Merge remote-tracking branch 'upstream/dev' into feat/ui

README.md

@@ -29,8 +29,7 @@ SurfSense is a highly customizable AI research agent, connected to external sour
 
 # Video 
 
-https://github.com/user-attachments/assets/42a29ea1-d4d8-4213-9c69-972b5b806d58
+https://github.com/user-attachments/assets/cc0c84d3-1f2f-4f7a-b519-2ecce22310b1
-
 
 
 ## Podcast Sample
@@ -52,8 +51,10 @@ https://github.com/user-attachments/assets/a0a16566-6967-4374-ac51-9b3e07fbecd7
 - Interact in Natural Language and get cited answers.
 ### 📄 **Cited Answers**
 - Get Cited answers just like Perplexity.
+### 🧩 **Universal Compatibility**
+- Connect virtually any inference provider via the OpenAI spec and LiteLLM.
 ### 🔔 **Privacy & Local LLM Support**
-- Works Flawlessly with Ollama local LLMs.
+- Works Flawlessly with local LLMs like vLLM and Ollama.
 ### 🏠 **Self Hostable**
 - Open source and easy to deploy locally.
 ### 👥 **Team Collaboration with RBAC**
@@ -61,6 +62,7 @@ https://github.com/user-attachments/assets/a0a16566-6967-4374-ac51-9b3e07fbecd7
 - Invite team members with customizable roles (Owner, Admin, Editor, Viewer)
 - Granular permissions for documents, chats, connectors, and settings
 - Share knowledge bases securely within your organization
+- Team chats update in real-time and "Chat about the chat" in comment threads
 ### 🎙️ Podcasts 
 - Blazingly fast podcast generation agent. (Creates a 3-minute podcast in under 20 seconds.)
 - Convert your chat conversations into engaging audio content
@@ -237,6 +239,8 @@ Before self-hosting installation, make sure to complete the [prerequisite setup
 
  ### **BackEnd** 
 
+-  **LiteLLM**: Universal LLM integration supporting 100+ models (OpenAI, Anthropic, Ollama, etc.)
+
 -  **FastAPI**: Modern, fast web framework for building APIs with Python
   
 -  **PostgreSQL with pgvector**: Database with vector search capabilities for similarity searches
@@ -253,8 +257,6 @@ Before self-hosting installation, make sure to complete the [prerequisite setup
 
 -  **LangChain**: Framework for developing AI-powered applications.
 
--  **LiteLLM**: Universal LLM integration supporting 100+ models (OpenAI, Anthropic, Ollama, etc.)
-
 -  **Rerankers**: Advanced result ranking for improved search relevance
 
 -  **Hybrid Search**: Combines vector similarity and full-text search for optimal results using Reciprocal Rank Fusion (RRF)

surfsense_backend/app/agents/new_chat/chat_deepagent.py

@@ -7,6 +7,7 @@ via NewLLMConfig.
 """
 
 from collections.abc import Sequence
+from typing import Any
 
 from deepagents import create_deep_agent
 from langchain_core.tools import BaseTool
@@ -23,6 +24,90 @@ from app.agents.new_chat.system_prompt import (
 from app.agents.new_chat.tools.registry import build_tools_async
 from app.services.connector_service import ConnectorService
 
+# =============================================================================
+# Connector Type Mapping
+# =============================================================================
+
+# Maps SearchSourceConnectorType enum values to the searchable document/connector types
+# used by the knowledge_base tool. Some connectors map to different document types.
+_CONNECTOR_TYPE_TO_SEARCHABLE: dict[str, str] = {
+    # Direct mappings (connector type == searchable type)
+    "TAVILY_API": "TAVILY_API",
+    "SEARXNG_API": "SEARXNG_API",
+    "LINKUP_API": "LINKUP_API",
+    "BAIDU_SEARCH_API": "BAIDU_SEARCH_API",
+    "SLACK_CONNECTOR": "SLACK_CONNECTOR",
+    "TEAMS_CONNECTOR": "TEAMS_CONNECTOR",
+    "NOTION_CONNECTOR": "NOTION_CONNECTOR",
+    "GITHUB_CONNECTOR": "GITHUB_CONNECTOR",
+    "LINEAR_CONNECTOR": "LINEAR_CONNECTOR",
+    "DISCORD_CONNECTOR": "DISCORD_CONNECTOR",
+    "JIRA_CONNECTOR": "JIRA_CONNECTOR",
+    "CONFLUENCE_CONNECTOR": "CONFLUENCE_CONNECTOR",
+    "CLICKUP_CONNECTOR": "CLICKUP_CONNECTOR",
+    "GOOGLE_CALENDAR_CONNECTOR": "GOOGLE_CALENDAR_CONNECTOR",
+    "GOOGLE_GMAIL_CONNECTOR": "GOOGLE_GMAIL_CONNECTOR",
+    "GOOGLE_DRIVE_CONNECTOR": "GOOGLE_DRIVE_FILE",  # Connector type differs from document type
+    "AIRTABLE_CONNECTOR": "AIRTABLE_CONNECTOR",
+    "LUMA_CONNECTOR": "LUMA_CONNECTOR",
+    "ELASTICSEARCH_CONNECTOR": "ELASTICSEARCH_CONNECTOR",
+    "WEBCRAWLER_CONNECTOR": "CRAWLED_URL",  # Maps to document type
+    "BOOKSTACK_CONNECTOR": "BOOKSTACK_CONNECTOR",
+    "CIRCLEBACK_CONNECTOR": "CIRCLEBACK",  # Connector type differs from document type
+    "OBSIDIAN_CONNECTOR": "OBSIDIAN_CONNECTOR",
+    # Composio connectors
+    "COMPOSIO_GOOGLE_DRIVE_CONNECTOR": "COMPOSIO_GOOGLE_DRIVE_CONNECTOR",
+    "COMPOSIO_GMAIL_CONNECTOR": "COMPOSIO_GMAIL_CONNECTOR",
+    "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR": "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR",
+}
+
+# Document types that don't come from SearchSourceConnector but should always be searchable
+_ALWAYS_AVAILABLE_DOC_TYPES: list[str] = [
+    "EXTENSION",  # Browser extension data
+    "FILE",  # Uploaded files
+    "NOTE",  # User notes
+    "YOUTUBE_VIDEO",  # YouTube videos
+]
+
+
+def _map_connectors_to_searchable_types(
+    connector_types: list[Any],
+) -> list[str]:
+    """
+    Map SearchSourceConnectorType enums to searchable document/connector types.
+
+    This function:
+    1. Converts connector type enums to their searchable counterparts
+    2. Includes always-available document types (EXTENSION, FILE, NOTE, YOUTUBE_VIDEO)
+    3. Deduplicates while preserving order
+
+    Args:
+        connector_types: List of SearchSourceConnectorType enum values
+
+    Returns:
+        List of searchable connector/document type strings
+    """
+    result_set: set[str] = set()
+    result_list: list[str] = []
+
+    # Add always-available document types first
+    for doc_type in _ALWAYS_AVAILABLE_DOC_TYPES:
+        if doc_type not in result_set:
+            result_set.add(doc_type)
+            result_list.append(doc_type)
+
+    # Map each connector type to its searchable equivalent
+    for ct in connector_types:
+        # Handle both enum and string types
+        ct_str = ct.value if hasattr(ct, "value") else str(ct)
+        searchable = _CONNECTOR_TYPE_TO_SEARCHABLE.get(ct_str)
+        if searchable and searchable not in result_set:
+            result_set.add(searchable)
+            result_list.append(searchable)
+
+    return result_list
+
+
 # =============================================================================
 # Deep Agent Factory
 # =============================================================================
@@ -116,6 +201,30 @@ async def create_surfsense_deep_agent(
             additional_tools=[my_custom_tool]
         )
     """
+    # Discover available connectors and document types for this search space
+    # This enables dynamic tool docstrings that inform the LLM about what's actually available
+    available_connectors: list[str] | None = None
+    available_document_types: list[str] | None = None
+
+    try:
+        # Get enabled search source connectors for this search space
+        connector_types = await connector_service.get_available_connectors(
+            search_space_id
+        )
+        if connector_types:
+            # Convert enum values to strings and also include mapped document types
+            available_connectors = _map_connectors_to_searchable_types(connector_types)
+
+        # Get document types that have at least one document indexed
+        available_document_types = await connector_service.get_available_document_types(
+            search_space_id
+        )
+    except Exception as e:
+        # Log but don't fail - fall back to all connectors if discovery fails
+        import logging
+
+        logging.warning(f"Failed to discover available connectors/document types: {e}")
+
     # Build dependencies dict for the tools registry
     dependencies = {
         "search_space_id": search_space_id,
@@ -123,6 +232,9 @@ async def create_surfsense_deep_agent(
         "connector_service": connector_service,
         "firecrawl_api_key": firecrawl_api_key,
         "user_id": user_id,  # Required for memory tools
+        # Dynamic connector/document type discovery for knowledge base tool
+        "available_connectors": available_connectors,
+        "available_document_types": available_document_types,
     }
 
