{
  "assessment": {
    "decisions": [
      {
        "decided_by": "locality",
        "defect_id": "13",
        "finding_id": "f1",
        "id": "d1",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "12",
        "finding_id": "f2",
        "id": "d2",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "6",
        "finding_id": "f3",
        "id": "d3",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "8",
        "finding_id": "f4",
        "id": "d4",
        "outcome": "matched",
        "reason": null
      }
    ],
    "judge": null,
    "judged": false,
    "scorer": {
      "commit": "c4bc25bc962489fe5de7f71b59f19b2f426564c0",
      "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": "2116b14e41cc",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "minimax/minimax-m3",
        "protocol": null,
        "provider": "minimax",
        "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": "sha256:0332bfce9a1b449d05637d512a7f6ea9e152fea138da50acdaa32fe0f7fa87a4",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:2e66536a1571a2fa03a9741bc87c87a07de119338d4c03a144d2c3fc5d1e3cc4",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:60f137a29d167fa626b49c855d3a608aafff48a7efa2f703d79aa1405d7581e5",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:f49d036319c77dc117384b9b3f14bbb14deef0eba29472962a4a777003505b87",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:f91671db56887ba5df8530588b8cd330fe37cfec837647b1b0444e73a23ef9e3",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:27cdef74c06a278f364ffe9525f239d8ddf0e99602501ff3ab7cfe24e02073eb",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:5f1ef7c1e7dbea183afac3ae30b5eec4da2f97c8492d7600f9807e06cb63f977",
      "media_type": "application/gzip",
      "path": "afi-home/logs.tar.gz",
      "role": "traffic"
    }
  ],
  "execution": {
    "billing_limit_usd": 3.0,
    "budget_usd": 3.0,
    "deadline_exceeded": false,
    "exit_code": 0,
    "finished_at": "2026-08-31T17:03:21Z",
    "started_at": "2026-08-31T16:58:28Z",
    "wall_seconds": 293.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 4
      },
      "passes": null,
      "review_seconds": 290.849,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The `values()` array orders the two new counters as `[..., sweep_bytes_reclaimed, sweep_blobs_removed]`, but the `COUNTERS` table at line 33-58 lists them as `[..., sweep_blobs_removed_total,\u2026\n\nThe `values()` array orders the two new counters as `[..., sweep_bytes_reclaimed, sweep_blobs_removed]`, but the `COUNTERS` table at line 33-58 lists them as `[..., sweep_blobs_removed_total, sweep_bytes_reclaimed_total]`. `render()` pairs them positionally, so Prometheus sees blobs_removed reporting the bytes total and bytes_reclaimed reporting the blob count \u2014 exactly the swap the \"Keeping the two side by side\" comment is supposed to prevent.",
        "id": "f1",
        "locations": [
          {
            "end_line": 95,
            "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": "forget(&index, &gone)` is invoked unconditionally at the end of `sweep`, and `gone` accumulates hex digests regardless of `dry_run` (line 137).\n\nThe route is documented as `?dry_run=true` reports what a sweep would reclaim without removing anything, but a dry run still `unlink`s the index files via `forget`, leaving blobs on disk with no index entries and forcing a refetch on the next cache lookup.",
        "id": "f2",
        "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": "reclaim` calls `app.sweeper.sweep(dry_run)` (the synchronous entry point at sweep.rs:90), bypassing the `tokio::sync::Mutex` that `Sweeper::run` (sweep.rs:82-85) acquires to honour the module's \"One\u2026\n\nreclaim` calls `app.sweeper.sweep(dry_run)` (the synchronous entry point at sweep.rs:90), bypassing the `tokio::sync::Mutex` that `Sweeper::run` (sweep.rs:82-85) acquires to honour the module's \"One sweep at a time\" promise. The background task and any number of concurrent admin requests can now run sweeps in parallel, each iterating candidates over a total the other is mutating.",
        "id": "f3",
        "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": "tokio::time::interval(app.cfg.sweep_interval)` fires its first tick at t=0, but the surrounding doc comment on line 106-108 claims \"The first tick is one interval away, which is what keeps a proxy\u2026\n\ntokio::time::interval(app.cfg.sweep_interval)` fires its first tick at t=0, but the surrounding doc comment on line 106-108 claims \"The first tick is one interval away, which is what keeps a proxy that has only just started from sweeping a cache it has not begun to fill.\" A fresh proxy sweeps an empty store immediately on startup; either the comment or the choice of constructor (`interval_at`) is wrong.",
        "id": "f4",
        "locations": [
          {
            "end_line": 113,
            "path": "services/proxy/src/main.rs",
            "start_line": 113
          }
        ],
        "severity": "bug",
        "title": "bug"
      }
    ],
    "problems": [],
    "state": "measured"
  },
  "harness": {
    "adapter": {
      "digest": "sha256:a1a935298956020ee6d767a756847abb4c00694c88c2eb80d454886ebc4acf8c",
      "id": "afi",
      "version": "1"
    },
    "commit": "c4bc25bc962489fe5de7f71b59f19b2f426564c0",
    "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": "minimax-m3",
  "metrics": {
    "anchor_max": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 1
    },
    "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": 0.15384615384615385
    },
    "category_maintainability": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "category_performance": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.6666666666666666
    },
    "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": 4
    },
    "found": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 4
    },
    "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": 16
    },
    "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": 0.2
    },
    "review_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.0849459
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 293.0
    },
    "tier_1": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.0
    },
    "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": 0.0
    },
    "tokens": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 81706
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.0849459
    },
    "unkeyed": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 0
    }
  },
  "producer": {
    "commit": "c4bc25bc962489fe5de7f71b59f19b2f426564c0",
    "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/minimax-m3/20260831T163152Z",
  "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": "20260831T163152Z",
  "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": 139037,
      "input_tokens": 80579,
      "models": null,
      "output_tokens": 1127,
      "reasoning_tokens": 31203,
      "requests": 11,
      "stages": []
    }
  }
}