{
  "generatedBy": "pnpm run report:ai-efficiency",
  "evidence": "local candidate experiment",
  "schemaVersion": 1,
  "createdAt": "2026-10-04T16:11:07.218Z",
  "model": "gpt-6-astra",
  "effort": "xhigh",
  "cli": "codex-cli 0.159.0-alpha.12.1",
  "revision": "972348dec4333b8b597c6cee57c96a4896c22171",
  "revisionRole": "checkout-base",
  "hashes": {
    "harness": "4161cb166c80f20dd1ded9b9b0810f19f3330ed03e610219612b1681d029b5b8",
    "verifier": "1b783743e1631274980a9c15f70062fcaa5fd13a0fb1d1d2115ed6d848508370",
    "metrics": "28a71efddf8e835b53614d645fd37cf087631175494d9a4b75087ae6464919fe",
    "stylesheet": "a53239226d49f29a2a7809ddf92ffe904210b3c491bfd99cad2843899a82924e",
    "react": "8edc0fde33cd424d93434d217e59ea2cf8682434a9789a2da7c8ad8e6e911e54",
    "catalog": "80966dbee5888713b9c2d9ca47f81b7e7eaf65b34604f515ae8a5a1666afcb7f",
    "skill": "240d1cb15f0df9c24ff069879749409edddcc803e92c4520c174ee4345592d9f"
  },
  "repetitions": 3,
  "maxAttempts": 2,
  "scenarios": [
    {
      "id": "profile-dialog",
      "prompt": "Build a profile settings screen with the main h1 Profile. The Edit profile button opens a modal dialog named Profile settings. Its Display name text field initially contains Ada and receives focus on opening. Editing the field persists across closing and reopening. Escape and the Cancel button both close the dialog and return focus to Edit profile. Trap keyboard focus while the modal is open."
    },
    {
      "id": "notification-settings",
      "prompt": "Build a settings screen with the main h1 Notification settings. The Email address field initially contains ada@example.com. Show delivery details toggles the initially hidden text Weekly summaries arrive on Monday. without clearing edited input. Save preferences displays a status region containing Preferences saved for <email>. using the current field value. This is an in-memory demo, with no network or persistence across page reloads."
    }
  ],
  "runs": [
    {
      "case": "profile-dialog",
      "mode": "scratch",
      "repetition": 1,
      "status": "passed",
      "durationMs": 154374,
      "usage": {
        "inputTokens": 111968,
        "cachedInputTokens": 91136,
        "outputTokens": 4553,
        "totalTokens": 116521,
        "toolCalls": 4
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 111968,
            "cachedInputTokens": 91136,
            "outputTokens": 4553,
            "totalTokens": 116521,
            "toolCalls": 4
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "docs",
      "repetition": 1,
      "status": "passed",
      "durationMs": 226540,
      "usage": {
        "inputTokens": 483746,
        "cachedInputTokens": 405760,
        "outputTokens": 5936,
        "totalTokens": 489682,
        "toolCalls": 22
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 260926,
            "cachedInputTokens": 212480,
            "outputTokens": 4408,
            "totalTokens": 265334,
            "toolCalls": 10
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 222820,
            "cachedInputTokens": 193280,
            "outputTokens": 1528,
            "totalTokens": 224348,
            "toolCalls": 12
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "skill-mcp",
      "repetition": 1,
      "status": "passed",
      "durationMs": 267841,
      "usage": {
        "inputTokens": 685261,
        "cachedInputTokens": 603392,
        "outputTokens": 6890,
        "totalTokens": 692151,
        "toolCalls": 45
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 279403,
            "cachedInputTokens": 238464,
            "outputTokens": 3923,
            "totalTokens": 283326,
            "toolCalls": 26
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 405858,
            "cachedInputTokens": 364928,
            "outputTokens": 2967,
            "totalTokens": 408825,
            "toolCalls": 19
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "docs",
      "repetition": 1,
      "status": "passed",
      "durationMs": 154903,
      "usage": {
        "inputTokens": 248642,
        "cachedInputTokens": 196096,
        "outputTokens": 5377,
        "totalTokens": 254019,
        "toolCalls": 10
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 248642,
            "cachedInputTokens": 196096,
            "outputTokens": 5377,
            "totalTokens": 254019,
            "toolCalls": 10
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "skill-mcp",
      "repetition": 1,
      "status": "passed",
      "durationMs": 333092,
      "usage": {
        "inputTokens": 580768,
        "cachedInputTokens": 494848,
        "outputTokens": 6129,
        "totalTokens": 586897,
        "toolCalls": 50
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 354615,
            "cachedInputTokens": 307200,
            "outputTokens": 3894,
            "totalTokens": 358509,
