Vapora/scripts/test.nu

123 lines
2.7 KiB
Plaintext
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
#!/usr/bin/env nu
# VAPORA Test Script
# Phase 0: Run tests for all workspace crates
# Follows NUSHELL_GUIDELINES.md - 17 rules
# Run tests for a single crate
def test-crate [crate_name: string]: record {
print $"Testing [$crate_name]..."
let result = (do { cargo test -p $crate_name } | complete)
if ($result.exit_code == 0) {
{
crate: $crate_name,
success: true,
error: null
}
} else {
{
crate: $crate_name,
success: false,
error: ($result.stderr | str trim)
}
}
}
# Run tests for all workspace crates
def test-all []: list {
let crates = [
"vapora-shared",
"vapora-agents",
"vapora-llm-router",
"vapora-backend",
"vapora-mcp-server"
]
$crates | each {|crate| test-crate $crate }
}
# Check if all tests passed
def check-test-results [results: list]: bool {
let failures = ($results | where {|r| not $r.success })
if (($failures | length) > 0) {
print ""
print "=== Test Failures ==="
for failure in $failures {
print $"✗ ($failure.crate): ($failure.error)"
}
false
} else {
true
}
}
# Run workspace-wide tests
def test-workspace []: record {
print "Running workspace tests..."
let result = (do { cargo test --workspace } | complete)
if ($result.exit_code == 0) {
{
success: true,
error: null
}
} else {
{
success: false,
error: ($result.stderr | str trim)
}
}
}
# Main test function
def main [
--all = false # Test all crates individually
--workspace = false # Test entire workspace
--crate: string = "" # Test specific crate
]: void {
print "=== VAPORA Test Suite ==="
print ""
let results = if ($crate != "") {
# Test specific crate
[
(test-crate $crate)
]
} else if $workspace {
# Test entire workspace
let ws_result = (test-workspace)
if $ws_result.success {
print ""
print "=== All Tests Passed ==="
print "✓ Workspace tests completed"
return
} else {
print ""
print $"ERROR: ($ws_result.error)"
exit 1
}
} else {
# Test all crates individually
test-all
}
# Check results
print ""
let success = (check-test-results $results)
if $success {
print ""
print "=== All Tests Passed ==="
let test_count = ($results | length)
print $"✓ ($test_count) crate(s) tested successfully"
} else {
print ""
print "Tests failed"
exit 1
}
}