fix: install tenacity, proxy health server handles OpenClaw crashes gracefully

Dockerfile

@@ -6,7 +6,7 @@ RUN apt-get update && apt-get install -y \
 
 RUN curl -fsSL https://ollama.com/install.sh | sh
 
-RUN pip install --no-cache-dir openclaw huggingface_hub
+RUN pip install --no-cache-dir tenacity openclaw huggingface_hub
 
 RUN printf 'server {\n    listen 7860;\n    location / {\n        proxy_pass http://127.0.0.1:8080;\n        proxy_http_version 1.1;\n        proxy_set_header Upgrade $http_upgrade;\n        proxy_set_header Connection "upgrade";\n        proxy_set_header Host $host;\n    }\n}\n' > /etc/nginx/sites-available/default
 

start.sh

@@ -88,14 +88,41 @@ CRONEOF
 chmod +x /tmp/backup.sh
 echo "*/15 * * * * /tmp/backup.sh" | crontab -
 
+# Health server stays alive FOREVER — we proxy to OpenClaw when it's up
 python3 -c "
-from http.server import HTTPServer, BaseHTTPRequestHandler
-class H(BaseHTTPRequestHandler):
+import http.server, urllib.request, os
+class H(http.server.BaseHTTPRequestHandler):
     def do_GET(self):
-        self.send_response(200); self.end_headers(); self.wfile.write(b'ok')
-HTTPServer(('0.0.0.0', 8080), H).serve_forever()
+        try:
+            r = urllib.request.urlopen('http://127.0.0.1:8080' + self.path, timeout=5)
+            self.send_response(r.status)
+            self.send_header('Content-Type', r.headers.get('Content-Type','text/plain'))
+            self.end_headers()
+            self.wfile.write(r.read())
+        except:
+            self.send_response(200)
+            self.end_headers()
+            self.wfile.write(b'OpenClaw starting...')
+    def do_POST(self):
+        try:
+            data = self.rfile.read(int(self.headers.get('Content-Length',0)))
+            r = urllib.request.urlopen(urllib.request.Request(
+                'http://127.0.0.1:8080' + self.path, data=data,
+                headers={k:v for k,v in self.headers.items()}
+            ), timeout=30)
+            self.send_response(r.status)
+            self.send_header('Content-Type', r.headers.get('Content-Type','text/plain'))
+            self.end_headers()
+            self.wfile.write(r.read())
+        except:
+            self.send_response(502)
+            self.end_headers()
+            self.wfile.write(b'Gateway not ready')
+    def log_message(self,*a): pass
+http.server.HTTPServer(('0.0.0.0', 8080), H).serve_forever()
 " &
 HEALTH_PID=$!
+echo "[boot] Health proxy PID: $HEALTH_PID"
 
 echo "[boot] Starting nginx..."
 nginx
@@ -112,7 +139,7 @@ for i in $(seq 1 30); do
     sleep 2
 done
 
-echo "[boot] Building DeepSeek R1 Distill Qwen 14B IQ2_XS model..."
+echo "[boot] Building DeepSeek R1 Distill Qwen 14B IQ2_XS..."
 python3 << PYEOF
 import subprocess, sys, os
 from pathlib import Path
@@ -141,20 +168,11 @@ subprocess.run(["ollama", "create", "deepseek-qwen-14b", "-f", "/tmp/Modelfile"]
 Path(gguf_path).unlink()
 PYEOF
 
-echo "[boot] Starting OpenClaw gateway..."
+echo "[boot] Starting OpenClaw gateway on port 8081..."
 python3 -m openclaw gateway &
 OPENCLAW_PID=$!
+echo "[boot] OpenClaw PID: $OPENCLAW_PID"
 
-echo "[boot] Waiting for OpenClaw gateway on port 8080..."
-for i in $(seq 1 30); do
-    if curl -sf http://127.0.0.1:8080/health > /dev/null 2>&1; then
-        echo "[boot] OpenClaw gateway ready after ${i}s"
-        break
-    fi
-    sleep 2
-done
-
-kill $HEALTH_PID 2>/dev/null
-echo "[boot] Deployment complete. PID: $OPENCLAW_PID"
+echo "[boot] Deployment complete. Sleeping forever..."
 wait $OPENCLAW_PID 2>/dev/null
 sleep infinity