dao-ai 0.1.12__py3-none-any.whl → 0.1.14__py3-none-any.whl

dao_ai/apps/handlers.py

@@ -14,7 +14,7 @@ from typing import AsyncGenerator
 
 import mlflow
 from dotenv import load_dotenv
-from mlflow.genai.agent_server import invoke, stream
+from mlflow.genai.agent_server import get_request_headers, invoke, stream
 from mlflow.types.responses import (
     ResponsesAgentRequest,
     ResponsesAgentResponse,
@@ -25,6 +25,23 @@ from dao_ai.config import AppConfig
 from dao_ai.logging import configure_logging
 from dao_ai.models import LanggraphResponsesAgent
 
+
+def _inject_headers_into_request(request: ResponsesAgentRequest) -> None:
+    """Inject request headers into custom_inputs for Context propagation.
+
+    Captures headers from the MLflow AgentServer context (where they're available)
+    and injects them into request.custom_inputs.configurable.headers so they
+    flow through to Context and can be used for OBO authentication.
+    """
+    headers: dict[str, str] = get_request_headers()
+    if headers:
+        if request.custom_inputs is None:
+            request.custom_inputs = {}
+        if "configurable" not in request.custom_inputs:
+            request.custom_inputs["configurable"] = {}
+        request.custom_inputs["configurable"]["headers"] = headers
+
+
 # Load environment variables from .env.local if it exists
 load_dotenv(dotenv_path=".env.local", override=True)
 
@@ -61,6 +78,8 @@ async def non_streaming(request: ResponsesAgentRequest) -> ResponsesAgentRespons
     Returns:
         ResponsesAgentResponse with the complete output
     """
+    # Capture headers while in the AgentServer async context (before they're lost)
+    _inject_headers_into_request(request)
     return await _responses_agent.apredict(request)
 
 
@@ -80,5 +99,7 @@ async def streaming(
     Yields:
         ResponsesAgentStreamEvent objects as they are generated
     """
+    # Capture headers while in the AgentServer async context (before they're lost)
+    _inject_headers_into_request(request)
     async for event in _responses_agent.apredict_stream(request):
         yield event

dao_ai/config.py

@@ -7,6 +7,7 @@ from enum import Enum
 from os import PathLike
 from pathlib import Path
 from typing import (
+    TYPE_CHECKING,
     Any,
     Callable,
     Iterator,
@@ -18,6 +19,9 @@ from typing import (
     Union,
 )
 
+if TYPE_CHECKING:
+    from dao_ai.state import Context
+
 from databricks.sdk import WorkspaceClient
 from databricks.sdk.credentials_provider import (
     CredentialsStrategy,
@@ -284,8 +288,8 @@ class IsDatabricksResource(ABC, BaseModel):
 
         Authentication priority:
         1. On-Behalf-Of User (on_behalf_of_user=True):
-           - Forwarded headers (Databricks Apps)
-           - ModelServingUserCredentials (Model Serving)
+           - Uses ModelServingUserCredentials (Model Serving)
+           - For Databricks Apps with headers, use workspace_client_from(context)
         2. Service Principal (client_id + client_secret + workspace_host)
         3. PAT (pat + workspace_host)
         4. Ambient/default authentication
@@ -294,36 +298,6 @@ class IsDatabricksResource(ABC, BaseModel):
 
         # Check for OBO first (highest priority)
         if self.on_behalf_of_user:
-            # NEW: In Databricks Apps, use forwarded headers for per-user auth
-            try:
-                from mlflow.genai.agent_server import get_request_headers
-
-                headers = get_request_headers()
-                forwarded_token = headers.get("x-forwarded-access-token")
-
-                if forwarded_token:
-                    forwarded_user = headers.get("x-forwarded-user", "unknown")
-                    logger.debug(
-                        f"Creating WorkspaceClient for {self.__class__.__name__} "
-                        f"with OBO using forwarded token from Databricks Apps",
-                        forwarded_user=forwarded_user,
-                    )
-                    # Use workspace_host if configured, otherwise SDK will auto-detect
-                    workspace_host_value: str | None = (
-                        normalize_host(value_of(self.workspace_host))
-                        if self.workspace_host
-                        else None
-                    )
-                    return WorkspaceClient(
-                        host=workspace_host_value,
-                        token=forwarded_token,
-                        auth_type="pat",
-                    )
-            except (ImportError, LookupError):
-                # mlflow not available or headers not set - fall through to Model Serving
-                pass
-
-            # Fall back to Model Serving OBO (existing behavior)
             credentials_strategy: CredentialsStrategy = ModelServingUserCredentials()
             logger.debug(
                 f"Creating WorkspaceClient for {self.__class__.__name__} "
@@ -382,6 +356,55 @@ class IsDatabricksResource(ABC, BaseModel):
         )
         return WorkspaceClient()
 
