Test 122

Jan 1, 2028 / 1 fact

Request

The current renewal-prioritization sizing question has been reopened. Please send Owen a concise request for the previously approved sizing deliverable, and create a short cover note for Customer Success that explains the allowed scope and how the output may be used.

Required memory

Fact 201

Owen gave Customer Success a one-time aggregate sizing cut for the immediate renewal question instead of an account-level feed.

Source evidence (1)

003604Jun 9, 2026 / 16:15 UTC-05:00

Daniela and I completed the renewal-prioritization review and declined the proposed direct connection, so Lifecycle Systems remains at four production consumers. For any future shared-state consumer, the requester must name the customer action; every governed field used with its unchanged meaning; each source owner and freshness limit; fail-closed and suppression behavior; customer-correction and incident-stop ownership; and engineering rollback ownership before replay work begins. A candidate can move from replay to shadow only if no semantic disagreement appears. Production requires my approval of the customer-action scope and Daniela’s approval of release and rollback controls. For the immediate renewal question, Owen gave Customer Success a one-time aggregate sizing cut rather than an account-level feed. Update `Shared-state consumer admission review — renewal prioritization` with the final decline, the replay-to-shadow-to-production admission gate, the bounded aggregate alternative, and the final four-production-consumer boundary.

Message 003604 in history

Expected tool calls

send_slack_dm
create_doc

Grading

1. field_equals / send_slack_dm

{
  "type": "field_equals",
  "tool": "send_slack_dm",
  "action_id": "request_owen_sizing",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_122_00"
}

2. field_equals / create_doc

{
  "type": "field_equals",
  "tool": "create_doc",
  "action_id": "create_cs_cover_note",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_122_01"
}

3. field_equals / send_slack_dm

{
  "type": "field_equals",
  "tool": "send_slack_dm",
  "action_id": "request_owen_sizing",
  "path": "args.user",
  "value": "owen",
  "check_id": "riley_122_02"
}

4. field_llm_judge / send_slack_dm

{
  "type": "field_llm_judge",
  "tool": "send_slack_dm",
  "action_id": "request_owen_sizing",
  "path": "args",
  "criterion": "The message asks Owen for a one-time aggregate sizing cut for the reopened current renewal-prioritization question. It must not ask for account-level records, a reusable account list or feed, or recurring delivery. Missing or contradictory scope must fail.",
  "check_id": "riley_122_03"
}

5. field_llm_judge / create_doc

{
  "type": "field_llm_judge",
  "tool": "create_doc",
  "action_id": "create_cs_cover_note",
  "path": "args",
  "criterion": "The document is clearly a cover note for Customer Success and explains that the deliverable is a one-time aggregate sizing cut for the current renewal-prioritization question. Stating that it is one-time is sufficient to communicate the nonrecurring limit unless the note contradictorily permits or requests recurring delivery. The note must explicitly prevent use or repurposing as an account-level list or feed and must not permit a reusable audience or recurring delivery. Missing or contradictory limits must fail.",
  "check_id": "riley_122_04"
}

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": "request_owen_sizing",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_122_00"
      },
      {
        "type": "field_equals",
        "tool": "create_doc",
        "action_id": "create_cs_cover_note",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_122_01"
      },
      {
        "type": "field_equals",
        "tool": "send_slack_dm",
        "action_id": "request_owen_sizing",
        "path": "args.user",
        "value": "owen",
        "check_id": "riley_122_02"
      },
      {
        "type": "field_llm_judge",
        "tool": "send_slack_dm",
        "action_id": "request_owen_sizing",
        "path": "args",
        "criterion": "The message asks Owen for a one-time aggregate sizing cut for the reopened current renewal-prioritization question. It must not ask for account-level records, a reusable account list or feed, or recurring delivery. Missing or contradictory scope must fail.",
        "check_id": "riley_122_03"
      },
      {
        "type": "field_llm_judge",
        "tool": "create_doc",
        "action_id": "create_cs_cover_note",
        "path": "args",
        "criterion": "The document is clearly a cover note for Customer Success and explains that the deliverable is a one-time aggregate sizing cut for the current renewal-prioritization question. Stating that it is one-time is sufficient to communicate the nonrecurring limit unless the note contradictorily permits or requests recurring delivery. The note must explicitly prevent use or repurposing as an account-level list or feed and must not permit a reusable audience or recurring delivery. Missing or contradictory limits must fail.",
        "check_id": "riley_122_04"
      }
    ]
  }
}

App state

Download JSON

Source file

tests/riley/122.yaml

SHA-256: 4a77d81a15edbe8607a7bdc0ebe63b757c78626818c59ada2fb4ec4e5d2bba87