     # Build tools using the async registry (includes MCP tools)

surfsense_backend/app/agents/new_chat/tools/__init__.py

@@ -19,6 +19,7 @@ Available tools:
 # Tool factory exports (for direct use)
 from .display_image import create_display_image_tool
 from .knowledge_base import (
+    CONNECTOR_DESCRIPTIONS,
     create_search_knowledge_base_tool,
     format_documents_for_context,
     search_knowledge_base_async,
@@ -40,6 +41,8 @@ from .user_memory import create_recall_memory_tool, create_save_memory_tool
 __all__ = [
     # Registry
     "BUILTIN_TOOLS",
+    # Knowledge base utilities
+    "CONNECTOR_DESCRIPTIONS",
     "ToolDefinition",
     "build_tools",
     # Tool factories
@@ -51,7 +54,6 @@ __all__ = [
     "create_scrape_webpage_tool",
     "create_search_knowledge_base_tool",
     "create_search_surfsense_docs_tool",
-    # Knowledge base utilities
     "format_documents_for_context",
     "get_all_tool_names",
     "get_default_enabled_tools",

surfsense_backend/app/agents/new_chat/tools/knowledge_base.py

@@ -12,7 +12,8 @@ import json
 from datetime import datetime
 from typing import Any
 
-from langchain_core.tools import tool
+from langchain_core.tools import StructuredTool
+from pydantic import BaseModel, Field
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.services.connector_service import ConnectorService
@@ -22,6 +23,7 @@ from app.services.connector_service import ConnectorService
 # =============================================================================
 
 # Canonical connector values used internally by ConnectorService
+# Includes all document types and search source connectors
 _ALL_CONNECTORS: list[str] = [
     "EXTENSION",
     "FILE",
@@ -50,41 +52,117 @@ _ALL_CONNECTORS: list[str] = [
     "CRAWLED_URL",
     "CIRCLEBACK",
     "OBSIDIAN_CONNECTOR",
+    # Composio connectors
+    "COMPOSIO_GOOGLE_DRIVE_CONNECTOR",
+    "COMPOSIO_GMAIL_CONNECTOR",
+    "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR",
 ]
 
+# Human-readable descriptions for each connector type
+# Used for generating dynamic docstrings and informing the LLM
+CONNECTOR_DESCRIPTIONS: dict[str, str] = {
+    "EXTENSION": "Web content saved via SurfSense browser extension (personal browsing history)",
+    "FILE": "User-uploaded documents (PDFs, Word, etc.) (personal files)",
+    "NOTE": "SurfSense Notes (notes created inside SurfSense)",
+    "SLACK_CONNECTOR": "Slack conversations and shared content (personal workspace communications)",
+    "TEAMS_CONNECTOR": "Microsoft Teams messages and conversations (personal Teams communications)",
+    "NOTION_CONNECTOR": "Notion workspace pages and databases (personal knowledge management)",
+    "YOUTUBE_VIDEO": "YouTube video transcripts and metadata (personally saved videos)",
+    "GITHUB_CONNECTOR": "GitHub repository content and issues (personal repositories and interactions)",
+    "ELASTICSEARCH_CONNECTOR": "Elasticsearch indexed documents and data (personal Elasticsearch instances)",
+    "LINEAR_CONNECTOR": "Linear project issues and discussions (personal project management)",
+    "JIRA_CONNECTOR": "Jira project issues, tickets, and comments (personal project tracking)",
+    "CONFLUENCE_CONNECTOR": "Confluence pages and comments (personal project documentation)",
+    "CLICKUP_CONNECTOR": "ClickUp tasks and project data (personal task management)",
+    "GOOGLE_CALENDAR_CONNECTOR": "Google Calendar events, meetings, and schedules (personal calendar)",
+    "GOOGLE_GMAIL_CONNECTOR": "Google Gmail emails and conversations (personal emails)",
+    "GOOGLE_DRIVE_FILE": "Google Drive files and documents (personal cloud storage)",
+    "DISCORD_CONNECTOR": "Discord server conversations and shared content (personal community)",
+    "AIRTABLE_CONNECTOR": "Airtable records, tables, and database content (personal data)",
+    "TAVILY_API": "Tavily web search API results (real-time web search)",
+    "SEARXNG_API": "SearxNG search API results (privacy-focused web search)",
+    "LINKUP_API": "Linkup search API results (web search)",
+    "BAIDU_SEARCH_API": "Baidu search API results (Chinese web search)",
+    "LUMA_CONNECTOR": "Luma events and meetings",
+    "WEBCRAWLER_CONNECTOR": "Webpages indexed by SurfSense (personally selected websites)",
+    "CRAWLED_URL": "Webpages indexed by SurfSense (personally selected websites)",
+    "BOOKSTACK_CONNECTOR": "BookStack pages (personal documentation)",
+    "CIRCLEBACK": "Circleback meeting notes, transcripts, and action items",
+    "OBSIDIAN_CONNECTOR": "Obsidian vault notes and markdown files (personal notes)",
+    # Composio connectors
+    "COMPOSIO_GOOGLE_DRIVE_CONNECTOR": "Google Drive files via Composio (personal cloud storage)",
+    "COMPOSIO_GMAIL_CONNECTOR": "Gmail emails via Composio (personal emails)",
+    "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR": "Google Calendar events via Composio (personal calendar)",
+}
 