+    def workspace_client_from(self, context: "Context | None") -> WorkspaceClient:
+        """
+        Get a WorkspaceClient using headers from the provided Context.
+
+        Use this method from tools that have access to ToolRuntime[Context].
+        This allows OBO authentication to work in Databricks Apps where headers
+        are captured at request entry and passed through the Context.
+
+        Args:
+            context: Runtime context containing headers for OBO auth.
+                     If None or no headers, falls back to workspace_client property.
+
+        Returns:
+            WorkspaceClient configured with appropriate authentication.
+        """
+        from dao_ai.utils import normalize_host
+
+        # Check if we have headers in context for OBO
+        if context and context.headers and self.on_behalf_of_user:
+            headers = context.headers
+            # Try both lowercase and title-case header names (HTTP headers are case-insensitive)
+            forwarded_token = headers.get("x-forwarded-access-token") or headers.get(
+                "X-Forwarded-Access-Token"
+            )
+
+            if forwarded_token:
+                forwarded_user = headers.get("x-forwarded-user") or headers.get(
+                    "X-Forwarded-User", "unknown"
+                )
+                logger.debug(
+                    f"Creating WorkspaceClient for {self.__class__.__name__} "
+                    f"with OBO using forwarded token from Context",
+                    forwarded_user=forwarded_user,
+                )
+                # Use workspace_host if configured, otherwise SDK will auto-detect
+                workspace_host_value: str | None = (
+                    normalize_host(value_of(self.workspace_host))
+                    if self.workspace_host
+                    else None
+                )
+                return WorkspaceClient(
+                    host=workspace_host_value,
+                    token=forwarded_token,
+                    auth_type="pat",
+                )
+
+        # Fall back to existing workspace_client property
+        return self.workspace_client
+
 
 class DeploymentTarget(str, Enum):
     """Target platform for agent deployment."""

dao_ai/tools/genie.py

@@ -139,29 +139,53 @@ Returns:
 GenieResponse: A response object containing the conversation ID and result from Genie."""
     tool_description = tool_description + function_docs
 
-    genie: Genie = Genie(
-        space_id=space_id,
-        client=genie_room.workspace_client,
-        truncate_results=truncate_results,
-    )
+    # Cache for genie service - created lazily on first call
+    # This allows us to use workspace_client_from with runtime context for OBO
+    _cached_genie_service: GenieServiceBase | None = None
+
+    def _get_genie_service(context: Context | None) -> GenieServiceBase:
+        """Get or create the Genie service, using context for OBO auth if available."""
+        nonlocal _cached_genie_service
+
+        # Use cached service if available (for non-OBO or after first call)
+        # For OBO, we need fresh workspace client each time to use the user's token
+        if _cached_genie_service is not None and not genie_room.on_behalf_of_user:
+            return _cached_genie_service
+
+        # Get workspace client using context for OBO support
+        from databricks.sdk import WorkspaceClient
 
-    genie_service: GenieServiceBase = GenieService(genie)
-
-    # Wrap with semantic cache first (checked second due to decorator pattern)
-    if semantic_cache_parameters is not None:
-        genie_service = SemanticCacheService(
-            impl=genie_service,
-            parameters=semantic_cache_parameters,
-            workspace_client=genie_room.workspace_client,  # Pass workspace client for conversation history
-        ).initialize()  # Eagerly initialize to fail fast and create table
-
-    # Wrap with LRU cache last (checked first - fast O(1) exact match)
-    if lru_cache_parameters is not None:
-        genie_service = LRUCacheService(
-            impl=genie_service,
-            parameters=lru_cache_parameters,
+        workspace_client: WorkspaceClient = genie_room.workspace_client_from(context)
+
+        genie: Genie = Genie(
+            space_id=space_id,
+            client=workspace_client,
+            truncate_results=truncate_results,
         )
 
+        genie_service: GenieServiceBase = GenieService(genie)
+
+        # Wrap with semantic cache first (checked second due to decorator pattern)
+        if semantic_cache_parameters is not None:
+            genie_service = SemanticCacheService(
+                impl=genie_service,
+                parameters=semantic_cache_parameters,
+                workspace_client=workspace_client,
+            ).initialize()
+
+        # Wrap with LRU cache last (checked first - fast O(1) exact match)
+        if lru_cache_parameters is not None:
+            genie_service = LRUCacheService(
+                impl=genie_service,
+                parameters=lru_cache_parameters,
+            )
+
+        # Cache for non-OBO scenarios
+        if not genie_room.on_behalf_of_user:
+            _cached_genie_service = genie_service
+
+        return genie_service
+
     @tool(
         name_or_callable=tool_name,
         description=tool_description,
@@ -177,6 +201,10 @@ GenieResponse: A response object containing the conversation ID and result from
         # Access state through runtime
         state: AgentState = runtime.state
         tool_call_id: str = runtime.tool_call_id
+        context: Context | None = runtime.context
+
+        # Get genie service with OBO support via context
+        genie_service: GenieServiceBase = _get_genie_service(context)
 
