{
  "schema_version": "preflight/v2",
  "base_url": "http://127.0.0.1:39062/v1",
  "model": "deepseek-v4-flash-0731-r16-b12x-dspark5-maxseq16-tp2-650k",
  "thinking": {
    "mode": "default",
    "chat_template_kwargs": null,
    "reasoning_effort": "low"
  },
  "budget": {
    "visible_answer_tokens": 512,
    "reasoning_headroom_tokens": 4096,
    "max_completion_tokens": 4608
  },
  "multimodal_input": null,
  "video_input": null,
  "image_expect": [],
  "ocr_expect": [],
  "video_expect": [],
  "checks": [
    "smoke",
    "json",
    "tools",
    "streaming-tools",
    "tool-result",
    "responses"
  ],
  "results": [
    {
      "name": "smoke (short coding)",
      "passed": true,
      "detail": "2.0s got='The simplest one-liner is to use the built-in `sum' finish='stop' visible=233 reasoning_chars=737 reasoning_tokens=None"
    },
    {
      "name": "structured JSON",
      "passed": true,
      "detail": "parsed keys=['language', 'ok'] finish='stop' visible=31 reasoning_chars=171 reasoning_tokens=None"
    },
    {
      "name": "shared-prefix tool batch x3",
      "passed": true,
      "detail": "3/3 clean (sample: 1.2s valid tool_call get_weather(city='Oakland') finish='tool_calls' visible=0 reasoning_chars=73 reasoning_tokens=None)"
    },
    {
      "name": "streaming tool call",
      "passed": true,
      "detail": "0.7s done=True events=12 valid tool_call get_weather(city='Oakland') finish='tool_calls'"
    },
    {
      "name": "tool-result continuation",
      "passed": true,
      "detail": "1.4s tool result retained finish='stop' visible=11 reasoning_chars=274 reasoning_tokens=None"
    },
    {
      "name": "Responses API subset",
      "passed": true,
      "detail": "0.6s status='completed' output='READY' reasoning_chars=167"
    }
  ],
  "observations": [
    {
      "content": "The simplest one-liner is to use the built-in `sum` function directly:\n\n```python\nsum(xs)\n```\n\nIf you need a reusable function (e.g., to pass as a callback), use a lambda:\n\n```python\nlambda xs: sum(xs)\n```\n\nBoth are valid one-liners.",
      "finish_reason": "stop",
      "content_chars": 233,
      "content_excerpt": "The simplest one-liner is to use the built-in `sum` function directly:\n\n```python\nsum(xs)\n```\n\nIf you need a reusable function (e.g., to pass as a callback), use a lambda:\n\n```python\nlambda xs: sum(xs",
      "reasoning_field": "reasoning",
      "reasoning_chars": 737,
      "reasoning_excerpt": "We need to write a Python one-liner that returns the sum of a list `xs`. The user likely expects a lambda or a function definition in one line. The simplest is `sum(xs)`, but that's not a one-liner in",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 20,
        "total_tokens": 287,
        "completion_tokens": 267,
        "prompt_tokens_details": {
          "cached_tokens": 0,
          "multimodal_tokens": null
        }
      },
      "test": "smoke",
      "seconds": 2.025,
      "passed": true,
      "validation_detail": "contains sum("
    },
    {
      "content": "{\"language\":\"python\",\"ok\":true}",
      "finish_reason": "stop",
      "content_chars": 31,
      "content_excerpt": "{\"language\":\"python\",\"ok\":true}",
      "reasoning_field": "reasoning",
      "reasoning_chars": 171,
      "reasoning_excerpt": "We need to output only a JSON object as specified. The user says \"Return ONLY a JSON object: {\"language\":\"python\",\"ok\":true}. No prose.\" So we just output that exact JSON.",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 22,
        "total_tokens": 74,
        "completion_tokens": 52,
        "prompt_tokens_details": {
          "cached_tokens": 0,
          "multimodal_tokens": null
        }
      },
      "test": "json",
      "seconds": 0.432,
      "passed": true,
      "validation_detail": "parsed keys=['language', 'ok']"
    },
    {
      "content": "",
      "finish_reason": "tool_calls",
      "content_chars": 0,
      "content_excerpt": "",
      "reasoning_field": "reasoning",
      "reasoning_chars": 73,
      "reasoning_excerpt": "The user wants the weather in Oakland. I should use the get_weather tool.",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 5085,
        "total_tokens": 5149,
        "completion_tokens": 64,
        "prompt_tokens_details": {
          "cached_tokens": 0,
          "multimodal_tokens": null
        }
      },
      "test": "tools",
      "seconds": 1.235,
      "request_index": 1,
      "passed": true,
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "",
      "finish_reason": "tool_calls",
