# --- Server ---
# BACKEND_PORT takes precedence over PORT. Prefer it: many tools inject PORT
# for the frontend, and Flask would otherwise take the React dev server's port.
BACKEND_PORT=5000

# --- Database: sqlite (default) or mariadb ---
DB_TYPE=sqlite
# SQLite file (used when DB_TYPE=sqlite)
DATABASE_PATH=./data/health.db

# MariaDB (used when DB_TYPE=mariadb) — runs on the NAS
# MARIADB_SOCKET=/run/mysqld/mysqld10.sock
# MARIADB_HOST=127.0.0.1
# MARIADB_PORT=3306
# MARIADB_USER=root
# MARIADB_PASSWORD=your_nas_mariadb_root_password
# MARIADB_DATABASE=garmin_health_lab

# --- Auth ---
# CHANGE THIS in production! Used to sign JWTs (7-day expiry by default).
JWT_SECRET=dev_secret_change_me
JWT_EXPIRY_DAYS=7

# --- CORS (comma-separated allowed front-end origins) ---
CORS_ORIGIN=http://localhost:3000,http://localhost:5173

# --- AI models (text-only, large context) ---
# Put REAL keys in backend/.env — that file is gitignored. Never commit keys.
# Any model whose credentials are absent is skipped automatically.

# Self-hosted AI gateway (model id "gateway"). OpenAI-compatible; it fans out
# over nvidia/gemini/ollama itself and rotates several Gemini keys, so it
# absorbs single-vendor quota limits. Reached directly, bypassing any local
# HTTP proxy. NOTE: its NVIDIA upstream is a large reasoning model — replies
# can take 2-3 minutes, so set AI_TIMEOUT_SECONDS accordingly.
AI_GATEWAY_BASE_URL=http://129.146.203.203:5100/v1
AI_GATEWAY_TOKEN=
AI_GATEWAY_MODEL=ai-gateway-auto

# Google AI Studio -> "gemini-flash". Free-tier quota is small; 429s are common.
GEMINI_API_KEY=

# NVIDIA NIM -> "llama-70b", "nemotron-49b", "mistral-large".
# Model ids come from that account's live GET /v1/models — do not guess them.
NVIDIA_API_KEY=
# NVIDIA_BASE_URL=https://integrate.api.nvidia.com/v1

# Preference order. The first configured model answers; if it fails or times
# out, the next is tried. Read per request, so changes need no restart.
AI_MODEL_CHAIN=gateway,gemini-flash,llama-70b

# Max days of history sent (CSV-encoded). Trimmed further per model so the
# payload always fits that model's own context window.
AI_DAY_BUDGET=365

AI_TIMEOUT_SECONDS=180
# Output cap. Reasoning models spend part of it thinking before they answer;
# entries that need more declare their own budget in services/ai.py.
AI_MAX_TOKENS=1024