Use decoupled way for backend client

app/config.py

@@ -468,9 +468,21 @@ class Settings(BaseSettings):
     ws_require_auth: bool = Field(default=False, description="Require auth in hello message even when ws_api_key is not set")
 
     # Backend bridge configuration (for call/transcript persistence)
+    backend_mode: str = Field(
+        default="auto",
+        description="Backend integration mode: auto | http | disabled"
+    )
     backend_url: Optional[str] = Field(default=None, description="Backend API base URL (e.g. http://localhost:8787)")
     backend_timeout_sec: int = Field(default=10, description="Backend API request timeout in seconds")
+    history_enabled: bool = Field(default=True, description="Enable history write bridge")
     history_default_user_id: int = Field(default=1, description="Fallback user_id for history records")
+    history_queue_max_size: int = Field(default=256, description="Max buffered transcript writes per session")
+    history_retry_max_attempts: int = Field(default=2, description="Retry attempts for each transcript write")
+    history_retry_backoff_sec: float = Field(default=0.2, description="Base retry backoff for transcript writes")
+    history_finalize_drain_timeout_sec: float = Field(
+        default=1.5,
+        description="Max wait before finalizing history when queue is still draining"
+    )
 
     # Agent YAML metadata
     agent_config_path: Optional[str] = Field(default=None, description="Resolved agent YAML path")