Dockerfile

FROM node:22-slim

# 1. Install system dependencies, python, and browser requirements
RUN apt-get update && apt-get install -y \
    git \
    curl \
    zip \
    unzip \
    tar \
    xz-utils \
    bzip2 \
    python3 \
    python3-pip \
    libglib2.0-0 \
    libnss3 \
    libnspr4 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcups2 \
    libdrm2 \
    libxkbcommon0 \
    libxcomposite1 \
    libxdamage1 \
    libxrandr2 \
    libgbm1 \
    libgtk-3-0 \
    libasound2 \
    libpango-1.0-0 \
    libcairo2 \
    rsync \
    && npx playwright install-deps chromium \
    && rm -rf /var/lib/apt/lists/*

# 2. Install OpenClaw and browser tools
RUN npm install -g openclaw@latest agent-browser pdfnano

# 3. Install Hugging Face Hub (Python)
RUN pip3 install --no-cache-dir --break-system-packages huggingface_hub

# 4. Install Chromium and link it for OpenClaw
RUN agent-browser install chromium && \
    ln -s $(find /root/.cache/ms-playwright -name chrome -type f | grep -v "shell" | head -n 1) /usr/bin/google-chrome

# 5. Create directory structure
RUN mkdir -p /root/.openclaw/agents/main/agent \
    /root/.openclaw/agents/main/sessions \
    /root/.openclaw/credentials \
    /root/.openclaw/workspace

ENV PORT=7860
ENV OPENCLAW_GATEWAY_MODE=local
EXPOSE 7860

# 6. Startup script
RUN cat > /usr/local/bin/start-openclaw << 'EOF'
#!/bin/bash
set -e

OPENCLAW_DIR="/root/.openclaw"
HF_TMP="/tmp/hf-restore"

# DNS
echo "nameserver 1.1.1.1" > /etc/resolv.conf 2>/dev/null || true
echo "nameserver 8.8.8.8" >> /etc/resolv.conf 2>/dev/null || true

# --- RESTORE FROM HF DATASET ---
if [[ -n "$HF_DATASET_TOKEN" && -n "$HF_DATASET" ]]; then
  echo "[HF] Restoring dataset: $HF_DATASET"

  rm -rf "$HF_TMP"
  mkdir -p "$HF_TMP"

  python3 << 'EOP'
import os
from huggingface_hub import snapshot_download

snapshot_download(
    repo_id=os.environ["HF_DATASET"],
    repo_type="dataset",
    local_dir="/tmp/hf-restore",
    allow_patterns=["data/**"],
    token=os.environ["HF_DATASET_TOKEN"]
)
print("[HF] Download complete")
EOP

  # CRITICAL FIX: merge data/* into live OpenClaw dir
  if [ -d "$HF_TMP/data" ]; then
    rsync -a "$HF_TMP/data/" "$OPENCLAW_DIR/"
    echo "[HF] Data merged into OpenClaw workspace"
  fi
fi

# --- GENERATE CONFIG ONLY IF MISSING ---
if [ ! -f "$OPENCLAW_DIR/openclaw.json" ]; then
  echo "[CFG] Generating initial openclaw.json"

  if [ -z "$GEMINI_APIKEY" ]; then
    echo "ERROR: GEMINI_APIKEY not set"
    exit 1
  fi

