贡献指南

browseruse_bench/
└── agents/
    └── your_agent.py
config/
└── agents/
    └── your-agent/
        ├── config.yaml
        └── config.yaml.example  # 可选示例配置

from __future__ import annotations

import logging
from pathlib import Path
from typing import Any, Dict

from browseruse_bench.agents.base import BaseAgent
from browseruse_bench.agents.registry import register_agent

logger = logging.getLogger(__name__)


@register_agent
class YourAgent(BaseAgent):
    name = "your-agent"

    def run_task(
        self,
        task_info: Dict[str, Any],
        agent_config: Dict[str, Any],
        task_workspace: Path,
    ) -> Dict[str, Any]:
        task_id = task_info.get("task_id", "unknown")
        logger.info("Running task %s", task_id)
        return {
            "task_id": task_id,
            "status": "success",
            "answer": "",
            "metrics": {"steps": 0},
        }

from browseruse_bench.agents import your_agent  # noqa: F401

agents:
  your-agent:
    path: browseruse_bench/agents
    entrypoint: scripts/agent_runner.py
    config: configs/agents/your-agent/config.yaml
    supported_benchmarks:
      - Online-Mind2Web
    venv: .venv

# 使用 ruff 格式化
ruff format .

# 检查代码风格
ruff check .

# 使用 mypy 进行类型检查
mypy browseruse_bench

# 运行所有测试
pytest tests/

# 运行特定测试
pytest tests/test_eval.py -v

feat: add WebArena benchmark support
fix: resolve timeout issue in browser-use agent
docs: update quickstart guide