chore: snapshot in-progress question-gen work before preflight fixes

This commit is contained in:
2026-07-16 04:12:21 -04:00
parent 11a5545f57
commit a4c429b247
39 changed files with 738 additions and 283 deletions
+9 -9
View File
@@ -14,21 +14,21 @@ from app.question_gen.families import (
get_family_for_slot,
)
# 12 种任务类型(来自 harness config
# Video-MME 12 种任务类型
ALL_TASK_TYPES: frozenset[str] = frozenset(
[
"Action Recognition",
"Action Reasoning",
"Action Prediction",
"Action Sequence",
"Attribute Perception",
"Counting Problem",
"Information Synopsis",
"Object Recognition",
"Object Reasoning",
"Object Interaction",
"Scene Understanding",
"Event Reasoning",
"Causal Reasoning",
"Temporal Reasoning",
"OCR Problems",
"Spatial Perception",
"Spatial Reasoning",
"Temporal Perception",
"Temporal Reasoning",
]
)
@@ -163,7 +163,7 @@ class TestGetFamilyForSlot:
def test_no_legal_family_raises(self) -> None:
"""所有 family 权重为 0 时合法族为空,应抛出 ValueError。"""
rng = random.Random(0)
# Spatial Reasoning 合法族: RETRIEVAL, REASONING, VISUAL, SPATIAL
# Spatial Reasoning 合法族: SPATIAL
# 如果 ratios 中只含不合法的族名,应抛错
with pytest.raises(ValueError, match="合法"):
get_family_for_slot(