test(ci): repair stale tests and move retired OpenAI text-completion fixtures

tests/integration/security/_sweeps.py

@@ -105,6 +105,7 @@
         "/plugin-proxy/{plugin_name}/{path:path}": "reverse proxy to a plugin process",
         "/openai_passthrough/{endpoint:path}": "forwards to a provider, not a proxy read",
         "/get/latest_release_info": "fetches the latest release from api.github.com",
+        "/roi-calculator/repositories": "lists repositories from the configured GitHub API, api.github.com by default",
     }
 )
 

tests/local_testing/test_completion.py

@@ -11,7 +11,9 @@
 
 from unittest.mock import AsyncMock, MagicMock, patch
 
+import httpx
 import pytest
+from openai import OpenAI
 
 import litellm
 from litellm import RateLimitError, Timeout, completion, completion_cost, embedding
@@ -1580,7 +1582,7 @@ class EventsList(BaseModel):
 def test_completion_text_openai():
     try:
         # litellm.set_verbose =True
-        response = completion(model="gpt-3.5-turbo-instruct", messages=messages)
+        response = completion(model="text-completion-openai/gpt-5.4-nano", messages=messages)
         print(response["choices"][0]["message"]["content"])
     except Exception as e:
         print(e)
@@ -1592,75 +1594,41 @@ async def test_completion_text_openai_async():
     try:
         # litellm.set_verbose =True
         response = await litellm.acompletion(
-            model="gpt-3.5-turbo-instruct", messages=messages
+            model="text-completion-openai/gpt-5.4-nano", messages=messages
         )
         print(response["choices"][0]["message"]["content"])
     except Exception as e:
         print(e)
         pytest.fail(f"Error occurred: {e}")
 
 
-def custom_callback(
-    kwargs,  # kwargs to completion
-    completion_response,  # response from completion
-    start_time,
-    end_time,  # start/end time
-):
-    # Your custom code here
-    try:
-        print("LITELLM: in custom callback function")
-        print("\nkwargs\n", kwargs)
-        model = kwargs["model"]
-        messages = kwargs["messages"]
-        user = kwargs.get("user")
-
-        #################################################
-
-        print(
-            f"""
-                Model: {model},
-                Messages: {messages},
-                User: {user},
-                Seed: {kwargs["seed"]},
-                temperature: {kwargs["temperature"]},
-            """
-        )
-
-        assert kwargs["user"] == "ishaans app"
-        assert kwargs["model"] == "gpt-3.5-turbo-1106"
-        assert kwargs["seed"] == 12
-        assert kwargs["temperature"] == 0.5
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
-
-
 def test_completion_openai_with_optional_params():
     # [Proxy PROD TEST] WARNING: DO NOT DELETE THIS TEST
-    # assert that `user` gets passed to the completion call
-    # Note: This tests that we actually send the optional params to the completion call
-    # We use custom callbacks to test this
-    try:
-        litellm.set_verbose = True
-        litellm.success_callback = [custom_callback]
-        response = completion(
-            model="gpt-3.5-turbo-1106",
-            messages=[
-                {"role": "user", "content": "respond in valid, json - what is the day"}
-            ],
-            temperature=0.5,
-            top_p=0.1,
-            seed=12,
-            response_format={"type": "json_object"},
-            logit_bias=None,
-            user="ishaans app",
-        )
-        # Add any assertions here to check the response
-
-        print(response)
-        litellm.success_callback = []  # unset callbacks
+    on_request = MagicMock()
+    client = OpenAI(http_client=httpx.Client(event_hooks={"request": [on_request]}))
+    response = completion(
+        model="gpt-6-luna",
+        reasoning_effort="none",
+        messages=[{"role": "user", "content": "respond in valid, json - what is the day"}],
+        temperature=0.5,
+        top_p=0.1,
+        seed=12,
+        response_format={"type": "json_object"},
+        logit_bias=None,
+        user="ishaans app",
+        client=client,
+    )
 
