{
  "context": {
    "cap_tokens": 64448,
    "max_model_len": 65536,
    "targets": [
      {
        "attempted_context_tokens": 32768,
        "chars_per_token": 3.0,
        "clamped_tokens": 32768,
        "e2e_ms": 4015.0637999995524,
        "estimated_prompt_tokens": 32768,
        "output_tokens": 48,
        "status": "passed",
        "target_tokens": 32768,
        "ttft_ms": 3234.4085999993695,
        "usage": {
          "completion_tokens": 48,
          "prompt_tokens": 29887,
          "total_tokens": 29935
        }
      }
    ]
  },
  "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": 512
  },
  "failures": [],
  "identity": {
    "base_url": "http://127.0.0.1:39052/v1",
    "candidate_id": "nemotron3-super-120b-a12b-nvfp4-tp2",
    "config_id": "tp2-ep2-thinking-disabled",
    "engine": "nvidia-vllm-0.22.1",
    "gpu": "dual-rtx-pro-6000-blackwell-max-q-tp2-pcie",
    "model": "nemotron3-super-120b-a12b-nvfp4-tp2",
    "started_at": "2026-08-01T12:54:47Z"
  },
  "intelligence": {
    "checks": [
      {
        "attempt_count": 3,
        "attempts": [
          {
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "--- app.py\n+++ app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "content_excerpt": "--- app.py\n+++ app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 754.5269000002008,
            "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": 39,
              "prompt_tokens": 55,
              "prompt_tokens_details": null,
              "total_tokens": 94
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "--- app.py\n+++ app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "content_excerpt": "--- app.py\n+++ app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 750.5273999995552,
            "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": 39,
              "prompt_tokens": 55,
              "prompt_tokens_details": null,
              "total_tokens": 94
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "--- app.py\n+++ app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "content_excerpt": "--- app.py\n+++ app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 787.5385000006645,
            "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": 39,
              "prompt_tokens": 55,
              "prompt_tokens_details": null,
              "total_tokens": 94
            }
          }
        ],
        "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": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "The total latency (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, primarily due to the LLM\u2019s 1800 ms response time; a practical fix is to optimize the LLM inference via model quantization, caching frequent responses, or switching to a smaller, faster model.",
            "content_excerpt": "The total latency (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, primarily due to the LLM\u2019s 1800 ms response time; a practical fix is to optimize the LLM inference via model quantizati",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 1467.2005000011268,
            "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": 81,
              "prompt_tokens": 84,
              "prompt_tokens_details": null,
              "total_tokens": 165
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "The total latency (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, primarily due to the LLM\u2019s 1800 ms response time; a practical fix is to optimize the LLM inference via model quantization, caching frequent responses, or switching to a smaller, faster model.",
            "content_excerpt": "The total latency (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, primarily due to the LLM\u2019s 1800 ms response time; a practical fix is to optimize the LLM inference via model quantizati",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 1450.9081999985938,
            "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": 81,
              "prompt_tokens": 84,
              "prompt_tokens_details": null,
              "total_tokens": 165
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "The total latency (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, primarily due to the LLM\u2019s 1800 ms response time; a practical fix is to optimize the LLM inference via model quantization, caching frequent responses, or switching to a smaller, faster model.",
            "content_excerpt": "The total latency (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, primarily due to the LLM\u2019s 1800 ms response time; a practical fix is to optimize the LLM inference via model quantizati",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 1446.5532999984134,
            "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": 81,
              "prompt_tokens": 84,
              "prompt_tokens_details": null,
              "total_tokens": 165
            }
          }
        ],
        "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-20260801T125447Z",
  "schema": "anvil-serving.fast-tier-bakeoff/v1",
  "score_inputs": {
    "e2e_p50_ms": 4015.0637999995524,
    "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": 3234.4085999993695,
    "usable_context_tokens": 32768,
    "voice_latency_ms": null
  },
  "selection": {
    "context_targets": [
      32768
    ],
    "endpoint_already_loaded": true,
