{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:01.264798+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_additional_features.test_combined_options",
      "eval.tests.test_animation.test_duration_numeric",
      "eval.tests.test_additional_features.test_format_and_color_combination",
      "eval.tests.test_additional_features.test_no_preprocess_with_high_colors",
      "eval.tests.test_additional_features.test_relative_positioning",
      "eval.tests.test_additional_features.test_polite_mode_combinations",
      "eval.tests.test_additional_features.test_color_extractors_with_quantization",
      "eval.tests.test_additional_features.test_different_alignments",
      "eval.tests.test_additional_features.test_all_symbol_classes",
      "eval.tests.test_colors.test_colors_none",
      "eval.tests.test_basic_invocation.test_verbose_flag",
      "eval.tests.test_animation.test_duration_zero",
      "eval.tests.test_colors.test_colors_2",
      "eval.tests.test_colors.test_fg_color",
      "eval.tests.test_colors.test_color_space_rgb",
      "eval.tests.test_additional_features.test_passthrough_modes",
      "eval.tests.test_additional_features.test_optimization_with_different_formats",
      "eval.tests.test_additional_features.test_various_scales",
      "eval.tests.test_colors.test_colors_16_8",
      "eval.tests.test_additional_features.test_dither_with_different_grains",
      "eval.tests.test_additional_features.test_preprocess_with_low_colors",
      "eval.tests.test_colors.test_color_extractor_average",
      "eval.tests.test_additional_features.test_fill_classes",
      "eval.tests.test_colors.test_colors_8",
      "eval.tests.test_colors.test_color_space_din99d",
      "eval.tests.test_colors.test_dither_none",
      "eval.tests.test_colors.test_fg_color_hex",
      "eval.tests.test_colors.test_preprocess_on",
      "eval.tests.test_colors.test_colors_full",
      "eval.tests.test_edge_cases.test_very_small_font_ratio",
      "eval.tests.test_edge_cases.test_dither_intensity_zero",
      "eval.tests.test_colors.test_dither_diffusion",
      "eval.tests.test_colors.test_threshold",
      "eval.tests.test_colors.test_dither_grain",
      "eval.tests.test_colors.test_colors_240",
      "eval.tests.test_colors.test_preprocess_off",
      "eval.tests.test_colors.test_color_extractor_median",
      "eval.tests.test_colors.test_dither_ordered",
      "eval.tests.test_colors.test_invert",
      "eval.tests.test_colors.test_colors_16",
      "eval.tests.test_colors.test_bg_color",
      "eval.tests.test_edge_cases.test_negative_size_works",
      "eval.tests.test_edge_cases.test_negative_threads",
      "eval.tests.test_edge_cases.test_symbols_range",
      "eval.tests.test_edge_cases.test_narrow_symbols",
      "eval.tests.test_edge_cases.test_very_large_font_ratio",
      "eval.tests.test_edge_cases.test_dither_intensity_very_high",
      "eval.tests.test_colors.test_dither_intensity",
      "eval.tests.test_colors.test_dither_noise",
      "eval.tests.test_edge_cases.test_very_large_size",
      "eval.tests.test_edge_cases.test_wide_symbols",
      "eval.tests.test_colors.test_colors_256",
      "eval.tests.test_colors.test_bg_color_hex",
      "eval.tests.test_edge_cases.test_multiple_images_with_durations",
      "eval.tests.test_input_handling.test_single_image",
      "eval.tests.test_input_handling.test_webp_loader",
      "eval.tests.test_input_handling.test_xwd_loader",
      "eval.tests.test_input_handling.test_jpeg_loader",
      "eval.tests.test_optimization.test_relative_off",
      "eval.tests.test_optimization.test_passthrough_none",
      "eval.tests.test_optimization.test_optimize_levels",
      "eval.tests.test_optimization.test_passthrough_auto",
      "eval.tests.test_input_handling.test_files0_option_stdin",
      "eval.tests.test_optimization.test_relative_on",
      "eval.tests.test_input_handling.test_png_loader",
      "eval.tests.test_input_handling.test_tiff_loader",
      "eval.tests.test_optimization.test_optimize_5",
      "eval.tests.test_input_handling.test_stdin_input",
      "eval.tests.test_input_handling.test_files_option_stdin",
      "eval.tests.test_optimization.test_passthrough_tmux",
      "eval.tests.test_optimization.test_polite_off",
      "eval.tests.test_optimization.test_passthrough_screen",
      "eval.tests.test_optimization.test_optimize_9",
      "eval.tests.test_probing.test_probe_timeout",
      "eval.tests.test_optimization.test_optimize_0",
      "eval.tests.test_optimization.test_polite_on",
      "eval.tests.test_resources.test_threads_1",
      "eval.tests.test_output_formats.test_format_symbols",
      "eval.tests.test_output_formats.test_format_default",
      "eval.tests.test_output_formats.test_format_sixels"
    ],
    "failed_tests_omitted": 2263,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 2768,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "hpjansson__chafa.dd4d4c1",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "6701312",
    "calls": "94",
    "created_at": "2026-05-17T22:47:29.473594+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "5.8527",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "6854312",
    "instance_id": "hpjansson__chafa.dd4d4c1",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "317",
    "n_system_errors": "0",
    "n_tests": "1931",
    "n_warnings": "0",
    "output_tokens": "57902",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "16050",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-hpjansson-chafa-attempt-3",
    "run_version": "20260517T094700Z",
    "score": "0.1641636457793889",
    "session_ended_at": "2026-05-17T23:05:11.362Z",
    "session_started_at": "2026-05-17T22:47:32.521Z",
    "test_branch_errors": "{}",
    "total_tokens": "6912214",
    "wall_clock_seconds": "1058"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./chafa.py",
      "./compile.sh",
      "./executable"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-hpjansson-chafa-attempt-3",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
