# Copy to .env and adjust — or just run ./scripts/update.sh, which creates
# .env from this file and fills in every secret/key below it can generate
# itself (see each var's comment). All values below are defaults baked into
# docker-compose.yml — only uncomment/change what you actually want to
# override.

# --- llama.cpp / model ---
LLAMA_MODEL_FILE=Qwen3.8-27B-UD-Q4_K_XL.gguf
# 999 = every layer on GPU (this model is dense, not MoE, and already fits
# fully in 32GB VRAM — see docs/research/qwen3.8-27b-quant.md). Lower this
# to leave that many fewer layers on GPU and push the rest to CPU/system RAM
# if something else is contending for VRAM — llama.cpp has no separate
# "RAM offload" flag, --n-gpu-layers *is* the RAM-offload knob for a dense
# model. Don't reach for --n-cpu-moe/--cpu-moe/--override-tensor "exps" —
# those target Mixture-of-Experts models (e.g. Qwen3.8-2.4T-A95B), not this
# one, and are no-ops here.
# There's no separate "then SSD" tier to enable either: llama.cpp mmaps the
# model file by default (no --no-mmap here), so if GPU+RAM ever can't hold
# the working set, the OS pages the rest in from disk automatically — an
# implicit, slow last resort, not a config knob. An explicit tiered SSD
# offload has been an open llama.cpp feature request since 2025 (still
# unimplemented): https://github.com/ggml-org/llama.cpp/discussions/12507
LLAMA_GPU_LAYERS=999
# 131072 (128K): ~25.6GB (17.6GB weights + ~8GB KV cache) on the 32GB
# R9700, ~6GB headroom — see docs/research/qwen3.8-27b-quant.md for the full
# table (64K only used ~19.6GB/~12GB headroom, but real usage was burning
# through 64K fast). If headroom gets tight, quantize the KV cache instead
# of dropping context: --cache-type-k/v q8_0 roughly halves it.
LLAMA_CTX_SIZE=131072

# --- Lazytainer ---
# Seconds of inactivity before llama-server is stopped. 900 = 15 min.
LAZYTAINER_INACTIVE_TIMEOUT=900

# --- SearXNG web search (see docs/research/litellm-searxng-search.md) ---
# Resolved automatically by ./scripts/update.sh from search.home on this
# host — leave blank. Only set by hand if that resolution fails (e.g.
# search.home isn't a static DHCP reservation and its IP drifted).
SEARXNG_LAN_IP=

# --- OmniRoute gateway (see docs/proxy-key-onboarding.md, docs/network-access.md) ---
# OMNIROUTE_PORT is the host-published port (reverse-proxied by NPM) — kept
# at 4000, same as the old LiteLLM setup, so existing NPM/firewall config
# doesn't need to change. It's mapped via plain Docker port publishing onto
# API_PORT, omniroute's own container-internal port (left at its default,
# not reconfigured to match). The dashboard (DASHBOARD_PORT) is never
# published at all — see docker-compose.yml's omniroute service comment.
OMNIROUTE_PORT=4000
OMNIROUTE_API_PORT=20129
OMNIROUTE_DASHBOARD_PORT=20128
# Random values, filled in automatically by ./scripts/update.sh — leave
# blank. Bootstrap dashboard admin password (log in at the dashboard port,
# change it there afterwards — this is only the first-boot value):
OMNIROUTE_INITIAL_PASSWORD=
# Signs dashboard session cookies:
OMNIROUTE_JWT_SECRET=
# Encrypts API key values at rest in omniroute's SQLite DB:
OMNIROUTE_API_KEY_SECRET=
# Encrypts the whole SQLite DB at rest. Do not change after first run —
# existing encrypted data becomes unreadable if you do (same caveat as
# LiteLLM's old LITELLM_SALT_KEY):
OMNIROUTE_STORAGE_ENCRYPTION_KEY=
# Per-deployment salts — random is fine, just needs to be stable:
OMNIROUTE_MACHINE_ID_SALT=
OMNIROUTE_CLI_SALT=
# Per-workload virtual keys (one per client that calls the gateway) have no
# scripted /key/generate equivalent yet — omniroute's key-creation endpoint
# needs a dashboard login session, not a static bearer key (see issue #37).
# Mint them by hand in the dashboard, add a KEY=value line here per workload
# as you onboard one. See docs/proxy-key-onboarding.md.