docs: design spec for Hermes Agent on mibook

Locks in host (mibook, not jupiter), deployment mode (NixOS native
module), and auth (claude setup-token / ANTHROPIC_TOKEN, Max extra
credits) after a grilling round. Builds on feat/sops-nix as-is.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Vbvwg3Qt2u9nbkEA3wL17S
This commit is contained in:
2026-09-08 16:56:26 +02:00
co-authored by Claude Sonnet 5
parent 621ca5dde6
commit 6212b4fcf7
@@ -0,0 +1,147 @@
# Hermes Agent on mibook
**Date:** 2026-09-08
**Machine:** mibook (laptop, KDE desktop, current daily driver)
**Status:** Design approved, pending implementation plan
**Base branch:** `feat/sops-nix` (pushed to `origin`, not yet merged to `main`)
## Goal
Deploy [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent)
as a NixOS-native systemd service on mibook, reachable via Telegram and Email,
using an Anthropic Claude subscription (`claude setup-token`) rather than a
pay-per-token API key. Design + implementation plan only — no execution in
this round; a later session applies the plan.
## Decisions
| Topic | Decision |
|-------|----------|
| Host | mibook, not jupiter. Availability gap (laptop sleeps/lid-closes) is accepted, not engineered around |
| Use case | Messaging gateway (Telegram + Email), not CLI-only |
| Deployment mode | NixOS native module (`services.hermes-agent.*` from upstream `nixosModules.default`), wrapped in `my.profiles.hermes-agent`. Home Manager was considered and rejected — not wired into this flake anywhere; adding it for one service is a new framework dependency, not proportionate |
| Module source | Official `github:NousResearch/hermes-agent`, not the community `0xrsydn/nix-hermes-agent` wrapper |
| Nix support tier | Docs explicitly call Nix/NixOS "Tier 2, best-effort" — Docker/FHS is upstream's primary supported path. Accepted tradeoff, not a blocker |
| LLM provider auth | Anthropic via `claude setup-token` (long-lived, headless-friendly token) → `ANTHROPIC_TOKEN`, not `ANTHROPIC_API_KEY` |
| Billing caveat | Setup-token/OAuth path only draws from a **Claude Max "extra usage credits"** pool, never the base Max allowance. Claude Pro cannot use this path at all. User intends to use `claude setup-token`; not independently re-verified that extra credits are purchased — confirm in Anthropic console before/during implementation |
| Secrets | One sops secret, `hermes-env`, containing a full env-file blob (matches the module's `environmentFiles` list-of-paths interface — not a single-value secret) |
| sops prerequisite | **None.** mibook is already a registered sops recipient (`host_mibook` in `.sops.yaml`, `secrets/mibook.yaml` exists, proven via a live `nixos-rebuild switch` in the sops-nix work). No "Phase 9"-style bootstrapping needed — that deferred work is about *jupiter*, irrelevant now that mibook is the target |
| Network exposure | None. Telegram (long-polling) and Email (IMAP/SMTP) are both outbound-initiated from mibook. No Caddy/webserver module changes, no public endpoint |
| Messaging platforms | Telegram + Email only, first pass. Hermes Agent supports 27+ platforms total (Discord, Slack, WhatsApp, Matrix, etc.) — others deliberately out of scope, same pattern applies later if wanted |
### Deliberately deferred (YAGNI)
- Any workaround for mibook's availability gap (cloud relay, wake scheduling, HA failover to jupiter)
- Discord, Slack, or any other messaging platform beyond Telegram + Email
- Public/internet exposure of any kind
- Merging or rebasing `feat/sops-nix` — this design builds on top of it as-is
## Part 1 — The module
New flake input in `flake.nix`, following the exact shape `sops-nix` already
uses:
```nix
hermes-agent = {
url = "github:NousResearch/hermes-agent";
inputs.nixpkgs.follows = "nixpkgs";
};
```
Import the upstream module **only into mibook's module list**, not
`baseModules` — this is a single-host service, unlike `sops-nix.nixosModules.sops`
which every machine needs. In `machines/configuration.nix`, mibook's
`modules = defaultModules ++ [ hermes-agent.nixosModules.default ./mibook/configuration.nix ]`
(exact insertion point to be confirmed against the file at implementation
time — `defaultModules` is currently machine-agnostic, so this is a targeted,
minimal deviation from that shared list, not a restructuring of it).
