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/app/gateway/routers/memory.py

@@ -12,7 +12,7 @@ from deerflow.agents.memory.updater import (
     reload_memory_data,
     update_memory_fact,
 )
-from deerflow.config.memory_config import get_memory_config
+from deerflow.config.app_config import AppConfig
 
 router = APIRouter(prefix="/api", tags=["memory"])
 
@@ -311,7 +311,7 @@ async def get_memory_config_endpoint() -> MemoryConfigResponse:
         }
         ```
     """
-    config = get_memory_config()
+    config = AppConfig.current().memory
     return MemoryConfigResponse(
         enabled=config.enabled,
         storage_path=config.storage_path,
@@ -336,7 +336,7 @@ async def get_memory_status() -> MemoryStatusResponse:
     Returns:
         Combined memory configuration and current data.
     """
-    config = get_memory_config()
+    config = AppConfig.current().memory
     memory_data = get_memory_data()
 
     return MemoryStatusResponse(