ollieb89/AI Root Cause Hints

Explain why your AI pipeline failed — not just that it failed. Correlates signals from eval, RAG, cost, PR quality, and output safety actions.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github-tokenGitHub token for posting PR commentsno${{ github.token }}
eval-failuresNumber of eval failures (from ai-workflow-evals)no
eval-suiteEval suite name/pathno
rag-deletion-pctPercentage of RAG corpus deleted/changedno
rag-pathRAG corpus pathno
cost-spikeCost spike multiplier (e.g. 2.5 = 2.5x normal spend)no
modelLLM model nameno
pr-quality-scorePR quality score 0-100 (from ai-pr-guardian)no
redaction-hitsNumber of redaction hits (from ai-output-redacter)no
redact-modeRedaction mode usedno
risk-levelPR risk level: low | medium | high (from pr-context-enricher)no
complexity-scorePR complexity score (from pr-context-enricher)no
signals-jsonCustom signals as JSON array [{source, type, severity, value?, metadata?}]no
pr-numberPR number for comment postingno
post-commentPost findings as a PR commentnotrue
fail-on-findingsFail the workflow step when findings are detectednofalse
namedescription
hints-countNumber of root cause hints generated
has-findingsWhether any correlated failure patterns were found
top-confidenceConfidence level of top finding: HIGH | MEDIUM | LOW | none
signal-countTotal number of signals analyzed