# --- 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) — production DB on the Oracle server
# (129.146.26.249, local MariaDB 10.3). Dedicated account over TCP 127.0.0.1;
# MARIADB_SOCKET is only needed if TCP auth is disabled for the app user.
# MARIADB_HOST=127.0.0.1
# MARIADB_PORT=3306
# MARIADB_USER=garmin
# MARIADB_PASSWORD=your_production_mariadb_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

# --- auth-hub OAuth2 provider (centralized SSO) ---
# See docs/AUTH_HUB_INTEGRATION.md for setup instructions.
#
# Base URL of the auth-hub service
AUTH_HUB_BASE_URL=http://129.146.26.249:5300
#
# OAuth2 client credentials (obtain from auth-hub.manage_clients create)
# NOTE: these must be registered against the auth-hub instance AUTH_HUB_BASE_URL
# actually points to (dev vs prod are separate databases with separate clients).
# Put the REAL values in backend/.env (gitignored) — never here.
AUTH_HUB_CLIENT_ID=your_client_id
AUTH_HUB_CLIENT_SECRET=your_client_secret
#
# Callback URL (must exactly match what's registered in auth-hub)
AUTH_HUB_REDIRECT_URI=http://129.146.26.249:8123/auth/callback

# --- CORS (comma-separated allowed front-end origins) ---
# localhost stays in the production list on purpose: CORS is not an auth
# boundary — every data route requires a valid JWT — so allowing a developer's
# dev server costs nothing and saves toggling this on every session.
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.
# HTTPS (Caddy, strips the /ai prefix) rather than http://…:5100 — the token
# rides in an Authorization header and should not cross the internet in clear.
AI_GATEWAY_BASE_URL=https://oracle.zichuan.xyz/ai/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

# Measured against the gateway, not guessed: a trivial prompt took 138s end to
# end, because its primary upstream emits a full chain of thought before the
# answer. Nothing user-facing blocks on this (the briefing generates in a
# background thread), but the timeout still has to clear the real latency.
AI_TIMEOUT_SECONDS=300
# 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

# Output cap for the AI coach (晨报 / 趋势归因 / Copilot). Larger than
# AI_MAX_TOKENS above: the same reasoning trace is spent from this budget
# before the answer starts, and at 1024 the reply was all thinking with the
# JSON truncated away.
AI_COACH_MAX_TOKENS=4000

# --- AI coach job queue ---
# The gateway runs `gunicorn -w 1 --threads 4` and is shared with fam-edge and
# the camera project: four concurrent requests for everyone, while one of ours
# holds a thread for 2-5 minutes. So this consumer runs one job at a time
# across the whole deployment (not one per Gunicorn worker) and waits between
# jobs. Raising either of these makes the backfill finish sooner at the cost of
# the shared box — a 502 there is a 502 for the other two projects as well.
AI_JOB_CONCURRENCY=1
AI_JOB_GAP_SECONDS=20
# Set AI_JOBS=false to stop consuming entirely (screens then show the computed
# figures with no model reading).
AI_JOBS=true