{
  "assessment": {
    "decisions": [
      {
        "decided_by": "locality",
        "defect_id": "12",
        "finding_id": "f1",
        "id": "d1",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "17",
        "finding_id": "f2",
        "id": "d2",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "18",
        "finding_id": "f3",
        "id": "d3",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "4",
        "finding_id": "f4",
        "id": "d4",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "6",
        "finding_id": "f5",
        "id": "d5",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "11",
        "finding_id": "f6",
        "id": "d6",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "1",
        "finding_id": "f7",
        "id": "d7",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "2",
        "finding_id": "f8",
        "id": "d8",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "13",
        "finding_id": "f9",
        "id": "d9",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "5",
        "finding_id": "f10",
        "id": "d10",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "7",
        "finding_id": "f11",
        "id": "d11",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "3",
        "finding_id": "f12",
        "id": "d12",
        "outcome": "matched",
        "reason": null
      }
    ],
    "judge": null,
    "judged": false,
    "scorer": {
      "commit": "348a7e367b8c52f1ce72828ed09c15b0e9fac38b",
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "bench-score",
      "version": "1"
    },
    "state": "measured"
  },
  "benchmark": {
    "input_fingerprint": "69301578538a",
    "key_fingerprint": "bd331c0b144e",
    "policy_fingerprint": "c53f8cfc8c75",
    "prompt_fingerprint": "74234e98afe7",
    "subject": "proxy"
  },
  "build": {
    "commit": "b0f313c0b59a66ecc7612396dc8db0ea5da13a7a",
    "digest": null,
    "dirty": false,
    "label": "afi 0.30.0",
    "version": "0.30.0"
  },
  "configuration": {
    "fingerprint": "89cd13e3b4e0",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "openai/gpt-5.6-sol",
        "protocol": null,
        "provider": "openai",
        "role": "agent"
      }
    ],
    "profile": null,
    "resolved": {
      "effort": "high",
      "instructions": [],
      "sandbox": {
        "backend": "macOS Seatbelt",
        "mode": "read-only",
        "network": "denied"
      },
      "source": "openrouter",
      "system_prompt": {
        "file": null,
        "mode": "builtin"
      },
      "tools": [
        "read_file",
        "write_file",
        "edit_file",
        "list_dir",
        "search_files",
        "glob_files",
        "run_bash",
        "wait_background"
      ]
    }
  },
  "coverage": {
    "chunks": null,
    "files_failed": 0,
    "files_kept": null,
    "files_skipped": 0,
    "files_unreviewed": 0,
    "hunks": null,
    "state": "measured"
  },
  "evidence": [
    {
      "digest": "sha256:962e3e344998b41369cffef272f5ab05479d1ba6f004816a3f6682f5e5f17404",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:7b97b1c4d57e38baa117629126f11cc74ed68f3b99f26e10a9f7d7720ecaffac",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:a6fbee0aff6c5c01fb07bf6d86379f14a17a01d9645a459937f48d7ddaf6b13e",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:adc06c4158543b64d469eb00f9e8af1710fe9196cfc5edd1024c0d9c01dd7265",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:2b7b64d88d6ed066c4474c48ce5c3292a3ff156fc7ee66ebcb99bf558ab8ab5a",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:281d1c27f018dfebd95fc66a7312d60e41cdcaad8d7a25a1c9caf64d7afbf0b5",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:61f184591fa331aab75e3e4dca6a420a7872492e1350cd8dceec492622bbb903",
      "media_type": "application/gzip",
      "path": "afi-home/logs.tar.gz",
      "role": "traffic"
    }
  ],
  "execution": {
    "billing_limit_usd": 8.0,
    "budget_usd": 8.0,
    "deadline_exceeded": false,
    "exit_code": 0,
    "finished_at": "2026-08-31T15:48:20Z",
    "started_at": "2026-08-31T15:46:15Z",
    "wall_seconds": 125.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 12
      },
      "passes": null,
      "review_seconds": 123.893,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "forget` runs even for `dry_run=true`, deleting index entries and turning a supposedly non-destructive preview into cache misses and upstream refetches",
        "id": "f1",
        "locations": [
          {
            "end_line": 140,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 140
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The sweep unlinks every file in `incoming` without checking age or ownership, including active artifact and index writes, causing concurrent fetches to fail during commit or link",
        "id": "f2",
        "locations": [
          {
            "end_line": 232,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 232
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "A newly committed blob is temporarily absent from the index before `BlobStore::link`, so a concurrent sweep treats it as orphaned, deletes it, and makes the in-flight cache request fail",
        "id": "f3",
        "locations": [
          {
            "end_line": 119,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 119
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "security",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "fs::metadata` follows directory symlinks, so recursive collection can escape the blob root and the sweep can delete files in the symlink target",
        "id": "f4",
        "locations": [
          {
            "end_line": 164,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 164
          }
        ],
        "severity": "security",
        "title": "security"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "On-demand sweeps call `sweep` directly instead of the mutex-protected `run`, allowing HTTP sweeps and the scheduled sweep to overlap and over-evict the cache",
        "id": "f5",
        "locations": [
          {
            "end_line": 76,
            "path": "services/proxy/src/routes/admin.rs",
            "start_line": 76
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "performance",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The synchronous recursive filesystem walk runs directly on a Tokio worker thread, so a large scheduled or HTTP sweep can stall unrelated requests",
        "id": "f6",
        "locations": [
          {
            "end_line": 84,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 84
          }
        ],
        "severity": "performance",
        "title": "performance"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Sorting elapsed ages ascending processes the newest blobs first, so capacity eviction removes recently written blobs instead of the oldest ones",
        "id": "f7",
        "locations": [
