scripts/litellm-health-check.py

@@ -78,18 +78,34 @@ def check_model_probes():
     
     results = []
     
-    for model in ["gpu-dense", "gpu-vision", "strix-moe", "syslog-auto"]:
-        # Use unique prompt per run to avoid caching
-        prompt = "health " + str(random.randint(1000, 9999))
-        data = '{"model":"' + model + '","messages":[{"role":"user","content":"' + prompt + '"}],"max_tokens":4}'
-        
+    for model in ["gpu-dense", "gpu-vision", "strix-moe"]:
+        # Single-host aliases: 30s timeout
         code = probe_http("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
                          method="POST",
                          bearer_token=monitor_key,
-                         data=data)
+                         data='{"model":"' + model + '","messages":[{"role":"user","content":"health ' + str(random.randint(1000, 9999)) + '"}],"max_tokens":4}',
+                         timeout=30)
         
         results.append((model, code == 200, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=" + model + ")"))
     
+    # Pool alias (syslog-auto): 60s timeout, retry once on 000
+    code = probe_http("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
+                     method="POST",
+                     bearer_token=monitor_key,
+                     data='{"model":"syslog-auto","messages":[{"role":"user","content":"health ' + str(random.randint(1000, 9999)) + '"}],"max_tokens":4}',
+                     timeout=60)
+    
+    if code == 000:
+        # Retry once with same timeout
+        time.sleep(1)
+        code = probe_http("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
+                         method="POST",
+                         bearer_token=monitor_key,
+                         data='{"model":"syslog-auto","messages":[{"role":"user","content":"health ' + str(random.randint(1000, 9999)) + '"}],"max_tokens":4}',
+                         timeout=60)
+    
+    results.append(("syslog-auto", code == 200, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=syslog-auto)"))
+    
     return results
 
 def check_admin_key_list():
@@ -105,9 +121,6 @@ def check_admin_key_list():
     if not mk or "NO-CURL" in mk:
         return "Admin Key List", False, "credential-missing (empty or NO-CURL)"
     
-    # Print key length for debugging
-    print("  DEBUG: keylen=" + str(len(mk)), file=sys.stderr)
-    
     # Step 2: Call using the key - use double quotes inside SSH command
     cmd = "ssh -o BatchMode=yes root@192.168.68.116 \"curl -s -H \\\"Authorization: Bearer " + mk + "\\\" http://127.0.0.1:4000/key/list\""
     rc, stdout, stderr = run_command(cmd)
@@ -115,9 +128,6 @@ def check_admin_key_list():
     if rc != 0:
         return "Admin Key List", False, "admin-call-failed (exit=" + str(rc) + ", stderr=" + stderr + ")"
     
-    # Print response for debugging
-    print("  DEBUG: response=" + stdout[:120] + "...", file=sys.stderr)
-    
     # Try to parse the response
     try:
         data = json.loads(stdout)