The monolithic compliance/db/models.py is decomposed into seven sibling
aggregate modules following the existing repo pattern (dsr_models.py,
vvt_models.py, tom_models.py, etc.):
regulation_models.py (134 LOC) — RegulationDB, RequirementDB
control_models.py (279 LOC) — ControlDB, ControlMappingDB, EvidenceDB, RiskDB
ai_system_models.py (141 LOC) — AISystemDB, AuditExportDB
service_module_models.py (176 LOC) — ServiceModuleDB, ModuleRegulationMappingDB, ModuleRiskDB
audit_session_models.py (177 LOC) — AuditSessionDB, AuditSignOffDB
isms_governance_models.py (323 LOC) — ISMSScope, Context, Policy, Objective, SoA
isms_audit_models.py (468 LOC) — AuditFinding, CAPA, ManagementReview, InternalAudit,
AuditTrail, ReadinessCheck
models.py becomes an 85-line re-export shim — every public symbol is
re-exported in dependency order so existing imports work unchanged:
from compliance.db.models import RegulationDB, ControlDB, AuditFindingDB # still works
New code SHOULD import from the aggregate module directly; the shim is
for backwards compatibility during the migration.
Schema freeze preserved:
- __tablename__ byte-identical
- Column names, types, indexes, constraints byte-identical
- relationship() string references and back_populates unchanged
- cascade directives unchanged
Verified:
- 173/173 pytest compliance/tests/ pass
- tests/contracts/test_openapi_baseline.py passes (360 paths,
484 operations — identical to baseline)
- All new sibling files under the 500-line hard cap
(largest: isms_audit_models.py at 468 LOC)
- No file in compliance/db/ now exceeds the hard cap
This is Phase 1 Step 2 from PHASE1_RUNBOOK.md. Phase 1 Step 3 (split
compliance/api/schemas.py, 1899 LOC) is the next target.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
177 lines
7.5 KiB
Python
177 lines
7.5 KiB
Python
"""
|
|
Service Module Registry models — extracted from compliance/db/models.py.
|
|
|
|
Sprint 3: registry of all Breakpilot services/modules for compliance mapping,
|
|
per-module regulation applicability, and per-module risk aggregation.
|
|
Re-exported from ``compliance.db.models`` for backwards compatibility.
|
|
|
|
DO NOT change __tablename__, column names, or relationship strings.
|
|
"""
|
|
|
|
import uuid
|
|
import enum
|
|
from datetime import datetime, timezone
|
|
|
|
from sqlalchemy import (
|
|
Column, String, Text, Integer, Boolean, DateTime,
|
|
ForeignKey, Enum, JSON, Index, Float,
|
|
)
|
|
from sqlalchemy.orm import relationship
|
|
|
|
from classroom_engine.database import Base
|
|
# RiskLevelEnum is re-used across aggregates; sourced here from control_models.
|
|
from compliance.db.control_models import RiskLevelEnum # noqa: F401
|
|
|
|
|
|
# ============================================================================
|
|
# ENUMS
|
|
# ============================================================================
|
|
|
|
class ServiceTypeEnum(str, enum.Enum):
|
|
"""Type of Breakpilot service/module."""
|
|
BACKEND = "backend" # API/Backend services
|
|
DATABASE = "database" # Data storage
|
|
AI = "ai" # AI/ML services
|
|
COMMUNICATION = "communication" # Chat/Video/Messaging
|
|
STORAGE = "storage" # File/Object storage
|
|
INFRASTRUCTURE = "infrastructure" # Load balancer, reverse proxy
|
|
MONITORING = "monitoring" # Logging, metrics
|
|
SECURITY = "security" # Auth, encryption, secrets
|
|
|
|
|
|
class RelevanceLevelEnum(str, enum.Enum):
|
|
"""Relevance level of a regulation to a service."""
|
|
CRITICAL = "critical" # Non-compliance = shutdown
|
|
HIGH = "high" # Major risk
|
|
MEDIUM = "medium" # Moderate risk
|
|
LOW = "low" # Minor risk
|
|
|
|
|
|
# ============================================================================
|
|
# MODELS
|
|
# ============================================================================
|
|
|
|
class ServiceModuleDB(Base):
|
|
"""
|
|
Registry of all Breakpilot services/modules for compliance mapping.
|
|
|
|
Tracks which regulations apply to which services, enabling:
|
|
- Service-specific compliance views
|
|
- Aggregated risk per service
|
|
- Gap analysis by module
|
|
"""
|
|
__tablename__ = 'compliance_service_modules'
|
|
|
|
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
name = Column(String(100), unique=True, nullable=False, index=True) # e.g., "consent-service"
|
|
display_name = Column(String(200), nullable=False) # e.g., "Go Consent Service"
|
|
description = Column(Text)
|
|
|
|
# Technical details
|
|
service_type = Column(Enum(ServiceTypeEnum), nullable=False)
|
|
port = Column(Integer) # Primary port (if applicable)
|
|
technology_stack = Column(JSON) # e.g., ["Go", "Gin", "PostgreSQL"]
|
|
repository_path = Column(String(500)) # e.g., "/consent-service"
|
|
docker_image = Column(String(200)) # e.g., "breakpilot-pwa-consent-service"
|
|
|
|
# Data categories handled
|
|
data_categories = Column(JSON) # e.g., ["personal_data", "consent_records"]
|
|
processes_pii = Column(Boolean, default=False) # Handles personally identifiable info?
