jesus/Vapora
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
Vapora/assets/vapora_v_favicon.svg

39 lines
1.6 KiB
XML
Raw Normal View History

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
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" width="64" height="64" preserveAspectRatio="xMidYMid meet">
<defs>
<!-- Google Fonts import -->
<style>
@import url('https://fonts.googleapis.com/css2?family=JetBrains+Mono:wght@800&amp;display=swap');
</style>
<linearGradient id="faviconGradV" x1="0%" y1="0%" x2="100%" y2="0%">
<stop offset="0%" style="stop-color:#22d3ee;stop-opacity:1"/>
<stop offset="50%" style="stop-color:#a855f7;stop-opacity:1"/>
<stop offset="100%" style="stop-color:#ec4899;stop-opacity:1"/>
</linearGradient>
</defs>
<!-- Fondo -->
<rect width="64" height="64" fill="#000000"/>
<!-- Símbolo simplificado vertical -->
<g transform="translate(32, 12)">
<!-- Línea central -->
<path d="M 0 0 L 0 -6 L 1 -7 L -1 -9 L 1 -11 L 0 -12" stroke="url(#faviconGradV)" stroke-width="0.8" fill="none" stroke-linecap="round" stroke-linejoin="round"/>
<!-- Línea izquierda -->
<path d="M -3 0 L -3 -5 L -2.5 -7 L -3.5 -9 L -3 -11" stroke="#22d3ee" stroke-width="0.5" fill="none" stroke-linecap="round" opacity="0.7"/>
<!-- Línea derecha -->
<path d="M 3 0 L 3 -5 L 2.5 -7 L 3.5 -9 L 3 -11" stroke="#ec4899" stroke-width="0.5" fill="none" stroke-linecap="round" opacity="0.7"/>
<!-- Círculos decorativos -->
<circle cx="0" cy="-4" r="0.6" fill="#22d3ee"/>
<circle cx="0" cy="-7" r="0.5" fill="#a855f7"/>
</g>
<!-- Texto V simplificado -->
<text x="32" y="50" font-family="'JetBrains Mono', monospace" font-size="12" font-weight="800" fill="url(#faviconGradV)" letter-spacing="0.5" text-anchor="middle">
V
</text>
</svg>
Reference in New Issue Copy Permalink