{
  "run_id": "fixtures-20261017T195514-b9747e",
  "kind": "explicit test fixtures, not Mercury",
  "ok": true,
  "results": [
    {
      "fixture": "incorrect",
      "expected": "test_failure",
      "actual": "test_failure",
      "ok": true,
      "sandbox_id": "sb-01m55pxvcdmyacdj5hqq27vxqb",
      "forked_from": "sb-01m55pxk4r3qzxhv0cksa4mydp",
      "feedback": {
        "baseline_ms": null,
        "benchmark": null,
        "benchmark_n": 5000,
        "candidate_ms": null,
        "compile_ok": true,
        "detail": "46 of 60 correctness tests disagree with the trusted brute-force reference",
        "elapsed_ms": 62.939689999999885,
        "error_subtype": null,
        "error_type": "test_failure",
        "errors": [
          {
            "candidate_error": null,
            "case": {
              "a": [
                0
              ],
              "b": [
                0
              ],
              "index": 3,
              "lower": 0,
              "upper": 0
            },
            "expected": 1,
            "got": 0
          },
          {
            "candidate_error": null,
            "case": {
              "a": [
                5,
                5,
                5
              ],
              "b": [
                5,
                5
              ],
              "index": 6,
              "lower": 10,
              "upper": 10
            },
            "expected": 6,
            "got": 0
          }
        ],
        "exception_type": null,
        "phase": "correctness",
        "protocol": {
          "budget_s": 20.0,
          "candidate_path": "/workspace/candidate/solution.py",
          "framing": "newline-delimited JSON, one request object and one response object per line",
          "output_caps_bytes": {
            "max_line": 4194304,
            "max_total": 16777216
          },
          "request_cap_bytes": 16777216,
          "runs_as_user": "nobody",
          "spawn": "runuser -u nobody -- env -i <minimal env> python3 -I worker.py",
          "supervisor_imports_candidate": false,
          "version": 1,
          "worker_imports_candidate": true,
          "worker_path": "/workspace/.kiss_trusted/worker.py"
        },
        "protocol_version": 1,
        "seed": 1730,
        "speedup": null,
        "status": "test_failure",
        "supervisor_self_protect": {
          "mode": "0o400",
          "path": "/workspace/.kiss_trusted/harness.py"
        },
        "tests_passed": 14,
        "total": 60,
        "worker": {
          "numpy": false,
          "pid": null,
          "python": "3.12.3",
          "user": "nobody"
        }
      }
    },
    {
      "fixture": "controlled-timeout",
      "expected": "timeout",
      "actual": "timeout",
      "ok": true,
      "sandbox_id": "sb-01m55py2fm19sn7q3bvymctpps",
      "forked_from": "sb-01m55pxk4r3qzxhv0cksa4mydp",
      "feedback": {
        "baseline_ms": null,
        "benchmark": null,
        "benchmark_n": 5000,
        "candidate_ms": null,
        "compile_ok": true,
        "detail": "worker produced no output before its deadline",
        "elapsed_ms": 6065.662869999999,
        "error_subtype": null,
        "error_type": "timeout",
        "errors": [],
        "exception_type": null,
        "phase": "correctness",
        "protocol": {
          "budget_s": 20.0,
          "candidate_path": "/workspace/candidate/solution.py",
          "framing": "newline-delimited JSON, one request object and one response object per line",
          "output_caps_bytes": {
            "max_line": 4194304,
            "max_total": 16777216
          },
          "request_cap_bytes": 16777216,
          "runs_as_user": "nobody",
          "spawn": "runuser -u nobody -- env -i <minimal env> python3 -I worker.py",
          "supervisor_imports_candidate": false,
          "version": 1,
          "worker_imports_candidate": true,
          "worker_path": "/workspace/.kiss_trusted/worker.py"
        },
        "protocol_version": 1,
        "seed": 1730,
        "speedup": null,
        "status": "timeout",
        "supervisor_self_protect": {
          "mode": "0o400",
          "path": "/workspace/.kiss_trusted/harness.py"
        },
        "tests_passed": 0,
        "total": 60,
        "worker": {
          "numpy": false,
          "pid": null,
          "python": "3.12.3",
          "user": "nobody"
        }
      }
    },
    {
      "fixture": "syntax-error",
      "expected": "compilation_error",
      "actual": "compilation_error",
      "ok": true,
      "sandbox_id": "sb-01m55pyfej6t8ncq1dsc6840xt",
      "forked_from": "sb-01m55pxk4r3qzxhv0cksa4mydp",
      "feedback": {
        "baseline_ms": null,
        "benchmark": null,
        "benchmark_n": 5000,
        "candidate_ms": null,
        "compile_ok": false,
        "detail": "SyntaxError: invalid syntax (line 1)",
        "elapsed_ms": 46.49414000000007,
        "error_subtype": "syntax_error",
        "error_type": "compilation_error",
        "errors": [],
        "exception_type": "SyntaxError",
        "phase": "startup",
        "protocol": {
          "budget_s": 20.0,
          "candidate_path": "/workspace/candidate/solution.py",
          "framing": "newline-delimited JSON, one request object and one response object per line",
          "output_caps_bytes": {
            "max_line": 4194304,
            "max_total": 16777216
          },
          "request_cap_bytes": 16777216,
          "runs_as_user": "nobody",
          "spawn": "runuser -u nobody -- env -i <minimal env> python3 -I worker.py",
