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

tests/litellm/proxy/test_route_llm_request.py

@@ -0,0 +1,46 @@
+import json
+import os
+import sys
+
+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 MagicMock
+
+from litellm.proxy.route_llm_request import route_request
+
+
+@pytest.mark.parametrize(
+    "route_type",
+    [
+        "atext_completion",
+        "acompletion",
+        "aembedding",
+        "aimage_generation",
+        "aspeech",
+        "atranscription",
+        "amoderation",
+        "arerank",
+    ],
+)
+@pytest.mark.asyncio
+async def test_route_request_dynamic_credentials(route_type):
+    data = {
+        "model": "openai/gpt-4o-mini-2024-07-18",
+        "api_key": "my-bad-key",
+        "api_base": "https://api.openai.com/v1 ",
+    }
+    llm_router = MagicMock()
+    # Ensure that the dynamic method exists on the llm_router mock.
+    getattr(llm_router, route_type).return_value = "fake_response"
+
+    response = await route_request(data, llm_router, None, route_type)
+    # Optionally verify the response if needed:
+    assert response == "fake_response"
+    # Now assert that the dynamic method was called once with the expected kwargs.
+    getattr(llm_router, route_type).assert_called_once_with(**data)