feat: Anti-Fake-Evidence System (Phase 1-4b)

Implement full evidence integrity pipeline to prevent compliance theater:
- Confidence levels (E0-E4), truth status tracking, assertion engine
- Four-Eyes approval workflow, audit trail, reject endpoint
- Evidence distribution dashboard, LLM audit routes
- Traceability matrix (backend endpoint + Compliance Hub UI tab)
- Anti-fake badges, control status machine, normative patterns
- 2 migrations, 4 test suites, MkDocs documentation

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

backend-compliance/compliance/db/__init__.py

@@ -8,12 +8,16 @@ from .models import (
     EvidenceDB,
     RiskDB,
     AuditExportDB,
+    LLMGenerationAuditDB,
+    AssertionDB,
     RegulationTypeEnum,
     ControlTypeEnum,
     ControlDomainEnum,
     RiskLevelEnum,
     EvidenceStatusEnum,
     ControlStatusEnum,
+    EvidenceConfidenceEnum,
+    EvidenceTruthStatusEnum,
 )
 from .repository import (
     RegulationRepository,
@@ -33,6 +37,8 @@ __all__ = [
     "EvidenceDB",
     "RiskDB",
     "AuditExportDB",
+    "LLMGenerationAuditDB",
+    "AssertionDB",
     # Enums
     "RegulationTypeEnum",
     "ControlTypeEnum",
@@ -40,6 +46,8 @@ __all__ = [
     "RiskLevelEnum",
     "EvidenceStatusEnum",
     "ControlStatusEnum",
+    "EvidenceConfidenceEnum",
+    "EvidenceTruthStatusEnum",
     # Repositories
     "RegulationRepository",
     "RequirementRepository",