id: '154'
narrative_anchor_date: '2028-01-01'
test: Create a standalone historical evidence card for the annual controls package covering the incomplete-setup
  reminder’s initial limited-production interval before expansion. Reconcile the total fresh evaluations
  across all four dispositions, including the reason for each non-display disposition, and record cross-surface
  agreement plus the customer-correction, incident, source-age, and rollback outcomes. Title it “Incomplete-setup
  reminder — initial production interval evidence card” and save it in the “Annual Controls” folder.
load_bearing_facts:
- 285
- 289
- 290
expected_tool_calls:
- create_doc
grade:
  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_evidence_card
      path: result.ok
      value: true
      check_id: riley_154_00
    - check_id: riley_154_01
      type: field_equals
      tool: create_doc
      action_id: create_evidence_card
      path: args.title
      value: Incomplete-setup reminder — initial production interval evidence card
    - check_id: riley_154_02
      type: field_equals
      tool: create_doc
      action_id: create_evidence_card
      path: args.folder
      value: Annual Controls
    - type: field_llm_judge
      tool: create_doc
      action_id: create_evidence_card
      path: args
      criterion: 'The body must identify the historical interval as October 6–18 at the unchanged 10%
        release and state that 3,240 fresh evaluations reconcile exactly across four distinct dispositions:
        412 displayed; 138 suppressed because current Customer Success work was active; 61 held because
        required state was missing, stale, unresolved, or conflicting; and 2,629 produced no display because
        the current incomplete-setup or qualifying-human-admin condition was not met. The four counts
        must be presented as a complete reconciliation of the 3,240 evaluations, not conflated with one
        another.


        The body must state that reporting, lifecycle, and reminder outcomes agreed for every evaluation
        and that the interval had no customer correction, no incident stop, no source-age breach, and
        no rollback. Wording that also says there was no need for rollback is acceptable.'
      check_id: riley_154_03
mock_state: {}