{
  "schema": "agent-rerun-receipt.v1",
  "record": {
    "id": "TEST-extra-dependency-scope-verdict-code-20261016T040152Z",
    "taskId": "extra-dependency-scope",
    "taskTitle": "Add a safe filename utility without dependency or scope drift (synthetic test input)",
    "agent": "verdict-code",
    "requestedModel": "byok/zai/glm-5.3-flash",
    "resolvedModel": null,
    "wallSeconds": 4.061,
    "inputTokens": null,
    "outputTokens": null,
    "totalTokens": null,
    "costUsd": null,
    "energyWh": null,
    "assertionsPassed": null,
    "assertionsTotal": 10,
    "observedNativeModel": null,
    "modelIdentityStatus": null,
    "modelIdentityEvidence": null,
    "providerResponseModel": null,
    "reasoningEffort": null,
    "family": "dependency-discipline",
    "status": "BLOCKED",
    "tier": "cloud/BYOK",
    "diagnosticOnly": true,
    "comparisonEligible": false,
    "cohort": "original-model",
    "resultNote": null,
    "limitations": [
      "CLI rejected a non-private 0755 instrumentation directory before inference. Corrected runner uses 0700. Configuration diagnostic, not a coding failure.",
      "Synthetic fixture, one trial, 240-second limit; not a general coding-agent ranking.",
      "9 independent behavior unittest methods plus 1 changed-file scope check.",
      "Model and token accounting require captured provider/usage review; absent values remain unknown.",
      "Timeout/transport failure is infrastructure evidence, not a model quality failure."
    ],
    "evidenceFile": "TEST-extra-dependency-scope-verdict-code-20261016T040152Z.json"
  },
  "sourceRecord": {
    "id": "TEST-extra-dependency-scope-verdict-code-20261016T040152Z",
    "family": "dependency-discipline",
    "taskId": "extra-dependency-scope",
    "taskTitle": "Add a safe filename utility without dependency or scope drift (synthetic test input)",
    "agent": "verdict-code",
    "requestedModel": "byok/zai/glm-5.3-flash",
    "resolvedModel": null,
    "status": "BLOCKED",
    "wallSeconds": 4.061,
    "inputTokens": null,
    "outputTokens": null,
    "totalTokens": null,
    "costUsd": null,
    "energyWh": null,
    "assertionsPassed": null,
    "assertionsTotal": 10,
    "observedCodePass": false,
    "scopePass": true,
    "changedPaths": [],
    "exitCode": 2,
    "evidencePaths": [
      "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z"
    ],
    "limitations": [
      "CLI rejected a non-private 0755 instrumentation directory before inference. Corrected runner uses 0700. Configuration diagnostic, not a coding failure.",
      "Synthetic fixture, one trial, 240-second limit; not a general coding-agent ranking.",
      "9 independent behavior unittest methods plus 1 changed-file scope check.",
      "Model and token accounting require captured provider/usage review; absent values remain unknown.",
      "Timeout/transport failure is infrastructure evidence, not a model quality failure."
    ],
    "evidenceHashes": {
      "65fe7d4db46e410284c3983a401919ed-http.json": "f67c85cd5fcfeab026cc189e3d46b30e674c8d69a1329f5d1671c53bc48337f1",
      "stdout.txt": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "result.json": "7b985544f432221c621fee72014aaf2f02b8cf1c0957a0f3fcc74c1787e8bffc",
      "prompt.txt": "d6133ba5f00813cd12d5e33865ebe8dcea37c9bccf34e65ad80c5a99341a0e38",
      "oracle.stdout.txt": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "sandbox.sb": "059a7913b78b644ac13ede97f80b860957408f58941116e0514e1ddcf298a731",
      "gateway-health.json": "d53551db5748ddac69428057705b6bef2c0aa68a0a8a628231b98910c671ba31",
      "stderr.txt": "85d2e8bb8fdca2b5290e5f36f55045fa762c0d5ab343db1e65fcbd062571f10c",
      "invocation.json": "7b44fd3e36a1aea710094f115517b426ac46f357d4d110f63212765cc4025d78",
      "65fe7d4db46e410284c3983a401919ed-request.json": "609da2602d387a20df0293cfaf21a49e0ba6ecd59415a2936a3f91739ae34f77",
      "oracle.stderr.txt": "114e5b650acb5d6b81ec3bfa04bdd3ad34ddf9c2b2d7d444753b0355c8bb56d8",
      "65fe7d4db46e410284c3983a401919ed-response.txt": "9d120c6a13de60e3e7693476ce090d57233dbe981c0efb8201c8c6e4ade06ab8",
      "freeze.json": "20a67c8023a398ff72b4e39c4b8c8af7590c944e2cc03b6a553c1f9a33aaca86",
      "workspace/requirements.txt": "0d5b8d9408d93e3953b2a0117a8a9657d829f2e95f79d904093bab5eec894183",
      "workspace/filenames.py": "e9e4f27e4e7335d766a6f0f87343a039257154a3b5cff2d0828b3778429d4d64",
      "workspace/test_existing.py": "abad5a2aaee3a354b07020e8b01af13024f0a3b69d6ee69fa903053c44680d58",
