mirror of
https://github.com/tiennm99/litellm.git
synced 2026-06-17 18:48:36 +00:00
2c733c00f5
* test: modernize models used in CircleCI e2e test suites
Replaces obsolete models (gpt-4o, gpt-4o-mini, gpt-3.5-turbo,
claude-3-5-sonnet-20240620, claude-sonnet-4-20250514) with current
equivalents across the e2e_openai_endpoints and
proxy_e2e_anthropic_messages_tests CircleCI jobs.
- gpt-4o -> gpt-5.5 (responses API e2e tests)
- gpt-4o-mini -> gpt-5-mini (websocket responses, oai_misc_config)
- gpt-4o-mini-2024-07-18 -> gpt-4.1-mini-2025-04-14 (fine-tuning,
still actively fine-tunable)
- gpt-4 / gpt-3.5-turbo target_model_names example -> gpt-5.5 /
gpt-5-mini
- bedrock claude-3-5-sonnet-20240620 batch entry -> haiku-4-5-20251001
(also aligning oai_misc_config model_name with what
test_bedrock_batches_api.py actually requests)
- bedrock claude-sonnet-4-20250514 (deprecated, retires 2026-06-15)
-> claude-sonnet-4-5-20250929
* test: point bedrock-claude-sonnet-4 alias at Sonnet 4.6, not 4.5
Greptile/Cursor flagged that after the previous commit, the
bedrock-claude-sonnet-4 alias collided with bedrock-claude-sonnet-4.5
(both pointed to claude-sonnet-4-5-20250929). Rename to
bedrock-claude-sonnet-4.6 and point it at the Sonnet 4.6 Bedrock ID
(us.anthropic.claude-sonnet-4-6, already in the litellm model
registry) so the alias name matches the underlying model version.
* test: modernize models across remaining CI-mounted configs & tests
Expands the modernization sweep to all CircleCI-mounted proxy configs
and to test directories where the model literal is a fixture/route key
(not the test's subject).
Config changes:
- proxy_server_config.yaml: bump gpt-3.5-turbo / gpt-3.5-turbo-1106 /
gpt-4o / gemini-1.5-flash / dall-e-3 underlying models; rename
gpt-3.5-turbo-end-user-test alias to gpt-5-mini-end-user-test; bump
text-embedding-ada-002 underlying to text-embedding-3-small. User-
facing aliases (gpt-3.5-turbo, gpt-4, text-embedding-ada-002, etc.)
preserved for backward compatibility with tests.
- simple_config.yaml, otel_test_config.yaml, spend_tracking_config.yaml:
bump gpt-3.5-turbo underlying to gpt-5-mini.
- pass_through_config.yaml: claude-3-5-sonnet / claude-3-7-sonnet /
claude-3-haiku entries replaced with claude-sonnet-4-5 / claude-
haiku-4-5 / claude-opus-4-7.
- oai_misc_config.yaml: align alias name with the gpt-5-mini rename.
Test changes (proactive: claude-sonnet-4-20250514 / claude-opus-4-
20250514 retire 2026-06-15):
- tests/llm_translation/test_anthropic_completion.py: bump 3 references
+ paired Vertex AI ID to claude-sonnet-4-5.
- tests/llm_translation/test_optional_params.py: bump 2 references.
- tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py
and test_bedrock_anthropic_messages_test.py: bump router fixtures
using the deprecated model IDs.
- tests/pass_through_unit_tests/base_anthropic_messages_tool_search_test.py:
modernize docstring examples.
- tests/test_end_users.py: update references to renamed alias.
* test: modernize placeholder model literals in router_unit_tests
Mass replace_all on fixture/placeholder model literals across the
router_unit_tests/ suite (model name is a routing key / label, not the
test subject). Sub-agent sweep so far — additional commits will follow
for logging_callback_tests/, enterprise/, top-level tests/test_*.py,
and other CI-mounted dirs.
