d14150da75
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.
98 lines
2.2 KiB
Plaintext
98 lines
2.2 KiB
Plaintext
#!/usr/bin/env nu
|
|
|
|
# VAPORA Build Script
|
|
# Phase 0: Build all workspace crates
|
|
# Follows NUSHELL_GUIDELINES.md - 17 rules
|
|
|
|
# Build a single crate
|
|
def build-crate [crate_name: string, release: bool = false]: record {
|
|
print $"Building [$crate_name]..."
|
|
|
|
let result = if $release {
|
|
do { cargo build --release -p $crate_name } | complete
|
|
} else {
|
|
do { cargo build -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)
|
|
}
|
|
}
|
|
}
|
|
|
|
# Build all workspace crates
|
|
def build-all [release: bool = false]: list {
|
|
let crates = [
|
|
"vapora-shared",
|
|
"vapora-agents",
|
|
"vapora-llm-router",
|
|
"vapora-backend",
|
|
"vapora-frontend",
|
|
"vapora-mcp-server"
|
|
]
|
|
|
|
$crates | each {|crate| build-crate $crate $release }
|
|
}
|
|
|
|
# Check if all builds succeeded
|
|
def check-build-results [results: list]: bool {
|
|
let failures = ($results | where {|r| not $r.success })
|
|
|
|
if (($failures | length) > 0) {
|
|
print ""
|
|
print "=== Build Failures ==="
|
|
for failure in $failures {
|
|
print $"✗ ($failure.crate): ($failure.error)"
|
|
}
|
|
false
|
|
} else {
|
|
true
|
|
}
|
|
}
|
|
|
|
# Main build function
|
|
def main [
|
|
--release = false # Build in release mode
|
|
--all = false # Build all crates (default)
|
|
--crate: string = "" # Build specific crate
|
|
]: void {
|
|
print "=== VAPORA Build ==="
|
|
print ""
|
|
|
|
let build_mode = if $release { "release" } else { "debug" }
|
|
print $"Build mode: [$build_mode]"
|
|
print ""
|
|
|
|
let results = if ($crate != "") {
|
|
[
|
|
(build-crate $crate $release)
|
|
]
|
|
} else {
|
|
build-all $release
|
|
}
|
|
|
|
# Check results
|
|
print ""
|
|
let success = (check-build-results $results)
|
|
|
|
if $success {
|
|
print ""
|
|
print "=== Build Complete ==="
|
|
let success_count = ($results | length)
|
|
print $"✓ ($success_count) crate(s) built successfully"
|
|
} else {
|
|
print ""
|
|
print "Build failed"
|
|
exit 1
|
|
}
|
|
}
|