-def _normalize_connectors(connectors_to_search: list[str] | None) -> list[str]:
+
+def _normalize_connectors(
+    connectors_to_search: list[str] | None,
+    available_connectors: list[str] | None = None,
+) -> list[str]:
     """
     Normalize connectors provided by the model.
 
     - Accepts user-facing enums like WEBCRAWLER_CONNECTOR and maps them to canonical
       ConnectorService types.
     - Drops unknown values.
-    - If None/empty, defaults to searching across all known connectors.
+    - If available_connectors is provided, only includes connectors from that list.
+    - If connectors_to_search is None/empty, defaults to available_connectors or all.
+
+    Args:
+        connectors_to_search: List of connectors requested by the model
+        available_connectors: List of connectors actually available in the search space
+
+    Returns:
+        List of normalized connector strings to search
     """
+    # Determine the set of valid connectors to consider
+    valid_set = (
+        set(available_connectors) if available_connectors else set(_ALL_CONNECTORS)
+    )
+
     if not connectors_to_search:
-        return list(_ALL_CONNECTORS)
+        # Search all available connectors if none specified
+        return (
+            list(available_connectors)
+            if available_connectors
+            else list(_ALL_CONNECTORS)
+        )
 
     normalized: list[str] = []
     for raw in connectors_to_search:
         c = (raw or "").strip().upper()
         if not c:
             continue
+        # Map user-facing aliases to canonical names
         if c == "WEBCRAWLER_CONNECTOR":
             c = "CRAWLED_URL"
         normalized.append(c)
 
-    # de-dupe while preserving order + filter unknown
+    # de-dupe while preserving order + filter to valid connectors
     seen: set[str] = set()
     out: list[str] = []
     for c in normalized:
         if c in seen:
             continue
+        # Only include if it's a known connector AND available
         if c not in _ALL_CONNECTORS:
             continue
+        if c not in valid_set:
+            continue
         seen.add(c)
         out.append(c)
-    return out if out else list(_ALL_CONNECTORS)
+
+    # Fallback to all available if nothing matched
+    return (
+        out
+        if out
+        else (
+            list(available_connectors)
+            if available_connectors
+            else list(_ALL_CONNECTORS)
+        )
+    )
 
 
 # =============================================================================
@@ -233,6 +311,7 @@ async def search_knowledge_base_async(
     top_k: int = 10,
     start_date: datetime | None = None,
     end_date: datetime | None = None,
+    available_connectors: list[str] | None = None,
 ) -> str:
     """
     Search the user's knowledge base for relevant documents.
@@ -248,6 +327,8 @@ async def search_knowledge_base_async(
         top_k: Number of results per connector
         start_date: Optional start datetime (UTC) for filtering documents
         end_date: Optional end datetime (UTC) for filtering documents
+        available_connectors: Optional list of connectors actually available in the search space.
+                            If provided, only these connectors will be searched.
 
     Returns:
         Formatted string with search results
@@ -262,7 +343,7 @@ async def search_knowledge_base_async(
         end_date=end_date,
     )
 
-    connectors = _normalize_connectors(connectors_to_search)
+    connectors = _normalize_connectors(connectors_to_search, available_connectors)
 
     for connector in connectors:
         try:
@@ -316,6 +397,16 @@ async def search_knowledge_base_async(
                 )
                 all_documents.extend(chunks)
 
+            elif connector == "TEAMS_CONNECTOR":
+                _, chunks = await connector_service.search_teams(
+                    user_query=query,
+                    search_space_id=search_space_id,
+                    top_k=top_k,
+                    start_date=resolved_start_date,
+                    end_date=resolved_end_date,
+                )
+                all_documents.extend(chunks)
+
             elif connector == "NOTION_CONNECTOR":
                 _, chunks = await connector_service.search_notion(
                     user_query=query,
@@ -519,6 +610,39 @@ async def search_knowledge_base_async(
                 )
                 all_documents.extend(chunks)
 
+            # =========================================================
+            # Composio Connectors
+            # =========================================================
+            elif connector == "COMPOSIO_GOOGLE_DRIVE_CONNECTOR":
+                _, chunks = await connector_service.search_composio_google_drive(
+                    user_query=query,
+                    search_space_id=search_space_id,
+                    top_k=top_k,
+                    start_date=resolved_start_date,
+                    end_date=resolved_end_date,
+                )
+                all_documents.extend(chunks)
+
+            elif connector == "COMPOSIO_GMAIL_CONNECTOR":
+                _, chunks = await connector_service.search_composio_gmail(
+                    user_query=query,
+                    search_space_id=search_space_id,
+                    top_k=top_k,
+                    start_date=resolved_start_date,
+                    end_date=resolved_end_date,
+                )
+                all_documents.extend(chunks)
+
+            elif connector == "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR":
+                _, chunks = await connector_service.search_composio_google_calendar(
+                    user_query=query,
+                    search_space_id=search_space_id,
+                    top_k=top_k,
+                    start_date=resolved_start_date,
+                    end_date=resolved_end_date,
+                )
+                all_documents.extend(chunks)
+
         except Exception as e:
             print(f"Error searching connector {connector}: {e}")
             continue
@@ -543,11 +667,68 @@ async def search_knowledge_base_async(
     return format_documents_for_context(deduplicated)
 
