schema_version: 1
baseline_id: baseline-evalrun-b92aea0782574c129e3a933d662adcdd
suite_id: core-daily-demo
suite_version: e3571509e8ac
promoted_from_run_id: evalrun-b92aea0782574c129e3a933d662adcdd
registry_revision: unknown
created_at: '2026-05-12T09:34:51.965296+00:00'
created_by: huyibin@pingcap.com
notes: promote full core-daily-demo run on 2026-05-12
runtime:
  agent_type: opencode
  resolved_model: chat/claude-standard
summary:
  execution_status: completed
  comparison_status: review_only
  trigger_mode: manual_suite
  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: 27622
    cache_read_tokens: 704857
    cache_write_tokens: 31821
    cost_amount: 10.578556
runtime_export:
  dir: /evaluation/regression/baselines/runs/evalrun-b92aea0782574c129e3a933d662adcdd
  report_path: /evaluation/regression/baselines/runs/evalrun-b92aea0782574c129e3a933d662adcdd/report.txt
  report_detail_path: /evaluation/regression/baselines/runs/evalrun-b92aea0782574c129e3a933d662adcdd/report_detail.txt
cases:
- case_id: component-restart-during-incident-window
  case_version: cd03343f3ef7
  case_run_id: evalcase-2a1f53d943ae439fb37587caf4022af4
  workspace_id: ws-eval-1778572349654-4c7a65f6
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: fail
  primary_failure_code: critical_evidence_missing
  score: 28
  passed_checks: 2
  total_checks: 5
- case_id: cpu-spike-during-incident-window
  case_version: a5e75668e1f3
  case_run_id: evalcase-7e41841180ff478c81f88e2857f5f9bc
  workspace_id: ws-eval-1778573040647-657eeeaf
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 30
  passed_checks: 0
  total_checks: 3
- case_id: expensive-query-alert-correlation-during-incident-window
  case_version: 7a663f223623
  case_run_id: evalcase-c7ddaf254f3f406ea948d49a56da2103
  workspace_id: ws-eval-1778574447532-a3b1856e
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: pass
  primary_failure_code: ''
  score: 70
  passed_checks: 4
  total_checks: 6
- case_id: expensive-query-spike-during-incident-window
  case_version: 5c4d6bf173b9
  case_run_id: evalcase-75c218ed65e948f3bdb34eaf2660a5d7
  workspace_id: ws-eval-1778574617141-618cf3a5
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: pass
  primary_failure_code: ''
  score: 72
  passed_checks: 3
  total_checks: 4
- case_id: panic-in-recoverable-goroutine
  case_version: a330e001c7c5
  case_run_id: evalcase-1044e301c5204184bb6883771c7cc52b
  workspace_id: ws-eval-1778575526452-c5aeeaf3
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: pass
  primary_failure_code: ''
  score: 70
  passed_checks: 3
  total_checks: 5
- case_id: service-degradation-during-incident-window
  case_version: b86078f4564e
  case_run_id: evalcase-abbbe6993bfb48a080371e934cbe1b1a
  workspace_id: ws-eval-1778575345837-f2429901
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: pass
  primary_failure_code: ''
  score: 75
  passed_checks: 3
  total_checks: 4
- case_id: sql-tail-latency-spike-during-incident-window
  case_version: a2d3bafe2787
  case_run_id: evalcase-2a3466a2b76040b09879600b42bfd26e
  workspace_id: ws-eval-1778574980199-cef3cb3e
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 48
  passed_checks: 1
  total_checks: 4
- case_id: sustained-cpu-pressure-during-incident-window
  case_version: 54b423b69641
  case_run_id: evalcase-0380e08d721e48508375f8e1ed9c72da
  workspace_id: ws-eval-1778573201918-68b5e3dc
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 69
  passed_checks: 3
  total_checks: 4
- case_id: system-unavailability-during-incident-window
  case_version: 303681c39cf1
  case_run_id: evalcase-14240092b7f4417f8d4817f8b8605058
  workspace_id: ws-eval-1778573634113-cff7d373
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: fail
  primary_failure_code: critical_evidence_partial
  score: 54
  passed_checks: 3
  total_checks: 6
- case_id: tail-latency-surge-during-incident-window
  case_version: 0a496f2e3723
  case_run_id: evalcase-9093a69aa0bc42078a0f91e2d47102c0
  workspace_id: ws-eval-1778575728562-e2eaeeb7
  execution_status: completed
  comparison_status: review_only
  runtime_metadata:
    agent_type: opencode
    resolved_model: chat/claude-standard
  judgment_verdict: pass
  primary_failure_code: ''
  score: 100
  passed_checks: 3
  total_checks: 3
baseline_variants:
- baseline_id: baseline-evalrun-3e8725979333434fa751c2dfb9a6b21f
  suite_id: core-daily-demo
  suite_version: e3571509e8ac
  promoted_from_run_id: evalrun-3e8725979333434fa751c2dfb9a6b21f
  registry_revision: d3f3a12e3b5a67bd4d76718c7311970f105f3469
