Vapora/scripts/validate-deployment.nu
Jesús Pérez d14150da75 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

138 lines
4.5 KiB
Plaintext

#!/usr/bin/env nu
# VAPORA Deployment Validation Script
# Validates that all deployment files and artifacts are ready
def main [] {
print $"(ansi green)🔍 VAPORA Deployment Validation(ansi reset)"
print $"(ansi blue)═══════════════════════════════════════════════(ansi reset)"
print ""
mut all_valid = true
# Check Dockerfiles
print $"(ansi yellow)🐳 Checking Dockerfiles...(ansi reset)"
let dockerfiles = [
"crates/vapora-backend/Dockerfile"
"crates/vapora-frontend/Dockerfile"
"crates/vapora-agents/Dockerfile"
"crates/vapora-mcp-server/Dockerfile"
]
for dockerfile in $dockerfiles {
if ($dockerfile | path exists) {
print $" (ansi green)✅ ($dockerfile)(ansi reset)"
} else {
print $" (ansi red)❌ ($dockerfile) NOT FOUND(ansi reset)"
$all_valid = false
}
}
# Check Kubernetes manifests
print ""
print $"(ansi yellow)☸️ Checking Kubernetes manifests...(ansi reset)"
let k8s_manifests = [
"kubernetes/00-namespace.yaml"
"kubernetes/01-surrealdb.yaml"
"kubernetes/02-nats.yaml"
"kubernetes/03-secrets.yaml"
"kubernetes/04-backend.yaml"
"kubernetes/05-frontend.yaml"
"kubernetes/06-agents.yaml"
"kubernetes/07-mcp-server.yaml"
"kubernetes/08-ingress.yaml"
]
for manifest in $k8s_manifests {
if ($manifest | path exists) {
print $" (ansi green)✅ ($manifest)(ansi reset)"
} else {
print $" (ansi red)❌ ($manifest) NOT FOUND(ansi reset)"
$all_valid = false
}
}
# Check deployment scripts
print ""
print $"(ansi yellow)📜 Checking deployment scripts...(ansi reset)"
let scripts = [
"scripts/build-docker.nu"
"scripts/deploy-k8s.nu"
"scripts/validate-provisioning.nu"
]
for script in $scripts {
if ($script | path exists) {
print $" (ansi green)✅ ($script)(ansi reset)"
} else {
print $" (ansi red)❌ ($script) NOT FOUND(ansi reset)"
$all_valid = false
}
}
# Check documentation
print ""
print $"(ansi yellow)📚 Checking documentation...(ansi reset)"
let docs = [
"README.md"
"DEPLOYMENT.md"
"PROJECT_COMPLETION_REPORT.md"
"kubernetes/README.md"
"provisioning-integration/README.md"
]
for doc in $docs {
if ($doc | path exists) {
print $" (ansi green)✅ ($doc)(ansi reset)"
} else {
print $" (ansi red)❌ ($doc) NOT FOUND(ansi reset)"
$all_valid = false
}
}
# Check source code (binaries for health endpoints)
print ""
print $"(ansi yellow)🔧 Checking health endpoint implementations...(ansi reset)"
let source_files = [
"crates/vapora-backend/src/api/health.rs"
"crates/vapora-agents/src/bin/server.rs"
"crates/vapora-mcp-server/src/main.rs"
]
for file in $source_files {
if ($file | path exists) {
print $" (ansi green)✅ ($file)(ansi reset)"
} else {
print $" (ansi red)❌ ($file) NOT FOUND(ansi reset)"
$all_valid = false
}
}
# Summary
print ""
print $"(ansi blue)═══════════════════════════════════════════════(ansi reset)"
if $all_valid {
print $"(ansi green)✅ ALL VALIDATION CHECKS PASSED!(ansi reset)"
print ""
print $"(ansi cyan)VAPORA v2.0 is ready for deployment.(ansi reset)"
print ""
print $"(ansi yellow)Next steps:(ansi reset)"
print " 1. Build Docker images: nu scripts/build-docker.nu --push"
print " 2. Update secrets: Edit kubernetes/03-secrets.yaml"
print " 3. Update ingress: Edit kubernetes/08-ingress.yaml"
print " 4. Deploy: nu scripts/deploy-k8s.nu"
print ""
print $"(ansi cyan)Documentation:(ansi reset)"
print " • Deployment Guide: DEPLOYMENT.md"
print " • K8s README: kubernetes/README.md"
print " • Project Summary: PROJECT_COMPLETION_REPORT.md"
exit 0
} else {
print $"(ansi red)❌ VALIDATION FAILED - Some files are missing(ansi reset)"
print ""
print $"(ansi yellow)Please ensure all required files are present before deployment.(ansi reset)"
exit 1
}
}