mirror of
https://github.com/tiennm99/litellm.git
synced 2026-07-12 19:04:59 +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.
480 lines
16 KiB
Python
480 lines
16 KiB
Python
import asyncio
|
|
import base64
|
|
import json
|
|
import os
|
|
from copy import deepcopy
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
from urllib.parse import unquote
|
|
|
|
import litellm
|
|
import pytest
|
|
|
|
from litellm.integrations.sqs import SQSLogger
|
|
from litellm.types.utils import StandardLoggingPayload
|
|
|
|
from litellm.litellm_core_utils.app_crypto import AppCrypto
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_sqs_logger_flush():
|
|
expected_queue_url = "https://sqs.us-east-1.amazonaws.com/123456789012/test-queue"
|
|
expected_region = "us-east-1"
|
|
|
|
sqs_logger = SQSLogger(
|
|
sqs_queue_url=expected_queue_url,
|
|
sqs_region_name=expected_region,
|
|
sqs_flush_interval=1,
|
|
)
|
|
|
|
# Mock the httpx client
|
|
mock_response = MagicMock()
|
|
mock_response.raise_for_status = MagicMock()
|
|
sqs_logger.async_httpx_client.post = AsyncMock(return_value=mock_response)
|
|
|
|
litellm.callbacks = [sqs_logger]
|
|
|
|
await litellm.acompletion(
|
|
model="gpt-5.5",
|
|
messages=[{"role": "user", "content": "hello"}],
|
|
mock_response="hi",
|
|
)
|
|
|
|
await asyncio.sleep(2)
|
|
|
|
# Verify that httpx post was called
|
|
sqs_logger.async_httpx_client.post.assert_called()
|
|
|
|
# Get the call arguments
|
|
call_args = sqs_logger.async_httpx_client.post.call_args
|
|
|
|
# Verify the URL is correct
|
|
called_url = call_args[0][0] # First positional argument
|
|
assert (
|
|
called_url == expected_queue_url
|
|
), f"Expected URL {expected_queue_url}, got {called_url}"
|
|
|
|
# Verify the payload contains StandardLoggingPayload data
|
|
called_data = call_args.kwargs["data"]
|
|
|
|
# Extract the MessageBody from the URL-encoded data
|
|
# Format: "Action=SendMessage&Version=2012-11-05&MessageBody=<url_encoded_json>"
|
|
assert "Action=SendMessage" in called_data
|
|
assert "Version=2012-11-05" in called_data
|
|
assert "MessageBody=" in called_data
|
|
|
|
# Extract and decode the message body
|
|
message_body_start = called_data.find("MessageBody=") + len("MessageBody=")
|
|
message_body_encoded = called_data[message_body_start:]
|
|
message_body_json = unquote(message_body_encoded)
|
|
|
|
# Parse the JSON to verify it's a StandardLoggingPayload
|
|
payload_data = json.loads(message_body_json)
|
|
|
|
# Verify it has the expected StandardLoggingPayload structure
|
|
assert "model" in payload_data
|
|
assert "messages" in payload_data
|
|
assert "response" in payload_data
|
|
assert payload_data["model"] == "gpt-5.5"
|
|
assert len(payload_data["messages"]) == 1
|
|
assert payload_data["messages"][0]["role"] == "user"
|
|
assert payload_data["messages"][0]["content"] == "hello"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_sqs_logger_error_flush():
|
|
expected_queue_url = "https://sqs.us-east-1.amazonaws.com/123456789012/test-queue"
|
|
expected_region = "us-east-1"
|
|
|
|
sqs_logger = SQSLogger(
|
|
sqs_queue_url=expected_queue_url,
|
|
sqs_region_name=expected_region,
|
|
sqs_flush_interval=1,
|
|
)
|
|
|
|
# Mock the httpx client
|
|
mock_response = MagicMock()
|
|
mock_response.raise_for_status = Exception("Something went wrong")
|
|
sqs_logger.async_httpx_client.post = AsyncMock(return_value=mock_response)
|
|
|
|
litellm.callbacks = [sqs_logger]
|
|
|
|
await litellm.acompletion(
|
|
model="gpt-5.5",
|
|
messages=[{"role": "user", "content": "hello"}],
|
|
mock_response="Error occurred",
|
|
)
|
|
|
|
await asyncio.sleep(2)
|
|
|
|
# Verify that httpx post was called
|
|
sqs_logger.async_httpx_client.post.assert_called()
|
|
|
|
# Get the call arguments
|
|
call_args = sqs_logger.async_httpx_client.post.call_args
|
|
|
|
# Verify the URL is correct
|
|
called_url = call_args[0][0] # First positional argument
|
|
assert (
|
|
called_url == expected_queue_url
|
|
), f"Expected URL {expected_queue_url}, got {called_url}"
|
|
|
|
# Verify the payload contains StandardLoggingPayload data
|
|
called_data = call_args.kwargs["data"]
