{ "context": { "cap_tokens": 261056, "max_model_len": 262144, "targets": [ { "attempted_context_tokens": 32768, "chars_per_token": 3.0, "clamped_tokens": 32768, "e2e_ms": 2780.153751373291, "estimated_prompt_tokens": 32768, "output_tokens": 49, "status": "passed", "target_tokens": 32768, "ttft_ms": 2255.915880203247, "usage": { "completion_tokens": 50, "prompt_tokens": 27799, "total_tokens": 27849 } }, { "attempted_context_tokens": 128000, "chars_per_token": 3.536, "clamped_tokens": 128000, "e2e_ms": 21915.072202682495, "estimated_prompt_tokens": 127999, "output_tokens": 63, "status": "passed", "target_tokens": 128000, "ttft_ms": 21146.98314666748, "usage": { "completion_tokens": 64, "prompt_tokens": 148899, "total_tokens": 148963 } }, { "attempted_context_tokens": 240000, "chars_per_token": 3.04, "clamped_tokens": 240000, "e2e_ms": 51502.46047973633, "estimated_prompt_tokens": 239999, "output_tokens": 61, "status": "passed", "target_tokens": 240000, "ttft_ms": 50643.29481124878, "usage": { "completion_tokens": 64, "prompt_tokens": 243641, "total_tokens": 243705 } } ] }, "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": "poolside-laguna-s-2.1-nvfp4", "config_id": "laguna-s-vllm-f25953cc5-thinking-disabled", "engine": "vllm-0.23.1rc1.dev1327-gf25953cc5", "gpu": "rtx-pro-6000-blackwell-96gb", "model": "laguna-s-2.1-nvfp4", "started_at": "2026-07-26T18:14:19Z" }, "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": 562.9374980926514, "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": 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": 506.6838264465332, "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": 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": 512.8412246704102, "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": 256, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 256 }, "content": "The problem is that the combined STT (550 ms) + LLM (1800 ms) + TTS (650 ms) = 3000 ms exceeds the 2500 ms turn timeout, causing the agent to cut off before completing its response. A practical fix is to reduce the LLM latency (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 (550 ms) + LLM (1800 ms) + TTS (650 ms) = 3000 ms exceeds the 2500 ms turn timeout, causing the agent to cut off before completing its response. A practical fix is", "failure_class": null, "finish_reason": "stop", "latency_ms": 1075.9539604187012, "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": 97, "prompt_tokens": 106, "prompt_tokens_details": null, "total_tokens": 203 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 256, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 256 }, "content": "The problem is that the combined STT (550 ms) and LLM (1800 ms) processing times exceed the 2500 ms turn timeout, leaving insufficient time for TTS (650 ms). A practical fix is to reduce the LLM's response length or optimize its inference speed to ensure the total pipeline completes within the timeout.", "content_excerpt": "The problem is that the combined STT (550 ms) and LLM (1800 ms) processing times exceed the 2500 ms turn timeout, leaving insufficient time for TTS (650 ms). A practical fix is to reduce the LLM's res", "failure_class": null, "finish_reason": "stop", "latency_ms": 842.1857357025146, "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": 76, "prompt_tokens": 106, "prompt_tokens_details": null, "total_tokens": 182 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 256, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 256 }, "content": "The problem is that the combined STT (550 ms) and LLM (1800 ms) processing times exceed the 2500 ms turn timeout, leaving insufficient time for TTS (650 ms). A practical fix is to reduce the LLM's response length or optimize its inference speed to ensure the total pipeline fits within the timeout.", "content_excerpt": "The problem is that the combined STT (550 ms) and LLM (1800 ms) processing times exceed the 2500 ms turn timeout, leaving insufficient time for TTS (650 ms). A practical fix is to reduce the LLM's res", "failure_class": null, "finish_reason": "stop", "latency_ms": 833.8351249694824, "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": 76, "prompt_tokens": 106, "prompt_tokens_details": null, "total_tokens": 182 } } ], "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-20260726T181419Z", "schema": "anvil-serving.fast-tier-bakeoff/v1", "score_inputs": { "e2e_p50_ms": 21915.072202682495, "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": 21146.98314666748, "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": 129.48918342590332, "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": 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": 80.25693893432617, "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": 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": 80.4908275604248, "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": "C:\\Users\\operator\\ai-code\\anvil-serving\\docs\\findings\\2026-07-26-laguna-s-qualification-evidence\\thinking-disabled-control.json", "control_evidence_sha256": "7eb26ab85c3fe69212ed25eb5659b1b871e581eeaa3f5dde1f9e2b17324c7258", "control_mechanism": "chat_template_kwargs", "control_requested": { "enable_thinking": false }, "control_status": "verified", "mode": "disabled", "reasoning_effort": null, "unsupported": false }, "timing": { "chat": { "e2e_p50_ms": 21915.072202682495, "e2e_p95_ms": 51502.46047973633, "output_tokens": 173, "ttft_p50_ms": 21146.98314666748, "ttft_p95_ms": 50643.29481124878 }, "wall_ms": 81898.7843990326 }, "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": 343.49536895751953, "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": 256, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 256 }, "content": "", "content_excerpt": "", "failure_class": null, "finish_reason": "tool_calls", "latency_ms": 349.6119976043701, "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": 256, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 256 }, "content": "", "content_excerpt": "", "failure_class": null, "finish_reason": "tool_calls", "latency_ms": 342.19861030578613, "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 } }