Metadata-Version: 2.4
Name: tutorbot-safety-agent
Version: 0.1.2
Summary: Safety Agent for evaluating TutorBot AI responses
Author: TutorBot Team
License: MIT
Project-URL: Homepage, https://github.com/your-org/TutorBotAgent
Project-URL: Repository, https://github.com/your-org/TutorBotAgent
Project-URL: Documentation, https://github.com/your-org/TutorBotAgent/tree/main/TutorBot_Safety_Agent
Keywords: safety,education,tutorbot,content-moderation,ai
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Education
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: pydantic<3.0,>=2.6
Requires-Dist: pyyaml<7.0,>=6.0

# TutorBot Safety Agent

A deterministic, non-autonomous Safety Agent used to evaluate AI-generated
responses before they are shown to students.

## Purpose

The Safety Agent provides a single, enforceable decision point for:
- Allowing safe responses
- Rewriting risky responses
- Blocking unsafe responses

This package is framework-agnostic and can be reused or extracted into
a standalone service in the future.

## Public API

```python
from tutorbot_safety_agent import (
    SafetyAgent,
    DummySafetyAgent,
    SafetyDecision,
    DecisionType,
)
