{
  "schemaVersion": 1,
  "status": "ineligible-infrastructure-failure",
  "comparativePerformanceEligible": false,
  "reason": "The tool-enabled launches failed before model work because the recorder encoded an environment map incorrectly. Every attempted launch and the completed native session are retained. No measurements are pooled with the corrected study.",
  "protocol": "../protocol-001.json",
  "privateProtocolSha256": "5889188850bcd8367ae9e6161df366c23f83d18bd51ce07e1b4c4075a8802e01",
  "runs": [
    {
      "id": "pnpm-changed-project-move-r1-native",
      "task": "pnpm-changed-project-move",
      "repeat": 1,
      "arm": "native",
      "status": "completed",
      "startedAt": "2026-11-06T18:40:37.292Z",
      "finishedAt": "2026-11-06T18:41:00.744Z",
      "fixtureSetupMs": 14880.570416999999,
      "providerSetupMs": 0.0017499999994470272,
      "elapsedMs": 23452.495082999994,
      "teardownMs": 0.19745800000237068,
      "gradingMs": 8494.542791999993,
      "exitCode": 0,
      "timedOut": false,
      "processGroupStopped": true,
      "providerStopped": true,
      "correct": true,
      "capture": {
        "complete": true,
        "issues": [],
        "startupWarnings": [
          {
            "line": 2,
            "kind": "unstable-features",
            "messageSha256": "b7f966b81ed3d1a5878ecb513d7504e7f08289ae2bc88b0233f0794bf8f57666"
          }
        ],
        "turnStarts": 1,
        "turnCompletions": 1,
        "duplicateActions": 0,
        "duplicateCompletions": 0,
        "failedTurn": false
      },
      "usage": {
        "inputTokens": 89703,
        "cachedInputTokens": 77824,
        "cacheWriteInputTokens": 0,
        "outputTokens": 662,
        "reasoningOutputTokens": 28,
        "totalTokens": 90365,
        "uncachedInputTokens": 11879
      },
      "counts": {
        "shellCalls": 6,
        "mcpCalls": 0,
        "mcpSucceeded": 0,
        "mcpFailed": 0,
        "fileEdits": 1,
        "grepShellCalls": 3,
        "contentSearchShellCalls": 2,
        "fileListingShellCalls": 2,
        "ambiguousSearchShellCalls": 0
      },
      "fixtureSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "preparedSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "promptSha256": "ff8c8a9f67d6646b20ec49be83c3de61628eaa55187b93a329ed5261a1db5d3e",
      "recordingError": null,
      "rawSha256": "6aa03d4f8427a85fd25811e778c1d0432c54ef83f31d32c6c775a30b2d0c750c",
      "nativeValidation": {
        "checks": [
          {
            "line": 10,
            "actionIdSha256": "57dbfc296665f072254d15345fb3a2bbf457ae03cbb6ee8f6020e8f11d4b056b",
            "commandExitCode": 1,
            "individualCheckExitCode": null,
            "resultIndex": 0,
            "passed": false,
            "cases": 3,
            "outputSha256": "6c197a1af010895c88ca80e8a08b99a538c9effd951344f1f52ccd22271dfe74"
          },
          {
            "line": 17,
            "actionIdSha256": "f4fdd034b54297294baf2c6977028dba2f4e8949c52e921b04118670cad8192e",
            "commandExitCode": 0,
            "individualCheckExitCode": null,
            "resultIndex": 0,
            "passed": true,
            "cases": 3,
            "outputSha256": "fdb6754c2a04b999647857279f4ddb3b4f762ada31dcb49b08eb1d7e76ba1944"
          }
        ],
        "failingThenLaterCheckObserved": true,
        "limitation": "Checks are identified from completed native command and public runner output, including multiple check outputs in one command. Command exit is aggregate; individual check exit codes are unknown. This confirms an observed failing check followed by a later check; it does not reconstruct every source write hidden inside shell commands."
