fix(route_llm_request.py): move to using common router, even for clie… (#8966)

* fix(route_llm_request.py): move to using common router, even for client-side credentials

ensures fallbacks / cooldown logic still works

* test(test_route_llm_request.py): add unit test for route request

* feat(router.py): generate unique model id when clientside credential passed in

Prevents cooldowns for api key 1 from impacting api key 2

* test(test_router.py): update testing to ensure original litellm params not mutated

* fix(router.py): upsert clientside call into llm router model list

enables cooldown logic to work accurately

* fix: fix linting error

* test(test_router_utils.py): add direct test for new util on router

litellm/proxy/_new_secret_config.yaml

@@ -1,34 +1,11 @@
 model_list:
-  - model_name: claude-3.7
+  - model_name: openai-gpt-4o-mini-2024-07-18 
     litellm_params:
-      model: openai/gpt-3.5-turbo
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: http://0.0.0.0:8090
-  - model_name: deepseek-r1
-    litellm_params:
-      model: bedrock/deepseek_r1/arn:aws:bedrock:us-west-2:888602223428:imported-model/bnnr6463ejgf
-  - model_name: deepseek-r1-api
-    litellm_params:
-      model: deepseek/deepseek-reasoner
-  - model_name: cohere.embed-english-v3
-    litellm_params:
-      model: bedrock/cohere.embed-english-v3
-      api_key: os.environ/COHERE_API_KEY
-  - model_name: bedrock-claude-3-7
-    litellm_params:
-      model: bedrock/invoke/us.anthropic.claude-3-7-sonnet-20250219-v1:0
-  - model_name: bedrock-claude-3-5-sonnet
-    litellm_params:
-      model: bedrock/invoke/us.anthropic.claude-3-5-sonnet-20240620-v1:0
-  - model_name: bedrock-nova
-    litellm_params:
-      model: bedrock/us.amazon.nova-pro-v1:0
-  - model_name: gpt-4o
-    litellm_params:
-      model: openai/gpt-4o
+      model: openai/gpt-4o-mini-2024-07-18
+      configurable_clientside_auth_params: ["api_key"]
+      api_key: "my-bad-key"
+  # - model_name: openai-fallback-model
+  #   litellm_params:
+  #     model: openai/gpt-3.5-turbo
+
 
-litellm_settings:
-  cache: true 
-  cache_params:        # set cache params for redis
-    type: redis
-    namespace: "litellm.caching"

litellm/proxy/route_llm_request.py

@@ -53,7 +53,7 @@ async def route_request(
     """
     router_model_names = llm_router.model_names if llm_router is not None else []
     if "api_key" in data or "api_base" in data:
-        return getattr(litellm, f"{route_type}")(**data)
+        return getattr(llm_router, f"{route_type}")(**data)
 
     elif "user_config" in data:
         router_config = data.pop("user_config")