hub v0.59.0: Direction-2a agent-plane immediate-sync poke sender + ep0 felhom-poke surface

- internal/poke: pinned-host-key SSH poke sender (wgsync sibling) + fire-and-forget Notifier (PokeHost/PokeAllHosts). Poke refuses non-WG targets pre-dial; contentless via ep0 forced command to the box WG /32:51822. - wiring: Server.SetPoke; applyPBSDR pokes the host after each descriptor gen-bump; handleSetArtifacts (MinAgent floor) pokes all hosts. main.go env POKE_SSH_KEY_FILE (reuses peersync endpoint/hostkey). - scripts/felhom-poke.sh (non-root forced command) + offsite-endpoint.md §11; manifests/hub.yaml Secret/agent-poke + POKE_SSH_KEY_FILE (image tag bump follows the build).
2026-07-16 22:48:15 +02:00
parent bdb65a80e8
commit eb227486d0
11 changed files with 567 additions and 0 deletions
@@ -0,0 +1,100 @@
+package poke
+
+import (
+	"context"
+	"log"
+	"time"
+
+	"gitea.dooplex.hu/admin/felhom-hub/internal/store"
+)
+
+// peerStore is the WG-peer lookup seam (satisfied by *store.Store; tests fake it).
+type peerStore interface {
+	GetWGPeerForHost(hostID string) (*store.WGPeer, error)
+	ListWGPeers() ([]store.WGPeer, error)
+}
+
+// pokeSender is the SSH send seam (satisfied by *Client; tests fake it).
+type pokeSender interface {
+	Poke(ctx context.Context, boxWGIP string) error
+}
+
+// Notifier turns an operator-intent event (a host id, or "all hosts") into fire-and-forget pokes.
+// Every public method returns immediately and does the SSH work on a detached goroutine, so a poke
+// NEVER blocks or fails the hub save that triggered it — a lost poke is harmless (the 15-min cycle
+// reconciles). nil *Notifier is a safe no-op (poke disabled / not configured).
+type Notifier struct {
+	store   peerStore
+	client  pokeSender
+	timeout time.Duration
+	logger  *log.Logger
+}
+
+// NewNotifier builds a notifier. timeout bounds one poke (default 10s).
+func NewNotifier(st peerStore, client pokeSender, logger *log.Logger) *Notifier {
+	if logger == nil {
+		logger = log.Default()
+	}
+	return &Notifier{store: st, client: client, timeout: 10 * time.Second, logger: logger}
+}
+
+// PokeHost fires a poke to one host's box (async, fire-and-forget). Safe on a nil receiver.
+func (n *Notifier) PokeHost(hostID string) {
+	if n == nil {
+		return
+	}
+	go func() {
+		if err := n.pokeHost(context.Background(), hostID); err != nil {
+			n.logger.Printf("[INFO] poke: host %s not nudged (%v) — the 15-min cycle still reconciles", hostID, err)
+		}
+	}()
+}
+
+// PokeAllHosts fires a poke to EVERY host with a WG peer (async, fire-and-forget). Used by a
+// fleet-wide agent-plane change (e.g. a MinAgent floor). Safe on a nil receiver.
+func (n *Notifier) PokeAllHosts() {
+	if n == nil {
+		return
+	}
+	go func() {
+		peers, err := n.store.ListWGPeers()
+		if err != nil {
+			n.logger.Printf("[INFO] poke: fleet nudge skipped (peer list: %v) — the 15-min cycle still reconciles", err)
+			return
+		}
+		nudged := 0
+		for _, p := range peers {
+			if p.HostID == "" || p.AssignedIP == "" {
+				continue
+			}
+			ctx, cancel := context.WithTimeout(context.Background(), n.timeout)
+			if err := n.client.Poke(ctx, p.AssignedIP); err != nil {
+				n.logger.Printf("[INFO] poke: host %s (%s) not nudged (%v)", p.HostID, p.AssignedIP, err)
+			} else {
+				nudged++
+			}
+			cancel()
+		}
+		n.logger.Printf("[INFO] poke: fleet nudge sent to %d/%d WG peers", nudged, len(peers))
+	}()
+}
+
+// pokeHost is the synchronous body (test seam). Resolves the host's WG /32 and sends one poke.
+func (n *Notifier) pokeHost(ctx context.Context, hostID string) error {
+	peer, err := n.store.GetWGPeerForHost(hostID)
+	if err != nil {
+		return err
+	}
+	if peer == nil || peer.AssignedIP == "" {
+		return errNoPeer
+	}
+	tctx, cancel := context.WithTimeout(ctx, n.timeout)
+	defer cancel()
+	return n.client.Poke(tctx, peer.AssignedIP)
+}
+
+type pokeErr string
+
+func (e pokeErr) Error() string { return string(e) }
+
+const errNoPeer = pokeErr("host has no WG peer")