Merge pull request 'fix(litellm-health): retry single-host model probes once at a longer timeout' (#121) from fix/litellm-health-retry-timeout-20260919 into master

scripts/litellm-health-check.py

@@ -116,17 +116,31 @@ def check_model_probes():
     results = []
     
     for model in ["gpu-dense", "gpu-vision", "strix-moe"]:
-        # Single-host aliases: 30s timeout each
-        # gpu-dense (RTX 3090) may need long warmup/prefill - timeout is acceptable on cold-start
+        # Single-host aliases: 30s initial timeout, retry once at 45s on failure
+        # gpu-dense (RTX 3090) may need long warmup/prefill or concurrent generation hold
         code, failure_kind = probe_http("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
                                        method="POST",
                                        bearer_token=monitor_key,
                                        data='{"model":"' + model + '","messages":[{"role":"user","content":"health ' + str(random.randint(1000, 9999)) + '"}],"max_tokens":4}',
                                        timeout=30)
         
+        first_kind = None  # Track first attempt's failure kind
         if code == 000 and failure_kind:
-            # Report probe failure with kind, do not assert a service verdict
-            results.append((model, False, "probe-failed: " + model + " " + failure_kind + " (30s timeout)"))
+            # Retry once with longer timeout (45s) before declaring failure
+            first_kind = failure_kind
+            time.sleep(1)
+            code, failure_kind = probe_http("http://" + BACKEND_HOST + "/litellm/v1/chat/completions",
+                                           method="POST",
+                                           bearer_token=monitor_key,
+                                           data='{"model":"' + model + '","messages":[{"role":"user","content":"health ' + str(random.randint(1000, 9999)) + '"}],"max_tokens":4}',
+                                           timeout=45)
+        
+        if code == 000 and failure_kind:
+            # Both attempts failed - report both kinds
+            if first_kind:
+                results.append((model, False, "probe-failed: " + model + " " + first_kind + " then " + failure_kind + " (2 attempts)"))
+            else:
+                results.append((model, False, "probe-failed: " + model + " " + failure_kind))
         elif code == 200:
             results.append((model, True, str(code) + " (target: " + BACKEND_HOST + "/litellm/v1/chat/completions, model=" + model + ")"))
         elif code in (401, 403):