{
  "version": 5,
  "program": "missing_pytest_module_retry_v5",
  "title": "Retry a missing pytest command through registered Python",
  "kind": "conditional-gross-recorded-usage-replay-estimate",
  "policy": {
    "registeredInterpreter": "python3",
    "maxCommandBytes": 4096,
    "maxTargets": 8,
    "maxRetries": 1,
    "maxOutputBytes": 32768,
    "timeoutSeconds": 120,
    "requiresWorkingRegisteredPytestModule": true,
    "requiresSameEnvironmentAndRepository": true,
    "requiresExplicitRetryPolicy": true
  },
  "trajectories": 2498,
  "issues": 500,
  "denominator": {
    "calls": 129846,
    "callsWithUsage": 129846,
    "inputTokens": 3201225688,
    "inputTokensReportedCalls": 129846,
    "outputTokens": 42377608,
    "outputTokensReportedCalls": 129846,
    "totalTokens": 3243603296,
    "totalTokensReportedCalls": 129846,
    "cachedInputTokens": 2498865874,
    "cachedInputTokensReportedCalls": 121228,
    "cacheCreationInputTokens": 31547900,
    "cacheCreationInputTokensReportedCalls": 40589,
    "reasoningOutputTokens": 23075825,
    "reasoningOutputTokensReportedCalls": 129846,
    "sourceReportedCostSum": 1344.591070199989,
    "callsWithReportedCost": 129846
  },
  "proposals": 106,
  "matchedCalls": 0,
  "matchedIssues": 0,
  "matchedUsage": {
    "calls": 0,
    "callsWithUsage": 0,
    "inputTokens": 0,
    "inputTokensReportedCalls": 0,
    "outputTokens": 0,
    "outputTokensReportedCalls": 0,
    "totalTokens": 0,
    "totalTokensReportedCalls": 0,
    "cachedInputTokens": 0,
    "cachedInputTokensReportedCalls": 0,
    "cacheCreationInputTokens": 0,
    "cacheCreationInputTokensReportedCalls": 0,
    "reasoningOutputTokens": 0,
    "reasoningOutputTokensReportedCalls": 0,
    "sourceReportedCostSum": 0,
    "callsWithReportedCost": 0
  },
  "matchPercent": 0.0,
  "callPercent": 0.0,
  "tokenPercent": 0.0,
  "matchesWithReasoningOrProse": 0,
  "retryExitCodes": {},
  "diagnostics": {
    "nativeMissingPytestErrors": 122,
    "nextCommandDiffers": 94,
    "nextRetryUnavailableOrUnbounded": 12,
    "matchingCommandButPytestModuleMissing": 12
  },
  "cohorts": {
    "deepseek32": {
      "trajectories": 500,
      "issues": 500,
      "denominator": {
        "calls": 43683,
        "callsWithUsage": 43683,
        "inputTokens": 1177730550,
        "inputTokensReportedCalls": 43683,
        "outputTokens": 13441973,
        "outputTokensReportedCalls": 43683,
        "totalTokens": 1191172523,
        "totalTokensReportedCalls": 43683,
        "cachedInputTokens": 798975703,
        "cachedInputTokensReportedCalls": 43683,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 7941114,
        "reasoningOutputTokensReportedCalls": 43683,
        "sourceReportedCostSum": 223.9232482499986,
        "callsWithReportedCost": 43683
      },
      "proposals": 0,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {}
    },
    "gemini3flash": {
      "trajectories": 498,
      "issues": 498,
      "denominator": {
        "calls": 28054,
        "callsWithUsage": 28054,
        "inputTokens": 847926935,
        "inputTokensReportedCalls": 28054,
        "outputTokens": 10071357,
        "outputTokensReportedCalls": 28054,
        "totalTokens": 857998292,
        "totalTokensReportedCalls": 28054,
        "cachedInputTokens": 613767718,
        "cachedInputTokensReportedCalls": 19436,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 7549905,
        "reasoningOutputTokensReportedCalls": 28054,
        "sourceReportedCostSum": 177.98206539999973,
        "callsWithReportedCost": 28054
      },
      "proposals": 95,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0.0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {
        "nativeMissingPytestErrors": 110,
        "nextCommandDiffers": 83,
        "nextRetryUnavailableOrUnbounded": 12,
        "matchingCommandButPytestModuleMissing": 12
      }
    },
    "gpt52": {
      "trajectories": 500,
      "issues": 500,
      "denominator": {
        "calls": 17520,
        "callsWithUsage": 17520,
        "inputTokens": 322598043,
        "inputTokensReportedCalls": 17520,
        "outputTokens": 6692906,
        "outputTokensReportedCalls": 17520,
        "totalTokens": 329290949,
        "totalTokensReportedCalls": 17520,
        "cachedInputTokens": 267596032,
        "cachedInputTokensReportedCalls": 17520,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 4871131,
        "reasoningOutputTokensReportedCalls": 17520,
        "sourceReportedCostSum": 236.78350885000094,
        "callsWithReportedCost": 17520
      },
      "proposals": 11,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0.0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {
        "nativeMissingPytestErrors": 12,
        "nextCommandDiffers": 11
      }
    },
    "opus45": {
      "trajectories": 500,
      "issues": 500,
      "denominator": {
        "calls": 16446,
        "callsWithUsage": 16446,
        "inputTokens": 330622219,
        "inputTokensReportedCalls": 16446,
        "outputTokens": 4806100,
        "outputTokensReportedCalls": 16446,
        "totalTokens": 335428319,
        "totalTokensReportedCalls": 16446,
        "cachedInputTokens": 314095302,
        "cachedInputTokensReportedCalls": 16446,
        "cacheCreationInputTokens": 13695410,
        "cacheCreationInputTokensReportedCalls": 16446,
        "reasoningOutputTokens": 1193410,
        "reasoningOutputTokensReportedCalls": 16446,
        "sourceReportedCostSum": 376.95399849999967,
