# Serve this host's Ollama to the other machines you work from.
#
# The premise of this router is that a local LLM classifies your task before a
# cloud model answers it. "Local" means your hardware, not necessarily the
# machine you are typing on — the box with the GPU usually is not the laptop.
# Most developers already have WireGuard or a VPN back to a home lab, so the
# normal shape is: router and editor on the laptop, Ollama on the workstation,
# classifier.base_url pointing across the tunnel.
#
# Ollama listens on 127.0.0.1:11434 by default, so that fails with
# connection-refused until this drop-in is applied on the SERVING host.
#
# Install (needs root — ollama.service is a system unit):
#     sudo mkdir -p /etc/systemd/system/ollama.service.d
#     sudo cp deploy/ollama-over-vpn.conf \
#             /etc/systemd/system/ollama.service.d/override.conf
#     sudo nano /etc/systemd/system/ollama.service.d/override.conf   # set the address
#     sudo systemctl daemon-reload && sudo systemctl restart ollama
#
# Then on the client machine, in config.yaml:
#     classifier.base_url:   http://<vpn-ip-of-this-host>:11434/v1
#     verification.base_url: http://<vpn-ip-of-this-host>:11434
#
# Bind to the VPN address, NOT 0.0.0.0. Ollama has no authentication of any
# kind: anything that can reach the port can run inference, enumerate your
# models and pull new ones. 0.0.0.0 also publishes it on whatever cafe or
# hotel wifi the laptop is sitting on. Same reasoning that keeps the
# dispatcher itself on loopback.
#
# Replace with this host's own VPN address — 10.x.x.x for WireGuard,
# 100.x.x.x for Tailscale. `ip -4 -o addr show` will tell you.

[Service]
Environment="OLLAMA_HOST=10.0.0.1:11434"

# Keep the model resident between requests. Without this, the first
# classification after an idle gap pays a cold load — measured at 43s, which
# exceeds even the 120s ceiling once the SDK's retries are counted. Serving a
# laptop makes this matter more, not less: requests arrive in bursts separated
# by long gaps, which is exactly the pattern that keeps evicting the model.
Environment="OLLAMA_KEEP_ALIVE=24h"