Fix Gemma 4 vLLM startup and improve partial-provisioning UX

- provisioning.rb: auto-install pytest before pre_start_cmd to fix missing
dependency in nightly vLLM images that crashes EngineCore on cupy import
- cli.rb: relax active_config_loaders/vm1_alive? to match by vm_id+public_ip
instead of requiring status==ACTIVE, so watch/status/test work on VMs
that were interrupted mid-provisioning
- vm_lifecycle.rb: persist API status/vm_state back to state file during
status calls; add 'Provisioning: incomplete' notice when provisioned_at
is missing
- provisioning_orchestrator.rb: add wait_for_ssh polling before
ensure_trusted_host to fix race between SSH daemon readiness and keyscan

1 files changed, 7 insertions, 0 deletions

diff --git a/lib/hyperstack/vm_lifecycle.rb b/lib/hyperstack/vm_lifecycle.rb
index cc52880..22fbe62 100644
--- a/lib/hyperstack/vm_lifecycle.rb
+++ b/lib/hyperstack/vm_lifecycle.rb
@@ -110,9 +110,16 @@ module HyperstackVM
         info "Tracked VM: #{state['vm_id']} #{vm['name']}"
         info "Status: #{vm['status']} / #{vm['vm_state']}"
         info "Public IP: #{connect_host_for(vm) || 'none'}"
+        unless state['provisioned_at']
+          info "Provisioning: incomplete — run `create` to resume"
+        end
         info "Service mode: #{service_summary(vllm: vllm_e, ollama: ollama_e)}"
         info "Active model: #{state['vllm_model'] || @config.vllm_model}" if vllm_e
         info "Missing firewall rules: #{missing.empty? ? 'none' : missing.size}"
+        state['status'] = vm['status']
+        state['vm_state'] = vm['vm_state']
+        state['public_ip'] = connect_host_for(vm) || state['public_ip']
+        @state_store.save(state)
       rescue Error => e
         warn_out "Unable to load VM #{state['vm_id']}: #{e.message}"
         return state&.dig('public_ip')