mirror of
https://github.com/tiennm99/litellm.git
synced 2026-07-04 23:07:50 +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.
252 lines
8.8 KiB
Python
252 lines
8.8 KiB
Python
import sys
|
|
import os
|
|
import traceback
|
|
from dotenv import load_dotenv
|
|
from fastapi import Request
|
|
from datetime import datetime
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
from litellm import Router
|
|
import pytest
|
|
import litellm
|
|
from unittest.mock import patch, MagicMock, AsyncMock
|
|
|
|
import json
|
|
from io import BytesIO
|
|
from typing import Dict, List
|
|
from litellm.router_utils.batch_utils import (
|
|
replace_model_in_jsonl,
|
|
_get_router_metadata_variable_name,
|
|
InMemoryFile,
|
|
parse_jsonl_with_embedded_newlines,
|
|
)
|
|
|
|
|
|
# Fixtures
|
|
@pytest.fixture
|
|
def sample_jsonl_data() -> List[Dict]:
|
|
"""Fixture providing sample JSONL data"""
|
|
return [
|
|
{
|
|
"body": {
|
|
"model": "gpt-5-mini",
|
|
"messages": [{"role": "user", "content": "Hello"}],
|
|
}
|
|
},
|
|
{"body": {"model": "gpt-5.5", "messages": [{"role": "user", "content": "Hi"}]}},
|
|
]
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_jsonl_bytes(sample_jsonl_data) -> bytes:
|
|
"""Fixture providing sample JSONL as bytes"""
|
|
jsonl_str = "\n".join(json.dumps(line) for line in sample_jsonl_data)
|
|
return jsonl_str.encode("utf-8")
|
|
|
|
|
|
@pytest.fixture
|
|
def sample_file_like(sample_jsonl_bytes):
|
|
"""Fixture providing a file-like object"""
|
|
return BytesIO(sample_jsonl_bytes)
|
|
|
|
|
|
# Test cases
|
|
def test_bytes_input(sample_jsonl_bytes):
|
|
"""Test with bytes input"""
|
|
new_model = "claude-3"
|
|
result = replace_model_in_jsonl(sample_jsonl_bytes, new_model)
|
|
|
|
assert result is not None
|
|
assert isinstance(result, InMemoryFile)
|
|
assert result.name == "modified_file.jsonl"
|
|
assert result.content_type == "application/jsonl"
|
|
|
|
|
|
def test_tuple_input(sample_jsonl_bytes):
|
|
"""Test with tuple input"""
|
|
new_model = "claude-3"
|
|
test_tuple = ("test.jsonl", sample_jsonl_bytes, "application/json")
|
|
result = replace_model_in_jsonl(test_tuple, new_model)
|
|
|
|
assert result is not None
|
|
assert isinstance(result, InMemoryFile)
|
|
assert result.name == "modified_file.jsonl"
|
|
assert result.content_type == "application/jsonl"
|
|
|
|
|
|
def test_file_like_object(sample_file_like):
|
|
"""Test with file-like object input"""
|
|
new_model = "claude-3"
|
|
result = replace_model_in_jsonl(sample_file_like, new_model)
|
|
|
|
assert result is not None
|
|
assert isinstance(result, InMemoryFile)
|
|
assert result.name == "modified_file.jsonl"
|
|
assert result.content_type == "application/jsonl"
|
|
|
|
|
|
def test_router_metadata_variable_name():
|
|
"""Test that the variable name is correct"""
|
|
assert _get_router_metadata_variable_name(function_name="completion") == "metadata"
|
|
assert (
|
|
_get_router_metadata_variable_name(function_name="batch") == "litellm_metadata"
|
|
)
|
|
assert (
|
|
_get_router_metadata_variable_name(function_name="acreate_file")
|
|
== "litellm_metadata"
|
|
)
|
|
assert (
|
|
_get_router_metadata_variable_name(function_name="aget_file")
|
|
== "litellm_metadata"
|
|
)
|
|
|
|
|
|
def test_non_json_input():
|
|
"""Test that replace_model_in_jsonl returns original content for non-JSON input"""
|
|
from litellm.router_utils.batch_utils import replace_model_in_jsonl
|
|
|
|
# Test with non-JSON string
|
|
non_json_str = "This is not a JSON string"
|
|
result = replace_model_in_jsonl(non_json_str, "gpt-4")
|
|
assert result == non_json_str
|
|
|
|
# Test with non-JSON bytes
|
|
non_json_bytes = b"This is not JSON bytes"
|
|
result = replace_model_in_jsonl(non_json_bytes, "gpt-4")
|
|
assert result == non_json_bytes
|
|
|
|
# Test with non-JSON file-like object
|
|
from io import BytesIO
|
|
|
|
non_json_file = BytesIO(b"This is not JSON in a file")
|
|
result = replace_model_in_jsonl(non_json_file, "gpt-4")
|
|
assert result == non_json_file
|
|
|
|
|
|
def test_should_replace_model_in_jsonl():
|
|
"""Test that should_replace_model_in_jsonl returns the correct value"""
|
|
from litellm.router_utils.batch_utils import should_replace_model_in_jsonl
|
|
|
|
assert should_replace_model_in_jsonl(purpose="batch") == True
|
|
assert should_replace_model_in_jsonl(purpose="test") == False
|
|
assert should_replace_model_in_jsonl(purpose="user_data") == False
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_simple():
|
|
"""Test parsing simple JSONL without embedded newlines"""
|
|
