refactor(agent): inject deps via context_schema, LLM-driven photo/confirm nodes

- graph.py: LangGraph-native DI - StateGraph(context_schema=GraphDeps), nodes take (state, runtime: Runtime[GraphDeps]); build_graph() decoupled from LLM; deleted scaffold _event_reply/_fake_llm_propose/stub nodes - photo.py: model proposes stage+body via per-mode prompts (direct/addon); validator enforces clientMode exits; deterministic event forcing removed - confirm.py: single runtime for single/dual confirm, extraction call isolated per person_index - llm.py: workflow_fake_llm() (offline workflow-faithful responder, history-aware) for smoke/tests - backend: LangGraphBackend(graph, llm) passes context per call - tests: invoke helpers inject GraphDeps; illegal-proposal test asserts error + state untouched via second well-behaved fake Verified: 143 passed; smoke turns 1/2/1 with original welcome text
2026-10-21 15:11:16 +08:00
parent a5407e03b2
commit 6d0a2169c8
12 changed files with 794 additions and 187 deletions
@@ -0,0 +1,193 @@
+"""作业 5 验收测试：信息核实节点（LLM 决策版）。
+
+测试用脚本化 FakeLLM 模拟“行为良好的模型”：按用户最新输入
+返回对应的带前缀回复；字段提取调用按提示词返回 JSON。
+断言仍是行为级的：stage 推进、person_fields 落库、person_index
+切换、模糊不计入失败。
+"""
+
+import json
+
+import pytest
+
+from src.agent.graph import GraphDeps, build_graph, workflow_fake_llm
+from src.agent.llm import FakeLLMService
+
+
+def latest_input(message: str) -> str:
+    return message.split("【用户最新输入】")[-1].strip()
+
+
+def make_llm(dialogue_script, extraction_script=None):
+    """dialogue_script(latest_input) -> 带前缀回复；
+    extraction_script(extraction_system_prompt) -> JSON 字符串。"""
+
+    def responder(system, user):
+        if system.startswith("【字段提取】"):
+            if extraction_script:
+                return extraction_script(system)
+            return "{}"
+        return dialogue_script(latest_input(user))
+
+    return FakeLLMService(responder)
+
+
+async def invoke(graph, thread_id, text, llm=None, **initial):
+    payload = {"session_id": thread_id, "input_text": text}
+    payload.update(initial)
+    return await graph.ainvoke(
+        payload,
+        config={"configurable": {"thread_id": thread_id}},
+        context=GraphDeps(llm=llm or workflow_fake_llm()),
+    )
+
+
+# ---------- 单车核实 ----------
+
+
+@pytest.mark.asyncio
+async def test_entry_consumes_pending_identity_question():
+    # 用户确认车主身份 → 模型直接问姓名（身份问题的提问发生在
+    # 拍照节点进入 3001 的同一回复里，这里不得重复）
+    llm = make_llm(
+        lambda q: "<state>3001</state>好的，请问您的姓名是什么？"
+    )
+    graph = build_graph()
+    result = await invoke(
+        graph, "t-entry", "是的，我是车主", llm=llm,
+        stage_code="3001", client_mode="direct",
+    )
+
+    assert result["stage_code"] == "3001"
+    assert "姓名" in result["response_text"]
+    assert "车主" not in result["response_text"]
+
+
+@pytest.mark.asyncio
+async def test_single_confirm_full_chain_to_0000():
+    def dialogue(q):
+        if q == "是的":
+            return "<state>3001</state>好的，请问您的姓名是什么？"
+        if q == "张三":
+            return "<state>3001</state>张三您好，请问您的身份证号码后四位是否正确？"
+        if q == "是对的":
+            return "<state>3001</state>请问您的手机号码后四位是否正确？"
+        return "<state>0000</state>好的，信息已全部确认无误。感谢您的配合。"
+
+    def extraction(system):
+        if "【用户输入】张三" in system:
+            return json.dumps({"xm1": "张三"}, ensure_ascii=False)
+        return "{}"
+
+    llm = make_llm(dialogue, extraction)
+    graph = build_graph()
+