            "toolCalls": 25
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 226153,
            "cachedInputTokens": 187648,
            "outputTokens": 2235,
            "totalTokens": 228388,
            "toolCalls": 25
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "scratch",
      "repetition": 1,
      "status": "passed",
      "durationMs": 172933,
      "usage": {
        "inputTokens": 117744,
        "cachedInputTokens": 101504,
        "outputTokens": 3996,
        "totalTokens": 121740,
        "toolCalls": 7
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 117744,
            "cachedInputTokens": 101504,
            "outputTokens": 3996,
            "totalTokens": 121740,
            "toolCalls": 7
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "docs",
      "repetition": 2,
      "status": "passed",
      "durationMs": 343393,
      "usage": {
        "inputTokens": 596744,
        "cachedInputTokens": 521216,
        "outputTokens": 6851,
        "totalTokens": 603595,
        "toolCalls": 19
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 346335,
            "cachedInputTokens": 305280,
            "outputTokens": 5192,
            "totalTokens": 351527,
            "toolCalls": 10
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 250409,
            "cachedInputTokens": 215936,
            "outputTokens": 1659,
            "totalTokens": 252068,
            "toolCalls": 9
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "skill-mcp",
      "repetition": 2,
      "status": "passed",
      "durationMs": 346644,
      "usage": {
        "inputTokens": 1037195,
        "cachedInputTokens": 934400,
        "outputTokens": 7087,
        "totalTokens": 1044282,
        "toolCalls": 50
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 278418,
            "cachedInputTokens": 237696,
            "outputTokens": 3986,
            "totalTokens": 282404,
            "toolCalls": 25
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 758777,
            "cachedInputTokens": 696704,
            "outputTokens": 3101,
            "totalTokens": 761878,
            "toolCalls": 25
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "scratch",
      "repetition": 2,
      "status": "passed",
      "durationMs": 171737,
      "usage": {
        "inputTokens": 104503,
        "cachedInputTokens": 86784,
        "outputTokens": 4697,
        "totalTokens": 109200,
        "toolCalls": 3
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 104503,
            "cachedInputTokens": 86784,
            "outputTokens": 4697,
            "totalTokens": 109200,
            "toolCalls": 3
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "skill-mcp",
      "repetition": 2,
      "status": "passed",
      "durationMs": 272008,
      "usage": {
        "inputTokens": 457468,
        "cachedInputTokens": 346624,
        "outputTokens": 5889,
        "totalTokens": 463357,
        "toolCalls": 43
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 192810,
            "cachedInputTokens": 154880,
            "outputTokens": 3712,
            "totalTokens": 196522,
            "toolCalls": 20
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 264658,
            "cachedInputTokens": 191744,
            "outputTokens": 2177,
            "totalTokens": 266835,
            "toolCalls": 23
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "scratch",
      "repetition": 2,
      "status": "passed",
      "durationMs": 199842,
      "usage": {
        "inputTokens": 208620,
        "cachedInputTokens": 164224,
        "outputTokens": 4126,
        "totalTokens": 212746,
        "toolCalls": 10
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 89224,
            "cachedInputTokens": 67200,
            "outputTokens": 3461,
            "totalTokens": 92685,
            "toolCalls": 3
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 119396,
            "cachedInputTokens": 97024,
            "outputTokens": 665,
            "totalTokens": 120061,
            "toolCalls": 7
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "docs",
      "repetition": 2,
      "status": "passed",
      "durationMs": 188440,
      "usage": {
        "inputTokens": 296547,
        "cachedInputTokens": 256896,
        "outputTokens": 5189,
        "totalTokens": 301736,
        "toolCalls": 11
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 296547,
            "cachedInputTokens": 256896,
            "outputTokens": 5189,
            "totalTokens": 301736,
            "toolCalls": 11
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "skill-mcp",
      "repetition": 3,
      "status": "passed",
      "durationMs": 327824,
      "usage": {
        "inputTokens": 566982,
        "cachedInputTokens": 494208,
        "outputTokens": 7015,
        "totalTokens": 573997,
