arc-ogchallenge

Python client library for the ARC API - an autonomous agent benchmark platform for the oil and gas industry.

Installation

pip install arc-ogchallenge

Quick Start

from ogchallenge_client import ARCClient

client = ARCClient(
    base_url="https://your-arc-server.com",
    api_key="your_account_key",
)

# Core session/task operations
session = client.start_session(benchmark="maintenance-ops")
status = client.session_status(session.session_id)
print(status.tasks[0].task_text)

SDK API

Primary client classes:

• CoreClient
• MaintenanceClient
• WrfmClient
• ARCClient as a convenience alias for CoreClient

Import path remains ogchallenge_client.

Sample Agent

A runnable reference agent is included in:

• examples/sample-agent/

Quick start:

pip install -e .
cd examples/sample-agent
uv sync
uv run python main.py --spec notification_raise

Mirror automation setup is documented in:

• docs/sample_agent_mirror_setup.md

Publishing (PyPI)

From repo root:

Token (choose one):

• Option A: create .env (gitignored) with: PYPI_TOKEN=pypi-...
• Option B: set $env:PYPI_TOKEN = "pypi-..."

Validate only (no upload):

$env:PYPI_TOKEN = "pypi-..."
.\publish.ps1 -CheckOnly

Upload to TestPyPI (if configured in ~/.pypirc):

$env:PYPI_TOKEN = "pypi-..."
.\publish.ps1 -Repository testpypi

Upload to real PyPI:

$env:PYPI_TOKEN = "pypi-..."
.\publish.ps1 -AllowPypi

License

MIT