{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:07.406166+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_basic.test_warning_list",
      "eval.tests.test_basic.test_debug_list",
      "eval.tests.test_basic.test_help_flag",
      "eval.tests.test_error_handling.test_circular_dependency",
      "eval.tests.test_more_subtools.test_warning_phonycycle_err",
      "eval.tests.test_basic.test_help_short_flag",
      "tests.test_comprehensive_quality.test_help_output_completeness",
      "tests.test_absolute_final.test_phony_cycle_warning",
      "tests.test_absolute_70.test_circular_dependency_detection",
      "tests.test_advanced_features.test_targets_source_list",
      "tests.test_basic_invocation.test_debug_list_flag",
      "tests.test_build_scenarios.test_build_failure_with_keep_going",
      "tests.test_comprehensive_quality.test_build_specific_target",
      "tests.test_dyndep.test_dyndep_version_required",
      "tests.test_absolute_final.test_target_depends_on_itself",
      "tests.test_basic_invocation.test_warning_list_flag",
      "tests.test_edge_cases.test_circular_dependency",
      "tests.test_push_coverage_70.test_ninja_version_greater_than_required",
      "tests.test_push_to_70.test_help_output_detailed",
      "tests.test_util_functions.test_circular_dependency_detection",
      "tests.test_util_functions.test_self_referential_edge",
      "tests.test_version_checking.test_ninja_required_version_future_major",
      "tests.test_basic_invocation.test_invalid_debug_mode",
      "tests.test_dependencies.test_dyndep_variable_binding_error",
      "tests.test_dependencies.test_dyndep_unsupported_version_error",
      "tests.test_depfile.test_escaped_colon_no_whitespace",
      "tests.test_clean.test_clean_multiple_unknown_rules",
      "tests.test_clparser.test_msvc_deps_multiple_outputs",
      "tests.test_basic.test_help",
      "tests.test_build_log.test_log_version_too_new_triggers_rebuild",
      "tests.test_debug_modes.test_stats_with_parallel_builds",
      "tests.test_clean.test_clean_mixed_valid_and_invalid_targets",
      "tests.test_debug_modes.test_explain_mode_shows_why_file_modified",
      "tests.test_build_execution.test_multiple_rules_same_name_error",
      "tests.test_dependencies.test_depfile_multiple_outputs",
      "tests.test_build_execution.test_keep_going_on_error",
      "tests.test_build_execution.test_unknown_target_error",
      "tests.test_build_log.test_recompact_removes_duplicate_entries",
      "tests.test_browse.test_browse_custom_port",
      "tests.test_clean.test_clean_empty_target_name_error",
      "tests.test_depfile.test_carriage_return_continuation",
      "tests.test_basic.test_debug_mode_list",
      "tests.test_clparser.test_msvc_deps_crlf_line_endings",
      "tests.test_dependencies.test_dyndep_edge_not_in_manifest_error",
      "tests.test_debug_modes.test_explain_mode_shows_dependency_chain",
      "tests.test_clparser.test_msvc_deps_basic_include_extraction",
      "tests.test_build_execution.test_circular_dependency_detection",
      "tests.test_debug_modes.test_explain_mode_shows_why_output_missing",
      "tests.test_build_execution.test_validation_edge",
      "tests.test_depfile.test_windows_drive_letter_path",
      "tests.test_clean.test_clean_verbose_mode_with_depfiles",
      "tests.test_dependencies.test_dyndep_no_version_error",
      "tests.test_dependencies.test_dyndep_missing_file_error",
      "tests.test_basic.test_warning_list",
      "tests.test_depfile.test_odd_backslashes_before_space",
      "tests.test_clean.test_clean_specific_target_leaves_others",
      "tests.test_clparser.test_msvc_deps_custom_prefix",
      "tests.test_depfile.test_dollar_sign_escaping",
      "tests.test_clparser.test_msvc_deps_empty_output",
      "tests.test_debug_modes.test_explain_mode_shows_why_rule_changed",
      "tests.test_build_log.test_log_version_too_old_triggers_rebuild",
      "tests.test_debug_modes.test_stats_mode_shows_all_metrics_types",
      "tests.test_depfile.test_unicode_filenames",
      "tests.test_depfile.test_colon_in_middle_of_dependency",
      "tests.test_build_log.test_corrupted_log_handled_gracefully",
      "tests.test_clean.test_clean_with_multiple_depfiles",
      "tests.test_dependencies.test_depfile_missing_colon_error",
      "tests.test_depfile.test_even_backslashes_before_space",
      "tests.test_browse.test_browse_help",
      "tests.test_disk_interface.test_stat_error_with_filename_too_long",
      "tests.test_depfile.test_backslash_colon_not_at_end",
      "tests.test_clparser.test_msvc_deps_with_leading_spaces",
      "tests.test_clean.test_clean_verbose_with_rule_filtering",
      "tests.test_clparser.test_msvc_deps_various_file_extensions",
      "tests.test_depfile.test_early_newline_and_whitespace",
      "tests.test_elide.test_elide_middle_width_40_long_filename",
      "tests.test_debug_modes.test_multiple_targets_with_explain",
      "tests.test_depfile.test_multiple_continuation_lines",
      "tests.test_debug_modes.test_multiple_debug_modes_stats_and_explain",
      "tests.test_elide.test_elide_middle_short_string_narrow_terminal"
    ],
    "failed_tests_omitted": 338,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 1905,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "ninja-build__ninja.cc60300",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "8894848",
    "calls": "129",
    "created_at": "2026-05-17T13:23:26.802458+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "7.2844",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "9108269",
    "instance_id": "ninja-build__ninja.cc60300",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "1045",
    "n_system_errors": "0",
    "n_tests": "1438",
    "n_warnings": "0",
    "output_tokens": "58997",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "21995",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-ninja-build-ninja",
    "run_version": "20260517T094700Z",
    "score": "0.7267037552155772",
    "session_ended_at": "2026-05-17T13:44:31.074Z",
    "session_started_at": "2026-05-17T13:23:30.764Z",
    "test_branch_errors": "{}",
    "total_tokens": "9167266",
    "wall_clock_seconds": "1260"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./ninja.py"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-ninja-build-ninja",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
