# ---------------------------------------------------------------------------
# Freezmo - Ollama configuration
# Copy this file to `.env.local` and adjust if needed.
# ---------------------------------------------------------------------------

# WHO PROVIDES THE API KEY -----------------------------------------------------
#   user-key (default)  Every browser supplies its own key. The key is typed
#                       into the settings dialog, kept in that browser's local
#                       storage and sent with each request in the
#                       `x-ollama-key` header. The server never stores it.
#                       Point OLLAMA_BASE_URL at https://ollama.com.
#   server              One key for everyone, read from OLLAMA_API_KEY below
#                       (single-user installs). Nothing is sent from the client.
#   local               No key at all: a local daemon signed in with
#                       `ollama signin` proxies the cloud models.
OLLAMA_AUTH=user-key

# Ollama endpoint. https://ollama.com for cloud, http://localhost:11434 for a
# local daemon. In user-key mode this is the endpoint the browser's key is sent
# to; in server/local mode it is used directly.
OLLAMA_BASE_URL=https://ollama.com

# Only used when OLLAMA_AUTH=server. Never commit a real key.
OLLAMA_API_KEY=

# Model used for the vision/transcription step (reads photos of notes).
# Must be multimodal — gpt-oss and other text-only models cannot be used here.
# Free-tier friendly: gemma4:31b-cloud, kimi-k3:cloud (paid), mistral-large-3 (paid).
VISION_MODEL=gemma4:31b-cloud

# Model used to generate activities, grade short answers and restore the
# language if a transcription came back translated. gpt-oss:120b is free-tier
# friendly, very good at strict JSON and the strongest multilingual model in the
# free plan. NOTE: it is text-only, so it can't be used as VISION_MODEL.
# Free alternatives: nemotron-3-super:cloud, gpt-oss:20b-cloud.
# Paid/credit: glm-5.3-flash:cloud, kimi-k3:cloud.
TEXT_MODEL=gpt-oss:120b-cloud

# RATE LIMITS (per client IP, sliding window, in-memory) ----------------------
# Generation decks are expensive, so they are limited tightly by default.
# RATE_LIMIT_WINDOW_MS=300000
# RATE_LIMIT_GENERATE=12
# RATE_LIMIT_GRADE=40
# RATE_LIMIT_HOMEWORK=12
# RATE_LIMIT_HEALTH=90

# Optional tuning ------------------------------------------------------------
# OLLAMA_TIMEOUT_MS=300000
# OLLAMA_HEALTH_TIMEOUT_MS=8000
# Send `think: false` to thinking models for faster JSON output.
# OLLAMA_THINK=false
# FREEZMO_DEFAULT_ACTIVITY_COUNT=10