mirror of
https://github.com/tiennm99/litellm.git
synced 2026-06-17 12:48:57 +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.
216 lines
8.3 KiB
Python
216 lines
8.3 KiB
Python
# What is this?
|
|
## Unit tests for opentelemetry integration
|
|
|
|
# What is this?
|
|
## Unit test for presidio pii masking
|
|
import sys, os, asyncio, time, random
|
|
from datetime import datetime
|
|
import traceback
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
import os
|
|
import asyncio
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
import pytest
|
|
import litellm
|
|
from unittest.mock import patch, MagicMock, AsyncMock
|
|
from base_test import BaseLoggingCallbackTest
|
|
from litellm.types.utils import ModelResponse
|
|
|
|
|
|
class TestOpentelemetryUnitTests(BaseLoggingCallbackTest):
|
|
def test_parallel_tool_calls(self, mock_response_obj: ModelResponse):
|
|
tool_calls = mock_response_obj.choices[0].message.tool_calls
|
|
from litellm.integrations.opentelemetry import OpenTelemetry
|
|
from litellm.proxy._types import SpanAttributes
|
|
|
|
kv_pair_dict = OpenTelemetry._tool_calls_kv_pair(tool_calls)
|
|
|
|
assert kv_pair_dict == {
|
|
f"{SpanAttributes.LLM_COMPLETIONS.value}.0.function_call.arguments": '{"city": "New York"}',
|
|
f"{SpanAttributes.LLM_COMPLETIONS.value}.0.function_call.name": "get_weather",
|
|
f"{SpanAttributes.LLM_COMPLETIONS.value}.1.function_call.arguments": '{"city": "New York"}',
|
|
f"{SpanAttributes.LLM_COMPLETIONS.value}.1.function_call.name": "get_news",
|
|
}
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_opentelemetry_integration(self):
|
|
"""
|
|
Unit test to confirm external parent otel spans are NOT ended by LiteLLM.
|
|
|
|
External spans (passed via metadata) should be managed by their creators,
|
|
not by LiteLLM. This prevents premature closure of spans from Langfuse,
|
|
user code, or other external observability tools.
|
|
"""
|
|
# Reset all callbacks to ensure clean state
|
|
litellm.logging_callback_manager._reset_all_callbacks()
|
|
|
|
parent_otel_span = MagicMock()
|
|
litellm.callbacks = ["otel"]
|
|
|
|
await litellm.acompletion(
|
|
model="gpt-5-mini",
|
|
messages=[{"role": "user", "content": "Hello, world!"}],
|
|
mock_response="Hey!",
|
|
metadata={"litellm_parent_otel_span": parent_otel_span},
|
|
)
|
|
|
|
await asyncio.sleep(1)
|
|
|
|
# Verify external span was NOT ended by LiteLLM
|
|
# External spans should only be closed by their creators
|
|
parent_otel_span.end.assert_not_called()
|
|
|
|
def test_get_span_context_detects_active_span(self):
|
|
"""
|
|
Unit test: _get_span_context() should auto-detect active spans from global context.
|
|
|
|
Active spans should be automatically detected without explicit metadata
|
|
"""
|
|
from opentelemetry import trace
|
|
from opentelemetry.sdk.trace import TracerProvider
|
|
from litellm.integrations.opentelemetry import OpenTelemetry
|
|
|
|
# Setup: Create TracerProvider and tracer
|
|
tracer_provider = TracerProvider()
|
|
trace.set_tracer_provider(tracer_provider)
|
|
tracer = trace.get_tracer(__name__)
|
|
|
|
# Create OpenTelemetry integration
|
|
otel_integration = OpenTelemetry()
|
|
|
|
# Act: Create an active span and test detection
|
|
with tracer.start_as_current_span("test_parent") as parent_span:
|
|
parent_span_context = parent_span.get_span_context()
|
|
|
|
# Call _get_span_context without explicit parent in metadata
|
|
kwargs = {"litellm_params": {"metadata": {}}}
|
|
detected_context, detected_span = otel_integration._get_span_context(kwargs)
|
|
|
|
# Assert: Should detect the active span
|
|
assert (
|
|
detected_span is not None
|
|
), "Should detect active span from global context"
|
|
assert (
|
|
detected_span is parent_span
|
|
), "Detected span should be the active parent span"
|
|
|
|
detected_span_context = detected_span.get_span_context()
|
|
assert (
|
|
detected_span_context.trace_id == parent_span_context.trace_id
|
|
), "Detected span should have same trace_id as parent"
|
|
assert (
|
|
detected_span_context.span_id == parent_span_context.span_id
|
|
), "Detected span should have same span_id as parent"
|
|
|
|
def test_record_exception_on_span(self):
|
|
"""
|
|
Test that _record_exception_on_span properly records exception information.