          "supervisor_imports_candidate": false,
          "version": 1,
          "worker_imports_candidate": true,
          "worker_path": "/workspace/.kiss_trusted/worker.py"
        },
        "protocol_version": 1,
        "seed": 1730,
        "speedup": null,
        "status": "compilation_error",
        "supervisor_self_protect": {
          "mode": "0o400",
          "path": "/workspace/.kiss_trusted/harness.py"
        },
        "tests_passed": 0,
        "total": 60,
        "worker": null
      }
    },
    {
      "fixture": "input-mutation",
      "expected": "test_failure",
      "actual": "test_failure",
      "ok": true,
      "sandbox_id": "sb-01m55pym9j0n2z9qjee1zxm71j",
      "forked_from": "sb-01m55pxk4r3qzxhv0cksa4mydp",
      "feedback": {
        "baseline_ms": null,
        "benchmark": null,
        "benchmark_n": 5000,
        "candidate_ms": null,
        "compile_ok": true,
        "detail": "60 of 60 correctness tests disagree with the trusted brute-force reference",
        "elapsed_ms": 63.6416099999999,
        "error_subtype": null,
        "error_type": "test_failure",
        "errors": [
          {
            "candidate_error": "ValueError: candidate mutated caller inputs",
            "case": {
              "a": [],
              "b": [],
              "index": 0,
              "lower": 0,
              "upper": 0
            },
            "expected": 0,
            "got": null
          },
          {
            "candidate_error": "ValueError: candidate mutated caller inputs",
            "case": {
              "a": [],
              "b": [
                1,
                2,
                3
              ],
              "index": 1,
              "lower": -10,
              "upper": 10
            },
            "expected": 0,
            "got": null
          }
        ],
        "exception_type": null,
        "phase": "correctness",
        "protocol": {
          "budget_s": 20.0,
          "candidate_path": "/workspace/candidate/solution.py",
          "framing": "newline-delimited JSON, one request object and one response object per line",
          "output_caps_bytes": {
            "max_line": 4194304,
            "max_total": 16777216
          },
          "request_cap_bytes": 16777216,
          "runs_as_user": "nobody",
          "spawn": "runuser -u nobody -- env -i <minimal env> python3 -I worker.py",
          "supervisor_imports_candidate": false,
          "version": 1,
          "worker_imports_candidate": true,
          "worker_path": "/workspace/.kiss_trusted/worker.py"
        },
        "protocol_version": 1,
        "seed": 1730,
        "speedup": null,
        "status": "test_failure",
        "supervisor_self_protect": {
          "mode": "0o400",
          "path": "/workspace/.kiss_trusted/harness.py"
        },
        "tests_passed": 0,
        "total": 60,
        "worker": {
          "numpy": false,
          "pid": null,
          "python": "3.12.3",
          "user": "nobody"
        }
      }
    },
    {
      "fixture": "timing-spoof",
      "expected": "protocol_error",
      "actual": "protocol_error",
      "ok": true,
      "sandbox_id": "sb-01m55pys54e07rwmdybgvd8yr4",
      "forked_from": "sb-01m55pxk4r3qzxhv0cksa4mydp",
      "feedback": {
        "baseline_ms": null,
        "benchmark": null,
        "benchmark_n": 5000,
        "candidate_ms": null,
        "compile_ok": true,
        "detail": "worker timing samples must be finite and strictly positive",
        "elapsed_ms": 90.69650399999985,
        "error_subtype": null,
        "error_type": "protocol_error",
        "errors": [],
        "exception_type": null,
        "phase": "benchmark",
        "protocol": {
          "budget_s": 20.0,
          "candidate_path": "/workspace/candidate/solution.py",
          "framing": "newline-delimited JSON, one request object and one response object per line",
          "output_caps_bytes": {
            "max_line": 4194304,
            "max_total": 16777216
          },
          "request_cap_bytes": 16777216,
          "runs_as_user": "nobody",
          "spawn": "runuser -u nobody -- env -i <minimal env> python3 -I worker.py",
          "supervisor_imports_candidate": false,
          "version": 1,
          "worker_imports_candidate": true,
          "worker_path": "/workspace/.kiss_trusted/worker.py"
        },
        "protocol_version": 1,
        "seed": 1730,
        "speedup": null,
        "status": "protocol_error",
        "supervisor_self_protect": {
          "mode": "0o400",
          "path": "/workspace/.kiss_trusted/harness.py"
        },
        "tests_passed": 60,
        "total": 60,
        "worker": {
          "numpy": false,
          "pid": null,
          "python": "3.12.3",
          "user": "nobody"
        }
      }
    }
  ],
  "cleanup": [
    {
      "sandbox_id": "sb-01m55pys54e07rwmdybgvd8yr4",
      "status": "destroyed",
      "verified": true
    },
    {
      "sandbox_id": "sb-01m55pym9j0n2z9qjee1zxm71j",
      "status": "destroyed",
      "verified": true
    },
    {
      "sandbox_id": "sb-01m55pyfej6t8ncq1dsc6840xt",
      "status": "destroyed",
      "verified": true
    },
    {
      "sandbox_id": "sb-01m55py2fm19sn7q3bvymctpps",
      "status": "destroyed",
      "verified": true
    },
    {
      "sandbox_id": "sb-01m55pxvcdmyacdj5hqq27vxqb",
      "status": "destroyed",
      "verified": true
    },
    {
      "sandbox_id": "sb-01m55pxk4r3qzxhv0cksa4mydp",
      "status": "destroyed",
      "verified": true
    }
  ]
}