Test 041 for Riley Tanaka

Request

Create a concise archival booking-rule card for the roasted-chicken private-event policy that applied during the 2024 holiday season. Make it unmistakable that this is expired historical reference material, not current policy. State whether it was an advance-count option, the per-booking commitment cap, protected contingency portions, final entree-split deadline, and its relationship to the weekly menu. Save it as a new document in the default folder.

Required memory

Fact 60

Sam and the chef-owner reviewed the September and October private-dinner records and documented roasted chicken as an already-approved advance-count private-event option through the holiday season.

Source evidence (1)

002079Oct 21, 2024 / 10:40 UTC-05:00

Sam and the chef-owner reviewed the September and October private-dinner records and documented roasted chicken as an already-approved advance-count private-event option through the holiday season. A one-case booking may commit no more than 23 chicken meals, must preserve two kitchen-only contingency portions, and requires the final entrée split seven days before service. The tested pre-staging sequence remains the production method. The dish stays separate from the weekly menu, and this does not change Sam's restaurant role. Sharing the completed standardization as a one-way update.

Message 002079 in history

Fact 61

The roasted-chicken private-event standard limits a one-case booking to 23 committed chicken meals, reserves two additional portions for kitchen-only contingencies, and requires the final entrée split seven days before service.

Source evidence (1)

002079Oct 21, 2024 / 10:40 UTC-05:00

Sam and the chef-owner reviewed the September and October private-dinner records and documented roasted chicken as an already-approved advance-count private-event option through the holiday season. A one-case booking may commit no more than 23 chicken meals, must preserve two kitchen-only contingency portions, and requires the final entrée split seven days before service. The tested pre-staging sequence remains the production method. The dish stays separate from the weekly menu, and this does not change Sam's restaurant role. Sharing the completed standardization as a one-way update.

Message 002079 in history

Expected tool calls

create_doc

Grading

1. field_equals / create_doc

{
  "type": "field_equals",
  "tool": "create_doc",
  "action_id": "create_historical_rule_card",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_041_00"
}

2. field_llm_judge / create_doc

{
  "type": "field_llm_judge",
  "tool": "create_doc",
  "action_id": "create_historical_rule_card",
  "path": "args",
  "criterion": "The document is unmistakably an expired historical rule for the 2024 holiday season. It says roasted chicken was an advance-count private-event option; a one-case booking could commit no more than 23 chicken meals; two portions remained protected for kitchen-only contingencies; the final entree split was due seven days before service; and the dish remained separate from the weekly menu.",
  "check_id": "riley_041_01"
}

Complete grading specification

{
  "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_historical_rule_card",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_041_00"
      },
      {
        "type": "field_llm_judge",
        "tool": "create_doc",
        "action_id": "create_historical_rule_card",
        "path": "args",
        "criterion": "The document is unmistakably an expired historical rule for the 2024 holiday season. It says roasted chicken was an advance-count private-event option; a one-case booking could commit no more than 23 chicken meals; two portions remained protected for kitchen-only contingencies; the final entree split was due seven days before service; and the dish remained separate from the weekly menu.",
        "check_id": "riley_041_01"
      }
    ]
  }
}