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	e5e2244e04	feat(security): add SSRF protection and prompt injection scanning ... - Add security module (ssrf.rs, prompt_injection.rs) to vapora-backend - Block RFC 1918, link-local, cloud metadata URLs before channel registration - Scan 60+ injection patterns on RLM (load/query/analyze) and task endpoints - Fix channel SSRF: filter-before-register instead of warn-and-proceed - Add sanitize() to load_document (was missing, only analyze_document had it) - Return 400 Bad Request (not 500) for all security rejections - Add 11 integration tests via Surreal::init() — no external deps required - Document in ADR-0038, CHANGELOG, and docs/adrs/README.md	2026-02-26 18:20:07 +00:00
Jesús Pérez	027b8f2836	feat(channels): webhook notification channels with built-in secret resolution ... Add vapora-channels crate with trait-based Slack/Discord/Telegram webhook delivery. ${VAR}/${VAR:-default} interpolation is mandatory inside ChannelRegistry::from_config — callers cannot bypass secret resolution. Fire-and-forget dispatch via tokio::spawn in both vapora-workflow-engine (four lifecycle events) and vapora-backend (task Done, proposal approve/reject). New REST endpoints: GET /channels, POST /channels/:name/test. dispatch_notifications extracted as pub(crate) fn for inline testability; 5 handler tests + 6 workflow engine tests + 7 secret resolution unit tests. Closes: vapora-channels bootstrap, notification gap in workflow/backend layer ADR: docs/adrs/0035-notification-channels.md	2026-02-26 14:49:34 +00:00
Jesús Pérez	4efea3053e	chore: add A2A y RLM	2026-02-16 05:09:51 +00:00
Jesús Pérez	b6a4d77421	feat: add Leptos UI library and modularize MCP server	2026-02-14 20:10:55 +00:00
Jesús Pérez	cc55b97678	chore: update README and CHANGELOG with workflow orchestrator features	2026-01-24 02:07:45 +00:00
Jesús Pérez	dd68d190ef	ci: Update pre-commit hooks configuration ... - Exclude problematic markdown files from linting (existing legacy issues) - Make clippy check less aggressive (warnings only, not -D warnings) - Move cargo test to manual stage (too slow for pre-commit) - Exclude SVG files from end-of-file-fixer and trailing-whitespace - Add markdown linting exclusions for existing documentation This allows pre-commit hooks to run successfully on new code without blocking commits due to existing issues in legacy documentation files.	2026-01-11 21:32:56 +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