 Profa
|
b5e2a1f485
|
fix(security): add workflow permissions & implement memory adapters
Security fixes:
- Add explicit permissions to migration-validation.yml (fixes #37, #38, #39)
- analyze-duplicates job: contents:read, issues:write, pull-requests:write
- validate-migration & check-migration-compliance: contents:read
Issue #109 - RuVector & AgentDB v2 Integration:
- Add ReflexionMemoryAdapter for flaky test prediction (410 lines)
- Add SparseVectorSearch for hybrid BM25/vector search (174 lines)
- Add TieredCompression for 85% memory reduction (328 lines)
- Add comprehensive test suites for all memory adapters
Issue #108 - CI Pipeline fixes:
- Configure jest-junit reporter for CI integration
- Fix FleetManager.database.test.ts flaky tests
- Add mcp-tools-test workflow permissions
Also includes:
- Hackathon TV5 issue report and reliability analysis
- Security scan report
- Code complexity analysis script
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-12-03 19:26:41 +00:00 |
|
|
Profa
|
71e2df0f9d
|
feat: Complete Agentic QE Fleet v2.1 implementation (closes #101)
## Implemented Features
### Error Recovery Enhancement (Task 1.3)
- CircuitBreaker class with state management (CLOSED/OPEN/HALF_OPEN)
- RetryStrategy with exponential/linear/constant backoff
- RecoveryOrchestrator with 6 recovery strategies
- Transport fallback mechanisms
### Dynamic Skill Loader (Task 2.2)
- Metadata-only initial loading (98% token reduction)
- On-demand full skill retrieval
- LRU caching with configurable TTL (30min default)
- Preload suggestions for critical workflows
### Swarm Learning Optimizer (Task 4.1)
- Topology recommendation engine (hierarchical/mesh/ring/star)
- Agent allocation with capability matching and load balancing
- Bottleneck detection (agent/memory/coordination/IO)
- Real-time performance adjustments
- Added getLatestRecommendation() method
### Workflow Orchestrator (Task 4.2)
- AdaptiveScheduler with dynamic strategy selection
- Priority-based task queue with age boosting
- Task dependency resolution
- Work stealing and backpressure handling
- Added getQueueDepth() and getStatus() methods
### Unified Memory Coordinator (Task 4.3)
- Consolidated memory managers (SQLite, AgentDB, Vector, JSON)
- Automatic failover chain with health monitoring
- Batch operations and namespace isolation
- Periodic sync between backends
### SwarmCoordinator Improvements
- Real CPU utilization tracking via process.cpuUsage()
- Queue depth from WorkflowOrchestrator
- Optimizer recommendations in feedback data
- Calculated average complexity from metrics
## Additional Changes
- Migration documentation and test restructuring plan
- GitHub issue templates and workflows
- Test suite improvements and cleanup
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-12-02 15:02:30 +00:00 |
|