scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(langfuse): align trace IDs and v4 tests

Browse source
This commit is contained in:
Devin AI 2026-07-15 15:09:47 +00:00
parent 8d051020d0
commit db87acd9e9
24 changed files with 56 additions and 2493 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/integrations/SlackAlerting/utils.py
View file

@ -84,7 +84,7 @@ async def _add_langfuse_trace_id_to_alert(
#########################################################
langfuse_object = litellm_logging_obj._get_callback_object(service_name="langfuse")
if langfuse_object is not None:
base_url = langfuse_object.Langfuse.base_url
base_url = langfuse_object.langfuse_host
return f"{base_url}/trace/{trace_id}"
return None

2
litellm/integrations/langfuse/langfuse.py
View file

@ -751,7 +751,7 @@ class LangFuseLogger:
generation_client.end(end_time=end_time_ns)
trace.end(end_time=end_time_ns)
return trace.trace_id, generation_client.id
return trace_context["trace_id"], generation_client.id
except Exception:
verbose_logger.error(f"Langfuse Layer Error - {traceback.format_exc()}")
return None, None

36
tests/litellm_utils_tests/test_utils.py
View file

@ -930,6 +930,7 @@ def test_logging_trace_id(langfuse_trace_id, langfuse_existing_trace_id):
- Unit test for `_get_trace_id` function in Logging obj
"""
from litellm.litellm_core_utils.litellm_logging import Logging
from langfuse import Langfuse
litellm.success_callback = ["langfuse"]
litellm_call_id = "my-unique-call-id"
@ -961,24 +962,23 @@ def test_logging_trace_id(langfuse_trace_id, langfuse_existing_trace_id):
time.sleep(3)
assert litellm_logging_obj._get_trace_id(service_name="langfuse") is not None
## if existing_trace_id exists
if langfuse_existing_trace_id is not None:
assert (
litellm_logging_obj._get_trace_id(service_name="langfuse")
== langfuse_existing_trace_id
)
## if trace_id exists
elif langfuse_trace_id is not None:
assert (
litellm_logging_obj._get_trace_id(service_name="langfuse")
== langfuse_trace_id
)
## if no trace_id or existing_trace_id is provided, use litellm_trace_id
else:
assert (
litellm_logging_obj._get_trace_id(service_name="langfuse")
== litellm_logging_obj.litellm_trace_id
)
source_trace_id = (
langfuse_existing_trace_id
or langfuse_trace_id
or litellm_logging_obj.litellm_trace_id
)
normalized_trace_id = source_trace_id.lower().replace("-", "")
expected_trace_id = (
normalized_trace_id
if len(normalized_trace_id) == 32
and normalized_trace_id != "0" * 32
and all(character in "0123456789abcdef" for character in normalized_trace_id)
else Langfuse.create_trace_id(seed=source_trace_id)
)
assert (
litellm_logging_obj._get_trace_id(service_name="langfuse")
== expected_trace_id
)
def test_convert_model_response_object():

50
tests/local_testing/test_alangfuse.py
View file

@ -231,12 +231,16 @@ async def test_langfuse_logging_without_request_response(stream, langfuse_client
langfuse_client.flush()
await asyncio.sleep(5)
# get trace with _unique_trace_name
trace = langfuse_client.get_generations(trace_id=_unique_trace_name)
trace_id = langfuse_client.create_trace_id(seed=_unique_trace_name)
observations = langfuse_client.api.observations.get_many(
trace_id=trace_id,
type="GENERATION",
parse_io_as_json=True,
)
print("trace_from_langfuse", trace)
print("observations_from_langfuse", observations)
_trace_data = trace.data
_trace_data = observations.data
if (
len(_trace_data) == 0
@ -292,11 +296,16 @@ async def test_langfuse_logging_audio_transcriptions(langfuse_client):
langfuse_client.flush()
await asyncio.sleep(20)
# get trace with _unique_trace_name
print("lookiing up trace", _unique_trace_name)
trace = langfuse_client.get_trace(id=_unique_trace_name)
trace_id = langfuse_client.create_trace_id(seed=_unique_trace_name)
generations = list(
reversed(langfuse_client.get_generations(trace_id=_unique_trace_name).data)
reversed(
langfuse_client.api.observations.get_many(
trace_id=trace_id,
type="GENERATION",
parse_io_as_json=True,
).data
)
)
print("generations for given trace=", generations)
@ -338,11 +347,17 @@ async def test_langfuse_masked_input_output(langfuse_client):
langfuse_client.flush()
await asyncio.sleep(30)
# get trace with _unique_trace_name
trace = langfuse_client.get_trace(id=_unique_trace_name)
trace_id = langfuse_client.create_trace_id(seed=_unique_trace_name)
trace = langfuse_client.api.trace.get(trace_id)
print("trace_from_langfuse", trace)
generations = list(
reversed(langfuse_client.get_generations(trace_id=_unique_trace_name).data)
reversed(
langfuse_client.api.observations.get_many(
trace_id=trace_id,
type="GENERATION",
parse_io_as_json=True,
).data
)
)
assert expected_input in str(trace.input)
@ -443,17 +458,24 @@ async def test_aaalangfuse_logging_metadata(langfuse_client):
# Tests the metadata filtering and the override of the output to be the last generation
for trace_id, generation_ids in trace_identifiers.items():
resolved_trace_id = langfuse_client.create_trace_id(seed=trace_id)
try:
trace = langfuse_client.get_trace(id=trace_id)
trace = langfuse_client.api.trace.get(resolved_trace_id)
except Exception as e:
if "not found within authorized project" in str(e):
print(f"Trace {trace_id} not found")
continue
assert trace.id == trace_id
assert trace.id == resolved_trace_id
assert trace.session_id == session_id
assert trace.metadata != trace_metadata
generations = list(
reversed(langfuse_client.get_generations(trace_id=trace_id).data)
reversed(
langfuse_client.api.observations.get_many(
trace_id=resolved_trace_id,
type="GENERATION",
parse_io_as_json=True,
).data
)
)
assert len(generations) == len(generation_ids)
assert (
@ -470,7 +492,7 @@ async def test_aaalangfuse_logging_metadata(langfuse_client):
print("trace_from_langfuse", trace)
for generation_id, generation in zip(generation_ids, generations):
assert generation.id == generation_id
assert generation.trace_id == trace_id
assert generation.trace_id == resolved_trace_id
print(
"common keys in trace",
set(generation.metadata.keys()).intersection(

