{
  "context": "Tests whether the agent selects the small low-risk tier for a tiny documentation-only change, uses separate general and comments reviewers without irrelevant persona fanout, produces a valid verdict, and does not inflate documentation corrections into defects.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Small tier selected",
      "description": "The report treats this two-file documentation-only change as the small low-risk tier rather than a normal or high-risk review",
      "max_score": 14
    },
    {
      "name": "General persona used",
      "description": "The report includes the general reviewer persona (or equivalent broad code review lens)",
      "max_score": 10
    },
    {
      "name": "Comments persona used",
      "description": "The report includes the comments reviewer persona (or equivalent documentation/docstring lens) — appropriate given docstring change",
      "max_score": 10
    },
    {
      "name": "Irrelevant personas omitted",
      "description": "The report does not spawn tests, silent-failures, code-shape, types, or cleanup reviewers for this documentation-only change",
      "max_score": 12
    },
    {
      "name": "Verdict present",
      "description": "The report contains exactly one verdict label: 'ship it', 'needs review', or 'blocked'",
      "max_score": 10
    },
    {
      "name": "Separate reviewers evidenced",
      "description": "The report shows that general and comments were separate reviewer subagents rather than one blended persona pass",
      "max_score": 8
    },
    {
      "name": "No nit inflation",
      "description": "The report does NOT flag the parameter rename (amount → value) as a defect or high-severity finding — the JSDoc now correctly matches the actual parameter name",
      "max_score": 10
    },
    {
      "name": "Docstring accuracy noted",
      "description": "The report identifies that the @param name was corrected from 'amount' to 'value' to match the actual function signature — and treats this as an accuracy improvement, not a bug",
      "max_score": 8
    },
    {
      "name": "Unverified areas or residual risk",
      "description": "The report mentions any residual risk or unverified surfaces, OR explicitly states there are none (either outcome is acceptable — silence is not)",
      "max_score": 6
    },
    {
      "name": "Recommended follow-up",
      "description": "The report includes a recommended follow-up action such as implementation, runtime verification, readiness setup, documentation cleanup, or none",
      "max_score": 4
    },
    {
      "name": "Compact verdict block",
      "description": "The report stays concise: findings, if any, are not repeated in the verdict footer, and the final metadata uses no more than 4 labeled lines with no scope/persona noise unless needed",
      "max_score": 8
    }
  ]
}