{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:16.356416+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "tests.test_cookies.test_cookie_file_nonexistent",
      "eval.tests.test_cli_operations.test_isolate_with_no_css_combined",
      "eval.tests.test_cli_operations.test_no_js_flag",
      "eval.tests.test_cli_operations.test_timeout_flag",
      "eval.tests.test_cli_operations.test_output_to_stdout_explicit_dash",
      "eval.tests.test_cli_operations.test_stdin_with_malformed_html",
      "eval.tests.test_assets.test_base_url_resolves_absolute_paths",
      "eval.tests.test_assets.test_video_sources_removed_with_no_video_flag",
      "eval.tests.test_core_edge.test_unknown_encoding_error",
      "eval.tests.test_cli_operations.test_multiple_domains_whitelist",
      "eval.tests.test_core_edge.test_multiple_templates_in_output_path",
      "eval.tests.test_cookies.test_cookie_file_not_found_clear_error",
      "eval.tests.test_core_edge.test_output_with_no_title_uses_empty_string",
      "eval.tests.test_cache_cli.test_cache_basic_functionality",
      "eval.tests.test_css_edge.test_empty_import_url",
      "eval.tests.test_css_edge.test_no_fonts_flag_skips_font_face_blocks",
      "eval.tests.test_cache_cli.test_cache_with_different_resources",
      "eval.tests.test_cli_operations.test_quiet_mode_with_successful_operation",
      "eval.tests.test_cli_operations.test_no_css_no_js_combined",
      "eval.tests.test_cli_operations.test_user_agent_flag",
      "eval.tests.test_cli_operations.test_no_images_flag",
      "eval.tests.test_assets.test_svg_image_element_embedded",
      "eval.tests.test_assets.test_audio_sources_removed_with_no_audio_flag",
      "eval.tests.test_cli_operations.test_output_filename_with_special_chars",
      "eval.tests.test_cli_operations.test_invalid_flag_value_timeout",
      "eval.tests.test_core_edge.test_base_url_file_scheme_ignored_on_stdin",
      "eval.tests.test_encoding_edge_cases.test_encoding_flag_overrides_meta_tag",
      "eval.tests.test_encoding_edge_cases.test_data_url_with_charset_preserved",
      "eval.tests.test_css_edge.test_hash_fragment_url_preserved",
      "eval.tests.test_css_edge.test_import_preserves_fragment_identifier",
      "eval.tests.test_encoding_edge_cases.test_integrity_valid_sha512_embeds_resource",
      "eval.tests.test_cli_operations.test_ignore_errors_flag",
      "eval.tests.test_cli_operations.test_no_images_with_isolate",
      "eval.tests.test_cli_operations.test_mhtml_format_flag",
      "eval.tests.test_cli_operations.test_isolate_mode",
      "eval.tests.test_cache_cli.test_cache_with_large_file",
      "eval.tests.test_assets.test_integrity_attribute_validation_embeds_on_match",
      "eval.tests.test_assets.test_script_with_integrity_attribute",
      "eval.tests.test_css_final.test_import_url_unreachable_http",
      "eval.tests.test_cookies.test_invalid_cookie_file_header",
      "eval.tests.test_cli_operations.test_no_fonts_flag",
      "eval.tests.test_encoding_edge_cases.test_encoding_flag_invalid_charset_error",
      "eval.tests.test_cache_cli.test_cache_with_timeout",
      "eval.tests.test_css_edge.test_empty_url_variations_all_normalized",
      "eval.tests.test_encoding_edge_cases.test_integrity_invalid_hash_keeps_external_reference",
      "eval.tests.test_css_edge.test_url_in_non_image_property_with_no_images_flag",
      "eval.tests.test_error_paths.test_empty_target_error",
      "eval.tests.test_cli_operations.test_no_frames_flag",
      "eval.tests.test_cli_operations.test_absolute_path_input",
      "eval.tests.test_cli_operations.test_domain_whitelist_flag",
      "eval.tests.test_cli_operations.test_file_output_flag",
      "eval.tests.test_css_final.test_import_url_unreachable_https",
      "eval.tests.test_encoding_edge_cases.test_integrity_attribute_on_data_url_stripped",
      "eval.tests.test_css_final.test_nested_square_bracket_selectors",
      "eval.tests.test_encoding_edge_cases.test_integrity_sha384_validation",
      "eval.tests.test_css_edge.test_quoted_string_in_url_function_on_retrieval_failure",
      "eval.tests.test_encoding_edge_cases.test_noscript_nested_unwrap_all_levels",
      "eval.tests.test_css_final.test_square_bracket_attribute_selectors",
      "eval.tests.test_error_paths.test_directory_target_error",
      "eval.tests.test_cache_cli.test_cache_mixed_sizes",
      "eval.tests.test_cli_operations.test_file_input_simple_no_metadata",
      "eval.tests.test_cli_operations.test_multiple_removal_flags_combined",
      "eval.tests.test_cli_operations.test_invalid_output_path_panics",
      "eval.tests.test_cli_operations.test_domain_blacklist_flag",
      "eval.tests.test_cli_operations.test_base_url_flag",
      "eval.tests.test_css_final.test_background_url_unreachable_http",
      "eval.tests.test_css_final.test_mixed_import_and_url_errors",
      "eval.tests.test_encoding_edge_cases.test_encoding_flag_with_utf16",
      "eval.tests.test_harvest.test_set_existing_to_empty_when_empty_provided",
      "eval.tests.test_error_paths.test_invalid_encoding_with_force_flag",
      "eval.tests.test_css_edge.test_failed_import_url_drops_import",
      "eval.tests.test_error_paths.test_unsupported_url_scheme_error",
      "eval.tests.test_harvest.test_local_file_target_input_relative_target_path",
      "eval.tests.test_harvest.test_bad_input_data_url",
      "eval.tests.test_cli_operations.test_no_css_flag",
      "eval.tests.test_cli_operations.test_encoding_override_flag",
      "eval.tests.test_cli_operations.test_cookie_file_flag",
      "eval.tests.test_harvest.test_properly_save_document_with_gb2312_custom_charset",
      "eval.tests.test_cli_operations.test_nonexistent_file_error",
      "eval.tests.test_css_final.test_background_url_unreachable_https"
    ],
    "failed_tests_omitted": 179,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 777,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "y2z__monolith.8702e66",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "4140928",
    "calls": "77",
    "created_at": "2026-05-17T16:48:34.057458+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "4.2488",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "4297400",
    "instance_id": "y2z__monolith.8702e66",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "455",
    "n_system_errors": "0",
    "n_tests": "713",
    "n_warnings": "0",
    "output_tokens": "46532",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "14591",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-y2z-monolith",
    "run_version": "20260517T094700Z",
    "score": "0.638148667601683",
    "session_ended_at": "2026-05-17T17:01:26.081Z",
    "session_started_at": "2026-05-17T16:48:37.044Z",
    "test_branch_errors": "{}",
    "total_tokens": "4343932",
    "wall_clock_seconds": "769"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./monolith.py"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-y2z-monolith",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
