{
  "id": "aiwg-evals",
  "type": "addon",
  "name": "AIWG Evaluations",
  "version": "1.0.0",
  "description": "Automated evaluation framework for agent quality, based on KAMI benchmark methodology and ReAct patterns",
  "core": false,
  "autoInstall": false,
  "author": "AIWG Contributors",
  "license": "MIT",
  "repository": "https://github.com/jmagly/aiwg",
  "keywords": [
    "aiwg",
    "evals",
    "testing",
    "quality",
    "benchmark",
    "kami",
    "react"
  ],
  "researchFoundation": {
    "REF-001": "BP-9 - Continuous evaluation of agent performance",
    "REF-002": "KAMI benchmark - Real agentic task evaluation"
  },
  "entry": {
    "tests": "tests/",
    "scenarios": "scenarios/",
    "reports": "reports/",
    "commands": "commands/"
  },
  "commands": [
    "eval-agent",
    "eval-workflow",
    "eval-report"
  ],
  "scenarios": [
    "grounding-test",
    "distractor-test",
    "recovery-test",
    "parallel-test"
  ]
}