feat(#2484): unify in-DAG growth on append_subgraph (drop append_node)

append_subgraph is the multi-node/multi-agent generalisation of the
single-node append_node, so the two in-DAG-growth channels collapse to
one: the Reconcile planner now emits its mechanical Start/Stop as a
single-node append_subgraph rooted on the reconcile node (stamping
claim.agent on the NodeSpec, which append_node inherited implicitly).

Removes NodeOutput.append_nodes + its scheduler drain loop and
JobQueue::append_node. No behaviour change — a channel unification.
This commit is contained in:
atlas 2026-07-15 20:21:39 +02:00
commit b87eac0a61
3 changed files with 48 additions and 104 deletions

View file

@ -27,24 +27,19 @@ pub const GRACEFUL_STOP_TIMEOUT: std::time::Duration = std::time::Duration::from
/// success.
#[derive(Debug, Default)]
pub struct NodeOutput {
/// Mechanical sub-step nodes to append into *this same* DAG at
/// runtime, each depending `AfterOk` on the emitting node — e.g. a
/// `Reconcile` planner emitting a `Start` / `Stop`. Keeps the sub-step a
/// first-class node in the same DAG so the lease-window transient is held
/// across it. The scheduler applies these *before* the emitting node's
/// completion so the DAG never rolls terminal with the appended work
/// still pending.
pub append_nodes: Vec<NodeKind>,
/// Whole per-agent *subgraphs* to append into *this same* DAG at
/// runtime — the multi-node generalisation of `append_nodes`. Each
/// inner `Vec<NodeSpec>` is one independent subgraph whose `deps` are
/// local (0-based within that subgraph); the scheduler appends each via
/// runtime — the single in-DAG-growth channel. Each inner
/// `Vec<NodeSpec>` is one independent subgraph whose `deps` are local
/// (0-based within that subgraph); the scheduler appends each via
/// [`JobQueue::append_subgraph`], which rebases the deps onto the DAG's
/// node-id space and roots the subgraph on the emitting node. Both
/// `MetaLock` flavours use this to grow one rebuild subgraph per agent
/// into their own DAG (the startup sweep's stale agents; the meta-update
/// cascade's affected agents) instead of fanning out child DAGs. Same
/// before-completion ordering as `append_nodes`.
/// node-id space and roots the subgraph on the emitting node. Used both
/// for the multi-node case (`MetaLock` growing one rebuild subgraph per
/// agent — the startup sweep's stale agents, the meta-update cascade's
/// affected agents) and the single-node case (a `Reconcile` planner
/// emitting its mechanical `Start` / `Stop` as a one-node subgraph). The
/// scheduler applies these *before* the emitting node's completion so the
/// DAG never rolls terminal with the appended work still pending — keeping
/// the lease-window transient held across the sub-step.
pub append_subgraph: Vec<Vec<NodeSpec>>,
}
@ -293,10 +288,7 @@ async fn run_meta_lock(
.iter()
.map(|agent| super::templates::rebuild_nodes(agent, true, 0))
.collect();
return Ok(NodeOutput {
append_subgraph,
..Default::default()
});
return Ok(NodeOutput { append_subgraph });
}
let _progress = coord.meta_update_guard();
ctx.step("nix flake update");
@ -320,35 +312,34 @@ async fn run_meta_lock(
.iter()
.map(|agent| super::templates::rebuild_nodes(agent, false, 0))
.collect();
Ok(NodeOutput {
append_subgraph,
..Default::default()
})
Ok(NodeOutput { append_subgraph })
}
/// Idempotent power-converge *planner*: compare `wanted` (durable
/// intent) against observed state and, when they diverge, fan the
/// mechanical `Start` / `Stop` out as a first-class node appended to
/// *this* DAG (`NodeOutput::append_nodes`). Does no container work
/// itself — the sub-step becomes visible in the DAG and the
/// lease-window transient (or the sub-step's own node-local guard)
/// rides across it.
/// *this* DAG (a single-node `NodeOutput::append_subgraph` rooted on
/// this node). Does no container work itself — the sub-step becomes
/// visible in the DAG and the lease-window transient (or the sub-step's
/// own node-local guard) rides across it.
async fn run_reconcile(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
let name = &claim.agent;
let running = crate::lifecycle::is_running(name).await;
let wanted = coord.power.get_or_seed(name, running)?;
let append_nodes = match reconcile_action(wanted, running) {
ReconcileAction::Start => vec![NodeKind::Start],
ReconcileAction::Stop => vec![NodeKind::Stop],
// One node targeting this agent, rooted on this reconcile node. The old
// `append_node` inherited the emitter's agent implicitly; `append_subgraph`
// carries it on the `NodeSpec`, so stamp `claim.agent` explicitly (same
// effect, one in-DAG-growth channel instead of two).
let sub = |kind| vec![vec![super::templates::node(name, kind, Vec::new())]];
let append_subgraph = match reconcile_action(wanted, running) {
ReconcileAction::Start => sub(NodeKind::Start),
ReconcileAction::Stop => sub(NodeKind::Stop),
ReconcileAction::Noop => {
tracing::debug!(%name, wanted = wanted.as_str(), running, "reconcile: noop");
Vec::new()
}
};
Ok(NodeOutput {
append_nodes,
..Default::default()
})
Ok(NodeOutput { append_subgraph })
}
/// Mechanical container start — the sub-step a `Reconcile` planner fans