Mappings applied:
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 / claude-3-opus-20240229 /
claude-3-haiku-20240307 / claude-3-5-sonnet-20240620 ->
claude-sonnet-4-5-20250929 / claude-opus-4-7 /
claude-haiku-4-5-20251001 as appropriate
Explicitly preserved:
- gpt-4o-mini-* variants (transcribe, tts, etc.) where they're current
- gpt-4-turbo / gpt-4-vision-preview / gpt-4-0613 (subject literals)
- JSONL batch body literals
- Mock LLM response model fields (must match upstream)
- Fake/mock identifiers
* test: modernize placeholder model literals across remaining CI suites
Sub-agent sweep across logging_callback_tests/, guardrails_tests/,
enterprise/, pass_through_unit_tests/, otel_tests/,
llm_responses_api_testing/, batches_tests/, spend_tracking_tests/,
litellm_utils_tests/, unified_google_tests/, and a few top-level
tests/test_*.py files where the model literal is a fixture or
placeholder (router model_list, mock standard logging payload, mock
callback data) rather than the test's subject.
Mappings applied (see scope notes below):
- gpt-3.5-turbo -> gpt-5-mini
- gpt-4 (bare) -> gpt-5.5
- gpt-4o (bare) -> gpt-5.5 (corrected from initial gpt-5 — bare gpt-5
is not a valid OpenAI alias; only gpt-5.5 / gpt-5.4 / gpt-5.2-codex
/ gpt-5-mini exist)
- gpt-4o-mini (bare) -> gpt-5-mini
- text-embedding-ada-002 -> text-embedding-3-small
- claude-3-sonnet-20240229 -> claude-sonnet-4-5-20250929
- claude-3-opus-20240229 -> claude-opus-4-7
- claude-3-haiku-20240307 -> claude-haiku-4-5-20251001
- claude-3-5-sonnet-20240620/20241022 -> claude-sonnet-4-5-20250929
- claude-3-7-sonnet-20250219 -> claude-sonnet-4-6
- gemini-1.5-flash -> gemini-2.5-flash
- gemini-1.5-pro -> gemini-2.5-pro
Explicitly preserved (not modernized):
- llm_translation/ tests where model is the SUBJECT (provider-specific
translation/transformation logic). Only the deprecated 20250514
references were already bumped in a prior commit.
- Cost-calc / tokenizer subject tests in test_utils.py (skip-ranges
documented by the sub-agent).
- Bedrock model IDs in test_health_check.py path-stripping tests.
- JSONL batch request bodies and mock LLM response bodies (must match
upstream literal).
- Langfuse expected-request-body JSON fixtures (cost values are exact-
match-asserted; changing the model would shift response_cost).
- gpt-3.5-turbo-instruct (text-completion endpoint; no modern OpenAI
equivalent).
- Top-level tests calling the proxy through user-facing aliases
(gpt-3.5-turbo, gpt-4, text-embedding-ada-002, dall-e-3) — aliases
in proxy_server_config.yaml stay; only the underlying model was
bumped.
- tests/test_gpt5_azure_temperature_support.py (the test's whole point
is model-name handling).
- Fake / mock / openai/fake identifiers.
Notable side fixes:
- test_spend_accuracy_tests.py: UPSTREAM_MODEL now matches what
spend_tracking_config.yaml's proxy actually routes to (gpt-5-mini),
resolving a latent inconsistency.
- proxy_server_config.yaml: bare `gpt-5` alias renamed to `gpt-5.5`
(bare gpt-5 is not a valid OpenAI alias).
- test_batches_logging_unit_tests.py: explicit_models list entries
kept distinct (gpt-5-mini + gpt-5.5) after bulk rename.
* test: fix CI failures from model modernization sweep
CI surfaced 4 categories of regression from the bulk modernization:
1. Azure deployment names are customer-specific. Reverted:
- tests/litellm_utils_tests/test_health_check.py: azure/text-
embedding-3-small -> azure/text-embedding-ada-002 (the CI Azure
account does not have a text-embedding-3-small deployment).
- tests/logging_callback_tests/test_custom_callback_router.py:
same revert for two router fixtures driving aembedding.
