{
  "assessment": {
    "decisions": [
      {
        "decided_by": "scorer",
        "defect_id": null,
        "finding_id": "f1",
        "id": "d1",
        "outcome": "rejected",
        "reason": null
      },
      {
        "decided_by": "scorer",
        "defect_id": null,
        "finding_id": "f2",
        "id": "d2",
        "outcome": "rejected",
        "reason": null
      }
    ],
    "judge": null,
    "judged": false,
    "scorer": {
      "commit": "10b3b2068100b7ba429855e062500eaf83b90120",
      "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": "42c620064e2e",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "deepseek/deepseek-v4-flash",
        "protocol": null,
        "provider": "deepseek",
        "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": "sha256:6bac378d81b3e7f8867607d182e2a7d71a9e7bef88d847f9a4ac788795500259",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:6d5fd193399c27251e7b61cafe110a92411aac7f665d2c94032a20a29b71ae22",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:d553198c372d90d9d8e49392b4b9693364cb5d6ea00650db14274d229662117d",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:be8c102d7e14588cd1b3c497d510277cad25ea91a02b902a1a1287ff6550ad61",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:6eabbeeabf56100a989eaca8ef4cd31169ee971dbf8d60865027df7e5d913ea0",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:841cc0dc2b5316acae1eaf24313bf07ef8b59507b29fd3cc9c7ce3084375ff96",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:5b6a4a9554c27780082e31e8eb7ec01ea436608b992d1aa8ba1d5c04c7112ab1",
      "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": "2026-08-31T11:45:58Z",
    "started_at": "2026-08-31T11:41:24Z",
    "wall_seconds": 274.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 2
      },
      "passes": null,
      "review_seconds": 271.495,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "COUNTERS[4]` is `cairn_proxy_sweep_blobs_removed_total` and `COUNTERS[5]` is `cairn_proxy_sweep_bytes_reclaimed_total`, but `values()[4]` loads `self.sweep_bytes_reclaimed` while `values()[5]` loads\u2026\n\nCOUNTERS[4]` is `cairn_proxy_sweep_blobs_removed_total` and `COUNTERS[5]` is `cairn_proxy_sweep_bytes_reclaimed_total`, but `values()[4]` loads `self.sweep_bytes_reclaimed` while `values()[5]` loads `self.sweep_blobs_removed`. The `render()` method zips them positionally, so every metrics scrape would report the blob count under the \"bytes reclaimed\" metric name and the byte count under the \"blobs removed\" metric name \u2014 the two new counters are swapped.",
        "id": "f1",
        "locations": [
          {
            "end_line": 88,
            "path": "services/proxy/src/metrics.rs",
            "start_line": 88
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "the on-demand sweep route calls `app.sweeper.sweep(dry_run)` directly, which never acquires the `Sweeper::running` mutex.\n\nOnly the background path (`Sweeper::run()`) locks that mutex. Two concurrent POSTs to `/v1/admin/cache/sweep`, or one concurrent with the background sweep, therefore execute `sweep()` simultaneously, each making independent removal decisions against a filesystem state the other is mutating \u2014 directly violating the \"one sweep at a time\" invariant documented in `sweep.rs:10-12`.",
        "id": "f2",
        "locations": [
          {
            "end_line": 76,
            "path": "services/proxy/src/admin.rs",
            "start_line": 76
          }
        ],
        "severity": "bug",
        "title": "bug"
      }
    ],
    "problems": [],
    "state": "measured"
  },
  "harness": {
    "adapter": {
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "afi",
      "version": "1"
    },
    "commit": "10b3b2068100b7ba429855e062500eaf83b90120",
    "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": "deepseek-v4-flash",
  "metrics": {
    "anchor_max": {
      "reason": "no finding matched a defect, so there is no anchor distance",
      "state": "not_applicable",
      "unit": "count",
      "value": null
    },
    "anchor_median": {
      "reason": "no finding matched a defect, so there is no anchor distance",
      "state": "not_applicable",
      "unit": "count",
      "value": null
    },
    "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": 0.0
    },
    "category_maintainability": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "category_performance": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "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": 2
    },
    "found": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    },
    "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": 20
    },
    "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": 0.0
    },
    "review_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.022014244
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 274.0
    },
    "tier_1": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "tier_2": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "tier_3": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "tier_4": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "tokens": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 71896
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.022014244
    },
    "unkeyed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 2
    }
  },
  "producer": {
    "commit": "10b3b2068100b7ba429855e062500eaf83b90120",
    "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/deepseek-v4-flash/20260831T111215Z",
  "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": "20260831T111215Z",
  "status": {
    "reason": null,
    "state": "completed"
  },
  "target": {
    "base_sha": null,
    "diff_digest": "sha256:5b2a32e0467b97b089d6d82893abeb78d4c381923004a6dcce9092d250ea0f4d",
    "pull_request": 8,
    "repository_url": "https://github.com/smykla-skalski/cairn",
    "reviewed_sha": "9b51f95ef609a219e211e37b082cd2e6913190e0"
  },
  "usage": {
    "reason": null,
    "state": "measured",
    "value": {
      "cached_input_tokens": 99328,
      "input_tokens": 70825,
      "models": null,
      "output_tokens": 1071,
      "reasoning_tokens": 32206,
      "requests": 6,
      "stages": []
    }
  }
}