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.
46 lines
1.3 KiB
Plaintext
46 lines
1.3 KiB
Plaintext
#!/usr/bin/env nu
|
|
# Generate agent configuration JSON files from Nickel definitions
|
|
# Requires: nickel CLI installed
|
|
|
|
def main [] {
|
|
let script_dir = (get-env PWD | path split | drop 1 | path join)
|
|
let config_dir = $script_dir / config / agents
|
|
let output_dir = $config_dir / generated
|
|
|
|
print $"Generating agent configurations from Nickel definitions..."
|
|
print $"Input: ($config_dir)"
|
|
print $"Output: ($output_dir)"
|
|
|
|
# Create output directory
|
|
mkdir -p $output_dir
|
|
|
|
# List all agent definition files
|
|
let agents = (
|
|
ls ($config_dir | path join "*.ncl")
|
|
| filter { |it| $it.name != "schema.ncl" }
|
|
| each { |it| $it.name | str replace ".ncl" "" }
|
|
)
|
|
|
|
print $"\nFound ($agents | length) agent definitions:"
|
|
|
|
# Generate JSON for each agent
|
|
for agent in $agents {
|
|
print $" Generating ($agent)..."
|
|
|
|
let input_file = $config_dir | path join $"($agent).ncl"
|
|
let output_file = $output_dir | path join $"($agent).json"
|
|
|
|
# Use nickel to export to JSON
|
|
if (which nickel | is-empty) {
|
|
print $" ⚠ nickel command not found - skipping"
|
|
} else {
|
|
nickel export $input_file | save -f $output_file
|
|
print $" ✓ Generated ($output_file)"
|
|
}
|
|
}
|
|
|
|
print "\nAgent configuration generation complete!"
|
|
}
|
|
|
|
main
|