scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

test(vertex_ai): fix total_tokens assertion in gemma streaming tests

Browse source 
_make_gemma_vertex_response hardcodes completion_tokens=100, so usage
totals 114, not the 15 the moved tests asserted. Vertex AI shard failed
with 'assert 114 == 15' on the #43414 merge

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Krrish Dholakia 2026-09-27 04:57:14 +00:00
parent 491d454826
commit 18794f10af
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
tests/unit/llms/vertex_ai/vertex_gemma_models/test_vertex_gemma_transformation.py
View file

@ -1332,7 +1332,7 @@ def test_sync_gemma_stream(_gemma_cached_access_token):
def handle(request):
captured["body"] = json.loads(request.content)
return httpx.Response(200, json=_make_gemma_vertex_response(content="READY", total_tokens=15))
return httpx.Response(200, json=_make_gemma_vertex_response(content="READY"))
stream = litellm.completion(
model="vertex_ai/gemma/test-model",
@ -1362,7 +1362,7 @@ async def test_async_gemma_responses_stream(_gemma_cached_access_token):
def handle(request):
captured["body"] = json.loads(request.content)
return httpx.Response(200, json=_make_gemma_vertex_response(content="READY", total_tokens=15))
return httpx.Response(200, json=_make_gemma_vertex_response(content="READY"))
response = await litellm.aresponses(
model="vertex_ai/gemma/test-model",
@ -1380,4 +1380,4 @@ async def test_async_gemma_responses_stream(_gemma_cached_access_token):
assert "READY" in "".join(event.delta for event in events if isinstance(event, OutputTextDeltaEvent))
assert isinstance(events[-1], ResponseCompletedEvent)
assert events[-1].response.usage is not None
assert events[-1].response.usage.total_tokens == 15
assert events[-1].response.usage.total_tokens == 114