{
  "kind": "benchmark_record",
  "id": "teleion.benchmarks/eranos-featured-run-2026-10-31",
  "recorded_on": "2026-10-31",
  "title": "End-to-end nonprofit kit build and independent second-worker check",
  "setup": "Recorded local test of a weekly volunteer shift-schedule kit, using example data and muse-spark-1.3-contributor with two separate worker keys; actual workerd with SQLite Durable Objects and D1",
  "execution_scope": "Local queue runtime with real model calls. Build and review completed; the parent request remained ready, held for a person. No delivery or publication was performed.",
  "metrics": {
    "build_duration": "3 min 27 s",
    "build_seconds": 207.27,
    "build_model_calls": 25,
    "check_duration": "1 min 23 s",
    "check_seconds": 82.73,
    "check_model_calls": 14,
    "unit_tests_passed": 8,
    "rule_violations": 0,
    "separate_reviewer_key": true
  },
  "notes": [
    "Worker 1 drafted the kit, its 8 unit tests and its README in 207.27 seconds (25 model calls).",
    "Worker 2, holding a different key, ran all 8 unit tests and checked the stated coverage rules in 82.73 seconds (14 model calls), recording 0 violations on the example input.",
    "Public test work used muse-spark-1.3-contributor; live requests use the standard tier."
  ]
}