runlit-dev/runlit eval
Evaluate AI-generated code for hallucinated APIs, intent drift, security issues, and compliance violations
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| api-key | runlit API key (store in GitHub Secrets as RUNLIT_API_KEY) | yes | — |
| block-threshold | Score below which the action fails the check (0-100) | no | 50 |
| warn-threshold | Score below which a warning annotation is posted (0-100) | no | 70 |
| api-url | runlit API base URL (override for self-hosted) | no | https://api.runlit.dev |
Outputs
| name | description |
|---|---|
| score | Composite eval score (0-100) |
| grade | PASS, WARN, or BLOCK |
| eval-id | UUIDv7 eval identifier for audit trail |