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/community/tavily/tools.py

@@ -3,11 +3,11 @@ import json
 from langchain.tools import tool
 from tavily import TavilyClient
 
-from deerflow.config import get_app_config
+from deerflow.config.app_config import AppConfig
 
 
 def _get_tavily_client() -> TavilyClient:
-    config = get_app_config().get_tool_config("web_search")
+    config = AppConfig.current().get_tool_config("web_search")
     api_key = None
     if config is not None and "api_key" in config.model_extra:
         api_key = config.model_extra.get("api_key")
@@ -21,7 +21,7 @@ def web_search_tool(query: str) -> str:
     Args:
         query: The query to search for.
     """
-    config = get_app_config().get_tool_config("web_search")
+    config = AppConfig.current().get_tool_config("web_search")
     max_results = 5
     if config is not None and "max_results" in config.model_extra:
         max_results = config.model_extra.get("max_results")