 
+def _build_connector_docstring(available_connectors: list[str] | None) -> str:
+    """
+    Build the connector documentation section for the tool docstring.
+
+    Args:
+        available_connectors: List of available connector types, or None for all
+
+    Returns:
+        Formatted docstring section listing available connectors
+    """
+    connectors = available_connectors if available_connectors else list(_ALL_CONNECTORS)
+
+    lines = []
+    for connector in connectors:
+        # Skip internal names, prefer user-facing aliases
+        if connector == "CRAWLED_URL":
+            # Show as WEBCRAWLER_CONNECTOR for user-facing docs
+            description = CONNECTOR_DESCRIPTIONS.get(connector, connector)
+            lines.append(f"- WEBCRAWLER_CONNECTOR: {description}")
+        else:
+            description = CONNECTOR_DESCRIPTIONS.get(connector, connector)
+            lines.append(f"- {connector}: {description}")
+
+    return "\n".join(lines)
+
+
+# =============================================================================
+# Tool Input Schema
+# =============================================================================
+
+
+class SearchKnowledgeBaseInput(BaseModel):
+    """Input schema for the search_knowledge_base tool."""
+
+    query: str = Field(
+        description="The search query - be specific and include key terms"
+    )
+    top_k: int = Field(
+        default=10,
+        description="Number of results to retrieve (default: 10)",
+    )
+    start_date: str | None = Field(
+        default=None,
+        description="Optional ISO date/datetime (e.g. '2025-12-12' or '2025-12-12T00:00:00+00:00')",
+    )
+    end_date: str | None = Field(
+        default=None,
+        description="Optional ISO date/datetime (e.g. '2025-12-19' or '2025-12-19T23:59:59+00:00')",
+    )
+    connectors_to_search: list[str] | None = Field(
+        default=None,
+        description="Optional list of connector enums to search. If omitted, searches all available.",
+    )
+
+
 def create_search_knowledge_base_tool(
     search_space_id: int,
     db_session: AsyncSession,
     connector_service: ConnectorService,
-):
+    available_connectors: list[str] | None = None,
+    available_document_types: list[str] | None = None,
+) -> StructuredTool:
     """
     Factory function to create the search_knowledge_base tool with injected dependencies.
 
@@ -555,72 +736,57 @@ def create_search_knowledge_base_tool(
         search_space_id: The user's search space ID
         db_session: Database session
         connector_service: Initialized connector service
+        available_connectors: Optional list of connector types available in the search space.
+                            Used to dynamically generate the tool docstring.
+        available_document_types: Optional list of document types that have data in the search space.
+                                Used to inform the LLM about what data exists.
 
     Returns:
-        A configured tool function
+        A configured StructuredTool instance
     """
+    # Build connector documentation dynamically
+    connector_docs = _build_connector_docstring(available_connectors)
 
-    @tool
+    # Build context about available document types
-    async def search_knowledge_base(
+    doc_types_info = ""
+    if available_document_types:
+        doc_types_info = f"""
+
+## Document types with indexed content in this search space
+
+The following document types have content available for search:
+{", ".join(available_document_types)}
+
+Focus searches on these types for best results."""
+
+    # Build the dynamic description for the tool
+    # This is what the LLM sees when deciding whether/how to use the tool
+    dynamic_description = f"""Search the user's personal knowledge base for relevant information.
+
+Use this tool to find documents, notes, files, web pages, and other content that may help answer the user's question.
+
+IMPORTANT:
+- If the user requests a specific source type (e.g. "my notes", "Slack messages"), pass `connectors_to_search=[...]` using the enums below.
+- If `connectors_to_search` is omitted/empty, the system will search broadly.
+- Only connectors that are enabled/configured for this search space are available.{doc_types_info}
+
+## Available connector enums for `connectors_to_search`
+
+{connector_docs}
+
+NOTE: `WEBCRAWLER_CONNECTOR` is mapped internally to the canonical document type `CRAWLED_URL`."""
+
+    # Capture for closure
+    _available_connectors = available_connectors
+
+    async def _search_knowledge_base_impl(
         query: str,
         top_k: int = 10,
         start_date: str | None = None,
         end_date: str | None = None,
         connectors_to_search: list[str] | None = None,
     ) -> str:
-        """
+        """Implementation function for knowledge base search."""
-        Search the user's personal knowledge base for relevant information.
-
-        Use this tool to find documents, notes, files, web pages, and other content
-        that may help answer the user's question.
-
-        IMPORTANT:
-        - If the user requests a specific source type (e.g. "my notes", "Slack messages"),
-          pass `connectors_to_search=[...]` using the enums below.
-        - If `connectors_to_search` is omitted/empty, the system will search broadly.
-
-        ## Available connector enums for `connectors_to_search`
-
-        - EXTENSION: "Web content saved via SurfSense browser extension" (personal browsing history)
-        - FILE: "User-uploaded documents (PDFs, Word, etc.)" (personal files)
-        - NOTE: "SurfSense Notes" (notes created inside SurfSense)
-        - SLACK_CONNECTOR: "Slack conversations and shared content" (personal workspace communications)
-        - TEAMS_CONNECTOR: "Microsoft Teams messages and conversations" (personal Teams communications)
-        - NOTION_CONNECTOR: "Notion workspace pages and databases" (personal knowledge management)
-        - YOUTUBE_VIDEO: "YouTube video transcripts and metadata" (personally saved videos)
-        - GITHUB_CONNECTOR: "GitHub repository content and issues" (personal repositories and interactions)
-        - ELASTICSEARCH_CONNECTOR: "Elasticsearch indexed documents and data" (personal Elasticsearch instances and custom data sources)
-        - LINEAR_CONNECTOR: "Linear project issues and discussions" (personal project management)
-        - JIRA_CONNECTOR: "Jira project issues, tickets, and comments" (personal project tracking)
-        - CONFLUENCE_CONNECTOR: "Confluence pages and comments" (personal project documentation)
-        - CLICKUP_CONNECTOR: "ClickUp tasks and project data" (personal task management)
-        - GOOGLE_CALENDAR_CONNECTOR: "Google Calendar events, meetings, and schedules" (personal calendar and time management)
-        - GOOGLE_GMAIL_CONNECTOR: "Google Gmail emails and conversations" (personal emails and communications)
-        - GOOGLE_DRIVE_FILE: "Google Drive files and documents" (personal cloud storage and file management)
-        - DISCORD_CONNECTOR: "Discord server conversations and shared content" (personal community communications)
-        - AIRTABLE_CONNECTOR: "Airtable records, tables, and database content" (personal data management and organization)
-        - TAVILY_API: "Tavily search API results" (personalized search results)
-        - SEARXNG_API: "SearxNG search API results" (personalized search results)
-        - LINKUP_API: "Linkup search API results" (personalized search results)
-        - BAIDU_SEARCH_API: "Baidu search API results" (personalized search results)
-        - LUMA_CONNECTOR: "Luma events"
-        - WEBCRAWLER_CONNECTOR: "Webpages indexed by SurfSense" (personally selected websites)
-        - BOOKSTACK_CONNECTOR: "BookStack pages" (personal documentation)
-        - CIRCLEBACK: "Circleback meeting notes, transcripts, and action items" (personal meeting records)
-        - OBSIDIAN_CONNECTOR: "Obsidian vault notes and markdown files" (personal notes and knowledge management)
-
-        NOTE: `WEBCRAWLER_CONNECTOR` is mapped internally to the canonical document type `CRAWLED_URL`.
-
-        Args:
-            query: The search query - be specific and include key terms
-            top_k: Number of results to retrieve (default: 10)
-            start_date: Optional ISO date/datetime (e.g. "2025-12-12" or "2025-12-12T00:00:00+00:00")
-            end_date: Optional ISO date/datetime (e.g. "2025-12-19" or "2025-12-19T23:59:59+00:00")
-            connectors_to_search: Optional list of connector enums to search. If omitted, searches all.
-
-        Returns:
-            Formatted string with relevant documents and their content
-        """
         from app.agents.new_chat.utils import parse_date_or_datetime
 
