fix(proxy_server.py): fix setting router redis cache, if cache enable… (#8859)

* fix(proxy_server.py): fix setting router redis cache, if cache enabled on litellm_settings

enables configurations like namespace to just work

* fix(redis_cache.py): fix key for async increment, to use the set namespace

prevents collisions if redis instance shared across environments

* fix load tests on litellm release notes

* fix caching on main branch (#8858)

* fix(streaming_handler.py): fix is delta empty check to handle empty str

* fix(streaming_handler.py): fix delta chunk on final response

* [Bug]: Deepseek error on proxy after upgrading to 1.61.13-stable (#8860)

* fix deepseek error

* test_deepseek_provider_async_completion

* fix get_complete_url

* bump: version 1.61.17 → 1.61.18

* bump: version 1.61.18 → 1.61.19

* vertex ai anthropic thinking param support (#8853)

* fix(vertex_llm_base.py): handle credentials passed in as dictionary

* fix(router.py): support vertex credentials as json dict

* test(test_vertex.py): allows easier testing

mock anthropic thinking response for vertex ai

* test(vertex_ai_partner_models/): don't remove "@" from model

breaks anthropic cost calculation

* test: move testing

* fix: fix linting error

* fix: fix linting error

* fix(vertex_ai_partner_models/main.py): split @ for codestral model

* test: fix test

* fix: fix stripping "@" on mistral models

* fix: fix test

* test: fix test

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>

litellm/caching/redis_cache.py

@@ -543,6 +543,7 @@ class RedisCache(BaseCache):
         _redis_client: Redis = self.init_async_client()  # type: ignore
         start_time = time.time()
         _used_ttl = self.get_ttl(ttl=ttl)
+        key = self.check_and_fix_namespace(key=key)
         try:
             result = await _redis_client.incrbyfloat(name=key, amount=value)
             if _used_ttl is not None:

litellm/proxy/_new_secret_config.yaml

@@ -27,3 +27,8 @@ model_list:
     litellm_params:
       model: openai/gpt-4o
 
+litellm_settings:
+  cache: true 
+  cache_params:        # set cache params for redis
+    type: redis
+    namespace: "litellm.caching"

litellm/proxy/proxy_server.py

@@ -1653,10 +1653,6 @@ class ProxyConfig:
             ## INIT PROXY REDIS USAGE CLIENT ##
             redis_usage_cache = litellm.cache.cache
 
-            ## INIT ROUTER REDIS CACHE ##
-            if llm_router is not None:
-                llm_router._update_redis_cache(cache=redis_usage_cache)
-
     async def get_config(self, config_file_path: Optional[str] = None) -> dict:
         """
         Load config file
@@ -2183,6 +2179,9 @@ class ProxyConfig:
             ),
         )  # type:ignore
 
+        if redis_usage_cache is not None and router.cache.redis_cache is None:
+            router._update_redis_cache(cache=redis_usage_cache)
+
         # Guardrail settings
         guardrails_v2: Optional[List[Dict]] = None
 

tests/litellm/caching/test_redis_cache.py

@@ -0,0 +1,41 @@
+import json
+import os
+import sys
+from unittest.mock import MagicMock, patch
+
+import pytest
+from fastapi.testclient import TestClient
+
+sys.path.insert(
+    0, os.path.abspath("../../..")
+)  # Adds the parent directory to the system path
+from unittest.mock import AsyncMock
+
+from litellm.caching.redis_cache import RedisCache
+
+
+@pytest.mark.parametrize("namespace", [None, "test"])
+@pytest.mark.asyncio
+async def test_redis_cache_async_increment(namespace):
+    redis_cache = RedisCache(namespace=namespace)
+    # Create an AsyncMock for the Redis client
+    mock_redis_instance = AsyncMock()
+
+    # Make sure the mock can be used as an async context manager
+    mock_redis_instance.__aenter__.return_value = mock_redis_instance
+    mock_redis_instance.__aexit__.return_value = None
+
+    assert redis_cache is not None
+
+    expected_key = "test:test" if namespace else "test"
+
+    with patch.object(
+        redis_cache, "init_async_client", return_value=mock_redis_instance
+    ):
+        # Call async_set_cache
+        await redis_cache.async_increment(key=expected_key, value=1)
+
+        # Verify that the set method was called on the mock Redis instance
+        mock_redis_instance.incrbyfloat.assert_called_once_with(
+            name=expected_key, amount=1
+        )