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.
55 lines
1.6 KiB
Markdown
55 lines
1.6 KiB
Markdown
# Docker Build Configuration
|
|
|
|
Dockerfiles for VAPORA microservices. All images are built from the root of the repository.
|
|
|
|
## Services
|
|
|
|
| Service | Dockerfile | Port | Purpose |
|
|
|---------|-----------|------|---------|
|
|
| **Backend API** | `vapora-backend.Dockerfile` | 8001 | REST API (Axum) |
|
|
| **Agent Server** | `vapora-agents.Dockerfile` | 8002 | Agent orchestration (NATS) |
|
|
| **Frontend** | `vapora-frontend.Dockerfile` | 3000 | Leptos WASM UI |
|
|
| **MCP Gateway** | `vapora-mcp-server.Dockerfile` | 3030 | Model Context Protocol |
|
|
|
|
## Building Images
|
|
|
|
All Dockerfiles are located here and reference the root workspace. Build commands:
|
|
|
|
### Build All Images
|
|
|
|
```bash
|
|
cd /Users/Akasha/Development/vapora
|
|
|
|
# Backend
|
|
docker build -f docker/vapora-backend.Dockerfile -t vapora-backend:latest .
|
|
|
|
# Agents
|
|
docker build -f docker/vapora-agents.Dockerfile -t vapora-agents:latest .
|
|
|
|
# Frontend
|
|
docker build -f docker/vapora-frontend.Dockerfile -t vapora-frontend:latest .
|
|
|
|
# MCP Server
|
|
docker build -f docker/vapora-mcp-server.Dockerfile -t vapora-mcp-server:latest .
|
|
```
|
|
|
|
### Build Script
|
|
|
|
See `../scripts/build.nu` for automated multi-image builds.
|
|
|
|
## Image Specifications
|
|
|
|
- **Base Images**: Rust 1.75+ (distroless for production)
|
|
- **Optimization**: LTO, thin LTO, release builds
|
|
- **Size Target**: < 200MB per image (distroless)
|
|
|
|
## Development Container
|
|
|
|
See `../.devcontainer/Dockerfile` for development environment setup (VS Code).
|
|
|
|
---
|
|
|
|
**Architecture**: Multi-service containerized deployment
|
|
**Orchestration**: Kubernetes (see `../kubernetes/`)
|
|
**CI/CD**: GitHub Actions / Woodpecker (see `../.github/`, `../.woodpecker/`)
|