{
  "context": {
    "cap_tokens": 261056,
    "max_model_len": 262144,
    "targets": [
      {
        "attempted_context_tokens": 32768,
        "chars_per_token": 3.0,
        "clamped_tokens": 32768,
        "e2e_ms": 4392.906699999003,
        "estimated_prompt_tokens": 32768,
        "output_tokens": 62,
        "status": "passed",
        "target_tokens": 32768,
        "ttft_ms": 3591.8524999979127,
        "usage": {
          "completion_tokens": 62,
          "prompt_tokens": 31225,
          "total_tokens": 31287
        }
      },
      {
        "attempted_context_tokens": 128000,
        "chars_per_token": 3.148,
        "clamped_tokens": 128000,
        "e2e_ms": 28449.863800000458,
        "estimated_prompt_tokens": 127999,
        "output_tokens": 54,
        "status": "passed",
        "target_tokens": 128000,
        "ttft_ms": 27666.515400000208,
        "usage": {
          "completion_tokens": 54,
          "prompt_tokens": 136117,
          "total_tokens": 136171
        }
      },
      {
        "attempted_context_tokens": 240000,
        "chars_per_token": 2.961,
        "clamped_tokens": 240000,
        "e2e_ms": 75952.1879999993,
        "estimated_prompt_tokens": 239999,
        "output_tokens": 62,
        "status": "passed",
        "target_tokens": 240000,
        "ttft_ms": 74936.4671000003,
        "usage": {
          "completion_tokens": 62,
          "prompt_tokens": 241327,
          "total_tokens": 241389
        }
      }
    ]
  },
  "evaluation_protocol": {
    "budget_semantics": "visible_answer_tokens plus reasoning_headroom_tokens are sent as one max_tokens cap; the endpoint does not hard-partition the channels",
    "minimum_comparable_repetitions": 3,
    "minimum_pass_rate": 1.0,
    "reasoning_headroom_tokens": 0,
    "records_finish_reason": true,
    "records_full_visible_answer": true,
    "records_reasoning_channel_metadata": true,
    "repetitions": 3,
    "version": 3,
    "visible_answer_tokens": 256
  },
  "failures": [],
  "identity": {
    "base_url": "http://127.0.0.1:39017/v1",
    "candidate_id": "nvidia-qwen35-122b-a10b-nvfp4-98915d8",
    "config_id": "ngc26.06-bf16kv-262144-tp1",
    "engine": "vllm-0.22.1-7b9cb5b7.dev-ngc26.06",
    "gpu": "rtx-pro-6000-blackwell-max-q-96gb",
    "model": "qwen35-122b-a10b-nvfp4",
    "started_at": "2026-07-28T08:52:24Z"
  },
  "intelligence": {
    "checks": [
      {
        "attempt_count": 3,
        "attempts": [
          {
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "--- app.py\n+++ app.py\n@@ -1,3 +1,3 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "content_excerpt": "--- app.py\n+++ app.py\n@@ -1,3 +1,3 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 533.7785000010626,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "text_checks": [
              {
                "name": "diff_shape",
                "passed": true
              },
              {
                "name": "removes_old_timeout",
                "passed": true
              },
              {
                "name": "adds_new_timeout",
                "passed": true
              }
            ],
            "usage": {
              "completion_tokens": 38,
              "prompt_tokens": 51,
              "prompt_tokens_details": null,
              "total_tokens": 89
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "--- app.py\n+++ app.py\n@@ -1,3 +1,3 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "content_excerpt": "--- app.py\n+++ app.py\n@@ -1,3 +1,3 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 537.8086999990046,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "text_checks": [
              {
                "name": "diff_shape",
                "passed": true
              },
              {
                "name": "removes_old_timeout",
                "passed": true
              },
              {
                "name": "adds_new_timeout",
                "passed": true
              }
            ],
            "usage": {
              "completion_tokens": 38,
              "prompt_tokens": 51,
              "prompt_tokens_details": null,
              "total_tokens": 89
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "--- app.py\n+++ app.py\n@@ -1,3 +1,3 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "content_excerpt": "--- app.py\n+++ app.py\n@@ -1,3 +1,3 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 534.0704999980517,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "text_checks": [
              {
                "name": "diff_shape",
                "passed": true
              },
              {
                "name": "removes_old_timeout",
                "passed": true
              },
              {
                "name": "adds_new_timeout",
                "passed": true
              }
            ],
            "usage": {
              "completion_tokens": 38,
