id: 092
narrative_anchor_date: '2028-01-01'
test: I’m working from home on Tuesday, January 4, 2028. Please check my calendar from 9:00 to 11:00 a.m.
  Central and, if that window is clear, create a focus block for a high-bandwidth dashboard review. In
  the title or notes, identify the best room for stable video calls and large dashboard loads, and note
  how using it affects Sam’s access to the rest of the house during his off-hours.
load_bearing_facts:
- 22
- 23
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_dashboard_focus
      path: result.ok
      value: true
      check_id: riley_092_00
    - check_id: riley_092_01
      type: field_equals
      tool: list_calendar_events
      action_id: check_jan4_window
      path: args.date
      value: '2028-01-04'
    - check_id: riley_092_02
      type: datetime_absolute_eq
      tool: create_calendar_event
      action_id: create_dashboard_focus
      path: args.start
      value: '2028-01-04T09:00:00-06:00'
    - check_id: riley_092_03
      type: datetime_absolute_eq
      tool: create_calendar_event
      action_id: create_dashboard_focus
      path: args.end
      value: '2028-01-04T11:00:00-06:00'
    - type: field_equals
      tool: list_calendar_events
      action_id: check_jan4_window
      path: args.timezone
      value: America/Chicago
      check_id: riley_092_04
    - type: field_llm_judge
      tool: create_calendar_event
      action_id: create_dashboard_focus
      path: args
      criterion: 'The title or body must clearly identify this event as a focus block for a high-bandwidth
        dashboard review. Either content field is acceptable; missing or contradictory meaning fails.


        The title or body must unambiguously identify the workroom as the workspace for this block. The
        optional Cherrywood qualifier is not required. Either content field is acceptable; another room,
        ambiguous room information, no room identification, or contradictory meaning fails.


        The title or body must state that using the workroom leaves the rest of the house available for
        Sam during his off-hours. Either content field is acceptable; missing or contradictory meaning
        fails.'
      check_id: riley_092_05
mock_state:
  calendar: []