sync.py

import os
import sys
import tarfile
from huggingface_hub import HfApi, hf_hub_download

api = HfApi()
repo_id = os.getenv("HF_DATASET")
token = os.getenv("HF_TOKEN")
FILENAME = "openclaw_space.tar.gz"
BACKUP_ROOT = "/root/.openclaw"

def restore():
    try:
        if not repo_id or not token:
            print("Skip Restore: HF_DATASET or HF_TOKEN not set")
            return
            
        print(f"Downloading {FILENAME} from {repo_id} (Forcing cloud sync)...")
        
        # ================= 核心修复：强制穿透缓存与禁用软链接 =================
        path = hf_hub_download(
            repo_id=repo_id, 
            filename=FILENAME, 
            repo_type="dataset", 
            token=token,
            force_download=True,          # 强制去云端拉取最新鲜的数据，无视本地旧缓存
            local_dir_use_symlinks=False  # 禁用软链接，防止后续文件读写权限冲突
        )
        # ======================================================================
        
        os.makedirs(BACKUP_ROOT, exist_ok=True)
        with tarfile.open(path, "r:gz") as tar:
            tar.extractall(path=BACKUP_ROOT)
        print(f"Success: Restored from {FILENAME}")
        return True
    except Exception as e:
        # 如果是第一次运行，仓库里没文件，报错是正常的
        print(f"Restore Note: No existing backup found or error: {e}")

def backup():
    try:
        if not repo_id or not token:
            print("Skip Backup: HF_DATASET or HF_TOKEN not set")
            return
            
        temp_tar_path = f"/tmp/{FILENAME}"
        with tarfile.open(temp_tar_path, "w:gz") as tar:
            # 打包整个 .openclaw 文件夹
            if os.path.exists(BACKUP_ROOT):
                # arcname="" 确保解压后直接是文件夹内容，不会多一层目录
                tar.add(BACKUP_ROOT, arcname=".")
            else:
                print(f"Warning: {BACKUP_ROOT} does not exist")
                return
                
        print("Uploading to Hugging Face...")
        # 上传并覆盖
        api.upload_file(
            path_or_fileobj=temp_tar_path,
            path_in_repo=FILENAME,
            repo_id=repo_id,
            repo_type="dataset",
            token=token
        )
        print(f"Backup {FILENAME} Success (Overwritten in Git History).")
        
        # 清理临时文件
        os.remove(temp_tar_path)
    except Exception as e:
        print(f"Backup Error: {e}")

if __name__ == "__main__":
    if len(sys.argv) > 1 and sys.argv[1] == "backup":
        backup()
    else:
        restore()