sync.py

# ─────────────────────────────────────────────────────────────
# 📁 PATH: sync.py  (root HF Space repo)
# Upload/edit file ini di:
#   https://huggingface.co/spaces/mark421/OpenClaw-ai/blob/main/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")

# File backup utama (config, sessions)
FILENAME = "latest_backup.tar.gz"
# File backup browser (chromium binary ~150MB, download sekali saja)
BROWSER_FILENAME = "browser_backup.tar.gz"

def restore():
    try:
        if not repo_id or not token:
            print("Skip Restore: HF_DATASET or HF_TOKEN not set")
            return

        # Restore config & sessions
        print(f"Downloading {FILENAME} from {repo_id}...")
        path = hf_hub_download(
            repo_id=repo_id,
            filename=FILENAME,
            repo_type="dataset",
            token=token
        )
        with tarfile.open(path, "r:gz") as tar:
            tar.extractall(path="/root/.openclaw/")
        print(f"Success: Restored config from {FILENAME}")

    except Exception as e:
        print(f"Restore Note (config): {e}")

    try:
        if not repo_id or not token:
            return

        # Restore browser binary (kalau ada)
        print(f"Downloading {BROWSER_FILENAME} from {repo_id}...")
        browser_path = hf_hub_download(
            repo_id=repo_id,
            filename=BROWSER_FILENAME,
            repo_type="dataset",
            token=token
        )
        with tarfile.open(browser_path, "r:gz") as tar:
            tar.extractall(path="/root/.openclaw/")
        print(f"Success: Restored browser from {BROWSER_FILENAME}")

    except Exception as e:
        print(f"Restore Note (browser): {e} — will install fresh if needed")


def backup():
    """
    Backup strategy: Always backup the entire workspace directory.
    This ensures all agent workspaces (workspace, workspace-jarvis, workspace-writer, etc.)
    and their memory files are included in every backup.
    """
    try:
        if not repo_id or not token:
            print("Skip Backup: HF_DATASET or HF_TOKEN not set")
            return

        # ── Backup: Always include ALL workspaces (required) ──
        with tarfile.open(FILENAME, "w:gz") as tar:
            paths_to_backup = [
                "/root/.openclaw/sessions",
                "/root/.openclaw/agents/main/sessions",
                "/root/.openclaw/agents/jarvis/sessions",
                "/root/.openclaw/agents/writer/sessions",
                "/root/.openclaw/agents/mp-agent/sessions",
                "/root/.openclaw/agents/stocke/sessions",
                "/root/.openclaw/openclaw.json",
                "/root/.openclaw/credentials",
                # ALWAYS backup all workspaces (full workspace requirement)
                "/root/.openclaw/workspace",
                "/root/.openclaw/workspace-jarvis",
                "/root/.openclaw/workspace-writer",
                "/root/.openclaw/workspace-mp-agent",
                "/root/.openclaw/workspace-stock",
                # System skills and plugins
                "/usr/local/lib/node_modules/openclaw/skills",
                "/usr/local/lib/node_modules/openclaw/dist/extensions",
            ]
            for p in paths_to_backup:
                if os.path.exists(p):
                    arcname = p.replace("/root/.openclaw/", "")
                    tar.add(p, arcname=arcname)

        api.upload_file(
            path_or_fileobj=FILENAME,
            path_in_repo=FILENAME,
            repo_id=repo_id,
            repo_type="dataset",
            token=token
        )
        print(f"Backup config {FILENAME} Success.")

        # ── Backup 2: browser binary (besar ~150MB, hanya upload kalau belum ada) ──
        browsers_dir = "/root/.openclaw/browsers"
        if os.path.exists(browsers_dir):
            # Cek apakah browser_backup sudah ada di dataset
            try:
                hf_hub_download(
                    repo_id=repo_id,
                    filename=BROWSER_FILENAME,
                    repo_type="dataset",
                    token=token
                )
                print(f"Browser backup already exists in dataset, skipping upload.")
            except Exception:
                # Belum ada, upload sekarang
                print(f"Uploading browser backup (first time, ~150MB)...")
                with tarfile.open(BROWSER_FILENAME, "w:gz") as tar:
                    tar.add(browsers_dir, arcname="browsers")
                api.upload_file(
                    path_or_fileobj=BROWSER_FILENAME,
                    path_in_repo=BROWSER_FILENAME,
                    repo_id=repo_id,
                    repo_type="dataset",
                    token=token
                )
                print(f"Browser backup uploaded successfully.")

    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()