         parsed_start: datetime | None = None
@@ -640,6 +806,16 @@ def create_search_knowledge_base_tool(
             top_k=top_k,
             start_date=parsed_start,
             end_date=parsed_end,
+            available_connectors=_available_connectors,
         )
 
-    return search_knowledge_base
+    # Create StructuredTool with dynamic description
+    # This properly sets the description that the LLM sees
+    tool = StructuredTool(
+        name="search_knowledge_base",
+        description=dynamic_description,
+        coroutine=_search_knowledge_base_impl,
+        args_schema=SearchKnowledgeBaseInput,
+    )
+
+    return tool

surfsense_backend/app/agents/new_chat/tools/registry.py

@@ -85,6 +85,7 @@ class ToolDefinition:
 # Contributors: Add your new tools here!
 BUILTIN_TOOLS: list[ToolDefinition] = [
     # Core tool - searches the user's knowledge base
+    # Now supports dynamic connector/document type discovery
     ToolDefinition(
         name="search_knowledge_base",
         description="Search the user's personal knowledge base for relevant information",
@@ -92,8 +93,12 @@ BUILTIN_TOOLS: list[ToolDefinition] = [
             search_space_id=deps["search_space_id"],
             db_session=deps["db_session"],
             connector_service=deps["connector_service"],
+            # Optional: dynamically discovered connectors/document types
+            available_connectors=deps.get("available_connectors"),
+            available_document_types=deps.get("available_document_types"),
         ),
         requires=["search_space_id", "db_session", "connector_service"],
+        # Note: available_connectors and available_document_types are optional
     ),
     # Podcast generation tool
     ToolDefinition(

