nix(ci): trust the hive CA in the runner's Node actions (self-signed TLS)

With self-signed TLS the gateway/forge serve a hive-CA-signed leaf and
forgejo's ROOT_URL is https://forge.<domain>. The CI runner's Node-based
actions (e.g. upload-artifact) POST to the ROOT_URL-derived artifact
endpoint and fail with "unable to verify the first certificate": Node uses
its own bundled CA bundle, not the system store, so it rejects the
self-signed chain. checkout etc. are fine — they hit the localhost http
registration URL.

Bind-mount the public hive CA cert (only ca.pem — never the hive-tls state
dir, which holds the CA + leaf private keys) into the hive-ci container and
set NODE_EXTRA_CA_CERTS on the runner service so every Node action trusts
it, hive-wide. Order container@hive-ci after the host hive-tls-ca service so
the cert exists before the bind-mount is set up. All gated on self-signed
mode; with an operator cert / ACME the public CA already validates and the
mount + env var are absent.

Eval-proven: self-signed → /run/hive-ca/ca.pem bind-mount (from
/var/lib/hive-tls/ca.pem), NODE_EXTRA_CA_CERTS=/run/hive-ca/ca.pem, and
container@hive-ci ordered after hive-tls-ca.service; certDir → all absent.
This commit is contained in:
atlas 2026-06-18 00:08:45 +02:00
commit 9f03cf31ba

View file

@ -7,6 +7,18 @@
let
cfg = config.services.hyperhive.forge.ci;
forgeCfg = config.services.hyperhive.forge;
gatewayCfg = config.services.hyperhive.gateway;
tlsCfg = config.services.hyperhive.tls;
# Self-signed TLS is the gateway default (no operator cert / ACME). When
# active, forgejo's ROOT_URL is `https://forge.<domain>` and the leaf is
# signed by the host hive CA — so the runner's Node-based actions (e.g.
# `upload-artifact`, which POSTs to the ROOT_URL-derived artifact endpoint)
# reject the chain, since Node trusts only its bundled CA bundle, not the
# system store. Trust the hive CA explicitly via NODE_EXTRA_CA_CERTS below.
useSelfSigned = gatewayCfg.tls.certDir == null && !gatewayCfg.tls.acme.enable;
caHostPath = "${tlsCfg.stateDir}/ca.pem";
caContainerPath = "/run/hive-ca/ca.pem";
# hive-c0re writes its own admin token here on first forge startup.
# The token has read:admin + write:admin scopes — sufficient to call
@ -315,6 +327,15 @@ in
};
};
# Self-signed mode: the CA cert the bind-mount above sources is
# generated by the host `hive-tls-ca` service. Order the container after
# it so the bind source exists before nspawn sets the mount up (a
# condition-skipped/late CA would otherwise fail the container start).
systemd.services."container@hive-ci" = lib.mkIf useSelfSigned {
after = [ "hive-tls-ca.service" ];
requires = [ "hive-tls-ca.service" ];
};
containers.hive-ci = {
autoStart = true;
ephemeral = false;
@ -329,6 +350,18 @@ in
hostPath = "/run/hive-ci/runner-token";
isReadOnly = true;
};
}
# Self-signed mode: bind ONLY the public hive CA cert (never the
# `hive-tls` state dir — it holds the CA + leaf private keys) so the
# runner's Node actions can trust the gateway/forge self-signed leaf
# (see NODE_EXTRA_CA_CERTS in the container config). Source generated
# by the host `hive-tls-ca` service; the container@hive-ci ordering
# below guarantees it exists before this mount is set up.
// lib.optionalAttrs useSelfSigned {
${caContainerPath} = {
hostPath = caHostPath;
isReadOnly = true;
};
};
config =
@ -408,6 +441,19 @@ in
systemd.services."gitea-runner-hive" = {
path = [ pkgs.nix ];
# Trust the hive CA in Node-based actions. With self-signed TLS,
# forgejo's ROOT_URL is `https://forge.<domain>` (CA-signed leaf),
# so actions like `upload-artifact` — whose Node HTTP client uses
# Node's *bundled* CA bundle, not the system store — reject the
# chain with "unable to verify the first certificate". Pointing
# NODE_EXTRA_CA_CERTS at the bind-mounted CA adds it to Node's
# roots for every action, hive-wide. Inherited by the job
# processes the runner spawns (host execution mode). Only set in
# self-signed mode; with an operator cert / ACME the public CA
# already validates and the bind-mount is absent.
environment = lib.mkIf useSelfSigned {
NODE_EXTRA_CA_CERTS = caContainerPath;
};
# Gate runner start (and therefore job registration/claiming) on
# the in-container nix daemon being reachable. After a hive-ci
# restart the runner re-registers and immediately claims any