{
  "assessment": {
    "decisions": [
      {
        "decided_by": "locality",
        "defect_id": "2",
        "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": "11",
        "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": "13",
        "finding_id": "f6",
        "id": "d6",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "3",
        "finding_id": "f7",
        "id": "d7",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "7",
        "finding_id": "f8",
        "id": "d8",
        "outcome": "matched",
        "reason": null
      }
    ],
    "judge": null,
    "judged": false,
    "scorer": {
      "commit": "631c4107752a97104719622800c9815e030613cf",
      "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": "8c8c79c46163",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "openai/gpt-5.6-luna",
        "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": "sha256:1e1bdc1803df43666b03b9b51bba249e9334a1388ad7c191f6649fff2b3c74d5",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:21309f60fb9cf6ddace900569b07928d652a099e79f08cac286fc2ec7147b4ac",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:9cdfd3f325c2d2bc92fa8426a0db142c872a73788f1ccbec3c05b6899d89d929",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:a5d333b74122c7888ca129e1663cd761390c0ddb97fb1fa3b3c7d4ae724ffcce",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:32540ae0a3089ebf91dae36327522553b667ee94142c294910587dfece28a79c",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:100ed00c7cd55e3d01d4be22b534e93a17304732d413f2ec5f3d87a1af8e23f3",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:7f89817c0c06e84d0198fb324ef167c1368d70522d10058230390e17275babf9",
      "media_type": "application/gzip",
      "path": "afi-home/logs.tar.gz",
      "role": "traffic"
    }
  ],
  "execution": {
    "billing_limit_usd": 2.0,
    "budget_usd": 2.0,
    "deadline_exceeded": false,
    "exit_code": 0,
    "finished_at": "2026-08-31T14:34:48Z",
    "started_at": "2026-08-31T14:31:36Z",
    "wall_seconds": 192.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 8
      },
      "passes": null,
      "review_seconds": 190.786,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": ",140: Dry runs still pass the populated `gone` list to `forget`, deleting index entries even though the blobs were not removed; `?dry_run=true` therefore changes cache behavior and causes subsequent\u2026\n\n,140: Dry runs still pass the populated `gone` list to `forget`, deleting index entries even though the blobs were not removed; `?dry_run=true` therefore changes cache behavior and causes subsequent requests to refetch.",
        "id": "f1",
        "locations": [
          {
            "end_line": 137,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 137
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The sweep deletes every file in `incoming` without distinguishing active writers from abandoned partials, so an in-flight fetch can have its temporary file unlinked and then fail at\u2026\n\nThe sweep deletes every file in `incoming` without distinguishing active writers from abandoned partials, so an in-flight fetch can have its temporary file unlinked and then fail at `BlobWriter::commit`.",
        "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 has no index entry until the later link operation, so the sweep can delete it in that window and make the current fetch fail when it reopens the committed blob.",
        "id": "f3",
        "locations": [
          {
            "end_line": 119,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 119
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The synchronous sweep bypasses `Sweeper::running`, allowing concurrent admin sweeps and overlap with the background sweep, which can produce conflicting scans and over-eviction.",
        "id": "f4",
        "locations": [
          {
            "end_line": 76,
            "path": "services/proxy/src/routes/admin.rs",
            "start_line": 76
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The full synchronous filesystem walk and index read run directly on a Tokio request worker, so a large cache or concurrent sweep requests can block unrelated proxy traffic.",
        "id": "f5",
        "locations": [
          {
            "end_line": 76,
            "path": "services/proxy/src/routes/admin.rs",
            "start_line": 76
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The values place reclaimed bytes before removed blobs, while `COUNTERS` declares blobs before bytes, causing both sweep Prometheus metrics to report the other counter's value.",
        "id": "f6",
        "locations": [
          {
            "end_line": 94,
            "path": "services/proxy/src/metrics.rs",
            "start_line": 94
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Using `remaining >= max_bytes` evicts an eligible old blob even when the store is exactly at its configured ceiling, unnecessarily shrinking the cache on every sweep at that boundary.",
        "id": "f7",
        "locations": [
          {
            "end_line": 120,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 120
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "tokio::time::interval` fires its first tick immediately, contrary to the comment and intended behavior, so a proxy sweeps the cache during startup instead of waiting for the configured interval.",
        "id": "f8",
        "locations": [
          {
            "end_line": 108,
            "path": "services/proxy/src/main.rs",
            "start_line": 108
          }
        ],
        "severity": "bug",
        "title": "bug"
      }
    ],
    "problems": [],
    "state": "measured"
  },
  "harness": {
    "adapter": {
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "afi",
      "version": "1"
    },
    "commit": "631c4107752a97104719622800c9815e030613cf",
    "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-luna",
  "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": 0.5384615384615384
    },
    "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": 0.0
    },
    "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": 8
    },
    "found": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 8
    },
    "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": 12
    },
    "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": 0.4
    },
    "review_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.0387482
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 192.0
    },
    "tier_1": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.6666666666666666
    },
    "tier_2": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.2857142857142857
    },
    "tier_3": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.3333333333333333
    },
    "tier_4": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.5
    },
    "tokens": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 1427
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.0387482
    },
    "unkeyed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    }
  },
  "producer": {
    "commit": "631c4107752a97104719622800c9815e030613cf",
    "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-luna/20260831T143133Z",
  "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": "20260831T143133Z",
  "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": 237890,
      "input_tokens": 21,
      "models": null,
      "output_tokens": 1406,
      "reasoning_tokens": 15080,
      "requests": 7,
      "stages": []
    }
  }
}