Metadata-Version: 2.4
Name: alignmenter
Version: 0.0.12
Summary: Persona-aligned evaluation toolkit for auditing conversational AI authenticity, safety, and stability.
Author: Alignmenter
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, whether in Source or
              Object form, 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 any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to 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, "submitted"
              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 otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated 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 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 a Contribution incorporated 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, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, 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. 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.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this 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.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           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 redistributing 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 consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Support. 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 act only
              on Your own behalf and on Your sole responsibility, 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
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright 2024 Alignmenter Contributors
        
           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.
        
Project-URL: Homepage, https://alignmenter.com
Project-URL: Repository, https://github.com/justinGrosvenor/alignmenter
Project-URL: Documentation, https://github.com/justinGrosvenor/alignmenter
Project-URL: Bug Tracker, https://github.com/justinGrosvenor/alignmenter/issues
Keywords: llm,evaluation,alignment,persona,safety
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: typer[all]
Requires-Dist: pydantic
Requires-Dist: pydantic-settings>=2.0
Requires-Dist: openai>=1.12.0
Requires-Dist: anthropic>=0.18.0
Requires-Dist: scikit-learn>=1.3.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: sentence-transformers>=2.2.2
Requires-Dist: torch
Requires-Dist: tiktoken>=0.7.0
Requires-Dist: requests>=2.32.0
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Requires-Dist: build; extra == "dev"
Requires-Dist: twine; extra == "dev"
Provides-Extra: safety
Requires-Dist: transformers>=4.30.0; extra == "safety"
Dynamic: license-file

<p align="center">
  <img src="https://alignmenter-branding.s3.us-west-2.amazonaws.com/alignmenter-banner.png" alt="Alignmenter" width="800">
</p>

<p align="center">
  <strong>Persona-aligned evaluation for conversational AI</strong>
</p>

<p align="center">
  <a href="#quickstart">Quickstart</a> •
  <a href="#features">Features</a> •
  <a href="#architecture">Architecture</a> •
  <a href="#documentation">Documentation</a> •
  <a href="#license">License</a>
</p>

---

## Overview

**Alignmenter** is a lightweight, production-ready evaluation toolkit for auditing conversational AI systems across three core dimensions:

- **🎨 Authenticity**: Does the assistant stay on-brand?
- **🛡️ Safety**: Does it avoid harmful or policy-violating outputs?
- **⚖️ Stability**: Are responses consistent across sessions?

Unlike generic LLM evaluation frameworks, Alignmenter is purpose-built for **persona alignment**—ensuring your AI assistant speaks with your unique voice while staying safe and stable.

## Quickstart

### Installation

```bash
# Clone the repository
git clone https://github.com/yourusername/alignmenter.git
cd alignmenter

# Create virtual environment
python -m venv env
source env/bin/activate  # On Windows: env\Scripts\activate

# Install with dev dependencies
pip install -e .[dev]

# Optional: Install with offline safety classifier
pip install -e .[dev,safety]
```

### Install from PyPI

```bash
pip install alignmenter
alignmenter init
alignmenter run --config configs/run.yaml --no-generate
```

> **Note**: The `safety` extra includes `transformers` for the offline safety classifier (ProtectAI/distilled-safety-roberta). Without it, Alignmenter falls back to a lightweight heuristic classifier. See [docs/offline_safety.md](https://github.com/justinGrosvenor/alignmenter/blob/main/docs/offline_safety.md) for details.

### Run Your First Evaluation

```bash
# Set API key (for embedding and judge models)
export OPENAI_API_KEY="your-key-here"

# Run evaluation on demo dataset (regenerates transcripts via the provider)
alignmenter run \
  --model openai:gpt-4o-mini \
  --dataset datasets/demo_conversations.jsonl \
  --persona configs/persona/default.yaml

# Reuse existing transcripts without hitting the provider
alignmenter run --config configs/run.yaml --no-generate

# View interactive HTML report
alignmenter report --last

# Sanitize a dataset in-place or to a new file
alignmenter dataset sanitize datasets/demo_conversations.jsonl --out datasets/demo_sanitized.jsonl
```

**Output:**
```
Loading dataset: 60 turns across 10 sessions
✓ Brand voice score: 0.82 (range: 0.78-0.86)
✓ Safety score: 0.97
✓ Consistency score: 0.94
Report written to: reports/demo/2025-11-03T00-14-01_alignmenter_run/index.html
```

## Features

### 🎯 Three-Dimensional Scoring

#### Authenticity
- **Embedding similarity**: Measures semantic alignment with persona examples
- **Trait model**: Logistic regression on linguistic features (trained via calibration)
- **Lexicon matching**: Enforces preferred/avoided vocabulary
- **Bootstrap CI**: Statistical confidence intervals for reliability