2. gpt-5 family does not accept temperature != 1. Tests that pass a
custom temperature swapped from gpt-5-mini to gpt-4.1-mini (modern
non-reasoning OpenAI mini that still accepts temperature/logprobs):
- tests/logging_callback_tests/test_datadog.py
- tests/logging_callback_tests/test_langsmith_unit_test.py
- tests/logging_callback_tests/test_otel_logging.py
3. proxy_server_config.yaml's gpt-3.5-turbo-large alias was routing to
gpt-5.5 (a reasoning model that rejects logprobs). The proxy test
tests/test_openai_endpoints.py::test_chat_completion_streaming
exercises logprobs/top_logprobs through that alias. Bumped the
underlying model to gpt-4.1 (non-reasoning, still modern).
4. tests/logging_callback_tests/test_gcs_pub_sub.py asserts against a
pinned JSON fixture (gcs_pub_sub_body/spend_logs_payload.json) with
hardcoded model="gpt-4o" and a model-specific spend value. Reverted
the litellm.acompletion calls in the test to model="gpt-4o" so the
fixture's exact-match assertions still hold.
5. tests/pass_through_unit_tests/test_anthropic_messages_passthrough.py:
anthropic.messages.create routing to openai/gpt-5-mini returned an
empty content[0] with max_tokens=100 (reasoning-token consumption).
Swapped to openai/gpt-4.1-mini.
* test: fix Assistants API model + 2 cursor[bot] review nits
1. pass_through_unit_tests/test_custom_logger_passthrough.py: gpt-5.5
isn't accepted by the /v1/assistants endpoint
("unsupported_model"). Switch to gpt-4.1-mini (modern, Assistants-
API-supported, non-reasoning).
2. example_config_yaml/pass_through_config.yaml: the previous sweep
bumped the claude-3-7-sonnet alias to claude-opus-4-7, which is a
tier change (Sonnet -> Opus). Map to claude-sonnet-4-6 to keep the
Sonnet tier intact. (Cursor bugbot review.)
3. example_config_yaml/simple_config.yaml: model_name was left as
gpt-3.5-turbo while the underlying was bumped to gpt-5-mini, which
muddles the "simple" example. Make both sides gpt-5-mini so the
most basic example is a straight 1:1 mapping again. (Cursor bugbot
review.)
* fix: revert gpt-4/gpt-3.5-turbo alias underlying to non-reasoning models
tests/test_openai_endpoints.py::test_completion calls the proxy alias
"gpt-4" with temperature=0, and other tests call gpt-3.5-turbo with
custom temperature / logprobs / the legacy /v1/completions endpoint.
The earlier modernization mapped both aliases to gpt-5.5 / gpt-5-mini,
which are reasoning models that reject temperature != 1 and don't
expose /v1/completions. Map the aliases to gpt-4.1 / gpt-4.1-mini
(modern non-reasoning OpenAI models) instead — keeps user-facing
aliases preserved while picking a current underlying that still
supports the parameters/endpoints the tests exercise.
