Files
litellm/tests/router_unit_tests/test_router_batch_utils.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

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"