refactor(agents): consolidate chat runtime infra under chat/runtime

Move the lower-level runtime/infra modules out of multi_agent_chat/shared/
(they were never used by subagents, so they failed the shared-by-all-siblings
rule) and unify them with the already-relocated checkpointer:

  agents/runtime/                      -> agents/chat/runtime/
  mac/shared/errors.py                 -> chat/runtime/errors.py
  mac/shared/llm_config.py             -> chat/runtime/llm_config.py
  mac/shared/prompt_caching.py         -> chat/runtime/prompt_caching.py
  mac/shared/mention_resolver.py       -> chat/runtime/mention_resolver.py
  mac/shared/path_resolver.py          -> chat/runtime/path_resolver.py

These sit below the agent packages: the boundary + agent factory + shared
middleware depend on them, and they import no agent code (acyclic).

surfsense_backend/app/services/llm_service.py

@@ -204,7 +204,7 @@ async def validate_llm_config(
         if litellm_params:
             litellm_kwargs.update(litellm_params)
 
-        from app.agents.chat.multi_agent_chat.shared.llm_config import (
+        from app.agents.chat.runtime.llm_config import (
             SanitizedChatLiteLLM,
         )
 
@@ -381,7 +381,7 @@ async def get_search_space_llm_instance(
             if disable_streaming:
                 litellm_kwargs["disable_streaming"] = True
 
-            from app.agents.chat.multi_agent_chat.shared.llm_config import (
+            from app.agents.chat.runtime.llm_config import (
                 SanitizedChatLiteLLM,
             )
 
@@ -462,7 +462,7 @@ async def get_search_space_llm_instance(
         if disable_streaming:
             litellm_kwargs["disable_streaming"] = True
 
-        from app.agents.chat.multi_agent_chat.shared.llm_config import (
+        from app.agents.chat.runtime.llm_config import (
             SanitizedChatLiteLLM,
         )
 
@@ -586,7 +586,7 @@ async def get_vision_llm(
             if global_cfg.get("litellm_params"):
                 litellm_kwargs.update(global_cfg["litellm_params"])
 
-            from app.agents.chat.multi_agent_chat.shared.llm_config import (
+            from app.agents.chat.runtime.llm_config import (
                 SanitizedChatLiteLLM,
             )
 
@@ -642,7 +642,7 @@ async def get_vision_llm(
         if vision_cfg.litellm_params:
             litellm_kwargs.update(vision_cfg.litellm_params)
 
-        from app.agents.chat.multi_agent_chat.shared.llm_config import (
+        from app.agents.chat.runtime.llm_config import (
             SanitizedChatLiteLLM,
         )
 
@@ -689,7 +689,7 @@ def get_planner_llm() -> ChatLiteLLM | None:
     Callers MUST fall back to their chat LLM when this returns ``None`` so
     deployments without a planner config keep working unchanged.
     """
-    from app.agents.chat.multi_agent_chat.shared.llm_config import (
+    from app.agents.chat.runtime.llm_config import (
         create_chat_litellm_from_config,
     )
 

surfsense_backend/app/services/provider_capabilities.py

@@ -53,7 +53,7 @@ logger = logging.getLogger(__name__)
 #
 # Owned here because ``app.services.provider_capabilities`` is the
 # only edge that's safe to call from ``app.config``'s YAML loader at
-# class-body init time. ``app.agents.chat.multi_agent_chat.shared.llm_config`` re-exports
+# class-body init time. ``app.agents.chat.runtime.llm_config`` re-exports
 # this constant under the historical ``PROVIDER_MAP`` name; placing the
 # map there directly would re-introduce the
 # ``app.config -> ... -> deliverables/tools/generate_image ->

surfsense_backend/app/services/revert_service.py

@@ -38,7 +38,7 @@ from typing import Any, Literal
 from sqlalchemy import delete, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.agents.chat.multi_agent_chat.shared.path_resolver import (
+from app.agents.chat.runtime.path_resolver import (
     DOCUMENTS_ROOT,
     safe_filename,
     safe_folder_segment,