Metadata-Version: 2.5
Name: proofstep-cli
Version: 0.1.0
Summary: Proofstep command-line interface — run suites, gate CI, compare experiments
Project-URL: Homepage, https://github.com/IlaKhan17/proofstep
Project-URL: Documentation, https://github.com/IlaKhan17/proofstep/tree/main/docs
Project-URL: Repository, https://github.com/IlaKhan17/proofstep
Project-URL: Issues, https://github.com/IlaKhan17/proofstep/issues
License-Expression: Apache-2.0
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Topic :: Software Development :: Testing
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: httpx>=0.27
Requires-Dist: proofstep
Requires-Dist: proofstep-core
Requires-Dist: proofstep-trajectory
Requires-Dist: proofstep-types
Requires-Dist: pyyaml>=6.0
Requires-Dist: rich>=13.9
Requires-Dist: typer>=0.15
Description-Content-Type: text/markdown

# proofstep-cli

**The `proofstep` command** — part of [Proofstep](https://github.com/IlaKhan17/proofstep), the CI gate for AI
agents that knows the difference between a regression and a bad day.

Run an evaluation suite, apply its gates, and exit non-zero when a protected metric regresses.

```bash
proofstep eval evals/suites/reply-intent.yaml
echo $?   # 0 merge · 1 a blocking gate failed · 2 execution error · 3 the suite is wrong
```

The exit code is the contract. Everything else — the terminal table, the JSON report, the
pull-request comment — exists to explain it.

Gates can be statistically honest rather than just thresholded:

```yaml
gates:
  intent_accuracy:
    max_regression: 0.02
    significance: 0.05      # only fail if the drop is distinguishable from noise
    require_power: true     # and ERROR if this run could never have detected it
```

## Documentation

Full documentation lives in the [repository](https://github.com/IlaKhan17/proofstep/tree/main/docs).

Apache-2.0.