99
tests/logging_callback_tests/langfuse_expected_request_body/completion.json
View file

@ -1,99 +0,0 @@
{
"batch": [
{
"id": "7e00e081-468b-4fe9-a409-eb12ac7d3d2d",
"type": "trace-create",
"body": {
"id": "litellm-test-793c217f-9417-4e77-84a7-8dcc16e5b72b",
"timestamp": "2025-01-16T19:28:55.124873Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-16T19:28:55.125002Z"
},
{
"id": "b9ec2c0f-18df-46c7-9e90-624c60bf78ee",
"type": "generation-create",
"body": {
"name": "litellm-acompletion",
"startTime": "2025-01-16T11:28:54.796360-08:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 3.5e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 3.5e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-11-28-54-796360_chatcmpl-521e530f-5e29-4d0a-8d1a-58fca0a847c2",
"endTime": "2025-01-16T11:28:55.124353-08:00",
"completionStartTime": "2025-01-16T11:28:55.124353-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
},
"traceId": "litellm-test-6a51ae70-a4e7-499e-afcd-dce2a3b31850"
},
"timestamp": "2025-01-16T19:28:55.125258Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-03734ab3-8790-4c09-b5fb-8c3b663413b6"
}
}

85
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_bedrock_call.json
View file

@ -1,85 +0,0 @@
{
"batch": [
{
"id": "3c9b544f-ef3f-449e-8ec1-763acbb56bec",
"type": "trace-create",
"body": {
"id": "litellm-test-c4c1c850-e8c9-4b16-b5a4-bff2bf9fa4f6",
"timestamp": "2025-05-26T21:13:16.796768Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"tags": []
},
"timestamp": "2025-05-26T21:13:16.796875Z"
},
{
"id": "90e6bc70-05d9-4444-8b87-4523a9a54c17",
"type": "generation-create",
"body": {
"traceId": "litellm-test-c4c1c850-e8c9-4b16-b5a4-bff2bf9fa4f6",
"name": "litellm-acompletion",
"startTime": "2025-05-26T14:13:16.469836-07:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": null,
"response_cost": 6e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
"usage_object": null
},
"litellm_response_cost": 6e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"level": "DEFAULT",
"id": "time-14-13-16-469836_chatcmpl-3803a9e9-aa68-4493-94d9-247f354830d6",
"endTime": "2025-05-26T14:13:16.795438-07:00",
"completionStartTime": "2025-05-26T14:13:16.795438-07:00",
"model": "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
"modelParameters": {
"aws_region": "us-east-1"
},
"usage": {
"input": 10,
"output": 10,
"unit": "TOKENS",
"totalCost": 6e-05
},
"usageDetails": {
"input": 10,
"output": 10,
"total": 20,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-05-26T21:13:16.797156Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-3bfc4db9-217f-48e9-92e0-142566e3c204"
}
}

138
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_complex_metadata.json
View file

@ -1,138 +0,0 @@
{
"batch": [
{
"id": "9ee9100b-c4aa-4e40-a10d-bc189f8b4242",
"type": "trace-create",
"body": {
"id": "litellm-test-c414db10-dd68-406e-9d9e-03839bc2f346",
"timestamp": "2025-01-22T17:27:51.702596Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:27:51.702716Z"
},
{
"id": "f8d20489-ed58-429f-b609-87380e223746",
"type": "generation-create",
"body": {
"traceId": "litellm-test-c414db10-dd68-406e-9d9e-03839bc2f346",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:27:51.150898-08:00",
"metadata": {
"string_value": "hello",
"int_value": 42,
"float_value": 3.14,
"bool_value": true,
"nested_dict": {
"key1": "value1",
"key2": {
"inner_key": "inner_value"
}
},
"list_value": [
1,
2,
3
],
"set_value": [
1,
2,
3
],
"complex_list": [
{
"dict_in_list": "value"
},
"simple_string",
[
1,
2,
3
]
],
"user": {
"name": "John",
"age": 30,
"tags": [
"customer",
"active"
]
},
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-27-51-150898_chatcmpl-b783291c-dc76-4660-bfef-b79be9d54e57",
"endTime": "2025-01-22T09:27:51.702048-08:00",
"completionStartTime": "2025-01-22T09:27:51.702048-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:27:51.703046Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

116
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_langfuse_metadata.json
View file

@ -1,116 +0,0 @@
{
"batch": [
{
"id": "872a0a1c-4328-431b-80b6-fd55a8a44477",
"type": "trace-create",
"body": {
"id": "litellm-test-533ffb2d-a0a3-45b5-911c-7940466cdc8e",
"timestamp": "2025-01-22T17:19:11.234960Z",
"name": "test_trace_name",
"userId": "test_user_id",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"sessionId": "test_session_id",
"version": "test_trace_version",
"metadata": {
"test_key": "test_value"
},
"tags": [
"test_tag",
"test_tag_2"
]
},
"timestamp": "2025-01-22T17:19:11.235169Z"
},
{
"id": "18d6f044-e522-4376-96e0-7eec765677ed",
"type": "generation-create",
"body": {
"traceId": "litellm-test-533ffb2d-a0a3-45b5-911c-7940466cdc8e",
"name": "test_generation_name",
"startTime": "2025-01-22T09:19:10.957072-08:00",
"metadata": {
"tags": [
"test_tag",
"test_tag_2"
],
"parent_observation_id": "test_parent_observation_id",
"version": "test_version",
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 3.5e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 3.5e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"parentObservationId": "test_parent_observation_id",
"version": "test_version",
"id": "time-09-19-10-957072_chatcmpl-4da65aba-32e4-400d-aaa2-6bfe096d8141",
"endTime": "2025-01-22T09:19:11.234200-08:00",
"completionStartTime": "2025-01-22T09:19:11.234200-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:19:11.235541Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

