{
  "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": "91bb17f752bc",
    "label": "default",
    "models": [
      {
        "effort": "high",
        "model": "z-ai/glm-4.7-flash",
        "protocol": null,
        "provider": "z-ai",
        "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:b4dcf21f6543049bbe6efe792d7991e9937037870bf813ab7fd9de4770167a76",
      "media_type": "application/json",
      "path": "summary.json",
      "role": "summary"
    },
    {
      "digest": "sha256:3fcda84041267394b341a10f6f2dae2dd882ef43ccac14c84b8eed7239e0c9dd",
      "media_type": "application/json",
      "path": "findings.json",
      "role": "findings"
    },
    {
      "digest": "sha256:c576201956adf5754af784cbef7d94737f19c23964b271601b66da098bf5b00c",
      "media_type": "application/json",
      "path": "meta.json",
      "role": "meta"
    },
    {
      "digest": "sha256:a20d55cc95168b107001de4eec430e6e646d22501ebcfba7e8312c8f46f182d7",
      "media_type": "application/json",
      "path": "spend.json",
      "role": "spend"
    },
    {
      "digest": "sha256:bf30fbc7849c2b39559793d25369b75cdb69b256cd879ae504983992ed25d514",
      "media_type": "application/jsonl",
      "path": "result.jsonl",
      "role": "result"
    },
    {
      "digest": "sha256:f2cf0ce61f0ad6b32f1c1ddb199d027640289139502942ab8e86d91933b59696",
      "media_type": "text/plain",
      "path": "stderr.txt",
      "role": "stderr"
    },
    {
      "digest": "sha256:b322c2341aa2de16b5f3cfdce0d71925df749947fbf3c7fb8329b7dce0624fbc",
      "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": "2026-08-31T13:16:49Z",
    "started_at": "2026-08-31T13:01:35Z",
    "wall_seconds": 914.0
  },
  "extensions": {
    "afi": {
      "found_per_pass": {
        "agent": 2
      },
      "passes": null,
      "review_seconds": 912.31,
      "tier1_only": false,
      "variant_hash": null
    }
  },
  "findings": {
    "items": [
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "The synchronous `sweep()` method is public and callable from `reclaim()` in `admin.rs:374`, bypassing the mutex entirely so concurrent on-demand sweeps and background sweeps can interleave",
        "id": "f1",
        "locations": [
          {
            "end_line": 576,
            "path": "services/proxy/src/sweep.rs",
            "start_line": 576
          }
        ],
        "severity": "bug",
        "title": "bug"
      },
      {
        "attributes": {
          "category": "bug",
          "confidence": null,
          "evidence_quote": null,
          "suggested_fix": null
        },
        "body": "reclaim()` calls `app.sweeper.sweep(dry_run)` directly instead of `app.sweeper.run().await`, bypassing the mutex that `run()` acquires to ensure one sweep at a time",
        "id": "f2",
        "locations": [
          {
            "end_line": 374,
            "path": "services/proxy/src/routes/admin.rs",
            "start_line": 374
          }
        ],
        "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": "glm-4.7-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": 0.01417099
    },
    "seconds": {
      "reason": null,
      "state": "measured",
      "unit": "seconds",
      "value": 914.0
    },
    "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": 167260
    },
    "total_bill": {
      "reason": null,
      "state": "measured",
      "unit": "usd",
      "value": 0.01417099
    },
    "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/glm-4.7-flash/20260831T125926Z",
  "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": "20260831T125926Z",
  "status": {
    "reason": null,
    "state": "completed"
  },
  "target": {
    "base_sha": null,
    "diff_digest": "sha256:72a570259bd1845bafd1218d3dcabb40f8bbca7d9fdc64e1ddf2db168073826a",
    "pull_request": 8,
    "repository_url": "https://github.com/smykla-skalski/cairn",
    "reviewed_sha": "9b51f95ef609a219e211e37b082cd2e6913190e0"
  },
  "usage": {
    "reason": null,
    "state": "measured",
    "value": {
      "cached_input_tokens": 151808,
      "input_tokens": 166533,
      "models": null,
      "output_tokens": 727,
      "reasoning_tokens": 1762,
      "requests": 14,
      "stages": []
    }
  }
}