{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:00.177678+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_age_advanced.TestDuplicates.test_duplicate_identity_file_warns",
      "eval.tests.test_age_advanced.TestDuplicates.test_duplicate_recipient_warns",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_encrypt_decrypt",
      "eval.tests.test_age_coverage_boost.TestRSAFullRoundtrip.test_encrypt_to_rsa_decrypt_with_identity",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_decrypt_with_d_flag",
      "eval.tests.test_age_coverage_boost.TestPostQuantumRoundtrip.test_encrypt_decrypt_pq_roundtrip",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_inspect_shows_scrypt",
      "eval.tests.test_age_basic.TestSSHKeys.test_encrypt_decrypt_with_ed25519_ssh_key",
      "eval.tests.test_age_basic.TestOutputFile.test_input_output_same_file_rejected",
      "eval.tests.test_age_coverage_boost.TestPostQuantumRoundtrip.test_pq_wrong_key_fails",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_decrypt_with_armor_flag_fails",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_decrypt_with_recipients_file_flag_fails",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_identity_with_passphrase_fails",
      "eval.tests.test_age_coverage_boost.TestInspectPostQuantumAndMultiple.test_inspect_multiple_recipient_types",
      "eval.tests.test_age_identity_files.TestEncryptedIdentityFile.test_key_encrypted_identity_file_fails_with_helpful_error",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_encrypt_to_file",
      "eval.tests.test_age_advanced.TestDuplicates.test_duplicate_recipients_file_warns",
      "eval.tests.test_age_coverage_boost.TestRSAFullRoundtrip.test_rsa_wrong_key_decrypt_fails",
      "eval.tests.test_age_coverage_boost.TestRSAFullRoundtrip.test_encrypt_decrypt_rsa_roundtrip",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_empty_data",
      "eval.tests.test_age_basic.TestSSHKeys.test_encrypt_to_ssh_pubkey_inline",
      "eval.tests.test_age_coverage_boost.TestPostQuantumRoundtrip.test_pq_encrypt_to_identity",
      "eval.tests.test_age_identity_files.TestRecipientsFileParsing.test_recipients_file_with_ssh_pubkeys",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_decrypt_with_passphrase_flag_fails",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_passphrase_with_recipient_fails",
      "eval.tests.test_age_inspect.TestInspectBasic.test_inspect_postquantum",
      "eval.tests.test_age_parse_edge_cases.TestRecipientsFileEdgeCases.test_recipients_file_age_identity_in_file_error",
      "eval.tests.test_age_parse_edge_cases.TestRecipientsFileEdgeCases.test_recipients_file_no_recipients_error",
      "eval.tests.test_age_parse_edge_cases.TestRecipientsFileEdgeCases.test_identity_file_with_recipient_key_error",
      "eval.tests.test_age_identity_files.TestEncryptedIdentityFile.test_armored_identity_file",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_too_many_args_second_is_flag_hint",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_armored_encrypt_decrypt",
      "eval.tests.test_age_coverage_boost.TestRSAFullRoundtrip.test_rsa_armored_roundtrip",
      "eval.tests.test_age_identity_files.TestSSHIdentityParsing.test_ed25519_pem_parsed_correctly",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_max_work_factor",
      "eval.tests.test_age_coverage_boost.TestPostQuantumRoundtrip.test_pq_armored_roundtrip",
      "eval.tests.test_age_identity_files.TestRecipientsFileParsing.test_recipients_file_invalid_key_error",
      "eval.tests.test_age_ssh_keys.TestSSHEd25519.test_encrypt_to_ed25519_pubkey_file",
      "eval.tests.test_age_ssh_keys.TestSSHEd25519.test_encrypt_with_ed25519_identity",
      "eval.tests.test_age_error_paths.TestFlagConflicts.test_passphrase_with_recipients_file_fails",
      "eval.tests.test_age_ssh_keys.TestSSHEd25519.test_encrypt_to_ed25519_pubkey_inline",
      "eval.tests.test_age_ssh_keys.TestRSASSHKey.test_encrypt_to_rsa_pubkey_inline",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_parse_short_key",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tagpq_recipient_parse_invalid",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_encrypt_to_valid_key",
      "eval.tests.test_age_batchpass.TestBatchpassBasic.test_batchpass_wrong_password_fails",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_inspect",
      "eval.tests.test_age_coverage_boost.TestRSAFullRoundtrip.test_rsa_inspect_shows_ssh_rsa_stanza",