85
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_no_choices.json
View file

@ -1,85 +0,0 @@
{
"batch": [
{
"id": "1f1d7517-4602-4c59-a322-7fc0306f1b7a",
"type": "trace-create",
"body": {
"id": "litellm-test-dbadfdfc-f4e7-4f05-8992-984c37359166",
"timestamp": "2025-02-07T00:23:27.669634Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"tags": []
},
"timestamp": "2025-02-07T00:23:27.669809Z"
},
{
"id": "fbe610b6-f500-4c7d-8e34-d40a0e8c487b",
"type": "generation-create",
"body": {
"traceId": "litellm-test-dbadfdfc-f4e7-4f05-8992-984c37359166",
"name": "litellm-acompletion",
"startTime": "2025-02-06T16:23:27.220129-08:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 3.5e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 3.5e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"level": "DEFAULT",
"id": "time-16-23-27-220129_chatcmpl-565360d7-965f-4533-9c09-db789af77a7d",
"endTime": "2025-02-06T16:23:27.644253-08:00",
"completionStartTime": "2025-02-06T16:23:27.644253-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 10,
"unit": "TOKENS",
"totalCost": 1.9999999999999998e-05
},
"usageDetails": {
"input": 10,
"output": 10,
"total": 20,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-02-07T00:23:27.670175Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

95
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_router.json
View file

@ -1,95 +0,0 @@
{
"batch": [
{
"id": "45eb9b25-605c-4c4a-b2b3-8241e079cd31",
"type": "trace-create",
"body": {
"id": "litellm-test-32702f3d-8a1c-4912-a3d6-286e59a9c568",
"timestamp": "2025-05-24T17:01:19.408179Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"tags": []
},
"timestamp": "2025-05-24T17:01:19.408284Z"
},
{
"id": "9f5e9b7d-0cea-4776-b4b9-5c2e8f4bad3c",
"type": "generation-create",
"body": {
"traceId": "litellm-test-32702f3d-8a1c-4912-a3d6-286e59a9c568",
"name": "litellm-acompletion",
"startTime": "2025-05-24T10:01:19.142356-07:00",
"metadata": {
"model_group": "gpt-3.5-turbo",
"model_group_size": 1,
"deployment": "gpt-3.5-turbo",
"model_info": {
"id": "0f1cd8f9e6a22e499303d479486395563ea04decade83fe7334dc2f079a857c2",
"db_model": false
},
"api_base": null,
"hidden_params": {
"model_id": "0f1cd8f9e6a22e499303d479486395563ea04decade83fe7334dc2f079a857c2",
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 3.5e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 3.5e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"level": "DEFAULT",
"id": "time-10-01-19-142356_chatcmpl-16b215b7-e51e-47b0-8fe5-9dd6f226fda1",
"endTime": "2025-05-24T10:01:19.406531-07:00",
"completionStartTime": "2025-05-24T10:01:19.406531-07:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"stream": false,
"max_retries": 0,
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 10,
"unit": "TOKENS",
"totalCost": 1.9999999999999998e-05
},
"usageDetails": {
"input": 10,
"output": 10,
"total": 20,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-05-24T17:01:19.408586Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-3bfc4db9-217f-48e9-92e0-142566e3c204"
}
}

106
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_tags.json
View file

@ -1,106 +0,0 @@
{
"batch": [
{
"id": "42be960a-5dde-47df-9cbc-1fdd0fdcaa7d",
"type": "trace-create",
"body": {
"id": "litellm-test-f3ab679b-1e1d-43fd-9a9a-f11287aeb339",
"timestamp": "2025-01-22T15:31:28.963419Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": [
"test_tag",
"test_tag_2"
]
},
"timestamp": "2025-01-22T15:31:28.963706Z"
},
{
"id": "5486df5a-3776-4adf-abd0-bd22e51f7fb4",
"type": "generation-create",
"body": {
"traceId": "litellm-test-f3ab679b-1e1d-43fd-9a9a-f11287aeb339",
"name": "litellm-acompletion",
"startTime": "2025-01-22T07:31:28.960749-08:00",
"metadata": {
"tags": [
"test_tag",
"test_tag_2"
],
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-07-31-28-960749_chatcmpl-f06338f0-8c49-45d8-be35-2854a89723c1",
"endTime": "2025-01-22T07:31:28.962389-08:00",
"completionStartTime": "2025-01-22T07:31:28.962389-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T15:31:28.964179Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

106
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_tags_stream.json
View file

@ -1,106 +0,0 @@
{
"batch": [
{
"id": "06b8fa9f-151b-4e74-9fbf-8af5222a7f40",
"type": "trace-create",
"body": {
"id": "litellm-test-54368a51-a382-493c-b0a8-3f1af23e18c4",
"timestamp": "2025-01-22T16:38:26.016582Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": [
"test_tag_stream",
"test_tag_2_stream"
]
},
"timestamp": "2025-01-22T16:38:26.016828Z"
},
{
"id": "4ca1fd78-53e3-41b5-95d9-417b09e3f0eb",
"type": "generation-create",
"body": {
"traceId": "litellm-test-54368a51-a382-493c-b0a8-3f1af23e18c4",
"name": "litellm-acompletion",
"startTime": "2025-01-22T08:38:25.665692-08:00",
"metadata": {
"tags": [
"test_tag_stream",
"test_tag_2_stream"
],
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-08-38-25-665692_chatcmpl-8b67ffb8-4326-4e1b-bf4a-f70930c11c00",
"endTime": "2025-01-22T08:38:26.015666-08:00",
"completionStartTime": "2025-01-22T08:38:26.015666-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T16:38:26.017252Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

