Enhance workflow routing and agent configuration management

- Introduce WorkflowLLMRouter for pre-response LLM routing, allowing agents to determine the appropriate function to call based on user input.
- Implement UserTurnRoutingProcessor to manage user turns before reaching the LLM, ensuring proper routing and handling of user messages.
- Refactor WorkflowBrain to integrate new routing logic and enhance agent stage configuration, including entry modes and resource management.
- Update service factory to support dynamic LLM resource configuration based on workflow settings.
- Add tests for new routing functionality and ensure proper handling of user messages in various scenarios.

backend/services/brains/base.py

@@ -55,7 +55,9 @@ class BrainRuntime:
     worker: Any = None
     context_aggregator: Any = None
     transport: Any = None
-    switch_services: Callable[[str | None, str | None], Awaitable[None]] | None = None
+    switch_services: (
+        Callable[[str | None, str | None, str | None], Awaitable[None]] | None
+    ) = None
     set_knowledge_scope: Callable[[dict[str, Any]], None] | None = None
     set_input_enabled: Callable[[bool], None] | None = None
     flow_global_functions: list[Any] = field(default_factory=list)
@@ -84,6 +86,15 @@ class BaseBrain:
     def record_user_message(self, content: str) -> None:
         """Observe a committed user message for brain-owned routing state."""
 
+    async def on_user_turn_end(self, content: str) -> bool:
+        """Handle a complete user turn before the conversational LLM runs.
+
+        Return True when the brain scheduled the next action itself and the
+        in-flight context frame must not reach the previous Agent's LLM.
+        """
+        self.record_user_message(content)
+        return False
+
     async def on_assistant_text_start(self, turn_id: str) -> None:
         """Observe the start of a generated assistant turn."""
 
@@ -114,6 +125,8 @@ class Brain(Protocol):
 
     def record_user_message(self, content: str) -> None: ...
 
+    async def on_user_turn_end(self, content: str) -> bool: ...
+
     async def on_assistant_text_start(self, turn_id: str) -> None: ...
 
     async def on_assistant_text_end(