{ ... }:

# Hermes Agent (https://github.com/NousResearch/hermes-agent) — Nous
# Research's tool-calling CLI/gateway agent, pointed at the local ollama
# server (see hosts/terra/configuration.nix) over its OpenAI-compatible /v1
# route instead of a cloud provider. The nixosModules.default this pulls in
# comes from the hermes-agent flake input itself (flake.nix), not from
# nixpkgs — it builds the agent from source via uv2nix, so there's no
# curl-|-bash installer or runtime pip/npm involved.
#
# Native mode (container.enable stays false): a hardened systemd service is
# enough here since the agent only needs to reach loopback ollama, and it
# avoids the podman-rootful-needs-passwordless-sudo dance the module's docs
# call out for container mode. addToSystemPackages puts `hermes` on darman's
# PATH sharing state (sessions, memories, cron) with the service instead of
# starting a second, disconnected ~/.hermes.
{
  services.hermes-agent = {
    enable = true;
    addToSystemPackages = true;

    settings.model = {
      provider = "custom";
      base_url = "http://127.0.0.1:11434/v1";
      # gemma4:12b, not qwen3.6:35b-a3b: same daily-driver model already
      # loaded for librechat (services/desktop/librechat.nix) — reusing it
      # means no second model has to swap into the 6800 XT's 16G VRAM
      # alongside whatever's already resident.
      default = "gemma4:12b";
      # No api_key — ollama's OpenAI-compat endpoint doesn't check one.
      # Mirrors OLLAMA_CONTEXT_LENGTH set on the ollama service itself;
      # this is a client-side hint only, ollama enforces the real limit.
      context_length = 131072;
    };
  };
}