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/tasks/chat/stream_new_chat.py

@@ -32,7 +32,7 @@ from app.agents.new_chat.checkpointer import get_checkpointer
 from app.agents.shared.context import SurfSenseContextSchema
 from app.agents.shared.errors import BusyError
 from app.agents.shared.filesystem_selection import FilesystemMode, FilesystemSelection
-from app.agents.new_chat.llm_config import (
+from app.agents.shared.llm_config import (
     AgentConfig,
     create_chat_litellm_from_agent_config,
     create_chat_litellm_from_config,

surfsense_backend/app/tasks/chat/streaming/agent/builder.py

@@ -10,7 +10,7 @@ from __future__ import annotations
 from typing import Any
 
 from app.agents.shared.filesystem_selection import FilesystemSelection
-from app.agents.new_chat.llm_config import AgentConfig
+from app.agents.shared.llm_config import AgentConfig
 from app.db import ChatVisibility
 from app.services.connector_service import ConnectorService
 

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/llm_capability.py

@@ -15,7 +15,7 @@ tells the user what to change.
 
 from __future__ import annotations
 
-from app.agents.new_chat.llm_config import AgentConfig
+from app.agents.shared.llm_config import AgentConfig
 from app.observability import otel as ot
 
 

surfsense_backend/app/tasks/chat/streaming/flows/new_chat/title_gen.py

@@ -30,7 +30,7 @@ from app.prompts import TITLE_GENERATION_PROMPT
 from app.services.new_streaming_service import VercelStreamingService
 
 if TYPE_CHECKING:
-    from app.agents.new_chat.llm_config import AgentConfig
+    from app.agents.shared.llm_config import AgentConfig
     from app.services.token_tracking_service import TokenAccumulator
 
 

surfsense_backend/app/tasks/chat/streaming/flows/shared/llm_bundle.py

@@ -14,7 +14,7 @@ from typing import Any
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.agents.new_chat.llm_config import (
+from app.agents.shared.llm_config import (
     AgentConfig,
     create_chat_litellm_from_agent_config,
     create_chat_litellm_from_config,

surfsense_backend/app/tasks/chat/streaming/flows/shared/premium_quota.py

@@ -19,7 +19,7 @@ from dataclasses import dataclass
 from typing import TYPE_CHECKING
 from uuid import UUID
 
-from app.agents.new_chat.llm_config import AgentConfig
+from app.agents.shared.llm_config import AgentConfig
 from app.db import shielded_async_session
 
 if TYPE_CHECKING: