HuggingClaw-User-Deployment / scripts /verify-hf-dataset.sh
Claude Code
Claude Code: Review and verify Cain's HuggingFace dataset persistence configuration.
3be6dbc
Raw
History Blame Contribute Delete
2.7 kB
#!/bin/bash
# HF Dataset Persistence Verification Script for Cain
# This script checks if the required environment variables are set correctly
set -e
echo "======================================"
echo "HF Dataset Persistence Verification"
echo "======================================"
echo ""
# Check HF_TOKEN
if [ -z "$HF_TOKEN" ]; then
echo "❌ CRITICAL: HF_TOKEN is NOT set"
echo " Data persistence will NOT work!"
echo " Please add HF_TOKEN to your Space's Secrets"
else
echo "βœ… HF_TOKEN is set"
fi
echo ""
# Check AUTO_CREATE_DATASET
if [ "$AUTO_CREATE_DATASET" = "true" ] || [ "$AUTO_CREATE_DATASET" = "1" ]; then
echo "βœ… AUTO_CREATE_DATASET is enabled"
else
echo "⚠️ AUTO_CREATE_DATASET is NOT set to true"
echo " Dataset will NOT be auto-created if missing"
echo " Current value: $AUTO_CREATE_DATASET"
fi
echo ""
# Check SPACE_ID and derived dataset
if [ -n "$SPACE_ID" ]; then
echo "βœ… SPACE_ID: $SPACE_ID"
DERIVED_DATASET="${SPACE_ID}-data"
echo " β†’ Derived dataset: $DERIVED_DATASET"
else
echo "⚠️ SPACE_ID is not set (expected in HF Spaces)"
fi
echo ""
# Check for explicit OPENCLAW_DATASET_REPO override
if [ -n "$OPENCLAW_DATASET_REPO" ]; then
echo "ℹ️ OPENCLAW_DATASET_REPO (override): $OPENCLAW_DATASET_REPO"
else
echo "ℹ️ Using auto-derived dataset ID from SPACE_ID"
fi
echo ""
# Check sync script exists and is executable
SYNC_SCRIPT="/home/node/scripts/sync_hf.py"
if [ -f "$SYNC_SCRIPT" ]; then
echo "βœ… Sync script exists: $SYNC_SCRIPT"
if [ -x "$SYNC_SCRIPT" ]; then
echo " Script is executable"
else
echo " ⚠️ Script is NOT executable (chmod +x needed)"
fi
else
echo "❌ Sync script NOT found: $SYNC_SCRIPT"
fi
echo ""
# Check openclaw.json config
CONFIG_FILE="/home/node/.openclaw/openclaw.json"
if [ -f "$CONFIG_FILE" ]; then
echo "βœ… OpenClaw config exists: $CONFIG_FILE"
echo " Content preview:"
head -n 20 "$CONFIG_FILE" | sed 's/^/ /'
else
echo "⚠️ OpenClaw config NOT found (will be created on first run)"
fi
echo ""
echo "======================================"
echo "Summary"
echo "======================================"
echo ""
echo "Required for persistence:"
echo " 1. HF_TOKEN - Hugging Face access token"
echo " β†’ Create at: https://huggingface.co/settings/tokens"
echo " β†’ Add to Space: Settings β†’ Secrets (new)"
echo ""
echo " 2. AUTO_CREATE_DATASET=true (optional)"
echo " β†’ Auto-create dataset if it doesn't exist"
echo " β†’ Add to Space: Settings β†’ Environment Variables"
echo ""
echo "The dataset will be named: ${SPACE_ID:-<SPACE_ID>}-data"
echo ""