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
|
|
|
//! Tracking API endpoints for project change logs and TODOs
|
|
|
|
|
//!
|
|
|
|
|
//! Integrates vapora-tracking system with the main backend API,
|
|
|
|
|
//! providing unified access to project tracking data.
|
|
|
|
|
|
2026-01-11 21:46:08 +00:00
|
|
|
use axum::{extract::Query, http::StatusCode, routing::get, Json, Router};
|
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
|
|
|
use serde::{Deserialize, Serialize};
|
|
|
|
|
use serde_json::json;
|
|
|
|
|
use tracing::info;
|
|
|
|
|
|
|
|
|
|
/// Query parameters for filtering tracking entries
|
|
|
|
|
#[derive(Debug, Deserialize, Serialize)]
|
|
|
|
|
pub struct TrackingFilter {
|
|
|
|
|
/// Filter by project path
|
|
|
|
|
pub project: Option<String>,
|
|
|
|
|
/// Filter by source type
|
|
|
|
|
pub source: Option<String>,
|
|
|
|
|
/// Limit number of results
|
|
|
|
|
pub limit: Option<usize>,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// Initialize tracking routes for the API
|
|
|
|
|
///
|
|
|
|
|
/// # Arguments
|
|
|
|
|
///
|
|
|
|
|
/// * `db` - Shared TrackingDb instance
|
|
|
|
|
///
|
|
|
|
|
/// # Returns
|
|
|
|
|
///
|
|
|
|
|
/// Router configured with tracking endpoints
|
2026-01-11 21:32:56 +00:00
|
|
|
#[allow(dead_code)]
|
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
|
|
|
pub fn setup_tracking_routes() -> Router {
|
|
|
|
|
Router::new()
|
|
|
|
|
.route("/tracking/entries", get(list_tracking_entries))
|
|
|
|
|
.route("/tracking/summary", get(get_tracking_summary))
|
|
|
|
|
.route("/tracking/health", get(tracking_health))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// List all tracking entries with optional filtering
|
|
|
|
|
///
|
|
|
|
|
/// # Query Parameters
|
|
|
|
|
///
|
|
|
|
|
/// * `project` - Filter by project path
|
|
|
|
|
/// * `source` - Filter by source type
|
|
|
|
|
/// * `limit` - Limit results (default: 100)
|
|
|
|
|
///
|
|
|
|
|
/// # Examples
|
|
|
|
|
///
|
|
|
|
|
/// `GET /api/v1/tracking/entries?project=/myproject&limit=50`
|
|
|
|
|
pub async fn list_tracking_entries(
|
|
|
|
|
Query(filter): Query<TrackingFilter>,
|
|
|
|
|
) -> Result<Json<serde_json::Value>, StatusCode> {
|
|
|
|
|
info!("Getting tracking entries with filter: {:?}", filter);
|
|
|
|
|
|
|
|
|
|
// TODO: Implement actual query using filter parameters
|
|
|
|
|
// For now, return placeholder response
|
|
|
|
|
let response = json!({
|
|
|
|
|
"items": [],
|
|
|
|
|
"count": 0,
|
|
|
|
|
"filter": filter
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
Ok(Json(response))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// Get tracking summary statistics
|
|
|
|
|
///
|
|
|
|
|
/// # Examples
|
|
|
|
|
///
|
|
|
|
|
/// `GET /api/v1/tracking/summary`
|
|
|
|
|
pub async fn get_tracking_summary() -> Result<Json<serde_json::Value>, StatusCode> {
|
|
|
|
|
info!("Getting tracking summary");
|
|
|
|
|
|
|
|
|
|
let summary = json!({
|
|
|
|
|
"total_entries": 0,
|
|
|
|
|
"change_count": 0,
|
|
|
|
|
"todo_count": 0,
|
|
|
|
|
"todos_by_status": {
|
|
|
|
|
"pending": 0,
|
|
|
|
|
"in_progress": 0,
|
|
|
|
|
"completed": 0,
|
|
|
|
|
"blocked": 0
|
|
|
|
|
},
|
|
|
|
|
"last_sync": chrono::Utc::now().to_rfc3339()
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
Ok(Json(summary))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// Health check for tracking service
|
|
|
|
|
///
|
|
|
|
|
/// # Examples
|
|
|
|
|
///
|
|
|
|
|
/// `GET /api/v1/tracking/health`
|
|
|
|
|
pub async fn tracking_health() -> Result<Json<serde_json::Value>, StatusCode> {
|
|
|
|
|
info!("Tracking service health check");
|
|
|
|
|
|
|
|
|
|
let response = json!({
|
|
|
|
|
"status": "ok",
|
|
|
|
|
"service": "vapora-tracking",
|
|
|
|
|
"timestamp": chrono::Utc::now().to_rfc3339()
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
Ok(Json(response))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#[cfg(test)]
|
|
|
|
|
mod tests {
|
|
|
|
|
use super::*;
|
|
|
|
|
|
|
|
|
|
#[test]
|
|
|
|
|
fn test_tracking_filter_deserialization() {
|
|
|
|
|
let json = r#"{"project": "/test", "limit": 50}"#;
|
|
|
|
|
let filter: TrackingFilter = serde_json::from_str(json).unwrap();
|
|
|
|
|
assert_eq!(filter.project, Some("/test".to_string()));
|
|
|
|
|
assert_eq!(filter.limit, Some(50));
|
|
|
|
|
}
|
|
|
|
|
}
|