homelab/hosts/mars/hermes-agent.nix

{ config, ... }:

# Hermes Agent — moved here from jupiter (hosts/jupiter/hermes-agent.nix,
# see its git history / b5fa599 / 713d91d for the terra->jupiter->mars
# lineage). mars is dedicated to this one service, on-site, with no big
# data array of its own — unlike jupiter it has nothing under /mnt/data, so
# state lives on the local OS disk and the shared dropbox rides jupiter's
# samba share as a CIFS client instead of being served locally.
#
# Runs the OFFICIAL published image (docker.io/nousresearch/hermes-agent —
# real and actively maintained, contrary to what the checked-out repo's own
# README/docker-compose.yml suggested; verified directly on Docker Hub) as a
# plain podman container. It never sets HERMES_MANAGED or writes .managed, so
# Hermes fully self-manages config.yaml, profiles, memories and skills at
# runtime — no redeploy needed except to bump the pinned digest below.
#
# Security posture:
#   - Only two paths reachable: its own local state dir, and the small
#     shared "dropbox" below (via the jupiter samba mount) for darman to
#     hand files to Hermes — nothing else on jupiter's array is reachable
#     if a command goes wrong or gets injected via Telegram/tool output.
#   - Its own Telegram bot (own token, in secrets.nix) with an EXPLICIT
#     TELEGRAM_ALLOWED_USERS.
#   - Runs as a rootful podman container (services/containers.nix) with its
#     OWN numeric uid/gid — not darman, who is in the "hermes" group for
#     host-level debugging only (`podman exec -it hermes-agent hermes ...`).
#
# Dashboard (HERMES_DASHBOARD=1) is gated behind Authentik, same setup as on
# jupiter. Its default bind (0.0.0.0:9119) fails closed without an auth
# provider registered, and 0.0.0.0 (not loopback) is required so neptun's
# Caddy can reach it over tailscale0 — reachability itself stays LAN-closed
# (no networking.firewall.allowedTCPPorts entry; tailscale0 is already a
# trustedInterface, services/vpn/tailscale.nix). Public route: neptun's
# hermes.mgaction.town vhost (hosts/neptun/configuration.nix) proxies to this
# over the tailnet. mars runs no Caddy of its own (single-purpose box), so
# there is no LAN vhost — reach the dashboard directly via mars's tailnet
# name (mars.orbit.sol:9119) or LAN IP:9119 for local debugging.
#
# Uses upstream's generic self-hosted OIDC plugin, same Authentik
# application as before (slug `hermes`) — the client ID/secret didn't need
# to change since the public redirect URI (hermes.mgaction.town) didn't.
#
# Data migration: this starts with a FRESH state dir. jupiter's instance was
# itself reset to fresh on 2026-08-21 (see its old hermes-agent.nix), so
# there was nothing irreplaceable to carry forward; if that turns out to be
# wrong, jupiter's old data is backed up at
# /mnt/data/AppData/hermes.bak-2026-08-21 and can be rsynced into
# ${hermesHome} below before the first switch on mars.
let
  stateDir = "/var/lib/hermes";
  hermesHome = "${stateDir}/.hermes";
  # Shared drop-in folder: darman can put files here from any host. Lives on
  # jupiter's array (reachable at /mnt/jupiter, the samba mount below) rather
  # than locally, so it's the same physical location it always was — only
  # the container reading it moved. Mounted under /opt/data so it falls
  # inside Hermes's own sealed write-safe root (HERMES_WRITE_SAFE_ROOT=
  # /opt/data) rather than a path its own tooling would treat as untrusted.
  dropboxDir = "/mnt/jupiter/AppData/hermes-dropbox";

  # Pinned by digest (captured 2026-08-21 via `podman image inspect
  # docker.io/nousresearch/hermes-agent:latest --format '{{.Digest}}'` on
  # jupiter) rather than floating `:latest`, so a redeploy is reproducible —
  # bumping Hermes is an explicit edit here, not silent drift on next pull.
  hermesImage = "docker.io/nousresearch/hermes-agent@sha256:5342e518734a08f6c66b89b4262434813c28a77abbc59c230c8f1637df71a259";

