{ "agent_trace": { "codex_logs_available_local_only": true, "raw_logs_published": false }, "collected_at": "2026-05-18T13:25:01.033508+00:00", "docker_cpus": 16, "docker_memory": "30g", "eval": { "error_code": null, "failed_tests": [ "tests.test_basic.test_missing_url_error", "tests.test_debug.test_db_url_option", "tests.test_edge_cases.test_request_count_as_float", "tests.test_errors.test_invalid_regex_url", "tests.test_errors.test_conflicting_body_options", "tests.test_errors.test_invalid_http_version", "tests.test_errors.test_cert_without_key", "tests.test_final.test_request_count_with_m_suffix", "tests.test_request_config.test_query_per_second_rate_limit", "tests.test_request_config.test_duration_mode", "tests.test_final.test_longer_duration", "eval.tests.test_advanced.test_request_count_m_suffix", "eval.tests.test_advanced.test_request_count_decimal", "eval.tests.test_advanced.test_burst_mode", "eval.tests.test_basic.test_request_count_k_suffix", "eval.tests.test_basic.test_duration_based", "eval.tests.test_coverage_boost.test_very_short_duration", "eval.tests.test_coverage_boost.test_burst_default_rate", "eval.tests.test_errors.test_invalid_http_version", "eval.tests.test_errors.test_invalid_url_scheme", "eval.tests.test_errors.test_cert_without_key", "eval.tests.test_errors.test_key_without_cert", "eval.tests.test_errors.test_qps_with_burst", "eval.tests.test_errors.test_invalid_regex_url", "eval.tests.test_errors.test_invalid_connect_to", "eval.tests.test_errors.test_invalid_aws_sigv4_format", "eval.tests.test_more_coverage.test_decimal_k_variations", "tests.test_aws_auth.test_aws_sigv4_query_parameters", "tests.test_aws_auth.test_aws_sigv4_date_format_validation", "tests.test_aws_auth.test_aws_sigv4_missing_credentials", "tests.test_database.test_database_error_invalid_path", "tests.test_database.test_database_with_post_method", "tests.test_client_gaps.test_redirect_absolute_url", "tests.test_errors.test_http_version_conflict_error", "tests.test_client_final.test_tls_cert_key_both_required", "tests.test_errors.test_zero_concurrency_no_requests_made", "tests.test_database.test_run_id_is_unix_timestamp", "tests.test_client_final.test_proxy_invalid_url", "tests.test_client_gaps.test_redirect_with_fragment", "tests.test_aws_auth.test_aws_sigv4_credential_scope_in_auth_header", "tests.test_aws_auth.test_aws_sigv4_basic_signing_s3", "tests.test_aws_auth.test_aws_sigv4_credential_in_auth_header", "tests.test_errors.test_conflicting_aws_auth_requirements", "tests.test_client_gaps.test_redirect_relative_url_resolution", "tests.test_database.test_request_data_persisted_correctly", "tests.test_client_gaps.test_redirect_authority_change", "tests.test_client_easy_wins.test_redirect_relative_url_parse_error", "tests.test_aws_auth.test_aws_sigv4_amz_date_header", "tests.test_aws_auth.test_aws_sigv4_malformed_credentials_format", "tests.test_aws_auth.test_aws_sigv4_multiple_requests", "tests.test_errors.test_invalid_aws_auth_format", "tests.test_harvest_clean.TestBasicRequests.test_setting_content_type_header", "tests.test_database.test_database_with_custom_headers", "tests.test_client_gaps.test_redirect_loop_detection", "tests.test_errors.test_redirect_loop_detected", "tests.test_harvest_clean.TestOutputFile.test_output_to_file", "tests.test_client_easy_wins.test_redirect_authority_change_host_header", "tests.test_errors.test_invalid_http_version", "tests.test_harvest_clean.TestBasicRequests.test_setting_basic_auth", "tests.test_harvest.TestRedirects.test_redirect", "tests.test_aws_auth.test_aws_sigv4_different_services", "tests.test_aws_auth.test_aws_sigv4_long_path", "tests.test_aws_auth.test_aws_sigv4_signed_headers_list", "tests.test_errors.test_http3_not_compiled_in", "tests.test_lib_gaps.test_invalid_aws_sigv4_format_single_field", "tests.test_harvest_clean.TestDisableKeepAlive.test_disable_keepalive", "tests.test_harvest_clean.TestBasicRequests.test_setting_host", "tests.test_client_easy_wins.test_redirect_max_limit", "tests.test_client_gaps.test_redirect_max_limit", "tests.test_harvest.TestGoogle.test_google", "tests.test_errors.test_redirect_chain_exceeds_limit", "tests.test_lib_gaps.test_invalid_connect_to_format_too_few_parts", "tests.test_lib_gaps.test_invalid_aws_sigv4_format_too_many_fields", "tests.test_harvest_clean.TestTimeout.test_connect_timeout", "tests.test_harvest_clean.TestBasicRequests.test_setting_method", "tests.test_aws_auth.test_aws_sigv4_different_regions", "tests.test_aws_auth.test_aws_sigv4_concurrent_requests_different_signatures", "tests.test_aws_auth.test_aws_sigv4_put_method", "tests.test_harvest_clean.TestBasicRequests.test_enable_compression_default", "tests.test_harvest.TestRateLimiting.test_query_limit" ], "failed_tests_omitted": 116, "public_eval_path": "eval.json", "summary_path": "eval-summary.json", "test_branch_errors": {}, "test_records": 1095, "warnings": [] }, "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "instance_id": "hatoo__oha.8dc6349", "metrics": { "almost_resolved": "False", "cached_input_tokens": "6970496", "calls": "107", "created_at": "2026-05-17T11:32:39.250220+00:00", "docker_cpus": "16", "docker_memory": "30g", "error_code": "", "estimated_cost_usd": "6.2126", "evaluator_problem": "False", "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "input_tokens": "7188608", "instance_id": "hatoo__oha.8dc6349", "long_context_calls": "0", "model": "gpt-5.5", "n_resolved_tests": "754", "n_system_errors": "0", "n_tests": "899", "n_warnings": "0", "output_tokens": "54559", "paper_compliant": "False", "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5", "reasoning_effort": "xhigh", "reasoning_output_tokens": "17978", "resolved": "False", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-hatoo-oha", "run_version": "", "score": "0.8387096774193549", "session_ended_at": "2026-05-17T11:49:16.536Z", "session_started_at": "2026-05-17T11:32:41.921Z", "test_branch_errors": "{}", "total_tokens": "7243167", "wall_clock_seconds": "994" }, "model": "gpt-5.5", "package": { "contents": [ ".", "./__pycache__", "./__pycache__/oha_reimpl.cpython-312.pyc", "./compile.sh", "./executable", "./oha_reimpl.py" ], "contents_omitted": 0, "submission_available_local_only": true }, "paper_compliant": false, "paper_mode": false, "reasoning_effort": "xhigh", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-hatoo-oha", "run_version": "", "usage_audit": { "available_local_artifact": true, "public_path": "usage-audit.json" } }