{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:11.935087+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_argument_parsing.test_client_upload_size_formats",
      "eval.tests.test_argument_parsing.test_client_custom_host",
      "eval.tests.test_argument_parsing.test_server_buffer_size_with_M",
      "eval.tests.test_argument_parsing.test_server_buffer_size_plain_number",
      "eval.tests.test_advanced_options.test_server_with_initial_rtt",
      "eval.tests.test_advanced_options.test_server_with_multiple_options",
      "eval.tests.test_advanced_options.test_server_with_cubic_congestion",
      "eval.tests.test_advanced_options.test_server_with_stream_receive_window",
      "eval.tests.test_argument_parsing.test_server_buffer_size_with_G",
      "eval.tests.test_argument_parsing.test_server_buffer_size_with_k",
      "eval.tests.test_advanced_options.test_server_with_receive_window",
      "eval.tests.test_advanced_options.test_server_with_max_udp_payload_size",
      "eval.tests.test_advanced_options.test_server_with_bbr_congestion",
      "eval.tests.test_config_application.test_server_with_initial_mtu_config",
      "eval.tests.test_config_application.test_server_applies_ack_frequency",
      "eval.tests.test_config_application.test_server_applies_initial_rtt",
      "eval.tests.test_argument_parsing.test_server_buffer_size_with_T",
      "eval.tests.test_config_application.test_server_with_recv_buffer_config",
      "eval.tests.test_advanced_options.test_server_with_send_window",
      "eval.tests.test_advanced_options.test_server_with_new_reno_congestion",
      "eval.tests.test_integration.test_server_starts_and_binds",
      "eval.tests.test_integration.test_server_keylog_flag",
      "eval.tests.test_config_application.test_server_with_max_udp_payload_config",
      "eval.tests.test_config_application.test_server_with_window_configs",
      "eval.tests.test_integration.test_server_with_custom_buffer_sizes",
      "eval.tests.test_integration.test_server_no_protection_flag",
      "eval.tests.test_integration.test_client_connects_to_server",
      "eval.tests.test_config_application.test_client_applies_congestion_cubic",
      "eval.tests.test_config_application.test_client_applies_congestion_new_reno",
      "eval.tests.test_integration.test_server_with_qlog",
      "eval.tests.test_real_connections.test_actual_data_transfer",
      "eval.tests.test_integration.test_server_with_conn_stats_flag",
      "eval.tests.test_integration.test_server_ack_frequency_flag",
      "eval.tests.test_config_application.test_client_applies_congestion_bbr",
      "eval.tests.test_config_application.test_server_with_send_buffer_config",
      "eval.tests.test_special_features.test_server_with_no_protection",
      "eval.tests.test_special_features.test_server_with_custom_mtu",
      "eval.tests.test_special_features.test_client_with_custom_download_and_upload_sizes",
      "eval.tests.test_special_features.test_server_with_custom_max_udp_payload",
      "eval.tests.test_advanced.test_server_generates_self_signed_cert",
      "eval.tests.test_advanced.test_client_large_download_size",
      "eval.tests.test_advanced.test_client_with_local_addr_ipv4",
      "eval.tests.test_advanced.test_client_with_custom_interval",
      "eval.tests.test_coverage_boost.test_client_with_initial_rtt",
      "eval.tests.test_coverage_boost.test_client_with_cubic_congestion",
      "eval.tests.test_coverage_boost.test_client_with_stream_receive_window",
      "eval.tests.test_coverage_boost.test_client_with_new_reno_congestion",
      "eval.tests.test_coverage_boost.test_client_with_bbr_congestion",
      "eval.tests.test_coverage_boost.test_ipv6_socket_configuration",
      "eval.tests.test_coverage_boost.test_server_with_qlog",
      "eval.tests.test_coverage_boost.test_combined_transport_options",
      "eval.tests.test_coverage_boost.test_client_with_qlog",
      "eval.tests.test_advanced.test_server_with_keylog_env_var",
      "eval.tests.test_advanced.test_client_with_conn_stats",
      "eval.tests.test_advanced.test_client_large_upload_size",
      "eval.tests.test_coverage_boost.test_client_with_many_uni_streams",
      "eval.tests.test_advanced.test_client_with_ip_override",
      "eval.tests.test_coverage_boost.test_actual_G_suffix_parsing",
      "eval.tests.test_coverage_boost.test_client_with_ack_frequency",
      "eval.tests.test_coverage_boost.test_size_parsing_with_G_suffix",
      "eval.tests.test_coverage_boost.test_size_parsing_with_T_suffix",
      "eval.tests.test_coverage_boost.test_client_with_receive_window",
      "eval.tests.test_coverage_boost.test_client_with_json_output_to_stdout",
      "eval.tests.test_coverage_boost.test_client_with_json_output_to_file",
      "eval.tests.test_coverage_boost.test_client_with_send_window",
      "eval.tests.test_coverage_boost.test_client_with_keylog",
      "eval.tests.test_integration.test_server_with_no_protection_flag",
      "eval.tests.test_integration.test_server_with_custom_buffer_sizes",
      "eval.tests.test_integration.test_client_server_basic_connection",
      "eval.tests.test_integration.test_server_with_congestion_cubic",
      "eval.tests.test_integration.test_server_starts_with_defaults",
      "eval.tests.test_integration.test_server_with_congestion_new_reno",
      "eval.tests.test_coverage_boost.test_client_with_many_bi_streams",
      "eval.tests.test_coverage_boost.test_client_mixed_uni_and_bi_requests",
      "eval.tests.test_coverage_boost.test_client_with_very_small_downloads",
      "eval.tests.test_integration.test_server_with_initial_mtu",
      "eval.tests.test_coverage_boost.test_client_with_various_interval_settings",
      "eval.tests.test_coverage_boost.test_server_and_client_with_all_transport_options",
      "eval.tests.test_coverage_boost.test_client_with_large_concurrent_streams",
      "eval.tests.test_integration.test_server_with_max_udp_payload_size"
    ],
    "failed_tests_omitted": 191,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 599,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "quinn-rs__quinn.bb359cc",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "2437376",
    "calls": "54",
    "created_at": "2026-05-17T14:21:13.964247+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "2.6388",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "2536664",
    "instance_id": "quinn-rs__quinn.bb359cc",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "288",
    "n_system_errors": "0",
    "n_tests": "522",
    "n_warnings": "0",
    "output_tokens": "30789",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "9486",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-quinn-rs-quinn",
    "run_version": "20260517T094700Z",
    "score": "0.5517241379310345",
    "session_ended_at": "2026-05-17T14:30:40.948Z",
    "session_started_at": "2026-05-17T14:21:16.948Z",
    "test_branch_errors": "{}",
    "total_tokens": "2567453",
    "wall_clock_seconds": "564"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./quinn_perf.py"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-quinn-rs-quinn",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
