{ "agent_trace": { "codex_logs_available_local_only": true, "raw_logs_published": false }, "collected_at": "2026-05-18T13:25:06.511697+00:00", "docker_cpus": 16, "docker_memory": "30g", "eval": { "error_code": null, "failed_tests": [ "tests.test_basic_invocation.test_version_flag_equivalence", "tests.test_additional_coverage.test_package_with_build_error", "tests.test_display_options.test_failed_tests_always_shown", "tests.test_basic_invocation.test_version_flag_version", "tests.test_edge_cases.test_multiple_packages_mixed_results", "tests.test_failure_details.test_failure_with_stack_trace", "tests.test_follow_mode.test_follow_flag_prints_raw_output", "tests.test_failure_details.test_failure_details_shown", "tests.test_follow_mode.test_follow_output_writes_to_file", "tests.test_failure_details.test_subtest_failure_shown", "tests.test_package_summary.test_package_summary_failed_package", "tests.test_panic_handling.test_multiple_panics", "tests.test_panic_handling.test_panic_detection", "tests.test_progress_mode.test_progress_with_failed_package", "tests.test_panic_handling.test_panic_with_stack_trace", "tests.test_real_testdata.test_failed_test_01", "tests.test_real_testdata.test_race_testdata", "tests.test_failure_details.test_failure_output_formatting", "tests.test_failure_details.test_multiple_failures_shown", "tests.test_real_testdata.test_panic_testdata", "tests.test_real_testdata.test_cover_testdata", "eval.tests.test_edge_cases.test_skip_with_coverage_data", "eval.tests.test_basic_invocation.test_version_flag_long", "eval.tests.test_follow_mode.test_follow_verbose_flag", "eval.tests.test_parsing.test_parse_coverage_data", "eval.tests.test_summary_table.test_summary_coverage_column", "tests.test_follow.test_follow_with_timestamp", "tests.test_follow.test_follow_verbose_without_noisy_output_filtered", "tests.test_follow.test_progress_mode_basic", "tests.test_follow.test_follow_mode_without_file_flag_requires_pipe", "tests.test_follow.test_follow_output_file_error_handling", "tests.test_follow.test_follow_verbose_with_parallel_subtests", "tests.test_follow.test_follow_with_timestamp_and_file_output", "tests.test_follow.test_follow_timestamp_format_is_rfc3339", "tests.test_follow.test_follow_mode_basic", "tests.test_display.test_notests_only_package_displayed", "tests.test_format.test_format_basic_nocolor_exact_match_against_golden", "tests.test_format.test_format_plain_exact_match_against_golden", "tests.test_format.test_legacy_noborders_flag_produces_plain_format", "tests.test_format.test_plain_format_with_all_flag_shows_test_table", "tests.test_format.test_failed_test_basic_format_multiline_output", "tests.test_format.test_format_basic_with_no_color_env_and_all_flag", "tests.test_follow.test_follow_verbose_mode", "tests.test_follow.test_follow_output_to_file", "tests.test_follow.test_follow_verbose_preserves_test_hierarchy", "tests.test_format.test_format_basic_exact_match_against_golden", "tests.test_format.test_no_color_env_exact_match_against_golden", "tests.test_format.test_noborders_with_format_flag_format_takes_precedence", "tests.test_format.test_format_markdown_exact_match_against_golden", "tests.test_follow.test_follow_mode_with_failed_build", "tests.test_follow.test_progress_mode_multiple_packages", "tests.test_follow.test_follow_verbose_shows_panic_output", "tests.test_format.test_mixed_results_markdown_format", "tests.test_format.test_basic_format_with_all_flag_shows_test_table", "tests.test_harvest.test_failed_fixtures[test_02-1]", "tests.test_format.test_failed_test_markdown_format_code_block", "tests.test_format.test_basic_format_nocolor_with_all_flag", "tests.test_format.test_markdown_format_with_all_flag_shows_collapsible_details", "tests.test_follow.test_follow_verbose_with_notests", "tests.test_follow.test_follow_and_progress_combined", "tests.test_harvest.test_follow_verbose_fixtures[test_06-2]", "tests.test_harvest.test_follow_verbose_fixtures[test_05-1]", "tests.test_harvest.test_failed_fixtures[test_04-1]", "tests.test_harvest.test_follow_fixtures[test_01-0]", "tests.test_harvest.test_race_fixtures[test_03-1]", "tests.test_harvest.test_failed_fixtures[test_03-1]", "tests.test_harvest.test_follow_verbose_fixtures[test_02-0]", "tests.test_harvest.test_prescan_fixtures[test_01.txt-True]", "tests.test_harvest.test_follow_verbose_fixtures[test_03-0]", "tests.test_path.test_trimpath_auto_detects_common_prefix", "tests.test_path.test_trimpath_in_pass_test_table", "tests.test_harvest.test_failed_fixtures[test_01-1]", "tests.test_path.test_trimpath_with_markdown_format", "tests.test_harvest.test_follow_verbose_fixtures[test_01-1]", "tests.test_harvest.test_follow_verbose_fixtures[test_04-0]", "tests.test_path.test_trimpath_with_all_flag_mixed_statuses", "tests.test_path.test_trimpath_with_plain_format", "tests.test_path.test_trimpath_failed_section_shows_full_path", "tests.test_path.test_versioned_packages_smallscreen", "tests.test_path.test_trimpath_basic_removes_specified_prefix" ], "failed_tests_omitted": 15, "public_eval_path": "eval.json", "summary_path": "eval-summary.json", "test_branch_errors": {}, "test_records": 556, "warnings": [] }, "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "instance_id": "mfridman__tparse.2416b4b", "metrics": { "almost_resolved": "False", "cached_input_tokens": "6641792", "calls": "107", "created_at": "2026-05-17T12:46:36.115531+00:00", "docker_cpus": "16", "docker_memory": "30g", "error_code": "", "estimated_cost_usd": "5.6356", "evaluator_problem": "False", "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "input_tokens": "6839683", "instance_id": "mfridman__tparse.2416b4b", "long_context_calls": "0", "model": "gpt-5.5", "n_resolved_tests": "354", "n_system_errors": "0", "n_tests": "425", "n_warnings": "0", "output_tokens": "44176", "paper_compliant": "False", "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5", "reasoning_effort": "xhigh", "reasoning_output_tokens": "14156", "resolved": "False", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-mfridman-tparse", "run_version": "20260517T094700Z", "score": "0.8329411764705882", "session_ended_at": "2026-05-17T13:00:08.060Z", "session_started_at": "2026-05-17T12:46:39.227Z", "test_branch_errors": "{}", "total_tokens": "6883859", "wall_clock_seconds": "808" }, "model": "gpt-5.5", "package": { "contents": [ ".", "./compile.sh", "./executable", "./tparse.py" ], "contents_omitted": 0, "submission_available_local_only": true }, "paper_compliant": false, "paper_mode": false, "reasoning_effort": "xhigh", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-mfridman-tparse", "run_version": "20260517T094700Z", "usage_audit": { "available_local_artifact": true, "public_path": "usage-audit.json" } }