[
  {
    "run": "00-trial-1-agents-3",
    "agents": 3,
    "trial": 1,
    "work_started_utc": "2026-11-10T15:06:58.315728+00:00",
    "work_started_elapsed_seconds": 19.42044150014408,
    "final_validation": {
      "utc": "2026-11-10T15:16:17.968514+00:00",
      "elapsed_seconds": 579.0732284591068,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.684990874957293
    },
    "pytest_summary": "138 passed, 437 warnings in 9.97s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "01-trial-1-agents-1",
    "agents": 1,
    "trial": 1,
    "work_started_utc": "2026-11-10T15:16:33.370136+00:00",
    "work_started_elapsed_seconds": 15.378227083012462,
    "final_validation": {
      "utc": "2026-11-10T15:33:25.211814+00:00",
      "elapsed_seconds": 1027.219905457925,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.368989583104849
    },
    "pytest_summary": "134 passed, 437 warnings in 9.78s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "02-trial-1-agents-10",
    "agents": 10,
    "trial": 1,
    "work_started_utc": "2026-11-10T15:33:39.681452+00:00",
    "work_started_elapsed_seconds": 14.440482042031363,
    "final_validation": {
      "utc": "2026-11-10T15:41:20.561301+00:00",
      "elapsed_seconds": 475.32031429209746,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.093634832883254
    },
    "pytest_summary": "136 passed, 437 warnings in 9.51s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "03-trial-1-agents-5",
    "agents": 5,
    "trial": 1,
    "work_started_utc": "2026-11-10T15:45:53.057190+00:00",
    "work_started_elapsed_seconds": 21.56894062482752,
    "final_validation": {
      "utc": "2026-11-10T15:55:19.076604+00:00",
      "elapsed_seconds": 563.5275686669629,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.29642541706562
    },
    "pytest_summary": "137 passed, 437 warnings in 9.71s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "04-trial-2-agents-1",
    "agents": 1,
    "trial": 2,
    "work_started_utc": "2026-11-10T15:55:33.627621+00:00",
    "work_started_elapsed_seconds": 14.528902499936521,
    "final_validation": {
      "utc": "2026-11-10T16:20:41.877459+00:00",
      "elapsed_seconds": 1360.3018692499027,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.218605000060052
    },
    "pytest_summary": "134 passed, 442 warnings in 9.64s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "05-trial-2-agents-3",
    "agents": 3,
    "trial": 2,
    "work_started_utc": "2026-11-10T16:20:56.481079+00:00",
    "work_started_elapsed_seconds": 14.579217999940738,
    "final_validation": {
      "utc": "2026-11-10T16:27:39.917680+00:00",
      "elapsed_seconds": 418.0158224168699,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.2219070000574
    },
    "pytest_summary": "134 passed, 438 warnings in 9.62s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "06-trial-2-agents-5",
    "agents": 5,
    "trial": 2,
    "work_started_utc": "2026-11-10T16:27:54.647519+00:00",
    "work_started_elapsed_seconds": 14.706659000134096,
    "final_validation": {
      "utc": "2026-11-10T16:36:09.916388+00:00",
      "elapsed_seconds": 459.17015779111534,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 15.32552891690284
    },
    "pytest_summary": "139 passed, 449 warnings in 14.65s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "07-trial-2-agents-10",
    "agents": 10,
    "trial": 2,
    "work_started_utc": "2026-11-10T18:22:31.078158+00:00",
    "work_started_elapsed_seconds": 21.360975249903277,
    "final_validation": {
      "utc": "2026-11-10T18:29:27.851775+00:00",
      "elapsed_seconds": 438.1345949580427,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.658521624980494
