Add haproxy proxy: /metrics returns 200 empty, everything else proxies to SGLang

SGLang now runs on port+1, haproxy binds the original vLLM port.
haproxy serves a stub /metrics endpoint (200, empty body) and
passes all other traffic through to SGLang via raw TCP proxy.

vllm-shim.sh

@@ -5,6 +5,12 @@ set -euo pipefail
 # vLLM -> SGLang shim
 # This script replaces the vllm binary. The k8s production stack
 # calls `vllm serve <model> [flags]`, and we intercept everything.
+#
+# Architecture:
+#   haproxy on the vLLM port (front door)
+#     /metrics → 200 empty response
+#     /*       → proxy to SGLang on port+1
+#   SGLang on port+1 (internal)
 # ============================================================
 
 echo ""
@@ -22,6 +28,20 @@ done
 echo "=========================================="
 echo ""
 
+# Log to file
+LOG_PATH="${VLLM_SHIM_LOG:-/tmp/vllm-shim.log}"
+{
+  echo "$(date -Iseconds) vLLM -> SGLang Shim (shell)"
+  echo "  Invoked as: vllm $*"
+  echo "  All arguments received:"
+  i=1
+  for arg in "$@"; do
+    echo "    [$i] $arg"
+    i=$((i + 1))
+  done
+  echo ""
+} >> "$LOG_PATH"
+
 # Defaults
 HOST="0.0.0.0"
 PORT="8000"
@@ -38,12 +58,60 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-echo "Launching SGLang on ${HOST}:${PORT}"
+# SGLang runs one port higher; haproxy binds the original port
+SGLANG_PORT=$((PORT + 1))
+
+echo "Launching SGLang on ${HOST}:${SGLANG_PORT} (internal)"
+echo "Launching haproxy on ${HOST}:${PORT} (front door, /metrics stub)"
 echo ""
 
-exec python -m sglang.launch_server \
+# Write haproxy config
+HAPROXY_CFG="/tmp/haproxy-shim.cfg"
+cat > "$HAPROXY_CFG" <<EOF
+global
+  log /dev/log local0
+  maxconn 4096
+
+defaults
+  mode http
+  timeout connect 5s
+  timeout client 300s
+  timeout server 300s
+
+frontend proxy
+  bind ${HOST}:${PORT}
+  http-request return status 200 content-type text/plain "" if { path /metrics }
+  default_backend sglang
+
+backend sglang
+  server s1 127.0.0.1:${SGLANG_PORT}
+EOF
+
+echo "haproxy config written to ${HAPROXY_CFG}" >> "$LOG_PATH"
+
+# Start SGLang in the background
+python -m sglang.launch_server \
   --model-path mistralai/Devstral-2-123B-Instruct-2512 \
   --host "$HOST" \
-  --port "$PORT" \
+  --port "$SGLANG_PORT" \
   --tp 8 \
-  --tool-call-parser mistral
+  --tool-call-parser mistral &
+
+SGLANG_PID=$!
+
+# Give SGLang a moment to start before haproxy starts routing
+sleep 2
+
+# Start haproxy in the foreground (this is now PID 1 for the container)
+haproxy -f "$HAPROXY_CFG" &
+
+HAPROXY_PID=$!
+
+echo "SGLang PID: ${SGLANG_PID}, haproxy PID: ${HAPROXY_PID}" >> "$LOG_PATH"
+
+# Wait for whichever dies first — if either goes, we go
+wait -n "$SGLANG_PID" "$HAPROXY_PID"
+EXIT_CODE=$?
+echo "A process exited (code ${EXIT_CODE}), shutting down" >> "$LOG_PATH"
+kill "$SGLANG_PID" "$HAPROXY_PID" 2>/dev/null || true
+exit $EXIT_CODE