refactor(agents): move llm_config + prompt_caching to app/agents/shared (slice 4b)

Relocate the mutually-dependent LLM config layer and the LiteLLM prompt-caching
helper to the shared kernel as one unit, rewiring their internal cross-reference
to the shared paths. Flip 21 non-frozen importers. Re-export shims remain at
new_chat/{llm_config,prompt_caching}.py for the frozen single-agent stack
(chat_deepagent); they will be removed when that stack is retired.

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.new_chat.llm_config import SanitizedChatLiteLLM
+        from app.agents.shared.llm_config import SanitizedChatLiteLLM
 
         llm = SanitizedChatLiteLLM(**litellm_kwargs)
 
@@ -379,7 +379,7 @@ async def get_search_space_llm_instance(
             if disable_streaming:
                 litellm_kwargs["disable_streaming"] = True
 
-            from app.agents.new_chat.llm_config import SanitizedChatLiteLLM
+            from app.agents.shared.llm_config import SanitizedChatLiteLLM
 
             return SanitizedChatLiteLLM(**litellm_kwargs)
 
@@ -458,7 +458,7 @@ async def get_search_space_llm_instance(
         if disable_streaming:
             litellm_kwargs["disable_streaming"] = True
 
-        from app.agents.new_chat.llm_config import SanitizedChatLiteLLM
+        from app.agents.shared.llm_config import SanitizedChatLiteLLM
 
         return SanitizedChatLiteLLM(**litellm_kwargs)
 
@@ -580,7 +580,7 @@ async def get_vision_llm(
             if global_cfg.get("litellm_params"):
                 litellm_kwargs.update(global_cfg["litellm_params"])
 
-            from app.agents.new_chat.llm_config import SanitizedChatLiteLLM
+            from app.agents.shared.llm_config import SanitizedChatLiteLLM
 
             inner_llm = SanitizedChatLiteLLM(**litellm_kwargs)
 
@@ -634,7 +634,7 @@ async def get_vision_llm(
         if vision_cfg.litellm_params:
             litellm_kwargs.update(vision_cfg.litellm_params)
 
-        from app.agents.new_chat.llm_config import SanitizedChatLiteLLM
+        from app.agents.shared.llm_config import SanitizedChatLiteLLM
 
         return SanitizedChatLiteLLM(**litellm_kwargs)
 
@@ -679,7 +679,7 @@ 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.new_chat.llm_config import create_chat_litellm_from_config
+    from app.agents.shared.llm_config import create_chat_litellm_from_config
 
     planner_cfg = next(
         (cfg for cfg in config.GLOBAL_LLM_CONFIGS if cfg.get("is_planner") is True),

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.new_chat.llm_config`` re-exports
+# class-body init time. ``app.agents.shared.llm_config`` re-exports
 # this constant under the historical ``PROVIDER_MAP`` name; placing the
 # map there directly would re-introduce the
 # ``app.config -> ... -> app.agents.new_chat.tools.generate_image ->