Vapora/config/workflows.toml

130 lines
2.3 KiB
TOML
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
# Workflow Engine Configuration
# Phase 0: Workflow templates and execution rules
[engine]
# Maximum parallel tasks in a workflow
max_parallel_tasks = 10
# Workflow timeout (seconds)
workflow_timeout = 3600
# Enable approval gates
approval_gates_enabled = true
# Workflow Templates
[[workflows]]
name = "feature_development"
description = "Complete feature development workflow"
trigger = "task_type:feature"
# Workflow stages (sequential unless marked parallel)
[[workflows.stages]]
name = "architecture"
agents = ["architect"]
parallel = false
approval_required = true
[[workflows.stages]]
name = "implementation"
agents = ["developer"]
parallel = true
max_parallel = 3
[[workflows.stages]]
name = "review"
agents = ["code_reviewer", "security"]
parallel = true
[[workflows.stages]]
name = "testing"
agents = ["tester"]
parallel = false
[[workflows.stages]]
name = "documentation"
agents = ["documenter"]
parallel = true
[[workflows.stages]]
name = "deployment"
agents = ["devops"]
parallel = false
approval_required = true
[[workflows]]
name = "bugfix"
description = "Bug fix workflow"
trigger = "task_type:bugfix"
[[workflows.stages]]
name = "analysis"
agents = ["developer"]
parallel = false
[[workflows.stages]]
name = "fix_implementation"
agents = ["developer"]
parallel = false
[[workflows.stages]]
name = "review"
agents = ["code_reviewer"]
parallel = false
[[workflows.stages]]
name = "testing"
agents = ["tester"]
parallel = false
[[workflows.stages]]
name = "deployment"
agents = ["devops"]
parallel = false
[[workflows]]
name = "documentation_update"
description = "Update documentation workflow"
trigger = "task_type:documentation"
[[workflows.stages]]
name = "content_creation"
agents = ["documenter"]
parallel = false
[[workflows.stages]]
name = "review"
agents = ["code_reviewer", "project_manager"]
parallel = true
[[workflows.stages]]
name = "publish"
agents = ["devops"]
parallel = false
[[workflows]]
name = "security_audit"
description = "Security audit workflow"
trigger = "task_type:security"
[[workflows.stages]]
name = "audit"
agents = ["security"]
parallel = false
[[workflows.stages]]
name = "remediation"
agents = ["developer"]
parallel = true
[[workflows.stages]]
name = "verification"
agents = ["security", "tester"]
parallel = true
[[workflows.stages]]
name = "approval"
agents = ["decision_maker"]
parallel = false
approval_required = true