build: merge squashed commit

Squashed commit of the following: commit 6678e15381 Author: Ishaan Jaff <ishaanjaffer0324@gmail.com> Date: Wed Feb 26 09:29:15 2025 -0800 test_prompt_caching commit bd86e0ac47 Author: Ishaan Jaff <ishaanjaffer0324@gmail.com> Date: Wed Feb 26 08:57:16 2025 -0800 test_prompt_caching commit 2fc21ad51e Author: Ishaan Jaff <ishaanjaffer0324@gmail.com> Date: Wed Feb 26 08:13:45 2025 -0800 test_aprompt_caching commit d94cff55ff Author: Ishaan Jaff <ishaanjaffer0324@gmail.com> Date: Wed Feb 26 08:13:12 2025 -0800 test_prompt_caching commit 49c5e7811e Author: Ishaan Jaff <ishaanjaffer0324@gmail.com> Date: Wed Feb 26 07:43:53 2025 -0800 ui new build commit cb8d5e5917 Author: Ishaan Jaff <ishaanjaffer0324@gmail.com> Date: Wed Feb 26 07:38:56 2025 -0800 (UI) - Create Key flow for existing users (#8844) * working create user button * working create user for a key flow * allow searching users * working create user + key * use clear sections on create key * better search for users * fix create key * ui fix create key button - make it neater / cleaner * ui fix all keys table commit 335ba30467 Author: Krrish Dholakia <krrishdholakia@gmail.com> Date: Wed Feb 26 08:53:17 2025 -0800 fix: fix file name commit b8c5b31a4e Author: Krrish Dholakia <krrishdholakia@gmail.com> Date: Tue Feb 25 22:54:46 2025 -0800 fix: fix utils commit ac6e503461 Author: Krrish Dholakia <krrishdholakia@gmail.com> Date: Mon Feb 24 10:43:31 2025 -0800 fix(main.py): fix openai message for assistant msg if role is missing - openai allows this Fixes https://github.com/BerriAI/litellm/issues/8661 commit de3989dbc5 Author: Krrish Dholakia <krrishdholakia@gmail.com> Date: Mon Feb 24 21:19:25 2025 -0800 fix(get_litellm_params.py): handle no-log being passed in via kwargs Fixes https://github.com/BerriAI/litellm/issues/8380
2025-04-26 03:04:13 +00:00 · 2025-02-26 09:39:27 -08:00 · 2025-02-26 09:39:27 -08:00 · fcf4ea3608
commit fcf4ea3608
parent da1fd9b25f
8 changed files with 172 additions and 12 deletions
--- a/tests/litellm/test_main.py
+++ b/tests/litellm/test_main.py
@ -0,0 +1,119 @@
+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, patch
+
+import litellm
+
+
+@pytest.fixture
+def openai_api_response():
+    mock_response_data = {
+        "id": "chatcmpl-B0W3vmiM78Xkgx7kI7dr7PC949DMS",
+        "choices": [
+            {
+                "finish_reason": "stop",
+                "index": 0,
+                "logprobs": None,
+                "message": {
+                    "content": "",
+                    "refusal": None,
+                    "role": "assistant",
+                    "audio": None,
+                    "function_call": None,
+                    "tool_calls": None,
+                },
+            }
+        ],
+        "created": 1739462947,
+        "model": "gpt-4o-mini-2024-07-18",
+        "object": "chat.completion",
+        "service_tier": "default",
+        "system_fingerprint": "fp_bd83329f63",
+        "usage": {
+            "completion_tokens": 1,
+            "prompt_tokens": 121,
+            "total_tokens": 122,
+            "completion_tokens_details": {
+                "accepted_prediction_tokens": 0,
+                "audio_tokens": 0,
+                "reasoning_tokens": 0,
+                "rejected_prediction_tokens": 0,
+            },
+            "prompt_tokens_details": {"audio_tokens": 0, "cached_tokens": 0},
+        },
+    }
+
+    return mock_response_data
+
+
+def test_completion_missing_role(openai_api_response):
+    from openai import OpenAI
+
+    from litellm.types.utils import ModelResponse
+
+    client = OpenAI(api_key="test_api_key")
+
+    mock_raw_response = MagicMock()
+    mock_raw_response.headers = {
+        "x-request-id": "123",
+        "openai-organization": "org-123",
+        "x-ratelimit-limit-requests": "100",
+        "x-ratelimit-remaining-requests": "99",
+    }
+    mock_raw_response.parse.return_value = ModelResponse(**openai_api_response)
+
+    print(f"openai_api_response: {openai_api_response}")
+
+    with patch.object(
+        client.chat.completions.with_raw_response, "create", mock_raw_response
+    ) as mock_create:
+        litellm.completion(
+            model="gpt-4o-mini",
+            messages=[
+                {"role": "user", "content": "Hey"},
+                {
+                    "content": "",
+                    "tool_calls": [
+                        {
+                            "id": "call_m0vFJjQmTH1McvaHBPR2YFwY",
+                            "function": {
+                                "arguments": '{"input": "dksjsdkjdhskdjshdskhjkhlk"}',
+                                "name": "tool_name",
+                            },
+                            "type": "function",
+                            "index": 0,
+                        },
+                        {
+                            "id": "call_Vw6RaqV2n5aaANXEdp5pYxo2",
+                            "function": {
+                                "arguments": '{"input": "jkljlkjlkjlkjlk"}',
+                                "name": "tool_name",
+                            },
+                            "type": "function",
+                            "index": 1,
+                        },
+                        {
+                            "id": "call_hBIKwldUEGlNh6NlSXil62K4",
+                            "function": {
+                                "arguments": '{"input": "jkjlkjlkjlkj;lj"}',
+                                "name": "tool_name",
+                            },
+                            "type": "function",
+                            "index": 2,
+                        },
+                    ],
+                },
+            ],
+            client=client,
+        )
+
+        mock_create.assert_called_once()