.env.example

# ════════════════════════════════════════════════════════════════
# 🦞 HuggingClaw — OpenClaw Gateway for HuggingFace Spaces
# ════════════════════════════════════════════════════════════════
# Copy this file to .env and fill in your values.
# For local development: cp .env.example .env && nano .env

# ── REQUIRED: Core Configuration ──
# [REQUIRED] LLM provider API key
# - Anthropic: sk-ant-v0-...
# - OpenAI: sk-...
# - Google: AIzaSy...
LLM_API_KEY=your_api_key_here

# [REQUIRED] LLM model to use (format: provider/model-name)
# Auto-detects provider from prefix — any provider is supported!
# Model IDs sourced from https://openrouter.ai/api/v1/models
#
# ── Top-Tier Providers ──
#
# Anthropic Claude:
#   - anthropic/claude-opus-4.6
#   - anthropic/claude-sonnet-4.6
#   - anthropic/claude-sonnet-4.5
#   - anthropic/claude-haiku-4.5
#
# OpenAI:
#   - openai/gpt-5.4-pro (1M context)
#   - openai/gpt-5.4 (1M context)
#   - openai/gpt-5.4-mini
#   - openai/gpt-5.4-nano
#   - openai/gpt-4.1
#   - openai/gpt-4.1-mini
#   - openai/gpt-4.1-nano
#
# Google Gemini:
#   - google/gemini-3.1-pro-preview
#   - google/gemini-3.1-flash-lite-preview
#   - google/gemini-2.5-pro
#   - google/gemini-2.5-flash
#
# DeepSeek:
#   - deepseek/deepseek-v3.2
#   - deepseek/deepseek-r1-0528
#   - deepseek/deepseek-r1
#   - deepseek/deepseek-chat-v3.1
#
# ── Chinese/Asian Providers ──
#
# Qwen (Alibaba):
#   - qwen/qwen3.6-plus-preview:free (1M context, free!)
#   - qwen/qwen3-max
#   - qwen/qwen3-coder
#   - qwen/qwen3.5-397b-a17b
#   - qwen/qwen3.5-35b-a3b
#
# Z.ai (GLM):
#   - z-ai/glm-5
#   - z-ai/glm-5-turbo
#   - z-ai/glm-4.7
#   - z-ai/glm-4.7-flash
#   - z-ai/glm-4.5-air:free (free!)
#
# Moonshot (Kimi):
#   - moonshotai/kimi-k2.5
#   - moonshotai/kimi-k2
#   - moonshotai/kimi-k2-thinking
#
# Xiaomi (MiMo):
#   - xiaomi/mimo-v2-pro (1M context)
#   - xiaomi/mimo-v2-omni (multimodal)
#   - xiaomi/mimo-v2-flash
#
# ByteDance Seed:
#   - bytedance-seed/seed-2.0-lite
#   - bytedance-seed/seed-2.0-mini
#
# Baidu (ERNIE):
#   - baidu/ernie-4.5-300b-a47b
#   - baidu/ernie-4.5-21b-a3b
#
# Tencent:
#   - tencent/hunyuan-a13b-instruct
#
# StepFun:
#   - stepfun/step-3.5-flash
#   - stepfun/step-3.5-flash:free (free!)
#
# ── Western Providers ──
#
# Mistral:
#   - mistralai/mistral-large-2512
#   - mistralai/mistral-medium-3.1
#   - mistralai/mistral-small-2603
#   - mistralai/devstral-medium (coding)
#   - mistralai/codestral-2508
#
# xAI (Grok):
#   - x-ai/grok-4.20-beta
#   - x-ai/grok-4.20-multi-agent-beta
#   - x-ai/grok-4.1-fast
#   - x-ai/grok-4
#
# Meta (Llama):
#   - meta-llama/llama-4-maverick
#   - meta-llama/llama-4-scout
#   - meta-llama/llama-3.3-70b-instruct
#
# NVIDIA:
#   - nvidia/nemotron-3-super-120b-a12b
#   - nvidia/nemotron-3-super-120b-a12b:free (free!)
#
# Cohere:
#   - cohere/command-a
#   - cohere/command-r-plus-08-2024
#
# Perplexity:
#   - perplexity/sonar-deep-research
#   - perplexity/sonar-pro
#
# MiniMax:
#   - minimax/minimax-m2.7
#   - minimax/minimax-m2.5
#   - minimax/minimax-m2.5:free (free!)
#
# ── Speed & Specialty ──
#
# Inception (ultra-fast reasoning):
#   - inception/mercury-2 (1000+ tok/sec)
#   - inception/mercury-coder
#
# Amazon:
#   - amazon/nova-premier-v1
#   - amazon/nova-pro-v1
#
# ── OpenRouter (100+ models via single API key) ──
# Use any model above via OpenRouter with a single API key!
# See https://openrouter.ai/models for complete list
#
# Or any other provider — format: provider/model-name (auto-detected)
LLM_MODEL=anthropic/claude-sonnet-4.5

