Files
litellm/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py
T
Mateo WangandGitHub 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

201 lines
6.1 KiB
Python

import httpx
from openai import OpenAI, BadRequestError
import pytest
def generate_key():
"""Generate a key for testing"""
url = "http://0.0.0.0:4000/key/generate"
headers = {
"Authorization": "Bearer sk-1234",
"Content-Type": "application/json",
}
data = {}
response = httpx.post(url, headers=headers, json=data)
if response.status_code != 200:
raise Exception(f"Key generation failed with status: {response.status_code}")
return response.json()["key"]
def get_test_client():
"""Create OpenAI client with generated key"""
key = generate_key()
return OpenAI(api_key=key, base_url="http://0.0.0.0:4000")
def validate_response(response):
"""
Validate basic response structure from OpenAI responses API
"""
assert response is not None
assert hasattr(response, "choices")
assert len(response.choices) > 0
assert hasattr(response.choices[0], "message")
assert hasattr(response.choices[0].message, "content")
assert isinstance(response.choices[0].message.content, str)
assert hasattr(response, "id")
assert isinstance(response.id, str)
assert hasattr(response, "model")
assert isinstance(response.model, str)
assert hasattr(response, "created")
assert isinstance(response.created, int)
assert hasattr(response, "usage")
assert hasattr(response.usage, "prompt_tokens")
assert hasattr(response.usage, "completion_tokens")
assert hasattr(response.usage, "total_tokens")
def validate_stream_chunk(chunk):
"""
Validate streaming chunk structure from OpenAI responses API
"""
assert chunk is not None
assert hasattr(chunk, "choices")
assert len(chunk.choices) > 0
assert hasattr(chunk.choices[0], "delta")
# Some chunks might not have content in the delta
if (
hasattr(chunk.choices[0].delta, "content")
and chunk.choices[0].delta.content is not None
):
assert isinstance(chunk.choices[0].delta.content, str)
assert hasattr(chunk, "id")
assert isinstance(chunk.id, str)
assert hasattr(chunk, "model")
assert isinstance(chunk.model, str)
assert hasattr(chunk, "created")
assert isinstance(chunk.created, int)
@pytest.mark.flaky(retries=3, delay=2)
def test_basic_response():
client = get_test_client()
response = client.responses.create(
model="gpt-5.5", input="just respond with the word 'ping'"
)
print("basic response=", response)
# get the response
response = client.responses.retrieve(response.id)
print("GET response=", response)
# delete the response
delete_response = client.responses.delete(response.id)
print("DELETE response=", delete_response)
# expect an error when getting the response again since it was deleted
with pytest.raises(Exception):
get_response = client.responses.retrieve(response.id)
def test_streaming_response():
client = get_test_client()
stream = client.responses.create(
model="gpt-5.5", input="just respond with the word 'ping'", stream=True
)
collected_chunks = []
for chunk in stream:
print("stream chunk=", chunk)
collected_chunks.append(chunk)
assert len(collected_chunks) > 0
def test_bad_request_error():
client = get_test_client()
with pytest.raises(BadRequestError):
# Trigger error with invalid model name
client.responses.create(model="non-existent-model", input="This should fail")
def test_bad_request_bad_param_error():
client = get_test_client()
with pytest.raises(BadRequestError):
# Trigger error with invalid model name
client.responses.create(
model="gpt-5.5", input="This should fail", temperature=2000
)
def test_anthropic_with_responses_api():
client = get_test_client()
response = client.responses.create(
model="anthropic/claude-sonnet-4-5-20250929",
input="just respond with the word 'ping'",
previous_response_id="hi",
)
print("anthropic response=", response)
def test_cancel_response():
try:
client = get_test_client()
from litellm.types.llms.openai import ResponsesAPIResponse
response = client.responses.create(
model="gpt-5.5", input="just respond with the word 'ping'", background=True
)
print("basic response=", response)
# cancel the response
cancel_response = client.responses.cancel(response.id)
print("CANCEL response=", cancel_response)
# verify cancel response structure
assert hasattr(cancel_response, "id")
except Exception as e:
if "Cannot cancel a completed response" in str(e):
pass
else:
raise e
def test_cancel_streaming_response():
try:
client = get_test_client()
from litellm.types.llms.openai import ResponsesAPIResponse
stream = client.responses.create(
model="gpt-5.5",
input="just respond with the word 'ping'",
stream=True,
background=True,
)
collected_chunks = []
response_id = None
for chunk in stream:
print("stream chunk=", chunk)
collected_chunks.append(chunk)
# Extract response ID from the first chunk that has it
if (
response_id is None
and hasattr(chunk, "response")
and hasattr(chunk.response, "id")
):
response_id = chunk.response.id
assert len(collected_chunks) > 0
# cancel the response if we got a response ID
if response_id:
cancel_response = client.responses.cancel(response_id)
print("CANCEL streaming response=", cancel_response)
assert hasattr(cancel_response, "id")
except Exception as e:
if "Cannot cancel a completed response" in str(e):
pass
else:
raise e
def test_cancel_invalid_response_id():
client = get_test_client()
with pytest.raises(Exception):
# Try to cancel a non-existent response ID
client.responses.cancel("invalid_response_id_12345")