content = '{"id": 1, "name": "test"}\n{"id": 2, "name": "test2"}'
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 2
|
|
assert result[0] == {"id": 1, "name": "test"}
|
|
assert result[1] == {"id": 2, "name": "test2"}
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_in_strings():
|
|
"""Test parsing JSONL with newlines embedded in string values"""
|
|
content = (
|
|
'{"id": 1, "message": "Line 1\\nLine 2\\nLine 3"}\n{"id": 2, "message": "test"}'
|
|
)
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 2
|
|
assert result[0] == {"id": 1, "message": "Line 1\nLine 2\nLine 3"}
|
|
assert result[1] == {"id": 2, "message": "test"}
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_real_world_example():
|
|
"""Test with the real-world example from the Cooler Master Shark X case"""
|
|
# This simulates the actual problem case from the user's log
|
|
content = """{"custom_id":"16546277850245725","method":"POST","url":"/v1/chat/completions","body":{"model":"openai-gpt-4o-mini-dp-items-translation-dag","messages":[{"role":"system","content":"Translate the product title and description for an e-commerce marketplace in Saudi Arabia and the UAE. Text may be in English or Arabic.\\n"},{"role":"user","content":"\\nOriginal Title: ```Cooler Master Shark X PC Case```\\nOriginal Description: ```UNIQUE MASTERPIECEShark X is a system that provides an impressive unique alternative to traditional PC systems. Shark X will stand out and can be the ultimate trophy or conversation piece for people looking for a unique setup that stands head and fins above the res.```\\nStore Name: ```geekay```\\n"}]}}"""
|
|
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 1
|
|
assert result[0]["custom_id"] == "16546277850245725"
|
|
assert result[0]["method"] == "POST"
|
|
assert result[0]["body"]["model"] == "openai-gpt-4o-mini-dp-items-translation-dag"
|
|
assert len(result[0]["body"]["messages"]) == 2
|
|
assert "Translate the product title" in result[0]["body"]["messages"][0]["content"]
|
|
assert (
|
|
"Cooler Master Shark X PC Case" in result[0]["body"]["messages"][1]["content"]
|
|
)
|
|
assert "UNIQUE MASTERPIECEShark X" in result[0]["body"]["messages"][1]["content"]
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_multiple_complex_objects():
|
|
"""Test parsing multiple complex JSON objects with embedded newlines"""
|
|
content = """{"id":1,"text":"Line 1\\nLine 2"}
|
|
{"id":2,"nested":{"field":"Value\\nWith\\nNewlines"}}
|
|
{"id":3,"simple":"test"}"""
|
|
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 3
|
|
assert result[0]["id"] == 1
|
|
assert result[0]["text"] == "Line 1\nLine 2"
|
|
assert result[1]["id"] == 2
|
|
assert result[1]["nested"]["field"] == "Value\nWith\nNewlines"
|
|
assert result[2]["id"] == 3
|
|
assert result[2]["simple"] == "test"
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_no_trailing_newline():
|
|
"""Test parsing JSONL without trailing newline"""
|
|
content = '{"id": 1, "name": "test"}'
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 1
|
|
assert result[0] == {"id": 1, "name": "test"}
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_empty_string():
|
|
"""Test parsing empty string"""
|
|
content = ""
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 0
|
|
|
|
|
|
def test_parse_jsonl_with_embedded_newlines_whitespace_only():
|
|
"""Test parsing whitespace-only content"""
|
|
content = " \n \n "
|
|
result = parse_jsonl_with_embedded_newlines(content)
|
|
|
|
assert len(result) == 0
|
|
|
|
|
|
def test_replace_model_in_jsonl_with_embedded_newlines():
|
|
"""Test that replace_model_in_jsonl works correctly with embedded newlines in content"""
|
|
# Create a JSONL with embedded newlines in the message content
|
|
jsonl_data = {
|
|
"custom_id": "test123",
|
|
"body": {
|
|
"model": "old-model",
|
|
"messages": [
|
|
{"role": "user", "content": "This is a message\nwith multiple\nlines"}
|
|
],
|
|
},
|
|
}
|
|
|
|
jsonl_bytes = json.dumps(jsonl_data).encode("utf-8")
|
|
new_model = "new-model"
|
|
|
|
result = replace_model_in_jsonl(jsonl_bytes, new_model)
|
|
|
|
assert isinstance(result, InMemoryFile)
|
|
|
|
# Read and parse the result
|
|
result_content = result.read().decode("utf-8")
|
|
result_json = json.loads(result_content)
|
|
|
|
# Verify the model was replaced
|
|
assert result_json["body"]["model"] == "new-model"
|
|
# Verify the content with newlines is preserved
|
|
assert (
|
|
result_json["body"]["messages"][0]["content"]
|
|
== "This is a message\nwith multiple\nlines"
|
|
)
|
|
assert result_json["custom_id"] == "test123"
|