{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:06.941848+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_dropbear_cli.test_invalid_port_non_numeric",
      "eval.tests.test_dropbear_cli.test_multiple_ports",
      "eval.tests.test_dropbear_cli.test_address_port_format",
      "eval.tests.test_dropbear_cli.test_pid_file_creation",
      "eval.tests.test_dropbear_cli.test_foreground_mode",
      "eval.tests.test_dropbear_cli.test_receive_window_buffer_option",
      "eval.tests.test_dropbear_cli.test_receive_window_buffer_invalid",
      "eval.tests.test_dropbear_cli.test_keepalive_option",
      "eval.tests.test_dropbear_cli.test_keepalive_zero_disables",
      "eval.tests.test_dropbear_cli.test_disable_qos_flag",
      "eval.tests.test_dropbear_cli.test_disable_root_login_flag",
      "eval.tests.test_dropbear_cli.test_disable_password_logins_flag",
      "eval.tests.test_dropbear_cli.test_disable_root_password_flag",
      "eval.tests.test_dropbear_cli.test_allow_blank_password_flag",
      "eval.tests.test_dropbear_cli.test_two_factor_auth_flag",
      "eval.tests.test_dropbear_cli.test_max_auth_tries_option",
      "eval.tests.test_dropbear_cli.test_max_auth_tries_invalid",
      "eval.tests.test_dropbear_cli.test_disable_local_port_forwarding",
      "eval.tests.test_dropbear_cli.test_disable_remote_port_forwarding",
      "eval.tests.test_dropbear_cli.test_allow_forwarded_ports_from_any_host",
      "eval.tests.test_dropbear_cli.test_forced_command_option",
      "eval.tests.test_dropbear_cli.test_motd_disabled_flag",
      "eval.tests.test_dropbear_cli.test_pass_environment_flag",
      "eval.tests.test_dropbear_cli.test_restrict_group_option",
      "eval.tests.test_dropbear_cli.test_authorized_keys_directory_option",
      "eval.tests.test_dropbear_cli.test_interface_binding_option",
      "eval.tests.test_dropbear_cli.test_inetd_mode_flag",
      "eval.tests.test_dropbear_cli.test_multiple_hostkey_files",
      "eval.tests.test_dropbear_cli.test_combination_of_flags",
      "tests.test_03_error_handling.test_unreadable_hostkey",
      "tests.test_03_error_handling.test_empty_forced_command",
      "tests.test_03_error_handling.test_string_too_long_error",
      "tests.test_08_server_with_real_keys.test_server_starts_with_ed25519_key",
      "tests.test_08_server_with_real_keys.test_server_responds_with_ssh_banner",
      "tests.test_08_server_with_real_keys.test_server_starts_with_ecdsa_key",
      "tests.test_08_server_with_real_keys.test_server_with_banner_file",
      "tests.test_08_server_with_real_keys.test_server_multiple_connections",
      "tests.test_08_server_with_real_keys.test_server_with_all_options",
      "tests.test_08_server_with_real_keys.test_server_starts_with_rsa_key",
      "tests.test_08_server_with_real_keys.test_server_pid_file_with_real_key",
      "tests.test_08_server_with_real_keys.test_server_with_multiple_key_types",
      "tests.test_09_ssh_protocol.test_server_handles_sigterm",
      "tests.test_auth_options.test_combined_w_and_g_flags",
      "tests.test_authkey_options_gap.test_no_pty_option_blocks_pty_allocation",
      "tests.test_authkey_options_gap.test_malformed_command_unclosed_quote",
      "tests.test_auth_options.test_D_flag_empty_string",
      "tests.test_auth_options.test_multiple_r_flags_valid",
      "tests.test_command_exec.test_forced_command_multiple_c_flags_last_wins",
      "tests.test_auth_dispatcher_gap.test_group_restriction_nonmember_rejected",
      "tests.test_auth_dispatcher_gap.test_max_auth_tries_exceeded_valid_user",
      "tests.test_algo_gap.test_server_client_cipher_negotiation_success",
      "tests.test_ecdsa_gap.test_ecdsa_nistp256_key_exchange",
      "tests.test_dbutil_gap.test_very_large_banner_file",
      "tests.test_channels.test_channel_burst_then_idle",
      "tests.test_channels.test_channel_extended_data_stderr",
      "tests.test_environment_motd.test_basic_env_vars_always_set",
      "tests.test_authkey_options_gap.test_no_port_forwarding_parsed",
      "tests.test_authkey_options_gap.test_malformed_permitopen_missing_colon",
      "tests.test_auth_options.test_combined_w_and_B_flags",
      "tests.test_auth_options.test_w_flag_disallow_root_login",
      "tests.test_authkey_options_gap.test_forced_command_basic",
      "tests.test_dbutil_gap.test_banner_file_missing_warning",
      "tests.test_channels.test_channel_early_data_before_ready",
      "tests.test_channels.test_channel_close_without_eof",
      "tests.test_auth_dispatcher_gap.test_combined_flags_password_and_root_disabled",
      "tests.test_auth_dispatcher_gap.test_max_auth_tries_exceeded_invalid_user",
      "tests.test_environment_motd.test_env_no_pass_on_clears_environment",
      "tests.test_ecdsa_gap.test_ecdsa_nistp384_key_exchange",
      "tests.test_auth_options.test_combined_g_and_B_flags",
      "tests.test_authkey_options_gap.test_permitopen_single_destination",
      "tests.test_authkey_options_gap.test_malformed_permitopen_non_numeric_port",
      "tests.test_auth_options.test_g_flag_disable_root_password",
      "tests.test_algo_gap.test_server_client_cipher_negotiation_with_preference_order",
      "tests.test_authkey_options_gap.test_forced_command_with_escaped_quotes",
      "tests.test_dbutil_gap.test_banner_file_with_control_characters",
      "tests.test_environment_motd.test_ssh_tty_set_for_pty_session",
      "tests.test_channels.test_channel_partial_packet_assembly",
      "tests.test_channels.test_channel_simultaneous_bidirectional_data",
      "tests.test_environment_motd.test_ssh_connection_format",
      "tests.test_circbuffer.test_cbuf_multiple_wrap_cycles"
    ],
    "failed_tests_omitted": 431,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 1075,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "mkj__dropbear.75f699b",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "2528512",
    "calls": "54",
    "created_at": "2026-05-17T13:02:11.940469+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "3.0178",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "2691324",
    "instance_id": "mkj__dropbear.75f699b",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "329",
    "n_system_errors": "0",
    "n_tests": "678",
    "n_warnings": "0",
    "output_tokens": "31315",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "10906",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-mkj-dropbear",
    "run_version": "20260517T094700Z",
    "score": "0.48525073746312686",
    "session_ended_at": "2026-05-17T13:11:34.749Z",
    "session_started_at": "2026-05-17T13:02:15.111Z",
    "test_branch_errors": "{}",
    "total_tokens": "2722639",
    "wall_clock_seconds": "559"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./dropbear_compat.c",
      "./executable"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-mkj-dropbear",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
