From 2672294c01e30be25112baa92bd5402ba1ab8de7 Mon Sep 17 00:00:00 2001
From: naaa760 <neh6a683@gmail.com>
Date: Sat, 7 Mar 2026 00:46:49 +0530
Subject: [PATCH] fix(vertex): drop extra_body.cache from Gemini request
 payload

---
 .../llms/vertex_ai/gemini/transformation.py   |  1 +
 .../test_vertex_ai_gemini_transformation.py   | 48 +++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/litellm/llms/vertex_ai/gemini/transformation.py b/litellm/llms/vertex_ai/gemini/transformation.py
index 57889284a8c..5e16ab67d05 100644
--- a/litellm/llms/vertex_ai/gemini/transformation.py
+++ b/litellm/llms/vertex_ai/gemini/transformation.py
@@ -533,6 +533,7 @@ def _pop_and_merge_extra_body(data: RequestBody, optional_params: dict) -> None:
     """Pop extra_body from optional_params and shallow-merge into data, deep-merging dict values."""
     extra_body: Optional[dict] = optional_params.pop("extra_body", None)
     if extra_body is not None:
+        extra_body.pop("cache", None)
         data_dict: dict = data  # type: ignore[assignment]
         for k, v in extra_body.items():
             if k in data_dict and isinstance(data_dict[k], dict) and isinstance(v, dict):
diff --git a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py
index b264964b14b..1c641e101b4 100644
--- a/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py
+++ b/tests/test_litellm/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py
@@ -125,6 +125,54 @@ def test_vertex_ai_includes_labels():
     assert result["labels"] == {"project": "test", "team": "ai"}
 
 
+def test_vertex_ai_filters_cache_from_extra_body():
+    """Test that LiteLLM cache controls in extra_body are not forwarded to Vertex payloads."""
+    messages = [{"role": "user", "content": "test"}]
+    optional_params = {
+        "extra_body": {
+            "cache": {"use-cache": True, "ttl": 86400},
+            "labels": {"project": "test"},
+        }
+    }
+    litellm_params = {}
+
+    result = _transform_request_body(
+        messages=messages,
+        model="gemini-2.5-pro",
+        optional_params=optional_params,
+        custom_llm_provider="vertex_ai",
+        litellm_params=litellm_params,
+        cached_content=None,
+    )
+
+    assert "cache" not in result
+    assert result.get("labels") == {"project": "test"}
+
+
+def test_gemini_filters_cache_from_extra_body():
+    """Test that LiteLLM cache controls in extra_body are not forwarded to Gemini payloads."""
+    messages = [{"role": "user", "content": "test"}]
+    optional_params = {
+        "extra_body": {
+            "cache": {"use-cache": True, "ttl": 86400},
+            "generationConfig": {"temperature": 0.2},
+        }
+    }
+    litellm_params = {}
+
+    result = _transform_request_body(
+        messages=messages,
+        model="gemini-2.5-pro",
+        optional_params=optional_params,
+        custom_llm_provider="gemini",
+        litellm_params=litellm_params,
+        cached_content=None,
+    )
+
+    assert "cache" not in result
+    assert result["generationConfig"]["temperature"] == 0.2
+
+
 
 def test_metadata_to_labels_vertex_only():
     """Test that metadata->labels conversion only happens for Vertex AI"""