planner: fix model-name casing and kv_hit_rate namespace so engine metrics resolve

components/src/dynamo/planner/monitoring/traffic_metrics.py

@@ -453,16 +453,28 @@ def get_avg_kv_hit_rate(self, interval: str, model_name: str) -> Optional[float]
             f"{prometheus_names.router.KV_HIT_RATE}"
         )
         try:
-            ns = self.dynamo_namespace.replace("-", "_")
-            ns_filter = f'{prometheus_names.labels.NAMESPACE}="{ns}"'
-            query = (
-                f"sum(increase({full_metric_name}_sum{{{ns_filter}}}[{interval}])) / "
-                f"sum(increase({full_metric_name}_count{{{ns_filter}}}[{interval}]))"
-            )
-            result = self.prom.custom_query(query=query)
+            # The router emits `dynamo_namespace` sanitized to underscores, but
+            # some scrape paths relabel it back to the hyphenated k8s form
+            # (nvidia.com/dynamo-namespace). Try both so the query works under
+            # either emission style instead of silently returning no data.
+            candidates = []
+            for ns in (self.dynamo_namespace.replace("-", "_"), self.dynamo_namespace):
+                if ns not in candidates:
+                    candidates.append(ns)
+            result = []
+            for ns in candidates:
+                ns_filter = f'{prometheus_names.labels.NAMESPACE}="{ns}"'
+                query = (
+                    f"sum(increase({full_metric_name}_sum{{{ns_filter}}}[{interval}])) / "
+                    f"sum(increase({full_metric_name}_count{{{ns_filter}}}[{interval}]))"
+                )
+                result = self.prom.custom_query(query=query)
+                if result:
+                    break
             if not result:
                 logger.info(
-                    f"No prometheus data for {full_metric_name}, returning None"
+                    f"No prometheus data for {full_metric_name} "
+                    f"(tried dynamo_namespace in {candidates}), returning None"
                 )
                 return None
             value = float(result[0]["value"][1])

components/src/dynamo/planner/monitoring/worker_info.py

@@ -163,7 +163,21 @@ def resolve_worker_info(
         model_name = config_model_name
     else:
         mdc_model = decode_info.model_name or prefill_info.model_name
-        if mdc_model:
+        # Prefer the operator-supplied name. Discovery-derived MDC names are
+        # normalized to lowercase, but engine metrics carry the model's real
+        # casing, so an MDC name silently makes every engine-metric query
+        # (spec-decode accept_length, kv_hit_rate) return empty.
+        if config_model_name:
+            model_name = config_model_name
+            if mdc_model and mdc_model != config_model_name:
+                logger.info(
+                    "Using model name from config: %s (MDC reported %s)",
+                    model_name,
+                    mdc_model,
+                )
+            else:
+                logger.info(f"Using model name from config: {model_name}")
+        elif mdc_model:
             model_name = mdc_model
             logger.info(f"Using model name from MDC: {model_name}")
         elif can_query_mdc: