Test 169

Jan 1, 2028 / 1 fact

Request

Please send a concise Slack DM to the person who owned the nudge copy for EXP-2023-05-expansion-nudge when it was live. Ask them to verify the archived nudge-copy package and note any provenance correction in `doc_expansion_nudge_copy_archive_2028`.

Required memory

Fact 387

Ines owns the nudge copy for EXP-2023-05-expansion-nudge.

Source evidence (1)

000259May 23, 2023 / 10:00 UTC-05:00

launched it. PostHog flag is `expansion_nudge_60d_v1`, sitting at 25% right now on retained mid-seg only -- the 75-200 seat v2 band, not touching anything else. I own the run, Owen's doing the weekly cuts, Ines has the nudge copy. feels about right to start there vs 50% and spend a week arguing with ourselves about noise. status finally moved from designed to running.

Message 000259 in history

Expected tool calls

send_slack_dm

Grading

1. field_equals / send_slack_dm

{
  "type": "field_equals",
  "tool": "send_slack_dm",
  "action_id": "send_archive_provenance_dm",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_169_00"
}

2. field_equals / send_slack_dm

{
  "type": "field_equals",
  "tool": "send_slack_dm",
  "action_id": "send_archive_provenance_dm",
  "path": "args.user",
  "value": "ines",
  "check_id": "riley_169_01"
}

3. field_llm_judge / send_slack_dm

{
  "type": "field_llm_judge",
  "tool": "send_slack_dm",
  "action_id": "send_archive_provenance_dm",
  "path": "args",
  "criterion": "The message asks the recipient to verify the archived nudge-copy package for EXP-2023-05-expansion-nudge and to note any provenance correction in `doc_expansion_nudge_copy_archive_2028`. Equivalent concise wording is acceptable; either missing instruction must fail.",
  "check_id": "riley_169_02"
}

Complete grading specification

{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2028-01-01",
    "semantic_judge_version": 2,
    "assertions": [
      {
        "type": "field_equals",
        "tool": "send_slack_dm",
        "action_id": "send_archive_provenance_dm",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_169_00"
      },
      {
        "type": "field_equals",
        "tool": "send_slack_dm",
        "action_id": "send_archive_provenance_dm",
        "path": "args.user",
        "value": "ines",
        "check_id": "riley_169_01"
      },
      {
        "type": "field_llm_judge",
        "tool": "send_slack_dm",
        "action_id": "send_archive_provenance_dm",
        "path": "args",
        "criterion": "The message asks the recipient to verify the archived nudge-copy package for EXP-2023-05-expansion-nudge and to note any provenance correction in `doc_expansion_nudge_copy_archive_2028`. Equivalent concise wording is acceptable; either missing instruction must fail.",
        "check_id": "riley_169_02"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/riley/169.yaml

SHA-256: b250c237ed9261c269e062c9f06ffed0dadfeae727e8fc47b3f2fd5077e97db4