id: '137'
narrative_anchor_date: '2028-01-01'
test: Please create a durable maintenance entry for the Cherrywood workroom smoke detector using the completed
  service history, including the unit serviced, replacement and test results, service-record status, and
  the related fault findings. Then check my calendar for July 9, 2028. If 9:00 a.m. Central is clear,
  add a 15-minute routine anniversary inspection reminder for the workroom detector. Keep the reminder
  routine and do not imply there is a current unresolved defect.
load_bearing_facts:
- 262
- 261
expected_tool_calls:
- create_doc
- list_calendar_events
- create_calendar_event
grade:
  type: tool_trace
  config:
    check_version: 2
    today: '2028-01-01'
    semantic_judge_version: 2
    assertions:
    - type: field_equals
      tool: create_doc
      action_id: create_maintenance_record
      path: result.ok
      value: true
      check_id: riley_137_00
    - type: field_equals
      tool: create_calendar_event
      action_id: create_anniversary_reminder
      path: result.ok
      value: true
      check_id: riley_137_01
    - check_id: riley_137_02
      type: field_equals
      tool: list_calendar_events
      action_id: check_anniversary_availability
      path: args.date
      value: '2028-07-09'
    - check_id: riley_137_03
      type: datetime_absolute_eq
      tool: create_calendar_event
      action_id: create_anniversary_reminder
      path: args.start
      value: '2028-07-09T09:00:00-05:00'
    - check_id: riley_137_04
      type: datetime_absolute_eq
      tool: create_calendar_event
      action_id: create_anniversary_reminder
      path: args.end
      value: '2028-07-09T09:15:00-05:00'
    - type: field_equals
      tool: list_calendar_events
      action_id: check_anniversary_availability
      path: args.timezone
      value: America/Chicago
      check_id: riley_137_05
    - type: field_llm_judge
      tool: create_doc
      action_id: create_maintenance_record
      path: args
      criterion: The document body must state that the Cherrywood workroom smoke detector was replaced
        on July 9, 2027; the installed unit successfully passed both alarm and power tests; a dated service
        record identifying the workroom unit as replaced was issued; and no wiring, ceiling, moisture,
        or adjacent-equipment fault was found. Missing or contradictory service status, test results,
        or fault findings must fail.
      check_id: riley_137_06
    - type: field_llm_judge
      tool: create_calendar_event
      action_id: create_anniversary_reminder
      path: args
      criterion: Across the event title and body, with either content field acceptable, the event must
        clearly be a routine anniversary inspection reminder for the Cherrywood workroom smoke detector
        and must not claim or imply that the detector currently has an unresolved defect.
      check_id: riley_137_07
mock_state:
  calendar: []