regent-sdk 0.1.5

LLM regression testing — route your LLM calls through Regent's proxy

Regent SDK

pip install regent-sdk

Usage

import regent
regent.init(api_key="your-regent-api-key")

# All OpenAI/Anthropic clients instantiated after this call
# will automatically route through Regent's proxy.

# Must be called before importing or instantiating OpenAI/Anthropic clients.
from openai import OpenAI
client = OpenAI()  # automatically proxied

Local development

regent.init(api_key="your-regent-api-key", proxy_url="http://localhost:8000")

What gets proxied

Only LLM calls made without an explicit api_key argument are routed through Regent. If you pass your own api_key when constructing a client, the SDK leaves that client untouched — this is intentional so auxiliary clients (e.g. embeddings, sidecar services) are never accidentally rerouted.

OpenAI()                        # proxied — Regent injects base_url + api_key
OpenAI(api_key="sk-...")        # not proxied — your key, your endpoint

Privacy

Regent only proxies traffic from your test runs (GitHub Actions / CI). We do not intercept or touch your production traffic. If REGENT_ENABLED is not set to "true", regent.init() is a no-op and nothing is patched.

---

Publishing to PyPI

# First time setup
pip install hatch twine

# Build
cd sdk/python
hatch build

# Publish (prompts for PyPI credentials)
twine upload dist/*

# For subsequent releases — bump version in pyproject.toml, then:
hatch build
twine upload dist/*