fa68141d47
- Add pipeline-judge agent for objective fitness scoring - Update capability-index.yaml with pipeline-judge, evolution config - Add fitness-evaluation.md workflow for auto-optimization - Update evolution.md command with /evolve CLI - Create .kilo/logs/fitness-history.jsonl for metrics logging - Update AGENTS.md with new workflow state machine - Add 6 new issues to MILESTONE_ISSUES.md for evolution integration - Preserve ideas in agent-evolution/ideas/ Pipeline Judge computes fitness = (test_rate*0.5) + (gates*0.25) + (efficiency*0.25) Auto-triggers prompt-optimizer when fitness < 0.70
85 lines
2.3 KiB
JSON
85 lines
2.3 KiB
JSON
{
|
|
"$schema": "https://app.kilo.ai/agent-recommendations.json",
|
|
"generated": "2026-04-05T20:00:00Z",
|
|
"source": "APAW Evolution System Design",
|
|
"description": "Adds pipeline-judge agent and evolution workflow to APAW",
|
|
|
|
"new_files": [
|
|
{
|
|
"path": ".kilo/agents/pipeline-judge.md",
|
|
"source": "pipeline-judge.md",
|
|
"description": "Automated fitness evaluator — runs tests, measures tokens/time, produces fitness score"
|
|
},
|
|
{
|
|
"path": ".kilo/workflows/evolution.md",
|
|
"source": "evolution-workflow.md",
|
|
"description": "Continuous self-improvement loop for agent pipeline"
|
|
},
|
|
{
|
|
"path": ".kilo/commands/evolve.md",
|
|
"source": "evolve-command.md",
|
|
"description": "/evolve command — trigger evolution cycle"
|
|
}
|
|
],
|
|
|
|
"capability_index_additions": {
|
|
"agents": {
|
|
"pipeline-judge": {
|
|
"capabilities": [
|
|
"test_execution",
|
|
"fitness_scoring",
|
|
"metric_collection",
|
|
"bottleneck_detection"
|
|
],
|
|
"receives": [
|
|
"completed_workflow",
|
|
"pipeline_logs"
|
|
],
|
|
"produces": [
|
|
"fitness_report",
|
|
"bottleneck_analysis",
|
|
"improvement_triggers"
|
|
],
|
|
"forbidden": [
|
|
"code_writing",
|
|
"code_changes",
|
|
"prompt_changes"
|
|
],
|
|
"model": "ollama-cloud/nemotron-3-super",
|
|
"mode": "subagent"
|
|
}
|
|
},
|
|
"capability_routing": {
|
|
"fitness_scoring": "pipeline-judge",
|
|
"test_execution": "pipeline-judge",
|
|
"bottleneck_detection": "pipeline-judge"
|
|
},
|
|
"iteration_loops": {
|
|
"evolution": {
|
|
"evaluator": "pipeline-judge",
|
|
"optimizer": "prompt-optimizer",
|
|
"max_iterations": 3,
|
|
"convergence": "fitness_above_0.85"
|
|
}
|
|
},
|
|
"evolution": {
|
|
"enabled": true,
|
|
"auto_trigger": true,
|
|
"fitness_threshold": 0.70,
|
|
"max_evolution_attempts": 3,
|
|
"fitness_history": ".kilo/logs/fitness-history.jsonl",
|
|
"budgets": {
|
|
"feature": {"tokens": 50000, "time_s": 300},
|
|
"bugfix": {"tokens": 20000, "time_s": 120},
|
|
"refactor": {"tokens": 40000, "time_s": 240},
|
|
"security": {"tokens": 30000, "time_s": 180}
|
|
}
|
|
}
|
|
},
|
|
|
|
"workflow_state_additions": {
|
|
"evaluated": ["evolving", "completed"],
|
|
"evolving": ["evaluated"]
|
|
}
|
|
}
|