iomgaa/Video-Tree-TRM5
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(search): append raw entity fields after view_node summary

Browse Source 
view_node 按题两轮摘要（summarize_node）会吞掉 entities/visible_text
字段信号，Agent 站在证据节点上仍漏读实体（benchmark 错题 M1，案例
786-2、872-3、750-1）。dispatcher 侧在摘要后确定性追加 [实体]/[画面
文字] 原文区块，LLM 无法吞掉。

- TreeEnvironment.node_entity_fields：按层级取 card 实体字段原文，
  去空白、去重、分号拼接；空字段省键；未知节点抛 KeyError
- _handle_view_node Phase 2.5：摘要后、子节点概览前追加实体区块
- 附带 ruff format 修正 test_tree_environment.py 两处既有格式

算法 #11（树环境语义搜索）数据访问层扩展，不改搜索算法本身。
This commit is contained in:
iomgaa
2026-07-11 08:53:56 -04:00
parent 291a8108e1
commit 4e0e05210d
4 changed files with 226 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/unit/test_search_tools.py
+83
View File
@@ -444,3 +444,86 @@ class TestDispatchErrors:
context={},
)
assert "工具执行错误" in result
# ── view_node 实体追加测试（Spec-1 B）────────────────────────
def _make_entity_tree() -> TreeIndex:
"""L2 带实体字段的最小树（与 _make_test_tree 同构，仅换 card 内容）。"""
l2 = L2Node(
id="vid_L1_000_L2_000",
card=L2Card(
event_description="产品评测",
entities=["Bluetooth headset (both ears)", "reviewer"],
actions=["reviewing"],
action_subjects=["reviewer"],
visible_text=["$9.99"],
spatial_relations="",
state_changes=None,
),
time_range=(5.0, 15.0),
children=[],
)
l1 = L1Node(
id="vid_L1_000",
card=L1Card(
scene_summary="评测场景",
main_setting="室内",
key_entities=["reviewer"],
main_actions=["评测"],
topic_keywords=["数码"],
visible_text=[],
temporal_flow="线性",
),
time_range=(0.0, 30.0),
children=[l2],
)
return TreeIndex(
metadata=IndexMeta(source_path="test.mp4", modality="video"),
roots=[l1],
)
@pytest.fixture()
def entity_dispatcher(
prompts_dir: Path,
skills_registry: SkillRegistry,
) -> SearchToolDispatcher:
"""树含实体字段的 dispatcher（其余配置与 dispatcher fixture 一致）。"""
return SearchToolDispatcher(
env=TreeEnvironment(_make_entity_tree()),
tool_llm=FakeLLM(),
vlm=FakeVLM(),
ocr=FakeOCR(),
prompts_dir=prompts_dir,
skills=skills_registry,
embed_fn=_fake_embed_fn,
verify_vision=False,
anchor=False,
assemble_mode="ids",
)
class TestViewNodeEntityAppendix:
"""view_node 实体区块确定性追加测试。"""
@pytest.mark.asyncio()
async def test_view_node_appends_entity_blocks(
self, monkeypatch: pytest.MonkeyPatch, entity_dispatcher: SearchToolDispatcher
) -> None:
"""摘要后必须出现 [实体]/[画面文字] 区块（确定性追加，不经 LLM）。"""
async def _stub_summarize(*args: Any, **kwargs: Any) -> str:
return "[内容摘要] 与问题无关的摘要"
monkeypatch.setattr("app.search.tools.summarize_node", _stub_summarize)
result = await entity_dispatcher.dispatch(
"view_node",
{"node_id": "vid_L1_000_L2_000", "question": "耳机戴哪只耳？"},
context={},
)
assert "[实体]" in result
assert "Bluetooth headset (both ears)" in result
assert "[画面文字]" in result
assert "$9.99" in result
tests/unit/test_tree_environment.py
+94 -2
View File
@@ -250,7 +250,8 @@ class TestGetNodeText:
"""锚模式应返回带锚文本和 anchor_map 字典。"""
env = TreeEnvironment(_make_test_index())
text, anchor_map = env.get_node_text(
