iomgaa
b6b6a48503
- TaskTypeStrategy Protocol: pipeline 的唯一接口，定义 task_type、 sampling_level、sampling_constraint、prompt_template 等属性 - SubPattern frozen dataclass: 出题子模式，靶向特定失败机制 - BaseTaskTypeStrategy: 封装现有 QuestionFamilySpec 行为的默认策略， 所有属性委托给绑定的 family - _TASK_TYPE_TO_FAMILY: 消歧绑定表，12 个题型确定性绑定到 1 个 family - register_strategy/get_strategy: 注册表 API，未注册题型自动创建 BaseTaskTypeStrategy - 13 个单元测试全部通过 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
119 lines
4.0 KiB
Python
119 lines
4.0 KiB
Python
"""TaskTypeStrategy Protocol 与 BaseTaskTypeStrategy 单元测试。"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import random
|
|
|
|
import pytest
|
|
|
|
from app.question_gen.families import (
|
|
ENUMERATION_FAMILY,
|
|
REASONING_FAMILY,
|
|
RETRIEVAL_FAMILY,
|
|
SPATIAL_FAMILY,
|
|
VISUAL_FAMILY,
|
|
)
|
|
from app.question_gen.strategy import (
|
|
BaseTaskTypeStrategy,
|
|
SubPattern,
|
|
get_strategy,
|
|
register_strategy,
|
|
)
|
|
|
|
|
|
class TestBaseTaskTypeStrategy:
|
|
"""BaseTaskTypeStrategy 封装 family 行为。"""
|
|
|
|
def test_task_type_and_strategy_name(self):
|
|
"""task_type 和 strategy_name 正确返回。"""
|
|
s = BaseTaskTypeStrategy(task_type="Object Recognition", family=RETRIEVAL_FAMILY)
|
|
assert s.task_type == "Object Recognition"
|
|
assert s.strategy_name == "RETRIEVAL"
|
|
|
|
def test_sampling_from_family(self):
|
|
"""采样参数从绑定的 family 读取。"""
|
|
s = BaseTaskTypeStrategy(task_type="Temporal Reasoning", family=ENUMERATION_FAMILY)
|
|
assert s.sampling_level == 1
|
|
assert s.sampling_constraint.min_l3_nodes == 5
|
|
|
|
def test_skill_target_from_family(self):
|
|
"""skill_target 从 family 读取。"""
|
|
s = BaseTaskTypeStrategy(task_type="Action Reasoning", family=REASONING_FAMILY)
|
|
assert s.skill_target == "M2"
|
|
|
|
def test_leak_probe_template(self):
|
|
"""leak_probe_template 从 family.leak_profile 读取。"""
|
|
s = BaseTaskTypeStrategy(task_type="Spatial Reasoning", family=SPATIAL_FAMILY)
|
|
assert s.leak_probe_template == "gate_leak_spatial.md"
|
|
|
|
def test_prompt_template_from_family(self):
|
|
"""prompt_template 从 family 读取。"""
|
|
s = BaseTaskTypeStrategy(task_type="OCR Problems", family=VISUAL_FAMILY)
|
|
assert s.prompt_template == "visual.md"
|
|
|
|
def test_select_sub_pattern_returns_none(self):
|
|
"""BaseTaskTypeStrategy 无子模式。"""
|
|
s = BaseTaskTypeStrategy(task_type="Object Recognition", family=RETRIEVAL_FAMILY)
|
|
rng = random.Random(42)
|
|
assert s.select_sub_pattern(rng) is None
|
|
|
|
def test_extra_gates_returns_empty(self):
|
|
"""BaseTaskTypeStrategy 无额外 gate。"""
|
|
s = BaseTaskTypeStrategy(task_type="Object Recognition", family=RETRIEVAL_FAMILY)
|
|
assert s.extra_gates(None) == []
|
|
|
|
|
|
class TestSamplingLevelMapping:
|
|
"""BaseTaskTypeStrategy 的 sampling_level 从 _TASK_TYPE_TO_LEVEL 读取。"""
|
|
|
|
def test_l3_types(self):
|
|
"""L3 题型。"""
|
|
for tt in ("Object Recognition",):
|
|
s = BaseTaskTypeStrategy(task_type=tt, family=RETRIEVAL_FAMILY)
|
|
assert s.sampling_level == 3, f"{tt} should be L3"
|
|
|
|
def test_l2_types(self):
|
|
"""L2 题型。"""
|
|
s = BaseTaskTypeStrategy(task_type="Action Reasoning", family=REASONING_FAMILY)
|
|
assert s.sampling_level == 2
|
|
|
|
def test_l1_types(self):
|
|
"""L1 题型。"""
|
|
s = BaseTaskTypeStrategy(task_type="Temporal Reasoning", family=ENUMERATION_FAMILY)
|
|
assert s.sampling_level == 1
|
|
|
|
|
|
class TestStrategyRegistry:
|
|
"""注册表查找。"""
|
|
|
|
def test_get_unregistered_returns_base(self):
|
|
"""未注册题型返回 BaseTaskTypeStrategy。"""
|
|
s = get_strategy("Spatial Reasoning")
|
|
assert isinstance(s, BaseTaskTypeStrategy)
|
|
assert s.task_type == "Spatial Reasoning"
|
|
|
|
def test_register_and_get(self):
|
|
"""注册后 get 返回注册的策略。"""
|
|
custom = BaseTaskTypeStrategy(task_type="Object Recognition", family=RETRIEVAL_FAMILY)
|
|
register_strategy(custom)
|
|
assert get_strategy("Object Recognition") is custom
|
|
|
|
|
|
class TestSubPattern:
|
|
"""SubPattern 数据类。"""
|
|
|
|
def test_frozen(self):
|
|
"""SubPattern 不可变。"""
|
|
sp = SubPattern(
|
|
name="test",
|
|
weight=0.5,
|
|
sampling_level_override=None,
|
|
constraint_override=None,
|
|
instruction="test instruction",
|
|
positive_examples=[],
|
|
negative_examples=[],
|
|
distractor_rules="",
|
|
)
|
|
with pytest.raises(AttributeError):
|
|
sp.name = "changed"
|