refactor(config): eliminate global mutable state, wire DeerFlowContext into runtime

- Freeze all config models (AppConfig + 15 sub-configs) with frozen=True
- Purify from_file() — remove 9 load_*_from_dict() side-effect calls
- Replace mtime/reload/push/pop machinery with single ContextVar + init_app_config()
- Delete 10 sub-module globals and their getters/setters/loaders
- Migrate 50+ consumers from get_*_config() to get_app_config().xxx

- Expand DeerFlowContext: app_config + thread_id + agent_name (frozen dataclass)
- Wire into Gateway runtime (worker.py) and DeerFlowClient via context= parameter
- Remove sandbox_id from runtime.context — flows through ThreadState.sandbox only
- Middleware/tools access runtime.context directly via Runtime[DeerFlowContext] generic
- resolve_context() retained at server entry points for LangGraph Server fallback

backend/packages/harness/deerflow/agents/middlewares/loop_detection_middleware.py

@@ -24,6 +24,8 @@ from langchain.agents.middleware import AgentMiddleware
 from langchain_core.messages import HumanMessage
 from langgraph.runtime import Runtime
 
+from deerflow.config.deer_flow_context import DeerFlowContext
+
 logger = logging.getLogger(__name__)
 
 # Defaults — can be overridden via constructor
@@ -180,12 +182,9 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         self._tool_freq: dict[str, dict[str, int]] = defaultdict(lambda: defaultdict(int))
         self._tool_freq_warned: dict[str, set[str]] = defaultdict(set)
 
-    def _get_thread_id(self, runtime: Runtime) -> str:
+    def _get_thread_id(self, runtime: Runtime[DeerFlowContext]) -> str:
         """Extract thread_id from runtime context for per-thread tracking."""
-        thread_id = runtime.context.get("thread_id") if runtime.context else None
-        if thread_id:
-            return thread_id
-        return "default"
+        return runtime.context.thread_id or "default"
 
     def _evict_if_needed(self) -> None:
         """Evict least recently used threads if over the limit.
@@ -350,11 +349,11 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
         return None
 
     @override
-    def after_model(self, state: AgentState, runtime: Runtime) -> dict | None:
+    def after_model(self, state: AgentState, runtime: Runtime[DeerFlowContext]) -> dict | None:
         return self._apply(state, runtime)
 
     @override
-    async def aafter_model(self, state: AgentState, runtime: Runtime) -> dict | None:
+    async def aafter_model(self, state: AgentState, runtime: Runtime[DeerFlowContext]) -> dict | None:
         return self._apply(state, runtime)
 
     def reset(self, thread_id: str | None = None) -> None: