Heartbeat-first dispatch: retire WoL-as-default, add WaitingReboot
CI / Lint + build + test (push) Has been cancelled

Every supported host runs vetting-reporter in-OS and heartbeats every
30s. WoL was never the thing that started vetting — the heartbeat
response's reboot_for_vetting command was. Firing WoL first only
crowded the run log with misleading diagnostics when the real failure
mode is "reporter isn't installed."

- StartRun 409s if the host hasn't heartbeated within 60s, pointing
  the operator at /register/quick.sh.
- Dispatcher re-checks LastSeenAt at dispatch time (run may sit in
  Queued long enough for the host to go offline); stale hosts mark
  the run Failed with failed_stage=dispatch instead of looping.
- New StateWaitingReboot + TriggerRebootCommanded capture the actual
  semantics. StateWaitingWoL kept as the hook point for a future
  manual-override button.
- Tile disables the Start button with a quick.sh tooltip when the
  host is offline, matching the server-side 409.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-04-18 01:10:34 -04:00
parent c9927ca2bf
commit d0bfae14c8
17 changed files with 632 additions and 155 deletions
@@ -40,6 +40,40 @@ func TestNextForOverride(t *testing.T) {
}
}
// TestTriggerRebootCommanded exercises the new heartbeat-first trigger:
// Queued → WaitingReboot, and any other current state is an error.
func TestTriggerRebootCommanded(t *testing.T) {
got, err := orchestrator.Next(model.StateQueued, orchestrator.TriggerRebootCommanded)
if err != nil {
t.Fatalf("Queued + RebootCommanded: %v", err)
}
if got != model.StateWaitingReboot {
t.Fatalf("got %q, want %q", got, model.StateWaitingReboot)
}
for _, bad := range []model.RunState{
model.StateRegistered, model.StateBooting, model.StateInventoryCheck, model.StateCompleted,
} {
if _, err := orchestrator.Next(bad, orchestrator.TriggerRebootCommanded); err == nil {
t.Fatalf("RebootCommanded from %q: expected error", bad)
}
}
}
// TestTriggerAgentClaimedFromWaitingReboot: the agent's /claim must
// advance the run out of WaitingReboot (new happy path) AND out of
// legacy WaitingWoL, otherwise live boots wouldn't be recognised.
func TestTriggerAgentClaimedFromWaitingReboot(t *testing.T) {
for _, from := range []model.RunState{model.StateWaitingReboot, model.StateWaitingWoL, model.StateBooting} {
got, err := orchestrator.Next(from, orchestrator.TriggerAgentClaimed)
if err != nil {
t.Fatalf("AgentClaimed from %q: %v", from, err)
}
if got != model.StateInventoryCheck {
t.Fatalf("AgentClaimed from %q = %q, want InventoryCheck", from, got)
}
}
}
func TestNextStageWalk(t *testing.T) {
// Walking StageCompleted from each stage should land on the next
// one in the canonical order, and from Reporting onto Completed.