rework(#2072): seed mirrors in c0re startup, not a host-side oneshot

Per mara: the mirror seeding belongs in hive-c0re's forge provisioning
sweep, where the core admin token + org-ensure already live — not a parallel
host-side nix oneshot.

- forge.rs: ensure_mirrors() reads HYPERHIVE_FORGE_MIRRORS (JSON list of
  {upstream,dest}), ensures each dest org (reuse ensure_org) + creates the
  pull-mirror via the migrate API (reuse forge_http, serde_json::json! body,
  409/existing = success). Called in ensure_all() right after the SEEDED_ORGS
  loop (token in scope, warn-and-continue like the other ensure_* steps).
- hive-forge.nix: forward effectiveMirrors to c0re via
  systemd.services.hive-c0re.environment.HYPERHIVE_FORGE_MIRRORS; drop the
  forgejo-seed-mirrors.service + its script + the host-side core-token read.
  Keep the forge.mirrors option, DEFAULT_ACTIONS_URL=self (CI-gated), and the
  dest-shape / no-c0re-namespace-collision assertions.

Verified locally: nix parse + treefmt (incl rustfmt) clean; serde/serde_json
patterns mirror dashboard.rs. cargo build runs in CI (no cc in my container).
This commit is contained in:
atlas 2026-06-29 00:10:15 +02:00 committed by mara
commit 53df2c9598
2 changed files with 100 additions and 101 deletions

View file

@ -913,6 +913,94 @@ async fn ensure_org(name: &str, admin_token: &str) -> Result<()> {
}
}
/// One operator-declared pull-mirror, forwarded from the nix
/// `services.hyperhive.forge.mirrors` option as JSON in
/// `HYPERHIVE_FORGE_MIRRORS`.
#[derive(serde::Deserialize)]
struct Mirror {
/// Upstream clone URL to mirror from (e.g. `https://github.com/actions/checkout`).
upstream: String,
/// Local `<owner>/<repo>` the mirror is created at.
dest: String,
}
/// Ensure each `HYPERHIVE_FORGE_MIRRORS` entry exists as a real Forgejo
/// pull-mirror. The env carries the JSON-encoded nix `forge.mirrors` list
/// (plus the CI-auto `actions/checkout` entry). Absent/empty env = no-op.
/// Per-mirror failures warn and continue — never abort the startup sweep.
async fn ensure_mirrors(admin_token: &str) {
let raw = match std::env::var("HYPERHIVE_FORGE_MIRRORS") {
Ok(s) if !s.trim().is_empty() => s,
_ => return,
};
let mirrors: Vec<Mirror> = match serde_json::from_str(&raw) {
Ok(m) => m,
Err(e) => {
tracing::warn!(error = ?e, "forge: HYPERHIVE_FORGE_MIRRORS is not valid JSON; skipping mirror seed");
return;
}
};
for m in mirrors {
let Some((owner, repo)) = m.dest.split_once('/') else {
tracing::warn!(dest = %m.dest, "forge: mirror dest is not <owner>/<repo>; skipping");
continue;
};