        "toolCalls": 36
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 275386,
            "cachedInputTokens": 235776,
            "outputTokens": 4054,
            "totalTokens": 279440,
            "toolCalls": 22
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 291596,
            "cachedInputTokens": 258432,
            "outputTokens": 2961,
            "totalTokens": 294557,
            "toolCalls": 14
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "scratch",
      "repetition": 3,
      "status": "passed",
      "durationMs": 176757,
      "usage": {
        "inputTokens": 119694,
        "cachedInputTokens": 102144,
        "outputTokens": 4934,
        "totalTokens": 124628,
        "toolCalls": 4
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 119694,
            "cachedInputTokens": 102144,
            "outputTokens": 4934,
            "totalTokens": 124628,
            "toolCalls": 4
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "profile-dialog",
      "mode": "docs",
      "repetition": 3,
      "status": "passed",
      "durationMs": 243693,
      "usage": {
        "inputTokens": 508260,
        "cachedInputTokens": 433536,
        "outputTokens": 6405,
        "totalTokens": 514665,
        "toolCalls": 19
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 314262,
            "cachedInputTokens": 268544,
            "outputTokens": 4674,
            "totalTokens": 318936,
            "toolCalls": 12
          },
          "status": "failed"
        },
        {
          "attempt": 2,
          "usage": {
            "inputTokens": 193998,
            "cachedInputTokens": 164992,
            "outputTokens": 1731,
            "totalTokens": 195729,
            "toolCalls": 7
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "scratch",
      "repetition": 3,
      "status": "passed",
      "durationMs": 128958,
      "usage": {
        "inputTokens": 103485,
        "cachedInputTokens": 86528,
        "outputTokens": 3825,
        "totalTokens": 107310,
        "toolCalls": 3
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 103485,
            "cachedInputTokens": 86528,
            "outputTokens": 3825,
            "totalTokens": 107310,
            "toolCalls": 3
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "docs",
      "repetition": 3,
      "status": "passed",
      "durationMs": 150058,
      "usage": {
        "inputTokens": 233783,
        "cachedInputTokens": 197504,
        "outputTokens": 4356,
        "totalTokens": 238139,
        "toolCalls": 10
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 233783,
            "cachedInputTokens": 197504,
            "outputTokens": 4356,
            "totalTokens": 238139,
            "toolCalls": 10
          },
          "status": "passed"
        }
      ]
    },
    {
      "case": "notification-settings",
      "mode": "skill-mcp",
      "repetition": 3,
      "status": "passed",
      "durationMs": 136321,
      "usage": {
        "inputTokens": 221866,
        "cachedInputTokens": 176640,
        "outputTokens": 3792,
        "totalTokens": 225658,
        "toolCalls": 18
      },
      "attempts": [
        {
          "attempt": 1,
          "usage": {
            "inputTokens": 221866,
            "cachedInputTokens": 176640,
            "outputTokens": 3792,
            "totalTokens": 225658,
            "toolCalls": 18
          },
          "status": "passed"
        }
      ]
    }
  ],
  "summary": [
    {
      "case": "profile-dialog",
      "mode": "scratch",
      "runs": 3,
      "passed": 3,
      "measured": 3,
      "medianTotalTokens": 116521,
      "medianDurationMs": 171737,
      "totalTokens": 350349
    },
    {
      "case": "profile-dialog",
      "mode": "docs",
      "runs": 3,
      "passed": 3,
      "measured": 3,
      "medianTotalTokens": 514665,
      "medianDurationMs": 243693,
      "totalTokens": 1607942
    },
    {
      "case": "profile-dialog",
      "mode": "skill-mcp",
      "runs": 3,
      "passed": 3,
      "measured": 3,
      "medianTotalTokens": 692151,
      "medianDurationMs": 327824,
      "totalTokens": 2310430
    },
    {
      "case": "notification-settings",
      "mode": "docs",
      "runs": 3,
      "passed": 3,
      "measured": 3,
      "medianTotalTokens": 254019,
      "medianDurationMs": 154903,
      "totalTokens": 793894
    },
    {
      "case": "notification-settings",
      "mode": "skill-mcp",
      "runs": 3,
      "passed": 3,
      "measured": 3,
      "medianTotalTokens": 463357,
      "medianDurationMs": 272008,
      "totalTokens": 1275912
    },
    {
      "case": "notification-settings",
      "mode": "scratch",
      "runs": 3,
      "passed": 3,
      "measured": 3,
      "medianTotalTokens": 121740,
      "medianDurationMs": 172933,
      "totalTokens": 441796
    }
  ]
}
