tkenaz/Semantic Diff
AI-powered semantic analysis of git commits. Understand intent, assess risk, get review questions.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| anthropic_api_key | Anthropic API key for Claude | yes | — |
| model | Model to use (claude-sonnet-4-5-20250929 or claude-opus-4-5-20251101) | no | claude-sonnet-4-5-20250929 |
| fail_on_risk | Fail the check if risk level meets or exceeds this (low, medium, high, critical, never) | no | never |
| comment_on_pr | Post analysis as PR comment | no | true |
| base_ref | Base ref for comparison (default: auto-detect from PR) | no | "" |
Outputs
| name | description |
|---|---|
| risk_level | Overall risk level (low, medium, high, critical) |
| analysis_json | Full analysis as JSON |
| report_path | Path to saved markdown report |