{ "context": { "cap_tokens": 261056, "max_model_len": 262144, "targets": [ { "attempted_context_tokens": 32768, "chars_per_token": 3.0, "clamped_tokens": 32768, "e2e_ms": 2847.961299936287, "estimated_prompt_tokens": 32768, "output_tokens": 64, "status": "passed", "target_tokens": 32768, "ttft_ms": 2172.514899983071, "usage": { "completion_tokens": 64, "prompt_tokens": 31254, "total_tokens": 31318 } } ] }, "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://127.0.0.1:30002/v1", "candidate_id": "poolside-laguna-s-2.1-nvfp4-07614121", "config_id": "release-sweep-thinking-disabled", "engine": "vllm-nightly-f25953cc", "gpu": "rtx-pro-6000-blackwell", "model": "laguna-s-2.1-nvfp4", "started_at": "2026-07-27T16:40:04Z" }, "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": "```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": 507.77479994576424, "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": 44, "prompt_tokens": 79, "prompt_tokens_details": null, "total_tokens": 123 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "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": 506.7628000397235, "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": 44, "prompt_tokens": 79, "prompt_tokens_details": null, "total_tokens": 123 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "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": 511.79699995554984, "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": 44, "prompt_tokens": 79, "prompt_tokens_details": null, "total_tokens": 123 } } ], "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 problem is that the combined STT, LLM, and TTS processing time (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, causing the agent to time out. A practical fix is to reduce the LLM latency (e.g., by using a faster model or optimizing prompts) to bring the total processing time under 2500 ms.", "content_excerpt": "The problem is that the combined STT, LLM, and TTS processing time (550 + 1800 + 650 = 3000 ms) exceeds the 2500 ms turn timeout, causing the agent to time out. A practical fix is to reduce the LLM la", "failure_class": null, "finish_reason": "stop", "latency_ms": 1032.1972999954596, "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": 95, "prompt_tokens": 106, "prompt_tokens_details": null, "total_tokens": 201 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "The problem is that the combined STT, LLM, and TTS processing times (550 + 1800 + 650 = 3000 ms) exceed the 2500 ms turn timeout, causing the agent to fail. A practical fix is to reduce the LLM's processing time (e.g., by using a faster model or optimizing prompts) to bring the total under 2500 ms.", "content_excerpt": "The problem is that the combined STT, LLM, and TTS processing times (550 + 1800 + 650 = 3000 ms) exceed the 2500 ms turn timeout, causing the agent to fail. A practical fix is to reduce the LLM's proc", "failure_class": null, "finish_reason": "stop", "latency_ms": 1034.8589000059292, "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": 94, "prompt_tokens": 106, "prompt_tokens_details": null, "total_tokens": 200 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "The problem is that the combined STT+LLM+TTS latency (550+1800+650 = 3000 ms) exceeds the 2500 ms turn timeout, causing the agent to cut off before completing; a practical fix is to reduce the LLM latency (e.g., use a faster model or lower max tokens) to bring the total under 2500 ms.", "content_excerpt": "The problem is that the combined STT+LLM+TTS latency (550+1800+650 = 3000 ms) exceeds the 2500 ms turn timeout, causing the agent to cut off before completing; a practical fix is to reduce the LLM lat", "failure_class": null, "finish_reason": "stop", "latency_ms": 990.5426000477746, "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": 91, "prompt_tokens": 106, "prompt_tokens_details": null, "total_tokens": 197 } } ], "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-20260727T164004Z", "schema": "anvil-serving.fast-tier-bakeoff/v1", "score_inputs": { "e2e_p50_ms": 2847.961299936287, "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": 2172.514899983071, "usable_context_tokens": 32768, "voice_latency_ms": null }, "selection": { "context_targets": [ 32768 ], "endpoint_already_loaded": true, "requests_per_context": 1, "suites": [ "chat", "tool", "session", "intelligence" ] }, "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": 118.04690002463758, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "usage": { "completion_tokens": 6, "prompt_tokens": 81, "prompt_tokens_details": null, "total_tokens": 87 } }, { "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": 77.81109993811697, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "usage": { "completion_tokens": 6, "prompt_tokens": 81, "prompt_tokens_details": null, "total_tokens": 87 } }, { "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": 77.27100001648068, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "usage": { "completion_tokens": 6, "prompt_tokens": 81, "prompt_tokens_details": null, "total_tokens": 87 } } ], "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": null, "control_evidence_sha256": null, "control_mechanism": "chat_template_kwargs", "control_requested": { "enable_thinking": false }, "control_status": "requested_unverified", "mode": "disabled", "reasoning_effort": null, "unsupported": false }, "timing": { "chat": { "content_chunks": 64, "e2e_p50_ms": 2847.961299936287, "e2e_p95_ms": 2847.961299936287, "output_tokens": 64, "ttft_p50_ms": 2172.514899983071, "ttft_p95_ms": 2172.514899983071, "ttft_samples": 1 }, "wall_ms": 8739.683200023137 }, "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": 340.69360001012683, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "tool_call_count": 1, "usage": { "completion_tokens": 27, "prompt_tokens": 149, "prompt_tokens_details": null, "total_tokens": 176 }, "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": 335.6898999772966, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "tool_call_count": 1, "usage": { "completion_tokens": 27, "prompt_tokens": 149, "prompt_tokens_details": null, "total_tokens": 176 }, "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": 326.4251999789849, "reasoning_chars": 0, "reasoning_excerpt": "", "reasoning_field": null, "reasoning_tokens": null, "status": "passed", "tool_call_count": 1, "usage": { "completion_tokens": 27, "prompt_tokens": 149, "prompt_tokens_details": null, "total_tokens": 176 }, "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 } }