// Create the dest org first (idempotent); the mirror can't land
// without its owner existing.
if let Err(e) = ensure_org(owner, admin_token).await {
tracing::warn!(%owner, error = ?e, "forge: ensure_org for mirror failed");
continue;
}
if let Err(e) = ensure_mirror_repo(&m.upstream, owner, repo, admin_token).await {
tracing::warn!(dest = %m.dest, error = ?e, "forge: ensure_mirror_repo failed");
}
}
}
/// Create `owner/repo` as a pull-mirror of `upstream` via the migrate API.
/// Idempotent: a cheap existence check skips an already-seeded mirror (it
/// persists in the non-ephemeral forge state across reboots), and a
/// 409/422 from migrate is also treated as success.
async fn ensure_mirror_repo(
upstream: &str,
owner: &str,
repo: &str,
admin_token: &str,
) -> Result<()> {
let get_url = format!("{FORGE_HTTP}/api/v1/repos/{owner}/{repo}");
let (status, _) = forge_http(reqwest::Method::GET, &get_url, admin_token, "").await?;
if status.is_success() {
tracing::debug!(%owner, %repo, "forge: pull-mirror already present");
return Ok(());
}
// serde_json::json! → the upstream URL is escaped safely (no string
// interpolation into the JSON body).
let body = serde_json::json!({
"clone_addr": upstream,
"repo_owner": owner,
"repo_name": repo,
"mirror": true,
"service": "git",
"private": false,
})
.to_string();
let url = format!("{FORGE_HTTP}/api/v1/repos/migrate");
let (status, text) = forge_http(reqwest::Method::POST, &url, admin_token, &body).await?;
match status.as_u16() {
201 => {
tracing::info!(%owner, %repo, %upstream, "forge: created pull-mirror");
Ok(())
}
409 | 422 => {
tracing::debug!(%owner, %repo, "forge: pull-mirror already exists");
Ok(())
}
other => {
anyhow::bail!("POST /api/v1/repos/migrate {owner}/{repo} returned HTTP {other}: {text}")
}
}
}
/// Whether `ns` is a hive-managed Forgejo namespace that agent-initiated
/// repo creation must never target — `internal` (operator-curated
/// shared content) + `agent-configs` / `core` (hive-c0re-internal). The
@ -1141,6 +1229,11 @@ pub async fn ensure_all() {
tracing::warn!(%org, error = ?e, "forge: ensure_org failed");
}
}
// Seed the operator-declared pull-mirrors (nix `forge.mirrors` +
// the CI-auto `actions/checkout`, forwarded via the
// `HYPERHIVE_FORGE_MIRRORS` env). Each ensures its own dest org, so
// this is independent of the SEEDED_ORGS loop above.
ensure_mirrors(token).await;
// Provision the operator merge-gate team (empty) inside the agents
// org so branch protection can reference it before anyone joins
//. The operator adds herself as a member out-of-band.

