load_execution_info
Retrieve detailed requirements and inputs for specific workflows or operations, enabling informed action execution. Save configuration data to 'jentic.json' for streamlined coding agent integration.
Instructions
Get more details about a specific action (like what information it needs from the user) before confirming you want to run it. Usually used if the action requires specific inputs. Coding Agents: To provide tools to an LLM that you have selected at runtime, use this tool to retrieve the necessary information and save it to 'jentic.json' at the root of your project.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| operation_uuids | Yes | The UUIDs of the operations to include in the configuration files. | |
| workflow_uuids | Yes | The UUIDs of the workflows to include in the configuration files. |
Input Schema (JSON Schema)
{
"properties": {
"operation_uuids": {
"description": "The UUIDs of the operations to include in the configuration files.",
"items": {
"type": "string"
},
"type": "array"
},
"workflow_uuids": {
"description": "The UUIDs of the workflows to include in the configuration files.",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"workflow_uuids",
"operation_uuids"
],
"type": "object"
}
Implementation Reference
- mcp/src/mcp/adapters/mcp.py:49-95 (handler)Core handler function for the 'load_execution_info' tool. Extracts workflow_uuids and operation_uuids from the request, combines them into ids for LoadRequest, calls self.jentic.load(), and returns the result or an error response.async def generate_runtime_config(self, request: dict[str, Any]) -> dict[str, Any]: """MCP endpoint for generating a configuration file from a selection set. Args: request: MCP tool request parameters. Returns: MCP tool response. """ # Get the workflow and operation UUIDs from the request workflow_uuids = request.get("workflow_uuids", []) if isinstance(workflow_uuids, str): workflow_uuids = [workflow_uuids] operation_uuids = request.get("operation_uuids", []) if isinstance(operation_uuids, str): operation_uuids = [operation_uuids] # Get the API name or use empty string as default api_name = request.get("api_name", "") logger = logging.getLogger(__name__) logger.debug( f"Generating config with workflow_uuids: {workflow_uuids}, operation_uuids: {operation_uuids}, api_name: {api_name}" ) try: # In generate_runtime_config method replace load_execution_info call load_request = LoadRequest( ids=workflow_uuids + operation_uuids, ) load_response = await self.jentic.load(load_request) result = load_response.model_dump(exclude_none=False) return {"result": result} except ValueError as e: logger.error(f"Error generating config: {str(e)}") return { "result": { "success": False, "operation_uuids": operation_uuids, "workflow_uuids": workflow_uuids, "api_name": api_name, "message": str(e), "config": {}, } }
- mcp/src/mcp/tools.py:48-75 (schema)Tool schema definition for 'load_execution_info', including description, input parameters (workflow_uuids array required, operation_uuids array required, api_name optional), used in tool lists and MCP initialization.LOAD_CONFIG_TOOL = { "name": "load_execution_info", "description": ( "Get more details about a specific action (like what information it needs from the user) before confirming you want to run it. " "Usually used if the action requires specific inputs. " "Coding Agents: To provide tools to an LLM that you have selected at runtime, use this tool to retrieve the necessary information and save it to 'jentic.json' at the root of your project." ), "parameters": { "type": "object", "properties": { "workflow_uuids": { "type": "array", "items": {"type": "string"}, "description": "The UUIDs of the workflows to include in the configuration files.", }, "operation_uuids": { "type": "array", "items": {"type": "string"}, "description": "The UUIDs of the operations to include in the configuration files.", }, "api_name": { "type": "string", "description": "The API name of the workflows to include in the configuration files." }, }, "required": ["workflow_uuids", "operation_uuids"], }, }
- mcp/src/mcp/handlers.py:45-50 (registration)Registers 'load_execution_info' tool to call mcp_adapter.generate_runtime_config in the central handle_request function.tool_handlers = { "search_apis": mcp_adapter.search_api_capabilities, "load_execution_info": mcp_adapter.generate_runtime_config, "execute": mcp_adapter.execute, # Add the execute tool handler "submit_feedback": mcp_adapter.submit_feedback }
- mcp/src/mcp/transport/jsonrpc_handler.py:127-132 (registration)Registers 'load_execution_info' to self.adapter.generate_runtime_config for JSON-RPC tools/call handling.tool_handlers = { "search_apis": self.adapter.search_api_capabilities, "load_execution_info": self.adapter.generate_runtime_config, "execute": self.adapter.execute, "submit_feedback": self.adapter.submit_feedback, }
- mcp/src/mcp/transport/stdio.py:36-42 (registration)Registers 'load_execution_info' to wrapper method self._handle_generate_runtime_from_selection_set (which delegates to adapter.generate_runtime_config) for stdio transport.self._handlers = { "search_apis": self._handle_search_api_capabilities, "load_execution_info": self._handle_generate_runtime_from_selection_set, "generate_code_sample": self._handle_generate_code_sample, "execute": self._handle_execute, # Add execute handler "submit_feedback": self._handle_submit_feedback, # Add submit_feedback handler }