83
tests/logging_callback_tests/langfuse_expected_request_body/completion_with_vertex_call.json
View file

@ -1,83 +0,0 @@
{
"batch": [
{
"id": "7d33d536-2730-4815-8957-80866c09c053",
"type": "trace-create",
"body": {
"id": "litellm-test-72861437-ff5b-4c48-89c0-a143534d9e7a",
"timestamp": "2025-05-26T21:15:40.610459Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"tags": []
},
"timestamp": "2025-05-26T21:15:40.610603Z"
},
{
"id": "ebb5079c-7726-4adb-9616-e1862735e1d8",
"type": "generation-create",
"body": {
"traceId": "litellm-test-72861437-ff5b-4c48-89c0-a143534d9e7a",
"name": "litellm-acompletion",
"startTime": "2025-05-26T14:15:40.349639-07:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": null,
"response_cost": 7.5e-06,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "vertex_ai/gemini-2.0-flash-001",
"usage_object": null
},
"litellm_response_cost": 7.5e-06,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"level": "DEFAULT",
"id": "time-14-15-40-349639_chatcmpl-59a988d0-7ef1-4dc4-bc18-d2e78961817f",
"endTime": "2025-05-26T14:15:40.607266-07:00",
"completionStartTime": "2025-05-26T14:15:40.607266-07:00",
"model": "gemini-2.0-flash-001",
"modelParameters": {},
"usage": {
"input": 10,
"output": 10,
"unit": "TOKENS",
"totalCost": 7.5e-06
},
"usageDetails": {
"input": 10,
"output": 10,
"total": 20,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-05-26T21:15:40.610953Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-3bfc4db9-217f-48e9-92e0-142566e3c204"
}
}

113
tests/logging_callback_tests/langfuse_expected_request_body/complex_metadata.json
View file

@ -1,113 +0,0 @@
{
"batch": [
{
"id": "ddf567e5-a1b5-4e38-8a7c-f48bc847f721",
"type": "trace-create",
"body": {
"id": "litellm-test-46551fc7-c916-4a83-aeef-4274b5582ce1",
"timestamp": "2025-01-22T17:59:39.367430Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:59:39.367707Z"
},
{
"id": "d3eb2c9e-e123-419d-b27b-c8283a505ae8",
"type": "generation-create",
"body": {
"traceId": "litellm-test-46551fc7-c916-4a83-aeef-4274b5582ce1",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:59:39.362554-08:00",
"metadata": {
"int": 42,
"str": "hello",
"list": [
1,
2,
3
],
"set": [
4,
5
],
"dict": {
"nested": "value"
},
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-59-39-362554_chatcmpl-d20ba1d9-cda6-4773-822e-921ebcd426a0",
"endTime": "2025-01-22T09:59:39.365756-08:00",
"completionStartTime": "2025-01-22T09:59:39.365756-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:59:39.368310Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

105
tests/logging_callback_tests/langfuse_expected_request_body/complex_metadata_2.json
View file

@ -1,105 +0,0 @@
{
"batch": [
{
"id": "ea3d694a-ce6b-417e-86e3-23ac17c6f6c6",
"type": "trace-create",
"body": {
"id": "litellm-test-38dcf290-8742-4fc5-ad03-c5d47e91dec0",
"timestamp": "2025-01-22T18:06:50.959206Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T18:06:50.959409Z"
},
{
"id": "5fe03133-5798-4f87-8eec-ae0264f1eccc",
"type": "generation-create",
"body": {
"traceId": "litellm-test-38dcf290-8742-4fc5-ad03-c5d47e91dec0",
"name": "litellm-acompletion",
"startTime": "2025-01-22T10:06:50.957097-08:00",
"metadata": {
"list": [
"list",
"not",
"a",
"dict"
],
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-10-06-50-957097_chatcmpl-62d4ad7c-291b-4fc7-a8a4-3ed0fc3912a5",
"endTime": "2025-01-22T10:06:50.958374-08:00",
"completionStartTime": "2025-01-22T10:06:50.958374-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T18:06:50.959850Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

4
tests/logging_callback_tests/langfuse_expected_request_body/embedding_with_vllm.json
View file

@ -1,4 +0,0 @@
{
"model": "BAAI/bge-small-en-v1.5",
"input": ["Hello from litellm!"]
}

99
tests/logging_callback_tests/langfuse_expected_request_body/empty_metadata.json
View file

@ -1,99 +0,0 @@
{
"batch": [
{
"id": "28d0c943-284b-4151-bf0d-8acf0f449865",
"type": "trace-create",
"body": {
"id": "litellm-test-d9506624-457c-40bc-9a37-578b896fa22a",
"timestamp": "2025-01-22T17:59:32.888622Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:59:32.888940Z"
},
{
"id": "384e9fb4-3516-47b2-a4ae-1666337ec4a7",
"type": "generation-create",
"body": {
"traceId": "litellm-test-d9506624-457c-40bc-9a37-578b896fa22a",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:59:32.878577-08:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-59-32-878577_chatcmpl-1195f870-fd4d-4e38-8dc8-99dd3da5ab0b",
"endTime": "2025-01-22T09:59:32.880691-08:00",
"completionStartTime": "2025-01-22T09:59:32.880691-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:59:32.889548Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

99
tests/logging_callback_tests/langfuse_expected_request_body/metadata_with_function.json
View file

@ -1,99 +0,0 @@
{
"batch": [
{
"id": "88b1898a-cc5d-4e8e-93bc-3e71300c5e8d",
"type": "trace-create",
"body": {
"id": "litellm-test-a46356d9-ecff-44c8-a3da-fed3588b5128",
"timestamp": "2025-01-22T17:59:36.162545Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:59:36.162702Z"
},
{
"id": "96bb77a6-a350-431b-bfd8-425491259728",
"type": "generation-create",
"body": {
"traceId": "litellm-test-a46356d9-ecff-44c8-a3da-fed3588b5128",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:59:36.161090-08:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-59-36-161090_chatcmpl-1ee988c9-9133-4655-bbe4-b97ffb6e3dc9",
"endTime": "2025-01-22T09:59:36.161959-08:00",
"completionStartTime": "2025-01-22T09:59:36.161959-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:59:36.162997Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

