{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:24:57.399448+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_argparse_validation.test_debug_flag_requires_known_specifier",
      "eval.tests.test_argparse_validation.test_missing_or_invalid_format_specifiers[args3-expected3]",
      "eval.tests.test_argparse_validation.test_missing_or_invalid_format_specifiers[args1-expected1]",
      "tests.test_mode_dispatch.TestErrorHandling.test_feature_mode_missing_specifier",
      "tests.test_mode_dispatch.TestDebugModes.test_debug_level_recognized",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[001_001_a.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[002_002_addindex.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[003_003_anchor.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[004_004_arg.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[005_005_attention.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[006_006_author.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[007_007_b.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[010_010_c.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[012_012_cite.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[014_014_code.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[017_017_copyright.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[020_020_only.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[023_023_e.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[024_024_if.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[030_030_htmlinclude.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[031_031_image.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[033_033_internal.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[034_034_internal.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[038_038_n.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[043_043_page.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[045_045_refitem.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[050_050_verbatim.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[051_051_escape.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[052_052_tilde.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[053_053_tilde.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[056_056_latexinclude.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[065_065_tilde.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[079_079_tableofcontents.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[109_109_htmlcmds.dox]",
      "eval.tests.test_doxygen_testing_suite_externalized.test_ext_internal_dox_test_via_cli[110_110_backticks.dox]",
      "eval.tests.test_config_env_handling.test_x_noenv_disables_env_substitution",
      "eval.tests.test_config_env_handling.test_env_var_substitution_in_value_affects_behavior_quiet",
      "eval.tests.test_config_env_handling.test_invalid_boolean_value_warns_and_defaults",
      "eval.tests.test_config_env_handling.test_env_var_substitution_in_path_uses_HOME",
      "eval.tests.test_cli_outputs.test_version_short_exact",
      "eval.tests.test_cli_outputs.test_version_extended_contains_sqlite_line",
      "eval.tests.test_config_and_run.test_read_config_from_stdin_dash",
      "eval.tests.test_cli_outputs.test_help_text_starts_and_ends_with_expected_lines",
      "eval.tests.test_config_and_run.test_documentation_run_generates_expected_html_files",
      "tests.test_doxygen.test_doxygen[032_test the \\\\include and \\\\includelineno commands]",
      "tests.test_doxygen.test_doxygen[018_test the \\\\def, \\\\var, \\\\fn, and \\\\typedef commands]",
      "tests.test_doxygen.test_doxygen[007_test the \\\\b command]",
      "tests.test_doxygen.test_doxygen[001_test the \\\\a and \\\\mainpage commands]",
      "tests.test_doxygen.test_doxygen[026_test the \\\\exception, \\\\param, and \\\\tparam commands]",
      "tests.test_doxygen.test_doxygen[028_test the \\\\f$, \\\\f[, \\\\f], \\\\f{, and \\\\f} commands]",
      "tests.test_doxygen.test_doxygen[011_test the \\\\interface and \\\\category command]",
      "tests.test_doxygen.test_doxygen[016_test the \\\\copydoc, \\\\copybrief, \\\\copydetails, and \\\\]",
      "tests.test_doxygen.test_doxygen[005_test \\\\attention, \\\\note, \\\\remark, \\\\warning, and \\\\pa]",
      "tests.test_doxygen.test_doxygen[022_test the \\\\dot and \\\\enddot commands]",
      "tests.test_doxygen.test_doxygen[030_test the \\\\htmlinclude command]",
      "tests.test_doxygen.test_doxygen[024_test the \\\\if, \\\\ifnot, \\\\elsif, \\\\else, and \\\\endif co]",
      "tests.test_doxygen.test_doxygen[014_test the \\\\code command]",
      "tests.test_doxygen.test_doxygen[003_test \\\\anchor command]",
      "tests.test_doxygen.test_doxygen[020_test the \\\\*only and \\\\end*only commands]",
      "tests.test_doxygen.test_doxygen[009_test the \\\\bug, \\\\deprecated, \\\\todo, \\\\test, and \\\\xre]",
      "tests.test_doxygen.test_doxygen[019_test the \\\\defgroup, \\\\addtogroup, and \\\\ingroup comm]",
      "tests.test_doxygen.test_doxygen[033_test the \\\\internal and \\\\endinternal commands (1)]",
      "tests.test_doxygen.test_doxygen[023_test the \\\\e, \\\\em commands]",
      "tests.test_doxygen.test_doxygen[008_test \\\\brief and \\\\file command]",
      "tests.test_doxygen.test_doxygen[027_test the \\\\extends, \\\\implements, \\\\memberof, \\\\privat]",
      "tests.test_doxygen.test_doxygen[004_test \\\\arg and \\\\li commands]",
      "tests.test_doxygen.test_doxygen[006_test the \\\\author, \\\\since, and \\\\version command]",
      "tests.test_doxygen.test_doxygen[015_test the `cond` command]",
      "tests.test_doxygen.test_doxygen[029_test the \\\\hideinitializer command]",
      "tests.test_doxygen.test_doxygen[017_test \\\\copyright and \\\\date commands]",
      "tests.test_doxygen.test_doxygen[013_test the \\\\class and \\\\headerfile commands]",
      "tests.test_doxygen.test_doxygen[025_test the \\\\example command]",
      "tests.test_doxygen.test_doxygen[002_test \\\\addindex command]",
      "tests.test_doxygen.test_doxygen[031_test the \\\\image command]",
      "tests.test_doxygen.test_doxygen[021_test the \\\\dontinclude, \\\\skip, \\\\until, \\\\skipline, \\\\]",
      "tests.test_doxygen.test_doxygen[010_test the \\\\c and \\\\p commands]",
      "tests.test_doxygen.test_doxygen[034_test the \\\\internal and \\\\endinternal commands (2)]",
      "tests.test_doxygen.test_doxygen[035_test \\\\invariant, \\\\pre and \\\\post commands]",
      "tests.test_doxygen.test_doxygen[040_test the \\\\namespace command]",
      "tests.test_doxygen.test_doxygen[036_test \\\\link command]"
    ],
    "failed_tests_omitted": 78,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 251,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "doxygen__doxygen.966d98e",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "2727168",
    "calls": "50",
    "created_at": "2026-05-17T10:40:01.936423+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "3.1120",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "2869024",
    "instance_id": "doxygen__doxygen.966d98e",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "78",
    "n_system_errors": "0",
    "n_tests": "229",
    "n_warnings": "0",
    "output_tokens": "34637",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "10250",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-doxygen-doxygen",
    "run_version": "",
    "score": "0.3406113537117904",
    "session_ended_at": "2026-05-17T10:49:02.187Z",
    "session_started_at": "2026-05-17T10:40:04.968Z",
    "test_branch_errors": "{}",
    "total_tokens": "2903661",
    "wall_clock_seconds": "537"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./doxygen_clone.py",
      "./executable",
      "./resources",
      "./resources/Doxyfile.full",
      "./resources/Doxyfile.simple",
      "./resources/DoxygenLayout.xml",
      "./resources/emoji.txt",
      "./resources/html_css",
      "./resources/html_footer",
      "./resources/html_header",
      "./resources/latex_footer",
      "./resources/latex_header",
      "./resources/latex_style",
      "./resources/rtfext",
      "./resources/rtfstyle"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-doxygen-doxygen",
  "run_version": "",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