  # Kept identical to jupiter's instance purely so nothing else needs to
  # change if state ever gets migrated over.
  hermesUid = "986";
  hermesGid = "983";
in
{
  # Browsing convenience (ssh access to the bind-mounted local state) — does
  # NOT touch the container, which keeps using HERMES_UID/GID above
  # regardless of what's declared here.
  users.groups.hermes.gid = 983;
  users.users.darman.extraGroups = [ "hermes" ];

  systemd.tmpfiles.rules = [
    "d ${stateDir} 0750 root hermes -"
  ];

  # podman requires the bind-mount source to already exist (no auto-create),
  # and the dropbox lives on the CIFS mount below — mkdir there works fine
  # over cifs, no server-side (jupiter) config needed.
  systemd.services.hermes-agent-prepare-dirs = {
    description = "Create Hermes state dirs before the container starts";
    before = [ "podman-hermes-agent.service" ];
    wantedBy = [ "podman-hermes-agent.service" ];
    unitConfig.RequiresMountsFor = [ "/mnt/jupiter" ];
    serviceConfig.Type = "oneshot";
    script = ''
      mkdir -p ${hermesHome}
      mkdir -p ${dropboxDir}
    '';
  };

  virtualisation.oci-containers.containers.hermes-agent = {
    image = hermesImage;
    autoStart = true;
    # Host networking: Hermes only long-polls Telegram outbound, no inbound
    # ports to publish (same reasoning as clonarr on jupiter).
    extraOptions = [ "--network=host" ];
    # Upstream's own documented single-mount pattern (docker/docker-compose.yml):
    # ~/.hermes:/opt/data.
    volumes = [
      "${hermesHome}:/opt/data"
      "${dropboxDir}:/opt/data/dropbox"
    ];
    environment = {
      HERMES_UID = hermesUid;
      HERMES_GID = hermesGid;
      TZ = "Europe/Berlin";
      # HERMES_TIMEZONE is the highest-priority source hermes_time.py checks
      # (ahead of config.yaml's `timezone` key) — the container has no host
      # /etc/localtime bind-mount, so it defaults to UTC otherwise (fixed in
      # 9403122 on jupiter; carried forward here).
      HERMES_TIMEZONE = "Europe/Berlin";

      # Dashboard + Authentik OIDC gate — see the file-level comment above.
      HERMES_DASHBOARD = "1";
      HERMES_DASHBOARD_HOST = "0.0.0.0"; # must be tailscale0-reachable, not just loopback
      HERMES_DASHBOARD_OIDC_ISSUER = "https://auth.mgaction.town/application/o/hermes/";
      HERMES_DASHBOARD_OIDC_CLIENT_ID = "4BqdJu3htnMtSZnyEu5zHnsSOvlEbw3Ie3mYVlh6";
      # uvicorn's proxy_headers=True (web_server.py) only trusts
      # X-Forwarded-Proto from forwarded_allow_ips, which defaults to
      # 127.0.0.1 — neptun's Caddy reaches this over the tailnet (a real
      # routed IP), so without this the dashboard sees the raw scheme (http)
      # and builds an http:// redirect_uri that Authentik rejects against its
      # registered https:// one. Safe to trust any peer here: 9119 is already
      # scoped to loopback + tailscale0 only (no LAN firewall rule), so
      # nothing untrusted can reach this process to begin with.
      FORWARDED_ALLOW_IPS = "*";
    };
    environmentFiles = [ config.sops.templates."hermes-agent.env".path ];
    cmd = [ "gateway" "run" ];
  };

  systemd.services.podman-hermes-agent = {
    after = [
      "hermes-agent-prepare-dirs.service"
      "systemd-tmpfiles-setup.service"
    ];
    requires = [ "hermes-agent-prepare-dirs.service" ];
    unitConfig.RequiresMountsFor = [ "/mnt/jupiter" ];
  };
}