Vapora/migrations/001_initial_schema.surql

69 lines
3.8 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 001: Initial Schema
-- Creates core tables: projects, tasks, users
-- Establishes multi-tenant architecture with permissions
-- Projects table
DEFINE TABLE projects SCHEMAFULL
PERMISSIONS
FOR select WHERE tenant_id = $auth.tenant_id
FOR create, update, delete WHERE tenant_id = $auth.tenant_id;
DEFINE FIELD id ON TABLE projects TYPE record<projects>;
DEFINE FIELD tenant_id ON TABLE projects TYPE string ASSERT $value != NONE;
DEFINE FIELD title ON TABLE projects TYPE string ASSERT $value != NONE AND string::len($value) > 0;
DEFINE FIELD description ON TABLE projects TYPE option<string>;
DEFINE FIELD status ON TABLE projects TYPE string ASSERT $value INSIDE ["active", "archived", "completed"] DEFAULT "active";
DEFINE FIELD features ON TABLE projects TYPE array<string> DEFAULT [];
DEFINE FIELD created_at ON TABLE projects TYPE datetime DEFAULT time::now();
DEFINE FIELD updated_at ON TABLE projects TYPE datetime DEFAULT time::now() VALUE time::now();
DEFINE INDEX idx_projects_tenant ON TABLE projects COLUMNS tenant_id;
DEFINE INDEX idx_projects_status ON TABLE projects COLUMNS status;
DEFINE INDEX idx_projects_tenant_status ON TABLE projects COLUMNS tenant_id, status;
-- Tasks table
DEFINE TABLE tasks SCHEMAFULL
PERMISSIONS
FOR select WHERE tenant_id = $auth.tenant_id
FOR create, update, delete WHERE tenant_id = $auth.tenant_id;
DEFINE FIELD id ON TABLE tasks TYPE record<tasks>;
DEFINE FIELD tenant_id ON TABLE tasks TYPE string ASSERT $value != NONE;
DEFINE FIELD project_id ON TABLE tasks TYPE string ASSERT $value != NONE;
DEFINE FIELD title ON TABLE tasks TYPE string ASSERT $value != NONE AND string::len($value) > 0;
DEFINE FIELD description ON TABLE tasks TYPE option<string>;
DEFINE FIELD status ON TABLE tasks TYPE string ASSERT $value INSIDE ["todo", "doing", "review", "done"] DEFAULT "todo";
DEFINE FIELD assignee ON TABLE tasks TYPE string DEFAULT "unassigned";
DEFINE FIELD priority ON TABLE tasks TYPE string ASSERT $value INSIDE ["low", "medium", "high", "critical"] DEFAULT "medium";
DEFINE FIELD task_order ON TABLE tasks TYPE int DEFAULT 0;
DEFINE FIELD feature ON TABLE tasks TYPE option<string>;
DEFINE FIELD created_at ON TABLE tasks TYPE datetime DEFAULT time::now();
DEFINE FIELD updated_at ON TABLE tasks TYPE datetime DEFAULT time::now() VALUE time::now();
DEFINE INDEX idx_tasks_tenant ON TABLE tasks COLUMNS tenant_id;
DEFINE INDEX idx_tasks_project ON TABLE tasks COLUMNS project_id;
DEFINE INDEX idx_tasks_status ON TABLE tasks COLUMNS status;
DEFINE INDEX idx_tasks_assignee ON TABLE tasks COLUMNS assignee;
DEFINE INDEX idx_tasks_tenant_project ON TABLE tasks COLUMNS tenant_id, project_id;
DEFINE INDEX idx_tasks_project_status ON TABLE tasks COLUMNS project_id, status;
DEFINE INDEX idx_tasks_project_order ON TABLE tasks COLUMNS project_id, task_order;
-- Users table
DEFINE TABLE users SCHEMAFULL
PERMISSIONS
FOR select WHERE id = $auth.id OR "admin" IN $auth.roles
FOR create WHERE "admin" IN $auth.roles
FOR update WHERE id = $auth.id OR "admin" IN $auth.roles
FOR delete WHERE "admin" IN $auth.roles;
DEFINE FIELD id ON TABLE users TYPE record<users>;
DEFINE FIELD email ON TABLE users TYPE string ASSERT $value != NONE AND string::is::email($value);
DEFINE FIELD username ON TABLE users TYPE string ASSERT $value != NONE AND string::len($value) >= 3;
DEFINE FIELD password_hash ON TABLE users TYPE string ASSERT $value != NONE;
DEFINE FIELD roles ON TABLE users TYPE array<string> DEFAULT ["user"];
DEFINE FIELD created_at ON TABLE users TYPE datetime DEFAULT time::now();
DEFINE FIELD updated_at ON TABLE users TYPE datetime DEFAULT time::now() VALUE time::now();
DEFINE INDEX idx_users_email ON TABLE users COLUMNS email UNIQUE;
DEFINE INDEX idx_users_username ON TABLE users COLUMNS username UNIQUE;