Metadata-Version: 2.4
Name: judge-kappa
Version: 0.1.0
Summary: Unified LLM evaluation: A/B uplift, Panel/Jury judges, Krippendorff α, Cohen κ, pairwise preference, Elo tournament, and bias detection
Project-URL: Homepage, https://github.com/williamcaban/judge-kappa-eval
Project-URL: Repository, https://github.com/williamcaban/judge-kappa-eval
Project-URL: Documentation, https://github.com/williamcaban/judge-kappa-eval/tree/main/docs
Project-URL: Issues, https://github.com/williamcaban/judge-kappa-eval/issues
Project-URL: Changelog, https://github.com/williamcaban/judge-kappa-eval/blob/main/CHANGELOG.md
Author-email: William Caban <william.caban@gmail.com>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship made available under
              the License, as indicated by a copyright notice that is included in
              or attached to the work (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean, as submitted to the Licensor for inclusion
              in the Work by the copyright owner or by an individual or Legal Entity
              authorized to submit on behalf of the copyright owner. For the purposes
              of this definition, "submit" means any form of electronic, verbal, or
              written communication sent to the Licensor or its representatives,
              including but not limited to communication on electronic mailing lists,
              source code control systems, and issue tracking systems that are managed
              by, or on behalf of, the Licensor for the purpose of discussing and
              improving the Work, but excluding communication that is conspicuously
              marked or designated in writing by the copyright owner as "Not a
              Contribution."
        
              "Contributor" shall mean Licensor and any Legal Entity on behalf of
              whom a Contribution has been received by the Licensor and included
              within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by the combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a cross-claim
              or counterclaim in a lawsuit) alleging that the Work or any
              Contribution embodied within the Work constitutes direct or
              contributory patent infringement, then any patent licenses granted to
              You under this License for that Work shall terminate as of the date
              such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or Derivative
                  Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, You must include a readable copy of the
                  attribution notices contained within such NOTICE file, in
                  at least one of the following places: within a NOTICE text
                  file distributed as part of the Derivative Works; within
                  the Source form or documentation, if provided along with the
                  Derivative Works; or, within a display generated by the
                  Derivative Works, if and wherever such third-party notices
                  normally appear. The contents of the NOTICE file are for
                  informational purposes only and do not modify the License.
        
              (e) You may add Your own attribution notices within Derivative
                  Works that You distribute, alongside or as an addendum to
                  the NOTICE text from the Work, provided that such additional
                  attribution notices cannot be construed as modifying the License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or agreed
              to in writing, Licensor provides the Work (and each Contributor
              provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES
              OR CONDITIONS OF ANY KIND, either express or implied, including,
              without limitation, any warranties or conditions of TITLE,
              NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR
              PURPOSE. You are solely responsible for determining the
              appropriateness of using or reproducing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or exemplary damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (even if such Contributor has been advised of the possibility
              of such damages).
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer, and
              charge a fee for, acceptance of support, warranty, indemnity, or
              other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may offer only
              conditions on Your behalf, and not on behalf of any other Contributor,
              and only if You agree to indemnify, defend, and hold each Contributor
              harmless for any liability incurred by, or claims asserted against,
              such Contributor by reason of your accepting any such warranty or
              additional liability.
        
           END OF TERMS AND CONDITIONS
        
           Copyright 2026 William Caban
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
License-File: LICENSE
Keywords: agent-skills-eval,ai-evaluation,bias-detection,cohen-kappa,elo,evaluation,inter-rater-agreement,judge,krippendorff,llm,llm-evaluation,mlflow,pairwise,positional-bias,rubric,tournament,verbosity-bias
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Topic :: Software Development :: Testing
Classifier: Typing :: Typed
Requires-Python: >=3.12
Requires-Dist: krippendorff>=0.6
Requires-Dist: numpy>=1.26
Requires-Dist: pydantic>=2.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: scikit-learn>=1.5
Requires-Dist: scipy>=1.13
Provides-Extra: all
Requires-Dist: anthropic>=0.28; extra == 'all'
Requires-Dist: openai>=1.30; extra == 'all'
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.28; extra == 'anthropic'
Provides-Extra: openai
Requires-Dist: openai>=1.30; extra == 'openai'
Description-Content-Type: text/markdown

# judge-kappa

Unified LLM evaluation that bridges **agent-skills-eval** (A/B uplift, assertion lists) and **MLflow LLMaJ** (datasets, named rubric dimensions) while adding statistical rigor missing from both.