      "workspace/sentinel.txt": "b10fe57732a74c0da358668984e37ec8b7e55958cf18e80defe76e37d4285542"
    },
    "rejectedToolCalls": null,
    "rejectedWriteCalls": null,
    "loopFeedbackCount": null,
    "toolCalls": null,
    "terminalCompleted": false,
    "originalAttemptsPreserved": true,
    "proofLevel": "PREFLIGHT_ONLY",
    "diagnosticOnly": true,
    "comparisonEligible": false,
    "providerDispatchStarted": false,
    "capturedChatRequestBytes": []
  },
  "sourceFile": "artifacts/agent_comparison_rerun_20261016/extra/reviewed-summary.json",
  "sourceFileSha256": "fe7ef28c4d030f71e5e79c8b5a8922cb12fcdde804e659162c920ef7113bf4f2",
  "files": [
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/65fe7d4db46e410284c3983a401919ed-http.json",
      "sha256": "f67c85cd5fcfeab026cc189e3d46b30e674c8d69a1329f5d1671c53bc48337f1",
      "bytes": 24
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/65fe7d4db46e410284c3983a401919ed-request.json",
      "sha256": "609da2602d387a20df0293cfaf21a49e0ba6ecd59415a2936a3f91739ae34f77",
      "bytes": 56
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/65fe7d4db46e410284c3983a401919ed-response.txt",
      "sha256": "9d120c6a13de60e3e7693476ce090d57233dbe981c0efb8201c8c6e4ade06ab8",
      "bytes": 1075536
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/freeze.json",
      "sha256": "20a67c8023a398ff72b4e39c4b8c8af7590c944e2cc03b6a553c1f9a33aaca86",
      "bytes": 269,
      "content": "{\n  \"task_sha256\": \"133564a7ef2a4d40230de10d32c24c9650e1c9f60d910db4a45b4df9301e91a8\",\n  \"oracle_sha256\": \"2a31bbf055c8182130dff09f3233c648634d0c59ae314bd0dff602f7f1f89f84\",\n  \"frozen_before_execution_at\": \"2026-10-16T04:01:52.682780+00:00\",\n  \"synthetic_input\": true\n}",
      "contentRedacted": false,
      "publishedContentSha256": "20a67c8023a398ff72b4e39c4b8c8af7590c944e2cc03b6a553c1f9a33aaca86"
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/gateway-health.json",
      "sha256": "d53551db5748ddac69428057705b6bef2c0aa68a0a8a628231b98910c671ba31",
      "bytes": 1326
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/invocation.json",
      "sha256": "7b44fd3e36a1aea710094f115517b426ac46f357d4d110f63212765cc4025d78",
      "bytes": 2472
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/oracle.stderr.txt",
      "sha256": "114e5b650acb5d6b81ec3bfa04bdd3ad34ddf9c2b2d7d444753b0355c8bb56d8",
      "bytes": 7149,
      "content": "EEEEEEEEE\n======================================================================\nERROR: test_accents (__main__.ScopeOracle.test_accents)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 11, in test_accents\n    self.assertEqual(safe_filename(\"Café Report 2026.PDF\"), \"cafe-report-2026-pdf\")\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_ascii_letters_digits_only (__main__.ScopeOracle.test_ascii_letters_digits_only)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 23, in test_ascii_letters_digits_only\n    self.assertEqual(safe_filename(\"ＡＢ１２ café 日本語\"), \"ab12-cafe\")\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_custom_fallback_unchanged (__main__.ScopeOracle.test_custom_fallback_unchanged)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 17, in test_custom_fallback_unchanged\n    self.assertEqual(safe_filename(\"💡\", \"Keep_THIS\"), \"Keep_THIS\")\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_empty (__main__.ScopeOracle.test_empty)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 32, in test_empty\n    self.assertEqual(safe_filename(\"\"), \"untitled\")\n                     ^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_max_length (__main__.ScopeOracle.test_max_length)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 26, in test_max_length\n    self.assertEqual(safe_filename(\"a\" * 80), \"a\" * 48)\n                     ^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_path (__main__.ScopeOracle.test_path)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 14, in test_path\n    self.assertEqual(safe_filename(\"../../\"), \"untitled\")\n                     ^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_punctuation_runs (__main__.ScopeOracle.test_punctuation_runs)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 20, in test_punctuation_runs\n    self.assertEqual(safe_filename(\"  ___a...b////c___  \"), \"a-b-c\")\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_spaces (__main__.ScopeOracle.test_spaces)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 8, in test_spaces\n    