  created_at: '2026-05-14T12:11:51+00:00'
  created_by: recovered-from-export
  notes: recovered gpt-5.2 baseline variant from exported run artifacts; source DB record unavailable locally
  runtime:
    agent_type: opencode
    resolved_model: openai/gpt-5.2
  summary:
    execution_status: completed
    comparison_status: review_only
    trigger_mode: manual_suite
    case_count: 10
    passed_count: 4
    failed_count: 6
    invalid_count: 0
    token_usage_summary:
      workspace_count: 10
      session_count: 10
      input_tokens: 27860
      output_tokens: 13469
      cache_read_tokens: 520960
      cache_write_tokens: 0
      cost_amount: 0.0
  runtime_export:
    dir: /evaluation/regression/baselines/runs/evalrun-3e8725979333434fa751c2dfb9a6b21f
    report_path: /evaluation/regression/baselines/runs/evalrun-3e8725979333434fa751c2dfb9a6b21f/report.txt
    report_detail_path: ''
  cases:
  - case_id: component-restart-during-incident-window
    case_version: cd03343f3ef7
    case_run_id: evalcase-748d06d6b6f3449b93920bc45de66cde
    workspace_id: ws-eval-1778483930424-ae89fba7
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: fail
    primary_failure_code: critical_evidence_missing
    score: 20
    passed_checks: 1
    total_checks: 5
  - case_id: cpu-spike-during-incident-window
    case_version: a5e75668e1f3
    case_run_id: evalcase-0fc4dcc566d54df9b5a93af851e4cd2f
    workspace_id: ws-eval-1778484091473-fee04d31
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: fail
    primary_failure_code: diagnosis_critical_gate_failed
    score: 50
    passed_checks: 1
    total_checks: 3
  - case_id: expensive-query-alert-correlation-during-incident-window
    case_version: 7a663f223623
    case_run_id: evalcase-01ed5ecd58584f75b460647ff77158b6
    workspace_id: ws-eval-1778484959089-9f11779d
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: pass
    primary_failure_code: ''
    score: 92
    passed_checks: 5
    total_checks: 6
  - case_id: expensive-query-spike-during-incident-window
    case_version: 5c4d6bf173b9
    case_run_id: evalcase-9d9c80bc09454c489b1f1c9672225292
    workspace_id: ws-eval-1778485209312-cccaae73
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: fail
    primary_failure_code: diagnosis_critical_gate_failed
    score: 69
    passed_checks: 3
    total_checks: 4
  - case_id: panic-in-recoverable-goroutine
    case_version: a330e001c7c5
    case_run_id: evalcase-f2ba950f1c6f4c40a19c0fb2d22f0437
    workspace_id: ws-eval-1778486019543-7351cc3c
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: pass
    primary_failure_code: ''
    score: 88
    passed_checks: 4
    total_checks: 5
  - case_id: service-degradation-during-incident-window
    case_version: b86078f4564e
    case_run_id: evalcase-9f720c6bcbc34831a00369684597362a
    workspace_id: ws-eval-1778485779958-a171cd48
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: pass
    primary_failure_code: ''
    score: 71
    passed_checks: 2
    total_checks: 4
  - case_id: sql-tail-latency-spike-during-incident-window
    case_version: a2d3bafe2787
    case_run_id: evalcase-d13fad687c5f44b193d158c91bded21a
    workspace_id: ws-eval-1778485451230-a73e4c96
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: fail
    primary_failure_code: critical_evidence_partial
    score: 48
    passed_checks: 1
    total_checks: 4
  - case_id: sustained-cpu-pressure-during-incident-window
    case_version: 54b423b69641
    case_run_id: evalcase-30e1b76e6414451e99a2425d978b0373
    workspace_id: ws-eval-1778491681212-31f560ac
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: fail
    primary_failure_code: critical_evidence_partial
    score: 48
    passed_checks: 1
    total_checks: 4
  - case_id: system-unavailability-during-incident-window
    case_version: 303681c39cf1
    case_run_id: evalcase-bf218bc80fc64a728549406d1c7af6fa
    workspace_id: ws-eval-1778484716929-c6d22bd0
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: fail
    primary_failure_code: critical_evidence_partial
    score: 39
    passed_checks: 2
    total_checks: 6
  - case_id: tail-latency-surge-during-incident-window
    case_version: 0a496f2e3723
    case_run_id: evalcase-09408f2686be4b7988dcc839789f636a
    workspace_id: ws-eval-1778486319562-371b45dd
    execution_status: completed
    comparison_status: review_only
    runtime_metadata:
      agent_type: opencode
      resolved_model: openai/gpt-5.2
    judgment_verdict: pass
    primary_failure_code: ''
    score: 83
    passed_checks: 2
    total_checks: 3