      },
      "evidence": "runs/pnpm-changed-project-move-r1-native.json",
      "evidenceSha256": "90224a45d6ecb787525ec9d09e75d6ae13beaba0bacb2567fe6cd9bdb7806e87"
    },
    {
      "id": "pnpm-changed-project-move-r1-typelatch",
      "task": "pnpm-changed-project-move",
      "repeat": 1,
      "arm": "typelatch",
      "status": "failed",
      "startedAt": "2026-11-06T18:41:55.292Z",
      "finishedAt": "2026-11-06T18:41:55.314Z",
      "fixtureSetupMs": 17612.904333,
      "providerSetupMs": 0.0016250000044237822,
      "elapsedMs": 21.64083400000527,
      "teardownMs": 0.08379199999035336,
      "gradingMs": 8472.601125000001,
      "exitCode": 1,
      "timedOut": false,
      "processGroupStopped": true,
      "providerStopped": true,
      "correct": false,
      "capture": {
        "complete": false,
        "issues": [
          {
            "code": "expected-one-turn-start",
            "observed": 0
          },
          {
            "code": "missing-turn-completion"
          },
          {
            "code": "missing-required-usage"
          }
        ],
        "startupWarnings": [],
        "turnStarts": 0,
        "turnCompletions": 0,
        "duplicateActions": 0,
        "duplicateCompletions": 0,
        "failedTurn": false
      },
      "usage": {
        "inputTokens": null,
        "cachedInputTokens": null,
        "cacheWriteInputTokens": null,
        "outputTokens": null,
        "reasoningOutputTokens": null,
        "totalTokens": null,
        "uncachedInputTokens": null
      },
      "counts": {
        "shellCalls": 0,
        "mcpCalls": 0,
        "mcpSucceeded": 0,
        "mcpFailed": 0,
        "fileEdits": 0,
        "grepShellCalls": 0,
        "contentSearchShellCalls": 0,
        "fileListingShellCalls": 0,
        "ambiguousSearchShellCalls": 0
      },
      "fixtureSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "preparedSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "promptSha256": "ff8c8a9f67d6646b20ec49be83c3de61628eaa55187b93a329ed5261a1db5d3e",
      "recordingError": null,
      "rawSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "nativeValidation": {
        "checks": [],
        "failingThenLaterCheckObserved": false,
        "limitation": "Checks are identified from completed native command and public runner output, including multiple check outputs in one command. Command exit is aggregate; individual check exit codes are unknown. This confirms an observed failing check followed by a later check; it does not reconstruct every source write hidden inside shell commands."
      },
      "evidence": "runs/pnpm-changed-project-move-r1-typelatch.json",
      "evidenceSha256": "088bff5d16b4b4dae315aff63c3334e52d0a693c5b128258b9decc3dc33e6499"
    },
    {
      "id": "pnpm-changed-project-move-r1-competitor",
      "task": "pnpm-changed-project-move",
      "repeat": 1,
      "arm": "competitor",
      "status": "failed",
      "startedAt": "2026-11-06T18:42:49.971Z",
      "finishedAt": "2026-11-06T18:42:49.991Z",
      "fixtureSetupMs": 16854.397708000004,
      "providerSetupMs": 3.1180830000084825,
      "elapsedMs": 19.824874999991152,
      "teardownMs": 0.34362500000861473,
      "gradingMs": 8552.542625000002,
      "exitCode": 1,
      "timedOut": false,
      "processGroupStopped": true,
      "providerStopped": true,
      "correct": false,
      "capture": {
        "complete": false,
        "issues": [
          {
            "code": "expected-one-turn-start",
            "observed": 0
          },
          {
            "code": "missing-turn-completion"
          },
          {
            "code": "missing-required-usage"
          }
        ],
        "startupWarnings": [],
        "turnStarts": 0,
        "turnCompletions": 0,
        "duplicateActions": 0,
        "duplicateCompletions": 0,
        "failedTurn": false
      },
      "usage": {
        "inputTokens": null,
        "cachedInputTokens": null,
        "cacheWriteInputTokens": null,
        "outputTokens": null,
        "reasoningOutputTokens": null,
        "totalTokens": null,
        "uncachedInputTokens": null
      },
      "counts": {
        "shellCalls": 0,
        "mcpCalls": 0,
        "mcpSucceeded": 0,
        "mcpFailed": 0,
        "fileEdits": 0,
        "grepShellCalls": 0,
        "contentSearchShellCalls": 0,
        "fileListingShellCalls": 0,
        "ambiguousSearchShellCalls": 0
      },
      "fixtureSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "preparedSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "promptSha256": "ff8c8a9f67d6646b20ec49be83c3de61628eaa55187b93a329ed5261a1db5d3e",
      "recordingError": null,
      "rawSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "nativeValidation": {
        "checks": [],
        "failingThenLaterCheckObserved": false,
        "limitation": "Checks are identified from completed native command and public runner output, including multiple check outputs in one command. Command exit is aggregate; individual check exit codes are unknown. This confirms an observed failing check followed by a later check; it does not reconstruct every source write hidden inside shell commands."