|
|
|
|
# Extract the MessageBody from the URL-encoded data
|
|
# Format: "Action=SendMessage&Version=2012-11-05&MessageBody=<url_encoded_json>"
|
|
assert "Action=SendMessage" in called_data
|
|
assert "Version=2012-11-05" in called_data
|
|
assert "MessageBody=" in called_data
|
|
|
|
# Extract and decode the message body
|
|
message_body_start = called_data.find("MessageBody=") + len("MessageBody=")
|
|
message_body_encoded = called_data[message_body_start:]
|
|
message_body_json = unquote(message_body_encoded)
|
|
|
|
# Parse the JSON to verify it's a StandardLoggingPayload
|
|
payload_data = json.loads(message_body_json)
|
|
|
|
# Verify it has the expected StandardLoggingPayload structure
|
|
assert "model" in payload_data
|
|
assert "messages" in payload_data
|
|
assert "response" in payload_data
|
|
assert payload_data["model"] == "gpt-5.5"
|
|
assert len(payload_data["messages"]) == 1
|
|
assert payload_data["messages"][0]["role"] == "user"
|
|
assert payload_data["messages"][0]["content"] == "hello"
|
|
|
|
|
|
# =============================================================================
|
|
# 📥 Logging Queue Tests
|
|
# =============================================================================
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_log_success_event_adds_to_queue(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
|
|
fake_payload = {"some": "data"}
|
|
await logger.async_log_success_event(
|
|
{"standard_logging_object": fake_payload}, None, None, None
|
|
)
|
|
assert fake_payload in logger.log_queue
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_log_failure_event_adds_to_queue(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
|
|
fake_payload = {"fail": True}
|
|
await logger.async_log_failure_event(
|
|
{"standard_logging_object": fake_payload}, None, None, None
|
|
)
|
|
assert fake_payload in logger.log_queue
|
|
|
|
|
|
# =============================================================================
|
|
# 🧾 async_send_batch Tests
|
|
# =============================================================================
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_send_batch_triggers_tasks(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
logger.async_send_message = AsyncMock()
|
|
|
|
logger.log_queue = [{"log": 1}, {"log": 2}]
|
|
await logger.async_send_batch()
|
|
|
|
assert logger.async_send_message.await_count == 0 # uses create_task internally
|
|
|
|
|
|
# =============================================================================
|
|
# 🔐 AppCrypto Tests
|
|
# =============================================================================
|
|
|
|
|
|
def test_appcrypto_encrypt_decrypt_roundtrip():
|
|
key = os.urandom(32)
|
|
crypto = AppCrypto(key)
|
|
data = {"event": "test", "value": 42}
|
|
aad = b"context"
|
|
enc = crypto.encrypt_json(data, aad=aad)
|
|
dec = crypto.decrypt_json(enc, aad=aad)
|
|
assert dec == data
|
|
|
|
|
|
def test_appcrypto_invalid_key_length():
|
|
with pytest.raises(ValueError, match="32 bytes"):
|
|
AppCrypto(b"short")
|
|
|
|
|
|
# =============================================================================
|
|
# 🪣 SQSLogger Initialization Tests
|
|
# =============================================================================
|
|
|
|
|
|
def test_sqs_logger_init_without_encryption(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
# Patch asyncio.create_task to avoid RuntimeError
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
assert logger.sqs_queue_url == "https://example.com"
|
|
assert logger.app_crypto is None
|
|
|
|
|
|
def test_sqs_logger_init_with_encryption(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
key_b64 = base64.b64encode(os.urandom(32)).decode()
|
|
|
|
logger = SQSLogger(
|
|
sqs_queue_url="https://example.com",
|
|
sqs_region_name="us-west-2",
|
|
sqs_aws_use_application_level_encryption=True,
|
|
sqs_app_encryption_key_b64=key_b64,
|
|
sqs_app_encryption_aad="tenant=bill",
|
|
)
|
|
assert logger.app_crypto is not None
|
|
assert logger.sqs_app_encryption_aad == "tenant=bill"
|
|
|
|
|
|