-    except Exception as e:
-        pytest.fail(f"Error occurred: {e}")
+    assert response.choices[0].message.content
+    on_request.assert_called_once()
+    sent = json.loads(on_request.call_args.args[0].content)
+    assert sent["model"] == "gpt-6-luna"
+    assert sent["user"] == "ishaans app"
+    assert sent["seed"] == 12
+    assert sent["temperature"] == 0.5
+    assert sent["top_p"] == 0.1
+    assert sent["response_format"] == {"type": "json_object"}
+    assert "logit_bias" not in sent
 
 
 # test_completion_openai_with_optional_params()
@@ -4008,7 +3976,7 @@ def test_deepseek_reasoning_content_completion():
 def test_qwen_text_completion():
     # litellm._turn_on_debug()
     resp = litellm.completion(
-        model="gpt-3.5-turbo-instruct",
+        model="text-completion-openai/gpt-5.4-nano",
         messages=[{"content": "hello", "role": "user"}],
         stream=False,
         logprobs=1,

tests/local_testing/test_http_parsing_utils.py

@@ -1,75 +1,61 @@
+from collections.abc import Awaitable, Callable
+
 import pytest
 from fastapi import Request
-from fastapi.testclient import TestClient
-from starlette.datastructures import Headers
-from starlette.requests import HTTPConnection
-
+from starlette.types import Message
 
-from litellm.proxy.common_utils.http_parsing_utils import _read_request_body
 from litellm.proxy._types import ProxyException
+from litellm.proxy.common_utils.http_parsing_utils import _read_request_body
 
 
-@pytest.mark.asyncio
-async def test_read_request_body_valid_json():
-    """Test the function with a valid JSON payload."""
+def _request(receive: Callable[[], Awaitable[Message]]) -> Request:
+    return Request(
+        {
+            "type": "http",
+            "method": "POST",
+            "path": "/v1/chat/completions",
+            "headers": [(b"content-type", b"application/json")],
+        },
+        receive,
+    )
 
-    class MockRequest:
-        async def body(self):
-            return b'{"key": "value"}'
 
-    request = MockRequest()
-    result = await _read_request_body(request)
-    assert result == {"key": "value"}
+def _request_with_body(body: bytes) -> Request:
+    async def receive() -> Message:
+        return {"type": "http.request", "body": body, "more_body": False}
+
+    return _request(receive)
 
 
 @pytest.mark.asyncio
-async def test_read_request_body_empty_body():
-    """Test the function with an empty body."""
+async def test_read_request_body_valid_json():
+    result = await _read_request_body(_request_with_body(b'{"key": "value"}'))
+    assert result == {"key": "value"}
 
-    class MockRequest:
-        async def body(self):
-            return b""
 
-    request = MockRequest()
-    result = await _read_request_body(request)
+@pytest.mark.asyncio
+async def test_read_request_body_empty_body():
+    result = await _read_request_body(_request_with_body(b""))
     assert result == {}
 
 
 @pytest.mark.asyncio
 async def test_read_request_body_invalid_json():
-    """Test the function with an invalid JSON payload."""
-
-    class MockRequest:
-        async def body(self):
-            return b'{"key": value}'  # Missing quotes around `value`
-
-    request = MockRequest()
     with pytest.raises(ProxyException):
-        await _read_request_body(request)
+        await _read_request_body(_request_with_body(b'{"key": value}'))
 
 
 @pytest.mark.asyncio
 async def test_read_request_body_large_payload():
-    """Test the function with a very large payload."""
-    large_payload = '{"key":' + '"a"' * 10**6 + "}"  # Large payload
-
-    class MockRequest:
-        async def body(self):
-            return large_payload.encode()
-
-    request = MockRequest()
+    large_payload = '{"key":' + '"a"' * 10**6 + "}"
     with pytest.raises(ProxyException):
-        await _read_request_body(request)
+        await _read_request_body(_request_with_body(large_payload.encode()))
 
 
 @pytest.mark.asyncio
 async def test_read_request_body_unexpected_error():
-    """Test the function when an unexpected error occurs."""
+    async def receive() -> Message:
+        raise ValueError("Unexpected error")
 
