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
|
|
|
// Error types for VAPORA v1.0
|
|
|
|
|
// Phase 1: Comprehensive error handling with proper conversions
|
|
|
|
|
|
|
|
|
|
use thiserror::Error;
|
|
|
|
|
|
|
|
|
|
/// Main error type for VAPORA
|
|
|
|
|
#[derive(Error, Debug)]
|
|
|
|
|
pub enum VaporaError {
|
|
|
|
|
/// Configuration loading or validation error
|
|
|
|
|
#[error("Configuration error: {0}")]
|
|
|
|
|
ConfigError(String),
|
|
|
|
|
|
|
|
|
|
/// Database operation error
|
|
|
|
|
#[error("Database error: {0}")]
|
|
|
|
|
DatabaseError(String),
|
|
|
|
|
|
|
|
|
|
/// Resource not found error
|
|
|
|
|
#[error("Not found: {0}")]
|
|
|
|
|
NotFound(String),
|
|
|
|
|
|
|
|
|
|
/// Invalid input or validation error
|
|
|
|
|
#[error("Invalid input: {0}")]
|
|
|
|
|
InvalidInput(String),
|
|
|
|
|
|
2026-01-14 21:12:49 +00:00
|
|
|
/// Schema validation error (Nickel contracts)
|
|
|
|
|
#[error("Validation error: {0}")]
|
|
|
|
|
ValidationError(String),
|
|
|
|
|
|
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
|
|
|
/// Authentication or authorization error
|
|
|
|
|
#[error("Unauthorized: {0}")]
|
|
|
|
|
Unauthorized(String),
|
|
|
|
|
|
|
|
|
|
/// Agent system error
|
|
|
|
|
#[error("Agent error: {0}")]
|
|
|
|
|
AgentError(String),
|
|
|
|
|
|
|
|
|
|
/// LLM router error
|
|
|
|
|
#[error("LLM router error: {0}")]
|
|
|
|
|
LLMRouterError(String),
|
|
|
|
|
|
|
|
|
|
/// Workflow execution error
|
|
|
|
|
#[error("Workflow error: {0}")]
|
|
|
|
|
WorkflowError(String),
|
|
|
|
|
|
|
|
|
|
/// NATS messaging error
|
|
|
|
|
#[error("NATS error: {0}")]
|
|
|
|
|
NatsError(String),
|
|
|
|
|
|
|
|
|
|
/// IO operation error
|
|
|
|
|
#[error("IO error: {0}")]
|
|
|
|
|
IoError(#[from] std::io::Error),
|
|
|
|
|
|
|
|
|
|
/// Serialization/deserialization error
|
|
|
|
|
#[error("Serialization error: {0}")]
|
|
|
|
|
SerializationError(#[from] serde_json::Error),
|
|
|
|
|
|
|
|
|
|
/// TOML parsing error
|
|
|
|
|
#[error("TOML error: {0}")]
|
|
|
|
|
TomlError(String),
|
|
|
|
|
|
|
|
|
|
/// Internal server error
|
|
|
|
|
#[error("Internal server error: {0}")]
|
|
|
|
|
InternalError(String),
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// Result type alias using VaporaError
|
|
|
|
|
pub type Result<T> = std::result::Result<T, VaporaError>;
|
|
|
|
|
|
|
|
|
|
// ============================================================================
|
|
|
|
|
// Error Conversions
|
|
|
|
|
// ============================================================================
|
|
|
|
|
|
|
|
|
|
#[cfg(feature = "backend")]
|
|
|
|
|
impl From<surrealdb::Error> for VaporaError {
|
|
|
|
|
fn from(err: surrealdb::Error) -> Self {
|
|
|
|
|
VaporaError::DatabaseError(err.to_string())
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
impl From<toml::de::Error> for VaporaError {
|
|
|
|
|
fn from(err: toml::de::Error) -> Self {
|
|
|
|
|
VaporaError::TomlError(err.to_string())
|
|
|
|
|
}
|
|
|
|
|
}
|