Felipe Cardoso
60ebeaa582
test(safety): add comprehensive tests for safety framework modules
...
Add tests to improve backend coverage from 85% to 93%:
- test_audit.py: 60 tests for AuditLogger (20% -> 99%)
- Hash chain integrity, sanitization, retention, handlers
- Fixed bug: hash chain modification after event creation
- Fixed bug: verification not using correct prev_hash
- test_hitl.py: Tests for HITL manager (0% -> 100%)
- test_permissions.py: Tests for permissions manager (0% -> 99%)
- test_rollback.py: Tests for rollback manager (0% -> 100%)
- test_metrics.py: Tests for metrics collector (0% -> 100%)
- test_mcp_integration.py: Tests for MCP safety wrapper (0% -> 100%)
- test_validation.py: Additional cache and edge case tests (76% -> 100%)
- test_scoring.py: Lock cleanup and edge case tests (78% -> 91%)
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-04 19:41:54 +01:00
Felipe Cardoso
520c06175e
refactor(safety): apply consistent formatting across services and tests
...
Improved code readability and uniformity by standardizing line breaks, indentation, and inline conditions across safety-related services, models, and tests, including content filters, validation rules, and emergency controls.
2026-01-03 16:23:39 +01:00
Felipe Cardoso
498c0a0e94
feat(backend): add safety framework foundation (Phase A) ( #63 )
...
Core safety framework architecture for autonomous agent guardrails:
**Core Components:**
- SafetyGuardian: Main orchestrator for all safety checks
- AuditLogger: Comprehensive audit logging with hash chain tamper detection
- SafetyConfig: Pydantic-based configuration
- Models: Action requests, validation results, policies, checkpoints
**Exception Hierarchy:**
- SafetyError base with context preservation
- Permission, Budget, RateLimit, Loop errors
- Approval workflow errors (Required, Denied, Timeout)
- Rollback, Sandbox, Emergency exceptions
**Safety Policy System:**
- Autonomy level based policies (FULL_CONTROL, MILESTONE, AUTONOMOUS)
- Cost limits, rate limits, permission patterns
- HITL approval requirements per action type
- Configurable loop detection thresholds
**Directory Structure:**
- validation/, costs/, limits/, loops/ - Control subsystems
- permissions/, rollback/, hitl/ - Access and recovery
- content/, sandbox/, emergency/ - Protection systems
- audit/, policies/ - Logging and configuration
Phase A establishes the architecture. Subsystems to be implemented in Phase B-C.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-03 11:22:25 +01:00
