2 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Jesús Pérez
|
75e5ebd9a2
|
chore: ontology sync + 4 NCL ADRs + landing page update
Some checks failed
Documentation Lint & Validation / Markdown Linting (push) Has been cancelled
Documentation Lint & Validation / Validate mdBook Configuration (push) Has been cancelled
Documentation Lint & Validation / Content & Structure Validation (push) Has been cancelled
mdBook Build & Deploy / Build mdBook (push) Has been cancelled
Nickel Type Check / Nickel Type Checking (push) Has been cancelled
Rust CI / Security Audit (push) Has been cancelled
Rust CI / Check + Test + Lint (nightly) (push) Has been cancelled
Rust CI / Check + Test + Lint (stable) (push) Has been cancelled
Documentation Lint & Validation / Lint & Validation Summary (push) Has been cancelled
mdBook Build & Deploy / Documentation Quality Check (push) Has been cancelled
mdBook Build & Deploy / Deploy to GitHub Pages (push) Has been cancelled
mdBook Build & Deploy / Notification (push) Has been cancelled
on+re:
- core.ncl: 5 new Practice nodes (notification-channels,
vapora-capabilities, agent-hot-reload-stable-identity,
merkle-audit-trail, notification-channels) + 5 new edges;
knowledge-graph-execution-history updated with HNSW+BM25+RRF
- state.ncl: production-readiness blocker/catalyst updated (hot-reload
complete, BudgetManager/LLMRouter still require restart);
ontoref-integration catalyst updated (vapora-ontology/reflection
crates, api-catalog.json, nickel contracts)
ADRs (NCL):
- adr-013: KG hybrid search — HNSW+BM25+RRF, rejected in-process scan
- adr-014: capability packages — AgentDefinition→vapora-shared,
DashMap shard-before-await constraint
- adr-015: Merkle audit trail — SHA-256 hash chain, rejected HMAC
- adr-016: agent hot-reload — stable_id=role, learning_profiles survive
drain, BudgetManager excluded from reload scope
landing page:
- 2 new feature boxes: VCS-Agnostic Worktree (jj/git), Ontology Protocol
- KG box: 20→28 tests, HNSW+BM25+RRF description
- Agents box: 71→82 tests, hot-reload + stable_id
- tech stack: Rust 21→23 crates, added jj, Radicle, ontoref badges
- status badge: 620→691 tests
|
||
|
Jesús Pérez
|
d14150da75 |
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. |