         # Ensure space_id is a string for state keys
         space_id_str: str = str(space_id)
@@ -194,6 +222,14 @@ GenieResponse: A response object containing the conversation ID and result from
             conversation_id=existing_conversation_id,
         )
 
+        # Log the prompt being sent to Genie
+        logger.trace(
+            "Sending prompt to Genie",
+            space_id=space_id_str,
+            conversation_id=existing_conversation_id,
+            prompt=question[:500] + "..." if len(question) > 500 else question,
+        )
+
         # Call ask_question which always returns CacheResult with cache metadata
         cache_result: CacheResult = genie_service.ask_question(
             question, conversation_id=existing_conversation_id
@@ -211,6 +247,22 @@ GenieResponse: A response object containing the conversation ID and result from
             cache_key=cache_key,
         )
 
+        # Log truncated response for debugging
+        result_preview: str = str(genie_response.result)
+        if len(result_preview) > 500:
+            result_preview = result_preview[:500] + "..."
+        logger.trace(
+            "Genie response content",
+            question=question[:100] + "..." if len(question) > 100 else question,
+            query=genie_response.query,
+            description=(
+                genie_response.description[:200] + "..."
+                if genie_response.description and len(genie_response.description) > 200
+                else genie_response.description
+            ),
+            result_preview=result_preview,
+        )
+
         # Update session state with cache information
         if persist_conversation:
             session.genie.update_space(

dao_ai/tools/mcp.py

@@ -30,6 +30,7 @@ from dao_ai.config import (
     McpFunctionModel,
     TransportType,
 )
+from dao_ai.state import Context
 
 
 @dataclass
@@ -173,6 +174,7 @@ def _get_auth_resource(function: McpFunctionModel) -> IsDatabricksResource:
 
 def _build_connection_config(
     function: McpFunctionModel,
+    context: Context | None = None,
 ) -> dict[str, Any]:
     """
     Build the connection configuration dictionary for MultiServerMCPClient.
@@ -193,6 +195,7 @@ def _build_connection_config(
 
     Args:
         function: The MCP function model configuration.
+        context: Optional runtime context with headers for OBO auth.
 
     Returns:
         A dictionary containing the transport-specific connection settings.
@@ -205,14 +208,17 @@ def _build_connection_config(
         }
 
     # For HTTP transport, use DatabricksOAuthClientProvider with unified auth
+    from databricks.sdk import WorkspaceClient
     from databricks_mcp import DatabricksOAuthClientProvider
 
     # Get the resource to use for authentication
-    auth_resource = _get_auth_resource(function)
+    auth_resource: IsDatabricksResource = _get_auth_resource(function)
 
-    # Get workspace client from the auth resource
-    workspace_client = auth_resource.workspace_client
-    auth_provider = DatabricksOAuthClientProvider(workspace_client)
+    # Get workspace client from the auth resource with OBO support via context
+    workspace_client: WorkspaceClient = auth_resource.workspace_client_from(context)
+    auth_provider: DatabricksOAuthClientProvider = DatabricksOAuthClientProvider(
+        workspace_client
+    )
 
     # Log which resource is providing auth
     resource_name = (
@@ -509,19 +515,28 @@ async def acreate_mcp_tools(
     def _create_tool_wrapper(mcp_tool: Tool) -> RunnableLike:
         """
         Create a LangChain tool wrapper for an MCP tool.
+
+        Supports OBO authentication via context headers.
         """
+        from langchain.tools import ToolRuntime
 
         @create_tool(
             mcp_tool.name,
             description=mcp_tool.description or f"MCP tool: {mcp_tool.name}",
             args_schema=mcp_tool.inputSchema,
         )
-        async def tool_wrapper(**kwargs: Any) -> str:
+        async def tool_wrapper(
+            runtime: ToolRuntime[Context] = None,
+            **kwargs: Any,
+        ) -> str:
             """Execute MCP tool with fresh session."""
             logger.trace("Invoking MCP tool", tool_name=mcp_tool.name, args=kwargs)
 
-            invocation_client = MultiServerMCPClient(
-                {"mcp_function": _build_connection_config(function)}
+            # Get context for OBO support
+            context: Context | None = runtime.context if runtime else None
+
+            invocation_client: MultiServerMCPClient = MultiServerMCPClient(
+                {"mcp_function": _build_connection_config(function, context)}
             )
 
             try:
@@ -530,7 +545,7 @@ async def acreate_mcp_tools(
                         mcp_tool.name, kwargs
                     )
 