    "requests_per_context": 1,
    "suites": [
      "chat",
      "context",
      "intelligence",
      "session",
      "tool"
    ]
  },
  "session": {
    "checks": [
      {
        "attempt_count": 3,
        "attempts": [
          {
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "RIVER-918",
            "content_excerpt": "RIVER-918",
            "expected": "RIVER-918",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 207.56339999934426,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "usage": {
              "completion_tokens": 7,
              "prompt_tokens": 59,
              "prompt_tokens_details": null,
              "total_tokens": 66
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "RIVER-918",
            "content_excerpt": "RIVER-918",
            "expected": "RIVER-918",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 202.84760000140523,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "usage": {
              "completion_tokens": 7,
              "prompt_tokens": 59,
              "prompt_tokens_details": null,
              "total_tokens": 66
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "RIVER-918",
            "content_excerpt": "RIVER-918",
            "expected": "RIVER-918",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 212.05809999992198,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "usage": {
              "completion_tokens": 7,
              "prompt_tokens": 59,
              "prompt_tokens_details": null,
              "total_tokens": 66
            }
          }
        ],
        "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/tp2-model-campaign-recipes.toml",
    "serve_command": null
  },
  "suites": {},
  "thinking": {
    "chat_template_kwargs": {
      "enable_thinking": false
    },
    "control_evidence": "docs/findings/2026-08-01-dual-pro-tp2-campaign-evidence/nemotron3-super-thinking-disabled-control.json",
    "control_evidence_sha256": "d5a1b07fbc9e756aabcbe9bb3b69a7e84a19520ad9fac88027eafc5c3a0007b1",
    "control_mechanism": "chat_template_kwargs",
    "control_requested": {
      "enable_thinking": false
    },
    "control_status": "verified",
    "mode": "disabled",
    "reasoning_effort": null,
    "unsupported": false
  },
  "timing": {
    "chat": {
      "content_chunks": 47,
      "decode_tok_s_p50": 60.2058373530196,
      "decode_tok_s_p95": 60.2058373530196,
      "e2e_p50_ms": 4015.0637999995524,
      "e2e_p95_ms": 4015.0637999995524,
      "effective_prefill_tok_s_p50": 9240.329128486062,
      "effective_prefill_tok_s_p95": 9240.329128486062,
      "generation_p50_ms": 780.655200000183,
      "generation_p95_ms": 780.655200000183,
      "mean_inter_token_latency_ms_p50": 16.60968510638687,
      "mean_inter_token_latency_ms_p95": 16.60968510638687,
      "output_tokens": 48,
      "prompt_token_samples": 1,
      "prompt_tokens": 29887,
      "prompt_tokens_p50": 29887.0,
      "prompt_tokens_p95": 29887.0,
      "ttft_p50_ms": 3234.4085999993695,
      "ttft_p95_ms": 3234.4085999993695,
      "ttft_samples": 1
    },
    "wall_ms": 13226.709799999298
  },
  "tool": {
    "checks": [
      {
        "attempt_count": 3,
        "attempts": [
          {
            "arguments": {
              "zip": "98101"
            },
            "attempt": 1,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "",
            "content_excerpt": "",
            "failure_class": null,
            "finish_reason": "tool_calls",
            "latency_ms": 633.3443999992596,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "tool_call_count": 1,
            "usage": {
              "completion_tokens": 32,
              "prompt_tokens": 289,
              "prompt_tokens_details": null,
              "total_tokens": 321
            },
            "valid_tool_call_count": 1,
            "validation_errors": []
          },
          {
            "arguments": {
              "zip": "98101"
            },
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "",
            "content_excerpt": "",
            "failure_class": null,
            "finish_reason": "tool_calls",
            "latency_ms": 641.6726000006747,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "tool_call_count": 1,
            "usage": {
              "completion_tokens": 32,
              "prompt_tokens": 289,
              "prompt_tokens_details": null,
              "total_tokens": 321
            },
            "valid_tool_call_count": 1,
            "validation_errors": []
          },
          {
            "arguments": {
              "zip": "98101"
            },
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 512,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 512
            },
            "content": "",
            "content_excerpt": "",
            "failure_class": null,
            "finish_reason": "tool_calls",
            "latency_ms": 624.7899999998481,
            "reasoning_chars": 0,
            "reasoning_excerpt": "",
            "reasoning_field": null,
            "reasoning_tokens": null,
            "status": "passed",
            "tool_call_count": 1,
            "usage": {
              "completion_tokens": 32,
              "prompt_tokens": 289,
              "prompt_tokens_details": null,
              "total_tokens": 321
            },
            "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
  }
}