Vapora/migrations/002_agents.surql

51 lines
2.9 KiB
Plaintext
Raw Permalink 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
-- Migration 002: Agent System
-- Creates tables for agent registry and instance management
-- Agents table (registry of agent types/roles)
DEFINE TABLE agents SCHEMAFULL
PERMISSIONS
FOR select FULL
FOR create, update, delete WHERE "admin" IN $auth.roles OR "devops" IN $auth.roles;
DEFINE FIELD id ON TABLE agents TYPE record<agents>;
DEFINE FIELD role ON TABLE agents TYPE string ASSERT $value INSIDE [
"architect", "developer", "code_reviewer", "tester",
"documenter", "marketer", "presenter", "devops",
"monitor", "security", "project_manager", "decision_maker"
];
DEFINE FIELD name ON TABLE agents TYPE string ASSERT $value != NONE;
DEFINE FIELD version ON TABLE agents TYPE string DEFAULT "0.1.0";
DEFINE FIELD status ON TABLE agents TYPE string ASSERT $value INSIDE ["active", "inactive", "updating", "error"] DEFAULT "active";
DEFINE FIELD capabilities ON TABLE agents TYPE array<string> DEFAULT [];
DEFINE FIELD skills ON TABLE agents TYPE array<string> DEFAULT [];
DEFINE FIELD llm_provider ON TABLE agents TYPE string ASSERT $value INSIDE ["claude", "openai", "gemini", "ollama"];
DEFINE FIELD llm_model ON TABLE agents TYPE string ASSERT $value != NONE;
DEFINE FIELD max_concurrent_tasks ON TABLE agents TYPE int DEFAULT 3 ASSERT $value > 0;
DEFINE FIELD created_at ON TABLE agents TYPE datetime DEFAULT time::now();
DEFINE INDEX idx_agents_role ON TABLE agents COLUMNS role UNIQUE;
DEFINE INDEX idx_agents_status ON TABLE agents COLUMNS status;
DEFINE INDEX idx_agents_provider ON TABLE agents COLUMNS llm_provider;
-- Agent instances table (runtime instances of agents)
DEFINE TABLE agent_instances SCHEMAFULL
PERMISSIONS
FOR select FULL
FOR create, update, delete WHERE "admin" IN $auth.roles OR "devops" IN $auth.roles;
DEFINE FIELD id ON TABLE agent_instances TYPE record<agent_instances>;
DEFINE FIELD agent_id ON TABLE agent_instances TYPE string ASSERT $value != NONE;
DEFINE FIELD pod_id ON TABLE agent_instances TYPE string ASSERT $value != NONE;
DEFINE FIELD ip ON TABLE agent_instances TYPE string;
DEFINE FIELD port ON TABLE agent_instances TYPE int ASSERT $value > 0 AND $value < 65536;
DEFINE FIELD start_time ON TABLE agent_instances TYPE datetime DEFAULT time::now();
DEFINE FIELD last_heartbeat ON TABLE agent_instances TYPE datetime DEFAULT time::now();
DEFINE FIELD tasks_completed ON TABLE agent_instances TYPE int DEFAULT 0;
DEFINE FIELD uptime_percentage ON TABLE agent_instances TYPE float DEFAULT 100.0;
DEFINE FIELD status ON TABLE agent_instances TYPE string ASSERT $value INSIDE ["running", "stopped", "error"] DEFAULT "running";
DEFINE INDEX idx_agent_instances_agent ON TABLE agent_instances COLUMNS agent_id;
DEFINE INDEX idx_agent_instances_pod ON TABLE agent_instances COLUMNS pod_id;
DEFINE INDEX idx_agent_instances_status ON TABLE agent_instances COLUMNS status;
DEFINE INDEX idx_agent_instances_heartbeat ON TABLE agent_instances COLUMNS last_heartbeat;