-    class MockRequest:
-        async def body(self):
-            raise ValueError("Unexpected error")
-
-    request = MockRequest()
-    result = await _read_request_body(request)
-    assert result == {}  # Ensure fallback behavior
+    result = await _read_request_body(_request(receive))
+    assert result == {}

tests/local_testing/test_text_completion.py

@@ -1,7 +1,9 @@
 import asyncio
 from typing import Final
 import json
+import os
 import traceback
+from types import MappingProxyType
 
 from dotenv import load_dotenv
 
@@ -26,6 +28,14 @@
 litellm.num_retries = 3
 
 
+FIREWORKS_TEXT_COMPLETION: Final = MappingProxyType(
+    {
+        "model": "text-completion-openai/accounts/fireworks/models/glm-5p3-flash",
+        "api_base": "https://api.fireworks.ai/inference/v1",
+        "api_key": os.environ.get("FIREWORKS_AI_API_KEY"),
+    }
+)
+
 token_prompt = [
     [
         32,
@@ -3778,8 +3788,9 @@ def test_completion_openai_prompt():
     try:
         print("\n text 003 test\n")
         response = text_completion(
-            model="gpt-3.5-turbo-instruct",
             prompt=["What's the weather in SF?", "How is Manchester?"],
+            max_tokens=5,
+            **FIREWORKS_TEXT_COMPLETION,
         )
         print(response)
         assert len(response.choices) == 2
@@ -3841,9 +3852,9 @@ def test_completion_chatgpt_prompt():
 def test_completion_gpt_instruct():
     try:
         response = text_completion(
-            model="gpt-3.5-turbo-instruct-0914",
+            model="gpt-5.4-nano",
             prompt="What's the weather in SF?",
-            custom_llm_provider="openai",
+            custom_llm_provider="text-completion-openai",
         )
         print(response)
         response_str = response["choices"][0]["text"]
@@ -3862,7 +3873,7 @@ def test_text_completion_basic():
         print("\n test 003 with logprobs \n")
         litellm.set_verbose = False
         response = text_completion(
-            model="gpt-3.5-turbo-instruct",
+            model="text-completion-openai/gpt-5.4-nano",
             prompt="good morning",
             max_tokens=10,
             logprobs=10,
@@ -3886,13 +3897,11 @@ def test_completion_text_003_prompt_array():
     try:
         litellm.set_verbose = False
         response = text_completion(
-            model="gpt-3.5-turbo-instruct",
             prompt=token_prompt,  # token prompt is a 2d list
+            max_tokens=5,
+            **FIREWORKS_TEXT_COMPLETION,
         )
-        print("\n\n response")
-
-        print(response)
-        # response_str = response["choices"][0]["text"]
+        assert len(response.choices) == len(token_prompt)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
@@ -4151,8 +4160,8 @@ def test_completion_fireworks_ai_multiple_choices():
 def test_text_completion_with_echo(stream):
     litellm.set_verbose = True
     response = litellm.text_completion(
-        model="davinci-002",
         prompt="hello",
+        **FIREWORKS_TEXT_COMPLETION,
         max_tokens=1,  # only see the first token
         stop="\n",  # stop at the first newline
         logprobs=1,  # return log prob
@@ -4166,6 +4175,8 @@ def test_text_completion_with_echo(stream):
             print(chunk)
     else:
         assert isinstance(response, TextCompletionResponse)
+        assert response.choices[0].text.startswith("hello")
+        assert response.choices[0].logprobs.token_logprobs
 
 
 def test_text_completion_ollama():

