{
  "context": {
    "cap_tokens": 129984,
    "max_model_len": 131072,
    "targets": [
      {
        "attempted_context_tokens": 32768,
        "chars_per_token": 3.0,
        "clamped_tokens": 32768,
        "e2e_ms": 2064.59950000135,
        "estimated_prompt_tokens": 32768,
        "output_tokens": 64,
        "status": "passed",
        "target_tokens": 32768,
        "ttft_ms": 1725.7140000001527,
        "usage": {
          "completion_tokens": 64,
          "prompt_tokens": 31225,
          "total_tokens": 31289
        }
      },
      {
        "attempted_context_tokens": 120000,
        "chars_per_token": 3.148,
        "clamped_tokens": 120000,
        "e2e_ms": 12287.853699999687,
        "estimated_prompt_tokens": 119999,
        "output_tokens": 64,
        "status": "passed",
        "target_tokens": 120000,
        "ttft_ms": 11924.257599999692,
        "usage": {
          "completion_tokens": 64,
          "prompt_tokens": 127498,
          "total_tokens": 127562
        }
      }
    ]
  },
  "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://127.0.0.1:30010/v1",
    "candidate_id": "protoLabsAI/Agents-A1-NVFP4@ff24ba5c35b99af25d7bf03c7997be5a0d2a5520",
    "config_id": "agents-a1-nvfp4-text-f25953cc-marlin",
    "engine": "vllm-f25953cc-marlin",
    "gpu": "rtx-pro-6000",
    "model": "agents-a1-nvfp4-text",
    "started_at": "2026-07-29T04:44:05Z"
  },
  "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": "```diff\n--- a/app.py\n+++ b/app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2\n```",
            "content_excerpt": "```diff\n--- a/app.py\n+++ b/app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2\n```",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 301.82000000058906,
            "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": 45,
              "prompt_tokens": 51,
              "prompt_tokens_details": null,
              "total_tokens": 96
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "```diff\n--- a/app.py\n+++ b/app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2\n```",
            "content_excerpt": "```diff\n--- a/app.py\n+++ b/app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2\n```",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 302.29079999844544,
            "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": 45,
              "prompt_tokens": 51,
              "prompt_tokens_details": null,
              "total_tokens": 96
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "```diff\n--- a/app.py\n+++ b/app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2\n```",
            "content_excerpt": "```diff\n--- a/app.py\n+++ b/app.py\n@@ -1,2 +1,2 @@\n-timeout = 30\n+timeout = 45\n retries = 2\n```",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 301.95829999865964,
            "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": 45,
              "prompt_tokens": 51,
              "prompt_tokens_details": null,
              "total_tokens": 96
            }
          }
        ],
        "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 processing time of 3000 ms exceeds the 2500 ms turn timeout, so a practical fix is to implement streaming TTS to start generating audio before the LLM finishes its full response.",
            "content_excerpt": "The total processing time of 3000 ms exceeds the 2500 ms turn timeout, so a practical fix is to implement streaming TTS to start generating audio before the LLM finishes its full response.",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 313.38940000023285,
            "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": 46,
              "prompt_tokens": 79,
              "prompt_tokens_details": null,
              "total_tokens": 125
            }
          },
          {
            "attempt": 2,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "The total processing time of 3000 ms exceeds the 2500 ms turn timeout, so a practical fix is to implement parallel execution for the STT and LLM stages or reduce the LLM response length to lower latency.",
            "content_excerpt": "The total processing time of 3000 ms exceeds the 2500 ms turn timeout, so a practical fix is to implement parallel execution for the STT and LLM stages or reduce the LLM response length to lower laten",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 338.32929999880434,
            "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": 51,
              "prompt_tokens": 79,
              "prompt_tokens_details": null,
              "total_tokens": 130
            }
          },
          {
            "attempt": 3,
            "budget": {
              "legacy_max_tokens_as_visible": false,
              "max_completion_tokens": 256,
              "reasoning_headroom_tokens": 0,
              "visible_answer_tokens": 256
            },
            "content": "The total processing time of 3000 ms exceeds the 2500 ms turn timeout, so a practical fix is to implement streaming TTS to begin generating audio before the LLM finishes its full response.",
            "content_excerpt": "The total processing time of 3000 ms exceeds the 2500 ms turn timeout, so a practical fix is to implement streaming TTS to begin generating audio before the LLM finishes its full response.",
            "failure_class": null,
            "finish_reason": "stop",
            "latency_ms": 308.81740000040736,
            "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": 46,
              "prompt_tokens": 79,
              "prompt_tokens_details": null,
              "total_tokens": 125
            }
          }
        ],
        "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-20260729T044405Z",
  "schema": "anvil-serving.fast-tier-bakeoff/v1",
  "score_inputs": {
    "e2e_p50_ms": 2064.59950000135,
    "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": 1725.7140000001527,
    "usable_context_tokens": 120000,
    "voice_latency_ms": null
  },
  "selection": {
    "context_targets": [
      32768,
      120000
    ],
    "endpoint_already_loaded": true,
    "requests_per_context": 1,
    "suites": [
      "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": 105.11440000118455,
            "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": 108.86899999968591,
            "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": 106.26479999882577,
            "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/agents-a1-qualification-text-recipes.toml",
    "serve_command": null
  },
  "suites": {},
  "thinking": {
    "chat_template_kwargs": {
      "enable_thinking": false
    },
    "control_evidence": "C:\\Users\\operator\\ai-code\\anvil-serving-wt-agents-a1-qualification\\docs\\findings\\2026-07-28-agents-a1-multimodal-qualification-evidence\\nvfp4-thinking-disabled-control.json",
    "control_evidence_sha256": "fa87148f19e783a0db21a0865f08fbf273d3992eefed7d7e23525dc925225ac0",
    "control_mechanism": "chat_template_kwargs",
    "control_requested": {
      "enable_thinking": false
    },
    "control_status": "verified",
    "mode": "disabled",
    "reasoning_effort": null,
    "unsupported": false
  },
  "timing": {
    "chat": {
      "content_chunks": 126,
      "e2e_p50_ms": 2064.59950000135,
      "e2e_p95_ms": 12287.853699999687,
      "output_tokens": 128,
      "ttft_p50_ms": 1725.7140000001527,
      "ttft_p95_ms": 11924.257599999692,
      "ttft_samples": 2
    },
    "wall_ms": 17247.34139999964
  },
  "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": 235.40539999885368,
            "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": 235.7510000001639,
            "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": 233.49840000082622,
            "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
  }
}