-                    text_result = _extract_text_content(result)
+                    text_result: str = _extract_text_content(result)
 
                     logger.trace(
                         "MCP tool completed",
@@ -625,20 +640,28 @@ def create_mcp_tools(
         This wrapper handles:
         - Fresh session creation per invocation (stateless)
         - Content extraction to plain text (avoiding extra fields)
+        - OBO authentication via context headers
         """
+        from langchain.tools import ToolRuntime
 
         @create_tool(
             mcp_tool.name,
             description=mcp_tool.description or f"MCP tool: {mcp_tool.name}",
             args_schema=mcp_tool.inputSchema,
         )
-        async def tool_wrapper(**kwargs: Any) -> str:
+        async def tool_wrapper(
+            runtime: ToolRuntime[Context] = None,
+            **kwargs: Any,
+        ) -> str:
             """Execute MCP tool with fresh session."""
             logger.trace("Invoking MCP tool", tool_name=mcp_tool.name, args=kwargs)
 
-            # Create a fresh client/session for each invocation
-            invocation_client = MultiServerMCPClient(
-                {"mcp_function": _build_connection_config(function)}
+            # Get context for OBO support
+            context: Context | None = runtime.context if runtime else None
+
+            # Create a fresh client/session for each invocation with OBO support
+            invocation_client: MultiServerMCPClient = MultiServerMCPClient(
+                {"mcp_function": _build_connection_config(function, context)}
             )
 
             try:
@@ -648,7 +671,7 @@ def create_mcp_tools(
                     )
 
                     # Extract text content, avoiding extra fields
-                    text_result = _extract_text_content(result)
+                    text_result: str = _extract_text_content(result)
 
                     logger.trace(
                         "MCP tool completed",

dao_ai/tools/slack.py

@@ -1,11 +1,13 @@
 from typing import Any, Callable, Optional
 
 from databricks.sdk.service.serving import ExternalFunctionRequestHttpMethod
+from langchain.tools import ToolRuntime
 from langchain_core.tools import tool
 from loguru import logger
 from requests import Response
 
 from dao_ai.config import ConnectionModel
+from dao_ai.state import Context
 
 
 def _find_channel_id_by_name(
@@ -129,8 +131,17 @@ def create_send_slack_message_tool(
         name_or_callable=name,
         description=description,
     )
-    def send_slack_message(text: str) -> str:
-        response: Response = connection.workspace_client.serving_endpoints.http_request(
+    def send_slack_message(
+        text: str,
+        runtime: ToolRuntime[Context] = None,
+    ) -> str:
+        from databricks.sdk import WorkspaceClient
+
+        # Get workspace client with OBO support via context
+        context: Context | None = runtime.context if runtime else None
+        workspace_client: WorkspaceClient = connection.workspace_client_from(context)
+
+        response: Response = workspace_client.serving_endpoints.http_request(
             conn=connection.name,
             method=ExternalFunctionRequestHttpMethod.POST,
             path="/api/chat.postMessage",

dao_ai/tools/sql.py

@@ -7,10 +7,11 @@ pre-configured SQL statements against a Databricks SQL warehouse.
 
 from databricks.sdk import WorkspaceClient
 from databricks.sdk.service.sql import StatementResponse, StatementState
-from langchain.tools import tool
+from langchain.tools import ToolRuntime, tool
 from loguru import logger
 
 from dao_ai.config import WarehouseModel, value_of
+from dao_ai.state import Context
 
 
 def create_execute_statement_tool(
@@ -63,7 +64,6 @@ def create_execute_statement_tool(
         description = f"Execute a pre-configured SQL query against the {warehouse.name} warehouse and return the results."
 
     warehouse_id: str = value_of(warehouse.warehouse_id)
-    workspace_client: WorkspaceClient = warehouse.workspace_client
 
     logger.debug(
         "Creating SQL execution tool",
@@ -74,7 +74,7 @@ def create_execute_statement_tool(
     )
 
     @tool(name_or_callable=name, description=description)
-    def execute_statement_tool() -> str:
+    def execute_statement_tool(runtime: ToolRuntime[Context] = None) -> str:
         """
         Execute the pre-configured SQL statement against the Databricks SQL warehouse.
 