surfsense_backend/app/services/connector_service.py

@@ -2871,3 +2871,350 @@ class ConnectorService:
         }
 
         return result_object, obsidian_docs
+
+    # =========================================================================
+    # Composio Connector Search Methods
+    # =========================================================================
+
+    async def search_composio_google_drive(
+        self,
+        user_query: str,
+        search_space_id: int,
+        top_k: int = 20,
+        start_date: datetime | None = None,
+        end_date: datetime | None = None,
+    ) -> tuple:
+        """
+        Search for Composio Google Drive files and return both the source information
+        and langchain documents.
+
+        Uses combined chunk-level and document-level hybrid search with RRF fusion.
+
+        Args:
+            user_query: The user's query
+            search_space_id: The search space ID to search in
+            top_k: Maximum number of results to return
+            start_date: Optional start date for filtering documents by updated_at
+            end_date: Optional end date for filtering documents by updated_at
+
+        Returns:
+            tuple: (sources_info, langchain_documents)
+        """
+        composio_drive_docs = await self._combined_rrf_search(
+            query_text=user_query,
+            search_space_id=search_space_id,
+            document_type="COMPOSIO_GOOGLE_DRIVE_CONNECTOR",
+            top_k=top_k,
+            start_date=start_date,
+            end_date=end_date,
+        )
+
+        # Early return if no results
+        if not composio_drive_docs:
+            return {
+                "id": 54,
+                "name": "Google Drive (Composio)",
+                "type": "COMPOSIO_GOOGLE_DRIVE_CONNECTOR",
+                "sources": [],
+            }, []
+
+        def _title_fn(doc_info: dict[str, Any], metadata: dict[str, Any]) -> str:
+            return (
+                doc_info.get("title")
+                or metadata.get("title")
+                or metadata.get("file_name")
+                or "Untitled Document"
+            )
+
+        def _url_fn(_doc_info: dict[str, Any], metadata: dict[str, Any]) -> str:
+            return metadata.get("url") or metadata.get("web_view_link") or ""
+
+        def _description_fn(
+            chunk: dict[str, Any], _doc_info: dict[str, Any], metadata: dict[str, Any]
+        ) -> str:
+            description = self._chunk_preview(chunk.get("content", ""), limit=200)
+            info_parts = []
+            mime_type = metadata.get("mime_type")
+            modified_time = metadata.get("modified_time")
+            if mime_type:
+                info_parts.append(f"Type: {mime_type}")
+            if modified_time:
+                info_parts.append(f"Modified: {modified_time}")
+            if info_parts:
+                description = (description + " | " + " | ".join(info_parts)).strip(" |")
+            return description
+
+        def _extra_fields_fn(
+            _chunk: dict[str, Any], _doc_info: dict[str, Any], metadata: dict[str, Any]
+        ) -> dict[str, Any]:
+            return {
+                "mime_type": metadata.get("mime_type", ""),
+                "file_id": metadata.get("file_id", ""),
+                "modified_time": metadata.get("modified_time", ""),
+            }
+
+        sources_list = self._build_chunk_sources_from_documents(
+            composio_drive_docs,
+            title_fn=_title_fn,
+            url_fn=_url_fn,
+            description_fn=_description_fn,
+            extra_fields_fn=_extra_fields_fn,
+        )
+
+        # Create result object
+        result_object = {
+            "id": 54,
+            "name": "Google Drive (Composio)",
+            "type": "COMPOSIO_GOOGLE_DRIVE_CONNECTOR",
+            "sources": sources_list,
+        }
+
+        return result_object, composio_drive_docs
+
+    async def search_composio_gmail(
+        self,
+        user_query: str,
+        search_space_id: int,
+        top_k: int = 20,
+        start_date: datetime | None = None,
+        end_date: datetime | None = None,
+    ) -> tuple:
+        """
+        Search for Composio Gmail messages and return both the source information
+        and langchain documents.
+
+        Uses combined chunk-level and document-level hybrid search with RRF fusion.
+
+        Args:
+            user_query: The user's query
+            search_space_id: The search space ID to search in
+            top_k: Maximum number of results to return
+            start_date: Optional start date for filtering documents by updated_at
+            end_date: Optional end date for filtering documents by updated_at
+
+        Returns:
+            tuple: (sources_info, langchain_documents)
+        """
+        composio_gmail_docs = await self._combined_rrf_search(
+            query_text=user_query,
+            search_space_id=search_space_id,
+            document_type="COMPOSIO_GMAIL_CONNECTOR",
+            top_k=top_k,
+            start_date=start_date,
+            end_date=end_date,
+        )
+
+        # Early return if no results
+        if not composio_gmail_docs:
+            return {
+                "id": 55,
+                "name": "Gmail (Composio)",
+                "type": "COMPOSIO_GMAIL_CONNECTOR",
+                "sources": [],
+            }, []
+
+        def _title_fn(doc_info: dict[str, Any], metadata: dict[str, Any]) -> str:
+            return (
+                doc_info.get("title")
+                or metadata.get("subject")
+                or metadata.get("title")
+                or "Untitled Email"
+            )
+
+        def _url_fn(_doc_info: dict[str, Any], metadata: dict[str, Any]) -> str:
+            return metadata.get("url") or ""
+
+        def _description_fn(
+            chunk: dict[str, Any], _doc_info: dict[str, Any], metadata: dict[str, Any]
+        ) -> str:
+            description = self._chunk_preview(chunk.get("content", ""), limit=200)
+            info_parts = []
+            sender = metadata.get("from") or metadata.get("sender")
+            date = metadata.get("date") or metadata.get("received_at")
+            if sender:
+                info_parts.append(f"From: {sender}")
+            if date:
+                info_parts.append(f"Date: {date}")
+            if info_parts:
+                description = (description + " | " + " | ".join(info_parts)).strip(" |")
+            return description
+
+        def _extra_fields_fn(
+            _chunk: dict[str, Any], _doc_info: dict[str, Any], metadata: dict[str, Any]
+        ) -> dict[str, Any]:
+            return {
+                "message_id": metadata.get("message_id", ""),
+                "thread_id": metadata.get("thread_id", ""),
+                "from": metadata.get("from", ""),
+                "to": metadata.get("to", ""),
+                "date": metadata.get("date", ""),
+            }
+
+        sources_list = self._build_chunk_sources_from_documents(
+            composio_gmail_docs,
+            title_fn=_title_fn,
+            url_fn=_url_fn,
+            description_fn=_description_fn,
+            extra_fields_fn=_extra_fields_fn,
+        )
+
+        # Create result object
+        result_object = {
+            "id": 55,
+            "name": "Gmail (Composio)",
+            "type": "COMPOSIO_GMAIL_CONNECTOR",
+            "sources": sources_list,
+        }
+
+        return result_object, composio_gmail_docs
+
+    async def search_composio_google_calendar(
+        self,
+        user_query: str,
+        search_space_id: int,
+        top_k: int = 20,
+        start_date: datetime | None = None,
+        end_date: datetime | None = None,
+    ) -> tuple:
+        """
+        Search for Composio Google Calendar events and return both the source information
+        and langchain documents.
+
+        Uses combined chunk-level and document-level hybrid search with RRF fusion.
+
+        Args:
+            user_query: The user's query
+            search_space_id: The search space ID to search in
+            top_k: Maximum number of results to return
+            start_date: Optional start date for filtering documents by updated_at
+            end_date: Optional end date for filtering documents by updated_at
+
+        Returns:
+            tuple: (sources_info, langchain_documents)
+        """
+        composio_calendar_docs = await self._combined_rrf_search(
+            query_text=user_query,
+            search_space_id=search_space_id,
+            document_type="COMPOSIO_GOOGLE_CALENDAR_CONNECTOR",
+            top_k=top_k,
+            start_date=start_date,
+            end_date=end_date,
+        )
+
+        # Early return if no results
+        if not composio_calendar_docs:
+            return {
+                "id": 56,
+                "name": "Google Calendar (Composio)",
+                "type": "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR",
+                "sources": [],
+            }, []
+
+        def _title_fn(doc_info: dict[str, Any], metadata: dict[str, Any]) -> str:
+            return (
+                doc_info.get("title")
+                or metadata.get("summary")
+                or metadata.get("title")
+                or "Untitled Event"
+            )
+
+        def _url_fn(_doc_info: dict[str, Any], metadata: dict[str, Any]) -> str:
+            return metadata.get("url") or metadata.get("html_link") or ""
+
+        def _description_fn(
+            chunk: dict[str, Any], _doc_info: dict[str, Any], metadata: dict[str, Any]
+        ) -> str:
+            description = self._chunk_preview(chunk.get("content", ""), limit=200)
+            info_parts = []
+            start_time = metadata.get("start_time") or metadata.get("start")
+            end_time = metadata.get("end_time") or metadata.get("end")
+            if start_time:
+                info_parts.append(f"Start: {start_time}")
+            if end_time:
+                info_parts.append(f"End: {end_time}")
+            if info_parts:
+                description = (description + " | " + " | ".join(info_parts)).strip(" |")
+            return description
+
+        def _extra_fields_fn(
+            _chunk: dict[str, Any], _doc_info: dict[str, Any], metadata: dict[str, Any]
+        ) -> dict[str, Any]:
+            return {
+                "event_id": metadata.get("event_id", ""),
+                "calendar_id": metadata.get("calendar_id", ""),
+                "start_time": metadata.get("start_time", ""),
+                "end_time": metadata.get("end_time", ""),
+                "location": metadata.get("location", ""),
+            }
+
+        sources_list = self._build_chunk_sources_from_documents(
+            composio_calendar_docs,
+            title_fn=_title_fn,
+            url_fn=_url_fn,
+            description_fn=_description_fn,
+            extra_fields_fn=_extra_fields_fn,
+        )
+
+        # Create result object
+        result_object = {
+            "id": 56,
+            "name": "Google Calendar (Composio)",
+            "type": "COMPOSIO_GOOGLE_CALENDAR_CONNECTOR",
+            "sources": sources_list,
+        }
+
+        return result_object, composio_calendar_docs
+
+    # =========================================================================
+    # Utility Methods for Connector Discovery
+    # =========================================================================
+
+    async def get_available_connectors(
+        self,
+        search_space_id: int,
+    ) -> list[SearchSourceConnectorType]:
+        """
+        Get all available (enabled) connector types for a search space.
+
+        Args:
+            search_space_id: The search space ID
+
+        Returns:
+            List of SearchSourceConnectorType enums for enabled connectors
+        """
+        query = (
+            select(SearchSourceConnector.connector_type)
+            .filter(
+                SearchSourceConnector.search_space_id == search_space_id,
+            )
+            .distinct()
+        )
+
+        result = await self.session.execute(query)
+        connector_types = result.scalars().all()
+        return list(connector_types)
+
+    async def get_available_document_types(
+        self,
+        search_space_id: int,
+    ) -> list[str]:
+        """
+        Get all document types that have at least one document in the search space.
+
+        Args:
+            search_space_id: The search space ID
+
+        Returns:
+            List of document type strings that have documents indexed
+        """
+        from sqlalchemy import distinct
+
+        from app.db import Document
+
+        query = select(distinct(Document.document_type)).filter(
+            Document.search_space_id == search_space_id,
+        )
+
+        result = await self.session.execute(query)
+        doc_types = result.scalars().all()
+        return [str(dt) for dt in doc_types]

