From 482bc9391009f3a2441f754557c57360cc98ca08 Mon Sep 17 00:00:00 2001
From: Sameer Kankute <sameer@berri.ai>
Date: Thu, 5 Mar 2026 10:49:37 +0530
Subject: [PATCH] fix(azure_ai): strip scope from cache_control for Anthropic
 messages

Azure AI Foundry's Anthropic endpoint does not support the scope field in
cache_control. Strip it from both system and messages before sending.

Made-with: Cursor
---
 .../anthropic/messages_transformation.py      | 52 ++++++++++++++++++-
 ...azure_anthropic_messages_transformation.py | 44 ++++++++++++++++
 2 files changed, 95 insertions(+), 1 deletion(-)

diff --git a/litellm/llms/azure_ai/anthropic/messages_transformation.py b/litellm/llms/azure_ai/anthropic/messages_transformation.py
index a4dc88f9c6..8e60e84391 100644
--- a/litellm/llms/azure_ai/anthropic/messages_transformation.py
+++ b/litellm/llms/azure_ai/anthropic/messages_transformation.py
@@ -1,7 +1,7 @@
 """
 Azure Anthropic messages transformation config - extends AnthropicMessagesConfig with Azure authentication
 """
-from typing import TYPE_CHECKING, Any, List, Optional, Tuple
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
 
 from litellm.llms.anthropic.experimental_pass_through.messages.transformation import (
     AnthropicMessagesConfig,
@@ -114,3 +114,53 @@ class AzureAnthropicMessagesConfig(AnthropicMessagesConfig):
 
         return api_base
 
+    def _remove_scope_from_cache_control(
+        self, anthropic_messages_request: Dict
+    ) -> None:
+        """
+        Remove `scope` field from cache_control for Azure AI Foundry.
+
+        Azure AI Foundry's Anthropic endpoint does not support the `scope` field
+        (e.g., "global" for cross-request caching). Only `type` and `ttl` are supported.
+
+        Processes both `system` and `messages` content blocks.
+        """
+        def _sanitize(cache_control: Any) -> None:
+            if isinstance(cache_control, dict):
+                cache_control.pop("scope", None)
+
+        def _process_content_list(content: list) -> None:
+            for item in content:
+                if isinstance(item, dict) and "cache_control" in item:
+                    _sanitize(item["cache_control"])
+
+        if "system" in anthropic_messages_request:
+            system = anthropic_messages_request["system"]
+            if isinstance(system, list):
+                _process_content_list(system)
+
+        if "messages" in anthropic_messages_request:
+            for message in anthropic_messages_request["messages"]:
+                if isinstance(message, dict) and "content" in message:
+                    content = message["content"]
+                    if isinstance(content, list):
+                        _process_content_list(content)
+
+    def transform_anthropic_messages_request(
+        self,
+        model: str,
+        messages: List[Dict],
+        anthropic_messages_optional_request_params: Dict,
+        litellm_params: GenericLiteLLMParams,
+        headers: dict,
+    ) -> Dict:
+        anthropic_messages_request = super().transform_anthropic_messages_request(
+            model=model,
+            messages=messages,
+            anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
+            litellm_params=litellm_params,
+            headers=headers,
+        )
+        self._remove_scope_from_cache_control(anthropic_messages_request)
+        return anthropic_messages_request
+
diff --git a/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py b/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
index bdced849c7..83653bc037 100644
--- a/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
+++ b/tests/test_litellm/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py
@@ -239,6 +239,50 @@ class TestAzureAnthropicMessagesConfig:
         assert "tools" in params
         assert "tool_choice" in params
 
+    def test_transform_anthropic_messages_request_removes_scope_from_cache_control(
+        self,
+    ):
+        """Test that scope is removed from cache_control (Azure AI Foundry doesn't support it)"""
+        config = AzureAnthropicMessagesConfig()
+        model = "claude-sonnet-4-5"
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": "Hello",
+                        "cache_control": {"type": "ephemeral", "scope": "global"},
+                    }
+                ],
+            }
+        ]
+        anthropic_messages_optional_request_params = {
+            "max_tokens": 1024,
+            "system": [
+                {
+                    "type": "text",
+                    "text": "You are an AI assistant.",
+                    "cache_control": {"type": "ephemeral", "scope": "global"},
+                }
+            ],
+        }
+        litellm_params = GenericLiteLLMParams()
+        headers = {}
+
+        result = config.transform_anthropic_messages_request(
+            model=model,
+            messages=messages,
+            anthropic_messages_optional_request_params=anthropic_messages_optional_request_params,
+            litellm_params=litellm_params,
+            headers=headers,
+        )
+
+        assert "scope" not in result["system"][0]["cache_control"]
+        assert result["system"][0]["cache_control"]["type"] == "ephemeral"
+        assert "scope" not in result["messages"][0]["content"][0]["cache_control"]
+        assert result["messages"][0]["content"][0]["cache_control"]["type"] == "ephemeral"
+
 
 class TestProviderConfigManagerAzureAnthropicMessages:
     """Test ProviderConfigManager returns correct config for Azure AI Anthropic Messages API"""