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.
231 lines
5.1 KiB
Plaintext
231 lines
5.1 KiB
Plaintext
"""
|
|
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
|
|
}
|