321 lines
11 KiB
Python
321 lines
11 KiB
Python
import json
|
|
import os
|
|
import sys
|
|
from datetime import datetime
|
|
from unittest.mock import AsyncMock
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system-path
|
|
|
|
from typing import Literal
|
|
|
|
import pytest
|
|
import litellm
|
|
import asyncio
|
|
import logging
|
|
from litellm._logging import verbose_logger
|
|
from prometheus_client import REGISTRY, CollectorRegistry
|
|
from unittest.mock import patch
|
|
from litellm.litellm_core_utils.custom_logger_registry import (
|
|
CustomLoggerRegistry,
|
|
)
|
|
|
|
# clear prometheus collectors / registry
|
|
collectors = list(REGISTRY._collector_to_names.keys())
|
|
for collector in collectors:
|
|
REGISTRY.unregister(collector)
|
|
######################################
|
|
|
|
|
|
expected_env_vars = {
|
|
"LAGO_API_KEY": "api_key",
|
|
"LAGO_API_BASE": "mock_base",
|
|
"LAGO_API_EVENT_CODE": "mock_event_code",
|
|
"OPENMETER_API_KEY": "openmeter_api_key",
|
|
"BRAINTRUST_API_BASE": "braintrust_api_base",
|
|
"BRAINTRUST_API_KEY": "braintrust_api_key",
|
|
"GALILEO_API_KEY": "galileo_api_key",
|
|
"LITERAL_API_KEY": "literal_api_key",
|
|
"DD_API_KEY": "datadog_api_key",
|
|
"DD_SITE": "datadog_site",
|
|
"GOOGLE_APPLICATION_CREDENTIALS": "gcs_credentials",
|
|
"OPIK_API_KEY": "opik_api_key",
|
|
"LANGTRACE_API_KEY": "langtrace_api_key",
|
|
"LOGFIRE_TOKEN": "logfire_token",
|
|
"ARIZE_SPACE_KEY": "arize_space_key",
|
|
"ARIZE_API_KEY": "arize_api_key",
|
|
"PHOENIX_API_KEY": "phoenix_api_key",
|
|
"ARGILLA_API_KEY": "argilla_api_key",
|
|
"PAGERDUTY_API_KEY": "pagerduty_api_key",
|
|
"GCS_PUBSUB_TOPIC_ID": "gcs_pubsub_topic_id",
|
|
"GCS_PUBSUB_PROJECT_ID": "gcs_pubsub_project_id",
|
|
"CONFIDENT_API_KEY": "confident_api_key",
|
|
"LITELM_ENVIRONMENT": "development",
|
|
"AWS_BUCKET_NAME": "aws_bucket_name",
|
|
"AWS_SECRET_ACCESS_KEY": "aws_secret_access_key",
|
|
"AWS_ACCESS_KEY_ID": "aws_access_key_id",
|
|
"AWS_REGION": "aws_region",
|
|
"AWS_SQS_QUEUE_URL": "https://sqs.us-east-1.amazonaws.com/123456789012/test-queue",
|
|
}
|
|
|
|
|
|
def reset_all_callbacks():
|
|
litellm.callbacks = []
|
|
litellm.input_callback = []
|
|
litellm.success_callback = []
|
|
litellm.failure_callback = []
|
|
litellm._async_success_callback = []
|
|
litellm._async_failure_callback = []
|
|
|
|
|
|
initial_env_vars = {}
|
|
|
|
|
|
def init_env_vars():
|
|
for env_var, value in expected_env_vars.items():
|
|
if env_var not in os.environ:
|
|
os.environ[env_var] = value
|
|
else:
|
|
initial_env_vars[env_var] = os.environ[env_var]
|
|
|
|
|
|
def reset_env_vars():
|
|
for env_var, value in initial_env_vars.items():
|
|
os.environ[env_var] = value
|
|
|
|
|
|
all_callback_required_env_vars = []
|
|
|
|
|
|
async def use_callback_in_llm_call(
|
|
callback: str, used_in: Literal["callbacks", "success_callback"]
|
|
):
|
|
if callback == "dynamic_rate_limiter":
|
|
# internal CustomLogger class that expects internal_usage_cache passed to it, it always fails when tested in this way
|
|
return
|
|
elif callback == "dynamic_rate_limiter_v3":
|
|
# internal CustomLogger class that expects internal_usage_cache passed to it, it always fails when tested in this way
|
|
return
|
|
elif callback == "argilla":
|
|
litellm.argilla_transformation_object = {}
|
|
elif callback == "openmeter":
|
|
# it's currently handled in jank way, TODO: fix openmete and then actually run it's test
|
