tkenaz/Semantic Diff

AI-powered semantic analysis of git commits. Understand intent, assess risk, get review questions.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
anthropic_api_keyAnthropic API key for Claudeyes
modelModel to use (claude-sonnet-4-5-20250929 or claude-opus-4-5-20251101)noclaude-sonnet-4-5-20250929
fail_on_riskFail the check if risk level meets or exceeds this (low, medium, high, critical, never)nonever
comment_on_prPost analysis as PR commentnotrue
base_refBase ref for comparison (default: auto-detect from PR)no""
namedescription
risk_levelOverall risk level (low, medium, high, critical)
analysis_jsonFull analysis as JSON
report_pathPath to saved markdown report