99
tests/logging_callback_tests/langfuse_expected_request_body/metadata_with_lock.json
View file

@ -1,99 +0,0 @@
{
"batch": [
{
"id": "28d0c943-284b-4151-bf0d-8acf0f449865",
"type": "trace-create",
"body": {
"id": "litellm-test-d9506624-457c-40bc-9a37-578b896fa22a",
"timestamp": "2025-01-22T17:59:32.888622Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:59:32.888940Z"
},
{
"id": "384e9fb4-3516-47b2-a4ae-1666337ec4a7",
"type": "generation-create",
"body": {
"traceId": "litellm-test-d9506624-457c-40bc-9a37-578b896fa22a",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:59:32.878577-08:00",
"metadata": {
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-59-32-878577_chatcmpl-1195f870-fd4d-4e38-8dc8-99dd3da5ab0b",
"endTime": "2025-01-22T09:59:32.880691-08:00",
"completionStartTime": "2025-01-22T09:59:32.880691-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:59:32.889548Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

105
tests/logging_callback_tests/langfuse_expected_request_body/nested_metadata.json
View file

@ -1,105 +0,0 @@
{
"batch": [
{
"id": "44f179be-e3b9-486f-986f-030fc50614f0",
"type": "trace-create",
"body": {
"id": "litellm-test-8a04085c-1859-48fa-9fd8-1ec487fe455e",
"timestamp": "2025-01-22T17:55:28.854927Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:55:28.855187Z"
},
{
"id": "2175ee64-58a3-41ab-96df-405b76695f5f",
"type": "generation-create",
"body": {
"traceId": "litellm-test-8a04085c-1859-48fa-9fd8-1ec487fe455e",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:55:28.852503-08:00",
"metadata": {
"a": {
"nested_a": 1
},
"b": {
"nested_b": 2
},
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-55-28-852503_chatcmpl-131cf0da-a47b-4cd1-850b-50fa077362ac",
"endTime": "2025-01-22T09:55:28.853979-08:00",
"completionStartTime": "2025-01-22T09:55:28.853979-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:55:28.855732Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

105
tests/logging_callback_tests/langfuse_expected_request_body/simple_metadata.json
View file

@ -1,105 +0,0 @@
{
"batch": [
{
"id": "02c74119-76b7-4f79-91cb-c55f1495c100",
"type": "trace-create",
"body": {
"id": "litellm-test-e58116c7-ead0-417e-9f86-b35f1e5bc242",
"timestamp": "2025-01-22T17:53:53.754012Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:53:53.754178Z"
},
{
"id": "097968e0-52e9-46b5-9e8e-e6e08dd00e72",
"type": "generation-create",
"body": {
"traceId": "litellm-test-e58116c7-ead0-417e-9f86-b35f1e5bc242",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:53:53.752422-08:00",
"metadata": {
"a": {
"nested_a": 1
},
"b": {
"nested_b": 2
},
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-53-53-752422_chatcmpl-e99bc1d3-a393-493f-8afe-4507c0acff15",
"endTime": "2025-01-22T09:53:53.753431-08:00",
"completionStartTime": "2025-01-22T09:53:53.753431-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:53:53.754511Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

109
tests/logging_callback_tests/langfuse_expected_request_body/simple_metadata2.json
View file

@ -1,109 +0,0 @@
{
"batch": [
{
"id": "1a55383a-e6fa-41f9-81fe-e7aa58c55f40",
"type": "trace-create",
"body": {
"id": "litellm-test-08fd1578-4a67-49b4-ac23-2dff1c112c80",
"timestamp": "2025-01-22T17:56:35.477276Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:56:35.477571Z"
},
{
"id": "13ba66e8-f72b-4f57-a6cc-57c0be2829b1",
"type": "generation-create",
"body": {
"traceId": "litellm-test-08fd1578-4a67-49b4-ac23-2dff1c112c80",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:56:35.474752-08:00",
"metadata": {
"a": [
1,
2,
3
],
"b": [
4,
5,
6
],
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-56-35-474752_chatcmpl-9b152610-3d1e-4731-a84e-d0341ea69a0f",
"endTime": "2025-01-22T09:56:35.476236-08:00",
"completionStartTime": "2025-01-22T09:56:35.476236-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:56:35.478171Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

113
tests/logging_callback_tests/langfuse_expected_request_body/simple_metadata3.json
View file

@ -1,113 +0,0 @@
{
"batch": [
{
"id": "7fb1f295-a7af-47af-afbd-e2f2d08280aa",
"type": "trace-create",
"body": {
"id": "litellm-test-c3acc34b-3c06-4868-bcee-87a3c4c1367e",
"timestamp": "2025-01-22T17:56:38.786515Z",
"name": "litellm-acompletion",
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"tags": []
},
"timestamp": "2025-01-22T17:56:38.786742Z"
},
{
"id": "412870bc-fc50-4426-a0dc-9e8b016e14bb",
"type": "generation-create",
"body": {
"traceId": "litellm-test-c3acc34b-3c06-4868-bcee-87a3c4c1367e",
"name": "litellm-acompletion",
"startTime": "2025-01-22T09:56:38.784548-08:00",
"metadata": {
"a": [
1,
2
],
"b": [
3,
4
],
"c": {
"d": [
5,
6
]
},
"hidden_params": {
"model_id": null,
"cache_key": null,
"api_base": "https://api.openai.com",
"response_cost": 5.4999999999999995e-05,
"additional_headers": {},
"litellm_overhead_time_ms": null,
"batch_models": null,
"litellm_model_name": "gpt-3.5-turbo",
"usage_object": null
},
"litellm_response_cost": 5.4999999999999995e-05,
"cache_hit": false,
"requester_metadata": {}
},
"input": {
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
},
"output": {
"content": "Hello! How can I assist you today?",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"provider_specific_fields": null
},
"level": "DEFAULT",
"id": "time-09-56-38-784548_chatcmpl-438c8727-86b3-44d9-9b46-42330922cf50",
"endTime": "2025-01-22T09:56:38.785762-08:00",
"completionStartTime": "2025-01-22T09:56:38.785762-08:00",
"model": "gpt-3.5-turbo",
"modelParameters": {
"extra_body": "{}"
},
"usage": {
"input": 10,
"output": 20,
"unit": "TOKENS",
"totalCost": 3.5e-05
},
"usageDetails": {
"input": 10,
"output": 20,
"total": 30,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
},
"timestamp": "2025-01-22T17:56:38.787196Z"
}
],
"metadata": {
"batch_size": 2,
"sdk_integration": "litellm",
"sdk_name": "python",
"sdk_version": "2.44.1",
"public_key": "pk-lf-e02aaea3-8668-4c9f-8c69-771a4ea1f5c9"
}
}