    },
    "pytest_summary": "127 passed, 438 warnings in 9.98s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "08-trial-3-agents-10",
    "agents": 10,
    "trial": 3,
    "work_started_utc": "2026-11-10T18:29:44.915670+00:00",
    "work_started_elapsed_seconds": 16.884196958038956,
    "final_validation": {
      "utc": "2026-11-10T18:36:49.404654+00:00",
      "elapsed_seconds": 441.37318462505937,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.34870154201053
    },
    "pytest_summary": "133 passed, 438 warnings in 9.79s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "09-trial-3-agents-3",
    "agents": 3,
    "trial": 3,
    "work_started_utc": "2026-11-10T18:37:06.335680+00:00",
    "work_started_elapsed_seconds": 16.756297708954662,
    "final_validation": {
      "utc": "2026-11-10T18:47:44.133744+00:00",
      "elapsed_seconds": 654.5543673341163,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.370714916847646
    },
    "pytest_summary": "135 passed, 437 warnings in 9.69s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "10-trial-3-agents-1",
    "agents": 1,
    "trial": 3,
    "work_started_utc": "2026-11-10T18:48:00.057760+00:00",
    "work_started_elapsed_seconds": 15.725997667061165,
    "final_validation": {
      "utc": "2026-11-10T19:06:40.105037+00:00",
      "elapsed_seconds": 899.9589299999643,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.13463958306238
    },
    "pytest_summary": "134 passed, 442 warnings in 9.58s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  },
  {
    "run": "11-trial-3-agents-5",
    "agents": 5,
    "trial": 3,
    "work_started_utc": "2026-11-10T19:06:56.491744+00:00",
    "work_started_elapsed_seconds": 16.194932540878654,
    "final_validation": {
      "utc": "2026-11-10T19:13:53.799055+00:00",
      "elapsed_seconds": 433.50224520801567,
      "task_ids": [
        "task01",
        "task02",
        "task03",
        "task04",
        "task05",
        "task06",
        "task07",
        "task08",
        "task09",
        "task10"
      ],
      "returncode": 0,
      "timed_out": false,
      "seconds": 10.613177499966696
    },
    "pytest_summary": "131 passed, 437 warnings in 10.00s",
    "metadata": {
      "platform": "macOS-26.5-arm64-arm-64bit-Mach-O",
      "machine": "arm64",
      "cpu_count": 10,
      "harness_python": "3.14.5",
      "codex_version": "codex-cli 0.167.0",
      "target_python": "Python 3.14.5",
      "revision": "353c3ccdf3acdaae9acae78b5132241061b5decc",
      "evaluation_sha256": {
        "conftest.py": "9a960650d220405f2886322a473969dec5daab523bf90cf32c0f1926e092deca",
        "test_mcp_auth.py": "ac151bc4106dbc0a5eda483ae88a6c525970e4fe62d52291acb675901a43bb30",
        "test_demo_data.py": "fbd2d785b596ef8cd3eb3868d846655c7ccd032a60b2f5399c6cec1ec565ed10",
        "test_auth.py": "76e8feda4e00a7f59005aa98ffae3439dfae46c12a072773841126ff96506c78",
        "test_benchmark.py": "5b7287eb30f7bc66aa34c39f41f70fa07c39cc2bbace5df7df7365243305b9dc",
        "test_models.py": "58d165c5391f61e8eee0e9a5c0f330deee433f7f83abb992904552a65818f795",
        "test_api.py": "903671d71a524e1096a863d857f61d776d402af1f4d543e59a6ea74881b86e5b",
        "test_orders.py": "6c21755f1329b56d0bd449b128080078a2e1c7306ec48df09362a47309dcba6d"
      },
      "tasks_sha256": "efe62d068b97dd6a99fb9cf66b3addda2e6d5e7687a51ba6740d0112b132ac43",
      "harness_sha256": {
        "runner.py": "64afc5bcdb1f9c06fc95b4827173f5650f249450474b492d750165f33b906094",
        "__init__.py": "c4bb304adea0d61d768152331fefd4db061755b3cf4675aff854c88595e91032",
        "cli.py": "b4644f52df24ca7e9dd5ebdfa3904eebc3f2bf98e60c9e0a043cf6f45c0dae89"
      }
    }
  }
]
