Files
litellm/tests/logging_callback_tests/test_opentelemetry_unit_tests.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

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"
)