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.
68 lines
918 B
Plaintext
68 lines
918 B
Plaintext
CLAUDE.md
|
|
.claude
|
|
utils/save*sh
|
|
COMMIT_MESSAGE.md
|
|
.wrks
|
|
nushell
|
|
nushell-*
|
|
*.tar.gz
|
|
#*-nushell-plugins.tar.gz
|
|
github-com
|
|
.coder
|
|
target
|
|
distribution
|
|
.qodo
|
|
# enviroment to load on bin/build
|
|
.env
|
|
# OSX trash
|
|
.DS_Store
|
|
|
|
# Vscode files
|
|
.vscode
|
|
|
|
# Emacs save files
|
|
*~
|
|
\#*\#
|
|
.\#*
|
|
|
|
# Vim-related files
|
|
[._]*.s[a-w][a-z]
|
|
[._]s[a-w][a-z]
|
|
*.un~
|
|
Session.vim
|
|
.netrwhist
|
|
|
|
# cscope-related files
|
|
cscope.*
|
|
|
|
# User cluster configs
|
|
.kubeconfig
|
|
|
|
.tags*
|
|
|
|
# direnv .envrc files
|
|
.envrc
|
|
|
|
# make-related metadata
|
|
/.make/
|
|
|
|
# Just in time generated data in the source, should never be committed
|
|
/test/e2e/generated/bindata.go
|
|
|
|
# This file used by some vendor repos (e.g. github.com/go-openapi/...) to store secret variables and should not be ignored
|
|
!\.drone\.sec
|
|
|
|
# Godeps workspace
|
|
/Godeps/_workspace
|
|
|
|
/bazel-*
|
|
*.pyc
|
|
|
|
# generated by verify-vendor.sh
|
|
vendordiff.patch
|
|
.claude/settings.local.json
|
|
|
|
# Generated SBOM files
|
|
SBOM.*.json
|
|
*.sbom.json
|