231 lines
5.1 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
"""
VAPORA Kubernetes Cluster Configuration
Defines K8s cluster, networking, storage, and service mesh
"""
import k.api.all as k
# ===== CLUSTER DEFINITION =====
cluster = k.Cluster {
name = "vapora-cluster"
version = "1.30"
region = "us-east-1"
cloud_provider = "aws" # aws | gcp | azure | on-premise
# Networking
network = {
vpc_cidr = "10.0.0.0/16"
service_cidr = "10.96.0.0/12"
pod_cidr = "10.244.0.0/16"
cni = "cilium" # cilium | flannel | weave
serviceMesh = "istio"
networkPolicy = true
}
# Node configuration
nodes = {
master = {
count = 3
instance_type = "t3.large" # 2 vCPU, 8Gi RAM
zone = "us-east-1a"
disk_size = 100
disk_type = "gp3"
}
worker = {
count = 5
instance_type = "t3.xlarge" # 4 vCPU, 16Gi RAM
zone = "us-east-1b"
disk_size = 200
disk_type = "gp3"
taints = [
{"key": "workload", "value": "vapora", "effect": "NoSchedule"}
]
}
}
# Storage
storage = {
provider = "rook-ceph" # rook-ceph | ebs | local
replication_factor = 3
pools = [
{
name = "ssd"
device_class = "ssd"
size = "500Gi"
},
{
name = "hdd"
device_class = "hdd"
size = "2Ti"
}
]
}
# Monitoring stack
monitoring = {
prometheus = true
grafana = true
loki = true
alert_manager = true
}
# Security
security = {
mTLS = true
network_policies = true
pod_security_policy = true
rbac = true
audit_logging = true
}
# Ingress
ingress = {
provider = "istio" # istio | nginx | haproxy
domain = "vapora.example.com"
tls = true
cert_provider = "letsencrypt"
}
}
# ===== NAMESPACES =====
namespaces = [
{
name = "vapora-system"
labels = {"app": "vapora"}
},
{
name = "istio-system"
labels = {"istio-injection": "enabled"}
},
{
name = "monitoring"
labels = {"monitoring": "true"}
},
{
name = "rook-ceph"
labels = {"storage": "ceph"}
}
]
# ===== ISTIO SERVICE MESH =====
istio = {
enabled = true
version = "1.18"
# Traffic management
traffic_policy = {
connection_pool = {
http = {
http1MaxPendingRequests = 100
maxRequestsPerConnection = 2
h2UpgradePolicy = "UPGRADE"
}
tcp = {
maxConnections = 100
}
}
outlier_detection = {
consecutive5xxErrors = 5
interval = "30s"
baseEjectionTime = "30s"
}
}
# Authorization policies
authz_policies = {
deny_all = true
allow_prometheus = true
allow_inter_service_mtls = true
}
# Virtual Service for VAPORA frontend
virtual_services = [
{
name = "vapora-frontend"
namespace = "vapora-system"
hosts = ["vapora.example.com"]
routes = [
{
destination = "vapora-frontend"
weight = 100
timeout = "10s"
retries = {
attempts = 3
perTryTimeout = "2s"
}
}
]
}
]
# Gateway
gateway = {
name = "vapora-gateway"
selector = {"istio": "ingressgateway"}
servers = [
{
port = {number = 80, name = "http", protocol = "HTTP"}
hosts = ["vapora.example.com"]
redirectPort = 443
},
{
port = {number = 443, name = "https", protocol = "HTTPS"}
hosts = ["vapora.example.com"]
tls = {
mode = "SIMPLE"
credentialName = "vapora-tls"
}
}
]
}
}
# ===== RESOURCE QUOTAS =====
resource_quotas = [
{
namespace = "vapora-system"
hard = {
requests.cpu = "100"
requests.memory = "200Gi"
limits.cpu = "200"
limits.memory = "400Gi"
pods = "500"
services = "50"
configmaps = "100"
secrets = "100"
}
}
]
# ===== PERSISTENT VOLUMES =====
persistent_volumes = [
{
name = "vapora-data-ssd"
storage_class = "ssd"
size = "500Gi"
access_mode = "ReadWriteOnce"
reclaim_policy = "Retain"
},
{
name = "vapora-backup-hdd"
storage_class = "hdd"
size = "2Ti"
access_mode = "ReadWriteOnce"
reclaim_policy = "Retain"
}
]
# ===== OUTPUT =====
output = {
cluster_info = cluster
namespaces = namespaces
istio_config = istio
storage_config = cluster.storage
}