{
  "schema_version": "preflight/v2-public-projection",
  "endpoint": "redacted loopback endpoint",
  "model": "llm.primary",
  "checks": ["json"],
  "budget": {"max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512},
  "sampling": {"temperature": 0.0},
  "thinking": {"mode": "disabled", "chat_template_kwargs": {"enable_thinking": false}, "reasoning_effort": null},
  "observations": [
    {
      "content": "The user wants me to return ONLY a JSON object: {\"language\":\"python\",\"ok\":true}. No prose.\n\nThis is a simple, clear instruction. I should return exactly that JSON object with no additional text.{\"language\":\"python\",\"ok\":true}",
      "content_chars": 225,
      "finish_reason": "stop",
      "reasoning_chars": 0,
      "reasoning_field": null,
      "reasoning_tokens": 0,
      "seconds": 0.792,
      "usage": {
        "completion_tokens": 54,
        "completion_tokens_details": {"reasoning_tokens": 0},
        "prompt_tokens": 30,
        "prompt_tokens_details": {"cached_tokens": 0},
        "total_tokens": 84
      }
    }
  ],
  "passed": false,
  "results": [{"name": "structured JSON", "passed": false, "detail": "error: Extra data: line 1 column 32 (char 31)"}],
  "interpretation": "Operational restoration is verified, but strict functional restoration acceptance is incomplete. The response contains reasoning-like prose before the target object. No matched pretrial smoke exists, so a regression is not established.",
  "private_receipt_sha256": "d9022fbe50db29c890e5a32bc2d4c93a153f0123cf5ff5211bad538e58c93ff9"
}