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/router_utils/clientside_credential_handler.py

@@ -0,0 +1,37 @@
+"""
+Utils for handling clientside credentials
+
+Supported clientside credentials:
+- api_key
+- api_base
+- base_url
+
+If given, generate a unique model_id for the deployment.
+
+Ensures cooldowns are applied correctly.
+"""
+
+clientside_credential_keys = ["api_key", "api_base", "base_url"]
+
+
+def is_clientside_credential(request_kwargs: dict) -> bool:
+    """
+    Check if the credential is a clientside credential.
+    """
+    return any(key in request_kwargs for key in clientside_credential_keys)
+
+
+def get_dynamic_litellm_params(litellm_params: dict, request_kwargs: dict) -> dict:
+    """
+    Generate a unique model_id for the deployment.
+
+    Returns
+    - litellm_params: dict
+
+    for generating a unique model_id.
+    """
+    # update litellm_params with clientside credentials
+    for key in clientside_credential_keys:
+        if key in request_kwargs:
+            litellm_params[key] = request_kwargs[key]
+    return litellm_params