diff --git a/litellm/proxy/client/cli/commands/pi.py b/litellm/proxy/client/cli/commands/pi.py
index 19c4a94d380..37d485dc1b9 100644
--- a/litellm/proxy/client/cli/commands/pi.py
+++ b/litellm/proxy/client/cli/commands/pi.py
@@ -193,7 +193,13 @@ def _reasoning_fields(limit: ModelLimits | None) -> Mapping[str, JsonValue]:
     efforts: Final = limit.supported_reasoning_efforts if limit else None
     if not efforts:
         return MappingProxyType({})
-    return MappingProxyType({"reasoning": True, "thinkingLevelMap": _thinking_level_map(efforts)})
+    return MappingProxyType(
+        {
+            "reasoning": True,
+            "thinkingLevelMap": _thinking_level_map(efforts),
+            "compat": {"supportsDeveloperRole": False},
+        }
+    )
 
 
 def _model_entry(
diff --git a/tests/unit/proxy/client/cli/test_pi.py b/tests/unit/proxy/client/cli/test_pi.py
index ae485914507..f90febb3178 100644
--- a/tests/unit/proxy/client/cli/test_pi.py
+++ b/tests/unit/proxy/client/cli/test_pi.py
@@ -257,7 +257,7 @@ class TestProviderBlock:
             ),
         ],
     )
-    def test_reasoning_efforts_become_pi_thinking_levels(self, efforts, thinking_level_map):
+    def test_reasoning_efforts_become_pi_thinking_levels_and_keep_the_system_role(self, efforts, thinking_level_map):
         block = provider_block(
             "http://localhost:4000",
             ("m-1",),
@@ -270,6 +270,7 @@ class TestProviderBlock:
                 "maxTokens": 8192,
                 "reasoning": True,
                 "thinkingLevelMap": thinking_level_map,
+                "compat": {"supportsDeveloperRole": False},
             }
         ]