Benchmark Dirk Qwen3.8 against production

experiments/dirk-qwen38/wait-ready.sh

@@ -3,6 +3,11 @@ set -Eeuo pipefail
 
 deadline=$((SECONDS + ${READY_TIMEOUT:-900}))
 until curl -fsS --max-time 3 http://127.0.0.1:5004/health >/dev/null; do
+  state=$(docker inspect -f '{{.State.Running}}' mike-ai-llama-dirk-test 2>/dev/null || true)
+  if [[ $state != true ]]; then
+    docker logs --tail 100 mike-ai-llama-dirk-test >&2 || true
+    exit 1
+  fi
   if ((SECONDS >= deadline)); then
     docker logs --tail 100 mike-ai-llama-dirk-test >&2 || true
     exit 1
@@ -11,4 +16,3 @@ until curl -fsS --max-time 3 http://127.0.0.1:5004/health >/dev/null; do
 done
 curl -fsS http://127.0.0.1:5004/props
 printf '\nDirk test server is ready.\n'
-