schema_version: 1
baseline_id: baseline-evalrun-adhoc-evidence-demo-merged-20260722
suite_id: adhoc-evidence-demo
suite_version: 126ce520d38c
promoted_from_run_id: evalrun-adhoc-evidence-demo-merged-20260722
registry_revision: unknown
created_at: '2026-07-22T02:17:16.098231+00:00'
created_by: huyibin@pingcap.com
notes: 'merged baseline from recent dev adhoc runs on 2026-07-22; source runs: evalrun-9ca3e149083040cfa6e5a554382fc030,
  evalrun-6d3259e4b7624c89b6ac9c20e86209b0; overlapping cases resolved to the latest
  completed run'
runtime:
  agent_type: opencode
  resolved_model: chat/claude-standard/high
summary:
  execution_status: completed
  comparison_status: review_only
  trigger_mode: manual_merge
  case_count: 12
  passed_count: 6
  failed_count: 6
  invalid_count: 0
  token_usage_summary:
    workspace_count: 12
    session_count: 12
    input_tokens: 12
    output_tokens: 7914
    reasoning_tokens: 0
    cache_read_tokens: 404966
    cache_write_tokens: 45862
    cost_amount: 2.655796
runtime_export:
  dir: /evaluation/regression/baselines/runs/evalrun-adhoc-evidence-demo-merged-20260722
  report_path: /evaluation/regression/baselines/runs/evalrun-adhoc-evidence-demo-merged-20260722/report.txt
  report_detail_path: /evaluation/regression/baselines/runs/evalrun-adhoc-evidence-demo-merged-20260722/report_detail.txt
cases:
- case_id: tikv-read-iops-ranking-during-incident-window
  case_version: 11f65198440f
  case_run_id: evalcase-4f10f24010aa4e46875278543ee1f30a
  workspace_id: ws-eval-1784628349150-c92b148e
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 69
  passed_checks: 0
  total_checks: 0
- case_id: tikv-read-iops-full-ranking-across-two-clusters-during-incident-window
  case_version: 06429771f36b
  case_run_id: evalcase-12781bc4c05b488ebacc8ea229a28aba
  workspace_id: ws-eval-1784685385429-feac804f
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 69
  passed_checks: 0
  total_checks: 0
- case_id: topsql-links-for-hottest-two-tikv-nodes-during-incident-window
  case_version: 72cbcf82e62d
  case_run_id: evalcase-a4e7b424827349fabb737e1ee940fccf
  workspace_id: ws-eval-1784628476449-a1d374b1
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 69
  passed_checks: 0
  total_checks: 0
- case_id: representative-business-slow-queries-in-saas01-during-latest-window
  case_version: d540a138adf6
  case_run_id: evalcase-5f2c9ecf4b124edfb6000bcb9431a778
  workspace_id: ws-eval-1784628501401-3950606f
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 44
  passed_checks: 0
  total_checks: 0
- case_id: new-slow-query-digests-between-adjacent-windows-in-saas01
  case_version: 264f6a098ffe
  case_run_id: evalcase-032aea75814345bb827d83681ad2dd40
  workspace_id: ws-eval-1784628544729-860b0978
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: pass
  primary_failure_code: ''
  score: 100
  passed_checks: 0
  total_checks: 0
- case_id: top-cpu-overload-nodes-and-log-patterns-in-saas01-during-latest-window
  case_version: d7aaadae63ed
  case_run_id: evalcase-953d68b097254344af2acf6e28f4724e
  workspace_id: ws-eval-1784628628244-6b238c69
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: pass
  primary_failure_code: ''
  score: 100
  passed_checks: 0
  total_checks: 0
- case_id: top-tidb-p99-latency-nodes-in-saas01-during-latest-window
  case_version: 17641b98120a
  case_run_id: evalcase-c3a0bad379324895b0b63f5aacb5f33f
  workspace_id: ws-eval-1784685468326-179011a2
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: pass
  primary_failure_code: ''
  score: 100
  passed_checks: 0
  total_checks: 0
- case_id: classify-selected-stores-as-tikv-or-tiflash
  case_version: 80d079da7d81
  case_run_id: evalcase-b59665532b504cea96ed86eeaa72c2f8
  workspace_id: ws-eval-1784628733310-411e36ce
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: pass
  primary_failure_code: ''
  score: 100
  passed_checks: 0
  total_checks: 0
- case_id: compaction-signals-on-db-tikv-9-in-saas01-during-latest-window
  case_version: 855ab6923096
  case_run_id: evalcase-eb1a19c81bb149f2ad312c3eda9a9419
  workspace_id: ws-eval-1784628774908-142a0c7d
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 69
  passed_checks: 0
  total_checks: 0
- case_id: map-selected-tikv-pods-to-worker-nodes-in-saas01
  case_version: 4993c33dc2fa
  case_run_id: evalcase-e2f133c76f9a43689a1e011ae870a994
  workspace_id: ws-eval-1784628840145-28bfed9c
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: pass
  primary_failure_code: ''
  score: 100
  passed_checks: 0
  total_checks: 0
- case_id: single-node-cpu-core-scope-compare-during-incident-window
  case_version: 15599c069b9a
  case_run_id: evalcase-ae1b0b270b4440af8603b04990364c6b
  workspace_id: ws-eval-1784628888955-ff42d19f
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 62
  passed_checks: 0
  total_checks: 0
- case_id: ttl-row-processing-during-sql-tail-latency-incident-window
  case_version: e7127d23a894
  case_run_id: evalcase-a7f520fd07aa49af944a0a9a0a0f0413
  workspace_id: ws-eval-1784628958524-c18f0927
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard/high
  judgment_verdict: pass
  primary_failure_code: ''
  score: 73
  passed_checks: 7
  total_checks: 7
