{ "agent_trace": { "codex_logs_available_local_only": true, "raw_logs_published": false }, "collected_at": "2026-05-18T13:25:15.512038+00:00", "docker_cpus": 16, "docker_memory": "30g", "eval": { "error_code": null, "failed_tests": [ "eval.tests.test_args_edge_cases.test_filters_help_output", "eval.tests.test_advanced_coverage.test_test_mode_with_verbose", "eval.tests.test_basic.test_filters_help", "eval.tests.test_advanced_coverage.test_no_sync_option", "eval.tests.test_args_and_options.test_multiple_verbose_flags", "eval.tests.test_advanced_coverage.test_filters_string_syntax", "eval.tests.test_comprehensive_coverage.TestFilterChainAdvanced.test_filters_string_syntax_lzma2", "eval.tests.test_comprehensive_coverage.TestMemoryLimits.test_memlimit_too_low_with_no_adjust", "eval.tests.test_comprehensive_coverage.TestCommonFunctions.test_stream_flags_operations", "eval.tests.test_codec_options.test_bcj_filters", "eval.tests.test_comprehensive_coverage.TestComplexFilterCombinations.test_arm64_bcj_filter", "eval.tests.test_coverage_boost_70.TestBlockBufferOperations.test_block_buffer_multiple_filter_chains", "eval.tests.test_basic.test_info_memory", "eval.tests.test_args_edge_cases.test_short_option_combinations", "eval.tests.test_advanced_coverage.test_memlimit_mt_decompress", "eval.tests.test_comprehensive_coverage.TestFilterChainAdvanced.test_filters_string_with_bcj", "eval.tests.test_coverage_boost_70.TestOptionsProcessing.test_filters_syntax_variations", "eval.tests.test_advanced_coverage.test_compress_symlink", "eval.tests.test_coverage_intensive.test_filters_option_with_string", "eval.tests.test_coverage_intensive.test_bcj_filters", "eval.tests.test_comprehensive_coverage.TestComplexFilterCombinations.test_riscv_bcj_filter", "eval.tests.test_coverage_intensive.test_verbose_compression_stats", "eval.tests.test_coverage_boost.test_no_sync_option", "eval.tests.test_coverage_targeted.test_no_adjust_memory", "eval.tests.test_coverage_boost_70.TestIntegrityChecks.test_test_mode_on_valid_files", "eval.tests.test_comprehensive_coverage.TestFilterChainAdvanced.test_filters_string_with_delta", "eval.tests.test_args_edge_cases.test_verbose_flag_repetition", "eval.tests.test_advanced_coverage.test_very_verbose_compression", "eval.tests.test_coverage_boost_70.TestCoderOperations.test_memlimit_with_mt_decompress", "eval.tests.test_edge_cases_intensive.test_memlimit_too_small", "eval.tests.test_edge_cases_intensive.test_block_list_syntax_error", "eval.tests.test_edge_cases_intensive.test_verbose_shows_progress", "eval.tests.test_error_paths_comprehensive.test_negative_block_size", "eval.tests.test_error_paths_comprehensive.test_extreme_memory_limit", "eval.tests.test_error_paths_comprehensive.test_verbose_compression_shows_progress", "eval.tests.test_coverage_intensive.test_filters_help", "eval.tests.test_coverage_boost_70.TestVerbosityLevels.test_very_verbose_shows_details", "eval.tests.test_comprehensive_coverage.TestFilterChainAdvanced.test_multiple_filter_chains", "eval.tests.test_file_operations_enhanced.TestTestMode.test_test_mode_with_verbose", "eval.tests.test_file_operations_enhanced.TestNoSyncOption.test_no_sync_compression", "eval.tests.test_filters.test_arm64_filter", "eval.tests.test_edge_cases_intensive.test_invalid_block_size", "eval.tests.test_more_coverage.test_stderr_messages", "eval.tests.test_error_paths_comprehensive.test_invalid_block_size_format", "eval.tests.test_error_paths_comprehensive.test_very_verbose_shows_more_info", "eval.tests.test_more_coverage.test_bcj_all_architectures", "eval.tests.test_more_coverage_boost.test_all_bcj_filters", "eval.tests.test_more_coverage_boost.test_filters_with_multiple_chains", "eval.tests.test_options_comprehensive.test_lzma2_nice_length", "eval.tests.test_filters.test_filters_option", "eval.tests.test_file_operations_enhanced.TestNoSyncOption.test_no_sync_decompression", "eval.tests.test_options_comprehensive.test_filters_extreme_preset", "eval.tests.test_options_comprehensive.test_filters_string_syntax", "eval.tests.test_options_comprehensive.test_filters_with_preset", "eval.tests.test_special_cases.test_verbose_mode", "eval.tests.test_options_comprehensive.test_filters_multiple_chains", "eval.tests.test_error_paths_comprehensive.test_compress_xz_file_warns", "eval.tests.test_stream_and_format_coverage.TestFilterEncoding.test_bcj_filters_encoding", "eval.tests.test_stream_and_format_coverage.TestSimpleCoders.test_riscv_coder", "eval.tests.test_options_comprehensive.test_bcj_start_offset", "tests.test_args_edge_cases.test_block_list_complex_pattern", "tests.test_args_edge_cases.test_block_list_double_comma_repeats_previous", "tests.test_args_edge_cases.test_block_list_empty_string_rejected", "tests.test_args_edge_cases.test_block_list_filter_chain_not_defined_rejected", "tests.test_args_edge_cases.test_block_list_filter_chain_without_size_rejected", "tests.test_args_edge_cases.test_block_list_invalid_size_rejected", "tests.test_args_edge_cases.test_block_list_multiple_filter_chains", "tests.test_args_edge_cases.test_block_list_multiple_sizes", "tests.test_args_edge_cases.test_block_list_simple_size", "tests.test_args_edge_cases.test_block_list_starts_with_comma_rejected", "tests.test_args_edge_cases.test_block_list_with_filter_chain_number", "tests.test_args_edge_cases.test_block_list_with_units_g", "tests.test_args_edge_cases.test_block_list_with_units_k", "tests.test_args_edge_cases.test_block_list_with_units_m", "tests.test_args_edge_cases.test_block_list_with_very_large_size", "tests.test_args_edge_cases.test_block_list_zero_as_last_element", "tests.test_args_edge_cases.test_block_list_zero_not_last_rejected", "tests.test_args_edge_cases.test_block_size_invalid_value_rejected", "tests.test_args_edge_cases.test_block_size_option_basic", "tests.test_args_edge_cases.test_block_size_with_units" ], "failed_tests_omitted": 805, "public_eval_path": "eval.json", "summary_path": "eval-summary.json", "test_branch_errors": { "8502a61d4b30": [ { "error_code": "results_read_failed", "error_details": "Error response from daemon: Could not find the file /workspace/eval/results.xml in container 8bfcebbd702724abdf2b403f4a97a6b4669fc8a710e86681f233f3e7f61caefc" } ] }, "test_records": 2036, "warnings": [] }, "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "instance_id": "tukaani-project__xz.1007bf0", "metrics": { "almost_resolved": "False", "cached_input_tokens": "6272768", "calls": "118", "created_at": "2026-05-17T16:22:18.830507+00:00", "docker_cpus": "16", "docker_memory": "30g", "error_code": "", "estimated_cost_usd": "5.4777", "evaluator_problem": "True", "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "input_tokens": "6454288", "instance_id": "tukaani-project__xz.1007bf0", "long_context_calls": "0", "model": "gpt-5.5", "n_resolved_tests": "576", "n_system_errors": "0", "n_tests": "1410", "n_warnings": "0", "output_tokens": "47789", "paper_compliant": "False", "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5", "reasoning_effort": "xhigh", "reasoning_output_tokens": "15113", "resolved": "False", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-tukaani-project-xz", "run_version": "20260517T094700Z", "score": "0.4085106382978723", "session_ended_at": "2026-05-17T16:37:32.111Z", "session_started_at": "2026-05-17T16:22:21.530Z", "test_branch_errors": "{\"8502a61d4b30\": [\"results_read_failed\"]}", "total_tokens": "6502077", "wall_clock_seconds": "910" }, "model": "gpt-5.5", "package": { "contents": [ ".", "./compile.sh", "./executable", "./xz_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-tukaani-project-xz", "run_version": "20260517T094700Z", "usage_audit": { "available_local_artifact": true, "public_path": "usage-audit.json" } }