|
return
|
|
elif callback == "bitbucket" or callback == "gitlab":
|
|
# Set up mock bitbucket configuration required for initialization
|
|
litellm.global_bitbucket_config = {
|
|
"workspace": "test-workspace",
|
|
"repository": "test-repo",
|
|
"access_token": "test-token",
|
|
"branch": "main",
|
|
}
|
|
litellm.global_gitlab_config = {
|
|
"project": "a/b/<repo_name>",
|
|
"access_token": "your-access-token",
|
|
"base_url": "gitlab url",
|
|
"prompts_path": "src/prompts", # folder to point to, defaults to root
|
|
"branch": "main", # optional, defaults to main
|
|
}
|
|
# Mock BitBucket HTTP calls to prevent actual API requests
|
|
import httpx
|
|
from unittest.mock import MagicMock
|
|
|
|
mock_response = MagicMock()
|
|
mock_response.status_code = 200
|
|
mock_response.json.return_value = {"values": []}
|
|
mock_response.text = ""
|
|
|
|
patch.object(
|
|
litellm.module_level_client, "get", return_value=mock_response
|
|
).start()
|
|
elif callback == "prometheus":
|
|
# pytest teardown - clear existing prometheus collectors
|
|
collectors = list(REGISTRY._collector_to_names.keys())
|
|
for collector in collectors:
|
|
REGISTRY.unregister(collector)
|
|
|
|
# Mock the httpx call for Argilla dataset retrieval
|
|
if callback == "argilla":
|
|
import httpx
|
|
|
|
mock_response = httpx.Response(
|
|
status_code=200, json={"items": [{"id": "mocked_dataset_id"}]}
|
|
)
|
|
patch.object(
|
|
litellm.module_level_client, "get", return_value=mock_response
|
|
).start()
|
|
|
|
# Mock the httpx call for Argilla dataset retrieval
|
|
if callback == "argilla":
|
|
import httpx
|
|
|
|
mock_response = httpx.Response(
|
|
status_code=200, json={"items": [{"id": "mocked_dataset_id"}]}
|
|
)
|
|
patch.object(
|
|
litellm.module_level_client, "get", return_value=mock_response
|
|
).start()
|
|
|
|
if used_in == "callbacks":
|
|
litellm.callbacks = [callback]
|
|
elif used_in == "success_callback":
|
|
litellm.success_callback = [callback]
|
|
|
|
for _ in range(5):
|
|
await litellm.acompletion(
|
|
model="gpt-5-mini",
|
|
messages=[{"role": "user", "content": "hi"}],
|
|
temperature=0.1,
|
|
mock_response="hello",
|
|
)
|
|
|
|
await asyncio.sleep(0.5)
|
|
|
|
expected_class = CustomLoggerRegistry.CALLBACK_CLASS_STR_TO_CLASS_TYPE[callback]
|
|
|
|
if used_in == "callbacks":
|
|
assert isinstance(litellm._async_success_callback[0], expected_class)
|
|
assert isinstance(litellm._async_failure_callback[0], expected_class)
|
|
assert isinstance(litellm.success_callback[0], expected_class)
|
|
assert isinstance(litellm.failure_callback[0], expected_class)
|
|
|
|
assert (
|
|
len(litellm._async_success_callback) == 1
|
|
), f"Got={litellm._async_success_callback}"
|
|
assert len(litellm._async_failure_callback) == 1
|
|
assert len(litellm.success_callback) == 1
|
|
assert len(litellm.failure_callback) == 1
|
|
assert len(litellm.callbacks) == 1
|
|
elif used_in == "success_callback":
|
|
print(f"litellm.success_callback: {litellm.success_callback}")
|
|
print(f"litellm._async_success_callback: {litellm._async_success_callback}")
|
|
assert isinstance(litellm.success_callback[0], expected_class)
|
|
assert len(litellm.success_callback) == 1 # ["lago", LagoLogger]
|
|
assert isinstance(litellm._async_success_callback[0], expected_class)
|
|
assert len(litellm._async_success_callback) == 1
|
|
|
|
# TODO also assert that it's not set for failure_callback
|
|
# As of Oct 21 2024, it's currently set
|