| Capability | agent-skills-eval | MLflow LLMaJ | judge-kappa |
|---|---|---|---|
| Native A/B uplift | ✅ | ❌ | ✅ |
| Assertion-based scoring | ✅ | ❌ | ✅ |
| Named rubric dimensions | ❌ | ✅ | ✅ |
| Multi-judge Panel / Jury | ❌ | ❌ | ✅ |
| Krippendorff's α | ❌ | ❌ | ✅ |
| Cohen's κ + P(chance) | ❌ | ❌ | ✅ |
| ICL judge alignment | ❌ | ❌ | ✅ |
| Positional bias detection | ❌ | ❌ | ✅ |
| Verbosity bias detection | ❌ | ❌ | ✅ |
| Pairwise preference rates | ❌ | ❌ | ✅ |
| N-system Elo tournament | ❌ | ❌ | ✅ |
| CLI-first | ✅ | ❌ | ✅ |

---

## Installation

```bash
git clone https://github.com/williamcaban/judge-kappa-eval
cd judge-kappa

# Python 3.12+ required
uv sync --all-extras          # recommended
# or: pip install -e '.[all]'
```

```bash
export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."
# For local vLLM/Ollama, set base_url in the config instead of an API key
```

---

## Quick start

```bash
# Validate a config
judge-kappa validate examples/config_skill_minimal.yaml

# Run evaluation
judge-kappa run examples/config_skill_minimal.yaml

# JSON output → file
judge-kappa run examples/config_skill.yaml --format json --output report.json

# Print config JSON Schema (for editor autocomplete)
judge-kappa schema
```

---

## Documentation

| Doc | Contents |
|---|---|
| [Decision guide](docs/01-decision-guide.md) | Which mode to use — decision tree covering input format, judge strategy, bias detection, N systems, and providers |
| [Input types](docs/02-input-types.md) | All six entry points: `evaluate_skill`, `evaluate_dataset`, `evaluate_endpoints`, `evaluate_prerecorded`, `evaluate_pairwise_dataset`, `TournamentEvaluator` |
| [Pairwise and Tournament](docs/03-pairwise-tournament.md) | When and how to use pairwise preference scoring and N-system Elo tournaments; cost tables; champion-challenger pattern |
| [Examples](docs/04-examples.md) | Nine worked examples with configs, expected output, and interpretation guidance |
| [Key management](docs/05-key-management.md) | `api_key_env` three-case rule; provider quick reference; mixed-provider panel; Python API key passing |
| [CLI reference](docs/06-cli-reference.md) | `run`, `validate`, `schema` commands; output formats (`text`, `json`, `jsonl`); `--verdicts` flag; CI validation |
| [Python API](docs/07-python-api.md) | Eight usage patterns with full code; accessing report fields; serialization |
| [Config reference](docs/08-config-reference.md) | Every YAML field documented; skill/dataset/pairwise mode schemas; annotated full example |
| [Architecture](docs/09-architecture.md) | Package structure; ABCs and extension points; adding providers, judges, metrics, and bias detectors |

---

## Example configs

| Config | What it demonstrates |
|---|---|
| `examples/config_skill_minimal.yaml` | Single judge, no bias detection — fastest start |
| `examples/config_skill.yaml` | 3-judge panel + ICL calibration + positional bias |
| `examples/config_dataset.yaml` | Diverse JudgeJury with weighted rubric dimensions |
| `examples/config_dataset_panel.yaml` | Homogeneous panel to verify rubric consistency |
| `examples/config_endpoints.yaml` | Per-variant generation backend (endpoint A vs B) |
| `examples/config_prerecorded.yaml` | Score pre-recorded outputs (no generation calls) |
| `examples/config_pairwise.yaml` | Pairwise preference rates (PairwiseReport) |
| `examples/config_regulatory.yaml` | Full bias evidence for compliance submissions |
| `examples/config_mixed_panel.yaml` | Anthropic + OpenRouter + vLLM + Ollama in one panel |

---

## Development

```bash
uv sync --group dev
uv run pytest                                  # tests
uv run pytest --cov --cov-report=term-missing  # with coverage
uv run ruff check src tests                    # lint
uv run mypy src                                # type check
```

---

## License

Apache 2.0 — [github.com/williamcaban/judge-kappa-eval](https://github.com/williamcaban/judge-kappa-eval)
