lakehouse/tests/multi-agent/playbooks/scenario-2026-04-21T02-43-22/results.json

[
  {
    "event": {
      "kind": "baseline_fill",
      "at": "07:00",
      "role": "Electrician",
      "count": 5,
      "city": "Gary",
      "state": "IN",
      "shift_start": "07:00 AM",
      "scenario_note": "Gary IN has ZERO Electricians in the index. Local WILL fail this. Cloud should diagnose no-supply and recommend pivoting to Chicago IL (40min drive) or relaxing to 'Maintenance Tech'."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 24.921,
    "error": "aborted — 3 consecutive drift flags",
    "gap_signals": [
      "drift_or_tool: aborted — 3 consecutive drift flags"
    ]
  },
  {
    "event": {
      "kind": "expansion",
      "at": "09:30",
      "role": "Safety Coordinator",
      "count": 8,
      "city": "Peoria",
      "state": "IL",
      "shift_start": "09:30 AM",
      "scenario_note": "Safety Coordinator is the rarest role overall (~4500 nationally). 8× in a mid-sized city with availability > 0.5 is genuinely tight. Cloud should either confirm or suggest multi-city sourcing."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 48.719,
    "error": "aborted — 3 consecutive drift flags",
    "gap_signals": [
      "drift_or_tool: aborted — 3 consecutive drift flags"
    ]
  },
  {
    "event": {
      "kind": "emergency",
      "at": "11:45",
      "role": "Welder",
      "count": 3,
      "city": "Flint",
      "state": "MI",
      "shift_start": "12:00 PM",
      "deadline": "13:30",
      "scenario_note": "Flint MI has ZERO workers indexed — total data desert. Cloud must flag 'impossible supply' and recommend pivot (Detroit 60mi, Saginaw 40mi)."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 20.138,
    "error": "aborted — 3 consecutive drift flags",
    "gap_signals": [
      "drift_or_tool: aborted — 3 consecutive drift flags"
    ]
  },
  {
    "event": {
      "kind": "expansion",
      "at": "14:00",
      "role": "Tool & Die Maker",
      "count": 4,
      "city": "Grand Rapids",
      "state": "MI",
      "shift_start": "14:00 PM",
      "scenario_note": "Tool & Die Maker is scarce (~9000 total). 4× in Grand Rapids, availability > 0.5 AND reliability > 0.75. Tight but solvable if playbook_memory has history; cloud should prioritize proven performers."
    },
    "ok": true,
    "fills": [
      {
        "candidate_id": "W500K-49117",
        "name": "Deborah D. Wilson"
      },
      {
        "candidate_id": "W500K-4243",
        "name": "Jerry Thompson"
      },
      {
        "candidate_id": "W500K-14314",
        "name": "Carolyn Lopez"
      },
      {
        "candidate_id": "W500K-15737",
        "name": "Kyle H. Ramos"
      }
    ],
    "turns": 2,
    "duration_secs": 12.711,
    "gap_signals": [
      "double_book: undefined Jerry Thompson already booked for 14:00",
      "double_book: undefined Carolyn Lopez already booked for 14:00",
      "double_book: undefined Kyle H. Ramos already booked for 14:00",
      "artifact: undefined is not an object (evaluating 'f.reason.slice')"
    ],
    "sources_first_score": 0.72152853,
    "sources_last_score": 0.51832277,
    "pool_size": 133,
    "playbook_citations": [],
    "discovered_pattern": "Across 25 similar past playbooks (34 workers examined) · recurring certifications: OSHA-10 (47%) · archetype mostly: flexible · reliability median 0.77 (range 0.19–1.00)"
  },
  {
    "event": {
      "kind": "misplacement",
      "at": "15:30",
      "role": "Electrician",
      "count": 1,
      "city": "Gary",
      "state": "IN",
      "shift_start": "15:30 PM",
      "replaces_event": "07:00",
      "scenario_note": "Refilling 1× Electrician in Gary after a no-show. Same data desert as event 1 — cloud should recognize the repeat and recommend the SAME pivot it gave earlier, proving it learns within-run."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 26.796,
    "error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"plan\",\"steps\":[\"Expand search to nearby cities (South Bend, IN) and adjacent states (OH, MI) for Electricians with availability > 0.5.\",\"Verify top candidates via SQL to confirm role, location, and availability.\",\"Select the best verified candidate and propose_done.\"]{\"kind\":\"tool_call\",\"to",
    "gap_signals": [
      "drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"plan\",\"steps\":[\"Expand search to nearby cities (South Bend, IN) and adjacent states (OH, MI) for Electricians with availability > 0.5.\",\"Verify top candidates via SQL to confirm role, location, and availability.\",\"Select the best verified candidate and propose_done.\"]{\"kind\":\"tool_call\",\"to"
    ]
  }
]