Test 179

Jan 1, 2028 / 2 facts

Request

Review the production-method proposal in `doc_private_dinner_roasted_chicken_2028_01_29` and post a concise correction using the approved historical method. Limit the comment to production method; do not change the menu or invent a new sequence.

Required memory

Fact 36

The chef-owner reviewed the completed June 28 roasted-chicken sale-run economics and approved controlled repeat trials for July 26 and August 16; each trial must use the same 30-pound case and tested pre-staging sequence, require no more than 60 incremental labor minutes, yield at least 44 complete portions, and record plates prepared, plates sold, and the disposition of unsold portions.

Source evidence (1)

001670Jul 3, 2024 / 09:15 UTC-05:00

The chef-owner reviewed the completed June 28 sale-run economics and approved two controlled repeats, July 26 and August 16. Each must use the same 30-pound case and tested pre-staging sequence, stay within 60 incremental labor minutes, produce at least 44 complete portions, and record plates prepared, plates sold, and unsold disposition. This is not permanent menu placement. Carry the June 28 baseline into a comparative roasted-chicken repeat-trial document. The baseline was a 30-pound case yielding 19 pounds 12 ounces cooked, or 316 ounces: 45 complete seven-ounce portions with one ounce left over; 57 minutes of incremental labor; 45 plates prepared; 43 sold at $18 each; two portions chilled for staff meal under the restaurant's food-handling procedure; $146 food cost; $24-per-hour incremental labor valuation; no deviation from the tested pre-staging and tray sequence; $774 revenue; $22.80 labor cost; and $605.20 contribution after food and incremental labor. Include the fixed production thresholds, sales and disposition fields, economics fields, and separate sections for the July 26 and August 16 runs. Do not describe the dish as a standing special.

Message 001670 in history

Fact 48

The chef-owner approved the roasted chicken as an advance-count option for private dinners, allowing Sam to size batches to known guest counts while using the tested pre-staging sequence.

Source evidence (1)

001856Aug 19, 2024 / 17:40 UTC-05:00

The chef-owner reviewed the June 28, July 26, and August 16 roasted-chicken records. All three runs stayed within the labor and yield thresholds, but sell-through varied enough that the dish will not become a standing weekly special. It is approved instead as an advance-count option for private dinners, so Sam can size the batch to a known guest count and keep using the tested pre-staging sequence. This does not change Sam's head-chef role. Sharing the settled decision; the question left after the final controlled sale run is closed.

Message 001856 in history

Expected tool calls

post_doc_comment

Grading

1. field_equals / post_doc_comment

{
  "type": "field_equals",
  "tool": "post_doc_comment",
  "action_id": "production_method_comment",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_179_00"
}

2. field_equals / post_doc_comment

{
  "check_id": "riley_179_01",
  "type": "field_equals",
  "tool": "post_doc_comment",
  "action_id": "production_method_comment",
  "path": "args.doc_id",
  "value": "doc_private_dinner_roasted_chicken_2028_01_29"
}

3. field_llm_judge / post_doc_comment

{
  "type": "field_llm_judge",
  "tool": "post_doc_comment",
  "action_id": "production_method_comment",
  "path": "args",
  "criterion": "The comment must concisely reject or correct the proposed rolling/reordered preparation approach and direct production back to the established tested pre-staging sequence for the roasted chicken. It must not invent a replacement sequence or propose changing the approved menu choice. Missing, accepting, or contradicting the tested pre-staging requirement must fail.",
  "check_id": "riley_179_02"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2028-01-01",
    "semantic_judge_version": 2,
    "assertions": [
      {
        "type": "field_equals",
        "tool": "post_doc_comment",
        "action_id": "production_method_comment",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_179_00"
      },
      {
        "check_id": "riley_179_01",
        "type": "field_equals",
        "tool": "post_doc_comment",
        "action_id": "production_method_comment",
        "path": "args.doc_id",
        "value": "doc_private_dinner_roasted_chicken_2028_01_29"
      },
      {
        "type": "field_llm_judge",
        "tool": "post_doc_comment",
        "action_id": "production_method_comment",
        "path": "args",
        "criterion": "The comment must concisely reject or correct the proposed rolling/reordered preparation approach and direct production back to the established tested pre-staging sequence for the roasted chicken. It must not invent a replacement sequence or propose changing the approved menu choice. Missing, accepting, or contradicting the tested pre-staging requirement must fail.",
        "check_id": "riley_179_02"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/riley/179.yaml

SHA-256: 7b4fbe29e01253c3450ab3507c8351200a4c06b7a82a60e8dba6ec3d3605ee12