{
  "base_url": "REDACTED_LOOPBACK_ENDPOINT",
  "budget": {
    "max_completion_tokens": 10240,
    "reasoning_headroom_tokens": 8192,
    "visible_answer_tokens": 2048
  },
  "checks": [
    "smoke",
    "json",
    "tools",
    "streaming-tools",
    "tool-result"
  ],
  "evidence_policy": {
    "allowed_finish_reasons": [
      "stop",
      "tool_calls"
    ],
    "errors": [],
    "reasoning": "any"
  },
  "image_expect": [],
  "model": "baseline-local-tier-r11",
  "multimodal_input": null,
  "observations": [
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 357,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "stop",
      "passed": true,
      "reasoning_chars": 779,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "seconds": 4.151,
      "test": "smoke",
      "usage": {
        "completion_tokens": 301,
        "prompt_tokens": 28,
        "prompt_tokens_details": null,
        "total_tokens": 329
      },
      "validation_detail": "contains sum("
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 31,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "stop",
      "passed": true,
      "reasoning_chars": 183,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "seconds": 0.907,
      "test": "json",
      "usage": {
        "completion_tokens": 53,
        "prompt_tokens": 30,
        "prompt_tokens_details": null,
        "total_tokens": 83
      },
      "validation_detail": "parsed keys=['language', 'ok']"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 1,
      "seconds": 11.221,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 0,
      "seconds": 11.519,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 2,
      "seconds": 11.531,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 3,
      "seconds": 11.813,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 5,
      "seconds": 12.902,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 6,
      "seconds": 12.917,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 7,
      "seconds": 13.2,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 103,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 4,
      "seconds": 13.476,
      "test": "tools",
      "usage": {
        "completion_tokens": 38,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5005
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 8,
      "seconds": 14.545,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 9,
      "seconds": 14.562,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 10,
      "seconds": 14.841,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 11,
      "seconds": 15.121,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 12,
      "seconds": 16.196,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 13,
      "seconds": 16.211,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 14,
      "seconds": 16.486,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 15,
      "seconds": 16.767,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 17,
      "seconds": 17.855,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 18,
      "seconds": 17.872,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 81,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 19,
      "seconds": 17.887,
      "test": "tools",
      "usage": {
        "completion_tokens": 33,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5000
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 103,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "request_index": 16,
      "seconds": 17.916,
      "test": "tools",
      "usage": {
        "completion_tokens": 38,
        "prompt_tokens": 4967,
        "prompt_tokens_details": null,
        "total_tokens": 5005
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "event_count": 37,
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 123,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "stream_delta",
      "reasoning_tokens": null,
      "seconds": 8.806,
      "sse_done": true,
      "test": "streaming-tools",
      "usage": {
        "completion_tokens": 42,
        "prompt_tokens": 166,
        "total_tokens": 208
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 0,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "tool_calls",
      "passed": true,
      "reasoning_chars": 123,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "seconds": 0.699,
      "test": "tool-result-initial",
      "usage": {
        "completion_tokens": 42,
        "prompt_tokens": 166,
        "prompt_tokens_details": null,
        "total_tokens": 208
      },
      "validation_detail": "valid tool_call get_weather(city='Oakland')"
    },
    {
      "content": "REDACTED_BENCHMARK_CONTENT",
      "content_chars": 11,
      "content_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "finish_reason": "stop",
      "passed": true,
      "reasoning_chars": 234,
      "reasoning_excerpt": "REDACTED_BENCHMARK_CONTENT",
      "reasoning_field": "reasoning",
      "reasoning_tokens": null,
      "seconds": 1.124,
      "test": "tool-result-continuation",
      "usage": {
        "completion_tokens": 69,
        "prompt_tokens": 70,
        "prompt_tokens_details": null,
        "total_tokens": 139
      },
      "validation_detail": "tool result retained"
    }
  ],
  "ocr_expect": [],
  "passed": true,
  "results": [
    {
      "detail": "REDACTED_BENCHMARK_DETAIL",
      "name": "smoke (short coding)",
      "passed": true
    },
    {
      "detail": "REDACTED_BENCHMARK_DETAIL",
      "name": "structured JSON",
      "passed": true
    },
    {
      "detail": "REDACTED_BENCHMARK_DETAIL",
      "name": "shared-prefix tool batch x20",
      "passed": true
    },
    {
      "detail": "REDACTED_BENCHMARK_DETAIL",
      "name": "streaming tool call",
      "passed": true
    },
    {
      "detail": "REDACTED_BENCHMARK_DETAIL",
      "name": "tool-result continuation",
      "passed": true
    }
  ],
  "schema_version": "preflight/v2",
  "thinking": {
    "chat_template_kwargs": {
      "enable_thinking": true
    },
    "mode": "enabled",
    "reasoning_effort": null
  },
  "video_expect": [],
  "video_input": null
}
