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

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。
2026-07-11 08:53:56 -04:00
parent 291a8108e1
commit 4e0e05210d
4 changed files with 226 additions and 2 deletions
@@ -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