cat > "$OPENCLAW_DIR/openclaw.json" << EOC
{
  "env": {
    "GOOGLE_API_KEY": "${GEMINI_APIKEY}",
    "GEMINI_API_KEY": "${GEMINI_APIKEY}",
    "GOOGLE_GENERATIVE_AI_API_KEY": "${GEMINI_APIKEY}",
    "TELEGRAM_BOT_TOKEN": "${TELEGRAM_BOT_TOKEN}"
  },
  "gateway": {
    "mode": "local",
    "bind": "lan",
    "port": 7860,
    "trustedProxies": ["0.0.0.0/0"],
    "auth": {
      "mode": "token",
      "token": "${OPENCLAW_GATEWAY_PASSWORD}"
    },
    "controlUi": { "allowInsecureAuth": true }
  },
  "models": {
    "providers": {
      "nvidia": {
        "baseUrl": "https://integrate.api.nvidia.com/v1",
        "apiKey": "${NVIDIA_NIM_API_KEY}",
        "api": "openai-completions",
        "models": [
          { "id": "deepseek-ai/deepseek-r1-distill-qwen-7b", "name": "Deepseek R1 Distill Qwen 7b", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "deepseek-ai/deepseek-v3.2", "name": "Deepseek v3.2", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "openai/gpt-oss-120b", "name": "GPT OSS 120b", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "openai/gpt-oss-20b", "name": "GPT OSS 20b", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "qwen/qwen2.5-7b-instruct", "name": "Qwen 2.5 7B Instruct", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "qwen/qwen2.5-coder-32b-instruct", "name": "Qwen 2.5 Coder 32B", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "qwen/qwen2.5-coder-7b-instruct", "name": "Qwen 2.5 Coder 7B", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "mistralai/mistral-large-2-instruct", "name": "Mistral Large 2 Instruct", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "databricks/dbrx-instruct", "name": "DBRX Instruct", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "mistralai/mistral-7b-instruct-v0.3", "name": "Mistral 7B Instruct v0.3", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "minimaxai/minimax-m2.1", "name": "MiniMax M2.1", "contextWindow": 200000, "maxTokens": 8192 },
          { "id": "z-ai/glm4.7", "name": "GLM 4.7", "contextWindow": 200000, "maxTokens": 8192 }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "google/gemini-3-flash-preview",
        "fallbacks": [
          "google/gemini-3-pro-preview",
          "google/gemini-2.0-flash",
          "google/gemini-2.5-flash",
          "google/gemini-2.5-pro",
          "google/gemini-3-flash-preview"
        ]
      },
      "models": {
        "google/gemini-3-pro-preview": {},
        "google/gemini-2.0-flash": {},
        "google/gemini-2.5-flash": {},
        "google/gemini-2.5-pro": {},
        "google/gemini-3-flash-preview": {},
        "nvidia/deepseek-ai/deepseek-r1-distill-qwen-7b": {},
        "nvidia/deepseek-ai/deepseek-v3.2": {},
        "nvidia/openai/gpt-oss-120b": {},
        "nvidia/openai/gpt-oss-20b": {},
        "nvidia/qwen/qwen2.5-7b-instruct": {},
        "nvidia/qwen/qwen2.5-coder-32b-instruct": {},
        "nvidia/qwen/qwen2.5-coder-7b-instruct": {},
        "nvidia/mistralai/mistral-large-2-instruct": {},
        "nvidia/mistralai/mistral-7b-instruct-v0.3": {},
        "nvidia/databricks/dbrx-instruct": {},
        "nvidia/minimaxai/minimax-m2.1": {},
        "nvidia/z-ai/glm4.7": {}
      },
      "workspace": "/root/.openclaw/workspace",
      "compaction": { "mode": "safeguard" },
      "maxConcurrent": 4,
      "subagents": { "maxConcurrent": 8 }
    }
  },
  "commands": {
    "native": "auto",
    "nativeSkills": "auto",
    "restart": true
  },
  "plugins": {
    "entries": {
      "telegram": {
        "enabled": true
      },
      "whatsapp": {
        "enabled": false
      },
      "discord": {
        "enabled": false
      },
      "qwen-portal-auth": {
        "enabled": false
      }
    }
  },
"channels": {
    "telegram": {
      "enabled": true,
      "allowFrom": ["${TELEGRAM_USER}"]
    }
  }
}
EOC
fi

chmod -R 700 "$OPENCLAW_DIR"

# --- BACKUP LOOP (EVERY 5 MINUTES) ---
if [[ -n "$HF_DATASET_TOKEN" && -n "$HF_DATASET" ]]; then
  (
    while true; do
      sleep 300
      echo "[HF] Backup running"

      python3 << 'EOP'
import os
from huggingface_hub import HfApi

api = HfApi(token=os.environ["HF_DATASET_TOKEN"])
api.upload_folder(
    repo_id=os.environ["HF_DATASET"],
    repo_type="dataset",
    folder_path="/root/.openclaw",
    path_in_repo="data",
    ignore_patterns=[
    "openclawd.json",
    "agents/**/sessions/**",
    "workspace/node_modules/**",
    "browser/**",
    "workspace/.cache/**",
    "*.key",
    ".env"
  ]
)
print("[HF] Backup complete")
EOP
    done
  ) &
fi

exec openclaw gateway run --port 7860
EOF

RUN chmod +x /usr/local/bin/start-openclaw
CMD ["/usr/local/bin/start-openclaw"]