@@ -88,6 +88,10 @@ def create_execute_statement_tool(
             sql_preview=statement[:100] + "..." if len(statement) > 100 else statement,
         )
 
+        # Get workspace client with OBO support via context
+        context: Context | None = runtime.context if runtime else None
+        workspace_client: WorkspaceClient = warehouse.workspace_client_from(context)
+
         try:
             # Execute the SQL statement
             statement_response: StatementResponse = (

dao_ai/tools/unity_catalog.py

@@ -1,10 +1,11 @@
-from typing import Any, Dict, Optional, Sequence, Set
+from typing import Annotated, Any, Dict, Optional, Sequence, Set
 
 from databricks.sdk import WorkspaceClient
 from databricks.sdk.service.catalog import FunctionInfo, PermissionsChange, Privilege
 from databricks_langchain import DatabricksFunctionClient, UCFunctionToolkit
+from langchain.tools import ToolRuntime
 from langchain_core.runnables.base import RunnableLike
-from langchain_core.tools import StructuredTool
+from langchain_core.tools import InjectedToolArg, StructuredTool
 from loguru import logger
 from pydantic import BaseModel
 from unitycatalog.ai.core.base import FunctionExecutionResult
@@ -15,6 +16,7 @@ from dao_ai.config import (
     UnityCatalogFunctionModel,
     value_of,
 )
+from dao_ai.state import Context
 from dao_ai.utils import normalize_host
 
 
@@ -35,13 +37,11 @@ def create_uc_tools(
         A sequence of BaseTool objects that wrap the specified UC functions
     """
     original_function_model: UnityCatalogFunctionModel | None = None
-    workspace_client: WorkspaceClient | None = None
     function_name: str
 
     if isinstance(function, UnityCatalogFunctionModel):
         original_function_model = function
         function_name = function.resource.full_name
-        workspace_client = function.resource.workspace_client
     else:
         function_name = function
 
@@ -56,6 +56,12 @@ def create_uc_tools(
         # Use with_partial_args directly with UnityCatalogFunctionModel
         tools = [with_partial_args(original_function_model)]
     else:
+        # For standard UC toolkit, we need workspace_client at creation time
+        # Use the resource's workspace_client (will use ambient auth if no OBO)
+        workspace_client: WorkspaceClient | None = None
+        if original_function_model:
+            workspace_client = original_function_model.resource.workspace_client
+
         # Fallback to standard UC toolkit approach
         client: DatabricksFunctionClient = DatabricksFunctionClient(
             client=workspace_client
@@ -356,7 +362,6 @@ def with_partial_args(
     # Get function info from the resource
     function_name: str = uc_function.resource.full_name
     tool_name: str = uc_function.resource.name or function_name.replace(".", "_")
-    workspace_client: WorkspaceClient = uc_function.resource.workspace_client
 
     logger.debug(
         "Creating UC tool with partial args",
@@ -365,7 +370,7 @@ def with_partial_args(
         partial_args=list(resolved_args.keys()),
     )
 
-    # Grant permissions if we have credentials
+    # Grant permissions if we have credentials (using ambient auth for setup)
     if "client_id" in resolved_args:
         client_id: str = resolved_args["client_id"]
         host: Optional[str] = resolved_args.get("host")
@@ -376,14 +381,18 @@ def with_partial_args(
                 "Failed to grant permissions", function_name=function_name, error=str(e)
             )
 
-    # Create the client for function execution using the resource's workspace client
-    client: DatabricksFunctionClient = DatabricksFunctionClient(client=workspace_client)
+    # Get workspace client for schema introspection (uses ambient auth at definition time)
+    # Actual execution will use OBO via context
+    setup_workspace_client: WorkspaceClient = uc_function.resource.workspace_client
+    setup_client: DatabricksFunctionClient = DatabricksFunctionClient(
+        client=setup_workspace_client
+    )
 
     # Try to get the function schema for better tool definition
     schema_model: type[BaseModel]
     tool_description: str
     try:
-        function_info: FunctionInfo = client.get_function(function_name)
+        function_info: FunctionInfo = setup_client.get_function(function_name)
         schema_info = generate_function_input_params_schema(function_info)
         tool_description = (
             function_info.comment or f"Unity Catalog function: {function_name}"
@@ -419,8 +428,21 @@ def with_partial_args(
         tool_description = f"Unity Catalog function: {function_name}"
 
     # Create a wrapper function that calls _execute_uc_function with partial args
-    def uc_function_wrapper(**kwargs) -> str:
+    # Uses InjectedToolArg to ensure runtime is injected but hidden from the LLM
+    def uc_function_wrapper(
+        runtime: Annotated[ToolRuntime[Context], InjectedToolArg] = None,
+        **kwargs: Any,
+    ) -> str:
         """Wrapper function that executes Unity Catalog function with partial args."""
+        # Get workspace client with OBO support via context
+        context: Context | None = runtime.context if runtime else None
+        workspace_client: WorkspaceClient = uc_function.resource.workspace_client_from(
+            context
+        )
+        client: DatabricksFunctionClient = DatabricksFunctionClient(
+            client=workspace_client
+        )
+
         return _execute_uc_function(
             client=client,
             function_name=function_name,

dao_ai/tools/vector_search.py

@@ -7,13 +7,14 @@ with dynamic filter schemas based on table columns and FlashRank reranking suppo
 
 import json
 import os
-from typing import Any, Optional
+from typing import Annotated, Any, Optional
 
 import mlflow
 from databricks.sdk import WorkspaceClient
 from databricks.vector_search.reranker import DatabricksReranker
 from databricks_langchain import DatabricksVectorSearch
 from flashrank import Ranker, RerankRequest
+from langchain.tools import ToolRuntime, tool
 from langchain_core.documents import Document
 from langchain_core.tools import StructuredTool
 from loguru import logger
@@ -27,6 +28,7 @@ from dao_ai.config import (
     VectorStoreModel,
     value_of,
 )
+from dao_ai.state import Context
 from dao_ai.utils import normalize_host
 
