{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:06.266436+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_advanced_features.test_metamethod_le",
      "eval.tests.test_coverage_boost.test_debug_getlocal",
      "eval.tests.test_advanced_features.test_metamethod_add",
      "eval.tests.test_coverage_boost.test_string_pattern_invalid_escape",
      "eval.tests.test_coverage_boost.test_math_log_with_base",
      "eval.tests.test_coverage_boost.test_string_match_frontier",
      "eval.tests.test_coverage_boost.test_collectgarbage_count",
      "eval.tests.test_coverage_boost.test_string_char_overflow",
      "eval.tests.test_coverage_boost.test_metamethod_unm",
      "eval.tests.test_base_library.test_collectgarbage_count",
      "eval.tests.test_coverage_boost_2.test_io_type_closed",
      "eval.tests.test_coverage_boost_2.test_tonumber_negative_hex",
      "eval.tests.test_coverage_boost_3.test_runtime_error_concat_nil",
      "eval.tests.test_coverage_final_push.test_function_environment",
      "eval.tests.test_coverage_final_push.test_coroutine_error",
      "eval.tests.test_coverage_final_push.test_tail_call",
      "eval.tests.test_advanced_features.test_metamethod_sub",
      "eval.tests.test_coverage_boost.test_debug_setlocal",
      "eval.tests.test_coverage_boost.test_string_pattern_capture_error",
      "eval.tests.test_advanced_features.test_tail_call",
      "eval.tests.test_coverage_boost.test_string_char_large",
      "eval.tests.test_coverage_boost.test_metamethod_concat",
      "eval.tests.test_coverage_boost_2.test_coroutine_resume_after_yield",
      "eval.tests.test_coverage_final_push.test_debug_getupvalue",
      "eval.tests.test_coverage_boost_2.test_file_seek",
      "eval.tests.test_coverage_boost_2.test_coroutine_yield_multiple_values",
      "eval.tests.test_debug_library.test_debug_getfenv",
      "eval.tests.test_coverage_boost_3.test_stack_overflow",
      "eval.tests.test_coverage_boost_3.test_gc_isrunning",
      "eval.tests.test_coverage_final_push.test_coroutine_dead_status",
      "eval.tests.test_advanced_features.test_metamethod_mul",
      "eval.tests.test_coverage_boost.test_debug_setupvalue",
      "eval.tests.test_coverage_boost.test_metamethod_eq",
      "eval.tests.test_coverage_boost.test_string_rep_with_separator",
      "eval.tests.test_error_handling.test_stack_overflow",
      "eval.tests.test_coverage_boost.test_string_match_bracket_class_range",
      "eval.tests.test_coverage_boost_2.test_load_function",
      "eval.tests.test_base_library.test_load_from_function",
      "eval.tests.test_coverage_boost_2.test_file_setvbuf",
      "eval.tests.test_debug_library.test_debug_traceback",
      "eval.tests.test_final_50_percent_push.test_closure_environment",
      "eval.tests.test_debug_library.test_debug_setfenv",
      "eval.tests.test_final_50_percent_push.test_metamethod_combinations",
      "eval.tests.test_coverage_boost_3.test_setmetatable_protected",
      "eval.tests.test_coverage_final_push.test_hex_escape_in_string",
      "eval.tests.test_advanced_features.test_metamethod_div",
      "eval.tests.test_coverage_boost.test_debug_sethook_call",
      "eval.tests.test_coverage_boost.test_metamethod_lt",
      "eval.tests.test_final_push_2.test_load_binary_chunk",
      "eval.tests.test_coverage_boost.test_string_match_balance",
      "eval.tests.test_base_library.test_getfenv_setfenv",
      "eval.tests.test_debug_library.test_debug_getlocal",
      "eval.tests.test_error_handling.test_concat_with_non_string",
      "eval.tests.test_final_push_2.test_debug_setupvalue",
      "eval.tests.test_final_50_percent_push.test_file_operations_comprehensive",
      "eval.tests.test_io_operations.test_io_output",
      "eval.tests.test_io_operations.test_file_seek",
      "eval.tests.test_io_operations.test_io_tmpfile",
      "eval.tests.test_final_coverage_push.test_setfenv_with_level",
      "eval.tests.test_final_coverage_push.test_pairs_with_mixed_keys",
      "eval.tests.test_advanced_features.test_metamethod_mod",
      "eval.tests.test_coverage_boost.test_debug_sethook_return",
      "eval.tests.test_coverage_boost.test_metamethod_le",
      "eval.tests.test_lua_language_features.test_metatables",
      "eval.tests.test_final_50_percent_push.test_math_operations_edge_cases",
      "eval.tests.test_debug_library.test_debug_getupvalue",
      "eval.tests.test_lua_language_features.test_coroutines",
      "eval.tests.test_final_push_2.test_coroutine_status",
      "eval.tests.test_io_operations.test_io_input",
      "eval.tests.test_io_operations.test_file_setvbuf",
      "eval.tests.test_massive_coverage_push.test_io_input",
      "eval.tests.test_massive_coverage_push.test_io_tmpfile",
      "eval.tests.test_final_coverage_push.test_loadstring_with_env",
      "eval.tests.test_massive_coverage_push.test_metamethod_pow",
      "eval.tests.test_massive_coverage_push.test_pattern_char_class_control",
      "eval.tests.test_advanced_features.test_metamethod_pow",
      "eval.tests.test_coverage_boost.test_debug_sethook_line",
      "eval.tests.test_massive_coverage_push.test_type_thread",
      "eval.tests.test_debug_library.test_debug_sethook",
      "eval.tests.test_final_50_percent_push.test_coroutine_double_yield"
    ],
    "failed_tests_omitted": 816,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 3183,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "luajit__luajit.a553b3d",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "9451136",
    "calls": "135",
    "created_at": "2026-05-17T12:38:48.644319+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "7.6920",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "9672357",
    "instance_id": "luajit__luajit.a553b3d",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "2113",
    "n_system_errors": "0",
    "n_tests": "2967",
    "n_warnings": "0",
    "output_tokens": "62011",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "17619",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-luajit-luajit",
    "run_version": "20260517T094700Z",
    "score": "0.7121671722278395",
    "session_ended_at": "2026-05-17T12:59:05.512Z",
    "session_started_at": "2026-05-17T12:38:53.001Z",
    "test_branch_errors": "{}",
    "total_tokens": "9734368",
    "wall_clock_seconds": "1212"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./miniluajit.py"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-luajit-luajit",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
