{ "run_id": "2026-10-08-core-greedy-nothink-35cc5e", "suite": "decision-conformance", "tier": "core", "suite_hash": "554e796a858218e48bcb83da003554769782a4a32d3e061da87510d7f9cea490", "subject": "clef-flash/hf-fde727a/bnb-nf4-iammrduncan/decide-server-clef-torch-cuda-tf5.19.0-torch2.14.1-cu126", "mode": "native", "profile": "greedy-nothink", "status": "complete", "label": null, "items": { "planned": 17, "attempted": 17, "succeeded": 17, "failed": 0, "failed_by_status": {} }, "metrics": { "checks": { "invariants": { "passed": 33, "total": 33, "failures": [] }, "batched_vs_separate": { "passed": 3, "total": 6, "failures": [ "support/team: differs by 0.1254", "support/needs_human: differs by 0.0773", "invoice/disposition: differs by 0.0931" ], "max_abs_diff": 0.1254 }, "repeat_stability": { "passed": 6, "total": 6, "failures": [], "max_std": 0 }, "option_order": { "passed": 2, "total": 2, "failures": [], "max_confidence_delta": 0 }, "monotonic": { "passed": 2, "total": 2, "failures": [], "expected_scores": [ 0.9857, 1.1915, 2.8987 ] } }, "passed": 46, "total": 49 }, "latency_ms": { "p50": 1645.114375, "p95": 2294.507916, "p99": 2294.507916, "note": "successful requests, nearest rank, measured from America/Chicago" }, "usage": { "input_tokens": 5562, "output_tokens": 0, "cost_usd": 0 } }