id: '160'
narrative_anchor_date: '2028-01-01'
test: Create an audit-ready evidence card for the historical CS auto-nudge production shadow. Include
  the interval, reconciled outcomes and causes, suppressions, reviewer validations, release boundary,
  and a plain explanation of external-system authority. Distinguish shadow evaluation from a production
  switch.
load_bearing_facts:
- 102
- 103
- 104
- 105
- 114
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_shadow_evidence_card
      path: result.ok
      value: true
      check_id: riley_160_00
    - type: field_llm_judge
      tool: create_doc
      action_id: create_shadow_evidence_card
      path: args
      criterion: 'The title clearly identifies the document as an evidence card or audit record for the
        CS auto-nudge production shadow. A generic controls document or blank-template title fails.


        The body states that the production shadow ran from April 25 through May 2, 2025, that both paths
        evaluated live decisions, and that the shadow did not change the released audience. It must present
        this as a pre-release shadow gate rather than claiming the integration switched production during
        the shadow; missing or contradictory boundaries fail.


        The body reconciles the complete shadow population: 204 live decisions total, 191 agreements,
        and 13 decisions prevented from proceeding under the legacy eligibility result, with those 13
        further reconciling to nine field-specific holds plus four suppressions. Missing, inconsistent,
        or contradictory totals fail.


        The body breaks down the nine field-specific holds into exactly seven caused by stale qualifying-human-admin
        state and two caused by unresolved external-system authority for the connector''s required owner-level
        permission or network-allowlist action. Missing causes, wrong counts, or a materially different
        meaning of external-system authority fail.


        The body states that exactly four decisions were suppressed because current Customer Success adoption
        or renewal work was active. Missing, contradictory, or differently attributed suppressions fail.


        The body records that Daniela verified the field-specific hold and suppression reasons and production
        rollback behavior, and that Ines confirmed no held or suppressed case received adjacent lifecycle
        messaging that assumed eligibility. Both reviewer findings must be present and correctly attributed;
        missing or contradicted findings fail.


        The body states that every observed difference followed an established shared-contract rule and
        that there were no unmatched or unclassified cases. Missing or contradictory coverage findings
        fail.'
      check_id: riley_160_01
mock_state: {}