llama.cpp verification source 2026-05-22
Some checks are pending
Copilot Setup Steps / copilot-setup-steps (push) Waiting to run
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
Update Operations Documentation / update-ops-docs (push) Waiting to run
Some checks are pending
Copilot Setup Steps / copilot-setup-steps (push) Waiting to run
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
Update Operations Documentation / update-ops-docs (push) Waiting to run
This commit is contained in:
73
tools/server/tests/unit/test_compat_oai_responses.py
Normal file
73
tools/server/tests/unit/test_compat_oai_responses.py
Normal file
@@ -0,0 +1,73 @@
|
||||
import pytest
|
||||
from openai import OpenAI
|
||||
from utils import *
|
||||
|
||||
server: ServerProcess
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def create_server():
|
||||
global server
|
||||
server = ServerPreset.tinyllama2()
|
||||
|
||||
def test_responses_with_openai_library():
|
||||
global server
|
||||
server.start()
|
||||
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
|
||||
res = client.responses.create(
|
||||
model="gpt-4.1",
|
||||
input=[
|
||||
{"role": "system", "content": "Book"},
|
||||
{"role": "user", "content": "What is the best book"},
|
||||
],
|
||||
max_output_tokens=8,
|
||||
temperature=0.8,
|
||||
)
|
||||
assert res.id.startswith("resp_")
|
||||
assert res.output[0].id is not None
|
||||
assert res.output[0].id.startswith("msg_")
|
||||
assert match_regex("(Suddenly)+", res.output_text)
|
||||
|
||||
def test_responses_stream_with_openai_library():
|
||||
global server
|
||||
server.start()
|
||||
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
|
||||
stream = client.responses.create(
|
||||
model="gpt-4.1",
|
||||
input=[
|
||||
{"role": "system", "content": "Book"},
|
||||
{"role": "user", "content": "What is the best book"},
|
||||
],
|
||||
max_output_tokens=8,
|
||||
temperature=0.8,
|
||||
stream=True,
|
||||
)
|
||||
|
||||
gathered_text = ''
|
||||
resp_id = ''
|
||||
msg_id = ''
|
||||
for r in stream:
|
||||
if r.type == "response.created":
|
||||
assert r.response.id.startswith("resp_")
|
||||
resp_id = r.response.id
|
||||
if r.type == "response.in_progress":
|
||||
assert r.response.id == resp_id
|
||||
if r.type == "response.output_item.added":
|
||||
assert r.item.id is not None
|
||||
assert r.item.id.startswith("msg_")
|
||||
msg_id = r.item.id
|
||||
if (r.type == "response.content_part.added" or
|
||||
r.type == "response.output_text.delta" or
|
||||
r.type == "response.output_text.done" or
|
||||
r.type == "response.content_part.done"):
|
||||
assert r.item_id == msg_id
|
||||
if r.type == "response.output_item.done":
|
||||
assert r.item.id == msg_id
|
||||
|
||||
if r.type == "response.output_text.delta":
|
||||
gathered_text += r.delta
|
||||
if r.type == "response.completed":
|
||||
assert r.response.id.startswith("resp_")
|
||||
assert r.response.output[0].id is not None
|
||||
assert r.response.output[0].id.startswith("msg_")
|
||||
assert gathered_text == r.response.output_text
|
||||
assert match_regex("(Suddenly)+", r.response.output_text)
|
||||
Reference in New Issue
Block a user