+    r1 = await invoke(graph, "t-chain", "是的", llm=llm, stage_code="3001")
+    assert "姓名" in r1["response_text"]
+    r2 = await invoke(graph, "t-chain", "张三", llm=llm)
+    assert "身份证" in r2["response_text"]
+    assert r2["person_fields"]["xm1"] == "张三"
+    r3 = await invoke(graph, "t-chain", "是对的", llm=llm)
+    assert "手机" in r3["response_text"]
+    r4 = await invoke(graph, "t-chain", "没错", llm=llm)
+    assert r4["stage_code"] == "0000"
+    assert r4["response_text"].startswith("<state>0000</state>")
+
+
+@pytest.mark.asyncio
+async def test_deny_collects_correct_value():
+    llm = make_llm(
+        lambda q: "<state>3001</state>抱歉，请告诉我您正确的身份证号码后四位。",
+        lambda system: "{}",
+    )
+    graph = build_graph()
+    result = await invoke(
+        graph, "t-deny", "不对", llm=llm,
+        stage_code="3001", person_fields={"xm1": "张三"}, client_mode="direct",
+    )
+
+    assert result["stage_code"] == "3001"
+    assert "身份证" in result["response_text"]
+    assert result["person_fields"].get("sfzmwh1") in (None, "")
+
+
+@pytest.mark.asyncio
+async def test_vague_answer_stays_without_counting_failure():
+    llm = make_llm(
+        lambda q: "<state>3001</state>请问您是否是这辆车的车主？请回答“是”或“不是”。",
+        lambda system: "{}",
+    )
+    graph = build_graph()
+    result = await invoke(
+        graph, "t-vague", "嗯", llm=llm,
+        stage_code="3001", clarify_count=0, client_mode="direct",
+    )
+
+    assert result["stage_code"] == "3001"
+    assert "车主" in result["response_text"]
+    assert (result.get("clarify_count") or 0) == 0
+
+
+# ---------- 双车核实 ----------
+
+
+@pytest.mark.asyncio
+async def test_dual_person_index_switches_after_handoff():
+    llm = make_llm(
+        lambda q: "<state>3002</state>您好。请问这辆车是由您驾驶的吗？",
+        lambda system: json.dumps({"person_index": 2}),
+    )
+    graph = build_graph()
+    result = await invoke(
+        graph, "t-dual", "移交完毕", llm=llm,
+        stage_code="3002", person_index=1,
+        person_fields={"xm1": "张三"}, client_mode="direct",
+    )
+
+    assert result["stage_code"] == "3002"
+    assert result["person_index"] == 2
+    assert "驾驶" in result["response_text"]
+
+
+@pytest.mark.asyncio
+async def test_dual_second_person_fields_isolated():
+    def dialogue(q):
+        if q == "是的":
+            return "<state>3002</state>好的，驾驶员您好。请问您的姓名是什么？"
+        return "<state>3002</state>请问您的身份证号码后四位是否正确？"
+
+    def extraction(system):
+        if "【用户输入】李四" in system:
+            return json.dumps({"xm2": "李四"}, ensure_ascii=False)
+        return "{}"
+
+    llm = make_llm(dialogue, extraction)
+    graph = build_graph()
+
+    await invoke(
+        graph, "t-dual2", "是的", llm=llm,
+        stage_code="3002", person_index=2,
+        person_fields={"xm1": "张三", "sjhm1": "13800001111"},
+        client_mode="direct",
+    )
+    result = await invoke(graph, "t-dual2", "李四", llm=llm)
+
+    assert result["person_fields"]["xm2"] == "李四"
+    assert result["person_fields"]["xm1"] == "张三"
+
+
+@pytest.mark.asyncio
+async def test_dual_completion_goes_to_0000():
+    llm = make_llm(
+        lambda q: "<state>0000</state>好的，两位驾驶员的信息均已核实完毕。感谢配合。",
+        lambda system: "{}",
+    )
+    graph = build_graph()
+    result = await invoke(
+        graph, "t-dual-done", "没错", llm=llm,
+        stage_code="3002", person_index=2,
+        person_fields={"xm1": "张三", "xm2": "李四"},
+        client_mode="direct",
+    )
+
+    assert result["stage_code"] == "0000"