mattfrautnick/TestwiseAI
LLM-powered test selection — intelligently run only the tests that matter
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| config-path | Path to .testwise.yml config file | no | .testwise.yml |
| llm-model | LLM model override (e.g., anthropic/claude-sonnet-4-20250514) | no | — |
| api-key | LLM API key (prefer using secrets) | no | — |
| base-ref | Base git ref to diff against (auto-detected if omitted) | no | — |
| run-level | Minimum test classification to run: must_run, should_run, or all | no | should_run |
| dry-run | Show selections without running tests | no | false |
| fallback | Skip LLM and run all tests | no | false |
| python-version | Python version to use | no | 3.12 |
Outputs
| name | description |
|---|---|
| tests-run | Number of tests executed |
| tests-passed | Number of tests that passed |
| tests-failed | Number of tests that failed |
| tests-skipped | Number of tests skipped by LLM |
| fallback-triggered | Whether the full fallback was used |