def test_sqs_logger_init_with_encryption_missing_key(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
with pytest.raises(ValueError, match="required when encryption is enabled"):
|
|
SQSLogger(
|
|
sqs_queue_url="https://example.com",
|
|
sqs_region_name="us-west-2",
|
|
sqs_aws_use_application_level_encryption=True,
|
|
)
|
|
|
|
|
|
# =============================================================================
|
|
# 📥 Logging Queue Tests
|
|
# =============================================================================
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_log_success_event_adds_to_queue(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
|
|
fake_payload = {"some": "data"}
|
|
await logger.async_log_success_event(
|
|
{"standard_logging_object": fake_payload}, None, None, None
|
|
)
|
|
assert fake_payload in logger.log_queue
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_log_failure_event_adds_to_queue(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
|
|
fake_payload = {"fail": True}
|
|
await logger.async_log_failure_event(
|
|
{"standard_logging_object": fake_payload}, None, None, None
|
|
)
|
|
assert fake_payload in logger.log_queue
|
|
|
|
|
|
# =============================================================================
|
|
# 🧾 async_send_batch Tests
|
|
# =============================================================================
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_send_batch_triggers_tasks(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
|
|
logger.async_send_message = AsyncMock()
|
|
logger.log_queue = [{"log": 1}, {"log": 2}]
|
|
|
|
await logger.async_send_batch()
|
|
# It uses asyncio.create_task() so direct await count = 0 is expected
|
|
asyncio.create_task.assert_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_strip_base64_removes_file_and_nontext_entries():
|
|
logger = SQSLogger(sqs_strip_base64_files=True)
|
|
|
|
payload = {
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "text", "text": "Hello world"},
|
|
{
|
|
"type": "image",
|
|
"file": {"file_data": "data:image/png;base64,AAAA"},
|
|
},
|
|
{
|
|
"type": "file",
|
|
"file": {"file_data": "data:application/pdf;base64,BBBB"},
|
|
},
|
|
],
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": [
|
|
{"type": "text", "text": "Response"},
|
|
{
|
|
"type": "audio",
|
|
"file": {"file_data": "data:audio/wav;base64,CCCC"},
|
|
},
|
|
],
|
|
},
|
|
]
|
|
}
|
|
|
|
stripped = await logger._strip_base64_from_messages(payload)
|
|
|
|
# 1️⃣ All file/image/audio entries removed
|
|
assert len(stripped["messages"][0]["content"]) == 1
|
|
assert stripped["messages"][0]["content"][0]["text"] == "Hello world"
|
|
|
|
assert len(stripped["messages"][1]["content"]) == 1
|
|
assert stripped["messages"][1]["content"][0]["text"] == "Response"
|
|
|
|
# 2️⃣ No residual 'file' keys left
|
|
for msg in stripped["messages"]:
|
|
for content in msg["content"]:
|
|
assert "file" not in content
|
|
assert content.get("type") == "text"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_strip_base64_keeps_non_file_content():
|
|
logger = SQSLogger(sqs_strip_base64_files=True)
|
|
|
|
payload = {
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "text", "text": "Just text"},
|
|
{"type": "text", "text": "Another message"},
|
|
],
|
|
}
|
|
]
|
|
}
|
|
|
|
stripped = await logger._strip_base64_from_messages(payload)
|
|
|
|
# Should not modify normal text messages
|
|
assert stripped["messages"][0]["content"] == payload["messages"][0]["content"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_strip_base64_handles_empty_or_missing_messages():
|
|
logger = SQSLogger(sqs_strip_base64_files=True)
|
|
|
|
payload_no_messages = {}
|
|
stripped1 = await logger._strip_base64_from_messages(payload_no_messages)
|
|
assert stripped1 == payload_no_messages
|
|
|
|
payload_empty = {"messages": []}
|
|
stripped2 = await logger._strip_base64_from_messages(payload_empty)
|
|
assert stripped2 == payload_empty
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_strip_base64_mixed_nested_objects():
|
|
"""
|
|
Handles weird/nested content structures gracefully.