595
tests/logging_callback_tests/test_langfuse_e2e_test.py
View file

@ -1,595 +0,0 @@
import asyncio
import copy
import json
import logging
import os
import sys
import threading
from typing import Any, Optional
from unittest.mock import AsyncMock, MagicMock, patch
import httpx
logging.basicConfig(level=logging.DEBUG)
sys.path.insert(0, os.path.abspath("../.."))
import litellm
from litellm import completion
from litellm.caching import InMemoryCache
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler
litellm.num_retries = 3
litellm.success_callback = ["langfuse"]
os.environ["LANGFUSE_DEBUG"] = "True"
import time
import pytest
import pytest_asyncio
def assert_langfuse_request_matches_expected(
actual_request_body: dict,
expected_file_name: str,
trace_id: Optional[str] = None,
):
"""
Helper function to compare actual Langfuse request body with expected JSON file.
Args:
actual_request_body (dict): The actual request body received from the API call
expected_file_name (str): Name of the JSON file containing expected request body (e.g., "transcription.json")
"""
# Get the current directory and read the expected request body
pwd = os.path.dirname(os.path.realpath(__file__))
expected_body_path = os.path.join(
pwd, "langfuse_expected_request_body", expected_file_name
)
with open(expected_body_path, "r") as f:
expected_request_body = json.load(f)
# Filter out events that don't match the trace_id
if trace_id:
actual_request_body["batch"] = [
item
for item in actual_request_body["batch"]
if (item["type"] == "trace-create" and item["body"].get("id") == trace_id)
or (
item["type"] == "generation-create"
and item["body"].get("traceId") == trace_id
)
]
# When aggregating from multiple flush cycles, deduplicate by keeping
# only one trace-create and one generation-create per trace_id.
seen_types: dict = {}
deduped_batch: list = []
for item in actual_request_body["batch"]:
item_type = item["type"]
if item_type not in seen_types:
seen_types[item_type] = True
deduped_batch.append(item)
actual_request_body["batch"] = deduped_batch
# Ensure canonical order: trace-create first, generation-create second
actual_request_body["batch"].sort(
key=lambda x: 0 if x["type"] == "trace-create" else 1
)
print(
"actual_request_body after filtering", json.dumps(actual_request_body, indent=4)
)
assert len(actual_request_body["batch"]) >= 2, (
f"Expected at least 2 batch items (trace-create + generation-create) "
f"after filtering by trace_id={trace_id}, "
f"but got {len(actual_request_body['batch'])}. "
f"Items: {json.dumps(actual_request_body['batch'], indent=2)}"
)
# Replace dynamic values in actual request body
for item in actual_request_body["batch"]:
# Replace IDs with expected IDs
if item["type"] == "trace-create":
item["id"] = expected_request_body["batch"][0]["id"]
item["body"]["id"] = expected_request_body["batch"][0]["body"]["id"]
item["timestamp"] = expected_request_body["batch"][0]["timestamp"]
item["body"]["timestamp"] = expected_request_body["batch"][0]["body"][
"timestamp"
]
elif item["type"] == "generation-create":
item["id"] = expected_request_body["batch"][1]["id"]
item["body"]["id"] = expected_request_body["batch"][1]["body"]["id"]
item["timestamp"] = expected_request_body["batch"][1]["timestamp"]
item["body"]["startTime"] = expected_request_body["batch"][1]["body"][
"startTime"
]
item["body"]["endTime"] = expected_request_body["batch"][1]["body"][
"endTime"
]
item["body"]["completionStartTime"] = expected_request_body["batch"][1][
"body"
]["completionStartTime"]
if trace_id is None:
print("popping traceId")
item["body"].pop("traceId")
else:
item["body"]["traceId"] = trace_id
expected_request_body["batch"][1]["body"]["traceId"] = trace_id
# Replace SDK version with expected version
actual_request_body["batch"][0]["body"].pop("release", None)
actual_request_body["metadata"]["sdk_version"] = expected_request_body["metadata"][
"sdk_version"
]
# replace "public_key" with expected public key
actual_request_body["metadata"]["public_key"] = expected_request_body["metadata"][
"public_key"
]
actual_request_body["batch"][1]["body"]["metadata"] = expected_request_body[
"batch"
][1]["body"]["metadata"]
actual_request_body["metadata"]["sdk_integration"] = expected_request_body[
"metadata"
]["sdk_integration"]
actual_request_body["metadata"]["batch_size"] = expected_request_body["metadata"][
"batch_size"
]
# Assert the entire request body matches
assert (
actual_request_body == expected_request_body
), f"Difference in request bodies: {json.dumps(actual_request_body, indent=2)} != {json.dumps(expected_request_body, indent=2)}"
class TestLangfuseLogging:
@pytest_asyncio.fixture
async def mock_setup(self):
"""Common setup for Langfuse logging tests"""
from litellm._uuid import uuid
from unittest.mock import AsyncMock, patch
import httpx
# Create a mock Response object
mock_response = AsyncMock(spec=httpx.Response)
mock_response.status_code = 200
mock_response.json.return_value = {"status": "success"}
# Create mock for httpx.Client.post
mock_post = AsyncMock()
mock_post.return_value = mock_response
litellm.set_verbose = True
litellm.success_callback = ["langfuse"]
return {"trace_id": f"litellm-test-{str(uuid.uuid4())}", "mock_post": mock_post}
async def _verify_langfuse_call(
self,
mock_post,
expected_file_name: str,
trace_id: str,
):
"""Helper method to verify Langfuse API calls"""
await asyncio.sleep(3)
# Verify at least one call was made
assert mock_post.call_count >= 1
