feat: add deterministic message interaction stages

backend/services/workflow/agent.py

@@ -2,8 +2,6 @@
 
 from __future__ import annotations
 
-from copy import deepcopy
-
 from models import AssistantConfig
 from pipecat.flows import ContextStrategy, ContextStrategyConfig, NodeConfig
 from pipecat.frames.frames import LLMUpdateSettingsFrame
@@ -108,7 +106,6 @@ class WorkflowAgentStage:
         node_id: str,
         *,
         functions: list,
-        greeting_context_message: dict[str, str] | None,
         leading_messages: list[dict[str, str]] | None = None,
     ) -> NodeConfig:
         data = self._engine.data(node_id)
@@ -119,11 +116,6 @@ class WorkflowAgentStage:
             if data.get("contextPolicy") == "fresh"
             else ContextStrategy.APPEND
         )
-        greeting_messages = (
-            [deepcopy(greeting_context_message)]
-            if strategy == ContextStrategy.RESET and greeting_context_message
-            else []
-        )
         fixed_reply_messages = (
             [{"role": "assistant", "content": entry_speech}]
             if entry_mode == "fixed_speech" and entry_speech
@@ -133,7 +125,6 @@ class WorkflowAgentStage:
             "name": node_id,
             "role_message": self.role_message(node_id),
             "task_messages": [
-                *greeting_messages,
                 *(leading_messages or []),
                 *fixed_reply_messages,
             ],