Jesús Pérez
d14150da75
feat: Phase 5.3 - Multi-Agent Learning Infrastructure
...
Implement intelligent agent learning from Knowledge Graph execution history
with per-task-type expertise tracking, recency bias, and learning curves.
## Phase 5.3 Implementation
### Learning Infrastructure (✅ Complete)
- LearningProfileService with per-task-type expertise metrics
- TaskTypeExpertise model tracking success_rate, confidence, learning curves
- Recency bias weighting: recent 7 days weighted 3x higher (exponential decay)
- Confidence scoring prevents overfitting: min(1.0, executions / 20)
- Learning curves computed from daily execution windows
### Agent Scoring Service (✅ Complete)
- Unified AgentScore combining SwarmCoordinator + learning profiles
- Scoring formula: 0.3*base + 0.5*expertise + 0.2*confidence
- Rank agents by combined score for intelligent assignment
- Support for recency-biased scoring (recent_success_rate)
- Methods: rank_agents, select_best, rank_agents_with_recency
### KG Integration (✅ Complete)
- KGPersistence::get_executions_for_task_type() - query by agent + task type
- KGPersistence::get_agent_executions() - all executions for agent
- Coordinator::load_learning_profile_from_kg() - core KG→Learning integration
- Coordinator::load_all_learning_profiles() - batch load for multiple agents
- Convert PersistedExecution → ExecutionData for learning calculations
### Agent Assignment Integration (✅ Complete)
- AgentCoordinator uses learning profiles for task assignment
- extract_task_type() infers task type from title/description
- assign_task() scores candidates using AgentScoringService
- Fallback to load-based selection if no learning data available
- Learning profiles stored in coordinator.learning_profiles RwLock
### Profile Adapter Enhancements (✅ Complete)
- create_learning_profile() - initialize empty profiles
- add_task_type_expertise() - set task-type expertise
- update_profile_with_learning() - update swarm profiles from learning
## Files Modified
### vapora-knowledge-graph/src/persistence.rs (+30 lines)
- get_executions_for_task_type(agent_id, task_type, limit)
- get_agent_executions(agent_id, limit)
### vapora-agents/src/coordinator.rs (+100 lines)
- load_learning_profile_from_kg() - core KG integration method
- load_all_learning_profiles() - batch loading for agents
- assign_task() already uses learning-based scoring via AgentScoringService
### Existing Complete Implementation
- vapora-knowledge-graph/src/learning.rs - calculation functions
- vapora-agents/src/learning_profile.rs - data structures and expertise
- vapora-agents/src/scoring.rs - unified scoring service
- vapora-agents/src/profile_adapter.rs - adapter methods
## Tests Passing
- learning_profile: 7 tests ✅
- scoring: 5 tests ✅
- profile_adapter: 6 tests ✅
- coordinator: learning-specific tests ✅
## Data Flow
1. Task arrives → AgentCoordinator::assign_task()
2. Extract task_type from description
3. Query KG for task-type executions (load_learning_profile_from_kg)
4. Calculate expertise with recency bias
5. Score candidates (SwarmCoordinator + learning)
6. Assign to top-scored agent
7. Execution result → KG → Update learning profiles
## Key Design Decisions
✅ Recency bias: 7-day half-life with 3x weight for recent performance
✅ Confidence scoring: min(1.0, total_executions / 20) prevents overfitting
✅ Hierarchical scoring: 30% base load, 50% expertise, 20% confidence
✅ KG query limit: 100 recent executions per task-type for performance
✅ Async loading: load_learning_profile_from_kg supports concurrent loads
## Next: Phase 5.4 - Cost Optimization
Ready to implement budget enforcement and cost-aware provider selection.
2026-01-11 13:03:53 +00:00
Jesús Pérez
d2abda35f9
fix: resolve secretumvault integration and opentelemetry version conflicts
...
- Update opentelemetry ecosystem to v0.22+ (0.21 missing required features)
- Add openssl and cedar features to secretumvault build
- Enables secretumvault crypto backend and policy engine support
- Workspace now compiles successfully for Phase 5.3/5.4 implementation
Fixes:
- opentelemetry 0.21 → 0.22: rt-tokio feature availability
- opentelemetry-jaeger 0.20 → 0.21: compatibility
- tracing-opentelemetry 0.22 → 0.23: version alignment
- secretumvault features: add openssl and cedar for full functionality
2026-01-11 12:51:52 +00:00
Jesús Pérez
5ea9e3f4de
feat: add vapora-doc-lifecycle adapter for documentation management
...
- Create VAPORA adapter for doc-lifecycle-core integration
- DocLifecyclePlugin: Main plugin interface for orchestration
- DocumenterIntegration: Integrates with Documenter agent
- Configuration for VAPORA-specific settings
Features:
- Event-driven documentation processing (NATS)
- Automatic classification and consolidation
- RAG index generation with SurrealDB
- mdBook site generation
- Root files management (README, CHANGELOG, ROADMAP)
Dependency structure:
- Development: local path to doc-lifecycle-core
- Production: will use crates.io version
This enables gradual adoption:
1. Use standalone tool in any Rust project
2. Integrate into VAPORA for automatic processing
3. Share core library between both deployments
2025-11-10 18:13:38 +00:00
Jesús Pérez
ca3fa91d5d
chore: fix graphs
2025-11-10 12:24:13 +00:00
Jesús Pérez
748606325a
chore: fix graphs
2025-11-10 12:23:35 +00:00
Jesús Pérez
e7264f069d
chore: fix graphs
2025-11-10 12:21:03 +00:00
Jesús Pérez
d095e520f3
chore: fix graphs
2025-11-10 12:20:33 +00:00
Jesús Pérez
5fde6a87da
chore: fix graphs
2025-11-10 12:19:39 +00:00
Jesús Pérez
c97f712573
chore: fix graphs
2025-11-10 12:18:34 +00:00
Jesús Pérez
2669e2822f
chore: fix version
2025-11-10 12:13:05 +00:00
Jesús Pérez
c9163f6005
chore: fix features
2025-11-10 12:02:28 +00:00
Jesús Pérez
af9364267e
chore: add features
2025-11-10 11:57:49 +00:00
Jesús Pérez
cd8bc02944
chore: fix content
2025-11-10 11:45:23 +00:00
Jesús Pérez
d89a2bc26f
chore: fix content
2025-11-10 11:41:29 +00:00
Jesús Pérez
46ea1b03a4
chore: add image
2025-11-09 12:28:20 +00:00
Jesús Pérez
f9dbd54ca6
init project
2025-11-09 12:27:37 +00:00
