Test 166

Jan 1, 2028 / 1 fact

Request

Please use the effective start date we established for Sam’s expanded role to find its 2028 anniversary. Check my calendar on that date and, if 9:00 a.m. Central is open, add a private 10-minute reminder. Keep it as a personal reminder with no attendees—don’t turn it into a restaurant event or add celebration plans.

Required memory

Fact 87

Sam signed and accepted the revised written restaurant role agreement, effective April 7, 2025.

Source evidence (1)

002760Mar 26, 2025 / 08:10 UTC-05:00

The restaurant sent Sam a revised written role agreement after the chef-owner and operating partner reviewed his counter. It removes the proposed fixed requirement for two additional monthly closes and accepts his conditions: one fixed no-service evening each week, ordinary rota notice three weeks ahead, and no default private-event coverage on that protected evening. Beginning April 7, Sam has final authority over seasonal menu development and private dining and will receive quarterly profit participation. He signed and accepted the expanded role on those written terms. The schedule protections are part of the role agreement, not discretionary exceptions, though they have not operated long enough to prove sustainable.

Message 002760 in history

Expected tool calls

list_calendar_events
create_calendar_event

Grading

1. field_equals / create_calendar_event

{
  "type": "field_equals",
  "tool": "create_calendar_event",
  "action_id": "create_private_reminder",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_166_00"
}

2. field_equals / list_calendar_events

{
  "check_id": "riley_166_01",
  "type": "field_equals",
  "tool": "list_calendar_events",
  "action_id": "check_anniversary_date",
  "path": "args.date",
  "value": "2028-04-07"
}

3. datetime_absolute_eq / create_calendar_event

{
  "check_id": "riley_166_02",
  "type": "datetime_absolute_eq",
  "tool": "create_calendar_event",
  "action_id": "create_private_reminder",
  "path": "args.start",
  "value": "2028-04-07T09:00:00-05:00"
}

4. datetime_absolute_eq / create_calendar_event

{
  "check_id": "riley_166_03",
  "type": "datetime_absolute_eq",
  "tool": "create_calendar_event",
  "action_id": "create_private_reminder",
  "path": "args.end",
  "value": "2028-04-07T09:10:00-05:00"
}

5. field_absent_or_empty / create_calendar_event

{
  "check_id": "riley_166_04",
  "type": "field_absent_or_empty",
  "tool": "create_calendar_event",
  "action_id": "create_private_reminder",
  "path": "args.attendees"
}

6. field_equals / list_calendar_events

{
  "type": "field_equals",
  "tool": "list_calendar_events",
  "action_id": "check_anniversary_date",
  "path": "args.timezone",
  "value": "America/Chicago",
  "check_id": "riley_166_05"
}

7. field_llm_judge / create_calendar_event

{
  "type": "field_llm_judge",
  "tool": "create_calendar_event",
  "action_id": "create_private_reminder",
  "path": "args",
  "criterion": "The title or body must clearly frame this as a personal reminder of the anniversary of Sam's expanded role. It must not present it as a restaurant event, reservation, gathering, or planned celebration, and it must not add celebration logistics.",
  "check_id": "riley_166_06"
}

Complete grading specification

{
  "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_private_reminder",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_166_00"
      },
      {
        "check_id": "riley_166_01",
        "type": "field_equals",
        "tool": "list_calendar_events",
        "action_id": "check_anniversary_date",
        "path": "args.date",
        "value": "2028-04-07"
      },
      {
        "check_id": "riley_166_02",
        "type": "datetime_absolute_eq",
        "tool": "create_calendar_event",
        "action_id": "create_private_reminder",
        "path": "args.start",
        "value": "2028-04-07T09:00:00-05:00"
      },
      {
        "check_id": "riley_166_03",
        "type": "datetime_absolute_eq",
        "tool": "create_calendar_event",
        "action_id": "create_private_reminder",
        "path": "args.end",
        "value": "2028-04-07T09:10:00-05:00"
      },
      {
        "check_id": "riley_166_04",
        "type": "field_absent_or_empty",
        "tool": "create_calendar_event",
        "action_id": "create_private_reminder",
        "path": "args.attendees"
      },
      {
        "type": "field_equals",
        "tool": "list_calendar_events",
        "action_id": "check_anniversary_date",
        "path": "args.timezone",
        "value": "America/Chicago",
        "check_id": "riley_166_05"
      },
      {
        "type": "field_llm_judge",
        "tool": "create_calendar_event",
        "action_id": "create_private_reminder",
        "path": "args",
        "criterion": "The title or body must clearly frame this as a personal reminder of the anniversary of Sam's expanded role. It must not present it as a restaurant event, reservation, gathering, or planned celebration, and it must not add celebration logistics.",
        "check_id": "riley_166_06"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/riley/166.yaml

SHA-256: fe55bd1207a3077883120ad992d1580711c3f6996efb30f7187272bdb8c22c19