              "prompt_tokens": 51,
              "prompt_tokens_details": null,
              "total_tokens": 89
            }
          }
        ],
        "id": "unified_diff_timeout_edit",
        "pass_count": 3,
        "pass_rate": 1.0,
        "required_pass_rate": 1.0,
        "status": "passed",
        "validator": "deterministic_text_checks"
      },
      {
        "attempt_count": 3,
        "attempts": [
          {
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "The total latency of 3000 ms exceeds the 2500 ms limit primarily due to the LLM's 1800 ms response time, which can be fixed by implementing streaming to begin TTS synthesis before the LLM completes its full response.",
            "content_excerpt": "The total latency of 3000 ms exceeds the 2500 ms limit primarily due to the LLM's 1800 ms response time, which can be fixed by implementing streaming to begin TTS synthesis before the LLM completes it",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 782.9998999986856,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "text_checks": [
              {
                "name": "identifies_budget_overrun",
                "passed": true
              },
              {
                "name": "offers_latency_fix",
                "passed": true
              }
            ],
            "usage": {
              "completion_tokens": 57,
              "prompt_tokens": 79,
              "prompt_tokens_details": null,
              "total_tokens": 136
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "The total latency of 3000 ms exceeds the 2500 ms limit primarily due to the LLM's 1800 ms response time, which can be fixed by implementing streaming to begin TTS synthesis before the LLM completes its full response.",
            "content_excerpt": "The total latency of 3000 ms exceeds the 2500 ms limit primarily due to the LLM's 1800 ms response time, which can be fixed by implementing streaming to begin TTS synthesis before the LLM completes it",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 782.378100000642,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "text_checks": [
              {
                "name": "identifies_budget_overrun",
                "passed": true
              },
              {
                "name": "offers_latency_fix",
                "passed": true
              }
            ],
            "usage": {
              "completion_tokens": 57,
              "prompt_tokens": 79,
              "prompt_tokens_details": null,
              "total_tokens": 136
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "The total latency of 3000 ms exceeds the 2500 ms limit primarily due to the LLM's 1800 ms response time, which can be fixed by implementing streaming to begin TTS synthesis before the LLM completes its full response.",
            "content_excerpt": "The total latency of 3000 ms exceeds the 2500 ms limit primarily due to the LLM's 1800 ms response time, which can be fixed by implementing streaming to begin TTS synthesis before the LLM completes it",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 779.6720000005735,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "text_checks": [
              {
                "name": "identifies_budget_overrun",
                "passed": true
              },
              {
                "name": "offers_latency_fix",
                "passed": true
              }
            ],
            "usage": {
              "completion_tokens": 57,
              "prompt_tokens": 79,
              "prompt_tokens_details": null,
              "total_tokens": 136
            }
          }
        ],
        "id": "parallel_timeout_triage",
        "pass_count": 3,
        "pass_rate": 1.0,
        "required_pass_rate": 1.0,
        "status": "passed",
        "validator": "deterministic_text_checks"
      }
    ],
    "status": "passed"
  },
  "run_id": "fast-bakeoff-20260728T085224Z",
  "schema": "anvil-serving.fast-tier-bakeoff/v1",
  "score_inputs": {
    "e2e_p50_ms": 28449.863800000458,
    "intelligence_pass_rate": 1.0,
    "operational_fit_notes": [
      "endpoint was already loaded; benchmark did not start or stop serves"
    ],
    "session_recall_passed": true,
    "thinking_mode": "disabled",
    "tool_call_passed": true,
    "ttft_p50_ms": 27666.515400000208,
    "usable_context_tokens": 240000,
    "voice_latency_ms": null
  },
  "selection": {
    "context_targets": [
      32768,
      128000,
      240000
    ],
    "endpoint_already_loaded": true,
    "requests_per_context": 1,
    "suites": [
      "chat",
      "context",
      "tool",
      "session",
      "intelligence"
    ]
  },
  "session": {
    "checks": [
      {
        "attempt_count": 3,
        "attempts": [
          {
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "RIVER-918",
            "content_excerpt": "RIVER-918",
