{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:00.566672+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_brotli.TestBasicInvocation.test_help_mentions_coalesced_options",
      "eval.tests.test_brotli.TestFileDecompression.test_decompress_precompressed_alice",
      "eval.tests.test_brotli.TestFileCompression.test_compress_large_text_file_smaller",
      "eval.tests.test_brotli.TestFileDecompression.test_decompress_precompressed_zeros",
      "eval.tests.test_brotli.TestFileCompression.test_compress_file_with_keep_flag",
      "eval.tests.test_brotli.TestFileCompression.test_compress_file_creates_valid_br",
      "eval.tests.test_brotli.TestBasicInvocation.test_help_short_goes_to_stderr",
      "eval.tests.test_brotli.TestStdinInput.test_decompress_empty_compressed_stdin",
      "eval.tests.test_brotli.TestRoundTrip.test_roundtrip_all_quality_levels",
      "eval.tests.test_brotli.TestBasicInvocation.test_no_args_with_piped_stdin",
      "eval.tests.test_brotli.TestFileDecompression.test_decompress_suffix_mismatch_error",
      "eval.tests.test_brotli.TestRoundTrip.test_roundtrip_text",
      "eval.tests.test_brotli.TestStdinInput.test_compress_from_explicit_dash_stdin",
      "eval.tests.test_brotli.TestRoundTrip.test_roundtrip_known_test_files",
      "eval.tests.test_brotli.TestOutputOptions.test_stdout_flag_long",
      "eval.tests.test_brotli.TestOutputOptions.test_decompress_to_output_file",
      "eval.tests.test_brotli.TestBasicInvocation.test_help_mentions_stdin_dash",
      "eval.tests.test_brotli.TestBasicInvocation.test_help_long_goes_to_stderr",
      "eval.tests.test_brotli.TestFileCompression.test_compress_multiple_files_roundtrip",
      "eval.tests.test_brotli.TestFileDecompression.test_decompress_precompressed_empty",
      "eval.tests.test_brotli.TestStdinInput.test_compress_from_stdin_roundtrip",
      "eval.tests.test_brotli.TestFileCompression.test_compress_keeps_source_by_default",
      "eval.tests.test_brotli.TestFileDecompression.test_decompress_keeps_compressed_by_default",
      "eval.tests.test_brotli.TestFileDecompression.test_decompress_nonexistent_file",
      "eval.tests.test_brotli.TestStdinInput.test_compress_empty_stdin",
      "eval.tests.test_brotli.TestStdinInput.test_stdin_binary_data_roundtrip",
      "eval.tests.test_brotli.TestCompressionQuality.test_best_flag_Z_roundtrip",
      "eval.tests.test_brotli.TestOutputOptions.test_stdout_flag_short",
      "eval.tests.test_brotli.TestRoundTrip.test_roundtrip_binary",
      "eval.tests.test_brotli.TestCompressionQuality.test_quality_short_q_11_roundtrip",
      "eval.tests.test_brotli.TestOutputOptions.test_output_file_flag_short",
      "eval.tests.test_brotli.TestCompressionQuality.test_quality_short_q_0_roundtrip",
      "eval.tests.test_brotli.TestRemoveSource.test_compress_rm_removes_source_and_valid_output",
      "eval.tests.test_brotli.TestWindowSize.test_large_window_flag_roundtrip",
      "eval.tests.test_brotli.TestWindowSize.test_lgwin_10_roundtrip",
      "eval.tests.test_brotli.TestRemoveSource.test_compress_rm_long_flag",
      "eval.tests.test_brotli.TestWindowSize.test_lgwin_0_auto_roundtrip",
      "eval.tests.test_brotli.TestSquash.test_squash_with_stdout_is_invalid",
      "eval.tests.test_brotli.TestSquash.test_squash_removes_output_if_larger",
      "eval.tests.test_brotli.TestNoCopyStat.test_no_copy_stat_long",
      "eval.tests.test_brotli.TestForceOverwrite.test_compress_force_overwrite",
      "eval.tests.test_brotli.TestOutputOptions.test_output_file_flag_long_equals",
      "eval.tests.test_brotli.TestCompressionQuality.test_quality_long_flag_roundtrip",
      "eval.tests.test_brotli.TestForceOverwrite.test_compress_fails_if_output_exists",
      "eval.tests.test_brotli.TestForceOverwrite.test_decompress_force_overwrite",
      "eval.tests.test_brotli.TestCompressionQuality.test_quality_short_flag_0_to_9",
      "eval.tests.test_brotli.TestIntegrity.test_test_integrity_long_flag",
