ", ArticleLabel: "Art. 5 XYZ", Category: "regulation", Score: 0.58},
+	}
+	out := rerankByAuthority("Welche Controls und Massnahmen passen zu Security Updates?", results)
+	if out[0].RegulationShort != "NIST SP 800-82r3" {
+		t.Errorf("control_standard should beat a bare abstract obligation on a control question, got %q", out[0].RegulationShort)
+	}
+}

ai-compliance-sdk/internal/ucca/legal_rag_scroll.go

@@ -225,6 +225,18 @@ func getIntSlice(m map[string]interface{}, key string) []int {
 	return result
 }
 
+func getInt(m map[string]interface{}, key string) int {
+	if v, ok := m[key]; ok {
+		switch n := v.(type) {
+		case float64:
+			return int(n)
+		case int:
+			return n
+		}
+	}
+	return 0
+}
+
 func contains(slice []string, item string) bool {
 	for _, s := range slice {
 		if s == item {

ai-compliance-sdk/internal/ucca/legal_rag_supersede_test.go

@@ -0,0 +1,30 @@
+package ucca
+
+import "testing"
+
+// A superseded alt-source must rank below the same result when it is NOT
+// superseded (the eu-v1 norm), but only demoted — the penalty is finite, so it
+// stays in the pool and remains findable for history/transition questions.
+func TestAuthorityScore_SupersededIsDemotedNotRemoved(t *testing.T) {
+	fresh := LegalSearchResult{
+		Score: 0.65, SourceClass: "binding_law", AuthorityWeight: 100,
+		Jurisdiction: "EU", RegulationShort: "CRA", Article: "13",
+	}
+	old := fresh
+	old.Superseded = true
+
+	sFresh := authorityScore("CRA Sicherheitsupdates Hersteller", fresh, "", false)
+	sOld := authorityScore("CRA Sicherheitsupdates Hersteller", old, "", false)
+
+	if sOld >= sFresh {
+		t.Errorf("superseded must score lower: fresh=%.3f superseded=%.3f", sFresh, sOld)
+	}
+	gap := sFresh - sOld
+	if gap < supersededPenalty-0.001 || gap > supersededPenalty+0.001 {
+		t.Errorf("demotion should equal supersededPenalty (%.2f), got %.3f", supersededPenalty, gap)
+	}
+	// Still a positive, finite score → present in the pool, not hidden.
+	if sOld <= -1 {
+		t.Errorf("superseded score collapsed (%.3f) — must remain findable", sOld)
+	}
+}

ai-compliance-sdk/internal/ucca/legal_rag_test.go

@@ -399,8 +399,9 @@ func TestHybridSearch_UsesQueryAPI(t *testing.T) {
 			return
 		}
 
-		// Fallback: should not reach dense search
+		// /points/search is now the stratified binding-law augmentation query (it AUGMENTS
-		t.Error("Unexpected dense search call when hybrid succeeded")
+		// the hybrid pool, it is not a dense fallback). Return empty so the hybrid hit
+		// remains the sole result for this test.
 		json.NewEncoder(w).Encode(qdrantSearchResponse{Result: []qdrantSearchHit{}})
 	}))
 	defer qdrantMock.Close()
@@ -446,6 +447,59 @@ func TestHybridSearch_UsesQueryAPI(t *testing.T) {
 	}
 }
 