            "expected": "RIVER-918",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 150.7997999979125,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "usage": {
              "completion_tokens": 7,
              "prompt_tokens": 52,
              "prompt_tokens_details": null,
              "total_tokens": 59
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "RIVER-918",
            "content_excerpt": "RIVER-918",
            "expected": "RIVER-918",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 143.23929999954998,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "usage": {
              "completion_tokens": 7,
              "prompt_tokens": 52,
              "prompt_tokens_details": null,
              "total_tokens": 59
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "RIVER-918",
            "content_excerpt": "RIVER-918",
            "expected": "RIVER-918",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 146.5210999995179,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "usage": {
              "completion_tokens": 7,
              "prompt_tokens": 52,
              "prompt_tokens_details": null,
              "total_tokens": 59
            }
          }
        ],
        "name": "single_request_multiturn_recall",
        "pass_count": 3,
        "pass_rate": 1.0,
        "required_pass_rate": 1.0,
        "status": "passed"
      }
    ],
    "status": "passed"
  },
  "source_recipe": {
    "ref": "configs/serve-recipes.toml",
    "serve_command": null
  },
  "suites": {},
  "thinking": {
    "chat_template_kwargs": {
      "enable_thinking": false
    },
    "control_evidence": "C:\\Users\\operator\\ai-code\\anvil-serving-wt-qwen35-primary\\docs\\findings\\2026-07-28-qwen35-122b-primary-evidence\\thinking-disabled-control.json",
    "control_evidence_sha256": "3e4d26ac4667ffcf6f59062a5042dd1a75979a03c0a3e30aac5b15b30bfd38d9",
    "control_mechanism": "chat_template_kwargs",
    "control_requested": {
      "enable_thinking": false
    },
    "control_status": "verified",
    "mode": "disabled",
    "reasoning_effort": null,
    "unsupported": false
  },
  "timing": {
    "chat": {
      "content_chunks": 174,
      "e2e_p50_ms": 28449.863800000458,
      "e2e_p95_ms": 75952.1879999993,
      "output_tokens": 178,
      "ttft_p50_ms": 27666.515400000208,
      "ttft_p95_ms": 74936.4671000003,
      "ttft_samples": 3
    },
    "wall_ms": 114682.21790000098
  },
  "tool": {
    "checks": [
      {
        "attempt_count": 3,
        "attempts": [
          {
            "arguments": {
              "zip": "98101"
            },
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "",
            "content_excerpt": "",
            "failure_class": null,
            "finish_reason": "tool_calls",
            "latency_ms": 491.0691999975825,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "tool_call_count": 1,
            "usage": {
              "completion_tokens": 32,
              "prompt_tokens": 288,
              "prompt_tokens_details": null,
              "total_tokens": 320
            },
            "valid_tool_call_count": 1,
            "validation_errors": []
          },
          {
            "arguments": {
              "zip": "98101"
            },
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "",
            "content_excerpt": "",
            "failure_class": null,
            "finish_reason": "tool_calls",
            "latency_ms": 486.0370000023977,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "tool_call_count": 1,
            "usage": {
              "completion_tokens": 32,
              "prompt_tokens": 288,
              "prompt_tokens_details": null,
              "total_tokens": 320
            },
            "valid_tool_call_count": 1,
            "validation_errors": []
          },
          {
            "arguments": {
              "zip": "98101"
            },
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "",
            "content_excerpt": "",
            "failure_class": null,
            "finish_reason": "tool_calls",
            "latency_ms": 482.55239999707555,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "tool_call_count": 1,
            "usage": {
              "completion_tokens": 32,
              "prompt_tokens": 288,
              "prompt_tokens_details": null,
              "total_tokens": 320
            },
            "valid_tool_call_count": 1,
            "validation_errors": []
          }
        ],
        "expected_arguments": {
          "zip": "98101"
        },
        "expected_function": "record_weather_zip",
        "name": "openai_tool_call_smoke",
        "pass_count": 3,
        "pass_rate": 1.0,
        "required_pass_rate": 1.0,
        "status": "passed"
      }
    ],
    "status": "passed"
  },
  "voice": {
    "llm_latency_ms": null,
    "status": "not_run",
    "stt_latency_ms": null,
    "total_turn_latency_ms": null,
    "tts_latency_ms": null
  }
}