#### Safety
- **Keyword classifier**: Fast pattern matching for common violations
- **LLM judge**: GPT-4 as a safety oracle with budget controls
- **Offline classifier**: ProtectAI's distilled-safety-roberta (no API calls)
- **Fused scoring**: Weighted ensemble of rule-based + model-based signals
- **Adversarial testing**: Built-in safety traps in demo datasets

#### Stability
- **Cosine variance**: Detects semantic drift across conversation turns
- **Session clustering**: Identifies divergent response patterns
- **Temporal analysis**: Tracks consistency over time

### 📊 Rich Reporting

- **Interactive HTML**: Grade-based report cards with charts (Chart.js)
- **JSON export**: Machine-readable results for CI/CD pipelines
- **CSV downloads**: Per-metric exports for spreadsheet analysis
- **Turn-level explorer**: Drill down into individual responses

### 🔧 Production-Ready

- **Multi-provider support**: OpenAI, Anthropic, local (vLLM, Ollama)
- **Budget guardrails**: Halt runs at 90% of judge API budget
- **Cost projection**: Estimate expenses before execution
- **Reproducibility**: Logs Python version, model, seed, timestamps
- **PII sanitization**: Built-in scrubbing for production data

### 🚀 Developer Experience

- **CLI-first**: Simple commands for evaluation, calibration, reporting
- **YAML configuration**: Declarative persona packs and run configs
- **Python API**: Programmatic access for custom workflows
- **Comprehensive tests**: 69+ unit tests with pytest
- **Type safety**: Full type hints throughout

## Architecture

```
┌─────────────────────────────────────────────────────────────────┐
│                        Alignmenter CLI                          │
│  alignmenter run / report / calibrate / bootstrap / sanitize    │
└─────────────────────────────────────────────────────────────────┘
                               │
                               ▼
┌─────────────────────────────────────────────────────────────────┐
│                          Runner                                 │
│  Orchestrates evaluation: load data → score → report            │
└─────────────────────────────────────────────────────────────────┘
                               │
           ┌───────────────────┼───────────────────┐
           ▼                   ▼                   ▼
   ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
   │ Authenticity │    │    Safety    │    │  Stability   │
   │    Scorer    │    │    Scorer    │    │    Scorer    │
   └──────────────┘    └──────────────┘    └──────────────┘
           │                   │                   │
           │                   │                   │
   ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
   │  Embeddings  │    │  LLM Judge   │    │   Cosine     │
   │  Trait Model │    │  Keywords    │    │  Variance    │
   │   Lexicon    │    │  Fusion      │    │  Clustering  │
   └──────────────┘    └──────────────┘    └──────────────┘
                               │
                               ▼
           ┌───────────────────────────────────────┐
           │         Reporting Layer               │
           │  HTML / JSON / CSV / Interactive UI   │
           └───────────────────────────────────────┘
```

### Key Components

| Component | Purpose | Key Files |
|-----------|---------|-----------|
| **CLI** | Command-line interface | `src/alignmenter/cli.py` |
| **Runner** | Orchestration engine | `src/alignmenter/runner.py` |
| **Scorers** | Metric computation | `src/alignmenter/scorers/` |
| **Providers** | LLM/embedding backends | `src/alignmenter/providers/` |
| **Reporters** | Output generation | `src/alignmenter/reporting/` |
| **Datasets** | JSONL conversation data | `datasets/` |
| **Personas** | Brand voice definitions | `configs/persona/` |

## Documentation

- **[Persona Annotation Guide](https://github.com/justinGrosvenor/alignmenter/blob/main/docs/persona_annotation.md)**: How to label data and calibrate trait models
- **[Offline Safety Classifier](https://github.com/justinGrosvenor/alignmenter/blob/main/docs/offline_safety.md)**: Using distilled-safety-roberta without API calls
- **[Datasets README](https://github.com/justinGrosvenor/alignmenter/blob/main/alignmenter/datasets/README.md)**: Data provenance, licensing, and anonymization
- **[Requirements](https://github.com/justinGrosvenor/alignmenter/blob/main/docs/alignmenter_requirements.md)**: Full product specification

## Usage Examples

### Evaluate Multiple Models

```bash
# Compare GPT-4 vs Claude
alignmenter run \
  --model openai:gpt-4 \
  --compare anthropic:claude-3-5-sonnet-20241022 \
  --dataset datasets/demo_conversations.jsonl \
  --persona configs/persona/default.yaml
```

### Custom Judge and Embeddings

```bash
# Use Claude as safety judge, local embeddings
alignmenter run \
  --model openai:gpt-4o-mini \
  --judge anthropic:claude-3-5-sonnet-20241022 \
  --embedding sentence-transformer:all-MiniLM-L6-v2 \
  --dataset datasets/demo_conversations.jsonl \
  --persona configs/persona/default.yaml
```

### Bootstrap Synthetic Dataset

```bash
# Generate 50 conversations with adversarial traps
alignmenter bootstrap-dataset \
  --out datasets/my_test.jsonl \
  --sessions 50 \
  --safety-trap-ratio 0.15 \
  --brand-trap-ratio 0.20 \
  --seed 42
```

