Metadata-Version: 2.4
Name: flowharness-evaluation
Version: 0.1.0
Summary: Evaluation context (FLOWHARNESS_SPEC.md §6.6) — eval suites, golden-set corpus, signed eval runs, the gate service
License-Expression: Apache-2.0
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: flowharness-core==0.1.0
Requires-Dist: sqlalchemy>=2.0
Requires-Dist: alembic>=1.13
Requires-Python: >=3.12
Project-URL: Homepage, https://github.com/flowharness-ai
Description-Content-Type: text/markdown

# flowharness-evaluation

Evaluation bounded context — owns eval suites, golden-set corpus, signed eval runs, gate policies, and the gate service (verdict + scoring logic). Provides the domain layer for evaluating AI surfaces against a committed test suite, applying gate policies, and producing signed evaluation reports.

This is an **internal library package** of the FlowHarness toolchain, published to PyPI as a transitive dependency of [`flowharness`](https://github.com/flowharness-ai) (the scan CLI) and [`flowharness-ci-runner`](https://github.com/flowharness-ai). Install those packages instead of depending on `flowharness-evaluation` directly.

> **Note:** this package currently installs a top-level module named `evaluation`. Prefer `uvx` (isolated environments) over `pip install` into a shared venv until the 0.2 module-namespace rename lands.

**License:** Apache-2.0  
**Homepage:** https://github.com/flowharness-ai
