{
  "assessment": {
    "decisions": [
      {
        "decided_by": "locality",
        "defect_id": "17",
        "finding_id": "f1",
        "id": "d1",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "18",
        "finding_id": "f2",
        "id": "d2",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "1",
        "finding_id": "f3",
        "id": "d3",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "6",
        "finding_id": "f4",
        "id": "d4",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "13",
        "finding_id": "f5",
        "id": "d5",
        "outcome": "matched",
        "reason": null
      },
      {
        "decided_by": "locality",
        "defect_id": "7",
        "finding_id": "f6",
        "id": "d6",
        "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": "b9ed88e87764",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "openai/gpt-5.6-terra",
        "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:a9b9c340f8bb0fe21b1a6e3f00f4d475a964d6c0c63ede13ad8f03dd92ba11ae",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:3f1e96fe5c17f11ce8fa3bb9c167c4fa5ac88f296b338a6b3c92c4649d9b800e",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:ab05ca4b6dc3bd5187ad57cb831efc5bb1cff0c50931a2c65487ab99b0293fb4",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:9af75bee8f37a2574b6d9cb93ff5ed464154a7b72edab56ca0db9fa519ad8a87",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:ea47bf830488cfabda195ae4e6ea8cde0e2e536da87cfb03e47f39a73a8cf52c",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:32785bca285564a938e5e107565f933cb84ad460ef5a9200edea60657c7855cf",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:e1a60022d6dc6abf9f86c5d77a25b39a3e76c2c710c520cf1871873c0d6e51be",
      "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": "2026-08-31T15:14:41Z",
    "started_at": "2026-08-31T15:12:46Z",
    "wall_seconds": 115.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 6
      },
      "passes": null,
      "review_seconds": 112.967,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "Every file in `incoming` is unlinked without determining whether its `BlobWriter` is still active; a scheduled or admin sweep can unlink an in-progress fetch\u2019s temporary file, causing its later\u2026\n\nEvery file in `incoming` is unlinked without determining whether its `BlobWriter` is still active; a scheduled or admin sweep can unlink an in-progress fetch\u2019s temporary file, causing its later commit/rename to fail and the download to return an error.",
        "id": "f1",
        "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": "The index snapshot is taken before the blob walk and is not coordinated with fetches, so a blob committed between those steps and its subsequent `store.link` is treated as unreferenced and deleted;\u2026\n\nThe index snapshot is taken before the blob walk and is not coordinated with fetches, so a blob committed between those steps and its subsequent `store.link` is treated as unreferenced and deleted; that request then fails reopening its just-committed blob and leaves a stale index entry.",
        "id": "f2",
        "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": "Sorting ages ascending visits the newest eligible blobs first, despite the intended \u201coldest blobs\u201d policy, so eviction discards recently cached artifacts before older ones.",
        "id": "f3",
        "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": "The admin handler calls the synchronous sweep directly instead of acquiring `Sweeper::running`; simultaneous admin requests can run overlapping destructive sweeps, violating the one-sweep-at-a-time\u2026\n\nThe admin handler calls the synchronous sweep directly instead of acquiring `Sweeper::running`; simultaneous admin requests can run overlapping destructive sweeps, violating the one-sweep-at-a-time guarantee and blocking Tokio worker threads during filesystem traversal.",
        "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": "values()` returns reclaimed bytes in the slot named `cairn_proxy_sweep_blobs_removed_total`, while the blob count is emitted as bytes, so both new Prometheus metrics report the wrong quantities.",
        "id": "f5",
        "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": "tokio::time::interval` delivers its first tick immediately, not one interval later as intended, so each proxy startup immediately sweeps an existing cache rather than waiting for\u2026\n\ntokio::time::interval` delivers its first tick immediately, not one interval later as intended, so each proxy startup immediately sweeps an existing cache rather than waiting for `CAIRN_SWEEP_INTERVAL`.",
        "id": "f6",
        "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-terra",
  "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": 0.38461538461538464
    },
    "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": 6
    },
    "found": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 6
    },
    "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": 14
    },
    "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": 0.3
    },
    "review_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.21967
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 115.0
    },
    "tier_1": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.3333333333333333
    },
    "tier_2": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.2857142857142857
    },
    "tier_3": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.16666666666666666
    },
    "tier_4": {
      "reason": null,
      "state": "measured",
      "unit": "ratio",
      "value": 0.5
    },
    "tokens": {
      "reason": null,
      "state": "measured",
      "unit": "count",
      "value": 1460
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.21967
    },
    "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-terra/20260831T151243Z",
  "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": "20260831T151243Z",
  "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": 91985,
      "input_tokens": 15,
      "models": null,
      "output_tokens": 1445,
      "reasoning_tokens": 6309,
      "requests": 5,
      "stages": []
    }
  }
}