56 lines
2.0 KiB
Python
56 lines
2.0 KiB
Python
import json
|
|
import pytest
|
|
import httpx
|
|
|
|
|
|
@pytest.mark.parametrize("case", list(range(120)))
|
|
def test_responses_non_stream(api_client, respx_mock, case):
|
|
respx_mock.get("http://llama.test/v1/models").mock(
|
|
return_value=httpx.Response(200, json={"data": [{"id": "model-a.gguf"}]})
|
|
)
|
|
respx_mock.post("http://llama.test/v1/chat/completions").mock(
|
|
return_value=httpx.Response(200, json={"choices": [{"message": {"content": f"reply-{case}"}}]})
|
|
)
|
|
|
|
payload = {
|
|
"model": "model-a.gguf",
|
|
"input": f"prompt-{case}",
|
|
"max_output_tokens": 32,
|
|
}
|
|
resp = api_client.post("/v1/responses", json=payload)
|
|
assert resp.status_code == 200
|
|
data = resp.json()
|
|
assert data["object"] == "response"
|
|
assert data["output"][0]["content"][0]["text"].startswith("reply-")
|
|
|
|
|
|
@pytest.mark.parametrize("case", list(range(120)))
|
|
def test_responses_stream(api_client, respx_mock, case):
|
|
respx_mock.get("http://llama.test/v1/models").mock(
|
|
return_value=httpx.Response(200, json={"data": [{"id": "model-a.gguf"}]})
|
|
)
|
|
|
|
def stream_response(request):
|
|
payload = {
|
|
"id": "chunk",
|
|
"object": "chat.completion.chunk",
|
|
"choices": [{"delta": {"content": f"hi-{case}"}, "index": 0, "finish_reason": None}],
|
|
}
|
|
content = f"data: {json.dumps(payload)}\n\n".encode()
|
|
content += b"data: [DONE]\n\n"
|
|
return httpx.Response(200, content=content, headers={"Content-Type": "text/event-stream"})
|
|
|
|
respx_mock.post("http://llama.test/v1/chat/completions").mock(side_effect=stream_response)
|
|
|
|
payload = {
|
|
"model": "model-a.gguf",
|
|
"input": f"prompt-{case}",
|
|
"stream": True,
|
|
}
|
|
with api_client.stream("POST", "/v1/responses", json=payload) as resp:
|
|
assert resp.status_code == 200
|
|
body = b"".join(resp.iter_bytes())
|
|
assert b"event: response.created" in body
|
|
assert b"event: response.output_text.delta" in body
|
|
assert b"event: response.completed" in body
|