schema_version: 1
baseline_id: baseline-evalrun-adhoc-evidence-premium-demo-merged-20260721-afternoon
suite_id: adhoc-evidence-premium-demo
suite_version: 2214c0c56eb6
promoted_from_run_id: evalrun-adhoc-evidence-premium-demo-merged-20260721-afternoon
registry_revision: unknown
created_at: '2026-07-21T09:55:30.165997+00:00'
created_by: huyibin@pingcap.com
notes: 'merged baseline from afternoon dev adhoc runs on 2026-07-21; source runs:
  evalrun-dca9124193b04b2c873027cd9fb2ca6f, evalrun-9f9830380cfa4796ad7e093d293528af,
  evalrun-a6921afa263e4be1a7c1bdcc298bbe72; 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: 10
  passed_count: 5
  failed_count: 5
  invalid_count: 0
  token_usage_summary:
    workspace_count: 10
    session_count: 10
    input_tokens: 10
    output_tokens: 4818
    cache_read_tokens: 370192
    cache_write_tokens: 25196
    cost_amount: 3.319843
runtime_export:
  dir: /evaluation/regression/baselines/runs/evalrun-adhoc-evidence-premium-demo-merged-20260721-afternoon
  report_path: /evaluation/regression/baselines/runs/evalrun-adhoc-evidence-premium-demo-merged-20260721-afternoon/report.txt
  report_detail_path: /evaluation/regression/baselines/runs/evalrun-adhoc-evidence-premium-demo-merged-20260721-afternoon/report_detail.txt
cases:
- case_id: classify-selected-stores-as-tikv-or-tiflash-in-premium-cluster
  case_version: 493b1a6c3845
  case_run_id: evalcase-16816e19b9f640618511a2bd5bf56428
  workspace_id: ws-eval-1784617243353-88cd4ec7
  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: 16
  passed_checks: 0
  total_checks: 0
- case_id: new-slow-query-digests-between-adjacent-windows-in-premium-cluster
  case_version: ac925f7b785c
  case_run_id: evalcase-47d0b8b74e924c7dbdc81ef93bda727f
  workspace_id: ws-eval-1784617297384-4da98606
  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: 85
  passed_checks: 0
  total_checks: 0
- case_id: premium-keyspace-storage-query-semantics
  case_version: 8da2105ccd09
  case_run_id: evalcase-b5720968534a4efd9cb8fd9e4f335402
  workspace_id: ws-eval-1784617422348-71a05571
  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: 56
  passed_checks: 3
  total_checks: 5
- case_id: read-pool-cpu-scope-compare-in-premium-cluster-during-latest-window
  case_version: 186ae507c635
  case_run_id: evalcase-7fddf9b513a04a489f26355a44ae6c8e
  workspace_id: ws-eval-1784617551544-6c16bf5b
  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: 3
  total_checks: 3
- case_id: representative-business-slow-queries-in-premium-cluster-during-latest-window
  case_version: 028bfd401cb4
  case_run_id: evalcase-94272b66dd89438d8c831759f6bc608d
  workspace_id: ws-eval-1784625405607-0089da6b
  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-in-premium-cluster-during-incident-window
  case_version: 6ad73e1d9a98
  case_run_id: evalcase-0837f92db5d2414cb25b8e713a379a06
  workspace_id: ws-eval-1784617798848-469bdb0f
  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: 56
  passed_checks: 0
  total_checks: 0
- case_id: throttle-refill-rate-verification-after-change-window
  case_version: fc0dc52f0f72
  case_run_id: evalcase-b67c22d03b554347bbb675757a54ced2
  workspace_id: ws-eval-1784624523538-753849df
  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: 3
  total_checks: 3
- case_id: top-cpu-overload-nodes-and-log-patterns-in-premium-cluster-during-latest-window
  case_version: 586382c620a0
  case_run_id: evalcase-1dd5f72ba4a944f09e48502ce55f1652
  workspace_id: ws-eval-1784618267343-4a2d5ff3
  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: 21
  passed_checks: 0
  total_checks: 0
- case_id: top-tidb-p99-latency-nodes-in-premium-cluster-during-latest-window
  case_version: 97825d887d20
  case_run_id: evalcase-dcfcc204b5ac4c20bb3ff77b5c7b3c01
  workspace_id: ws-eval-1784618349255-46bfa596
  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: 40
  passed_checks: 0
  total_checks: 0
- case_id: ttl-row-processing-in-premium-cluster-during-sql-tail-latency-incident-window
  case_version: 711bc62c8fa6
  case_run_id: evalcase-62f2289b62dd466ebdeda9acf084dd67
  workspace_id: ws-eval-1784618394922-ee5c111b
  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: 70
  passed_checks: 7
  total_checks: 7