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
|
|
|
// Home page / landing page
|
|
|
|
|
|
2026-01-11 21:32:56 +00:00
|
|
|
use crate::components::{Card, GlowColor, NavBar};
|
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
|
|
|
use leptos::prelude::*;
|
|
|
|
|
use leptos_router::components::A;
|
|
|
|
|
|
|
|
|
|
/// Home page component
|
|
|
|
|
#[component]
|
|
|
|
|
pub fn HomePage() -> impl IntoView {
|
|
|
|
|
view! {
|
|
|
|
|
<div class="min-h-screen bg-gradient-to-br from-slate-900 via-slate-800 to-slate-900 flex flex-col">
|
|
|
|
|
<NavBar />
|
|
|
|
|
|
|
|
|
|
<main class="flex-1 container mx-auto px-6 py-12">
|
|
|
|
|
<div class="max-w-2xl mx-auto text-center mb-12">
|
|
|
|
|
<h2 class="text-5xl font-bold mb-4 text-white">
|
|
|
|
|
"Multi-Agent Development Platform"
|
|
|
|
|
</h2>
|
|
|
|
|
<p class="text-xl text-gray-300 mb-8">
|
|
|
|
|
"12 specialized AI agents working in parallel to build, review, and deploy your software."
|
|
|
|
|
</p>
|
|
|
|
|
<div class="flex gap-4 justify-center">
|
|
|
|
|
<A
|
|
|
|
|
href="/projects"
|
|
|
|
|
attr:class="px-6 py-3 rounded-lg bg-gradient-to-r from-cyan-500/90 to-cyan-600/90 text-white font-medium hover:from-cyan-400 hover:to-cyan-500 transition-all hover:shadow-lg hover:shadow-cyan-500/50"
|
|
|
|
|
>
|
|
|
|
|
"Get Started"
|
|
|
|
|
</A>
|
|
|
|
|
<A
|
|
|
|
|
href="/agents"
|
|
|
|
|
attr:class="px-6 py-3 rounded-lg bg-white/10 border border-white/20 text-white font-medium hover:bg-white/20 transition-all"
|
|
|
|
|
>
|
|
|
|
|
"Explore Agents"
|
|
|
|
|
</A>
|
|
|
|
|
</div>
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<div class="grid grid-cols-1 md:grid-cols-3 gap-6 mt-12">
|
|
|
|
|
<Card glow=GlowColor::Cyan hover_effect=true>
|
|
|
|
|
<h3 class="text-lg font-semibold text-cyan-400 mb-2">"12 Agents"</h3>
|
|
|
|
|
<p class="text-gray-300 text-sm">
|
|
|
|
|
"Architect, Developer, Reviewer, Tester, Documenter, and more"
|
|
|
|
|
</p>
|
|
|
|
|
</Card>
|
|
|
|
|
<Card glow=GlowColor::Purple hover_effect=true>
|
|
|
|
|
<h3 class="text-lg font-semibold text-purple-400 mb-2">"Parallel Workflows"</h3>
|
|
|
|
|
<p class="text-gray-300 text-sm">
|
|
|
|
|
"All agents work simultaneously without waiting"
|
|
|
|
|
</p>
|
|
|
|
|
</Card>
|
|
|
|
|
<Card glow=GlowColor::Pink hover_effect=true>
|
|
|
|
|
<h3 class="text-lg font-semibold text-pink-400 mb-2">"Multi-IA Routing"</h3>
|
|
|
|
|
<p class="text-gray-300 text-sm">
|
|
|
|
|
"Claude, OpenAI, Gemini, and Ollama integration"
|
|
|
|
|
</p>
|
|
|
|
|
</Card>
|
|
|
|
|
</div>
|
|
|
|
|
</main>
|
|
|
|
|
|
|
|
|
|
<footer class="border-t border-white/10 bg-white/5 backdrop-blur-md py-6">
|
|
|
|
|
<div class="container mx-auto px-6 text-center text-gray-400 text-sm">
|
|
|
|
|
"VAPORA v1.0 — Multi-Agent Development Platform"
|
|
|
|
|
</div>
|
|
|
|
|
</footer>
|
|
|
|
|
</div>
|
|
|
|
|
}
|
|
|
|
|
}
|