|
# 1st hoping to add test coverage for just setting in success_callback/_async_success_callback
|
|
|
|
if callback == "argilla":
|
|
patch.stopall()
|
|
|
|
if callback == "bitbucket":
|
|
# Clean up bitbucket configuration and patches
|
|
if hasattr(litellm, "global_bitbucket_config"):
|
|
delattr(litellm, "global_bitbucket_config")
|
|
patch.stopall()
|
|
|
|
|
|
def test_dynamic_logging_global_callback():
|
|
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
|
from litellm.integrations.custom_logger import CustomLogger
|
|
from litellm.types.utils import ModelResponse, Choices, Message, Usage
|
|
|
|
cl = CustomLogger()
|
|
|
|
litellm_logging = LiteLLMLoggingObj(
|
|
model="claude-opus-4-7",
|
|
messages=[{"role": "user", "content": "hi"}],
|
|
stream=False,
|
|
call_type="completion",
|
|
start_time=datetime.now(),
|
|
litellm_call_id="123",
|
|
function_id="456",
|
|
kwargs={
|
|
"langfuse_public_key": "my-mock-public-key",
|
|
"langfuse_secret_key": "my-mock-secret-key",
|
|
},
|
|
dynamic_success_callbacks=["langfuse"],
|
|
)
|
|
|
|
with patch.object(cl, "log_success_event") as mock_log_success_event:
|
|
cl.log_success_event = mock_log_success_event
|
|
litellm.success_callback = [cl]
|
|
|
|
try:
|
|
litellm_logging.success_handler(
|
|
result=ModelResponse(
|
|
id="chatcmpl-5418737b-ab14-420b-b9c5-b278b6681b70",
|
|
created=1732306261,
|
|
model="claude-opus-4-7",
|
|
object="chat.completion",
|
|
system_fingerprint=None,
|
|
choices=[
|
|
Choices(
|
|
finish_reason="stop",
|
|
index=0,
|
|
message=Message(
|
|
content="hello",
|
|
role="assistant",
|
|
tool_calls=None,
|
|
function_call=None,
|
|
),
|
|
)
|
|
],
|
|
usage=Usage(
|
|
completion_tokens=20,
|
|
prompt_tokens=10,
|
|
total_tokens=30,
|
|
completion_tokens_details=None,
|
|
prompt_tokens_details=None,
|
|
),
|
|
),
|
|
start_time=datetime.now(),
|
|
end_time=datetime.now(),
|
|
cache_hit=False,
|
|
)
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|
|
|
|
mock_log_success_event.assert_called_once()
|
|
|
|
|
|
def test_get_combined_callback_list():
|
|
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
|
|
|
_logging = LiteLLMLoggingObj(
|
|
model="claude-opus-4-7",
|
|
messages=[{"role": "user", "content": "hi"}],
|
|
stream=False,
|
|
call_type="completion",
|
|
start_time=datetime.now(),
|
|
litellm_call_id="123",
|
|
function_id="456",
|
|
)
|
|
|
|
assert "langfuse" in _logging.get_combined_callback_list(
|
|
dynamic_success_callbacks=["langfuse"], global_callbacks=["lago"]
|
|
)
|
|
assert "lago" in _logging.get_combined_callback_list(
|
|
dynamic_success_callbacks=["langfuse"], global_callbacks=["lago"]
|
|
)
|
|
|
|
|
|
def test_get_combined_callback_list_returns_copy_when_dynamic_is_none():
|
|
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
|
|
|
_logging = LiteLLMLoggingObj(
|
|
model="claude-opus-4-7",
|
|
messages=[{"role": "user", "content": "hi"}],
|
|
stream=False,
|
|
call_type="completion",
|
|
start_time=datetime.now(),
|
|
litellm_call_id="123",
|
|
function_id="456",
|
|
)
|
|
|
|
global_callbacks = ["langfuse"]
|
|
combined_callbacks = _logging.get_combined_callback_list(
|
|
dynamic_success_callbacks=None, global_callbacks=global_callbacks
|
|
)
|
|
|
|
assert combined_callbacks == ["langfuse"]
|
|
assert combined_callbacks is not global_callbacks
|
|
|
|
combined_callbacks.append("new_callback")
|
|
|
|
assert global_callbacks == ["langfuse"]
|