4b6817381b
CI (OpenClaw E2E) / openclaw test (push) Has been cancelled
CI / coverage-report (push) Has been cancelled
CI / test-kubernetes (push) Has been cancelled
CI / should-run-thorough (push) Has been cancelled
CI / test-thorough (cloudwatch-demo) (push) Has been cancelled
CI / test-thorough (flink-ecs) (push) Has been cancelled
CI / test-thorough (upstream-lambda) (push) Has been cancelled
CI / test-thorough (prefect-ecs-fargate) (push) Has been cancelled
Release / build-binaries (zip, opensre.exe, onefile, windows-latest, windows-x64) (push) Has been cancelled
Benchmark image — build + push to ECR (any adapter) / build + push (push) Has been cancelled
CI / quality (ubuntu-latest) (push) Has been cancelled
CI / test (tools-runtime) (push) Has been cancelled
CI / test (e2e-general) (push) Has been cancelled
CI / test (cli-runtime) (push) Has been cancelled
CI / test (e2e-provider-and-openclaw) (push) Has been cancelled
CI / test (integrations-and-misc) (push) Has been cancelled
Release / verify (push) Has been cancelled
Release / build-python-dist (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, macos-15-intel, darwin-x64) (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, macos-latest, darwin-arm64) (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04, linux-x64) (push) Has been cancelled
Release / publish-release (push) Has been cancelled
Release / publish-main-release (push) Has been cancelled
Interactive Shell Live (PR + post-merge) / turn-checks (no-LLM) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
Interactive Shell Live (PR + post-merge) / turn-live shard ${{ matrix.shard_index }} (push) Has been cancelled
Release / prepare (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04-arm, linux-arm64) (push) Has been cancelled
Synthetic Deterministic Tests / Synthetic offline (deterministic) (push) Has been cancelled
122 lines
3.7 KiB
JSON
122 lines
3.7 KiB
JSON
{
|
|
"category": "unknown",
|
|
"correlation": {
|
|
"correlated_signals": [],
|
|
"most_likely_causal_drivers": []
|
|
},
|
|
"evidence": {
|
|
"available_coverage": 0.0,
|
|
"missing_required_sources": [
|
|
"aws_performance_insights"
|
|
],
|
|
"observed_sources": [],
|
|
"required_coverage": 0.0,
|
|
"required_sources": [
|
|
"aws_performance_insights"
|
|
],
|
|
"source_presence": {
|
|
"aws_cloudwatch_metrics": false,
|
|
"aws_performance_insights": false,
|
|
"aws_rds_events": false
|
|
}
|
|
},
|
|
"failure_reasons": [
|
|
{
|
|
"code": "NO_ROOT_CAUSE",
|
|
"detail": "no root cause in output"
|
|
},
|
|
{
|
|
"code": "MISSING_REQUIRED_KEYWORD",
|
|
"detail": "missing required keywords: ['CPU', 'storage', 'analytics', 'audit_log']"
|
|
},
|
|
{
|
|
"code": "MISSING_REQUIRED_EVIDENCE_SOURCE",
|
|
"detail": "required evidence not gathered: ['aws_performance_insights']"
|
|
}
|
|
],
|
|
"gates": {
|
|
"category_match": {
|
|
"actual": "root_cause_present=False, actual_category='unknown'",
|
|
"status": "fail",
|
|
"threshold": "actual_category in ['dual_resource_exhaustion']"
|
|
},
|
|
"exact_keyword_match": {
|
|
"actual": "missing_exact=['CPU', 'storage', 'analytics', 'audit_log']",
|
|
"status": "fail",
|
|
"threshold": "all required keywords matched verbatim"
|
|
},
|
|
"failover_event_reasoning": {
|
|
"actual": "not_applicable",
|
|
"status": "pass",
|
|
"threshold": "not required unless failover sequence keywords are in answer key"
|
|
},
|
|
"forbidden_category_clear": {
|
|
"actual": "actual_category='unknown', forbidden=['connection_exhaustion']",
|
|
"status": "pass",
|
|
"threshold": "actual_category not in forbidden_categories"
|
|
},
|
|
"forbidden_keyword_clear": {
|
|
"actual": "forbidden_hits=[]",
|
|
"status": "pass",
|
|
"threshold": "no forbidden keywords appear in graded output text"
|
|
},
|
|
"required_evidence_sources": {
|
|
"actual": "missing_required_evidence=['aws_performance_insights']",
|
|
"status": "fail",
|
|
"threshold": "all required evidence sources populated"
|
|
},
|
|
"required_keyword_match": {
|
|
"actual": "missing_semantic=['CPU', 'storage', 'analytics', 'audit_log'], missing_exact=['CPU', 'storage', 'analytics', 'audit_log']",
|
|
"status": "fail",
|
|
"threshold": "all required keywords matched (semantic)"
|
|
},
|
|
"semantic_keyword_match": {
|
|
"actual": "missing_semantic=['CPU', 'storage', 'analytics', 'audit_log']",
|
|
"status": "fail",
|
|
"threshold": "all required keywords matched semantically"
|
|
},
|
|
"trajectory_budget": {
|
|
"actual": "extra_actions_count=0",
|
|
"status": "pass",
|
|
"threshold": "extra_actions_count == 0"
|
|
},
|
|
"trajectory_policy": {
|
|
"actual": "not_applicable",
|
|
"status": "pass",
|
|
"threshold": "not_applicable \u2014 no golden trajectory configured"
|
|
}
|
|
},
|
|
"report_schema_version": "report_v2",
|
|
"scoring_formula_version": "v2_gated_semantic",
|
|
"status": "fail",
|
|
"trajectory": {
|
|
"actual": [],
|
|
"coverage": 0.0,
|
|
"edit_distance": 5,
|
|
"extra_actions": [],
|
|
"failed_action_count": 0,
|
|
"golden": [
|
|
"query_grafana_metrics",
|
|
"query_grafana_logs",
|
|
"query_grafana_alert_rules",
|
|
"describe_rds_instance",
|
|
"describe_rds_events"
|
|
],
|
|
"lcs_ratio": 0.0,
|
|
"missing_actions": [
|
|
"query_grafana_metrics",
|
|
"query_grafana_logs",
|
|
"query_grafana_alert_rules",
|
|
"describe_rds_instance",
|
|
"describe_rds_events"
|
|
],
|
|
"policy": null,
|
|
"redundancy_count": 0,
|
|
"strict_match": false
|
|
},
|
|
"verdict_definitions": {
|
|
"sequencing_ok": "Sequencing checks expected action coverage only; order is ignored due to parallelism.",
|
|
"strict_match": "Strict trajectory match requires exact action order and membership equality."
|
|
}
|
|
}
|