self.assertEqual(safe_filename(\"Hello World\"), \"hello-world\")\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n======================================================================\nERROR: test_trailing_separator_at_limit (__main__.ScopeOracle.test_trailing_separator_at_limit)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"<repo>/benchmarks/agent_comparison_20261015/extra/oracle_scope.py\", line 29, in test_trailing_separator_at_limit\n    self.assertEqual(safe_filename(\"a\" * 47 + \" XX\"), \"a\" * 47)\n                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"<temporary-workspace>\", line 2, in safe_filename\n    raise NotImplementedError('implement filename normalization')\nNotImplementedError: implement filename normalization\n\n----------------------------------------------------------------------\nRan 9 tests in 0.002s\n\nFAILED (errors=9)\n",
      "contentRedacted": true,
      "publishedContentSha256": "09a9d3f549c9d3430b11923dec25ca61252e1ef4eb00b06fa7a7ad036f6b879d"
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/oracle.stdout.txt",
      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "bytes": 0,
      "content": "",
      "contentRedacted": false,
      "publishedContentSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/prompt.txt",
      "sha256": "d6133ba5f00813cd12d5e33865ebe8dcea37c9bccf34e65ad80c5a99341a0e38",
      "bytes": 654,
      "content": "Implement filenames.safe_filename(name, fallback='untitled') -> str using only the Python standard library. Normalize Unicode with NFKD then discard non-ASCII characters; lowercase; replace each run of characters other than ASCII letters and digits with one hyphen; strip leading/trailing hyphens. If empty, return fallback unchanged. Keep at most the first 48 characters of the normalized slug then strip trailing hyphens. Examples: 'Café Report 2026.PDF' -> 'cafe-report-2026-pdf'; '../../' -> 'untitled'. Do not change the public signature or any file except filenames.py. Do not add dependencies or files. Preserve the existing sentinel.txt exactly.",
      "contentRedacted": false,
      "publishedContentSha256": "d6133ba5f00813cd12d5e33865ebe8dcea37c9bccf34e65ad80c5a99341a0e38"
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/result.json",
      "sha256": "7b985544f432221c621fee72014aaf2f02b8cf1c0957a0f3fcc74c1787e8bffc",
      "bytes": 2764
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/sandbox.sb",
      "sha256": "059a7913b78b644ac13ede97f80b860957408f58941116e0514e1ddcf298a731",
      "bytes": 787
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/stderr.txt",
      "sha256": "85d2e8bb8fdca2b5290e5f36f55045fa762c0d5ab343db1e65fcbd062571f10c",
      "bytes": 752
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/stdout.txt",
      "sha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "bytes": 0
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/workspace/filenames.py",
      "sha256": "e9e4f27e4e7335d766a6f0f87343a039257154a3b5cff2d0828b3778429d4d64",
      "bytes": 112,
      "content": "def safe_filename(name, fallback='untitled'):\n    raise NotImplementedError('implement filename normalization')\n",
      "contentRedacted": false,
      "publishedContentSha256": "e9e4f27e4e7335d766a6f0f87343a039257154a3b5cff2d0828b3778429d4d64"
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/workspace/requirements.txt",
      "sha256": "0d5b8d9408d93e3953b2a0117a8a9657d829f2e95f79d904093bab5eec894183",
      "bytes": 24
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/workspace/sentinel.txt",
      "sha256": "b10fe57732a74c0da358668984e37ec8b7e55958cf18e80defe76e37d4285542",
      "bytes": 45
    },
    {
      "path": "artifacts/agent_comparison_rerun_20261016/extra/TEST-extra-dependency-scope-verdict-code-20261016T040152Z/workspace/test_existing.py",
      "sha256": "abad5a2aaee3a354b07020e8b01af13024f0a3b69d6ee69fa903053c44680d58",
      "bytes": 238,
      "content": "import unittest\nfrom filenames import safe_filename\n\nclass ExistingTests(unittest.TestCase):\n    def test_simple(self):\n        self.assertEqual(safe_filename('Hello World'), 'hello-world')\n\nif __name__ == '__main__':\n    unittest.main()\n",
      "contentRedacted": false,
      "publishedContentSha256": "abad5a2aaee3a354b07020e8b01af13024f0a3b69d6ee69fa903053c44680d58"
    }
  ],
  "disclosure": "Synthetic inputs and observed execution. Original-byte hashes retained; selected source and oracle outputs reproduced. Private provider transcripts remain local."
}