docs: simplify .env.example to show only required settings

Only include the 4 required environment variables:
- STEWARD__TELEGRAM__BOT_TOKEN
- STEWARD__OPENAI__API_KEY
- STEWARD__TELEGRAM__ALLOWED_USER_IDS
- STEWARD__TELEGRAM__GROUP_IDS

All other settings have sensible defaults in config_schema.yaml and can be
overridden if needed. This keeps the example file clean and focused.
This commit is contained in:
Daniel Wagner 2026-07-26 12:39:11 +10:00
parent d5eac108f8
commit d0ccc96507

View File

@ -2,41 +2,31 @@
# Never commit .env to version control.
# Telegram bot token from @BotFather
STEWARD__TELEGRAM__BOT_TOKEN=
TELEGRAM_BOT_TOKEN=
# List of user IDs allowed to interact via DM (JSON format, empty = all users)
STEWARD__TELEGRAM__ALLOWED_USER_IDS='[1234567890]'
# Comma-separated Telegram user IDs allowed to talk to Steward.
# Leave empty to allow everyone (not recommended for production).
TELEGRAM_ALLOWED_USER_IDS=
# List of group/channel IDs where bot operates (JSON format, empty = all groups)
STEWARD__TELEGRAM__GROUP_IDS='[-1005308306472]'
# OpenAI (or compatible) credentials
OPENAI_API_KEY=
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4o
# OpenAI API key
STEWARD__OPENAI__API_KEY=
# Optional: override the default system prompt
# OPENAI_SYSTEM_PROMPT=
# OpenAI API base URL (can use any OpenAI-compatible provider)
STEWARD__OPENAI__BASE_URL=https://api.openai.com/v1
# Daily analysis target (optional)
# ANALYSIS_TARGET_URL=https://your-internal-api/endpoint
# ANALYSIS_TARGET_API_KEY=
# ANALYSIS_CRON_HOUR=8
# ANALYSIS_CRON_MINUTE=0
# Model to use
STEWARD__OPENAI__MODEL=gpt-4o
# Thread memory store path (JSON file for persisted thread summaries)
# THREAD_MEMORY_PATH=thread_memory.json
# Optional: Custom system prompt for the LLM
# STEWARD__OPENAI__SYSTEM_PROMPT="You are Steward..."
# Optional: Target URL for API analysis
STEWARD__ANALYSIS__TARGET_URL=
# Optional: API key for analysis target
STEWARD__ANALYSIS__TARGET_API_KEY=
# Cron schedule for automatic analysis
STEWARD__ANALYSIS__CRON_HOUR=8
STEWARD__ANALYSIS__CRON_MINUTE=0
# Path to thread memory storage (use absolute path in containers)
STEWARD__MEMORY__THREAD_MEMORY_PATH=/data/thread_memory.json
# Optional: MCP/OpenAPI tool server URL
STEWARD__TOOLS__MCP_SERVER_URL=
# Optional: API key for MCP server
STEWARD__TOOLS__MCP_SERVER_API_KEY=
# MCP / OpenAPI tool server (open-webui/openapi-servers compatible)
# Point to any OpenAPI-spec tool server to enable LLM tool calling.
# The service fetches /openapi.json from MCP_SERVER_URL to discover tools.
# MCP_SERVER_URL=http://localhost:8000
# MCP_SERVER_API_KEY=