New file `modules/environments/hermes-agent/default.nix` following the
repo's standard profile pattern:
```nix
{ config, lib, pkgs, ... }:
let
cfg = config.my.profiles.hermes-agent;
in
{
options.my.profiles.hermes-agent.enable = lib.mkEnableOption "Hermes Agent (Telegram + Email gateway)";
config = lib.mkIf cfg.enable {
services.hermes-agent = {
enable = true;
settings.model.default = "anthropic/claude-sonnet-4-5"; # confirm exact model string at implementation
environmentFiles = [ config.sops.secrets."hermes-env".path ];
addToSystemPackages = true;
};
};
}
```
Add `./environments/hermes-agent` to `modules/environments/default.nix`;
enable `my.profiles.hermes-agent.enable = true` in
`machines/mibook/environments.nix`.
**Provided for free by the upstream module:** `hermes` system user/group
(`createUser` default true), hardened systemd unit (`NoNewPrivileges`,
`ProtectSystem=strict`, `PrivateTmp` — not independently user-configurable
per the docs), `hermes` CLI on `$PATH` via `addToSystemPackages`.
## Part 2 — Secret
Add to `machines/mibook/secrets.nix` (existing file, per `docs/secrets.md`):
```nix
sops.secrets.hermes-env = {
owner = "hermes";
group = "hermes";
mode = "0400";
restartUnits = [ "hermes-agent.service" ]; # confirm exact unit name at implementation
};
```
Populate via `nix develop -c sops secrets/mibook.yaml`, adding a
multi-line `hermes-env` block:
```
ANTHROPIC_TOKEN=<output of `claude setup-token`>
TELEGRAM_BOT_TOKEN=<from @BotFather>
<IMAP/SMTP host, user, password or app-password — exact keys per Hermes' email integration doc>
```
**Verify at implementation, not assumed:** the module's own documented
example uses `ANTHROPIC_API_KEY`; the setup-token path is documented
separately (and thinly) as `ANTHROPIC_TOKEN`. Confirm the running module
actually picks up `ANTHROPIC_TOKEN` before treating auth as working —
if it doesn't, the fallback is a plain `ANTHROPIC_API_KEY` (pay-per-token,
loses the subscription framing this design was built around).
**Must `git add secrets/mibook.yaml` before `nix build`** — untracked
files are invisible to flake evaluation (existing repo rule, `docs/secrets.md`).
## Part 3 — Rollout runbook (on mibook)
1. Confirm Claude Max extra-usage-credits are actually purchased (Anthropic
console) — the whole auth design depends on this pool being funded.
2. Run `claude setup-token` on mibook; capture the token.
3. Create/gather Telegram bot token (`@BotFather`) and email credentials.
4. Add the `hermes-agent` flake input; add the module wrapper file; wire it
into `modules/environments/default.nix` and `machines/mibook/environments.nix`.
5. Add `sops.secrets.hermes-env` to `machines/mibook/secrets.nix`.
6. `nix develop -c sops secrets/mibook.yaml`, populate `hermes-env`, `git add`.
7. `nix build '.#nixosConfigurations.mibook.config.system.build.toplevel'` — CI-style check before touching the running system.
8. `sudo nixos-rebuild test --flake '.#mibook'` — verify before persisting across reboot.
9. `journalctl -u hermes-agent.service -f` — confirm it starts, decrypts the secret, connects to Telegram (and doesn't loop-crash on the `ANTHROPIC_TOKEN` question from Part 2).
10. Send a test Telegram message; send a test email; confirm both round-trip.
11. `sudo nixos-rebuild switch --flake '.#mibook'` once verified.
### Rollback
`my.profiles.hermes-agent.enable = false`, `nixos-rebuild switch`. No data
migration involved (no existing deployment to preserve), so rollback is a
one-line revert, not a runbook.
## Open risks (carried forward, not resolved by design)
1. **`ANTHROPIC_TOKEN` vs `ANTHROPIC_API_KEY`** — thin upstream docs, needs a real test (Part 2).
2. **Extra-credits billing pool funding** — not independently verified, user-asserted intent (Part 3, step 1).
3. **Tier 2 Nix support** — expect some manual troubleshooting; upstream doesn't guarantee the flake stays working across their commits.
4. **Availability gap** — accepted by design, not a bug to fix later unless priorities change.