8 Commits

Author	SHA1	Message	Date
Jesús Pérez	847523e4d4	fix: eliminate stub implementations across 6 integration points ... - WorkflowOrchestrator and WorkflowService wired in main.rs (non-fatal) - try_fallback_with_budget actually calls fallback providers - vapora-tracking persistence: real TrackingEntry + NatsPublisher - vapora-doc-lifecycle: workspace + classify/consolidate/rag/NATS stubs - Merkle hash chain audit trail (tamper-evident, verify_integrity) - /api/v1/workflows/* routes operational; get_workflow_audit Result fix - ADR-0039, CHANGELOG, workflow-orchestrator docs updated	2026-02-27 00:00:02 +00:00
Jesús Pérez	27a290b369	feat(kg,channels): hybrid search + agent-inactive notifications ... - KG: HNSW + BM25 + RRF(k=60) hybrid search via SurrealDB 3 native indexes - Fix schema bug: kg_executions missing agent_role/provider/cost_cents (silent empty reads) - channels: on_agent_inactive hook (AgentStatus::Inactive → Message::error) - migration 012: adds missing fields + HNSW + BM25 indexes - docs: ADR-0036, update ADR-0035 + notification-channels feature doc	2026-02-26 15:32:44 +00:00
Jesús Pérez	bb55c80d2b	feat(workflow-engine): autonomous scheduling with timezone and distributed lock ... Add cron-based autonomous workflow firing with two hardening layers: - Timezone-aware scheduling via chrono-tz: ScheduledWorkflow.timezone (IANA identifier), compute_next_fire_at/after_tz, validate_timezone; DST-safe, UTC fallback when absent; validated at config load and REST API - Distributed fire-lock via SurrealDB conditional UPDATE (locked_by/locked_at fields, 120 s TTL); WorkflowScheduler gains instance_id (UUID) as lock owner; prevents double-fires across multi-instance deployments without extra infra - ScheduleStore: try_acquire_fire_lock, release_fire_lock (own-instance guard), full CRUD (load_one/all, full_upsert, patch, delete, load_runs) - REST: 7 endpoints (GET/PUT/PATCH/DELETE schedules, runs history, manual fire) with timezone field in all request/response types - Migrations 010 (schedule tables) + 011 (timezone + lock columns) - Tests: 48 passing (was 26); ADR-0034; changelog; feature docs updated	2026-02-26 11:34:44 +00:00
Jesús Pérez	b9e2cee9f7	feat(workflow-engine): add saga, persistence, auth, and NATS-integrated orchestrator hardening ... Key changes driving this: new saga.rs, persistence.rs, auth.rs in workflow-engine; SurrealDB migration 009_workflow_state.surql; backend services refactored; frontend dist built; ADR-0033 documenting the hardening decision.	2026-02-22 21:44:42 +00:00
Jesús Pérez	df829421d8	chore: udate docs, add architecture diagrams	2026-02-16 05:12:22 +00:00
Jesús Pérez	b6a4d77421	feat: add Leptos UI library and modularize MCP server	2026-02-14 20:10:55 +00:00
Jesús Pérez	fe4d138a14	feat: CLI arguments, distribution management, and approval gates ... - Add CLI support (--config, --help) with env var override for backend/agents - Implement distro justfile recipes: list-targets, install-targets, build-target, install - Fix OpenTelemetry API incompatibilities and remove deprecated calls - Add tokio "time" feature for timeout support - Fix Cargo profile warnings and Nushell script syntax - Update all dead_code warnings with strategic annotations - Zero compiler warnings in vapora codebase - Comprehensive CHANGELOG documenting risk-based approval gates system	2026-02-03 21:35:00 +00:00
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.	2026-01-11 13:03:53 +00:00