{ "base_url": "http://127.0.0.1:8081/v1", "budget": { "max_completion_tokens": 256, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 256 }, "checks": [ "smoke", "json", "needle", "tools", "streaming-tools", "tool-result" ], "evidence_policy": { "allowed_finish_reasons": [ "stop", "tool_calls" ], "errors": [], "reasoning": "forbidden" }, "image_expect": [], "model": "qwopus38-27b-flash-q6k-nospec-64k", "multimodal_input": null, "observations": [ { "content": "```python\nsum(xs)\n```", "content_chars": 21, "content_excerpt": "```python\nsum(xs)\n```", "finish_reason": "stop", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "seconds": 0.671, "test": "smoke", "usage": { "completion_tokens": 9, "prompt_tokens": 28, "prompt_tokens_details": { "cached_tokens": 24 }, "total_tokens": 37 }, "validation_detail": "contains sum(" }, { "content": "{\"language\":\"python\",\"ok\":true}", "content_chars": 31, "content_excerpt": "{\"language\":\"python\",\"ok\":true}", "finish_reason": "stop", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "seconds": 0.381, "test": "json", "usage": { "completion_tokens": 10, "prompt_tokens": 30, "prompt_tokens_details": { "cached_tokens": 26 }, "total_tokens": 40 }, "validation_detail": "parsed keys=['language', 'ok']" }, { "content": "ZEBRA-42917-QUARTZ", "content_chars": 18, "content_excerpt": "ZEBRA-42917-QUARTZ", "finish_reason": "stop", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "seconds": 23.657, "test": "needle", "usage": { "completion_tokens": 14, "prompt_tokens": 47349, "prompt_tokens_details": { "cached_tokens": 0 }, "total_tokens": 47363 }, "validation_detail": "needle present" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 7, "seconds": 3.217, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 0 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 0, "seconds": 3.71, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 2, "seconds": 4.196, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 16, "seconds": 4.679, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 14, "seconds": 5.167, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 4, "seconds": 5.655, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 6, "seconds": 6.143, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 8, "seconds": 6.627, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 1, "seconds": 7.116, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 3, "seconds": 7.601, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 5, "seconds": 8.085, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 13, "seconds": 8.564, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 11, "seconds": 9.049, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 9, "seconds": 9.54, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 12, "seconds": 10.041, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 10, "seconds": 10.521, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 15, "seconds": 11.003, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 18, "seconds": 11.483, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 17, "seconds": 11.965, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "request_index": 19, "seconds": 12.452, "test": "tools", "usage": { "completion_tokens": 22, "prompt_tokens": 5368, "prompt_tokens_details": { "cached_tokens": 5364 }, "total_tokens": 5390 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content_chars": 0, "content_excerpt": "", "event_count": 11, "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "seconds": 0.787, "sse_done": true, "test": "streaming-tools", "usage": { "completion_tokens": 22, "prompt_tokens": 168, "prompt_tokens_details": { "cached_tokens": 0 }, "total_tokens": 190 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "", "content_chars": 0, "content_excerpt": "", "finish_reason": "tool_calls", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "seconds": 0.467, "test": "tool-result-initial", "usage": { "completion_tokens": 22, "prompt_tokens": 168, "prompt_tokens_details": { "cached_tokens": 164 }, "total_tokens": 190 }, "validation_detail": "valid tool_call get_weather(city='Oakland')" }, { "content": "OAKLAND 72F", "content_chars": 11, "content_excerpt": "OAKLAND 72F", "finish_reason": "stop", "passed": true, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "seconds": 0.507, "test": "tool-result-continuation", "usage": { "completion_tokens": 8, "prompt_tokens": 94, "prompt_tokens_details": { "cached_tokens": 0 }, "total_tokens": 102 }, "validation_detail": "tool result retained" } ], "ocr_expect": [], "passed": true, "results": [ { "detail": "0.7s got='```python\\nsum(xs)\\n```' finish='stop' visible=21 reasoning_chars=0 reasoning_tokens=None", "name": "smoke (short coding)", "passed": true }, { "detail": "parsed keys=['language', 'ok'] finish='stop' visible=31 reasoning_chars=0 reasoning_tokens=None", "name": "structured JSON", "passed": true }, { "detail": "23.7s ctx~57344 got='ZEBRA-42917-QUARTZ' finish='stop' visible=18 reasoning_chars=0 reasoning_tokens=None", "name": "needle @ ~57344 ctx", "passed": true }, { "detail": "20/20 clean (sample: 3.2s valid tool_call get_weather(city='Oakland') finish='tool_calls' visible=0 reasoning_chars=0 reasoning_tokens=None)", "name": "shared-prefix tool batch x20", "passed": true }, { "detail": "0.8s done=True events=11 valid tool_call get_weather(city='Oakland') finish='tool_calls'", "name": "streaming tool call", "passed": true }, { "detail": "1.0s tool result retained finish='stop' visible=11 reasoning_chars=0 reasoning_tokens=None", "name": "tool-result continuation", "passed": true } ], "schema_version": "preflight/v2", "thinking": { "chat_template_kwargs": { "enable_thinking": false }, "mode": "disabled", "reasoning_effort": null }, "video_expect": [], "video_input": null }