From 0b9cd40f79f543a3845ba45cc3514fa47d33cd1c Mon Sep 17 00:00:00 2001 From: Paul Buetow Date: Mon, 25 May 2026 22:23:05 +0300 Subject: 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 --- lib/hyperstack/provisioning_orchestrator.rb | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'lib/hyperstack/provisioning_orchestrator.rb') diff --git a/lib/hyperstack/provisioning_orchestrator.rb b/lib/hyperstack/provisioning_orchestrator.rb index 7dbb10e..b9f9e3d 100644 --- a/lib/hyperstack/provisioning_orchestrator.rb +++ b/lib/hyperstack/provisioning_orchestrator.rb @@ -29,6 +29,7 @@ module HyperstackVM state['security_rules'] = Array(vm['security_rules']).map { |r| normalize_rule(r) } @state_store.save(state) + wait_for_ssh(state['public_ip']) @ssh_runner.ensure_trusted_host(state['public_ip']) if @config.guest_bootstrap_enabled? && state['bootstrapped_at'].nil? @@ -78,6 +79,12 @@ module HyperstackVM state end + def wait_for_ssh(host) + with_polling("SSH on #{host}:#{@config.ssh_port} to become reachable", timeout: 300) do + @ssh_runner.tcp_open?(host, @config.ssh_port) + end + end + def wait_for_ready(vm_id) with_polling("VM #{vm_id} to become ready for firewall updates") do vm = @client.get_vm(vm_id) -- cgit v1.2.3