# Aggregate batch items from ALL calls — the Langfuse SDK may split
# trace-create and generation-create across separate HTTP flushes.
langfuse_url = "https://us.cloud.langfuse.com/api/public/ingestion"
all_batch_items: list = []
metadata: Optional[dict] = None
for call in mock_post.call_args_list:
url = call[0][0]
if url != langfuse_url:
continue
request_body = call[1].get("content")
if request_body:
body = json.loads(request_body)
all_batch_items.extend(body.get("batch", []))
if metadata is None:
metadata = body.get("metadata")
assert len(all_batch_items) > 0, "No Langfuse ingestion calls found"
assert metadata is not None, "No metadata found in Langfuse calls"
actual_request_body = {
"batch": all_batch_items,
"metadata": metadata,
}
print("\nMocked Request Details (aggregated from all calls):")
print(f"Request Body: {json.dumps(actual_request_body, indent=4)}")
assert_langfuse_request_matches_expected(
actual_request_body,
expected_file_name,
trace_id,
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion(self, mock_setup):
"""Test Langfuse logging for chat completion"""
setup = mock_setup
with patch("httpx.Client.post", setup["mock_post"]):
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response="Hello! How can I assist you today?",
metadata={"trace_id": setup["trace_id"]},
)
await self._verify_langfuse_call(
setup["mock_post"], "completion.json", setup["trace_id"]
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion_with_tags(self, mock_setup):
"""Test Langfuse logging for chat completion with tags"""
setup = mock_setup
with patch("httpx.Client.post", setup["mock_post"]):
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response="Hello! How can I assist you today?",
metadata={
"trace_id": setup["trace_id"],
"tags": ["test_tag", "test_tag_2"],
},
)
await self._verify_langfuse_call(
setup["mock_post"], "completion_with_tags.json", setup["trace_id"]
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion_with_tags_stream(self, mock_setup):
"""Test Langfuse logging for chat completion with tags"""
setup = mock_setup
with patch("httpx.Client.post", setup["mock_post"]):
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response="Hello! How can I assist you today?",
metadata={
"trace_id": setup["trace_id"],
"tags": ["test_tag_stream", "test_tag_2_stream"],
},
)
await self._verify_langfuse_call(
setup["mock_post"],
"completion_with_tags_stream.json",
setup["trace_id"],
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion_with_langfuse_metadata(self, mock_setup):
"""Test Langfuse logging for chat completion with metadata for langfuse"""
setup = mock_setup
with patch("httpx.Client.post", setup["mock_post"]):
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response="Hello! How can I assist you today?",
metadata={
"trace_id": setup["trace_id"],
"tags": ["test_tag", "test_tag_2"],
"generation_name": "test_generation_name",
"parent_observation_id": "test_parent_observation_id",
"version": "test_version",
"trace_user_id": "test_user_id",
"session_id": "test_session_id",
"trace_name": "test_trace_name",
"trace_metadata": {"test_key": "test_value"},
"trace_version": "test_trace_version",
"trace_release": "test_trace_release",
},
)
await self._verify_langfuse_call(
setup["mock_post"],
"completion_with_langfuse_metadata.json",
setup["trace_id"],
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_with_non_serializable_metadata(self, mock_setup):
"""Test Langfuse logging with metadata that requires preparation (Pydantic models, sets, etc)"""
from pydantic import BaseModel
from typing import Set
import datetime
class UserPreferences(BaseModel):
favorite_colors: Set[str]
last_login: datetime.datetime
settings: dict
setup = mock_setup
test_metadata = {
"user_prefs": UserPreferences(
favorite_colors={"red", "blue"},
last_login=datetime.datetime.now(),
settings={"theme": "dark", "notifications": True},
),
"nested_set": {
"inner_set": {1, 2, 3},
"inner_pydantic": UserPreferences(
favorite_colors={"green", "yellow"},
last_login=datetime.datetime.now(),
settings={"theme": "light"},
),
},
"trace_id": setup["trace_id"],
}
with patch("httpx.Client.post", setup["mock_post"]):
response = await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response="Hello! How can I assist you today?",
metadata=test_metadata,
)
await self._verify_langfuse_call(
setup["mock_post"],
"completion_with_complex_metadata.json",
setup["trace_id"],
)
@pytest.mark.asyncio
@pytest.mark.parametrize(
"test_metadata, response_json_file",
[
({"a": 1, "b": 2, "c": 3}, "simple_metadata.json"),
(
{"a": {"nested_a": 1}, "b": {"nested_b": 2}},
"nested_metadata.json",
),
({"a": [1, 2, 3], "b": {4, 5, 6}}, "simple_metadata2.json"),
(
{"a": (1, 2), "b": frozenset([3, 4]), "c": {"d": [5, 6]}},
"simple_metadata3.json",
),
({"lock": threading.Lock()}, "metadata_with_lock.json"),
({"func": lambda x: x + 1}, "metadata_with_function.json"),
(
{
"int": 42,
"str": "hello",
"list": [1, 2, 3],
"set": {4, 5},
"dict": {"nested": "value"},
"non_copyable": threading.Lock(),
"function": print,
},
"complex_metadata.json",
),
(
{"list": ["list", "not", "a", "dict"]},
"complex_metadata_2.json",
),
({}, "empty_metadata.json"),
],
)
@pytest.mark.flaky(retries=6, delay=1)
async def test_langfuse_logging_with_various_metadata_types(
self, mock_setup, test_metadata, response_json_file
):
"""Test Langfuse logging with various metadata types including non-serializable objects"""
import threading
setup = mock_setup
