refactor(agents): move MAC middleware impls out of shared kernel

knowledge_search, memory_injection and scoped_model_fallback no longer
belong in the cross-agent kernel (app/agents/shared/middleware): they are
consumed only inside multi_agent_chat. Relocate each impl next to the
builder that uses it:

- knowledge_search.py -> multi_agent_chat/shared/middleware/ (genuinely
  shared: its _render_priority_message feeds kb_context_projection, used by
  both the main agent and the KB subagent)
- memory_injection.py -> multi_agent_chat/shared/middleware/ (beside its
  memory.py builder)
- scoped_model_fallback.py -> multi_agent_chat/shared/middleware/resilience/
  (beside fallback.py/bundle.py)

Impls moved verbatim (git rename). Builders/consumers now import the local
sibling; main_agent knowledge_priority imports the new shared path; shared
middleware barrel trimmed.

Tests: repoint imports; convert the knowledge_search monkeypatch targets
from brittle dotted-string form to object-based patching (monkeypatch.setattr
on the imported module), which is robust to import ordering. No behavior
change.

surfsense_backend/app/agents/multi_agent_chat/main_agent/middleware/knowledge_priority.py

@@ -4,8 +4,10 @@ from __future__ import annotations
 
 from langchain_core.language_models import BaseChatModel
 
+from app.agents.multi_agent_chat.shared.middleware.knowledge_search import (
+    KnowledgePriorityMiddleware,
+)
 from app.agents.shared.filesystem_selection import FilesystemMode
-from app.agents.shared.middleware import KnowledgePriorityMiddleware
 from app.services.llm_service import get_planner_llm
 
 

surfsense_backend/app/agents/multi_agent_chat/shared/middleware/kb_context_projection.py

@@ -12,9 +12,10 @@ from langgraph.runtime import Runtime
 from app.agents.multi_agent_chat.shared.state.filesystem_state import (
     SurfSenseFilesystemState,
 )
-from app.agents.shared.middleware.knowledge_search import _render_priority_message
 from app.utils.perf import get_perf_logger
 
+from .knowledge_search import _render_priority_message
+
 _perf_log = get_perf_logger()
 
 

surfsense_backend/app/agents/multi_agent_chat/shared/middleware/memory.py

@@ -2,9 +2,10 @@
 
 from __future__ import annotations
 
-from app.agents.shared.middleware import MemoryInjectionMiddleware
 from app.db import ChatVisibility
 
+from .memory_injection import MemoryInjectionMiddleware
+
 
 def build_memory_mw(
     *,

surfsense_backend/app/agents/multi_agent_chat/shared/middleware/resilience/bundle.py

@@ -12,13 +12,13 @@ from langchain.agents.middleware import (
 
 from app.agents.shared.feature_flags import AgentFeatureFlags
 from app.agents.shared.middleware import RetryAfterMiddleware
-from app.agents.shared.middleware.scoped_model_fallback import (
-    ScopedModelFallbackMiddleware,
-)
 
 from .fallback import build_fallback_mw
 from .model_call_limit import build_model_call_limit_mw
 from .retry import build_retry_mw
+from .scoped_model_fallback import (
+    ScopedModelFallbackMiddleware,
+)
 from .tool_call_limit import build_tool_call_limit_mw
 
 

surfsense_backend/app/agents/multi_agent_chat/shared/middleware/resilience/fallback.py

@@ -5,11 +5,11 @@ from __future__ import annotations
 import logging
 
 from app.agents.shared.feature_flags import AgentFeatureFlags
-from app.agents.shared.middleware.scoped_model_fallback import (
-    ScopedModelFallbackMiddleware,
-)
 
 from ..flags import enabled
+from .scoped_model_fallback import (
+    ScopedModelFallbackMiddleware,
+)
 
 
 def build_fallback_mw(

surfsense_backend/app/agents/shared/middleware/__init__.py

@@ -9,20 +9,12 @@ from app.agents.shared.middleware.kb_persistence import (
     KnowledgeBasePersistenceMiddleware,
     commit_staged_filesystem_state,
 )
-from app.agents.shared.middleware.knowledge_search import (
-    KnowledgePriorityMiddleware,
-)
-from app.agents.shared.middleware.memory_injection import (
-    MemoryInjectionMiddleware,
-)
 from app.agents.shared.middleware.permission import PermissionMiddleware
 from app.agents.shared.middleware.retry_after import RetryAfterMiddleware
 