 # Create FilterItem model at module level so it can be used in type hints
@@ -299,35 +301,67 @@ def create_vector_search_tool(
         client_args_keys=list(client_args.keys()) if client_args else [],
     )
 
-    # Create DatabricksVectorSearch
-    # Note: text_column should be None for Databricks-managed embeddings
-    # (it's automatically determined from the index)
-    vector_search: DatabricksVectorSearch = DatabricksVectorSearch(
-        index_name=index_name,
-        text_column=None,
-        columns=columns,
-        workspace_client=vector_store.workspace_client,
-        client_args=client_args if client_args else None,
-        primary_key=vector_store.primary_key,
-        doc_uri=vector_store.doc_uri,
-        include_score=True,
-        reranker=(
-            DatabricksReranker(columns_to_rerank=rerank_config.columns)
-            if rerank_config and rerank_config.columns
-            else None
-        ),
-    )
+    # Cache for DatabricksVectorSearch - created lazily for OBO support
+    _cached_vector_search: DatabricksVectorSearch | None = None
+
+    def _get_vector_search(context: Context | None) -> DatabricksVectorSearch:
+        """Get or create DatabricksVectorSearch, using context for OBO auth if available."""
+        nonlocal _cached_vector_search
+
+        # Use cached instance if available and not OBO
+        if _cached_vector_search is not None and not vector_store.on_behalf_of_user:
+            return _cached_vector_search
+
+        # Get workspace client with OBO support via context
+        workspace_client: WorkspaceClient = vector_store.workspace_client_from(context)
+
+        # Create DatabricksVectorSearch
+        # Note: text_column should be None for Databricks-managed embeddings
+        # (it's automatically determined from the index)
+        vs: DatabricksVectorSearch = DatabricksVectorSearch(
+            index_name=index_name,
+            text_column=None,
+            columns=columns,
+            workspace_client=workspace_client,
+            client_args=client_args if client_args else None,
+            primary_key=vector_store.primary_key,
+            doc_uri=vector_store.doc_uri,
+            include_score=True,
+            reranker=(
+                DatabricksReranker(columns_to_rerank=rerank_config.columns)
+                if rerank_config and rerank_config.columns
+                else None
+            ),
+        )
 
-    # Create dynamic input schema
-    input_schema: type[BaseModel] = _create_dynamic_input_schema(
-        index_name, vector_store.workspace_client
-    )
+        # Cache for non-OBO scenarios
+        if not vector_store.on_behalf_of_user:
+            _cached_vector_search = vs
+
+        return vs
+
+    # Determine tool name and description
+    tool_name: str = name or f"vector_search_{vector_store.index.name}"
+    tool_description: str = description or f"Search documents in {index_name}"
 
-    # Define the tool function
+    # Use @tool decorator for proper ToolRuntime injection
+    # The decorator ensures runtime is automatically injected and hidden from the LLM
+    @tool(name_or_callable=tool_name, description=tool_description)
     def vector_search_func(
-        query: str, filters: Optional[list[FilterItem]] = None
+        query: Annotated[str, "The search query to find relevant documents"],
+        filters: Annotated[
+            Optional[list[FilterItem]],
+            "Optional filters to apply to the search results",
+        ] = None,
+        runtime: ToolRuntime[Context] = None,
     ) -> str:
         """Search for relevant documents using vector similarity."""
+        # Get context for OBO support
+        context: Context | None = runtime.context if runtime else None
+
+        # Get vector search instance with OBO support
+        vector_search: DatabricksVectorSearch = _get_vector_search(context)
+
         # Convert FilterItem Pydantic models to dict format for DatabricksVectorSearch
         filters_dict: dict[str, Any] = {}
         if filters:
@@ -379,14 +413,6 @@ def create_vector_search_tool(
         # Return as JSON string
         return json.dumps(serialized_docs)
 
-    # Create the StructuredTool
-    tool: StructuredTool = StructuredTool.from_function(
-        func=vector_search_func,
-        name=name or f"vector_search_{vector_store.index.name}",
-        description=description or f"Search documents in {index_name}",
-        args_schema=input_schema,
-    )
-
-    logger.success("Vector search tool created", name=tool.name, index=index_name)
+    logger.success("Vector search tool created", name=tool_name, index=index_name)
 
