Test 156

Jan 1, 2028 / 1 fact

Request

Please check my calendar for Saturday, January 8, 2028, and, if 11:00 a.m.–12:30 p.m. Central is open, add brunch to my calendar.

Required memory

Fact 315

When Riley Tanaka says “brunch” without specifying a place, she almost always means Salud.

Source evidence (1)

000027Feb 11, 2023 / 11:00 UTC-06:00

Sam's at the restaurant so I did Salud again. the usual solo-Saturday move... 6 min walk, grab breakfast tacos, back before the line gets stupid. if I say brunch and don't specify it's basically always Salud.

Message 000027 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_brunch",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_156_00"
}

2. field_equals / list_calendar_events

{
  "check_id": "riley_156_01",
  "type": "field_equals",
  "tool": "list_calendar_events",
  "action_id": "check_jan8_conflicts",
  "path": "args.date",
  "value": "2028-01-08"
}

3. datetime_absolute_eq / create_calendar_event

{
  "check_id": "riley_156_02",
  "type": "datetime_absolute_eq",
  "tool": "create_calendar_event",
  "action_id": "create_brunch",
  "path": "args.start",
  "value": "2028-01-08T11:00:00-06:00"
}

4. datetime_absolute_eq / create_calendar_event

{
  "check_id": "riley_156_03",
  "type": "datetime_absolute_eq",
  "tool": "create_calendar_event",
  "action_id": "create_brunch",
  "path": "args.end",
  "value": "2028-01-08T12:30:00-06:00"
}

5. field_equals / list_calendar_events

{
  "type": "field_equals",
  "tool": "list_calendar_events",
  "action_id": "check_jan8_conflicts",
  "path": "args.timezone",
  "value": "America/Chicago",
  "check_id": "riley_156_04"
}

6. field_llm_judge / create_calendar_event

{
  "type": "field_llm_judge",
  "tool": "create_calendar_event",
  "action_id": "create_brunch",
  "path": "args",
  "criterion": "Across the event title and body, with either content field acceptable, the event must clearly be a brunch at Salud. Missing the venue, naming a different venue, or expressing uncertainty about the venue must fail.",
  "check_id": "riley_156_05"
}

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_brunch",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_156_00"
      },
      {
        "check_id": "riley_156_01",
        "type": "field_equals",
        "tool": "list_calendar_events",
        "action_id": "check_jan8_conflicts",
        "path": "args.date",
        "value": "2028-01-08"
      },
      {
        "check_id": "riley_156_02",
        "type": "datetime_absolute_eq",
        "tool": "create_calendar_event",
        "action_id": "create_brunch",
        "path": "args.start",
        "value": "2028-01-08T11:00:00-06:00"
      },
      {
        "check_id": "riley_156_03",
        "type": "datetime_absolute_eq",
        "tool": "create_calendar_event",
        "action_id": "create_brunch",
        "path": "args.end",
        "value": "2028-01-08T12:30:00-06:00"
      },
      {
        "type": "field_equals",
        "tool": "list_calendar_events",
        "action_id": "check_jan8_conflicts",
        "path": "args.timezone",
        "value": "America/Chicago",
        "check_id": "riley_156_04"
      },
      {
        "type": "field_llm_judge",
        "tool": "create_calendar_event",
        "action_id": "create_brunch",
        "path": "args",
        "criterion": "Across the event title and body, with either content field acceptable, the event must clearly be a brunch at Salud. Missing the venue, naming a different venue, or expressing uncertainty about the venue must fail.",
        "check_id": "riley_156_05"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/riley/156.yaml

SHA-256: 92835ea28c350c717389e67a03232b7eb8c05f0025606deeb040f65e9449041e