hyperhive/nix/host-modules/hive-gateway/options.nix
atlas 0e1a975f9f fix(3179): the gateway's config files get their own state dir
`agents.conf` and `gateway.htpasswd` move from /var/lib/hyperhive/gateway
to /var/lib/hive-gateway/conf, alongside the `tls/` the gateway already
kept there.

nginx reads both as an unprivileged user. Under c0re's state dir it could
only reach them by traversing a directory systemd re-declares `0750
hive-core` on every c0re start — so nginx was given `SupplementaryGroups
= [ "hive-core" ]`, which also handed it read access to everything else
group-readable in that tree. The tokens are individually 0600, but the
broker sqlite carries no explicit mode: every message between every agent
was readable by the process whose job is parsing untrusted network input.

Moving the files removes the need and the exposure together. The group is
gone, and its absence is now commented as load-bearing so it doesn't come
back as a fix for a symptom it would recreate.

Also drops this module's `/var/lib/hyperhive` tmpfiles rule. It declared
`0755 root root` and could never win against `StateDirectoryMode`, and a
losing declaration still reads as a guarantee — that is what sent the
first diagnosis of the outage looking for who had changed the mode.

Ordering is unchanged and still the thing that makes a fresh boot work:
tmpfiles runs before services and seeds both files empty-but-valid, nginx
names them (an `include` of a missing file is fatal, not empty), and
content arrives when c0re writes and reloads — which it does on every
topology change, so a boot against the empty seed resolves itself.

Folds in the mode fix: `write` now sets 0644 on the tmp file before the
rename, because a rename carries the source's mode and discards the
destination's, and the tmpfiles rule that declares 0644 is
create-if-absent so it never re-applies.
2026-08-12 10:29:27 +02:00