      },
      "evidence": "runs/pnpm-changed-project-move-r1-competitor.json",
      "evidenceSha256": "b188f6edd86fd84921870d2c3323c5ca46d246e1e7ed87d3a89fb9406d288788"
    },
    {
      "id": "pnpm-changed-project-move-r1-packet",
      "task": "pnpm-changed-project-move",
      "repeat": 1,
      "arm": "packet",
      "status": "failed",
      "startedAt": "2026-11-06T18:43:44.837Z",
      "finishedAt": "2026-11-06T18:43:44.859Z",
      "fixtureSetupMs": 16793.601124999986,
      "providerSetupMs": 0.0014159999846015126,
      "elapsedMs": 21.38404099998297,
      "teardownMs": 0.10874999998486601,
      "gradingMs": 8494.784374999988,
      "exitCode": 1,
      "timedOut": false,
      "processGroupStopped": true,
      "providerStopped": true,
      "correct": false,
      "capture": {
        "complete": false,
        "issues": [
          {
            "code": "expected-one-turn-start",
            "observed": 0
          },
          {
            "code": "missing-turn-completion"
          },
          {
            "code": "missing-required-usage"
          }
        ],
        "startupWarnings": [],
        "turnStarts": 0,
        "turnCompletions": 0,
        "duplicateActions": 0,
        "duplicateCompletions": 0,
        "failedTurn": false
      },
      "usage": {
        "inputTokens": null,
        "cachedInputTokens": null,
        "cacheWriteInputTokens": null,
        "outputTokens": null,
        "reasoningOutputTokens": null,
        "totalTokens": null,
        "uncachedInputTokens": null
      },
      "counts": {
        "shellCalls": 0,
        "mcpCalls": 0,
        "mcpSucceeded": 0,
        "mcpFailed": 0,
        "fileEdits": 0,
        "grepShellCalls": 0,
        "contentSearchShellCalls": 0,
        "fileListingShellCalls": 0,
        "ambiguousSearchShellCalls": 0
      },
      "fixtureSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "preparedSha256": "4456c2defad3db384f3febb45378aca969fd0d3362c29ce5e4d2843e2690fc6a",
      "promptSha256": "ff8c8a9f67d6646b20ec49be83c3de61628eaa55187b93a329ed5261a1db5d3e",
      "recordingError": null,
      "rawSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "nativeValidation": {
        "checks": [],
        "failingThenLaterCheckObserved": false,
        "limitation": "Checks are identified from completed native command and public runner output, including multiple check outputs in one command. Command exit is aggregate; individual check exit codes are unknown. This confirms an observed failing check followed by a later check; it does not reconstruct every source write hidden inside shell commands."
      },
      "evidence": "runs/pnpm-changed-project-move-r1-packet.json",
      "evidenceSha256": "2cafa8e92ced4a306a0e98470451dd0490ef99281cc63e254529bd408e8ac764"
    },
    {
      "id": "pnpm-global-bin-api-migration-r1-typelatch",
      "task": "pnpm-global-bin-api-migration",
      "repeat": 1,
      "arm": "typelatch",
      "status": "failed",
      "startedAt": "2026-11-06T18:44:37.810Z",
      "finishedAt": "2026-11-06T18:44:37.830Z",
      "fixtureSetupMs": 15030.234959000023,
      "providerSetupMs": 0.0021249999990686774,
      "elapsedMs": 19.21799999999348,
      "teardownMs": 0.0867500000167638,
      "gradingMs": 7149.975749999983,
      "exitCode": 1,
      "timedOut": false,
      "processGroupStopped": true,
      "providerStopped": true,
      "correct": false,
      "capture": {
        "complete": false,
        "issues": [
          {
            "code": "expected-one-turn-start",
            "observed": 0
          },
          {
            "code": "missing-turn-completion"
          },
          {
            "code": "missing-required-usage"
          }
        ],
        "startupWarnings": [],
        "turnStarts": 0,
        "turnCompletions": 0,
        "duplicateActions": 0,
        "duplicateCompletions": 0,
        "failedTurn": false
      },
      "usage": {
        "inputTokens": null,
        "cachedInputTokens": null,
        "cacheWriteInputTokens": null,
        "outputTokens": null,
        "reasoningOutputTokens": null,
        "totalTokens": null,
        "uncachedInputTokens": null
      },
      "counts": {
        "shellCalls": 0,
        "mcpCalls": 0,
        "mcpSucceeded": 0,
        "mcpFailed": 0,
        "fileEdits": 0,
        "grepShellCalls": 0,
        "contentSearchShellCalls": 0,
        "fileListingShellCalls": 0,
        "ambiguousSearchShellCalls": 0
      },
      "fixtureSha256": "ee4ac20446106435d226405e542fc416e56a75076a77009593d4f0573db64f15",
      "preparedSha256": "ee4ac20446106435d226405e542fc416e56a75076a77009593d4f0573db64f15",
      "promptSha256": "b9bc75bd344b4756686ca8f44a8ac7f45388ecb90d9d6546752c6960bbb14f1b",
      "recordingError": null,
      "rawSha256": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
      "nativeValidation": {
        "checks": [],
        "failingThenLaterCheckObserved": false,
        "limitation": "Checks are identified from completed native command and public runner output, including multiple check outputs in one command. Command exit is aggregate; individual check exit codes are unknown. This confirms an observed failing check followed by a later check; it does not reconstruct every source write hidden inside shell commands."
      },
      "evidence": "runs/pnpm-global-bin-api-migration-r1-typelatch.json",
      "evidenceSha256": "0f698bae1f275f50bcef1dfb1ea0a7e66d9eabd811916741b8d675dda2d2ede3"
    }
  ]
}