tests/logging_callback_tests/gcs_pub_sub_body/spend_logs_payload.json

@@ -11,7 +11,7 @@
     "user": "",
     "team_id": "",
     "organization_id": "",
-    "metadata": "{\"applied_guardrails\": [], \"attempted_fallbacks\": null, \"original_model_group\": null, \"batch_models\": null, \"batch_successful_requests\": null, \"batch_failed_requests\": null, \"mcp_tool_call_metadata\": null, \"vector_store_request_metadata\": null, \"routing_decision\": null, \"internal_call_origin\": null, \"router_metadata\": null, \"autorouter_savings_estimate\": null, \"autorouter_baseline_observation\": null, \"azure_spillover\": null, \"guardrail_information\": null, \"compression_savings\": null, \"litellm_gateway_injected_cache\": null, \"usage_object\": {\"completion_tokens\": 20, \"prompt_tokens\": 10, \"total_tokens\": 30, \"completion_tokens_details\": null, \"prompt_tokens_details\": null}, \"model_map_information\": {\"model_map_key\": \"gpt-4o\", \"model_map_value\": {\"key\": \"gpt-4o\", \"max_tokens\": 16384, \"max_input_tokens\": 128000, \"max_output_tokens\": 16384, \"input_cost_per_token\": 2.5e-06, \"cache_creation_input_token_cost\": null, \"cache_read_input_token_cost\": 1.25e-06, \"input_cost_per_character\": null, \"input_cost_per_token_above_128k_tokens\": null, \"input_cost_per_token_above_200k_tokens\": null, \"input_cost_per_query\": null, \"input_cost_per_second\": null, \"input_cost_per_audio_token\": null, \"input_cost_per_token_batches\": 1.25e-06, \"output_cost_per_token_batches\": 5e-06, \"output_cost_per_token\": 1e-05, \"output_cost_per_audio_token\": null, \"output_cost_per_character\": null, \"output_cost_per_token_above_128k_tokens\": null, \"output_cost_per_character_above_128k_tokens\": null, \"output_cost_per_token_above_200k_tokens\": null, \"output_cost_per_second\": null, \"output_cost_per_image\": null, \"output_vector_size\": null, \"litellm_provider\": \"openai\", \"mode\": \"chat\", \"supports_system_messages\": true, \"supports_response_schema\": true, \"supports_vision\": true, \"supports_function_calling\": true, \"supports_tool_choice\": true, \"supports_assistant_prefill\": false, \"supports_prompt_caching\": true, \"supports_audio_input\": false, \"supports_audio_output\": false, \"supports_pdf_input\": false, \"supports_embedding_image_input\": false, \"supports_native_streaming\": null, \"supports_web_search\": true, \"supports_reasoning\": false, \"search_context_cost_per_query\": {\"search_context_size_low\": 0.03, \"search_context_size_medium\": 0.035, \"search_context_size_high\": 0.05}, \"tpm\": null, \"rpm\": null, \"supported_openai_params\": [\"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"modalities\", \"prediction\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"audio\", \"response_format\", \"user\"]}}, \"additional_usage_values\": {\"completion_tokens_details\": null, \"prompt_tokens_details\": null}, \"user_api_key\": null, \"user_api_key_alias\": null, \"user_api_key_team_id\": null, \"user_api_key_project_id\": null, \"user_api_key_project_alias\": null, \"user_api_key_org_id\": null, \"user_api_key_user_id\": null, \"user_api_key_team_alias\": null, \"spend_logs_metadata\": null, \"requester_ip_address\": null, \"user_agent\": null, \"status\": null, \"proxy_server_request\": null, \"error_information\": null, \"attempted_retries\": null, \"max_retries\": null}",