+// TestSearch_StratifiedBindingRerank verifies that the binding-law pool augments the
+// semantic pool and that authority re-ranking lifts binding law above higher-semantic guidance.
+func TestSearch_StratifiedBindingRerank(t *testing.T) {
+	ollamaMock := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		json.NewEncoder(w).Encode(ollamaEmbeddingResponse{Embedding: make([]float64, 1024)})
+	}))
+	defer ollamaMock.Close()
+
+	qdrantMock := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if strings.Contains(r.URL.Path, "/index") {
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"result":{"status":"completed"}}`))
+			return
+		}
+		if strings.Contains(r.URL.Path, "/points/query") {
+			json.NewEncoder(w).Encode(qdrantQueryResponse{Result: []qdrantSearchHit{
+				{ID: "g1", Score: 0.72, Payload: map[string]interface{}{
+					"chunk_text": "ENISA guidance", "regulation_short": "ENISA",
+					"article_label": "ENISA CRA Mapping", "source_class": "supervisory_guidance",
+					"authority_weight": float64(70), "jurisdiction": "EU",
+				}},
+			}})
+			return
+		}
+		// /points/search = stratified binding-law pool (source_class=binding_law)
+		json.NewEncoder(w).Encode(qdrantSearchResponse{Result: []qdrantSearchHit{
+			{ID: "b1", Score: 0.66, Payload: map[string]interface{}{
+				"chunk_text": "CRA Anhang I requirement", "regulation_short": "CRA",
+				"article_label": "CRA Anhang I", "source_class": "binding_law",
+				"authority_weight": float64(100), "jurisdiction": "EU",
+			}},
+		}})
+	}))
+	defer qdrantMock.Close()
+
+	client := &LegalRAGClient{
+		qdrantURL: qdrantMock.URL, ollamaURL: ollamaMock.URL, embeddingModel: "bge-m3",
+		collection: "bp_compliance_ce", textIndexEnsured: make(map[string]bool),
+		hybridEnabled: true, httpClient: http.DefaultClient,
+	}
+
+	results, err := client.Search(context.Background(), "Was gilt hier?", nil, 5)
+	if err != nil {
+		t.Fatalf("search failed: %v", err)
+	}
+	if len(results) != 2 {
+		t.Fatalf("expected 2 merged results (guidance + binding), got %d", len(results))
+	}
+	if results[0].RegulationShort != "CRA" {
+		t.Errorf("binding CRA must rank first over higher-semantic guidance, got %q", results[0].RegulationShort)
+	}
+}
+
 func TestHybridSearch_FallbackToDense(t *testing.T) {
 	var requestedPaths []string
 

ai-compliance-sdk/internal/ucca/legal_rag_types.go

@@ -20,6 +20,38 @@ type LegalSearchResult struct {
 	Pages           []int   `json:"pages,omitempty"`
 	SourceURL       string  `json:"source_url"`
 	Score           float64 `json:"score"`
+
+	// Interne Felder fuer das Authority-Re-Ranking (Phase 1) — NICHT serialisiert
+	// (json:"-"), daher kein Contract-Change. Aus dem Qdrant-Payload befuellt und nur
+	// fuer die Sortierung in rerankByAuthority verwendet.
+	AuthorityWeight int    `json:"-"`
+	SourceClass     string `json:"-"`
+	Jurisdiction    string `json:"-"`
+
+	// Zitations-Graph (Phase 2) — intern, speist nur die Assessment-Berechnung
+	// (verbundene Normen, Begruendung). Pro-Result-Schema bleibt eingefroren.
+	CitationUnit  string   `json:"-"`
+	ReferencesOut []string `json:"-"`
+	ReferencesIn  []string `json:"-"`
+
+	// Supersede-Status (status="superseded", use_for_primary=false) — Alt-Quelle,
+	// die fuer Default-Fragen demoted wird (nicht versteckt; fuer Historie auffindbar).
+	Superseded bool `json:"-"`
+}
+
+// LegalAssessment is the auditable explanation layer over a ranked result set:
+// which norm is primary, which norms connect to it via the citation graph,
+// whether the answer crosses regulatory regimes, and whether a human should
+// review. Computed from the already-ranked results — it EXPLAINS retrieval, it
+// does not change it (graph edges for reasoning/completeness, not pool-expansion).
+type LegalAssessment struct {
+	PrimaryNorm       string   `json:"primary_norm"`
+	PrimaryRegulation string   `json:"primary_regulation"`
+	ConnectedNorms    []string `json:"connected_norms"`
+	CrossRegime       bool     `json:"cross_regime"`
+	HumanReviewFlag   bool     `json:"human_review_flag"`
+	WinnerMargin      float64  `json:"winner_margin"`
+	ScoreReasoning    string   `json:"score_reasoning"`
 }
 
 // LegalContext represents aggregated legal context for an assessment.