if test_metadata is not None:
test_metadata["trace_id"] = setup["trace_id"]
with patch("httpx.Client.post", setup["mock_post"]):
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response="Hello! How can I assist you today?",
metadata=test_metadata,
)
await self._verify_langfuse_call(
setup["mock_post"],
response_json_file,
setup["trace_id"],
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion_with_malformed_llm_response(
self, mock_setup
):
"""Test Langfuse logging for chat completion with malformed LLM response"""
setup = mock_setup
litellm._turn_on_debug()
with patch("httpx.Client.post", setup["mock_post"]):
mock_response = litellm.ModelResponse(
choices=[],
usage=litellm.Usage(
prompt_tokens=10,
completion_tokens=10,
total_tokens=20,
),
model="gpt-3.5-turbo",
object="chat.completion",
created=1723081200,
).model_dump()
await litellm.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response=mock_response,
metadata={"trace_id": setup["trace_id"]},
)
await self._verify_langfuse_call(
setup["mock_post"], "completion_with_no_choices.json", setup["trace_id"]
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion_with_bedrock_llm_response(
self, mock_setup
):
"""Test Langfuse logging for chat completion with malformed LLM response"""
setup = mock_setup
litellm._turn_on_debug()
with patch("httpx.Client.post", setup["mock_post"]):
mock_response = litellm.ModelResponse(
choices=[],
usage=litellm.Usage(
prompt_tokens=10,
completion_tokens=10,
total_tokens=20,
),
model="anthropic.claude-haiku-4-5-20251001-v1:0",
object="chat.completion",
created=1723081200,
).model_dump()
await litellm.acompletion(
model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
messages=[{"role": "user", "content": "Hello!"}],
mock_response=mock_response,
metadata={"trace_id": setup["trace_id"]},
aws_access_key_id="fake-key",
aws_secret_access_key="fake-key",
aws_region="us-east-1",
)
await self._verify_langfuse_call(
setup["mock_post"],
"completion_with_bedrock_call.json",
setup["trace_id"],
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_completion_with_vertex_llm_response(
self, mock_setup
):
"""Test Langfuse logging for chat completion with malformed LLM response"""
setup = mock_setup
litellm._turn_on_debug()
with patch("httpx.Client.post", setup["mock_post"]):
mock_response = litellm.ModelResponse(
choices=[],
usage=litellm.Usage(
prompt_tokens=10,
completion_tokens=10,
total_tokens=20,
),
model="vertex/gemini-2.0-flash-001",
object="chat.completion",
created=1723081200,
).model_dump()
await litellm.acompletion(
model="vertex_ai/gemini-2.0-flash-001",
messages=[{"role": "user", "content": "Hello!"}],
mock_response=mock_response,
metadata={"trace_id": setup["trace_id"]},
vertex_credentials="my-mock-credentials",
api_key="my-mock-credentials-2",
)
await self._verify_langfuse_call(
setup["mock_post"],
"completion_with_vertex_call.json",
setup["trace_id"],
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_vllm_embedding(self, mock_setup):
"""
Test that the request sent to the vllm embedding endpoint is correct.
Verifies the request body matches the expected JSON fixture,
including that the hosted_vllm/ prefix is stripped from the model name
and that no unexpected fields (e.g. encoding_format) are included.
"""
setup = mock_setup
vllm_response_data = {
"object": "list",
"data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}],
"model": "BAAI/bge-small-en-v1.5",
"usage": {"prompt_tokens": 10, "total_tokens": 10},
}
mock_vllm_response = httpx.Response(
status_code=200,
json=vllm_response_data,
)
mock_async_client = AsyncHTTPHandler()
mock_async_client.post = AsyncMock(return_value=mock_vllm_response)
with patch("httpx.Client.post", setup["mock_post"]):
await litellm.aembedding(
model="hosted_vllm/BAAI/bge-small-en-v1.5",
input=["Hello from litellm!"],
api_base="http://my-fake-vllm.com/v1",
metadata={"trace_id": setup["trace_id"]},
client=mock_async_client,
)
# Verify the request sent to vllm matches the expected JSON fixture
assert mock_async_client.post.call_count == 1
actual_vllm_request = mock_async_client.post.call_args.kwargs["json"]
pwd = os.path.dirname(os.path.realpath(__file__))
expected_body_path = os.path.join(
pwd, "langfuse_expected_request_body", "embedding_with_vllm.json"
)
with open(expected_body_path, "r") as f:
expected_vllm_request = json.load(f)
assert actual_vllm_request == expected_vllm_request, (
f"vllm request body mismatch:\n"
f"actual: {json.dumps(actual_vllm_request, indent=2)}\n"
f"expected: {json.dumps(expected_vllm_request, indent=2)}"
)
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_langfuse_logging_with_router(self, mock_setup):
"""Test Langfuse logging with router"""
litellm._turn_on_debug()
router = litellm.Router(
model_list=[
{
"model_name": "gpt-3.5-turbo",
"litellm_params": {
"model": "gpt-3.5-turbo",
"mock_response": "Hello! How can I assist you today?",
"api_key": "test_api_key",
},
}
]
)
with patch("httpx.Client.post", mock_setup["mock_post"]):
mock_response = litellm.ModelResponse(
choices=[],
usage=litellm.Usage(
prompt_tokens=10,
completion_tokens=10,
total_tokens=20,
),
model="gpt-3.5-turbo",
object="chat.completion",
created=1723081200,
).model_dump()
await router.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello!"}],
mock_response=mock_response,
metadata={"trace_id": mock_setup["trace_id"]},
)
await self._verify_langfuse_call(
mock_setup["mock_post"],
"completion_with_router.json",
mock_setup["trace_id"],
)