+    "metadata": "{\"actor_agent_id\": null, \"target_agent_id\": null, \"billing_agent_id\": null, \"agent_execution_mode\": null, \"verified_human_user_id\": null, \"applied_guardrails\": [], \"attempted_fallbacks\": null, \"original_model_group\": null, \"batch_models\": null, \"batch_successful_requests\": null, \"batch_failed_requests\": null, \"mcp_tool_call_metadata\": null, \"vector_store_request_metadata\": null, \"routing_decision\": null, \"internal_call_origin\": null, \"router_metadata\": null, \"autorouter_savings_estimate\": null, \"autorouter_baseline_observation\": null, \"azure_spillover\": null, \"guardrail_information\": null, \"compression_savings\": null, \"litellm_gateway_injected_cache\": null, \"usage_object\": {\"completion_tokens\": 20, \"prompt_tokens\": 10, \"total_tokens\": 30, \"completion_tokens_details\": null, \"prompt_tokens_details\": null}, \"model_map_information\": {\"model_map_key\": \"gpt-4o\", \"model_map_value\": {\"key\": \"gpt-4o\", \"max_tokens\": 16384, \"max_input_tokens\": 128000, \"max_output_tokens\": 16384, \"input_cost_per_token\": 2.5e-06, \"cache_creation_input_token_cost\": null, \"cache_read_input_token_cost\": 1.25e-06, \"input_cost_per_character\": null, \"input_cost_per_token_above_128k_tokens\": null, \"input_cost_per_token_above_200k_tokens\": null, \"input_cost_per_query\": null, \"input_cost_per_second\": null, \"input_cost_per_audio_token\": null, \"input_cost_per_token_batches\": 1.25e-06, \"output_cost_per_token_batches\": 5e-06, \"output_cost_per_token\": 1e-05, \"output_cost_per_audio_token\": null, \"output_cost_per_character\": null, \"output_cost_per_token_above_128k_tokens\": null, \"output_cost_per_character_above_128k_tokens\": null, \"output_cost_per_token_above_200k_tokens\": null, \"output_cost_per_second\": null, \"output_cost_per_image\": null, \"output_vector_size\": null, \"litellm_provider\": \"openai\", \"mode\": \"chat\", \"supports_system_messages\": true, \"supports_response_schema\": true, \"supports_vision\": true, \"supports_function_calling\": true, \"supports_tool_choice\": true, \"supports_assistant_prefill\": false, \"supports_prompt_caching\": true, \"supports_audio_input\": false, \"supports_audio_output\": false, \"supports_pdf_input\": false, \"supports_embedding_image_input\": false, \"supports_native_streaming\": null, \"supports_web_search\": true, \"supports_reasoning\": false, \"search_context_cost_per_query\": {\"search_context_size_low\": 0.03, \"search_context_size_medium\": 0.035, \"search_context_size_high\": 0.05}, \"tpm\": null, \"rpm\": null, \"supported_openai_params\": [\"frequency_penalty\", \"logit_bias\", \"logprobs\", \"top_logprobs\", \"max_tokens\", \"max_completion_tokens\", \"modalities\", \"prediction\", \"n\", \"presence_penalty\", \"seed\", \"stop\", \"stream\", \"stream_options\", \"temperature\", \"top_p\", \"tools\", \"tool_choice\", \"function_call\", \"functions\", \"max_retries\", \"extra_headers\", \"parallel_tool_calls\", \"audio\", \"response_format\", \"user\"]}}, \"additional_usage_values\": {\"completion_tokens_details\": null, \"prompt_tokens_details\": null}, \"user_api_key\": null, \"user_api_key_alias\": null, \"user_api_key_team_id\": null, \"user_api_key_project_id\": null, \"user_api_key_project_alias\": null, \"user_api_key_org_id\": null, \"user_api_key_user_id\": null, \"user_api_key_team_alias\": null, \"spend_logs_metadata\": null, \"requester_ip_address\": null, \"user_agent\": null, \"status\": null, \"proxy_server_request\": null, \"error_information\": null, \"attempted_retries\": null, \"max_retries\": null}",
     "cache_key": "Cache OFF",
     "spend": 0.00022500000000000002,
     "total_tokens": 30,
@@ -29,5 +29,6 @@
     "proxy_server_request": "{}",
     "status": "success",
     "mcp_namespaced_tool_name": null,
-    "agent_id": null
+    "agent_id": null,
+    "billing_agent_id": null
 }

tests/test_litellm/proxy/batches_endpoints/test_endpoints.py

@@ -1034,6 +1034,7 @@ def _raw_batches_request(body: Dict[str, Any]) -> MagicMock:
     request.url.__str__.return_value = "http://localhost/v1/batches"
     request.url.path = "/v1/batches"
     request.method = "POST"
+    request.scope = {"type": "http", "method": "POST", "path": "/v1/batches"}
     request.query_params = {}
     request.headers = {"Content-Type": "application/json"}
     request.client = MagicMock()