phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(tests): enable MCP tests in server mode (#4146)

Browse source 
We would like to run all OpenAI compatibility tests using only the
openai-client library. This is most friendly for contributors since they
can run tests without needing to update the client-sdks (which is
getting easier but still a long pole.)

This is the first step in enabling that -- no using "library client" for
any of the Responses tests. This seems like a reasonable trade-off since
the usage of an embeddeble library client for Responses (or any
OpenAI-compatible) behavior seems to be not very common. To do this, we
needed to enable MCP tests (which only worked in library client mode)
for server mode.
This commit is contained in:
Ashwin Bharambe 2025-11-13 07:23:23 -08:00 • committed by GitHub
parent 9eb81439d2
commit 1e81056a22
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
29 changed files with 13388 additions and 127 deletions
Download patch file Download diff file Expand all files Collapse all files

30
tests/integration/responses/test_basic_responses.py
View file

@ -13,8 +13,8 @@ from .streaming_assertions import StreamingValidator
@pytest.mark.parametrize("case", basic_test_cases)
def test_response_non_streaming_basic(compat_client, text_model_id, case):
response = compat_client.responses.create(
def test_response_non_streaming_basic(responses_client, text_model_id, case):
response = responses_client.responses.create(
model=text_model_id,
input=case.input,
stream=False,
@ -31,10 +31,10 @@ def test_response_non_streaming_basic(compat_client, text_model_id, case):
"Total tokens should equal input + output tokens"
)
retrieved_response = compat_client.responses.retrieve(response_id=response.id)
retrieved_response = responses_client.responses.retrieve(response_id=response.id)
assert retrieved_response.output_text == response.output_text
next_response = compat_client.responses.create(
next_response = responses_client.responses.create(
model=text_model_id,
input="Repeat your previous response in all caps.",
previous_response_id=response.id,
@ -44,8 +44,8 @@ def test_response_non_streaming_basic(compat_client, text_model_id, case):
@pytest.mark.parametrize("case", basic_test_cases)
def test_response_streaming_basic(compat_client, text_model_id, case):
response = compat_client.responses.create(
def test_response_streaming_basic(responses_client, text_model_id, case):
response = responses_client.responses.create(
model=text_model_id,
input=case.input,
stream=True,
@ -98,15 +98,15 @@ def test_response_streaming_basic(compat_client, text_model_id, case):
validator.assert_response_consistency()
# Verify stored response matches streamed response
retrieved_response = compat_client.responses.retrieve(response_id=response_id)
retrieved_response = responses_client.responses.retrieve(response_id=response_id)
final_event = events[-1]
assert retrieved_response.output_text == final_event.response.output_text
@pytest.mark.parametrize("case", basic_test_cases)
def test_response_streaming_incremental_content(compat_client, text_model_id, case):
def test_response_streaming_incremental_content(responses_client, text_model_id, case):
"""Test that streaming actually delivers content incrementally, not just at the end."""
response = compat_client.responses.create(
response = responses_client.responses.create(
model=text_model_id,
input=case.input,
stream=True,
@ -170,10 +170,10 @@ def test_response_streaming_incremental_content(compat_client, text_model_id, ca
@pytest.mark.parametrize("case", multi_turn_test_cases)
def test_response_non_streaming_multi_turn(compat_client, text_model_id, case):
def test_response_non_streaming_multi_turn(responses_client, text_model_id, case):
previous_response_id = None
for turn_input, turn_expected in case.turns:
response = compat_client.responses.create(
response = responses_client.responses.create(
model=text_model_id,
input=turn_input,
previous_response_id=previous_response_id,
@ -184,8 +184,8 @@ def test_response_non_streaming_multi_turn(compat_client, text_model_id, case):
@pytest.mark.parametrize("case", image_test_cases)
def test_response_non_streaming_image(compat_client, text_model_id, case):
response = compat_client.responses.create(
def test_response_non_streaming_image(responses_client, text_model_id, case):
response = responses_client.responses.create(
model=text_model_id,
input=case.input,
stream=False,
@ -195,10 +195,10 @@ def test_response_non_streaming_image(compat_client, text_model_id, case):
@pytest.mark.parametrize("case", multi_turn_image_test_cases)
def test_response_non_streaming_multi_turn_image(compat_client, text_model_id, case):
def test_response_non_streaming_multi_turn_image(responses_client, text_model_id, case):
previous_response_id = None
for turn_input, turn_expected in case.turns:
response = compat_client.responses.create(
response = responses_client.responses.create(
model=text_model_id,
input=turn_input,
previous_response_id=previous_response_id,