diff --git a/surfsense_backend/app/tasks/chat/stream_new_chat.py b/surfsense_backend/app/tasks/chat/stream_new_chat.py
index 727f1f9ad..cec13204f 100644
--- a/surfsense_backend/app/tasks/chat/stream_new_chat.py
+++ b/surfsense_backend/app/tasks/chat/stream_new_chat.py
@@ -27,7 +27,6 @@ from langchain_core.messages import HumanMessage
 from sqlalchemy.future import select
 
 from app.agents.multi_agent_chat import create_multi_agent_chat_deep_agent
-from app.agents.new_chat.chat_deepagent import create_surfsense_deep_agent
 from app.agents.shared.checkpointer import get_checkpointer
 from app.agents.shared.context import SurfSenseContextSchema
 from app.agents.shared.errors import BusyError
@@ -1181,19 +1180,12 @@ async def stream_new_chat(
         )
 
         visibility = thread_visibility or ChatVisibility.PRIVATE
-        from app.config import config as _app_config
-
-        use_multi_agent = bool(_app_config.MULTI_AGENT_CHAT_ENABLED)
-        chat_agent_mode = "multi" if use_multi_agent else "single"
+        chat_agent_mode = "multi"
         with contextlib.suppress(Exception):
             chat_span.set_attribute("agent.mode", chat_agent_mode)
 
         _t0 = time.perf_counter()
-        agent_factory = (
-            create_multi_agent_chat_deep_agent
-            if use_multi_agent
-            else create_surfsense_deep_agent
-        )
+        agent_factory = create_multi_agent_chat_deep_agent
         # Build the agent inline. Provider 429s surface through the
         # in-stream recovery loop below (``_is_provider_rate_limited``),
         # which repins the thread to an eligible alternative config and
@@ -2512,17 +2504,11 @@ async def stream_resume_chat(
         )
 
         visibility = thread_visibility or ChatVisibility.PRIVATE
-        from app.config import config as _app_config
-
-        chat_agent_mode = "multi" if _app_config.MULTI_AGENT_CHAT_ENABLED else "single"
+        chat_agent_mode = "multi"
         with contextlib.suppress(Exception):
             chat_span.set_attribute("agent.mode", chat_agent_mode)
         _t0 = time.perf_counter()
-        agent_factory = (
-            create_multi_agent_chat_deep_agent
-            if _app_config.MULTI_AGENT_CHAT_ENABLED
-            else create_surfsense_deep_agent
-        )
+        agent_factory = create_multi_agent_chat_deep_agent
         # Build the agent inline. Provider 429s are handled by the
         # in-stream recovery loop, which repins to an eligible
         # alternative config and rebuilds the agent before the user sees
diff --git a/surfsense_backend/app/tasks/chat/streaming/flows/new_chat/orchestrator.py b/surfsense_backend/app/tasks/chat/streaming/flows/new_chat/orchestrator.py
index f71e18770..e6803f5a1 100644
--- a/surfsense_backend/app/tasks/chat/streaming/flows/new_chat/orchestrator.py
+++ b/surfsense_backend/app/tasks/chat/streaming/flows/new_chat/orchestrator.py
@@ -30,10 +30,8 @@ from typing import Any, Literal
 import anyio
 
 from app.agents.multi_agent_chat import create_multi_agent_chat_deep_agent
-from app.agents.new_chat.chat_deepagent import create_surfsense_deep_agent
 from app.agents.shared.filesystem_selection import FilesystemMode, FilesystemSelection
 from app.agents.shared.middleware.busy_mutex import end_turn
-from app.config import config as _app_config
 from app.db import ChatVisibility, async_session_maker
 from app.observability import otel as ot
 from app.services.new_streaming_service import VercelStreamingService
@@ -387,16 +385,11 @@ async def stream_new_chat(
         )
 
         visibility = thread_visibility or ChatVisibility.PRIVATE
-        use_multi_agent = bool(_app_config.MULTI_AGENT_CHAT_ENABLED)
-        chat_agent_mode = "multi" if use_multi_agent else "single"
+        chat_agent_mode = "multi"
         set_agent_mode(chat_span, chat_agent_mode)
 
         _t0 = time.perf_counter()
-        agent_factory = (
-            create_multi_agent_chat_deep_agent
-            if use_multi_agent
-            else create_surfsense_deep_agent
-        )
+        agent_factory = create_multi_agent_chat_deep_agent
         # Build the agent inline. Provider 429s surface through the in-stream
         # recovery loop below, which repins the thread to an eligible
         # alternative config and rebuilds the agent before the user sees any
diff --git a/surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/orchestrator.py b/surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/orchestrator.py
index 6ed6fa166..aba603ce6 100644
--- a/surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/orchestrator.py
+++ b/surfsense_backend/app/tasks/chat/streaming/flows/resume_chat/orchestrator.py
@@ -24,10 +24,8 @@ from uuid import UUID
 import anyio
 
 from app.agents.multi_agent_chat import create_multi_agent_chat_deep_agent
-from app.agents.new_chat.chat_deepagent import create_surfsense_deep_agent
 from app.agents.shared.filesystem_selection import FilesystemMode, FilesystemSelection
 from app.agents.shared.middleware.busy_mutex import end_turn
-from app.config import config as _app_config
 from app.db import ChatVisibility, async_session_maker
 from app.observability import otel as ot
 from app.services.chat_session_state_service import set_ai_responding
@@ -326,16 +324,11 @@ async def stream_resume_chat(
         )
 
         visibility = thread_visibility or ChatVisibility.PRIVATE
-        use_multi_agent = bool(_app_config.MULTI_AGENT_CHAT_ENABLED)
-        chat_agent_mode = "multi" if use_multi_agent else "single"
+        chat_agent_mode = "multi"
         set_agent_mode(chat_span, chat_agent_mode)
 
         _t0 = time.perf_counter()
-        agent_factory = (
-            create_multi_agent_chat_deep_agent
-            if use_multi_agent
-            else create_surfsense_deep_agent
-        )
+        agent_factory = create_multi_agent_chat_deep_agent
         agent = await build_main_agent_for_thread(
             agent_factory,
             llm=llm,