      "content_chars": 0,
      "content_excerpt": "",
      "reasoning_field": "reasoning",
      "reasoning_chars": 69,
      "reasoning_excerpt": "The user wants the weather in Oakland. I'll use the get_weather tool.",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 5085,
        "total_tokens": 5149,
        "completion_tokens": 64,
        "prompt_tokens_details": {
          "cached_tokens": 4864,
          "multimodal_tokens": null
        }
      },
      "test": "tools",
      "seconds": 1.235,
      "request_index": 2,
      "passed": true,
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "",
      "finish_reason": "tool_calls",
      "content_chars": 0,
      "content_excerpt": "",
      "reasoning_field": "reasoning",
      "reasoning_chars": 69,
      "reasoning_excerpt": "The user wants the weather in Oakland. I'll use the get_weather tool.",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 5085,
        "total_tokens": 5149,
        "completion_tokens": 64,
        "prompt_tokens_details": {
          "cached_tokens": 4864,
          "multimodal_tokens": null
        }
      },
      "test": "tools",
      "seconds": 1.236,
      "request_index": 0,
      "passed": true,
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "test": "streaming-tools",
      "seconds": 0.672,
      "finish_reason": "tool_calls",
      "content_chars": 0,
      "content_excerpt": "",
      "reasoning_field": "stream_delta",
      "reasoning_chars": 69,
      "reasoning_excerpt": "The user wants the weather in Oakland. I'll use the get_weather tool.",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 285,
        "total_tokens": 349,
        "completion_tokens": 64,
        "prompt_tokens_details": {
          "cached_tokens": 0
        }
      },
      "sse_done": true,
      "event_count": 12,
      "passed": true,
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "",
      "finish_reason": "tool_calls",
      "content_chars": 0,
      "content_excerpt": "",
      "reasoning_field": "reasoning",
      "reasoning_chars": 69,
      "reasoning_excerpt": "The user wants the weather in Oakland. I'll use the get_weather tool.",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 285,
        "total_tokens": 349,
        "completion_tokens": 64,
        "prompt_tokens_details": {
          "cached_tokens": 0,
          "multimodal_tokens": null
        }
      },
      "test": "tool-result-initial",
      "seconds": 0.564,
      "passed": true,
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "OAKLAND 72F",
      "finish_reason": "stop",
      "content_chars": 11,
      "content_excerpt": "OAKLAND 72F",
      "reasoning_field": "reasoning",
      "reasoning_chars": 274,
      "reasoning_excerpt": "1.  The user asked to use the tool to get the weather in Oakland.\n2.  The tool result is: {\"city\":\"Oakland\",\"temperature_f\":72,\"condition\":\"sunny\"}.\n3.  The user then instructed: \"Reply exactly OAKLAN",
      "reasoning_tokens": null,
      "usage": {
        "prompt_tokens": 101,
        "total_tokens": 189,
        "completion_tokens": 88,
        "prompt_tokens_details": {
          "cached_tokens": 0,
          "multimodal_tokens": null
        }
      },
      "test": "tool-result-continuation",
      "seconds": 0.876,
      "passed": true,
      "validation_detail": "tool result retained"
    },
    {
      "test": "responses",
      "seconds": 0.561,
      "finish_reason": "stop",
      "content_chars": 5,
      "content_excerpt": "READY",
      "reasoning_field": "reasoning_text",
      "reasoning_chars": 167,
      "reasoning_excerpt": "1.  The user's instruction is \"Reply with exactly READY\".\n2.  The response must be exactly the word \"READY\".\n3.  No other text, punctuation, or explanation is allowed.",
      "reasoning_tokens": null,
      "usage": {
        "input_tokens": 9,
        "input_tokens_details": {
          "cached_tokens": 0,
          "input_tokens_per_turn": [],
          "cached_tokens_per_turn": []
        },
        "output_tokens": 47,
        "output_tokens_details": {
          "reasoning_tokens": 0,
          "tool_output_tokens": 0,
          "output_tokens_per_turn": [],
          "tool_output_tokens_per_turn": []
        },
        "total_tokens": 56
      },
      "response_status": "completed",
      "passed": true,
      "validation_detail": "completed exact READY"
    }
  ],
  "evidence_policy": {
    "reasoning": "required",
    "allowed_finish_reasons": [
      "stop",
      "tool_calls"
    ],
    "errors": []
  },
  "passed": true
}