Benchmark Harness (benchmark/harness.py)

Benchmark harness that runs challenges, manages optional Docker execution, logs results, and aggregates LangGraph agent responses.

# Source: https://github.com/mperkins0155/Decepticon-Cobaltai | License: Apache-2.0 | Copyright You must retain, in the Source form of any Derivative Works
# Provided via justclaw.it.com; keep this notice with the code.
from __future__ import annotations

import asyncio
import json
import logging
import os
import re
import shutil
import subprocess
import time
import uuid
from dataclasses import dataclass
from datetime import datetime, timezone
from pathlib import Path

import httpx
from langgraph_sdk import get_client

from benchmark.config import BenchmarkConfig
from benchmark.providers.base import BaseBenchmarkProvider
from benchmark.schemas import CancelOutcome, Challenge, ChallengeResult
from benchmark.state import BenchmarkRunState, BenchmarkStepResult

log = logging.getLogger(__name_

... (truncated -- full source via MCP)