vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

split Swap's Ok-tail into a first-class PostSwap DAG node (#2390)

Browse source
This commit is contained in:
damocles 2026-07-16 12:09:15 +02:00 • committed by mara
commit f2ff0deb6b
4 changed files with 126 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

75
hive-c0re/src/job_queue/exec.rs
View file

@ -84,6 +84,7 @@ pub(super) async fn run_node(coord: &Arc<Coordinator>, claim: &Claim) -> Result<
match &claim.kind {
NodeKind::Prebuild { relock } => run_prebuild(coord, claim, &ctx, *relock).await,
NodeKind::Swap => run_swap(coord, claim, &ctx).await,
NodeKind::PostSwap => run_post_swap(coord, claim, &ctx).await,
NodeKind::Provision => run_provision(coord, claim, &ctx).await,
NodeKind::Create => run_create(claim, &ctx).await,
NodeKind::MetaLock { sweep, fanout } => {
@ -192,41 +193,53 @@ async fn run_swap(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Res
ctx.build_log(log_id);
})
.await;
match &result {
Ok(()) => {
if let Some(rev) = crate::auto_update::current_flake_rev(&coord.hyperhive_flake)
&& let Err(e) = std::fs::write(crate::paths::applied_rev_marker(name), rev)
{
tracing::warn!(%name, error = ?e, "write rev marker failed");
}
// The `Rebuilt` manager event fires exactly once per DAG
// from the terminal hook — emitting ok here and letting a
// failed tail `Reconcile` add a contradictory !ok would
// double-report the same rebuild.
ctx.step("forge sync");
// Full forge + matrix sync on every successful rebuild so
// the rebuild path is equivalent to the startup sweep:
// tokens, config-repo mirror, meta access all recover
// without a hive-c0re restart.
crate::forge::sync_agent(name, crate::forge::core_token().as_deref()).await;
crate::matrix::sync_agent_standalone(name).await;
// Wake the agent on its next turn so claude sees a "you
// were rebuilt" hint; rescan so dashboards drop the
// "needs update" chip; lock bump → meta-inputs re-render.
coord.kick_agent(name, "container rebuilt");
coord.rescan_containers_and_emit().await;
crate::dashboard::emit_meta_inputs_snapshot(coord);
}
Err(_) => {
// The `Rebuilt { ok: false }` manager event fires once per
// DAG from the terminal hook (any node may be the one that
// failed); here only refresh the observed state.
coord.rescan_containers_and_emit().await;
}
// On success the Ok-only bookkeeping tail (rev marker, forge/matrix
// sync, kick, rescan, snapshot) runs in the sibling `PostSwap` node,
// which deps `AfterOk(Swap)`. On failure `PostSwap` is cancel-cascaded
// and the tail `Reconcile` (`AfterAny(PostSwap)`) handles recovery; here
// we only refresh the observed state so dashboards reflect the failed
// swap immediately. The `Rebuilt { ok: false }` manager event fires once
// per DAG from the terminal hook (any node may be the one that failed).
if result.is_err() {
coord.rescan_containers_and_emit().await;
}
result.map(|()| NodeOutput::default())
}
/// The post-`Swap` bookkeeping tail, split into its own node for dashboard
/// visibility + retry granularity. Deps `AfterOk(Swap)`, so reaching here
/// means the profile swap succeeded. Store/forge/matrix work only — no nix
/// build (build-slot-exempt); the agent lease taken at `Swap` is still held
/// (the whole chain up to `Reconcile` is one agent's subgraph).
async fn run_post_swap(
coord: &Arc<Coordinator>,
claim: &Claim,
ctx: &Ctx<'_>,
) -> Result<NodeOutput> {
let name = &claim.agent;
if let Some(rev) = crate::auto_update::current_flake_rev(&coord.hyperhive_flake)
&& let Err(e) = std::fs::write(crate::paths::applied_rev_marker(name), rev)
{
tracing::warn!(%name, error = ?e, "write rev marker failed");
}
// The `Rebuilt` manager event fires exactly once per DAG from the
// terminal hook — emitting ok here and letting a failed tail `Reconcile`
// add a contradictory !ok would double-report the same rebuild.
ctx.step("forge sync");
// Full forge + matrix sync on every successful rebuild so the rebuild
// path is equivalent to the startup sweep: tokens, config-repo mirror,
// meta access all recover without a hive-c0re restart.
crate::forge::sync_agent(name, crate::forge::core_token().as_deref()).await;
crate::matrix::sync_agent_standalone(name).await;
// Wake the agent on its next turn so claude sees a "you were rebuilt"
// hint; rescan so dashboards drop the "needs update" chip; lock bump →
// meta-inputs re-render.
coord.kick_agent(name, "container rebuilt");
coord.rescan_containers_and_emit().await;
crate::dashboard::emit_meta_inputs_snapshot(coord);
Ok(NodeOutput::default())
}
/// First-spawn pre-create provisioning: proposed/applied repos, state
/// subvolume, and the meta `sync_agents` registration. Holds the
/// deploy-window gate for the commit so it can't land inside another