          {
            "end_line": 102,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 102
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Failed deletions are still subtracted from `remaining`, counted as reclaimed, and added to `gone`, so the sweep can delete their index entries while leaving the bytes on disk and falsely report the\u2026\n\nFailed deletions are still subtracted from `remaining`, counted as reclaimed, and added to `gone`, so the sweep can delete their index entries while leaving the bytes on disk and falsely report the store under its ceiling",
        "id": "f8",
        "locations": [
          {
            "end_line": 134,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 134
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Sweep metric values are emitted in the reverse order of `COUNTERS`, causing the blobs-removed metric to report bytes and the bytes-reclaimed metric to report blob count",
        "id": "f9",
        "locations": [
          {
            "end_line": 94,
            "path": "services/proxy/src/metrics.rs",
            "start_line": 94
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "performance",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Eviction age uses modification time, which cache reads never update, so frequently accessed old blobs are treated as cold and evicted while less-used newer blobs remain",
        "id": "f10",
        "locations": [
          {
            "end_line": 186,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 186
          }
        ],
        "severity": "performance",
        "title": "performance"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "tokio::time::interval` yields its first tick immediately, so the proxy sweeps at startup rather than waiting one configured interval as documented",
        "id": "f11",
        "locations": [
          {
            "end_line": 108,
            "path": "services/proxy/src/main.rs",
            "start_line": 108
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Using `remaining >= self.max_bytes` evicts a blob when usage exactly equals the configured maximum, even though the store is already within the ceiling",
        "id": "f12",
        "locations": [
          {
            "end_line": 120,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 120
          }
        ],
        "severity": "bug",
        "title": "bug"
      }
    ],
    "problems": [],
    "state": "measured"
  },
  "harness": {
    "adapter": {
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "afi",
      "version": "1"
    },
    "commit": "348a7e367b8c52f1ce72828ed09c15b0e9fac38b",
    "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
    "dirty": true,
    "id": "bench",
    "repository_url": "https://github.com/smykla-skalski/benchee",
    "version": "1"
  },
  "incremental": {
    "carried_count": null,
    "mode": "not_recorded",
    "prior_reviewed_sha": null,
    "reused_tokens": null,
    "state_source": null
  },
  "label": "gpt-5.6-sol",
  "metrics": {
    "anchor_max": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    },
    "anchor_median": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    },
    "anchor_missed": {
      "reason": "no judging pass has looked beyond the scored slack",
      "state": "not_recorded",
      "unit": "count",
      "value": null
    },
    "carried": {
      "reason": "the reviewer reported no reuse figure",
      "state": "not_recorded",
      "unit": "count",
      "value": null
    },
    "category_defect": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.7692307692307693
    },
    "category_maintainability": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "category_performance": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.3333333333333333
    },
    "category_security": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.5
    },
    "f1": {
      "reason": "no qualified judge decided these findings, so only locality was measured",
      "state": "not_applicable",
      "unit": "ratio",
      "value": null
    },
    "finding_count": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 12
    },
    "found": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 12
    },
    "intended": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    },
    "judge_bill": {
      "reason": "no qualified judge decided these findings, so only locality was measured",
      "state": "not_applicable",
      "unit": "usd",
      "value": null
    },
    "missed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 8
    },
    "precision": {
      "reason": "no qualified judge decided these findings, so only locality was measured",
      "state": "not_applicable",
      "unit": "ratio",
      "value": null
    },
    "recall": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.6
    },
    "review_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.1997509
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 125.0
    },
    "tier_1": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 1.0
    },
    "tier_2": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.5714285714285714
    },
    "tier_3": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.5
    },
    "tier_4": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.5
    },
    "tokens": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 1574
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.1997509
    },
    "unkeyed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    }
  },
  "producer": {
    "commit": "348a7e367b8c52f1ce72828ed09c15b0e9fac38b",
    "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
    "dirty": true,
    "id": "benchee",
    "repository_url": "https://github.com/smykla-skalski/benchee",
    "version": "1"
  },
  "reviewer": {
    "id": "afi",
    "label": "afi review",
    "repository_url": "https://github.com/smykla-skalski/afi",
    "tool": {
      "interface": "cli",
      "name": "afi"
    }
  },
  "run_id": "afi/gpt-5.6-sol/20260831T154613Z",
  "runtime": {
    "architecture": "arm64",
    "cache_mode": null,
    "cpus": 14,
    "memory_bytes": 38654705664,
    "os": "Darwin",
    "provider_route": "openrouter",
    "region": null,
    "runner_image": null
  },
  "schema": "benchee-run-1",
  "stamp": "20260831T154613Z",
  "status": {
    "reason": null,
    "state": "completed"
  },
  "target": {
    "base_sha": null,
    "diff_digest": "sha256:8b6acd80424c8af9017d7db2e1ceeaca4da5cf1f29e87c3559b2e5ea55782cfe",
    "pull_request": 8,
    "repository_url": "https://github.com/smykla-skalski/cairn",
    "reviewed_sha": "9b51f95ef609a219e211e37b082cd2e6913190e0"
  },
  "usage": {
    "reason": null,
    "state": "measured",
    "value": {
      "cached_input_tokens": 96617,
      "input_tokens": 15,
      "models": null,
      "output_tokens": 1559,
      "reasoning_tokens": 6785,
      "requests": 5,
      "stages": []
    }
  }
}