Files
litellm/tests/logging_callback_tests/test_unit_tests_init_callbacks.py
T
Mateo Wang 2c733c00f5 chore(ci): modernize model references in tests and configs (#27856)
* 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.
2026-05-15 15:44:28 -07:00

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"]