      "eval.tests.test_age_targeted_coverage.TestEncryptedIdentityFile.test_encrypt_to_encrypted_identity",
      "eval.tests.test_age_parse_edge_cases.TestIdentityFileEdgeCases.test_hybrid_identity_file",
      "eval.tests.test_age_coverage_boost.TestPostQuantumRoundtrip.test_pq_inspect_shows_mlkem_stanza",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_multiple_encrypt",
      "eval.tests.test_age_targeted_coverage.TestSSHPassphraseKeys.test_ssh_rsa_passphrase_protected_key",
      "eval.tests.test_age_ssh_keys.TestSSHEd25519.test_wrong_ed25519_key_fails_decrypt",
      "eval.tests.test_age_ssh_keys.TestSSHEd25519.test_ed25519_inspect_shows_ssh_stanza",
      "eval.tests.test_age_ssh_keys.TestSSHKeyEncryptDecryptRoundtrip.test_ed25519_roundtrip_with_various_data",
      "eval.tests.test_age_ssh_keys.TestSSHKeyEncryptDecryptRoundtrip.test_ed25519_armor_roundtrip",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_parse_invalid_format",
      "eval.tests.test_age_targeted_coverage.TestSSHPassphraseKeys.test_ssh_ed25519_old_format_no_pub",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_to_file",
      "eval.tests.test_age_targeted_coverage.TestDecryptPassphrasePaths.test_decrypt_passphrase_file_with_identity_gives_error",
      "eval.tests.test_age_targeted_coverage.TestDecryptPassphrasePaths.test_decrypt_non_passphrase_file_without_identities",
      "eval.tests.test_age_targeted_coverage.TestRecipientFileEdgeCases.test_recipients_file_with_non_utf8",
      "eval.tests.test_age_targeted_coverage.TestMultipleIdentityTypes.test_encrypt_with_rsa_identity",
      "eval.tests.test_age_targeted_coverage.TestMultipleIdentityTypes.test_encrypt_with_ed25519_identity",
      "eval.tests.test_age_targeted_coverage.TestWarnDuplicates.test_duplicate_recipients_warning",
      "eval.tests.test_age_targeted_coverage.TestJFlag.test_j_flag_for_decrypt",
      "eval.tests.test_age_targeted_coverage.TestSSHPassphraseKeys.test_ssh_ed25519_passphrase_protected_key",
      "eval.tests.test_age_targeted_coverage.TestIdentityFileTypes.test_identity_file_empty_gives_no_identities_error",
      "eval.tests.test_age_targeted_coverage.TestAbsPath.test_same_input_output_file_error",
      "eval.tests.test_age_targeted_coverage.TestRecipientParseEdgeCases.test_github_recipient_gives_clear_error",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_encrypt_armored",
      "eval.tests.test_age_targeted_coverage.TestTagRecipients.test_tag_recipient_inspect_json",
      "eval.tests.test_age_targeted_coverage.TestWarnDuplicates.test_duplicate_identities_warning",
      "eval.tests.test_age_targeted_coverage.TestWarnDuplicates.test_duplicate_recipients_file_warning",
      "eval.tests.test_age_targeted_coverage.TestRecipientParseEdgeCases.test_ssh_rsa_recipient_from_file",
      "eval.tests.test_age_targeted_coverage.TestTagRecipientsFile.test_tag_recipient_in_recipients_file",
      "eval.tests.test_age_targeted_coverage.TestRecipientFileEdgeCases.test_recipients_file_with_too_long_line",
      "eval.tests.test_age_targeted_coverage.TestRecipientFileEdgeCases.test_recipients_file_with_unsupported_ssh_key_type",
      "eval.tests.test_age_targeted_coverage.TestMultipleRecipientTypes.test_x25519_and_ssh_ed25519_roundtrip"
    ],
    "failed_tests_omitted": 335,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 839,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "filosottile__age.706dfc1",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "12300672",
    "calls": "113",
    "created_at": "2026-05-17T11:07:53.656730+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "9.8259",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "12553670",
    "instance_id": "filosottile__age.706dfc1",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "305",
    "n_system_errors": "0",
    "n_tests": "676",
    "n_warnings": "0",
    "output_tokens": "80351",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "20734",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-filosottile-age",
    "run_version": "",
    "score": "0.4511834319526627",
    "session_ended_at": "2026-05-17T11:32:02.297Z",
    "session_started_at": "2026-05-17T11:07:56.852Z",
    "test_branch_errors": "{}",
    "total_tokens": "12634021",
    "wall_clock_seconds": "1445"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./__pycache__",
      "./__pycache__/age_cli.cpython-312.pyc",
      "./age_cli.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-filosottile-age",
  "run_version": "",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
