Vapora/scripts/start-tracking-service.nu

116 lines
3.4 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
# start-tracking-service.nu - Start the vapora-tracking background service
# Follows NuShell 0.108+ guidelines with explicit types
def main [
--port: int = 3000 # Server port
--database: string = "sqlite://tracking.db" # Database URL
--watch-dirs: string = "/Users/Akasha/Development" # Projects to watch
--verbose = false
]: void {
if $verbose {
print "🚀 Starting Vapora Tracking Service..."
print $" Port: [$port]"
print $" Database: [$database]"
print $" Watch: [$watch-dirs]"
}
# Rule 3: Early validation
validate-environment
# Rule 13: Predictable naming
let pid-file = "/tmp/vapora-tracking.pid"
let log-file = "/tmp/vapora-tracking.log"
# Check if service is already running
if check-service-running $pid-file {
print "⚠️ Tracking service is already running"
print $" PID: (cat $pid-file)"
return
}
print "📝 Starting service..."
print $" Logs: [$log-file]"
# Start the service in background
# Rule 17: Expression interpolation
let command = $"cd /Users/Akasha/Development/vapora && cargo run -p vapora-backend --release -- --tracking-port ($port) --tracking-database ($database)"
# Start in background with output redirection
let result = (
do {
# Create startup script
let startup-script = "
#!/bin/bash
$command >> $log-file 2>&1 &
echo $! > $pid-file
"
sh --stdin <<< $startup-script
} | complete
)
if $result.exit_code != 0 {
print $"❌ Failed to start service"
print $" Error: ($result.stderr)"
return
}
# Wait for service to start
print "⏳ Waiting for service to start..."
sleep 2s
# Rule 11: Never swallow errors
if not (check-service-running $pid-file) {
print "❌ Service failed to start"
print $" Check logs: ($log-file)"
return
}
let service-pid = (cat $pid-file)
print $"✅ Service started successfully!"
print $" PID: [$service-pid]"
print $" API: http://localhost:($port)/api/v1/tracking"
print $""
print "Available commands:"
print " /sync-tracking - Sync all projects"
print " /log-change 'summary' - Log a change"
print " /add-todo 'title' - Add a TODO"
print " /track-status - Show status"
print $"
To stop the service: kill ($service-pid) or use stop-tracking-service
To view logs: tail -f ($log-file)
"
}
# Rule 1: Single purpose - validates environment
def validate-environment []: void {
# Rule 11: Never swallow errors
if not (which cargo | is-not-empty) {
error make {
msg: "❌ Cargo not found. Install Rust from https://rustup.rs"
}
}
if not ("/Users/Akasha/Development/vapora" | path exists) {
error make {
msg: "❌ Vapora directory not found at /Users/Akasha/Development/vapora"
}
}
}
# Rule 1: Single purpose - checks if service is running
def check-service-running [pid-file: string]: bool {
if not ($pid-file | path exists) {
return false
}
try {
let pid = (cat $pid-file)
let is-running = (ps aux | grep $pid | grep -v grep | is-not-empty)
$is-running
} catch {
false
}
}