Evaluation Run Report Run ID: evalrun-adhoc-evidence-demo-merged-20260722 Suite: adhoc-evidence-demo @ 126ce520d38c Status: completed (comparison=review_only, trigger=manual_merge) Counts: cases=12 pass=6 fail=6 invalid=0 Score: avg=79.58 stddev=18.60 scored_cases=12/12 Timing: avg=0m53s stddev=0m21s measured_cases=12/12 Token usage: input_avg=1 input_stddev=0 output_avg=659.50 output_stddev=685.87 reasoning_avg=0 reasoning_stddev=0 cache_read_avg=33747.17 cache_read_stddev=14407.51 cache_write_avg=3821.83 cache_write_stddev=5024.20 cached_total_avg=37569 cached_total_stddev=15963.52 cost_avg=$0.2213 cost_stddev=$0.1103 measured_cases=12/12 Case Results - tikv-read-iops-ranking-during-incident-window: verdict=fail score=69 failure=critical_evidence_partial duration=0m28s - tikv-read-iops-full-ranking-across-two-clusters-during-incident-window: verdict=fail score=69 failure=critical_evidence_partial duration=1m23s - topsql-links-for-hottest-two-tikv-nodes-during-incident-window: verdict=fail score=69 failure=critical_evidence_partial duration=0m25s - representative-business-slow-queries-in-saas01-during-latest-window: verdict=fail score=44 failure=critical_evidence_partial duration=0m43s - new-slow-query-digests-between-adjacent-windows-in-saas01: verdict=pass score=100 failure=- duration=1m24s - top-cpu-overload-nodes-and-log-patterns-in-saas01-during-latest-window: verdict=pass score=100 failure=- duration=1m11s - top-tidb-p99-latency-nodes-in-saas01-during-latest-window: verdict=pass score=100 failure=- duration=0m49s - classify-selected-stores-as-tikv-or-tiflash: verdict=pass score=100 failure=- duration=0m42s - compaction-signals-on-db-tikv-9-in-saas01-during-latest-window: verdict=fail score=69 failure=critical_evidence_partial duration=1m05s - map-selected-tikv-pods-to-worker-nodes-in-saas01: verdict=pass score=100 failure=- duration=0m48s - single-node-cpu-core-scope-compare-during-incident-window: verdict=fail score=62 failure=critical_evidence_partial duration=1m10s - ttl-row-processing-during-sql-tail-latency-incident-window: verdict=pass score=73 failure=- duration=0m23s For bucket-level and case-level details, see report_detail.txt.