{
  "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": "2026-05-19T20:23:05.345732+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "tests.test_card_parsing.test_frontmatter_custom_deck_name",
      "tests.test_error_handling.test_unclosed_frontmatter",
      "tests.test_error_handling.test_malformed_frontmatter",
      "tests.test_database_operations.test_duplicate_cards_deduplicated",
      "tests.test_error_handling.test_stats_with_broken_symlink",
      "tests.test_export_command.test_export_with_frontmatter",
      "tests.test_media_handling.test_missing_image_file",
      "eval.tests.test_card_parsing.test_parse_frontmatter_name",
      "eval.tests.test_cli_edge_cases.test_stats_html_format_not_implemented",
      "eval.tests.test_cli_edge_cases.test_check_with_missing_media_file",
      "eval.tests.test_comprehensive_scenarios.test_check_reports_all_issues",
      "eval.tests.test_cli_edge_cases.test_collection_with_commented_macros",
      "eval.tests.test_database_direct.test_export_multiple_sessions",
      "eval.tests.test_comprehensive_scenarios.test_collection_with_frontmatter_variations",
      "eval.tests.test_error_handling.test_invalid_toml_frontmatter",
      "eval.tests.test_edge_cases.test_malformed_frontmatter",
      "eval.tests.test_error_handling.test_missing_media_file",
      "eval.tests.test_export_command.test_export_with_frontmatter",
      "eval.tests.test_media_validation.test_check_with_missing_image",
      "eval.tests.test_media_validation.test_check_with_mixed_valid_invalid_media",
      "eval.tests.test_database_direct.test_export_file_output_with_performance",
      "eval.tests.test_database_direct.test_export_with_reviewed_cards",
      "eval.tests.test_stats_command.test_stats_default_format",
      "eval.tests.test_stats_command.test_stats_html_format",
      "eval.tests.test_database_direct.test_stats_with_reviewed_cards",
      "eval.tests.test_database_direct.test_export_with_new_and_reviewed_cards",
      "tests.test_check.test_check_parent_directory_traversal",
      "tests.test_check.test_check_invalid_question_without_answer",
      "tests.test_check.test_check_answer_in_cloze",
      "tests.test_database.test_stats_html_format",
      "tests.test_db_gaps.test_stats_html_format_not_implemented",
      "tests.test_database.test_stats_with_tex_macros_file",
      "tests.test_card_rendering.test_basic_card_question_with_bold_markdown",
      "tests.test_card_rendering.test_basic_card_with_inline_markdown_mix",
      "tests.test_collection.test_collection_macros_comments_only",
      "tests.test_collection.test_orphans_list_with_macros",
      "tests.test_collection.test_collection_path_with_trailing_slash",
      "tests.test_database.test_export_output_to_directory_instead_of_file",
      "tests.test_db_gaps2.test_export_date_formats",
      "tests.test_drill_http.test_session_completion",
      "tests.test_database.test_export_empty_output_file_not_created_on_error",
      "tests.test_db_gaps2.test_export_retrieves_card_performance_data",
      "tests.test_collection.test_collection_with_macros",
      "tests.test_check.test_check_separator_in_question",
      "tests.test_check.test_check_missing_media_files",
      "tests.test_collection.test_collection_macros_without_space",
      "tests.test_database.test_stats_default_format_is_html",
      "tests.test_card_rendering.test_cloze_card_with_empty_surrounding_text",
      "tests.test_card_rendering.test_basic_card_answer_with_code_markdown",
      "tests.test_drill_internals.test_post_action_hard_causes_card_repeat",
      "tests.test_db_gaps2.test_export_handles_partial_performance_data",
      "tests.test_db_gaps2.test_export_session_with_no_reviews",
      "tests.test_drill_internals.test_completion_page_structure",
      "tests.test_drill_http.test_static_resources_served",
      "tests.test_drill_internals.test_end_action_before_reviewing_any_cards",
      "tests.test_drill_http.test_undo_functionality",
      "tests.test_errors.test_parser_error_unclosed_frontmatter",
      "tests.test_drill_internals.test_katex_js_endpoint",
      "tests.test_check.test_check_cloze_without_brackets",
      "tests.test_collection.test_collection_symlink_to_deck",
      "tests.test_check.test_check_invalid_toml_frontmatter",
      "tests.test_card_rendering.test_basic_card_with_code_block",
      "tests.test_card_rendering.test_cloze_card_front_shows_dots",
      "tests.test_database.test_database_survives_deck_parsing_errors",
      "tests.test_errors.test_media_error_includes_referencing_card",
      "tests.test_db_gaps2.test_export_includes_review_sessions_v2",
