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.
125 lines
4.2 KiB
Rust
125 lines
4.2 KiB
Rust
use criterion::{black_box, criterion_group, criterion_main, Criterion};
|
|
use vapora_knowledge_graph::{TemporalKG, ExecutionRecord};
|
|
use chrono::Utc;
|
|
|
|
async fn setup_kg_with_records(count: usize) -> TemporalKG {
|
|
let kg = TemporalKG::new("ws://localhost:8000", "root", "root")
|
|
.await
|
|
.unwrap();
|
|
|
|
for i in 0..count {
|
|
let record = ExecutionRecord {
|
|
id: format!("exec-{}", i),
|
|
task_id: format!("task-{}", i),
|
|
agent_id: format!("agent-{}", i % 10),
|
|
task_type: match i % 3 {
|
|
0 => "coding".to_string(),
|
|
1 => "analysis".to_string(),
|
|
_ => "review".to_string(),
|
|
},
|
|
description: format!("Execute task {} with description", i),
|
|
duration_ms: 1000 + (i as u64 * 100) % 5000,
|
|
input_tokens: 100 + (i as u64 * 10),
|
|
output_tokens: 200 + (i as u64 * 20),
|
|
success: i % 10 != 0,
|
|
error: if i % 10 == 0 { Some("timeout".to_string()) } else { None },
|
|
solution: Some(format!("Solution for task {}", i)),
|
|
root_cause: None,
|
|
timestamp: Utc::now(),
|
|
};
|
|
kg.record_execution(record).await.unwrap();
|
|
}
|
|
|
|
kg
|
|
}
|
|
|
|
fn kg_record_execution(c: &mut Criterion) {
|
|
c.bench_function("record_single_execution", |b| {
|
|
b.to_async(tokio::runtime::Runtime::new().unwrap())
|
|
.iter(|| async {
|
|
let kg = TemporalKG::new("ws://localhost:8000", "root", "root")
|
|
.await
|
|
.unwrap();
|
|
let record = ExecutionRecord {
|
|
id: "test-exec".to_string(),
|
|
task_id: "test-task".to_string(),
|
|
agent_id: "test-agent".to_string(),
|
|
task_type: "coding".to_string(),
|
|
description: "Test execution".to_string(),
|
|
duration_ms: 1000,
|
|
input_tokens: 100,
|
|
output_tokens: 200,
|
|
success: true,
|
|
error: None,
|
|
solution: None,
|
|
root_cause: None,
|
|
timestamp: Utc::now(),
|
|
};
|
|
black_box(kg.record_execution(black_box(record)).await)
|
|
});
|
|
});
|
|
}
|
|
|
|
fn kg_query_similar(c: &mut Criterion) {
|
|
c.bench_function("query_similar_tasks_100_records", |b| {
|
|
b.to_async(tokio::runtime::Runtime::new().unwrap())
|
|
.iter_batched(
|
|
|| {
|
|
let rt = tokio::runtime::Runtime::new().unwrap();
|
|
rt.block_on(setup_kg_with_records(100))
|
|
},
|
|
|kg| async move {
|
|
black_box(
|
|
kg.query_similar_tasks(
|
|
"coding",
|
|
"Write a function for processing data",
|
|
)
|
|
.await,
|
|
)
|
|
},
|
|
criterion::BatchSize::SmallInput,
|
|
);
|
|
});
|
|
}
|
|
|
|
fn kg_get_statistics(c: &mut Criterion) {
|
|
c.bench_function("get_statistics_1000_records", |b| {
|
|
b.to_async(tokio::runtime::Runtime::new().unwrap())
|
|
.iter_batched(
|
|
|| {
|
|
let rt = tokio::runtime::Runtime::new().unwrap();
|
|
rt.block_on(setup_kg_with_records(1000))
|
|
},
|
|
|kg| async move {
|
|
black_box(kg.get_statistics().await)
|
|
},
|
|
criterion::BatchSize::SmallInput,
|
|
);
|
|
});
|
|
}
|
|
|
|
fn kg_get_agent_profile(c: &mut Criterion) {
|
|
c.bench_function("get_agent_profile_500_records", |b| {
|
|
b.to_async(tokio::runtime::Runtime::new().unwrap())
|
|
.iter_batched(
|
|
|| {
|
|
let rt = tokio::runtime::Runtime::new().unwrap();
|
|
rt.block_on(setup_kg_with_records(500))
|
|
},
|
|
|kg| async move {
|
|
black_box(kg.get_agent_profile("agent-1").await)
|
|
},
|
|
criterion::BatchSize::SmallInput,
|
|
);
|
|
});
|
|
}
|
|
|
|
criterion_group!(
|
|
benches,
|
|
kg_record_execution,
|
|
kg_query_similar,
|
|
kg_get_statistics,
|
|
kg_get_agent_profile
|
|
);
|
|
criterion_main!(benches);
|