# [REQUIRED] Gateway authentication token
# Generate: openssl rand -hex 32
GATEWAY_TOKEN=your_gateway_token_here

# ── OPTIONAL: Telegram Integration ──
# Enable Telegram bot integration
# Get bot token from: https://t.me/BotFather
TELEGRAM_BOT_TOKEN=your_bot_token_here

# Single user ID for DM access
# Get your ID from: https://t.me/userinfobot
TELEGRAM_USER_ID=123456789

# Multiple user IDs (comma-separated for team access)
# TELEGRAM_USER_IDS=123456789,987654321,555555555

# ── OPTIONAL: Workspace Backup to HF Dataset ──
# Enable automatic workspace backup & restore
# Your HuggingFace username
HF_USERNAME=your_hf_username

# HuggingFace API token (with write access)
# Get from: https://huggingface.co/settings/tokens
HF_TOKEN=hf_your_token_here

# Name of the backup dataset (auto-created if missing)
# Default: huggingclaw-backup
BACKUP_DATASET_NAME=huggingclaw-backup

# Git commit email for workspace syncs
# Default: openclaw@example.com
WORKSPACE_GIT_USER=openclaw@example.com

# Git commit name for workspace syncs
# Default: OpenClaw Bot
WORKSPACE_GIT_NAME=OpenClaw Bot

# ── OPTIONAL: Background Services Configuration ──
# Keep-alive ping interval in seconds (prevents HF Spaces sleep)
# Default: 300 (5 minutes)
# Set to 0 to disable (not recommended on HF Spaces)
KEEP_ALIVE_INTERVAL=300

# Workspace auto-sync interval in seconds
# Default: 600 (10 minutes)
SYNC_INTERVAL=600

# ── OPTIONAL: Advanced Configuration ──
# Pin OpenClaw version (default: latest)
# Example: OPENCLAW_VERSION=2026.3.24
OPENCLAW_VERSION=latest

# Health endpoint port (default: 7861)
HEALTH_PORT=7861

# ════════════════════════════════════════════════════════════════
# QUICK START CHECKLIST
# ════════════════════════════════════════════════════════════════
#
# ✅ Minimum setup (3 secrets):
#    1. LLM_API_KEY - Get from your LLM provider
#    2. LLM_MODEL - Choose a model above
#    3. GATEWAY_TOKEN - Run: openssl rand -hex 32
#
# ✅ Add Telegram (2 more secrets):
#    4. TELEGRAM_BOT_TOKEN - From @BotFather
#    5. TELEGRAM_USER_ID - From @userinfobot
#
# ✅ Enable Backup (2 more secrets):
#    6. HF_USERNAME - Your HF account name
#    7. HF_TOKEN - From HF Settings → Tokens
#
# ════════════════════════════════════════════════════════════════
# DEPLOYMENT OPTIONS
# ════════════════════════════════════════════════════════════════
#
# 📦 HuggingFace Spaces (Recommended):
#    - Click "Duplicate this Space"
#    - Go to Settings → Secrets
#    - Add LLM_API_KEY, LLM_MODEL, GATEWAY_TOKEN
#    - Deploy (automatic!)
#
# 🐳 Docker Local:
#    docker build -t huggingclaw .
#    docker run -p 7860:7860 --env-file .env huggingclaw
#
# 💻 Direct (without Docker):
#    npm install -g openclaw@latest
#    export $(cat .env | xargs)
#    bash start.sh
#
# ════════════════════════════════════════════════════════════════
# VERIFY YOUR SETUP
# ════════════════════════════════════════════════════════════════
#
# After deployment, check:
# 1. Logs for "🦞 HuggingClaw Gateway" banner
# 2. Health endpoint: curl https://YOUR-SPACE-URL.hf.space/health
# 3. Control UI: https://YOUR-SPACE-URL.hf.space
# 4. (If Telegram) DM your bot to test
#
# ════════════════════════════════════════════════════════════════