feat(services): assignment 6 skeleton - app service, field registry, in-memory repository

- fields_registry: 24 business keys in acd/human1/human2 groups with
  value_type, writable and SensitiveLevel metadata; strict bool/int
  parsing (no bool('0') trap); INTERNAL_FIELD_KEYS protection list
- repository: SessionRepository protocol + InMemorySessionRepository
  (idempotent delete; PostgreSQL swap-in is assignment 7)
- AccidentAppService: chat/set_info/get_info/delete_session share one
  business state - chat injects latest repository fields into the graph
  and writes back validated field diffs; set/get/delete make zero LLM
  calls and zero helper conversations (includeInputInfo accepted but
  unused); unknown get keys keep the '' JSON-empty-string contract,
  unknown set keys are rejected by whitelist
- ChatInput.injected_fields neutral contract extension; LangGraphBackend
  merges injected fields into graph input (set_info visible next chat)
- endpoints: thin layer - langgraph mode routes business state through
  the app service (fastgpt mode keeps the legacy path); delete cleans
  repository + graph checkpoint, idempotent
- tests: registry completeness (sfzmwh/sjwh/csbw included), app service
  combos with LLM-call spy, HTTP acceptance flow (set -> get -> chat ->
  groups -> delete -> no leak, idempotent re-delete)
- docs/assignment6-compat.md: behavior diff list vs FastGPT status quo
  and the audit backlog (arbitrary set_info key usage, stream formUpdate
  write-back, sensitive-field display boundary)

Verified: 200 unit tests (172 existing + 28 new)

src/core/fastgpt_client.py

@@ -6,12 +6,15 @@ from ..agent.graph import build_graph
 from ..backends.chat import ChatBackend
 from ..backends.fastgpt import FastGPTBackend
 from ..backends.langgraph import LangGraphBackend
+from ..services.app_service import AccidentAppService
+from ..services.repository import InMemorySessionRepository
 from .config import Config
 
 
 _fastgpt_client: AsyncChatClient | None = None
 _chat_backend: ChatBackend | None = None
 _langgraph_graph = None
+_app_service: AccidentAppService | None = None
 
 
 @asynccontextmanager
@@ -25,9 +28,13 @@ async def lifespan(app: FastAPI):
         # TODO(作业 2): 若语音仍启用，需在此单独初始化并校验 FastGPT 配置。
         from ..agent.llm import build_llm_service
 
-        global _langgraph_graph
+        global _langgraph_graph, _app_service
         _langgraph_graph = build_graph()
         _chat_backend = LangGraphBackend(_langgraph_graph, llm=build_llm_service())
+        # 作业 6：应用服务 + 内存 repository（作业 7 换 PostgreSQL）。
+        _app_service = AccidentAppService(
+            _chat_backend, InMemorySessionRepository()
+        )
     else:
         _fastgpt_client = AsyncChatClient(
             api_key=Config.FASTGPT_API_KEY,
@@ -45,6 +52,7 @@ async def lifespan(app: FastAPI):
     finally:
         _chat_backend = None
         _langgraph_graph = None
+        _app_service = None
         if _fastgpt_client:
             await _fastgpt_client.__aexit__(None, None, None)
         _fastgpt_client = None
@@ -68,6 +76,13 @@ def get_fastgpt_client() -> AsyncChatClient:
     return _fastgpt_client
 
 
+def get_app_service() -> AccidentAppService:
+    """Get the initialized application service（langgraph 模式）。"""
+    if _app_service is None:
+        raise RuntimeError("Application service not initialized")
+    return _app_service
+
+
 def get_chat_backend() -> ChatBackend:
     """Get the backend-neutral chat service."""
     if _chat_backend is None: