{ "agent_trace": { "codex_logs_available_local_only": true, "raw_logs_published": false, "summary_path": "agent-summary.json" }, "codex_version": "codex-cli 0.131.0", "collected_at": "2026-05-19T20:21:33.258786+00:00", "docker_cpus": 16, "docker_memory": "30g", "eval": { "error_code": null, "failed_tests": [ "eval.tests.test_domain.test_domain_without_protocol", "eval.tests.test_basic_invocation.test_stdin_empty_input", "eval.tests.test_input_output.test_output_file_no_overwrite", "eval.tests.test_input_output.test_output_file_with_overwrite", "eval.tests.test_input_output.test_output_to_file", "eval.tests.test_input_output.test_empty_input_flag_value", "eval.tests.test_selectors.test_multiple_exclude_selectors", "eval.tests.test_selectors.test_multiple_include_selectors", "eval.tests.test_selectors.test_invalid_css_selector", "eval.tests.test_selectors.test_empty_css_selector", "eval.tests.test_basic_invocation.TestBasicConversion.test_empty_input", "eval.tests.test_error_handling.TestErrorHandling.test_output_to_nonexistent_directory", "eval.tests.test_file_io.TestFileOutput.test_output_to_file", "eval.tests.test_error_handling.TestErrorHandling.test_multiple_output_flags", "eval.tests.test_file_io.TestFileOutput.test_output_file_exists_with_overwrite", "eval.tests.test_selectors.TestSelectors.test_invalid_css_selector", "eval.tests.test_selectors.TestSelectors.test_empty_selector_string", "eval.tests.test_file_io.TestFileOutput.test_output_file_exists_without_overwrite", "tests.test_file_io.test_multiple_inputs_to_stdout_error", "tests.test_file_io.test_output_directory_with_trailing_slash", "tests.test_file_io.test_dot_files_in_glob", "tests.test_core_conversions.test_blockquote_containing_both_inline_and_block_code", "tests.test_core_conversions.test_links_with_various_attributes", "tests.test_core_conversions.test_empty_elements_various_types", "tests.test_core_conversions.test_blog_post_realistic_multi_element", "tests.test_core_conversions.test_adjacent_inline_elements_without_whitespace", "tests.test_file_io.test_output_to_symlink", "tests.test_file_io.test_output_overwrite_flag", "tests.test_core_conversions.test_multiple_consecutive_br_tags_collapse", "tests.test_gap_base_renderers.test_base_plugin_textarea_removed", "tests.test_gap_base_renderers.test_base_plugin_head_tag_removed", "tests.test_gap_base_renderers.test_base_plugin_null_character_in_html", "tests.test_file_io.test_duplicate_basenames_different_paths", "tests.test_file_io.test_single_file_to_file", "tests.test_core_conversions.test_large_document_many_sections_performance", "tests.test_file_io.test_mixed_extensions_in_glob", "tests.test_core_conversions.test_inline_code_basic_and_with_backticks", "tests.test_gap_converter.test_span_inside_strong", "tests.test_gap_converter.test_hr_void_and_block_element", "tests.test_gap_plugins.test_strikethrough_nested_tags", "tests.test_gap_base_renderers.test_base_plugin_mixed_removed_tags", "tests.test_gap_plugins.test_table_rowspan_behavior", "tests.test_gap_plugins.test_strikethrough_escapes_tildes_in_text", "tests.test_file_io.test_output_parent_directories_created", "tests.test_gap_validation.test_heading_h1_with_empty_content", "tests.test_gap_validation.test_heading_ending_with_hash_symbol", "tests.test_gap_validation.test_heading_ending_with_multiple_hashes", "tests.test_harvest_cli.test_cli_golden[[general]_version_terminal]", "tests.test_file_io.test_empty_output_path_error", "tests.test_file_io.test_stdin_to_file", "tests.test_core_conversions.test_inline_code_whitespace_edge_cases", "tests.test_harvest_cli.test_cli_golden[[general]_help_terminal]", "tests.test_harvest_cli.test_cli_golden[[general]_no_content]", "tests.test_harvest_cli.test_cli_golden[[argument_unknown]_html]", "tests.test_gap_converter.test_empty_span_between_formatted_elements", "tests.test_gap_base_renderers.test_base_plugin_nested_removed_tags", "tests.test_harvest_cli.test_cli_golden[[argument_unknown]_list_of_files]", "tests.test_harvest_cli.test_cli_golden[[flag_misspelled]_underscore]", "tests.test_gap_validation.test_heading_h2_with_empty_content", "tests.test_gap_validation.test_heading_h1_with_whitespace_only", "tests.test_harvest_cli.test_cli_golden[[include-selector]_empty_string]", "tests.test_harvest_cli.test_cli_golden[[exclude-selector]_exclude_multiple]", "tests.test_harvest_cli.test_cli_golden[[files]_without_suffix_existing_dir]", "tests.test_harvest_cli.test_cli_golden[[general]_version_pipe]", "tests.test_file_io.test_output_is_directory_without_trailing_slash_error", "tests.test_harvest_cli.test_cli_golden[[general]_help_pipe]", "tests.test_gap_converter.test_link_title_with_double_quotes", "tests.test_harvest_cli.test_cli_golden[[files]_input_directory]", "tests.test_harvest_cli.test_cli_golden[[argument_unknown]_long_string]", "tests.test_harvest_cli.test_cli_golden[[argument_unknown]_version]", "tests.test_gap_base_renderers.test_base_plugin_empty_document", "tests.test_gap_validation.test_heading_with_newlines_in_content", "tests.test_harvest_cli.test_cli_golden[[include-selector]_multiple_matches]", "tests.test_harvest_cli.test_cli_golden[[validation]_no_value]", "tests.test_harvest_cli.test_cli_golden[[include-selector]_invalid]", "tests.test_options_flags.test_exclude_selector_single_class", "tests.test_options_flags.test_include_selector_empty_string_error", "tests.test_options_flags.test_exclude_selector_multiple", "tests.test_harvest_cli.test_cli_golden[[files]_multiple_files_but_no_output]", "tests.test_options_flags.test_domain_with_empty_href" ], "failed_tests_omitted": 38, "public_eval_path": "eval.json", "summary_path": "eval-summary.json", "test_branch_errors": {}, "test_records": 974, "warnings": [] }, "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "paper-prompt-nointernet", "instance_id": "johanneskaufmann__html-to-markdown.3006818", "metrics": { "almost_resolved": "False", "cached_input_tokens": "2957568", "calls": "62", "codex_version": "codex-cli 0.131.0", "created_at": "2026-05-19T02:42:26.935292+00:00", "docker_cpus": "16", "docker_memory": "30g", "error_code": "", "estimated_cost_usd": "3.7647", "evaluator_problem": "False", "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "paper-prompt-nointernet", "input_tokens": "3105088", "instance_id": "johanneskaufmann__html-to-markdown.3006818", "long_context_calls": "0", "model": "gpt-5.5", "n_resolved_tests": "773", "n_system_errors": "0", "n_tests": "885", "n_warnings": "0", "output_tokens": "51610", "paper_compliant": "False", "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5", "reasoning_effort": "xhigh", "reasoning_output_tokens": "15409", "resolved": "False", "run_name": "cpx62-paperprompt-xhigh-shard-0-of-5-20260518T232006Z-johanneskaufmann-html-to-markdown", "run_version": "20260518T232006Z", "score": "0.8734463276836159", "session_ended_at": "2026-05-19T02:56:00.723Z", "session_started_at": "2026-05-19T02:42:34.912Z", "test_branch_errors": "{}", "total_tokens": "3156698", "wall_clock_seconds": "805" }, "model": "gpt-5.5", "package": { "contents": [ ".", "./.git", "./.git/COMMIT_EDITMSG", "./.git/HEAD", "./.git/branches", "./.git/config", "./.git/description", "./.git/hooks", "./.git/hooks/applypatch-msg.sample", "./.git/hooks/commit-msg.sample", "./.git/hooks/fsmonitor-watchman.sample", "./.git/hooks/post-update.sample", "./.git/hooks/pre-applypatch.sample", "./.git/hooks/pre-commit.sample", "./.git/hooks/pre-merge-commit.sample", "./.git/hooks/pre-push.sample", "./.git/hooks/pre-rebase.sample", "./.git/hooks/pre-receive.sample", "./.git/hooks/prepare-commit-msg.sample", "./.git/hooks/push-to-checkout.sample", "./.git/hooks/update.sample", "./.git/index", "./.git/info", "./.git/info/exclude", "./.git/logs", "./.git/logs/HEAD", "./.git/logs/refs", "./.git/logs/refs/heads", "./.git/logs/refs/heads/master", "./.git/objects", "./.git/objects/0a", "./.git/objects/0a/028f6ee44fde35a0dc38bb7113135a30d9fedd", "./.git/objects/0a/daa6b5b25d2307cab822bd3533acd44d1eac78", "./.git/objects/63", "./.git/objects/63/ea4b08245b528dc738b75e2351e056e8c8a635", "./.git/objects/67", "./.git/objects/67/b2424f8912efdd9a76a26880fd550e37d5db3b", "./.git/objects/d6", "./.git/objects/d6/3098d55f73abbc3fae6dee21883789aab47394", "./.git/objects/dd", "./.git/objects/dd/cf6935ffa6e4c02df975fd56a814dfa8e9e20d", "./.git/objects/info", "./.git/objects/pack", "./.git/refs", "./.git/refs/heads", "./.git/refs/heads/master", "./.git/refs/tags", "./ESCAPING.md", "./LICENSE", "./README.md", "./SECURITY.md", "./compile.sh", "./executable", "./html2markdown.py" ], "contents_omitted": 0, "submission_available_local_only": true }, "paper_compliant": false, "paper_mode": true, "reasoning_effort": "xhigh", "run_name": "cpx62-paperprompt-xhigh-shard-0-of-5-20260518T232006Z-johanneskaufmann-html-to-markdown", "run_version": "20260518T232006Z", "usage_audit": { "available_local_artifact": true, "public_path": "usage-audit.json" } }