|
|
processes_health_data = Column(Boolean, default=False) # Handles special category health data?
|
|
ai_components = Column(Boolean, default=False) # Contains AI/ML components?
|
|
|
|
# Status
|
|
is_active = Column(Boolean, default=True)
|
|
criticality = Column(String(20), default="medium") # "critical", "high", "medium", "low"
|
|
|
|
# Compliance aggregation
|
|
compliance_score = Column(Float) # Calculated score 0-100
|
|
last_compliance_check = Column(DateTime)
|
|
|
|
# Owner
|
|
owner_team = Column(String(100)) # e.g., "Backend Team"
|
|
owner_contact = Column(String(200)) # e.g., "backend@breakpilot.app"
|
|
|
|
# Timestamps
|
|
created_at = Column(DateTime, default=lambda: datetime.now(timezone.utc))
|
|
updated_at = Column(DateTime, default=lambda: datetime.now(timezone.utc), onupdate=lambda: datetime.now(timezone.utc))
|
|
|
|
# Relationships
|
|
regulation_mappings = relationship("ModuleRegulationMappingDB", back_populates="module", cascade="all, delete-orphan")
|
|
module_risks = relationship("ModuleRiskDB", back_populates="module", cascade="all, delete-orphan")
|
|
|
|
__table_args__ = (
|
|
Index('ix_module_type_active', 'service_type', 'is_active'),
|
|
)
|
|
|
|
def __repr__(self):
|
|
return f"<ServiceModule {self.name}: {self.display_name}>"
|
|
|
|
|
|
class ModuleRegulationMappingDB(Base):
|
|
"""
|
|
Maps services to applicable regulations with relevance level.
|
|
|
|
Enables filtering: "Show all GDPR requirements for consent-service"
|
|
"""
|
|
__tablename__ = 'compliance_module_regulations'
|
|
|
|
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
module_id = Column(String(36), ForeignKey('compliance_service_modules.id'), nullable=False, index=True)
|
|
regulation_id = Column(String(36), ForeignKey('compliance_regulations.id'), nullable=False, index=True)
|
|
|
|
relevance_level = Column(Enum(RelevanceLevelEnum), nullable=False, default=RelevanceLevelEnum.MEDIUM)
|
|
notes = Column(Text) # Why this regulation applies
|
|
applicable_articles = Column(JSON) # List of specific articles that apply
|
|
|
|
# Timestamps
|
|
created_at = Column(DateTime, default=lambda: datetime.now(timezone.utc))
|
|
updated_at = Column(DateTime, default=lambda: datetime.now(timezone.utc), onupdate=lambda: datetime.now(timezone.utc))
|
|
|
|
# Relationships
|
|
module = relationship("ServiceModuleDB", back_populates="regulation_mappings")
|
|
regulation = relationship("RegulationDB")
|
|
|
|
__table_args__ = (
|
|
Index('ix_module_regulation', 'module_id', 'regulation_id', unique=True),
|
|
)
|
|
|
|
|
|
class ModuleRiskDB(Base):
|
|
"""
|
|
Service-specific risks aggregated from requirements and controls.
|
|
"""
|
|
__tablename__ = 'compliance_module_risks'
|
|
|
|
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
|
|
module_id = Column(String(36), ForeignKey('compliance_service_modules.id'), nullable=False, index=True)
|
|
risk_id = Column(String(36), ForeignKey('compliance_risks.id'), nullable=False, index=True)
|
|
|
|
# Module-specific assessment
|
|
module_likelihood = Column(Integer) # 1-5, may differ from global
|
|
module_impact = Column(Integer) # 1-5, may differ from global
|
|
module_risk_level = Column(Enum(RiskLevelEnum))
|
|
|
|
assessment_notes = Column(Text) # Module-specific notes
|
|
|
|
# Timestamps
|
|
created_at = Column(DateTime, default=lambda: datetime.now(timezone.utc))
|
|
updated_at = Column(DateTime, default=lambda: datetime.now(timezone.utc), onupdate=lambda: datetime.now(timezone.utc))
|
|
|
|
# Relationships
|
|
module = relationship("ServiceModuleDB", back_populates="module_risks")
|
|
risk = relationship("RiskDB")
|
|
|
|
__table_args__ = (
|
|
Index('ix_module_risk', 'module_id', 'risk_id', unique=True),
|
|
)
|
|
|
|
|
|
__all__ = [
|
|
"ServiceTypeEnum",
|
|
"RelevanceLevelEnum",
|
|
"ServiceModuleDB",
|
|
"ModuleRegulationMappingDB",
|
|
"ModuleRiskDB",
|
|
]
|