View file

@ -53,86 +53,6 @@ let
++ lib.optional (
ciEnabled && !(lib.any (m: m.dest == actionCheckoutMirror.dest) cfg.mirrors)
) actionCheckoutMirror;
# Host-side core admin token hive-c0re mints after provisioning the forge
# admin (same file hive-ci-prefetch reads). Root-only; never enters a
# container — so the mirror seed runs host-side, exactly like
# hive-ci-prefetch, rather than minting a second token in-container.
coreTokenPath = "/var/lib/hyperhive/forge-core-token";
# Idempotently create each `effectiveMirrors` entry as a real Forgejo
# pull-mirror via the migrate API. Host-side: only talks to the forge on
# loopback (forgejo itself does the upstream clone, so the upstream-DNS
# dependency lives in the container + is off the CI critical path).
# Modelled on hive-ci-prefetch's wait-for-core-token loop.
seedMirrorsScript = pkgs.writeShellScript "forgejo-seed-mirrors" ''
set -uo pipefail
FORGE_URL="http://127.0.0.1:${toString cfg.httpPort}"
CORE_TOKEN=""
for i in $(seq 1 60); do
if [ -f "${coreTokenPath}" ]; then CORE_TOKEN=$(cat "${coreTokenPath}"); break; fi
echo "forgejo-seed-mirrors: waiting for core token ($i/60)..." >&2
sleep 1
done
if [ -z "''${CORE_TOKEN:-}" ]; then
echo "forgejo-seed-mirrors: core token absent after 60s cannot seed mirrors" >&2
exit 1
fi
AUTH="Authorization: token $CORE_TOKEN"
rc=0
seed_one() {
upstream="$1"; owner="$2"; repo="$3"
# Ensure the dest org (idempotent: 201 created / 422 already exists).
org_body=$(${pkgs.jq}/bin/jq -nc --arg u "$owner" '{ username: $u }')
ohttp=$(${pkgs.curl}/bin/curl -s -o /dev/null -w '%{http_code}' -X POST \
-H "$AUTH" -H 'Content-Type: application/json' \
"$FORGE_URL/api/v1/orgs" -d "$org_body" || echo 000)
case "$ohttp" in
201 | 422) ;;
*) echo "forgejo-seed-mirrors: ensure org '$owner' returned HTTP $ohttp" >&2 ;;
esac
# Skip if the repo already exists (the mirror persists across reboots
# in the non-ephemeral forge state, so this no-ops on every reboot
# after the first).
rhttp=$(${pkgs.curl}/bin/curl -s -o /dev/null -w '%{http_code}' \
-H "$AUTH" "$FORGE_URL/api/v1/repos/$owner/$repo" || echo 000)
if [ "$rhttp" = 200 ]; then
echo "forgejo-seed-mirrors: $owner/$repo already present skipping" >&2
return 0
fi
# Create the pull-mirror. service=git → generic git clone of
# clone_addr (no upstream API token needed); mirror=true → forgejo
# keeps it re-syncing on its mirror interval.
mig_body=$(${pkgs.jq}/bin/jq -nc \
--arg c "$upstream" --arg o "$owner" --arg r "$repo" \
'{ clone_addr: $c, repo_owner: $o, repo_name: $r, mirror: true, service: "git", private: false }')
resp=$(${pkgs.curl}/bin/curl -s -w $'\n%{http_code}' -X POST \
-H "$AUTH" -H 'Content-Type: application/json' \
"$FORGE_URL/api/v1/repos/migrate" \
-d "$mig_body" \
|| printf '\n000')
mhttp=$(printf '%s' "$resp" | tail -n1)
case "$mhttp" in
2*) echo "forgejo-seed-mirrors: created pull-mirror $owner/$repo from $upstream" >&2 ;;
*)
echo "forgejo-seed-mirrors: migrate $owner/$repo failed HTTP $mhttp: $(printf '%s' "$resp" | sed '$d')" >&2
rc=1
;;
esac
}
${lib.concatMapStringsSep "\n" (
m:
let
parts = lib.splitString "/" m.dest;
in
"seed_one ${lib.escapeShellArg m.upstream} ${lib.escapeShellArg (builtins.elemAt parts 0)} ${lib.escapeShellArg (builtins.elemAt parts 1)}"
) effectiveMirrors}
exit $rc
'';
in
{
# Private Forgejo in a `hive-forge` nixos-container, shared host
@ -591,26 +511,12 @@ in
];
};
# Seed the configured pull-mirrors once the forge + core token are up.
# Host-side (the core admin token never enters a container) and modelled
# on hive-ci-prefetch. partOf the forge container so it re-runs (and
# re-ensures, idempotently) on every forge (re)start. Only present when
# there's something to seed.
systemd.services.forgejo-seed-mirrors = lib.mkIf (effectiveMirrors != [ ]) {
description = "Seed Forgejo pull-mirrors (host-side)";
after = [
"hive-c0re.service"
"container@hive-forge.service"
];
wants = [ "container@hive-forge.service" ];
wantedBy = [ "multi-user.target" ];
partOf = [ "container@hive-forge.service" ];
serviceConfig = {
Type = "oneshot";
RemainAfterExit = true;
ExecStart = seedMirrorsScript;
SyslogIdentifier = "forgejo-seed-mirrors";
};
};
# Forward the declared pull-mirrors to hive-c0re, which seeds them in
# its forge provisioning sweep (`forge.rs::ensure_mirrors`, alongside
# the SEEDED_ORGS ensure). c0re already holds the core admin token and
# ensures the orgs there, so the seeding lives in one place rather than
# a parallel host-side unit. JSON-encoded list of { upstream, dest };
# `[]` when nothing to seed (c0re no-ops).
systemd.services.hive-c0re.environment.HYPERHIVE_FORGE_MIRRORS = builtins.toJSON effectiveMirrors;
};
}