surfsense_backend/app/tasks/chat/stream_new_chat.py

@@ -54,21 +54,64 @@ def format_attachments_as_context(attachments: list[ChatAttachment]) -> str:
 
 
 def format_mentioned_documents_as_context(documents: list[Document]) -> str:
-    """Format mentioned documents as context for the agent."""
+    """
+    Format mentioned documents as context for the agent.
+
+    Uses the same XML structure as knowledge_base.format_documents_for_context
+    to ensure citations work properly with chunk IDs.
+    """
     if not documents:
         return ""
 
     context_parts = ["<mentioned_documents>"]
     context_parts.append(
         "The user has explicitly mentioned the following documents from their knowledge base. "
-        "These documents are directly relevant to the query and should be prioritized as primary sources."
+        "These documents are directly relevant to the query and should be prioritized as primary sources. "
+        "Use [citation:CHUNK_ID] format for citations (e.g., [citation:123])."
     )
-    for i, doc in enumerate(documents, 1):
+    context_parts.append("")
-        context_parts.append(
+
-            f"<document index='{i}' id='{doc.id}' title='{doc.title}' type='{doc.document_type.value}'>"
+    for doc in documents:
+        # Build metadata JSON
+        metadata = doc.document_metadata or {}
+        metadata_json = json.dumps(metadata, ensure_ascii=False)
+
+        # Get URL from metadata
+        url = (
+            metadata.get("url")
+            or metadata.get("source")
+            or metadata.get("page_url")
+            or ""
         )
-        context_parts.append(f"<![CDATA[{doc.content}]]>")
+
+        context_parts.append("<document>")
+        context_parts.append("<document_metadata>")
+        context_parts.append(f"  <document_id>{doc.id}</document_id>")
+        context_parts.append(f"  <document_type>{doc.document_type.value}</document_type>")
+        context_parts.append(f"  <title><![CDATA[{doc.title}]]></title>")
+        context_parts.append(f"  <url><![CDATA[{url}]]></url>")
+        context_parts.append(f"  <metadata_json><![CDATA[{metadata_json}]]></metadata_json>")
+        context_parts.append("</document_metadata>")
+        context_parts.append("")
+        context_parts.append("<document_content>")
+
+        # Use chunks if available (preferred for proper citations)
+        if hasattr(doc, "chunks") and doc.chunks:
+            for chunk in doc.chunks:
+                context_parts.append(
+                    f"  <chunk id='{chunk.id}'><![CDATA[{chunk.content}]]></chunk>"
+                )
+        else:
+            # Fallback to document content if chunks not loaded
+            # Use document ID as chunk ID prefix for consistency
+            context_parts.append(
+                f"  <chunk id='{doc.id}'><![CDATA[{doc.content}]]></chunk>"
+            )
+
+        context_parts.append("</document_content>")
         context_parts.append("</document>")
+        context_parts.append("")
+
     context_parts.append("</mentioned_documents>")
 
     return "\n".join(context_parts)
@@ -81,8 +124,6 @@ def format_mentioned_surfsense_docs_as_context(
     if not documents:
         return ""
 
-    import json
-
     context_parts = ["<mentioned_surfsense_docs>"]
     context_parts.append(
         "The user has explicitly mentioned the following SurfSense documentation pages. "
@@ -262,11 +303,15 @@ async def stream_new_chat(
         # Build input with message history from frontend
         langchain_messages = []
 
-        # Fetch mentioned documents if any
+        # Fetch mentioned documents if any (with chunks for proper citations)
         mentioned_documents: list[Document] = []
         if mentioned_document_ids:
+            from sqlalchemy.orm import selectinload as doc_selectinload
+
             result = await session.execute(
-                select(Document).filter(
+                select(Document)
+                .options(doc_selectinload(Document.chunks))
+                .filter(
                     Document.id.in_(mentioned_document_ids),
                     Document.search_space_id == search_space_id,
                 )

surfsense_backend/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "surf-new-backend"
-version = "0.0.11"
+version = "0.0.12"
 description = "SurfSense Backend"
 requires-python = ">=3.12"
 dependencies = [

surfsense_backend/uv.lock

@@ -6545,7 +6545,7 @@ wheels = [
 
 [[package]]
 name = "surf-new-backend"
-version = "0.0.11"
+version = "0.0.12"
 source = { editable = "." }
 dependencies = [
     { name = "alembic" },

surfsense_browser_extension/package.json

@@ -1,7 +1,7 @@
 {
 	"name": "surfsense_browser_extension",
 	"displayName": "Surfsense Browser Extension",
-	"version": "0.0.11",
+	"version": "0.0.12",
 	"description": "Extension to collect Browsing History for SurfSense.",
 	"author": "https://github.com/MODSetter",
 	"engines": {

surfsense_web/components/assistant-ui/connector-popup/config/connector-status-config.json