        "callsWithReportedCost": 16446
      },
      "proposals": 0,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {}
    },
    "sonnet45": {
      "trajectories": 500,
      "issues": 500,
      "denominator": {
        "calls": 24143,
        "callsWithUsage": 24143,
        "inputTokens": 522347941,
        "inputTokensReportedCalls": 24143,
        "outputTokens": 7365272,
        "outputTokensReportedCalls": 24143,
        "totalTokens": 529713213,
        "totalTokensReportedCalls": 24143,
        "cachedInputTokens": 504431119,
        "cachedInputTokensReportedCalls": 24143,
        "cacheCreationInputTokens": 17852490,
        "cacheCreationInputTokensReportedCalls": 24143,
        "reasoningOutputTokens": 1520265,
        "reasoningOutputTokensReportedCalls": 24143,
        "sourceReportedCostSum": 328.9482491999996,
        "callsWithReportedCost": 24143
      },
      "proposals": 0,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {}
    }
  },
  "byPartition": {
    "discovery": {
      "trajectories": 550,
      "issues": 110,
      "denominator": {
        "calls": 28862,
        "callsWithUsage": 28862,
        "inputTokens": 702102702,
        "inputTokensReportedCalls": 28862,
        "outputTokens": 9426963,
        "outputTokensReportedCalls": 28862,
        "totalTokens": 711529665,
        "totalTokensReportedCalls": 28862,
        "cachedInputTokens": 543584191,
        "cachedInputTokensReportedCalls": 27013,
        "cacheCreationInputTokens": 6709415,
        "cacheCreationInputTokensReportedCalls": 8757,
        "reasoningOutputTokens": 5220878,
        "reasoningOutputTokensReportedCalls": 28862,
        "sourceReportedCostSum": 291.47569229000186,
        "callsWithReportedCost": 28862
      },
      "proposals": 21,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0.0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {
        "nativeMissingPytestErrors": 25,
        "nextCommandDiffers": 17,
        "nextRetryUnavailableOrUnbounded": 4,
        "matchingCommandButPytestModuleMissing": 4
      }
    },
    "validation": {
      "trajectories": 1948,
      "issues": 390,
      "denominator": {
        "calls": 100984,
        "callsWithUsage": 100984,
        "inputTokens": 2499122986,
        "inputTokensReportedCalls": 100984,
        "outputTokens": 32950645,
        "outputTokensReportedCalls": 100984,
        "totalTokens": 2532073631,
        "totalTokensReportedCalls": 100984,
        "cachedInputTokens": 1955281683,
        "cachedInputTokensReportedCalls": 94215,
        "cacheCreationInputTokens": 24838485,
        "cacheCreationInputTokensReportedCalls": 31832,
        "reasoningOutputTokens": 17854947,
        "reasoningOutputTokensReportedCalls": 100984,
        "sourceReportedCostSum": 1053.1153779099996,
        "callsWithReportedCost": 100984
      },
      "proposals": 85,
      "matchedCalls": 0,
      "matchedIssues": 0,
      "matchedUsage": {
        "calls": 0,
        "callsWithUsage": 0,
        "inputTokens": 0,
        "inputTokensReportedCalls": 0,
        "outputTokens": 0,
        "outputTokensReportedCalls": 0,
        "totalTokens": 0,
        "totalTokensReportedCalls": 0,
        "cachedInputTokens": 0,
        "cachedInputTokensReportedCalls": 0,
        "cacheCreationInputTokens": 0,
        "cacheCreationInputTokensReportedCalls": 0,
        "reasoningOutputTokens": 0,
        "reasoningOutputTokensReportedCalls": 0,
        "sourceReportedCostSum": 0,
        "callsWithReportedCost": 0
      },
      "matchPercent": 0.0,
      "callPercent": 0.0,
      "tokenPercent": 0.0,
      "matchesWithReasoningOrProse": 0,
      "retryExitCodes": {},
      "diagnostics": {
        "nativeMissingPytestErrors": 97,
        "nextCommandDiffers": 77,
        "nextRetryUnavailableOrUnbounded": 8,
        "matchingCommandButPytestModuleMissing": 8
      }
    }
  },
  "split": {
    "method": "SHA256('autotoken-v5:'+issue_id)%5==0 discovery; all other issues validation, grouped across models",
    "policyFrozenBeforeValidation": true,
    "notUntouchedExternalValidation": true
  },
  "sourceManifestSha256": "73cccd8079f5c3150015207a7d102f1a4409c7996f0ea9ae1305f1b45239247b",
  "plannerSha256": "ab3e70250de9e07a998253f3dbabb963055cc8b3dd370c27e63c990925fdc256",
  "limitations": [
    "Frozen after discovery-only inspection; validation never used to choose interpreter, arguments or trigger.",
    "Exact match means same canonical cwd/arguments for python3 -m pytest; python and python3 are not treated as interchangeable.",
    "Only standalone bounded invocations on explicit repository Python targets are supported. No install, shell bundle, pipeline, redirect, configuration edits or target guessing.",
    "Runtime must register a working Python3/pytest environment and unchanged repository, and enforce explicit retry/output/runtime bounds. Historical runtime registration is unverified.",
    "Missing pytest module results are excluded. A matched retry can still fail tests or collection; process success is not bug-fix quality.",
    "A matching response may contain needed reasoning. Recorded usage is a conditional gross opportunity, not demonstrated savings.",
    "Input includes cache subsets; output includes reasoning. No double counting.",
    "Routing/execution/false-positive costs and subsequent context/cache changes are not modeled.",
    "No recorded commands executed or paid inference used."
  ]
}