 __all__ = [
     "BusyMutexMiddleware",
     "KnowledgeBasePersistenceMiddleware",
-    "KnowledgePriorityMiddleware",
-    "MemoryInjectionMiddleware",
     "PermissionMiddleware",
     "RetryAfterMiddleware",
     "SurfSenseCompactionMiddleware",

surfsense_backend/tests/integration/retriever/test_knowledge_search_date_filters.py

@@ -8,7 +8,10 @@ from datetime import UTC, datetime, timedelta
 import numpy as np
 import pytest
 
-from app.agents.shared.middleware.knowledge_search import search_knowledge_base
+from app.agents.multi_agent_chat.shared.middleware import knowledge_search as ks
+from app.agents.multi_agent_chat.shared.middleware.knowledge_search import (
+    search_knowledge_base,
+)
 
 from .conftest import DUMMY_EMBEDDING
 
@@ -26,13 +29,9 @@ async def test_search_knowledge_base_applies_date_filters(
     async def fake_shielded_async_session():
         yield db_session
 
+    monkeypatch.setattr(ks, "shielded_async_session", fake_shielded_async_session)
     monkeypatch.setattr(
-        "app.agents.shared.middleware.knowledge_search.shielded_async_session",
-        fake_shielded_async_session,
-    )
-    monkeypatch.setattr(
-        "app.agents.shared.middleware.knowledge_search.embed_texts",
-        lambda texts: [np.array(DUMMY_EMBEDDING) for _ in texts],
+        ks, "embed_texts", lambda texts: [np.array(DUMMY_EMBEDDING) for _ in texts]
     )
 
     space_id = seed_date_filtered_docs["search_space"].id

surfsense_backend/tests/unit/agents/new_chat/middleware/test_scoped_model_fallback.py

@@ -87,7 +87,7 @@ class RateLimitError(Exception):
 def _build_agent(primary: BaseChatModel, fallback: BaseChatModel):
     from langchain.agents import create_agent
 
-    from app.agents.shared.middleware.scoped_model_fallback import (
+    from app.agents.multi_agent_chat.shared.middleware.resilience.scoped_model_fallback import (
         ScopedModelFallbackMiddleware,
     )
 

surfsense_backend/tests/unit/middleware/test_knowledge_search.py

@@ -5,10 +5,11 @@ import json
 import pytest
 from langchain_core.messages import AIMessage, HumanMessage
 
+from app.agents.multi_agent_chat.shared.middleware import knowledge_search as ks
 from app.agents.multi_agent_chat.shared.middleware.filesystem.backends.document_xml import (
     build_document_xml as _build_document_xml,
 )
-from app.agents.shared.middleware.knowledge_search import (
+from app.agents.multi_agent_chat.shared.middleware.knowledge_search import (
     KBSearchPlan,
     KnowledgePriorityMiddleware,
     _normalize_optional_date_range,
@@ -260,7 +261,7 @@ class TestKnowledgePriorityMiddlewarePlanner:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -303,7 +304,7 @@ class TestKnowledgePriorityMiddlewarePlanner:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -332,7 +333,7 @@ class TestKnowledgePriorityMiddlewarePlanner:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -377,11 +378,11 @@ class TestKnowledgePriorityMiddlewarePlanner:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.browse_recent_documents",
+            ks, "browse_recent_documents",
             fake_browse_recent_documents,
         )
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -424,11 +425,11 @@ class TestKnowledgePriorityMiddlewarePlanner:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.browse_recent_documents",
+            ks, "browse_recent_documents",
             fake_browse_recent_documents,
         )
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -551,11 +552,11 @@ class TestKnowledgePriorityMentionDrain:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.fetch_mentioned_documents",
+            ks, "fetch_mentioned_documents",
             fake_fetch_mentioned_documents,
         )
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -599,11 +600,11 @@ class TestKnowledgePriorityMentionDrain:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.fetch_mentioned_documents",
+            ks, "fetch_mentioned_documents",
             fake_fetch_mentioned_documents,
         )
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )
 
@@ -644,11 +645,11 @@ class TestKnowledgePriorityMentionDrain:
             return []
 
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.fetch_mentioned_documents",
+            ks, "fetch_mentioned_documents",
             fake_fetch_mentioned_documents,
         )
         monkeypatch.setattr(
-            "app.agents.shared.middleware.knowledge_search.search_knowledge_base",
+            ks, "search_knowledge_base",
             fake_search_knowledge_base,
         )