-    return tool
+    return vector_search_func

{dao_ai-0.1.12.dist-info → dao_ai-0.1.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dao-ai
-Version: 0.1.12
+Version: 0.1.14
 Summary: DAO AI: A modular, multi-agent orchestration framework for complex AI workflows. Supports agent handoff, tool integration, and dynamic configuration via YAML.
 Project-URL: Homepage, https://github.com/natefleming/dao-ai
 Project-URL: Documentation, https://natefleming.github.io/dao-ai
@@ -125,7 +125,7 @@ DAO AI Builder generates valid YAML configurations that work seamlessly with thi
 - **[Architecture](docs/architecture.md)** - Understand how DAO works under the hood
 
 ### Core Concepts
-- **[Key Capabilities](docs/key-capabilities.md)** - Explore 14 powerful features for production agents
+- **[Key Capabilities](docs/key-capabilities.md)** - Explore 15 powerful features for production agents
 - **[Configuration Reference](docs/configuration-reference.md)** - Complete YAML configuration guide
 - **[Examples](docs/examples.md)** - Ready-to-use example configurations
 
@@ -148,7 +148,7 @@ Before you begin, you'll need:
 - **Python 3.11 or newer** installed on your computer ([download here](https://www.python.org/downloads/))
 - **A Databricks workspace** (ask your IT team or see [Databricks docs](https://docs.databricks.com/))
   - Access to **Unity Catalog** (your organization's data catalog)
-  - **Model Serving** enabled (for deploying AI agents)
+  - **Model Serving** or **Databricks Apps** enabled (for deploying AI agents)
   - *Optional*: Vector Search, Genie (for advanced features)
 
 **Not sure if you have access?** Your Databricks administrator can grant you permissions.
@@ -345,6 +345,7 @@ DAO provides powerful capabilities for building production-ready AI agents:
 
 | Feature | Description |
 |---------|-------------|
+| **Dual Deployment Targets** | Deploy to Databricks Model Serving or Databricks Apps with a single config |
 | **Multi-Tool Support** | Python functions, Unity Catalog, MCP, Agent Endpoints |
 | **On-Behalf-Of User** | Per-user permissions and governance |
 | **Advanced Caching** | Two-tier (LRU + Semantic) caching for cost optimization |