"vid_L1_000_L2_000_L3_000", anchor=True,
"vid_L1_000_L2_000_L3_000",
anchor=True,
)
# 锚文本包含 [cN] 标记
assert "[c1]" in text
@@ -271,7 +272,8 @@ class TestGetNodeText:
"""无字幕的 L3 节点锚模式不应产生 [sN] 锚。"""
env = TreeEnvironment(_make_test_index())
text, anchor_map = env.get_node_text(
"vid_L1_000_L2_000_L3_001", anchor=True,
"vid_L1_000_L2_000_L3_001",
anchor=True,
)
assert anchor_map is not None
assert not any(k.startswith("s") for k in anchor_map)
@@ -322,3 +324,93 @@ class TestGetChildrenInfo:
env = TreeEnvironment(index)
children = env.get_children_info("vid_L1_000")
assert len(children[0]["summary"]) == 123 # 120 + "..."
# ── node_entity_fields 测试（Spec-1 B）───────────────────────
def _make_entity_test_index() -> TreeIndex:
"""带实体字段的最小三层树（含一个空字段 L2）。"""
l3 = L3Node(
id="vid_L1_000_L2_000_L3_000",
card=L3Card(
frame_summary="一名男子戴耳机",
visible_entities=["Bluetooth headset (both ears)", "man"],
ongoing_actions=["talking"],
visible_text=["EARPHONE BOTTLE OPENER"],
spatial_layout="man center",
visual_attributes={},
),
timestamp=10.0,
)
l2 = L2Node(
id="vid_L1_000_L2_000",
card=L2Card(
event_description="产品评测",
entities=["Bluetooth headset (both ears)", "reviewer"],
actions=["reviewing"],
action_subjects=["reviewer"],
visible_text=["$9.99"],
spatial_relations="",
state_changes=None,
),
time_range=(0.0, 60.0),
children=[l3],
)
l2_empty = L2Node(
id="vid_L1_000_L2_001",
card=L2Card(
event_description="空镜",
entities=[],
actions=[],
action_subjects=[],
visible_text=[],
spatial_relations="",
state_changes=None,
),
time_range=(60.0, 120.0),
)
l1 = L1Node(
id="vid_L1_000",
card=L1Card(
scene_summary="评测场景",
main_setting="室内",
key_entities=["reviewer"],
main_actions=["评测"],
topic_keywords=["数码"],
visible_text=[],
temporal_flow="线性",
),
time_range=(0.0, 120.0),
children=[l2, l2_empty],
)
return TreeIndex(metadata=IndexMeta("/test.mp4", "video"), roots=[l1])
class TestNodeEntityFields:
"""node_entity_fields 方法测试（B 修复：dispatcher 追加原文）。"""
def test_l2_entities_and_visible_text(self) -> None:
"""L2 节点应返回 entities 和 visible_text 原文。"""
env = TreeEnvironment(_make_entity_test_index())
fields = env.node_entity_fields("vid_L1_000_L2_000")
assert "Bluetooth headset (both ears)" in fields["实体"]
assert "$9.99" in fields["画面文字"]
def test_l3_visible_entities(self) -> None:
"""L3 节点应返回 visible_entities 和 visible_text 原文。"""
env = TreeEnvironment(_make_entity_test_index())
fields = env.node_entity_fields("vid_L1_000_L2_000_L3_000")
assert "Bluetooth headset (both ears)" in fields["实体"]
assert "EARPHONE BOTTLE OPENER" in fields["画面文字"]
def test_empty_fields_omitted(self) -> None:
"""实体/画面文字均为空时应返回空字典（不含空键）。"""
env = TreeEnvironment(_make_entity_test_index())
assert env.node_entity_fields("vid_L1_000_L2_001") == {}
def test_unknown_node_raises(self) -> None:
"""查询不存在的节点应抛出 KeyError。"""
env = TreeEnvironment(_make_entity_test_index())
with pytest.raises(KeyError):
env.node_entity_fields("nonexistent")