{
  "base_url": "http://127.0.0.1:8000/v1",
  "budget": {
    "max_completion_tokens": 10240,
    "reasoning_headroom_tokens": 8192,
    "visible_answer_tokens": 2048
  },
  "checks": [
    "image",
    "ocr"
  ],
  "evidence_policy": {
    "allowed_finish_reasons": [
      "stop",
      "tool_calls"
    ],
    "errors": [],
    "reasoning": "any"
  },
  "image_expect": [
    "ANVIL READY"
  ],
  "model": "llm.secondary",
  "multimodal_input": {
    "bytes": 15916,
    "mime": "image/png",
    "sha256": "a8d5158019fb2b08ee9f6a153860ab2342384644f7c53ab58fdd45658124e83e"
  },
  "observations": [
    {
      "content": "\n\nBased on the image provided, here is a description of the display:\n\n**General Description:**\nThe image shows a digital display screen with a dark background featuring three lines of text in different colors.\n\n**Key Labels, Values, and Status:**\n\n* **Status:** **ANVIL READY** (Displayed in bright green text at the top).\n* **Code:** **42917** (Displayed in white text in the middle).\n* **Temperature:** **42 C** (Displayed in light blue text at the bottom).",
      "content_chars": 459,
      "content_excerpt": "\n\nBased on the image provided, here is a description of the display:\n\n**General Description:**\nThe image shows a digital display screen with a dark background featuring three lines of text in differen",
      "expected": [
        "ANVIL READY"
      ],
      "finish_reason": "stop",
      "image": {
        "bytes": 15916,
        "mime": "image/png",
        "sha256": "a8d5158019fb2b08ee9f6a153860ab2342384644f7c53ab58fdd45658124e83e"
      },
      "passed": true,
      "reasoning_chars": 1125,
      "reasoning_excerpt": "The user wants me to inspect the image and report on its contents, specifically focusing on labels, values, and status.\n\n1.  **Analyze the image:**\n    *   **Background:** Dark blue/black.\n    *   **T",
      "reasoning_field": "reasoning_content",
      "reasoning_tokens": 332,
      "seconds": 9.263,
      "test": "image",
      "usage": {
        "completion_tokens": 450,
        "completion_tokens_details": {
          "reasoning_tokens": 332
        },
        "prompt_tokens": 294,
        "total_tokens": 744
      },
      "validation_detail": "all expected text present"
    },
    {
      "content": "\n\nANVIL READY\nCODE 42917\nTEMPERATURE 42 C",
      "content_chars": 41,
      "content_excerpt": "\n\nANVIL READY\nCODE 42917\nTEMPERATURE 42 C",
      "expected": [
        "42917"
      ],
      "finish_reason": "stop",
      "image": {
        "bytes": 15916,
        "mime": "image/png",
        "sha256": "a8d5158019fb2b08ee9f6a153860ab2342384644f7c53ab58fdd45658124e83e"
      },
      "passed": true,
      "reasoning_chars": 200,
      "reasoning_excerpt": "The user wants a transcription of the text in the image. I need to read the text exactly as it appears, preserving the layout and content. The image contains three lines of text on a dark background.\n",
      "reasoning_field": "reasoning_content",
      "reasoning_tokens": 42,
      "seconds": 1.501,
      "test": "ocr",
      "usage": {
        "completion_tokens": 65,
        "completion_tokens_details": {
          "reasoning_tokens": 42
        },
        "prompt_tokens": 295,
        "total_tokens": 360
      },
      "validation_detail": "all expected text present"
    }
  ],
  "ocr_expect": [
    "42917"
  ],
  "passed": true,
  "results": [
    {
      "detail": "9.3s all expected text present finish='stop' visible=459 reasoning_chars=1125 reasoning_tokens=332",
      "name": "general image understanding",
      "passed": true
    },
    {
      "detail": "1.5s all expected text present finish='stop' visible=41 reasoning_chars=200 reasoning_tokens=42",
      "name": "verbatim image OCR",
      "passed": true
    }
  ],
  "schema_version": "preflight/v2",
  "thinking": {
    "chat_template_kwargs": {
      "enable_thinking": true
    },
    "mode": "enabled",
    "reasoning_effort": null
  },
  "video_expect": [],
  "video_input": null
}