### Calibrate Persona Traits

```bash
# Train trait model from labeled data
alignmenter calibrate-persona \
  --persona-path configs/persona/mybot.yaml \
  --dataset annotations.jsonl \
  --out configs/persona/mybot.traits.json \
  --epochs 300
```

### Sanitize Production Data

```bash
# Remove PII before evaluation
alignmenter sanitize-dataset \
  --input prod_logs.jsonl \
  --out datasets/sanitized.jsonl \
  --hash-session-ids \
  --scrub-patterns "email|phone|ssn"
```

## Persona Configuration

Define your brand voice in YAML:

```yaml
# configs/persona/mybot.yaml
id: mybot
name: "MyBot Assistant"
description: "Professional, evidence-driven, technical"

voice:
  tone: ["professional", "precise", "measured"]
  formality: "business_casual"

  # Preferred vocabulary
  lexicon:
    preferred:
      - "baseline"
      - "signal"
      - "alignment"
      - "evidence-based"
    avoided:
      - "lol"
      - "bro"
      - "hype"
      - "vibes"

# Example on-brand responses (for embedding similarity)
examples:
  - "Our baseline analysis indicates a 15% improvement in alignment metrics."
  - "The signal-to-noise ratio suggests this approach is viable."
  - "Let's establish a clear baseline before proceeding."

# Trait model weights (generated by calibration)
traits:
  weights: [0.12, -0.34, 0.08, ...]  # Learned from annotations
  vocabulary: ["baseline", "signal", ...]
```

## API Usage

```python
from alignmenter.runner import Runner
from alignmenter.config import RunConfig

# Load configuration
config = RunConfig.from_yaml("configs/run/my_eval.yaml")

# Execute evaluation
runner = Runner(config)
results = runner.execute()

# Access scores
print(f"Authenticity: {results['scores']['authenticity']['mean']:.3f}")
print(f"Safety: {results['scores']['safety']['fused_judge']:.3f}")
print(f"Stability: {results['scores']['stability']['session_variance']:.3f}")

# Generate reports
from alignmenter.reporting import HTMLReporter, JSONReporter

html_reporter = HTMLReporter()
html_reporter.write(
    run_dir=results["run_dir"],
    summary=results["summary"],
    scores=results["scores"],
    sessions=results["sessions"],
)
```

## CI/CD Integration

```yaml
# .github/workflows/eval.yml
name: Persona Evaluation

on: [push, pull_request]

jobs:
  evaluate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: actions/setup-python@v4
        with:
          python-version: '3.11'

      - name: Install Alignmenter
        run: pip install alignmenter

      - name: Run Evaluation
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        run: |
          alignmenter run \
            --model openai:gpt-4o-mini \
            --dataset datasets/ci_test.jsonl \
            --persona configs/persona/default.yaml \
            --judge-budget 100

      - name: Upload Report
        uses: actions/upload-artifact@v3
        with:
          name: evaluation-report
          path: reports/
```

## Development

### Running Tests

```bash
# All tests
pytest

# With coverage
pytest --cov=src/alignmenter --cov-report=html

# Specific test file
pytest tests/test_scorers.py -v
```

### Code Quality

```bash
# Type checking
mypy src/

# Linting
ruff check src/

# Formatting
black src/ tests/
```

### Local Development

```bash
# Install in editable mode with dev dependencies
pip install -e .[dev]

# Run from source
python -m alignmenter.cli run --help

# Generate report from last run
make report-last
```

## Roadmap

- [ ] Web dashboard for team collaboration
- [ ] Hosted evaluation pipelines (CI/CD SaaS)
- [ ] Multi-language support (non-English personas)
- [ ] Offline safety model (no API required)
- [ ] Cost/latency tracking in scorers
- [ ] Competitive landscape analysis
- [ ] Metric cards and ablation studies

## Contributing

We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.

**Areas we'd love help with:**
- Additional persona packs (different brand voices)
- Language support beyond English
- Integration with other LLM providers
- Performance optimizations for large datasets

## License

Apache License 2.0 - see [LICENSE](LICENSE) for details.

## Citation

If you use Alignmenter in research, please cite:

```bibtex
@software{alignmenter2024,
  title={Alignmenter: A Framework for Persona-Aligned Conversational AI Evaluation},
  author={Alignmenter Contributors},
  year={2024},
  url={https://github.com/yourusername/alignmenter}
}
```

## Support

- **Documentation**: [docs/](https://github.com/justinGrosvenor/alignmenter/tree/main/docs)
- **Issues**: [GitHub Issues](https://github.com/justinGrosvenor/alignmenter/issues)
- **Discussions**: [GitHub Discussions](https://github.com/justinGrosvenor/alignmenter/discussions)

---

<p align="center">
  Made with ❤️ by the Alignmenter team
</p>
