{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:15.597503+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_additional_coverage.test_compile_with_figures",
      "eval.tests.test_additional_coverage.test_eval_boolean_operations",
      "eval.tests.test_advanced_compile.test_compile_multiple_inputs",
      "eval.tests.test_advanced_compile.test_compile_with_typst_code",
      "eval.tests.test_compile.test_compile_from_stdin",
      "eval.tests.test_compile.test_compile_to_stdout",
      "eval.tests.test_additional_coverage.test_eval_sys_version",
      "eval.tests.test_compile.test_compile_with_input_flag",
      "eval.tests.test_advanced_compile.test_compile_diagnostic_format_human",
      "eval.tests.test_compile.test_compile_unicode_content",
      "eval.tests.test_edge_cases.test_compile_invalid_ppi_value",
      "eval.tests.test_compile.test_compile_invalid_syntax",
      "eval.tests.test_eval.test_eval_with_in_flag",
      "eval.tests.test_eval.test_eval_target_html_feature",
      "eval.tests.test_eval.test_eval_with_input_flag",
      "eval.tests.test_info.test_info_human_readable",
      "eval.tests.test_typst_features.test_compile_math_expressions",
      "eval.tests.test_compile.test_compile_diagnostic_format_short",
      "eval.tests.test_typst_features.test_compile_tables",
      "eval.tests.test_typst_features.test_eval_string_operations",
      "eval.tests.test_typst_features.test_eval_dict_operations",
      "eval.tests.test_typst_features.test_compile_error_line_numbers",
      "eval.tests.test_edge_cases.test_compile_very_long_content",
      "eval.tests.test_watch_init.test_init_invalid_template",
      "eval.tests.test_typst_features.test_compile_images_placeholder",
      "tests.test_datetime.test_weekday_all_seven_days",
      "tests.test_datetime.test_repr_date_only",
      "tests.test_compile_advanced.test_input_flag_string_value",
      "tests.test_datetime.test_format_error_missing_component_name",
      "tests.test_datetime.test_time_accessors_all_components",
      "tests.test_compile_basic.test_compile_with_root_absolute_import",
      "tests.test_compile_formats.test_svg_complex_document_with_shapes",
      "tests.test_datetime.test_format_insufficient_information_date_needs_time",
      "tests.test_compile_advanced.test_pdf_standard_16_header_validation",
      "tests.test_compile_formats.test_png_single_page_with_template",
      "tests.test_document_structure.test_list_multiline_items",
      "tests.test_document_structure.test_footnote_reference",
      "tests.test_bibliography.test_bibliography_full_parameter",
      "tests.test_basic.test_compile_simple_pdf",
      "tests.test_bibliography.test_no_bibliography_but_with_citations",
      "tests.test_environment_flags.test_input_flag_with_sys_inputs",
      "tests.test_datetime.test_datetime_equality_with_different_types",
      "tests.test_datetime.test_repr_time_only",
      "tests.test_datetime.test_ordinal_leap_year_dec_31",
      "tests.test_compile_advanced.test_input_flag_empty_value",
      "tests.test_compile_basic.test_compile_with_math_equations",
      "tests.test_datetime.test_invalid_date_feb_29_non_leap_year",
      "tests.test_datetime.test_format_insufficient_information_time_needs_date",
      "tests.test_compile_advanced.test_input_flag_multiple_inputs",
      "tests.test_compile_formats.test_png_and_svg_with_pages_range_complex",
      "tests.test_basic.test_info_command",
      "tests.test_bibliography.test_malformed_bibtex_syntax_error",
      "tests.test_environment_flags.test_multiple_input_flags_accumulate",
      "tests.test_compile_formats.test_png_multipage_zero_padded_template",
      "tests.test_document_structure.test_list_custom_marker",
      "tests.test_document_structure.test_enum_numbering_function",
      "tests.test_compile_advanced.test_deps_json_format_multifile_project",
      "tests.test_datetime.test_repr_full_datetime",
      "tests.test_datetime.test_ordinal_non_leap_year_dec_31",
      "tests.test_datetime.test_full_datetime_comparison_precision",
      "tests.test_datetime.test_invalid_date_month_out_of_range",
      "tests.test_compile_basic.test_compile_with_image",
      "tests.test_compile_advanced.test_timings_file_path_with_directory",
      "tests.test_datetime.test_arithmetic_add_days_to_date",
      "tests.test_bibliography.test_basic_bibtex_citation",
      "tests.test_compile_formats.test_svg_with_pages_selection",
      "tests.test_bibliography.test_missing_bibliography_file_error",
      "tests.test_environment_flags.test_cert_env_only",
      "tests.test_compile_advanced.test_deps_json_with_nested_subdirectories",
      "tests.test_compile_formats.test_png_multipage_complex_template",
      "tests.test_compile_advanced.test_deps_zero_format_null_separated",
      "tests.test_document_structure.test_enum_custom_numbering",
      "tests.test_document_structure.test_list_marker_function",
      "tests.test_datetime.test_negative_year_construction",
      "tests.test_datetime.test_datetime_multiple_incomplete_components_error_message",
      "tests.test_datetime.test_format_year_last_two_digits",
      "tests.test_datetime.test_arithmetic_subtract_days_from_date",
      "tests.test_datetime.test_invalid_date_day_out_of_range",
      "tests.test_bibliography.test_hayagriva_yaml_format",
      "tests.test_compile_basic.test_compile_missing_image_file"
    ],
    "failed_tests_omitted": 946,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 1786,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "typst__typst.88356d0",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "3107584",
    "calls": "54",
    "created_at": "2026-05-17T16:22:20.310337+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "3.8981",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "3287159",
    "instance_id": "typst__typst.88356d0",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "716",
    "n_system_errors": "0",
    "n_tests": "1724",
    "n_warnings": "0",
    "output_tokens": "48215",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "10070",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-typst-typst",
    "run_version": "20260517T094700Z",
    "score": "0.41531322505800466",
    "session_ended_at": "2026-05-17T16:34:20.106Z",
    "session_started_at": "2026-05-17T16:22:23.107Z",
    "test_branch_errors": "{}",
    "total_tokens": "3335374",
    "wall_clock_seconds": "716"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./typst_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-typst-typst",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}