{
  "context": "The agent must produce a handoff for a partial test suite build. This scenario tests whether the agent clearly states the overall objective and what has been completed — and whether these sections are distinct, factual, and appropriately brief.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Objective section present",
      "description": "The document has a section explicitly labelled 'Objective' (or equivalent heading).",
      "max_score": 8
    },
    {
      "name": "Objective states the goal",
      "description": "The Objective section states the overarching goal (e.g. achieving a specific coverage target across the three payment flows), not just 'write more tests'.",
      "max_score": 10
    },
    {
      "name": "Completed section present",
      "description": "The document has a section explicitly labelled 'Completed' (or equivalent heading).",
      "max_score": 8
    },
    {
      "name": "Completed reflects actual done work",
      "description": "The Completed section lists only work that is genuinely done (checkout tests, refund tests, CI integration) and does not include in-progress or future items.",
      "max_score": 10
    },
    {
      "name": "Assumptions section present",
      "description": "The document has an Assumptions section with at least one stated assumption.",
      "max_score": 7
    },
    {
      "name": "Assumptions section covers mock requirement",
      "description": "The Assumptions section or another appropriate section explicitly notes that BillingProvider must be mocked in tests.",
      "max_score": 12
    },
    {
      "name": "Unresolved section present",
      "description": "The document has an Unresolved section listing open items or gaps.",
      "max_score": 7
    },
    {
      "name": "Next Action section present",
      "description": "The document has a Next Action section.",
      "max_score": 7
    },
    {
      "name": "Next action is concrete",
      "description": "The Next Action identifies a specific starting point (a file, flow, or test to write first) rather than saying 'continue testing'.",
      "max_score": 10
    },
    {
      "name": "Critical References section present",
      "description": "The document has a Critical References section with at least one entry.",
      "max_score": 7
    },
    {
      "name": "All six sections present",
      "description": "The document contains all six prescribed sections: Objective, Completed, Assumptions, Unresolved, Next Action, Critical References.",
      "max_score": 7
    },
    {
      "name": "No implementation explanation",
      "description": "The Completed section does NOT explain how the tests work; it states what was done (bullet points at most), keeping detail to the minimum needed for continuity.",
      "max_score": 7
    }
  ]
}