{dao_ai-0.1.12.dist-info → dao_ai-0.1.14.dist-info}/RECORD

@@ -1,7 +1,7 @@
 dao_ai/__init__.py,sha256=18P98ExEgUaJ1Byw440Ct1ty59v6nxyWtc5S6Uq2m9Q,1062
 dao_ai/catalog.py,sha256=sPZpHTD3lPx4EZUtIWeQV7VQM89WJ6YH__wluk1v2lE,4947
 dao_ai/cli.py,sha256=1Ox8qjLKRlrKu2YXozm0lWoeZnDCouECeZSGVPkQgIQ,50923
-dao_ai/config.py,sha256=9G_JiPbr_ihUCaqYPvnMbzLKtyppXTjraQfVOxnqeBA,129323
+dao_ai/config.py,sha256=7MDuX7xGSyDuBpdFZbKNDUPuTiuVe9onnUEGFtDI0jc,130123
 dao_ai/graph.py,sha256=1-uQlo7iXZQTT3uU8aYu0N5rnhw5_g_2YLwVsAs6M-U,1119
 dao_ai/logging.py,sha256=lYy4BmucCHvwW7aI3YQkQXKJtMvtTnPDu9Hnd7_O4oc,1556
 dao_ai/messages.py,sha256=4ZBzO4iFdktGSLrmhHzFjzMIt2tpaL-aQLHOQJysGnY,6959
@@ -14,7 +14,7 @@ dao_ai/types.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 dao_ai/utils.py,sha256=_Urd7Nj2VzrgPKf3NS4E6vt0lWRhEUddBqWN9BksqeE,11543
 dao_ai/vector_search.py,sha256=8d3xROg9zSIYNXjRRl6rSexsJTlufjRl5Fy1ZA8daKA,4019
 dao_ai/apps/__init__.py,sha256=RLuhZf4gQ4pemwKDz1183aXib8UfaRhwfKvRx68GRlM,661
-dao_ai/apps/handlers.py,sha256=nbJZOgmnHG5icR4Pb56jxIWsm_AGnsURgViMJX2_LTU,2608
+dao_ai/apps/handlers.py,sha256=6-IhhklHSPnS8aqKp155wPaSnYWTU1BSOPwbdWYBkFU,3594
 dao_ai/apps/model_serving.py,sha256=XLt3_0pGSRceMK6YtOrND9Jnh7mKLPCtwjVDLIaptQU,847
 dao_ai/apps/resources.py,sha256=5l6UxfMq6uspOql-HNDyUikfqRAa9eH_TiJHrGgMb6s,40029
 dao_ai/apps/server.py,sha256=neWbVnC2z9f-tJZBnho70FytNDEVOdOM1YngoGc5KHI,1264
@@ -58,18 +58,18 @@ dao_ai/tools/__init__.py,sha256=NfRpAKds_taHbx6gzLPWgtPXve-YpwzkoOAUflwxceM,1734
 dao_ai/tools/agent.py,sha256=plIWALywRjaDSnot13nYehBsrHRpBUpsVZakoGeajOE,1858
 dao_ai/tools/core.py,sha256=bRIN3BZhRQX8-Kpu3HPomliodyskCqjxynQmYbk6Vjs,3783
 dao_ai/tools/email.py,sha256=A3TsCoQgJR7UUWR0g45OPRGDpVoYwctFs1MOZMTt_d4,7389
-dao_ai/tools/genie.py,sha256=4e_5MeAe7kDzHbYeXuNPFbY5z8ci3ouj8l5254CZ2lA,8874
-dao_ai/tools/mcp.py,sha256=tfn-sdKwfNY31RsDFlafdGyN4XlKGfniXG_mO-Meh4E,21030
+dao_ai/tools/genie.py,sha256=b0R51N5D58H1vpOCUCA88ALjLs58KSMn6nl80ap8_c0,11009
+dao_ai/tools/mcp.py,sha256=K1yMQ39UgJ0Q4xhMpNWV3AVNx929w9vxZlLoCq_jrws,22016
 dao_ai/tools/memory.py,sha256=lwObKimAand22Nq3Y63tsv-AXQ5SXUigN9PqRjoWKes,1836
 dao_ai/tools/python.py,sha256=jWFnZPni2sCdtd8D1CqXnZIPHnWkdK27bCJnBXpzhvo,1879
 dao_ai/tools/search.py,sha256=cJ3D9FKr1GAR6xz55dLtRkjtQsI0WRueGt9TPDFpOxc,433
-dao_ai/tools/slack.py,sha256=QpLMXDApjPKyRpEanLp0tOhCp9WXaEBa615p4t0pucs,5040
-dao_ai/tools/sql.py,sha256=tKd1gjpLuKdQDyfmyYYtMiNRHDW6MGRbdEVaeqyB8Ok,7632
+dao_ai/tools/slack.py,sha256=QnMsA7cYD1MnEcqGqqSr6bKIhV0RgDpkyaiPmDqnAts,5433
+dao_ai/tools/sql.py,sha256=FG-Aa0FAUAnhCuZvao1J-y-cMM6bU5eCujNbsYn0xDw,7864
 dao_ai/tools/time.py,sha256=tufJniwivq29y0LIffbgeBTIDE6VgrLpmVf8Qr90qjw,9224
-dao_ai/tools/unity_catalog.py,sha256=AjQfW7bvV8NurqDLIyntYRv2eJuTwNdbvex1L5CRjOk,15534
-dao_ai/tools/vector_search.py,sha256=oe2uBwl2TfeJIXPpwiS6Rmz7wcHczSxNyqS9P3hE6co,14542
-dao_ai-0.1.12.dist-info/METADATA,sha256=BhkwtDjbzohpk86ICfQP2qAeNLsvo9kBbgwzpnB_WZQ,16698
-dao_ai-0.1.12.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-dao_ai-0.1.12.dist-info/entry_points.txt,sha256=Xa-UFyc6gWGwMqMJOt06ZOog2vAfygV_DSwg1AiP46g,43
-dao_ai-0.1.12.dist-info/licenses/LICENSE,sha256=YZt3W32LtPYruuvHE9lGk2bw6ZPMMJD8yLrjgHybyz4,1069
-dao_ai-0.1.12.dist-info/RECORD,,
+dao_ai/tools/unity_catalog.py,sha256=oBlW6pH-Ne08g60QW9wVi_tyeVYDiecuNoxQbIIFmN8,16515
+dao_ai/tools/vector_search.py,sha256=LF_72vlEF6TwUjKVv6nkUetLK766l9Kl6DQQTc9ebJI,15888
+dao_ai-0.1.14.dist-info/METADATA,sha256=3cgCatKya02uIxRs9fP-P2R_GbV3DfrQ-_JsknH0kkg,16830
+dao_ai-0.1.14.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+dao_ai-0.1.14.dist-info/entry_points.txt,sha256=Xa-UFyc6gWGwMqMJOt06ZOog2vAfygV_DSwg1AiP46g,43
+dao_ai-0.1.14.dist-info/licenses/LICENSE,sha256=YZt3W32LtPYruuvHE9lGk2bw6ZPMMJD8yLrjgHybyz4,1069
+dao_ai-0.1.14.dist-info/RECORD,,