{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:24:55.235266+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_oranda_comprehensive.test_build_with_license",
      "eval.tests.test_oranda_comprehensive.test_build_with_description",
      "eval.tests.test_oranda_comprehensive.test_build_with_package_json",
      "eval.tests.test_oranda_comprehensive.test_no_arguments_shows_help",
      "eval.tests.test_oranda_comprehensive.test_build_with_styles",
      "eval.tests.test_oranda_comprehensive.test_build_with_repository",
      "eval.tests.test_oranda_comprehensive.test_build_with_config",
      "eval.tests.test_oranda_comprehensive.test_build_with_cargo_toml",
      "eval.tests.test_oranda_comprehensive.test_build_markdown_features",
      "eval.tests.test_oranda_comprehensive.test_build_with_dist_dir",
      "eval.tests.test_oranda_comprehensive.test_build_with_changelog",
      "eval.tests.test_oranda_comprehensive.test_build_with_path_prefix",
      "eval.tests.test_oranda_comprehensive.test_build_with_favicon",
      "eval.tests.test_oranda_comprehensive.test_build_with_theme",
      "eval.tests.test_oranda_comprehensive.test_build_with_additional_css",
      "eval.tests.test_oranda_comprehensive.test_build_with_various_versions",
      "eval.tests.test_oranda_comprehensive.test_build_with_readme_path",
      "eval.tests.test_oranda_comprehensive.test_build_with_logo",
      "eval.tests.test_oranda_comprehensive.test_build_with_homepage",
      "eval.tests.test_oranda_comprehensive.test_build_with_components",
      "eval.tests.test_oranda_comprehensive.test_build_with_npm_scripts",
      "eval.tests.test_oranda_comprehensive.test_build_with_npm_dependencies",
      "eval.tests.test_oranda_comprehensive.test_build_large_readme",
      "eval.tests.test_oranda_comprehensive.test_build_with_code_blocks",
      "eval.tests.test_oranda_comprehensive.test_build_with_npm_bin",
      "eval.tests.test_oranda_comprehensive.test_build_with_blockquotes",
      "eval.tests.test_oranda_comprehensive.test_build_with_emphasis",
      "eval.tests.test_oranda_comprehensive.test_build_with_headings",
      "eval.tests.test_oranda_comprehensive.test_build_with_lists",
      "eval.tests.test_oranda_comprehensive.test_build_with_gitignore",
      "eval.tests.test_oranda_comprehensive.test_build_multiple_times",
      "eval.tests.test_oranda_comprehensive.test_build_with_github_workflows",
      "eval.tests.test_oranda_comprehensive.test_build_unicode_content",
      "eval.tests.test_oranda_comprehensive.test_build_with_images",
      "eval.tests.test_oranda_comprehensive.test_build_with_tables",
      "eval.tests.test_oranda_comprehensive.test_build_with_license_file",
      "eval.tests.test_oranda_comprehensive.test_build_with_links",
      "eval.tests.test_oranda_comprehensive.test_build_with_funding_file",
      "eval.tests.test_oranda_comprehensive.test_build_with_all_metadata_fields",
      "eval.tests.test_oranda_comprehensive.test_build_with_horizontal_rules",
      "eval.tests.test_oranda_comprehensive.test_build_with_changelog_file",
      "eval.tests.test_oranda_comprehensive.test_build_npm_engines",
      "eval.tests.test_oranda_comprehensive.test_build_npm_main",
      "eval.tests.test_oranda_comprehensive.test_build_with_assets",
      "eval.tests.test_oranda_comprehensive.test_build_with_docs",
      "eval.tests.test_oranda_comprehensive.test_multiple_config_combinations",
      "eval.tests.test_oranda_comprehensive.test_build_various_version_formats",
      "eval.tests.test_oranda_comprehensive.test_build_scoped_npm",
      "eval.tests.test_oranda_comprehensive.test_build_npm_workspace",
      "eval.tests.test_oranda_comprehensive.test_build_various_readme_names",
      "eval.tests.test_oranda_comprehensive.test_build_different_dist_dirs",
      "eval.tests.test_oranda_comprehensive.test_build_different_themes",
      "eval.tests.test_oranda_comprehensive.test_multiple_builds_in_sequence",
      "eval.tests.test_oranda_comprehensive.test_build_with_all_components_enabled",
      "eval.tests.test_oranda_comprehensive.test_package_json_with_keywords",
      "eval.tests.test_oranda_comprehensive.test_build_with_various_licenses",
      "eval.tests.test_oranda_comprehensive.test_build_with_various_descriptions",
      "eval.tests.test_oranda_comprehensive.test_build_with_various_repo_urls",
      "eval.tests.test_oranda_comprehensive.test_build_with_path_prefix_variations",
      "eval.tests.test_oranda_comprehensive.test_build_with_null_configs",
      "eval.tests.test_oranda_comprehensive.test_build_with_social_meta",
      "eval.tests.test_oranda_comprehensive.test_build_with_bool_configs",
      "eval.tests.test_oranda_comprehensive.test_package_json_with_author",
      "eval.tests.test_oranda_comprehensive.test_package_json_with_repository_object",
      "eval.tests.test_oranda_comprehensive.test_build_with_various_homepages",
      "eval.tests.test_oranda_comprehensive.test_build_stress_test",
      "eval.tests.test_oranda_comprehensive.test_build_maximal_configuration",
      "eval.tests.test_basic_invocation.test_no_args_shows_help",
      "eval.tests.test_cargo_detection.test_build_with_workspace_cargo_toml",
      "eval.tests.test_advanced_config.test_build_with_path_prefix",
      "eval.tests.test_advanced_config.test_build_with_changelog_disabled",
      "eval.tests.test_advanced_config.test_build_with_logo_and_favicon",
      "eval.tests.test_cargo_detection.test_build_cargo_and_config_preference",
      "eval.tests.test_advanced_config.test_build_with_homepage_url",
      "eval.tests.test_artifacts.test_build_with_artifacts_config",
      "eval.tests.test_build_command.test_build_with_minimal_config",
      "eval.tests.test_cargo_detection.test_build_with_cargo_toml",
      "eval.tests.test_components.test_build_with_analytics_plausible",
      "eval.tests.test_components.test_build_with_social_config",
      "eval.tests.test_components.test_build_with_analytics_google"
    ],
    "failed_tests_omitted": 454,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 978,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "axodotdev__oranda.27d60c7",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "3281024",
    "calls": "63",
    "created_at": "2026-05-17T12:32:02.983500+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "3.8326",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "3398330",
    "instance_id": "axodotdev__oranda.27d60c7",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "310",
    "n_system_errors": "0",
    "n_tests": "767",
    "n_warnings": "0",
    "output_tokens": "53518",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "8416",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-axodotdev-oranda-attempt-2",
    "run_version": "20260517T094700Z",
    "score": "0.4041720990873533",
    "session_ended_at": "2026-05-17T12:46:20.811Z",
    "session_started_at": "2026-05-17T12:32:05.845Z",
    "test_branch_errors": "{}",
    "total_tokens": "3451848",
    "wall_clock_seconds": "854"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./oranda_reimpl.py"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-axodotdev-oranda-attempt-2",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