@@ -24,6 +24,16 @@
 			"enabled": true,
 			"status": "warning",
 			"statusMessage": "Some requests may be blocked if not using Firecrawl."
+		},
+		"COMPOSIO_GOOGLE_DRIVE_CONNECTOR": {
+			"enabled": false,
+			"status": "disabled",
+			"statusMessage": "Not available yet."
+		},
+		"GITHUB_CONNECTOR": {
+			"enabled": false,
+			"status": "warning",
+			"statusMessage": "Some issues with indexing repositories."
 		}
 	},
 	"globalSettings": {

surfsense_web/components/layout/providers/LayoutDataProvider.tsx

@@ -1,13 +1,14 @@
 "use client";
 
 import { useQuery, useQueryClient } from "@tanstack/react-query";
-import { useAtomValue } from "jotai";
+import { useAtomValue, useSetAtom } from "jotai";
 import { Inbox, LogOut, SquareLibrary, Trash2 } from "lucide-react";
 import { useParams, usePathname, useRouter } from "next/navigation";
 import { useTranslations } from "next-intl";
 import { useTheme } from "next-themes";
-import { useCallback, useMemo, useState } from "react";
+import { useCallback, useEffect, useMemo, useState } from "react";
 import { toast } from "sonner";
+import { currentThreadAtom, resetCurrentThreadAtom } from "@/atoms/chat/current-thread.atom";
 import { deleteSearchSpaceMutationAtom } from "@/atoms/search-spaces/search-space-mutation.atoms";
 import { searchSpacesAtom } from "@/atoms/search-spaces/search-space-query.atoms";
 import { currentUserAtom } from "@/atoms/user/user-query.atoms";
@@ -68,11 +69,16 @@ export function LayoutDataProvider({
 	const { data: user } = useAtomValue(currentUserAtom);
 	const { data: searchSpacesData, refetch: refetchSearchSpaces } = useAtomValue(searchSpacesAtom);
 	const { mutateAsync: deleteSearchSpace } = useAtomValue(deleteSearchSpaceMutationAtom);
+	const currentThreadState = useAtomValue(currentThreadAtom);
+	const resetCurrentThread = useSetAtom(resetCurrentThreadAtom);
 
-	// Current IDs from URL
+	// State for handling new chat navigation when router is out of sync
+	const [pendingNewChat, setPendingNewChat] = useState(false);
+
+	// Current IDs from URL, with fallback to atom for replaceState updates
 	const currentChatId = params?.chat_id
 		? Number(Array.isArray(params.chat_id) ? params.chat_id[0] : params.chat_id)
-		: null;
+		: currentThreadState.id;
 
 	// Fetch current search space (for caching purposes)
 	useQuery({
@@ -124,6 +130,17 @@ export function LayoutDataProvider({
 	const [isDeletingSearchSpace, setIsDeletingSearchSpace] = useState(false);
 	const [isLeavingSearchSpace, setIsLeavingSearchSpace] = useState(false);
 
+	// Effect to complete new chat navigation after router syncs
+	// This runs when handleNewChat detected an out-of-sync state and triggered a sync
+	useEffect(() => {
+		if (pendingNewChat && params?.chat_id) {
+			// Router is now synced (chat_id is in params), complete navigation to new-chat
+			resetCurrentThread();
+			router.push(`/dashboard/${searchSpaceId}/new-chat`);
+			setPendingNewChat(false);
+		}
+	}, [pendingNewChat, params?.chat_id, router, searchSpaceId, resetCurrentThread]);
+
 	const searchSpaces: SearchSpace[] = useMemo(() => {
 		if (!searchSpacesData || !Array.isArray(searchSpacesData)) return [];
 		return searchSpacesData.map((space) => ({
@@ -175,12 +192,6 @@ export function LayoutDataProvider({
 	// Navigation items
 	const navItems: NavItem[] = useMemo(
 		() => [
-			{
-				title: "Documents",
-				url: `/dashboard/${searchSpaceId}/documents`,
-				icon: SquareLibrary,
-				isActive: pathname?.includes("/documents"),
-			},
 			{
 				title: "Inbox",
 				url: "#inbox", // Special URL to indicate this is handled differently
@@ -188,6 +199,12 @@ export function LayoutDataProvider({
 				isActive: isInboxSidebarOpen,
 				badge: unreadCount > 0 ? formatInboxCount(unreadCount) : undefined,
 			},
+			{
+				title: "Documents",
+				url: `/dashboard/${searchSpaceId}/documents`,
+				icon: SquareLibrary,
+				isActive: pathname?.includes("/documents"),
+			},
 		],
 		[searchSpaceId, pathname, isInboxSidebarOpen, unreadCount]
 	);
@@ -292,8 +309,20 @@ export function LayoutDataProvider({
 	);
 
 	const handleNewChat = useCallback(() => {
-		router.push(`/dashboard/${searchSpaceId}/new-chat`);
+		// Check if router is out of sync (thread created via replaceState but params don't have chat_id)
-	}, [router, searchSpaceId]);
+		const isOutOfSync = currentThreadState.id !== null && !params?.chat_id;
+
+		if (isOutOfSync) {
+			// First sync Next.js router by navigating to the current chat's actual URL
+			// This updates the router's internal state to match the browser URL
+			router.replace(`/dashboard/${searchSpaceId}/new-chat/${currentThreadState.id}`);
+			// Set flag to trigger navigation to new-chat after params update
+			setPendingNewChat(true);
+		} else {
+			// Normal navigation - router is in sync
+			router.push(`/dashboard/${searchSpaceId}/new-chat`);
+		}
+	}, [router, searchSpaceId, currentThreadState.id, params?.chat_id]);
 
 	const handleChatSelect = useCallback(
 		(chat: ChatItem) => {

surfsense_web/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "surfsense_web",
-	"version": "0.0.11",
+	"version": "0.0.12",
 	"private": true,
 	"description": "SurfSense Frontend",
 	"scripts": {