|
|
"""
|
|
logger = SQSLogger(sqs_strip_base64_files=True)
|
|
|
|
payload = {
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": [
|
|
{"type": "text", "text": "Keep me"},
|
|
{"type": "custom", "metadata": "ignore but non-text"},
|
|
{"foo": "bar"},
|
|
{"file": {"file_data": "data:application/pdf;base64,XXX"}},
|
|
],
|
|
"extra": {"trace_id": "123"},
|
|
}
|
|
]
|
|
}
|
|
|
|
stripped = await logger._strip_base64_from_messages(payload)
|
|
|
|
# 'custom' (non-text) and 'file' entries removed
|
|
content = stripped["messages"][0]["content"]
|
|
assert len(content) == 2
|
|
assert {"type": "text", "text": "Keep me"} in content
|
|
assert {"foo": "bar"} in content
|
|
# Other metadata stays
|
|
assert stripped["messages"][0]["extra"]["trace_id"] == "123"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_strip_base64_recursive_redaction():
|
|
logger = SQSLogger(sqs_strip_base64_files=True)
|
|
payload = {
|
|
"messages": [
|
|
{
|
|
"content": [
|
|
{"type": "text", "text": "normal text"},
|
|
{
|
|
"type": "text",
|
|
"text": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUg",
|
|
},
|
|
{
|
|
"type": "text",
|
|
"text": "Nested: {'data': 'data:application/pdf;base64,AAA...'}",
|
|
},
|
|
{"file": {"file_data": "data:application/pdf;base64,AAAA"}},
|
|
{"metadata": {"preview": "data:audio/mp3;base64,AAAAA=="}},
|
|
]
|
|
}
|
|
]
|
|
}
|
|
|
|
result = await logger._strip_base64_from_messages(payload)
|
|
content = result["messages"][0]["content"]
|
|
|
|
# Dropped file-type entry
|
|
assert not any("file" in c for c in content)
|
|
# Base64 redacted globally
|
|
for c in content:
|
|
if isinstance(c, dict):
|
|
s = json.dumps(c).lower()
|
|
# allow "[base64_redacted]" but nothing else
|
|
assert "base64," not in s, f"Found real base64 blob in: {s}"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_health_check_healthy(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
logger.async_send_message = AsyncMock(return_value=None)
|
|
|
|
result = await logger.async_health_check()
|
|
assert result["status"] == "healthy"
|
|
assert result.get("error_message") is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_health_check_unhealthy(monkeypatch):
|
|
monkeypatch.setattr("litellm.aws_sqs_callback_params", {})
|
|
monkeypatch.setattr(asyncio, "create_task", MagicMock())
|
|
logger = SQSLogger(sqs_queue_url="https://example.com", sqs_region_name="us-west-2")
|
|
logger.async_send_message = AsyncMock(side_effect=Exception("boom"))
|
|
|
|
result = await logger.async_health_check()
|
|
assert result["status"] == "unhealthy"
|
|
assert "boom" in (result.get("error_message") or "")
|