Files
breakpilot-compliance/ai-compliance-sdk/internal/ucca/legal_rag_intent_test.go
T
Benjamin Admin ae73904ad5
CI / detect-changes (pull_request) Successful in 7s
CI / branch-name (pull_request) Successful in 1s
CI / guardrail-integrity (pull_request) Successful in 5s
CI / secret-scan (pull_request) Successful in 5s
CI / dep-audit (pull_request) Failing after 55s
CI / sbom-scan (pull_request) Failing after 1m0s
CI / build-sha-integrity (pull_request) Successful in 6s
CI / validate-canonical-controls (pull_request) Successful in 6s
CI / loc-budget (pull_request) Successful in 19s
CI / go-lint (pull_request) Successful in 41s
CI / python-lint (pull_request) Failing after 14s
CI / nodejs-lint (pull_request) Failing after 1m10s
CI / nodejs-build (pull_request) Successful in 3m3s
CI / test-go (pull_request) Successful in 59s
CI / iace-gt-coverage (pull_request) Successful in 17s
CI / test-python-backend (pull_request) Successful in 27s
CI / test-python-document-crawler (pull_request) Successful in 13s
CI / test-python-dsms-gateway (pull_request) Successful in 9s
feat(ai-sdk): controlled interpretation-intent guidance override
The authority re-rank always ranked binding law above guidance, so a guideline
could never be Top-1 even when the user explicitly asked "what does the EDPB /
ENISA say?". Add a tightly-bounded override: only when the query carries an
explicit guidance signal (EDPB / DSK / ENISA / BSI / Leitlinie / Guideline /
Orientierungshilfe / Auslegung / empfiehlt / Empfehlung / sagt / laut) AND the
guideline is semantically competitive with the best binding hit (>= best_binding
- 0.05) does supervisory_guidance get a +0.25 boost that lets it overtake the
binding norm. Obligation questions (no signal) are unchanged: binding stays #1.

Gate verified on dev:
- "Ab wann DSB-Pflicht?"                  -> Art. 37 DSGVO (binding) Top-1
- "Was empfiehlt der EDPB zum DSB?"       -> EDPB guidance Top-1
- "Was sagt die ENISA zu Security Updates?" -> ENISA guidance Top-1
- "Welche Anforderungen an Security Updates?" -> Art. 13 CRA (binding) Top-1

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-24 10:51:02 +02:00

73 lines
2.5 KiB
Go

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)
}
}