lakehouse/tests/multi-agent/playbooks/scenario-2026-04-21T00-13-01/results.json

[
  {
    "event": {
      "kind": "baseline_fill",
      "at": "08:00",
      "role": "Warehouse Associate",
      "count": 3,
      "city": "Toledo",
      "state": "OH",
      "shift_start": "08:00 AM",
      "scenario_note": "Regular Monday morning shift, 8-hour."
    },
    "ok": true,
    "fills": [
      {
        "candidate_id": "W500K-49164",
        "name": "Christopher Y. Phillips",
        "reason": "SQL verified for high availability and semantic score of 0.63, making him the top candidate."
      },
      {
        "candidate_id": "W500K-34704",
        "name": "Fatima U. Rivera",
        "reason": "Semantic score of 0.61 and skills in cold storage make her a strong candidate."
      },
      {
        "candidate_id": "W500K-40928",
        "name": "Janet E. Hill",
        "reason": "Semantic score of 0.61, RF scanner skill, and high reliability score make her a suitable candidate."
      }
    ],
    "turns": 5,
    "duration_secs": 19.474,
    "gap_signals": [
      "double_book: undefined Fatima U. Rivera already booked for 08:00",
      "double_book: undefined Janet E. Hill already booked for 08:00"
    ],
    "sources_first_score": 0.6233225,
    "sources_last_score": 0.55385745,
    "pool_size": 770,
    "playbook_citations": [],
    "discovered_pattern": "Across 25 similar past playbooks (6 workers examined) · recurring certifications: Forklift (67%), OSHA-10 (50%) · recurring skills: mill (50%), 6S (50%) · archetype mostly: communicator · reliability median 0.83 (range 0.75–0.96)"
  },
  {
    "event": {
      "kind": "recurring",
      "at": "10:30",
      "role": "Machine Operator",
      "count": 2,
      "city": "Toledo",
      "state": "OH",
      "shift_start": "11:00 AM",
      "scenario_note": "Recurring Tuesday/Thursday slot — prior workers may still be available."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 48.986,
    "error": "no consensus after 14 turns",
    "gap_signals": [
      "drift_or_tool: no consensus after 14 turns"
    ]
  },
  {
    "event": {
      "kind": "expansion",
      "at": "12:15",
      "role": "Forklift Operator",
      "count": 5,
      "city": "Toledo",
      "state": "OH",
      "shift_start": "01:00 PM",
      "scenario_note": "New warehouse location opening, five-worker team needed."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 2.845,
    "error": "invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\",\n\"args\":{\"index_name\":\"workers_500k_v1\",\n\"sql_filter\":\"role = 'Forklift Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND CAST(reliability AS DOUBLE) > 0.75 AND worker_id NOT IN (42319, 68741, 34927)\",\n\"rationale\":\"Se",
    "gap_signals": [
      "drift_or_tool: invalid JSON from executor: JSON Parse error: Expected '}' | raw: {\"kind\":\"tool_call\",\"tool\":\"hybrid_search\",\n\"args\":{\"index_name\":\"workers_500k_v1\",\n\"sql_filter\":\"role = 'Forklift Operator' AND city = 'Toledo' AND state = 'OH' AND CAST(availability AS DOUBLE) > 0.5 AND CAST(reliability AS DOUBLE) > 0.75 AND worker_id NOT IN (42319, 68741, 34927)\",\n\"rationale\":\"Se"
    ]
  },
  {
    "event": {
      "kind": "emergency",
      "at": "14:00",
      "role": "Loader",
      "count": 4,
      "city": "Toledo",
      "state": "OH",
      "shift_start": "04:00 PM same day",
      "deadline": "16:00",
      "scenario_note": "Walkoff incident — replacement crew needed by 16:00 sharp."
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 48.905,
    "error": "no consensus after 14 turns",
    "gap_signals": [
      "drift_or_tool: no consensus after 14 turns"
    ]
  },
  {
    "event": {
      "kind": "misplacement",
      "at": "15:45",
      "role": "Warehouse Associate",
      "count": 1,
      "city": "Toledo",
      "state": "OH",
      "shift_start": "remainder of 08:00 shift",
      "scenario_note": "One worker from the 08:00 fill didn't show; rebuild the gap.",
      "replaces_event": "08:00",
      "exclude_worker_ids": [
        null,
        null,
        null
      ]
    },
    "ok": false,
    "fills": [],
    "turns": 0,
    "duration_secs": 47.789,
    "error": "no consensus after 14 turns",
    "gap_signals": [
      "drift_or_tool: no consensus after 14 turns"
    ]
  }
]