      "eval.tests.test_brotli.TestSquash.test_squash_large_compressible_data_keeps_output",
      "eval.tests.test_brotli.TestNoCopyStat.test_no_copy_stat_short",
      "eval.tests.test_brotli.TestRemoveSource.test_decompress_rm_removes_source",
      "eval.tests.test_brotli.TestSuffix.test_suffix_with_path_separator_fails",
      "eval.tests.test_brotli.TestIntegrity.test_test_integrity_precompressed_file",
      "eval.tests.test_brotli.TestForceOverwrite.test_decompress_fails_if_output_exists",
      "eval.tests.test_brotli.TestIntegrity.test_test_integrity_valid_file",
      "eval.tests.test_brotli.TestWindowSize.test_lgwin_24_max_roundtrip",
      "eval.tests.test_brotli.TestIntegrity.test_test_integrity_corrupt_file",
      "eval.tests.test_brotli.TestWindowSize.test_lgwin_long_flag_roundtrip",
      "eval.tests.test_brotli.TestSuffix.test_custom_suffix_decompress",
      "eval.tests.test_brotli.TestIntegrity.test_test_integrity_from_stdin",
      "eval.tests.test_brotli.TestForceOverwrite.test_force_flag_long_roundtrip",
      "eval.tests.test_brotli.TestComment.test_compress_with_comment_roundtrip",
      "eval.tests.test_brotli.TestComment.test_comment_too_much_padding",
      "eval.tests.test_brotli.TestComment.test_comment_no_padding_roundtrip",
      "eval.tests.test_brotli.TestComment.test_comment_length_mismatch_fails",
      "eval.tests.test_brotli.TestSuffix.test_custom_suffix_long_flag",
      "eval.tests.test_brotli.TestSuffix.test_default_suffix_is_br",
      "eval.tests.test_brotli.TestSuffix.test_custom_suffix_compress",
      "eval.tests.test_brotli.TestComment.test_decompress_ignores_comment_without_flag",
      "eval.tests.test_brotli.TestComment.test_decompress_with_matching_comment",
      "eval.tests.test_brotli.TestSuffix.test_suffix_with_backslash_fails",
      "eval.tests.test_brotli.TestConcatenated.test_concatenated_flag_K_allows_multi_stream",
      "eval.tests.test_brotli.TestConcatenated.test_concatenated_long_flag",
      "eval.tests.test_brotli.TestDoubleDash.test_double_dash_treats_args_as_files",
      "eval.tests.test_brotli.TestComment.test_decompress_with_mismatched_comment_fails",
      "eval.tests.test_brotli.TestConcatenated.test_decompress_concatenated_fails_without_flag",
      "eval.tests.test_brotli.TestConcatenated.test_concatenated_three_streams",
      "eval.tests.test_brotli.TestCoalescedOptions.test_coalesced_dKc",
      "eval.tests.test_brotli.TestMultipleInputFiles.test_multiple_files_roundtrip",
      "eval.tests.test_brotli.TestErrorHandling.test_corrupt_brotli_data",
      "eval.tests.test_brotli.TestComment.test_comment_long_flag_roundtrip"
    ],
    "failed_tests_omitted": 378,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 606,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "google__brotli.b3dc9cc",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "4267008",
    "calls": "64",
    "created_at": "2026-05-17T11:17:36.230085+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "4.0097",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "4410900",
    "instance_id": "google__brotli.b3dc9cc",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "110",
    "n_system_errors": "0",
    "n_tests": "441",
    "n_warnings": "0",
    "output_tokens": "38557",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "10927",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-google-brotli",
    "run_version": "",
    "score": "0.2494331065759637",
    "session_ended_at": "2026-05-17T11:29:46.042Z",
    "session_started_at": "2026-05-17T11:17:39.078Z",
    "test_branch_errors": "{}",
    "total_tokens": "4449457",
    "wall_clock_seconds": "726"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./brotli_cli.py",
      "./compile.sh",
      "./executable"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-google-brotli",
  "run_version": "",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
