{ "context": { "cap_tokens": 129984, "max_model_len": 131072, "targets": [ { "attempted_context_tokens": 32768, "chars_per_token": 3.0, "clamped_tokens": 32768, "e2e_ms": 2248.590200091712, "estimated_prompt_tokens": 32768, "output_tokens": 64, "status": "passed", "target_tokens": 32768, "ttft_ms": 1847.132100025192, "usage": { "completion_tokens": 64, "prompt_tokens": 31225, "total_tokens": 31289 } } ] }, "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": "agents-a1-addff08f", "config_id": "release-sweep-thinking-disabled", "engine": "vllm-nightly-f25953cc", "gpu": "rtx-pro-6000-blackwell", "model": "agents-a1", "started_at": "2026-07-27T17:18:43Z" }, "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": 347.51580003648996, "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": 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": 369.234099984169, "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": 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": 350.6162000121549, "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": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "The system exceeds its 2500 ms timeout because the sequential sum of STT, LLM, and TTS (3000 ms) is too long, so a practical fix is to run the LLM generation in parallel with the STT or TTS processes.", "content_excerpt": "The system exceeds its 2500 ms timeout because the sequential sum of STT, LLM, and TTS (3000 ms) is too long, so a practical fix is to run the LLM generation in parallel with the STT or TTS processes.", "failure_class": null, "finish_reason": "stop", "latency_ms": 437.1642000041902, "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": 59, "prompt_tokens": 79, "prompt_tokens_details": null, "total_tokens": 138 } }, { "attempt": 2, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "The system exceeds its 2500 ms timeout because the sequential sum of STT, LLM, and TTS (3000 ms) is too long, so a practical fix is to run the LLM generation in parallel with the STT or TTS processes.", "content_excerpt": "The system exceeds its 2500 ms timeout because the sequential sum of STT, LLM, and TTS (3000 ms) is too long, so a practical fix is to run the LLM generation in parallel with the STT or TTS processes.", "failure_class": null, "finish_reason": "stop", "latency_ms": 460.5851999949664, "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": 59, "prompt_tokens": 79, "prompt_tokens_details": null, "total_tokens": 138 } }, { "attempt": 3, "budget": { "legacy_max_tokens_as_visible": false, "max_completion_tokens": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "The system exceeds its 2500 ms timeout because the sequential sum of STT, LLM, and TTS (3000 ms) is too long, so a practical fix is to run the LLM generation in parallel with the STT or TTS processes.", "content_excerpt": "The system exceeds its 2500 ms timeout because the sequential sum of STT, LLM, and TTS (3000 ms) is too long, so a practical fix is to run the LLM generation in parallel with the STT or TTS processes.", "failure_class": null, "finish_reason": "stop", "latency_ms": 434.98399993404746, "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": 59, "prompt_tokens": 79, "prompt_tokens_details": null, "total_tokens": 138 } } ], "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-20260727T171843Z", "schema": "anvil-serving.fast-tier-bakeoff/v1", "score_inputs": { "e2e_p50_ms": 2248.590200091712, "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": 1847.132100025192, "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": 138.453199993819, "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": 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": 122.56909999996424, "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": 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": 110.85179995279759, "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": "temp-operator-registry", "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": 2248.590200091712, "e2e_p95_ms": 2248.590200091712, "output_tokens": 64, "ttft_p50_ms": 1847.132100025192, "ttft_p95_ms": 1847.132100025192, "ttft_samples": 1 }, "wall_ms": 5837.680500000715 }, "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": 264.66220000293106, "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": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "", "content_excerpt": "", "failure_class": null, "finish_reason": "tool_calls", "latency_ms": 255.42589998804033, "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": 512, "reasoning_headroom_tokens": 0, "visible_answer_tokens": 512 }, "content": "", "content_excerpt": "", "failure_class": null, "finish_reason": "tool_calls", "latency_ms": 265.1235000230372, "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 } }