feat: moved LLMConfigs from User to SearchSpaces

- RBAC soon??
- Updated various services and routes to handle search space-specific LLM preferences.
- Modified frontend components to pass search space ID for LLM configuration management.
- Removed onboarding page and settings page as part of the refactor.

surfsense_backend/app/tasks/connector_indexers/airtable_indexer.py

@@ -260,7 +260,9 @@ async def index_airtable_records(
                                 continue
 
                             # Generate document summary
-                            user_llm = await get_user_long_context_llm(session, user_id)
+                            user_llm = await get_user_long_context_llm(
+                                session, user_id, search_space_id
+                            )
 
                             if user_llm:
                                 document_metadata = {

surfsense_backend/app/tasks/connector_indexers/clickup_indexer.py

@@ -222,7 +222,9 @@ async def index_clickup_tasks(
                         continue
 
                     # Generate summary with metadata
-                    user_llm = await get_user_long_context_llm(session, user_id)
+                    user_llm = await get_user_long_context_llm(
+                        session, user_id, search_space_id
+                    )
 
                     if user_llm:
                         document_metadata = {

surfsense_backend/app/tasks/connector_indexers/confluence_indexer.py

@@ -233,7 +233,9 @@ async def index_confluence_pages(
                     continue
 
                 # Generate summary with metadata
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
                 comment_count = len(comments)
 
                 if user_llm:

surfsense_backend/app/tasks/connector_indexers/discord_indexer.py

@@ -325,7 +325,9 @@ async def index_discord_messages(
                             continue
 
                         # Get user's long context LLM
-                        user_llm = await get_user_long_context_llm(session, user_id)
+                        user_llm = await get_user_long_context_llm(
+                            session, user_id, search_space_id
+                        )
                         if not user_llm:
                             logger.error(
                                 f"No long context LLM configured for user {user_id}"

surfsense_backend/app/tasks/connector_indexers/github_indexer.py

@@ -213,7 +213,9 @@ async def index_github_repos(
                         continue
 
                     # Generate summary with metadata
-                    user_llm = await get_user_long_context_llm(session, user_id)
+                    user_llm = await get_user_long_context_llm(
+                        session, user_id, search_space_id
+                    )
                     if user_llm:
                         # Extract file extension from file path
                         file_extension = (

surfsense_backend/app/tasks/connector_indexers/google_calendar_indexer.py

@@ -266,7 +266,9 @@ async def index_google_calendar_events(
                     continue
 
                 # Generate summary with metadata
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
 
                 if user_llm:
                     document_metadata = {

surfsense_backend/app/tasks/connector_indexers/google_gmail_indexer.py

@@ -210,7 +210,9 @@ async def index_google_gmail_messages(
                     continue
 
                 # Generate summary with metadata
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
 
                 if user_llm:
                     document_metadata = {

surfsense_backend/app/tasks/connector_indexers/jira_indexer.py

@@ -216,7 +216,9 @@ async def index_jira_issues(
                     continue
 
                 # Generate summary with metadata
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
                 comment_count = len(formatted_issue.get("comments", []))
 
                 if user_llm:

surfsense_backend/app/tasks/connector_indexers/linear_indexer.py

@@ -228,7 +228,9 @@ async def index_linear_issues(
                     continue
 
                 # Generate summary with metadata
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
                 state = formatted_issue.get("state", "Unknown")
                 description = formatted_issue.get("description", "")
                 comment_count = len(formatted_issue.get("comments", []))

surfsense_backend/app/tasks/connector_indexers/luma_indexer.py

@@ -270,7 +270,9 @@ async def index_luma_events(
                     continue
 
                 # Generate summary with metadata
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
 
                 if user_llm:
                     document_metadata = {

surfsense_backend/app/tasks/connector_indexers/notion_indexer.py

@@ -299,7 +299,9 @@ async def index_notion_pages(
                     continue
 
                 # Get user's long context LLM
-                user_llm = await get_user_long_context_llm(session, user_id)
+                user_llm = await get_user_long_context_llm(
+                    session, user_id, search_space_id
+                )
                 if not user_llm:
                     logger.error(f"No long context LLM configured for user {user_id}")
                     skipped_pages.append(f"{page_title} (no LLM configured)")

surfsense_backend/app/tasks/document_processors/extension_processor.py

@@ -104,9 +104,11 @@ async def add_extension_received_document(
             return existing_document
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary with metadata
         document_metadata = {

surfsense_backend/app/tasks/document_processors/file_processors.py

@@ -60,9 +60,11 @@ async def add_received_file_document_using_unstructured(
         # TODO: Check if file_markdown exceeds token limit of embedding model
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary with metadata
         document_metadata = {
@@ -140,9 +142,11 @@ async def add_received_file_document_using_llamacloud(
             return existing_document
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary with metadata
         document_metadata = {
@@ -221,9 +225,11 @@ async def add_received_file_document_using_docling(
             return existing_document
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary using chunked processing for large documents
         from app.services.docling_service import create_docling_service

surfsense_backend/app/tasks/document_processors/markdown_processor.py

@@ -75,9 +75,11 @@ async def add_received_markdown_file_document(
             return existing_document
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary with metadata
         document_metadata = {

surfsense_backend/app/tasks/document_processors/url_crawler.py

@@ -161,9 +161,11 @@ async def add_crawled_url_document(
         )
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary
         await task_logger.log_task_progress(

surfsense_backend/app/tasks/document_processors/youtube_processor.py

@@ -234,9 +234,11 @@ async def add_youtube_video_document(
         )
 
         # Get user's long context LLM
-        user_llm = await get_user_long_context_llm(session, user_id)
+        user_llm = await get_user_long_context_llm(session, user_id, search_space_id)
         if not user_llm:
-            raise RuntimeError(f"No long context LLM configured for user {user_id}")
+            raise RuntimeError(
+                f"No long context LLM configured for user {user_id} in search space {search_space_id}"
+            )
 
         # Generate summary
         await task_logger.log_task_progress(

surfsense_backend/app/tasks/podcast_tasks.py

@@ -98,6 +98,7 @@ async def generate_chat_podcast(
             "configurable": {
                 "podcast_title": "SurfSense",
                 "user_id": str(user_id),
+                "search_space_id": search_space_id,
             }
         }
         # Initialize state with database session and streaming service