Merge refactor/config-deerflow-context into release/2.0-rc

Cherry-pick PR #2271's config refactor onto release/2.0-rc.
Used 'git merge -X theirs' to auto-resolve content conflicts in favor of
the PR's design (frozen AppConfig + explicit-parameter passing).

Limitations:
- Release-only changes that overlapped with PR's refactor in 119 files
  are NOT preserved — those files reflect PR's version. Follow-up commits
  on this branch will need to re-apply release-only modifications where
  meaningful.
- See PR #2271 for design rationale.

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

@@ -4,11 +4,10 @@ from typing import NotRequired, override
 
 from langchain.agents import AgentState
 from langchain.agents.middleware import AgentMiddleware
-from langchain_core.messages import HumanMessage
-from langgraph.config import get_config
 from langgraph.runtime import Runtime
 
 from deerflow.agents.thread_state import ThreadDataState
+from deerflow.config.deer_flow_context import DeerFlowContext
 from deerflow.config.paths import Paths, get_paths
 from deerflow.runtime.user_context import get_effective_user_id
 
@@ -79,14 +78,10 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
         return self._get_thread_paths(thread_id, user_id=user_id)
 
     @override
-    def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime) -> dict | None:
-        context = runtime.context or {}
-        thread_id = context.get("thread_id")
-        if thread_id is None:
-            config = get_config()
-            thread_id = config.get("configurable", {}).get("thread_id")
+    def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
+        thread_id = runtime.context.thread_id
 
-        if thread_id is None:
+        if not thread_id:
             raise ValueError("Thread ID is required in runtime context or config.configurable")
 
         user_id = get_effective_user_id()