76 lines
2.8 KiB
Python
76 lines
2.8 KiB
Python
"""镜像生成：成功造出正解相反的镜像；正解相同/生成 null → 返回 None。"""
|
|
|
|
import pytest
|
|
|
|
from app.question_gen.adversarial_filter import generate_mirror_question
|
|
from core.types import GeneratedQuestion, LLMResponse
|
|
|
|
|
|
class _FakeVLM:
|
|
def __init__(self, content: str):
|
|
self._content = content
|
|
|
|
async def chat_with_images(self, messages, images, *, session_id=None, parent_call_id=None):
|
|
return LLMResponse(
|
|
content=self._content, thinking="", model="fake", provider="fake",
|
|
prompt_tokens=0, completion_tokens=0, latency_ms=0,
|
|
ttft_ms=None, max_inter_token_ms=None, cache_hit=False, call_id="c",
|
|
)
|
|
|
|
|
|
def _q():
|
|
return GeneratedQuestion(
|
|
question_id="q1", video_id="v1", task_type="Action Recognition",
|
|
question="X 之前做了什么？", options=("A. 蒸", "B. 炒", "C. 煮", "D. 炸"),
|
|
answer="A", source_nodes=("n1",), difficulty="hard",
|
|
sub_pattern="temporal_reasoning_failure",
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mirror_distinct_correct_ok():
|
|
vlm = _FakeVLM('{"mirror": {"question": "X 之后做了什么？", '
|
|
'"options": ["A. 炒", "B. 蒸", "C. 煮", "D. 炸"], "answer": "A"}}')
|
|
mirror = await generate_mirror_question(
|
|
_q(), flip_axis="before/after", vlm=vlm, material=_FakeMaterial(), session_id="s",
|
|
)
|
|
assert mirror is not None
|
|
# 原正解 canonical="蒸"，镜像正解 canonical="炒" → 相异，有效
|
|
assert mirror.answer == "A"
|
|
assert mirror.options[0] == "A. 炒"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mirror_same_correct_rejected():
|
|
# 镜像正解 canonical 仍是"蒸" → 造不出有效对 → None
|
|
vlm = _FakeVLM('{"mirror": {"question": "X 之后？", '
|
|
'"options": ["A. 蒸", "B. 炒", "C. 煮", "D. 炸"], "answer": "A"}}')
|
|
mirror = await generate_mirror_question(
|
|
_q(), flip_axis="before/after", vlm=vlm, material=_FakeMaterial(), session_id="s",
|
|
)
|
|
assert mirror is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mirror_null_returns_none():
|
|
vlm = _FakeVLM('{"mirror": null}')
|
|
mirror = await generate_mirror_question(
|
|
_q(), flip_axis="before/after", vlm=vlm, material=_FakeMaterial(), session_id="s",
|
|
)
|
|
assert mirror is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_mirror_malformed_response_returns_none():
|
|
# 畸形 VLM 响应（连 json_repair 都救不回）不得抛异常中断本轮，须返 None
|
|
vlm = _FakeVLM("对不起，我无法完成这个请求。")
|
|
mirror = await generate_mirror_question(
|
|
_q(), flip_axis="before/after", vlm=vlm, material=_FakeMaterial(), session_id="s",
|
|
)
|
|
assert mirror is None
|
|
|
|
|
|
class _FakeMaterial:
|
|
subtitle_sentences = ["先炒后蒸"]
|
|
frame_paths = ["/f1.jpg"]
|