Litellm dev 02 07 2025 p2 (#8377)

* fix(caching_routes.py): mask redis password on `/cache/ping` route

* fix(caching_routes.py): fix linting erro

* fix(caching_routes.py): fix linting error on caching routes

* fix: fix test - ignore mask_dict - has a breakpoint

* fix(azure.py): add timeout param + elapsed time in azure timeout error

* fix(http_handler.py): add elapsed time to http timeout request

makes it easier to debug how long request took before failing

litellm/proxy/_new_secret_config.yaml

@@ -5,6 +5,12 @@ model_list:
   - model_name: gpt-4
     litellm_params:
       model: gpt-3.5-turbo
+  - model_name: azure-gpt-35-turbo
+    litellm_params:
+      model: azure/chatgpt-v-2
+      api_key: os.environ/AZURE_API_KEY
+      api_base: os.environ/AZURE_API_BASE
+      timeout: 0.000000001
   - model_name: o3-mini
     litellm_params:
       model: o3-mini
@@ -12,7 +18,7 @@ model_list:
   - model_name: anthropic-claude
     litellm_params:
       model: claude-3-5-haiku-20241022
-      mock_response: Hi!
+      timeout: 0.000000001
   - model_name: groq/*
     litellm_params:
       model: groq/*
@@ -28,16 +34,11 @@ model_list:
       api_key: fake-key
       api_base: https://exampleopenaiendpoint-production.up.railway.app/
 
-general_settings:
-  enable_jwt_auth: True
-  litellm_jwtauth:
-    team_id_jwt_field: "client_id"
-    team_id_upsert: true
-    scope_mappings:
-      - scope: litellm.api.consumer
-        models: ["anthropic-claude"]
-        routes: ["/v1/chat/completions"]
-      - scope: litellm.api.gpt_3_5_turbo
-        models: ["gpt-3.5-turbo-testing"]
-    enforce_scope_based_access: true
-    enforce_rbac: true
+litellm_settings:
+  cache: true
+      
+
+router_settings:
+  redis_host: os.environ/REDIS_HOST
+  redis_password: os.environ/REDIS_PASSWORD
+  redis_port: os.environ/REDIS_PORT

litellm/proxy/caching_routes.py

@@ -1,12 +1,15 @@
-import copy
+from typing import Any, Dict
 
 from fastapi import APIRouter, Depends, HTTPException, Request
 
 import litellm
 from litellm._logging import verbose_proxy_logger
 from litellm.caching.caching import RedisCache
+from litellm.litellm_core_utils.sensitive_data_masker import SensitiveDataMasker
 from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
 
+masker = SensitiveDataMasker()
+
 router = APIRouter(
     prefix="/cache",
     tags=["caching"],
@@ -21,27 +24,30 @@ async def cache_ping():
     """
     Endpoint for checking if cache can be pinged
     """
-    litellm_cache_params = {}
-    specific_cache_params = {}
+    litellm_cache_params: Dict[str, Any] = {}
+    specific_cache_params: Dict[str, Any] = {}
     try:
 
         if litellm.cache is None:
             raise HTTPException(
                 status_code=503, detail="Cache not initialized. litellm.cache is None"
             )
-
+        litellm_cache_params = {}
+        specific_cache_params = {}
         for k, v in vars(litellm.cache).items():
             try:
                 if k == "cache":
                     continue
-                litellm_cache_params[k] = str(copy.deepcopy(v))
+                litellm_cache_params[k] = v
             except Exception:
                 litellm_cache_params[k] = "<unable to copy or convert>"
         for k, v in vars(litellm.cache.cache).items():
             try:
-                specific_cache_params[k] = str(v)
+                specific_cache_params[k] = v
             except Exception:
                 specific_cache_params[k] = "<unable to copy or convert>"
+        litellm_cache_params = masker.mask_dict(litellm_cache_params)
+        specific_cache_params = masker.mask_dict(specific_cache_params)
         if litellm.cache.type == "redis":
             # ping the redis cache
             ping_response = await litellm.cache.ping()
@@ -56,6 +62,7 @@ async def cache_ping():
                 messages=[{"role": "user", "content": "test from litellm"}],
             )
             verbose_proxy_logger.debug("/cache/ping: done with set_cache()")
+
             return {
                 "status": "healthy",
                 "cache_type": litellm.cache.type,