Health of every node in the fleet, grouped by cluster: reachability, getHealth, version, slot lag vs the cluster reference RPC, and delinquency/stake for voting validators.

Full probe result for a single node by name, including its cluster's reference data.

Compare each node's solana-core version against its cluster's reference RPC version. Drift does not always mean outdated (the reference may itself lag a release), but it flags what to look at.

Voting health of a validator that a plain RPC check can't show: in the vote set, voting vs delinquent, epoch credits, last vote, root slot, commission, activated stake, identity SOL balance (+ low-balance warning; a validator pays vote fees every slot), catch-up, and the next leader window. Read-only.

Upcoming leader slots for a validator and whether it's safe to restart now (no leader slot within min_window_minutes). Read-only; helps plan restarts/upgrades without skipping your own slots.

Read-only readiness check of the whole fleet: per-node SSH/service/ binary/disk/RPC, per-builder cores/RAM/disk/toolchain, and DNS credential presence. Returns pass/warn/fail per check; ok is true only when nothing failed. Changes nothing.

Dry-run plan for upgrading one node in place to target_version, using artifacts from the cluster's dedicated builder. Read-only: produces the ordered steps and policy preflight, changes nothing.

Restart a node and wait for catch-up. RPC nodes cycle via systemctl; voting validators use a leader-aware safe-exit so they don't skip slots.

Defaults to a dry-run that returns the plan and policy preflight. Pass confirm=true to actually cycle the service; gated by policy and recorded in the audit log. Never touches keys.

Install the build toolchain + deps (Rust, protoc, libclang-dev, ...) on a builder host so it can compile agave from source. Dry-run by default; confirm=true runs it (idempotent) and records to the audit log. Run once per builder before the first upgrade/provision.

Bring up a bare host into a serving node: preflight, user, system tuning, disks, software install (via the builder), systemd unit, key check, start + catch-up.

Defaults to a dry-run plan. confirm=true executes, gated by preflight
and policy and recorded in the audit log. Disks marked format must be
listed in format_devices to be wiped; solfleet never creates keys.
catchup_timeout_s bounds the wait for the fresh node to catch up
(default 1800; raise it for slow snapshot downloads).

Upgrade one node in place to target_version: build on the cluster's builder, distribute + checksum-verify the agave + geyser artifact set, swap atomically, cycle (leader-aware for validators), and verify.

Defaults to a dry-run plan. confirm=true executes, gated by policy
(allowed versions, disk floor) and recorded in the audit log.

Current members of each managed DNS pool, mapped back to node names. Read-only.

Manually pull a node from its DNS pool(s). Dry-run unless confirm=true. Refuses to empty a pool (last-member protection). Audited.

Manually add a node back to its DNS pool(s). Dry-run unless confirm=true. Audited.

Recent audit entries (every dry-run and execute), newest first. Optionally filtered to one node.