{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:06.062229+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_args_coverage.test_invalid_priority",
      "eval.tests.test_comprehensive_cmdline.test_filter_hash_with_real_hash",
      "eval.tests.test_all_testdata.test_export_all_formats",
      "eval.tests.test_behavioral_strong.test_startday_shortcut",
      "eval.tests.test_behavioral_strong.test_query_appointments_specific_date",
      "eval.tests.test_additional_coverage.test_export_ical_explicit",
      "eval.tests.test_all_testdata.test_limit_with_all_commands",
      "eval.tests.test_additional_coverage.test_range_shortcut",
      "eval.tests.test_all_ical_testdata.test_ical_009_import",
      "eval.tests.test_all_testdata.test_main_apts_file",
      "eval.tests.test_additional_coverage.test_format_apt_with_time_specifiers",
      "eval.tests.test_behavioral_strong.test_from_to_date_range",
      "eval.tests.test_additional_coverage.test_filter_hash_with_prefix",
      "eval.tests.test_comprehensive_coverage.test_calendar_file_option",
      "eval.tests.test_comprehensive_final.test_startday",
      "eval.tests.test_comprehensive_cmdline.test_limit_and_search_combination",
      "eval.tests.test_args_coverage.test_priority_out_of_range_high",
      "eval.tests.test_behavioral_strong.test_query_with_filter_type_cal",
      "eval.tests.test_additional_coverage.test_export_pcal",
      "eval.tests.test_comprehensive_cmdline.test_custom_config_directory_usage",
      "eval.tests.test_behavioral_strong.test_nonexistent_data_directory",
      "eval.tests.test_additional_coverage.test_startday_shortcut",
      "eval.tests.test_all_ical_testdata.test_ical_010_import",
      "eval.tests.test_all_testdata.test_apts_export",
      "eval.tests.test_comprehensive_coverage.test_filter_type_cal_shorthand",
      "eval.tests.test_comprehensive_final.test_query_full_form",
      "eval.tests.test_comprehensive_coverage.test_zero_priority_completed_todos",
      "eval.tests.test_comprehensive_coverage.test_export_pcal_format",
      "eval.tests.test_comprehensive_final.test_custom_data_directory",
      "eval.tests.test_all_testdata.test_export_with_uid",
      "eval.tests.test_args_coverage.test_invalid_limit",
      "eval.tests.test_behavioral_strong.test_format_option_apt_custom",
      "eval.tests.test_comprehensive_cmdline.test_all_query_short_forms_with_test_data",
      "eval.tests.test_all_ical_testdata.test_ical_011_import",
      "eval.tests.test_additional_coverage.test_todo_with_priority",
      "eval.tests.test_comprehensive_cmdline.test_invalid_arguments_produce_errors",
      "eval.tests.test_all_testdata.test_todo_export",
      "eval.tests.test_core_functionality.test_conflicting_options",
      "eval.tests.test_comprehensive_coverage.test_filter_pattern_regex",
      "eval.tests.test_comprehensive_coverage.test_specific_priority_filter",
      "eval.tests.test_comprehensive_coverage.test_grep_with_format_option",
      "eval.tests.test_comprehensive_final.test_query_with_specific_date",
      "eval.tests.test_coverage_boost.test_very_long_descriptions",
      "eval.tests.test_all_testdata.test_export_with_all_filters",
      "eval.tests.test_args_coverage.test_invalid_days",
      "eval.tests.test_behavioral_strong.test_limit_option_restricts_output",
      "eval.tests.test_all_ical_testdata.test_ical_013_import",
      "eval.tests.test_coverage_push.test_recurring_appointment_query",
      "eval.tests.test_comprehensive_cmdline.test_purge_maintains_data_integrity",
      "eval.tests.test_all_testdata.test_event_files",
      "eval.tests.test_comprehensive_coverage.test_input_datefmt_option_2",
      "eval.tests.test_comprehensive_coverage.test_range_with_negative_number",
      "eval.tests.test_comprehensive_coverage.test_format_apt_custom",
      "eval.tests.test_comprehensive_final.test_ical_roundtrip",
      "eval.tests.test_edge_cases_final.test_missing_calendar_file",
      "eval.tests.test_coverage_boost.test_notes_with_items",
      "eval.tests.test_edge_cases_final.test_multiple_exports",
      "eval.tests.test_error_edge_cases.test_malformed_appointment_date",
      "eval.tests.test_comprehensive_coverage.test_format_event_custom",
      "eval.tests.test_coverage_push.test_recurring_event_export",
      "eval.tests.test_behavioral_strong.test_input_datefmt_option",
      "eval.tests.test_comprehensive_coverage.test_input_datefmt_option_3",
      "eval.tests.test_error_edge_cases.test_many_appointments",
      "eval.tests.test_comprehensive_coverage.test_startday_with_specific_date",
      "eval.tests.test_error_edge_cases.test_query_from_to_same_date",
      "eval.tests.test_all_testdata.test_appointment_files",
      "eval.tests.test_core_functionality.test_grep_operation",
      "eval.tests.test_error_paths.test_multiline_appointment_description",
      "eval.tests.test_error_paths.test_multiple_mode_options",
      "eval.tests.test_coverage_push.test_notes_in_appointments",
      "eval.tests.test_error_edge_cases.test_malformed_event_date",
      "eval.tests.test_error_paths.test_calendar_file_with_wrong_extension",
      "eval.tests.test_edge_cases_final.test_import_then_export",
      "eval.tests.test_comprehensive_coverage.test_format_raw_specifier",
      "eval.tests.test_behavioral_strong.test_output_datefmt_option",
      "eval.tests.test_comprehensive_coverage.test_input_datefmt_option_4",
      "eval.tests.test_coverage_push.test_format_duration_seconds",
      "eval.tests.test_error_edge_cases.test_special_characters_in_description",
      "eval.tests.test_core_functionality.test_export_ical_explicit",
      "eval.tests.test_error_paths.test_corrupted_apts_file"
    ],
    "failed_tests_omitted": 367,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 1994,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "lfos__calcurse.49180d5",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "4663552",
    "calls": "62",
    "created_at": "2026-05-17T12:34:19.468996+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "5.4309",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "5021197",
    "instance_id": "lfos__calcurse.49180d5",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "489",
    "n_system_errors": "0",
    "n_tests": "666",
    "n_warnings": "0",
    "output_tokens": "43698",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "11608",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-lfos-calcurse",
    "run_version": "20260517T094700Z",
    "score": "0.7342342342342343",
    "session_ended_at": "2026-05-17T12:46:26.354Z",
    "session_started_at": "2026-05-17T12:34:22.526Z",
    "test_branch_errors": "{}",
    "total_tokens": "5064895",
    "wall_clock_seconds": "723"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./calcurse.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-lfos-calcurse",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
