feat(ai-sdk): authority-aware re-ranking for legal RAG (Phase 1) (#31)
CI / detect-changes (push) Successful in 8s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / secret-scan (push) Has been skipped
CI / dep-audit (push) Has been skipped
CI / sbom-scan (push) Has been skipped
CI / build-sha-integrity (push) Successful in 5s
CI / validate-canonical-controls (push) Successful in 4s
CI / loc-budget (push) Successful in 28s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Has been skipped
CI / test-go (push) Successful in 58s
CI / iace-gt-coverage (push) Successful in 16s
CI / test-python-backend (push) Has been skipped
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped

This commit was merged in pull request #31.
This commit is contained in:
2026-06-23 09:30:52 +00:00
parent 23c6ac6f32
commit a1f425d43a
9 changed files with 641 additions and 2 deletions
@@ -399,8 +399,9 @@ func TestHybridSearch_UsesQueryAPI(t *testing.T) {
return
}
// Fallback: should not reach dense search
t.Error("Unexpected dense search call when hybrid succeeded")
// /points/search is now the stratified binding-law augmentation query (it AUGMENTS
// 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