312 lines
12 KiB
Nix

# Option declarations for `services.hyperhive.gateway.*`. The gateway
# is always run alongside hyperhive (it's the single nginx in front of
# every surface and the only thing exposed to the outside); there is
# no enable flag. An operator who wants their own reverse proxy in
# front points it at the gateway's `port`.
{
lib,
config,
...
}:
let
cfg = config.services.hyperhive.gateway;
in
{
imports = [
(lib.mkRemovedOptionModule [ "services" "hyperhive" "gateway" "selfSignedTls" ] ''
Self-signed TLS is the implicit default whenever neither
tls.certDir nor tls.acme is configured, and there is no http-only
mode. Remove the setting; configure `tls.certDir` or `tls.acme`
to override the self-signed default.
'')
];
options.services.hyperhive.gateway = {
port = lib.mkOption {
type = lib.types.port;
default = 80;
example = 8080;
description = ''
TCP port the gateway listens on. Default 80 (canonical web
port). nginx inside the container binds <1024 because the
container's init runs as root; if 80 is already taken on the
host (existing nginx, traefik, etc.) override to an unused
port like 8080 or move the conflicting service.
'';
};
upstreamHost = lib.mkOption {
type = lib.types.str;
default = "127.0.0.1";
description = ''
Host the gateway proxies non-static requests to. Defaults to
`127.0.0.1` because the gateway container shares the host
netns, so loopback resolves directly to hive-c0re.
'';
};
upstreamPort = lib.mkOption {
type = lib.types.port;
default = 7000;
description = ''
TCP port the gateway proxies non-static requests to. Defaults
to `7000` (hive-c0re's out-of-the-box dashboard port). Operators
who change `services.hyperhive.c0re.dashboardPort` should set
`upstreamPort` to match kept as a hardcoded default rather
than a cross-reference to keep this module's options eval
independent of c0re's option tree shape.
'';
};
openFirewall = lib.mkOption {
type = lib.types.bool;
default = false;
example = true;
description = ''
Open `port` in the host firewall. Off by default (secure-by-default).
Flip to `true` to expose the gateway to
the operator's browser / external clients required for any
out-of-host reach, since the agents themselves talk to
hive-c0re via the per-agent unix sockets and don't need the
nginx vhost. Leave off when running behind another reverse
proxy (e.g. caddy / traefik on the host) that handles TLS
termination + forwards to `port`.
**Note**: this used to default to `true`. Add
`services.hyperhive.gateway.openFirewall = true;` to your host
config if external reach stopped working after a recent upgrade.
'';
};
localHostsEntry = lib.mkOption {
type = lib.types.bool;
default = false;
example = true;
description = ''
Add an `/etc/hosts` entry mapping `services.hyperhive.domain`
to `127.0.0.1` on the host. Useful for local deployments +
tests where there's no real DNS for `services.hyperhive.domain`
but the operator (or browser-based tests) want to hit
`http://''${services.hyperhive.domain}` to exercise the
gateway shape. Off by default operators running with real
DNS shouldn't have a stale `/etc/hosts` entry sticking
around. Requires `services.hyperhive.domain` to be set.
'';
};
useSelfSigned = lib.mkOption {
type = lib.types.bool;
internal = true;
readOnly = true;
default = cfg.tls.certDir == null && !cfg.tls.acme.enable;
defaultText = lib.literalExpression "tls.certDir == null && !tls.acme.enable";
description = ''
Read-only derived flag: `true` when the gateway serves the
self-signed (hive-CA-signed) leaf i.e. neither `tls.certDir` nor
`tls.acme.enable` is configured. Single source of truth for the
self-signed condition; consumed by the `hive-tls` and `hive-ci`
modules so the derivation isn't duplicated. Internal not meant to
be set by operators (use `tls.certDir` / `tls.acme` to override the
self-signed default).
'';
};
httpsPort = lib.mkOption {
type = lib.types.port;
default = 443;
example = 8443;
description = ''
TCP port for the TLS-terminated vhosts. Default 443. The gateway
always terminates TLS (self-signed is the implicit floor when no
`tls.certDir` / ACME is configured), so this port is always active
alongside the plain-http `port`.
'';
};
tls = {
certDir = lib.mkOption {
type = lib.types.nullOr lib.types.path;
default = null;
example = lib.literalExpression ''"/var/lib/acme/example.com"'';
description = ''
Path to a host directory containing a TLS certificate and
private key for nginx. When set, nginx listens on `httpsPort`
and uses this cert, overriding the self-signed default the
auto-generated hive-CA-signed leaf is skipped entirely.
nginx reads `<certDir>/<tls.certName>` and
`<certDir>/<tls.keyName>` directly it runs on the host, so
the directory needs no bind mount and no copy.
Default filenames (`cert.pem` / `key.pem`) match the output
layout of nixpkgs's `security.acme` module.
Typical ACME setup:
```nix
security.acme.certs."example.com" = { ... };
services.hyperhive.gateway.tls.certDir =
config.security.acme.certs."example.com".directory;
```
When using an external CA cert, other hives can declare this
one in `services.hyperhive.swarm.hives` without
`certFingerprint` the standard CA bundle validates.
Mutual exclusion with `tls.acme.enable` set one or the other,
not both.
'';
};
certName = lib.mkOption {
type = lib.types.str;
default = "cert.pem";
description = ''
Filename of the TLS certificate within `tls.certDir`. Defaults
to `cert.pem` which matches nixpkgs's `security.acme` output.
'';
};
keyName = lib.mkOption {
type = lib.types.str;
default = "key.pem";
description = ''
Filename of the TLS private key within `tls.certDir`. Defaults
to `key.pem` which matches nixpkgs's `security.acme` output.
'';
};
acme = {
enable = lib.mkOption {
type = lib.types.bool;
default = false;
example = true;
description = ''
Let nginx inside the gateway container obtain and renew TLS
certificates automatically via ACME (Let's Encrypt). When
enabled, each vhost calls out to Let's Encrypt using the
HTTP-01 challenge on `port` (default 80) and stores certs
inside the gateway container's persistent state dir.
Requirements:
- `services.hyperhive.domain` must be set and publicly
DNS-resolvable to this host.
- `services.hyperhive.gateway.openFirewall = true` so
Let's Encrypt can reach `/.well-known/acme-challenge/`.
- `tls.acme.email` must be set (ACME account contact).
Mutual exclusion: `tls.certDir` set together with
`tls.acme.enable = true` fails at eval pick one TLS source.
Typical setup:
```nix
services.hyperhive.gateway = {
openFirewall = true;
tls.acme = {
enable = true;
email = "admin@example.com";
};
};
```
After enabling, this hive's entry in `swarm.hives` can omit
`certFingerprint` Let's Encrypt certs are CA-trusted
by default.
'';
};
email = lib.mkOption {
type = lib.types.nullOr lib.types.str;
default = null;
example = "admin@example.com";
description = ''
Email address for the ACME account registration with
Let's Encrypt. Required when `tls.acme.enable = true`.
Let's Encrypt sends expiry warnings to this address.
'';
};
};
};
auth = {
enable = lib.mkEnableOption ''
HTTP basic auth on the gateway using an htpasswd file. When
enabled, every request to the gateway's main vhost requires a
valid username and password. nginx's built-in `auth_basic`
module validates credentials against
`/var/lib/hive-gateway/conf/gateway.htpasswd`. Off by default.
Manage users with `hivectl gateway create-user`, `delete-user`,
and `list-users` see `hivectl gateway --help` for usage.
The htpasswd file is created automatically when auth is enabled;
add at least one user before enabling to avoid locking everyone out.
'';
realm = lib.mkOption {
type = lib.types.strMatching "[^\"$]*";
default = "hyperhive";
example = "my-hive";
description = ''
HTTP Basic auth `realm` value sent in the `WWW-Authenticate`
header when credentials are absent or rejected. Must not
contain `"` or `$` (nginx string metacharacters).
'';
};
};
swaggerUiTheme = lib.mkOption {
type = lib.types.package;
defaultText = lib.literalExpression "hyperhive.packages.\${system}.swagger-ui-theme";
description = ''
Full Swagger UI static dist, hyperhive-themed (see
`nix/packages/swagger-ui-theme.nix`, built on
`nix/packages/swagger-ui-dist.nix`). The gateway serves this
whole tree directly at `/api/docs/` hive-c0re hosts none of
it, only the dynamic `/api/openapi.json` route (proxied
through, unaffected by this option). Override to ship a
custom theme (or the plain vendored dist) without a gateway
rebuild.
'';
};
hsts = {
enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Add `Strict-Transport-Security` to all gateway vhosts.
Disabled by default: HSTS pins HTTPS in the browser's HSTS
preload list; enabling it on a deployment that later loses TLS
will lock browsers out until the max-age expires. Only enable
this when you are certain TLS is permanent.
The gateway always terminates TLS (self-signed floor), so
HSTS is always served over https when enabled but mind the
warning above: HSTS pins https in the browser, so only enable it
when TLS is permanent for this deployment.
'';
};
maxAge = lib.mkOption {
type = lib.types.ints.positive;
default = 31536000;
example = 86400;
description = ''
Value for the `max-age` directive in seconds.
Default: 31536000 (1 year), which is the value required for
HSTS preload list submission. Use a shorter value (e.g. 86400)
while testing so browsers forget the pin quickly.
'';
};
includeSubDomains = lib.mkOption {
type = lib.types.bool;
default = true;
description = ''
Whether to include `includeSubDomains` in the HSTS header.
Only disable this if the gateway host has sub-domains that
intentionally serve plain HTTP.
'';
};
};
};
}