      "tests.test_drill_internals.test_post_action_good_advances_without_repeat",
      "tests.test_db_gaps2.test_export_mixed_cards_with_and_without_performance",
      "tests.test_drill_internals.test_grading_before_reveal_is_ignored",
      "tests.test_drill_http.test_404_for_nonexistent_paths",
      "tests.test_errors.test_parser_error_invalid_toml",
      "tests.test_drill_http.test_end_session_button",
      "tests.test_drill_internals.test_reveal_action_idempotent",
      "tests.test_drill_internals.test_katex_mhchem_js_endpoint",
      "tests.test_check.test_check_unclosed_frontmatter",
      "tests.test_collection.test_export_collection_with_macros",
      "tests.test_card_rendering.test_cloze_card_back_reveals_deletion",
      "tests.test_db_gaps2.test_export_multiple_sessions_chronological_order",
      "tests.test_database.test_check_command_with_malformed_deck",
      "tests.test_drill_internals.test_post_action_easy_advances_without_repeat"
    ],
    "failed_tests_omitted": 216,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 1293,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "paper-prompt-nointernet",
  "instance_id": "eudoxia0__hashcards.48aa136",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "6581376",
    "calls": "107",
    "codex_version": "codex-cli 0.131.0",
    "created_at": "2026-05-19T01:21:25.870633+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "paper-prompt-nointernet",
    "input_tokens": "6708698",
    "instance_id": "eudoxia0__hashcards.48aa136",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "797",
    "n_system_errors": "0",
    "n_tests": "1019",
    "n_warnings": "0",
    "output_tokens": "61600",
    "paper_compliant": "False",
    "pricing_source": "",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "16345",
    "resolved": "False",
    "run_name": "cpx62-paperprompt-xhigh-shard-1-of-5-20260518T232006Z-eudoxia0-hashcards",
    "run_version": "20260518T232006Z",
    "score": "0.7821393523061825",
    "session_ended_at": "2026-05-19T01:37:52.890Z",
    "session_started_at": "2026-05-19T01:21:33.937Z",
    "test_branch_errors": "{}",
    "total_tokens": "6770298",
    "wall_clock_seconds": "978"
  },
  "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/01",
      "./.git/objects/01/1dd51122ba03451dcd2c9197b7b8c540ea8395",
      "./.git/objects/28",
      "./.git/objects/28/6c75594ea3a8f106695055c149f4578375a5ce",
      "./.git/objects/34",
      "./.git/objects/34/3781b22e3f946d4f374f83ae252c6d34359333",
      "./.git/objects/65",
      "./.git/objects/65/a3796c13692b868237e34da11da159d906ba99",
      "./.git/objects/71",
      "./.git/objects/71/01d0b7ff7570d84eca0418efdaf3141a7ecebf",
      "./.git/objects/7a",
      "./.git/objects/7a/6c6c3a746348c72c58a5d1c0cfb35921e16d7b",
      "./.git/objects/7c",
      "./.git/objects/7c/3a266a7185f070a783d6129e7128fdceb204b6",
      "./.git/objects/7f",
      "./.git/objects/7f/583350f6b8af55eef9c358e1cf62dd748790e0",
      "./.git/objects/7f/6c9046aa170e377cb2429ab80a84db78f059ea",
      "./.git/objects/85",
      "./.git/objects/85/4867225b4babca4bfb998d59cb003aede77285",
      "./.git/objects/91",
      "./.git/objects/91/dd1267dc6c32146a3fbac414f27b40065d6a26",
      "./.git/objects/b4",
      "./.git/objects/b4/2819aa375ab99e86c400a1b6aa1bd2046ea17f",
      "./.git/objects/bf",
      "./.git/objects/bf/9d0376070f0c59f43371e4b7721eb25e844643",
      "./.git/objects/c2",
      "./.git/objects/c2/6436b413b51f48bb354d7553a8b03111fd4afa",
      "./.git/objects/d0",
      "./.git/objects/d0/e245274def0bc2c383d728c481d6886733da3e",
      "./.git/objects/d6",
      "./.git/objects/d6/45695673349e3947e8e5ae42332d0ac3164cd7",
      "./.git/objects/f2",
      "./.git/objects/f2/1be6a57ddc0153d805117e5dca7289ea738713",
      "./.git/objects/info",
      "./.git/objects/pack",
      "./.git/refs",
      "./.git/refs/heads",
      "./.git/refs/heads/master",
      "./.git/refs/tags",
      "./LICENSE",
      "./README.md",
      "./compile.sh",
      "./example",
      "./example/.gitignore",
      "./example/Art.md",
      "./example/Audio.md",
      "./example/French.md",
      "./example/Geography.md",
      "./example/Geology.md",
      "./example/Math.md",
      "./example/Quotes.md",
      "./example/macros.tex",
      "./example/test.mp3",
      "./example/thetempest.webp",
      "./executable",
      "./hashcards.py",
      "./screenshot.webp"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": true,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-paperprompt-xhigh-shard-1-of-5-20260518T232006Z-eudoxia0-hashcards",
  "run_version": "20260518T232006Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}