cardosofelipe/syndarix
1
0
Fork 0
forked from cardosofelipe/fast-next-template
Code Issues 18 Pull Requests Wiki Activity
468 Commits 3 Branches 0 Tags
da85a8aba8726a9333223601ac818b8449d73c7a
Commit Graph

9 Commits

Author SHA1 Message Date
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
caf283bed2 feat(safety): enhance rate limiting and cost control with alert deduplication and usage tracking 
- Added `record_action` in `RateLimiter` for precise tracking of slot consumption post-validation.
- Introduced deduplication mechanism for warning alerts in `CostController` to prevent spamming.
- Refactored `CostController`'s session and daily budget alert handling for improved clarity.
- Implemented test suites for `CostController` and `SafetyGuardian` to validate changes.
- Expanded integration testing to cover deduplication, validation, and loop detection edge cases.
 2026-01-03 17:55:34 +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
c8b88dadc3 fix(safety): copy default patterns to avoid test pollution 
The ContentFilter was appending references to DEFAULT_PATTERNS objects,
so when tests modified patterns (e.g., disabling them), those changes
persisted across test runs. Use dataclass replace() to create copies.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-03 12:08:43 +01:00
Felipe Cardoso
015f2de6c6 test(safety): add Phase E comprehensive safety tests 
- Add tests for models: ActionMetadata, ActionRequest, ActionResult,
  ValidationRule, BudgetStatus, RateLimitConfig, ApprovalRequest/Response,
  Checkpoint, RollbackResult, AuditEvent, SafetyPolicy, GuardianResult
- Add tests for validation: ActionValidator rules, priorities, patterns,
  bypass mode, batch validation, rule creation helpers
- Add tests for loops: LoopDetector exact/semantic/oscillation detection,
  LoopBreaker throttle/backoff, history management
- Add tests for content filter: PII filtering (email, phone, SSN, credit card),
  secret blocking (API keys, GitHub tokens, private keys), custom patterns,
  scan without filtering, dict filtering
- Add tests for emergency controls: state management, pause/resume/reset,
  scoped emergency stops, callbacks, EmergencyTrigger events
- Fix exception kwargs in content filter and emergency controls to match
  exception class signatures

All 108 tests passing with lint and type checks clean.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-03 11:52:35 +01:00
Felipe Cardoso
f36bfb3781 feat(safety): add Phase D MCP integration and metrics 
- Add MCPSafetyWrapper for safe MCP tool execution
- Add MCPToolCall/MCPToolResult models for MCP interactions
- Add SafeToolExecutor context manager
- Add SafetyMetrics collector with Prometheus export support
- Track validations, approvals, rate limits, budgets, and more
- Support for counters, gauges, and histograms

Issue #63

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-03 11:40:14 +01:00
Felipe Cardoso
ef659cd72d feat(safety): add Phase C advanced controls 
- Add rollback manager with file checkpointing and transaction context
- Add HITL manager with approval queues and notification handlers
- Add content filter with PII, secrets, and injection detection
- Add emergency controls with stop/pause/resume capabilities
- Update SafetyConfig with checkpoint_dir setting

Issue #63

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-03 11:36:24 +01:00
Felipe Cardoso
728edd1453 feat(backend): add Phase B safety subsystems (#63) 
Implements core control subsystems for the safety framework:

**Action Validation (validation/validator.py):**
- Rule-based validation engine with priority ordering
- Allow/deny/require-approval rule types
- Pattern matching for tools and resources
- Validation result caching with LRU eviction
- Emergency bypass capability with audit

**Permission System (permissions/manager.py):**
- Per-agent permission grants on resources
- Resource pattern matching (wildcards)
- Temporary permissions with expiration
- Permission inheritance hierarchy
- Default deny with configurable defaults

**Cost Control (costs/controller.py):**
- Per-session and per-day budget tracking
- Token and USD cost limits
- Warning alerts at configurable thresholds
- Budget rollover and reset policies
- Real-time usage tracking

**Rate Limiting (limits/limiter.py):**
- Sliding window rate limiter
- Per-action, per-LLM-call, per-file-op limits
- Burst allowance with recovery
- Configurable limits per operation type

**Loop Detection (loops/detector.py):**
- Exact repetition detection (same action+args)
- Semantic repetition (similar actions)
- Oscillation pattern detection (A→B→A→B)
- Per-agent action history tracking
- Loop breaking suggestions

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-03 11:28:00 +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