id: '183'
narrative_anchor_date: '2028-01-01'
test: Owen expects to close the Q1 four-lane evidence packet on March 31, 2028. Please check April 3 and,
  if 10:00 a.m. Central is free, reserve a 30-minute audit handoff. Put the standard quarterly hands-on
  audit scope in the notes.
load_bearing_facts:
- 230
expected_tool_calls:
- 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_calendar_event
      action_id: create_audit_handoff
      path: result.ok
      value: true
      check_id: riley_183_00
    - type: field_equals
      tool: list_calendar_events
      action_id: check_apr3_calendar
      path: args.date
      value: '2028-04-03'
      check_id: riley_183_01
    - type: datetime_absolute_eq
      tool: create_calendar_event
      action_id: create_audit_handoff
      path: args.start
      value: '2028-04-03T10:00:00-05:00'
      check_id: riley_183_02
    - type: datetime_absolute_eq
      tool: create_calendar_event
      action_id: create_audit_handoff
      path: args.end
      value: '2028-04-03T10:30:00-05:00'
      check_id: riley_183_03
    - type: field_equals
      tool: list_calendar_events
      action_id: check_apr3_calendar
      path: args.timezone
      value: America/Chicago
      check_id: riley_183_04
    - type: field_llm_judge
      tool: create_calendar_event
      action_id: create_audit_handoff
      path: args
      criterion: The event is clearly a Q1 evidence audit handoff. Its notes say that after Owen closes
        the four-lane packet, one lane will be independently rechecked for its denominator or coverage
        dates, outcome window, exclusions, reliability evidence, revenue treatment, and forecast treatment.
      check_id: riley_183_05
mock_state:
  calendar: []