|
|
|
|
This test verifies that StandardLoggingPayloadErrorInformation is properly
|
|
extracted and set as span attributes using ErrorAttributes constants.
|
|
"""
|
|
from opentelemetry import trace
|
|
from opentelemetry.sdk.trace import TracerProvider
|
|
from litellm.integrations.opentelemetry import OpenTelemetry
|
|
from litellm.integrations._types.open_inference import ErrorAttributes
|
|
|
|
# Setup: Create TracerProvider and tracer
|
|
tracer_provider = TracerProvider()
|
|
trace.set_tracer_provider(tracer_provider)
|
|
tracer = trace.get_tracer(__name__)
|
|
|
|
# Create OpenTelemetry integration
|
|
otel_integration = OpenTelemetry()
|
|
|
|
# Create a mock span
|
|
mock_span = MagicMock()
|
|
|
|
# Create test exception
|
|
test_exception = ValueError("Test error message")
|
|
|
|
# Create kwargs with exception and error_information
|
|
kwargs = {
|
|
"exception": test_exception,
|
|
"standard_logging_object": {
|
|
"error_information": {
|
|
"error_code": "500",
|
|
"error_class": "ValueError",
|
|
"llm_provider": "openai",
|
|
"traceback": "Traceback (most recent call last)...",
|
|
"error_message": "Test error message",
|
|
},
|
|
"error_str": "Test error message",
|
|
},
|
|
}
|
|
|
|
# Act: Record exception on span
|
|
otel_integration._record_exception_on_span(span=mock_span, kwargs=kwargs)
|
|
|
|
# Assert: span.record_exception should be called with the exception
|
|
mock_span.record_exception.assert_called_once_with(test_exception)
|
|
|
|
# Assert: Error attributes should be set using ErrorAttributes constants
|
|
expected_calls = [
|
|
(ErrorAttributes.ERROR_CODE, "500"),
|
|
(ErrorAttributes.ERROR_TYPE, "ValueError"),
|
|
(ErrorAttributes.ERROR_MESSAGE, "Test error message"),
|
|
(ErrorAttributes.ERROR_LLM_PROVIDER, "openai"),
|
|
(ErrorAttributes.ERROR_STACK_TRACE, "Traceback (most recent call last)..."),
|
|
]
|
|
|
|
# Check that set_attribute was called with expected values
|
|
actual_calls = [call.args for call in mock_span.set_attribute.call_args_list]
|
|
|
|
for expected_call in expected_calls:
|
|
assert (
|
|
expected_call in actual_calls
|
|
), f"Expected set_attribute call {expected_call} not found in actual calls: {actual_calls}"
|
|
|
|
def test_record_exception_on_span_with_fallback(self):
|
|
"""
|
|
Test that _record_exception_on_span falls back to error_str when error_information is None.
|
|
"""
|
|
from opentelemetry import trace
|
|
from opentelemetry.sdk.trace import TracerProvider
|
|
from litellm.integrations.opentelemetry import OpenTelemetry
|
|
from litellm.integrations._types.open_inference import ErrorAttributes
|
|
|
|
# Setup: Create TracerProvider and tracer
|
|
tracer_provider = TracerProvider()
|
|
trace.set_tracer_provider(tracer_provider)
|
|
tracer = trace.get_tracer(__name__)
|
|
|
|
# Create OpenTelemetry integration
|
|
otel_integration = OpenTelemetry()
|
|
|
|
# Create a mock span
|
|
mock_span = MagicMock()
|
|
|
|
# Create test exception
|
|
test_exception = ValueError("Test error message")
|
|
|
|
# Create kwargs without error_information (should fallback to error_str)
|
|
kwargs = {
|
|
"exception": test_exception,
|
|
"standard_logging_object": {
|
|
"error_information": None,
|
|
"error_str": "Fallback error message",
|
|
},
|
|
}
|
|
|
|
# Act: Record exception on span
|
|
otel_integration._record_exception_on_span(span=mock_span, kwargs=kwargs)
|
|
|
|
# Assert: span.record_exception should be called
|
|
mock_span.record_exception.assert_called_once_with(test_exception)
|
|
|
|
# Assert: error.message should be set from error_str using ErrorAttributes constant
|
|
mock_span.set_attribute.assert_called_with(
|
|
ErrorAttributes.ERROR_MESSAGE, "Fallback error message"
|
|
)
|