{
  "record": "2026-10-06 search-with-proof feasibility pilot (path family, vulnerable side, cluster verify lane)",
  "image": "ghcr.io/norandom/ousast-search-task@sha256:60bfd73f...",
  "note": "First pilot after the verify-side keystone and the agent-side path-oracle target-parity fix. Feasibility only; payloads/boards live in the gitignored private area.",
  "ceiling_usd": 3.0,
  "searches": [
    {
      "pair_index": 3,
      "language": "php",
      "family": "path",
      "outcome": "inconclusive",
      "end_reason": "budget_spent",
      "end_detail": "demonstrations",
      "model_calls": 78,
      "executor_tasks": 12,
      "verify_tasks": 6,
      "settled_usd": 0.5779,
      "wall_seconds": 439,
      "failure_classes": [
        {
          "phase": "explore",
          "class": "no cli entrypoint exists"
        },
        {
          "phase": "verify/could_not_build",
          "class": "runtime entry missing from"
        },
        {
          "phase": "verify/could_not_build",
          "class": "runtime entry missing from"
        },
        {
          "phase": "verify",
          "class": "noconsistentdifferential"
        },
        {
          "phase": "verify/could_not_build",
          "class": "runtime entry missing from"
        },
        {
          "phase": "verify/could_not_build",
          "class": "runtime entry missing from"
        },
        {
          "phase": "verify",
          "class": "noconsistentdifferential"
        },
        {
          "phase": "verify/could_not_build",
          "class": "runtime entry missing from"
        },
        {
          "phase": "verify/could_not_build",
          "class": "runtime entry missing from"
        },
        {
          "phase": "verify",
          "class": "noconsistentdifferential"
        }
      ]
    },
    {
      "pair_index": 9,
      "language": "typescript",
      "family": "path",
      "outcome": "plausible_unproven",
      "end_reason": "budget_spent",
      "end_detail": "reason_rounds",
      "model_calls": 154,
      "executor_tasks": 12,
      "verify_tasks": 0,
      "settled_usd": 1.1979,
      "wall_seconds": 2300,
      "failure_classes": []
    },
    {
      "pair_index": 13,
      "language": "python",
      "family": "path",
      "outcome": "plausible_unproven",
      "end_reason": "budget_spent",
      "end_detail": "run_ceiling",
      "model_calls": 118,
      "executor_tasks": 9,
      "verify_tasks": 0,
      "settled_usd": 1.1739,
      "wall_seconds": 564,
      "failure_classes": [
        {
          "phase": "explore",
          "class": "as predicted the parent"
        },
        {
          "phase": "explore",
          "class": "passfalse canary workspacecheckoutcanary passfalse"
        },
        {
          "phase": "explore",
          "class": "with the servedroot prefix"
        },
        {
          "phase": "explore",
          "class": "h check at filepy"
        },
        {
          "phase": "explore",
          "class": "are plain attribute reads"
        }
      ]
    }
  ],
  "aggregate": {
    "outcomes": {
      "inconclusive": 1,
      "plausible_unproven": 2
    },
    "demonstrations": 0,
    "false_proofs_fixed_side": 0,
    "settled_usd": 2.9496,
    "searches": 3
  },
  "finding": "Parity fix validated: the agent now runs directed, target-aware search toward the named observable (pair 13 reasoned explicitly about reaching it and inspected the app's file-serving guard). No demonstration: all three exhausted their per-pair allowance (demonstrations/reason_rounds/run_ceiling) before a differential; pairs 9 and 13 wrote 0 verify demos (budget consumed in reason/explore). Pair 3 (php) hit entrypoint-discovery failures (no CLI entrypoint / runtime entry missing). Cost ~$0.98/search, higher than the $0.2-0.5 estimate."
}