forked from cardosofelipe/fast-next-template
Felipe Cardoso
498c0a0e94
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>
171 lines
3.5 KiB
Python
171 lines
3.5 KiB
Python
"""
|
|
Safety and Guardrails Framework
|
|
|
|
Comprehensive safety framework for autonomous agent operation.
|
|
Provides multi-layered protection including:
|
|
- Pre-execution validation
|
|
- Cost and budget controls
|
|
- Rate limiting
|
|
- Loop detection and prevention
|
|
- Human-in-the-loop approval
|
|
- Rollback and checkpointing
|
|
- Content filtering
|
|
- Sandboxed execution
|
|
- Emergency controls
|
|
- Complete audit trail
|
|
|
|
Usage:
|
|
from app.services.safety import get_safety_guardian, SafetyGuardian
|
|
|
|
guardian = await get_safety_guardian()
|
|
result = await guardian.validate(action_request)
|
|
|
|
if result.allowed:
|
|
# Execute action
|
|
pass
|
|
else:
|
|
# Handle denial
|
|
print(f"Action denied: {result.reasons}")
|
|
"""
|
|
|
|
# Exceptions
|
|
# Audit
|
|
from .audit import (
|
|
AuditLogger,
|
|
get_audit_logger,
|
|
reset_audit_logger,
|
|
shutdown_audit_logger,
|
|
)
|
|
|
|
# Configuration
|
|
from .config import (
|
|
AutonomyConfig,
|
|
SafetyConfig,
|
|
get_autonomy_config,
|
|
get_default_policy,
|
|
get_policy_for_autonomy_level,
|
|
get_safety_config,
|
|
load_policies_from_directory,
|
|
load_policy_from_file,
|
|
reset_config_cache,
|
|
)
|
|
from .exceptions import (
|
|
ApprovalDeniedError,
|
|
ApprovalRequiredError,
|
|
ApprovalTimeoutError,
|
|
BudgetExceededError,
|
|
CheckpointError,
|
|
ContentFilterError,
|
|
EmergencyStopError,
|
|
LoopDetectedError,
|
|
PermissionDeniedError,
|
|
PolicyViolationError,
|
|
RateLimitExceededError,
|
|
RollbackError,
|
|
SafetyError,
|
|
SandboxError,
|
|
SandboxTimeoutError,
|
|
ValidationError,
|
|
)
|
|
|
|
# Guardian
|
|
from .guardian import (
|
|
SafetyGuardian,
|
|
get_safety_guardian,
|
|
reset_safety_guardian,
|
|
shutdown_safety_guardian,
|
|
)
|
|
|
|
# Models
|
|
from .models import (
|
|
ActionMetadata,
|
|
ActionRequest,
|
|
ActionResult,
|
|
ActionType,
|
|
ApprovalRequest,
|
|
ApprovalResponse,
|
|
ApprovalStatus,
|
|
AuditEvent,
|
|
AuditEventType,
|
|
AutonomyLevel,
|
|
BudgetScope,
|
|
BudgetStatus,
|
|
Checkpoint,
|
|
CheckpointType,
|
|
GuardianResult,
|
|
PermissionLevel,
|
|
RateLimitConfig,
|
|
RateLimitStatus,
|
|
ResourceType,
|
|
RollbackResult,
|
|
SafetyDecision,
|
|
SafetyPolicy,
|
|
ValidationResult,
|
|
ValidationRule,
|
|
)
|
|
|
|
__all__ = [
|
|
"ActionMetadata",
|
|
"ActionRequest",
|
|
"ActionResult",
|
|
# Models
|
|
"ActionType",
|
|
"ApprovalDeniedError",
|
|
"ApprovalRequest",
|
|
"ApprovalRequiredError",
|
|
"ApprovalResponse",
|
|
"ApprovalStatus",
|
|
"ApprovalTimeoutError",
|
|
"AuditEvent",
|
|
"AuditEventType",
|
|
# Audit
|
|
"AuditLogger",
|
|
"AutonomyConfig",
|
|
"AutonomyLevel",
|
|
"BudgetExceededError",
|
|
"BudgetScope",
|
|
"BudgetStatus",
|
|
"Checkpoint",
|
|
"CheckpointError",
|
|
"CheckpointType",
|
|
"ContentFilterError",
|
|
"EmergencyStopError",
|
|
"GuardianResult",
|
|
"LoopDetectedError",
|
|
"PermissionDeniedError",
|
|
"PermissionLevel",
|
|
"PolicyViolationError",
|
|
"RateLimitConfig",
|
|
"RateLimitExceededError",
|
|
"RateLimitStatus",
|
|
"ResourceType",
|
|
"RollbackError",
|
|
"RollbackResult",
|
|
# Configuration
|
|
"SafetyConfig",
|
|
"SafetyDecision",
|
|
# Exceptions
|
|
"SafetyError",
|
|
# Guardian
|
|
"SafetyGuardian",
|
|
"SafetyPolicy",
|
|
"SandboxError",
|
|
"SandboxTimeoutError",
|
|
"ValidationError",
|
|
"ValidationResult",
|
|
"ValidationRule",
|
|
"get_audit_logger",
|
|
"get_autonomy_config",
|
|
"get_default_policy",
|
|
"get_policy_for_autonomy_level",
|
|
"get_safety_config",
|
|
"get_safety_guardian",
|
|
"load_policies_from_directory",
|
|
"load_policy_from_file",
|
|
"reset_audit_logger",
|
|
"reset_config_cache",
|
|
"reset_safety_guardian",
|
|
"shutdown_audit_logger",
|
|
"shutdown_safety_guardian",
|
|
]
|