Skip to main content
Glama

retry_workflow

Retry a failed workflow execution from the last failed task in Netflix Conductor, enabling recovery without restarting from the beginning.

Instructions

Retry a failed workflow execution from the last failed task.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
workflowIdYesThe workflow execution ID to retry
resumeSubworkflowTasksNoResume subworkflow tasks (default: false)

Implementation Reference

  • src/index.ts:184-202 (registration)
    Registration of the 'retry_workflow' tool in the tools array, including name, description, and input schema definition.
    { name: "retry_workflow", description: "Retry a failed workflow execution from the last failed task.", inputSchema: { type: "object", properties: { workflowId: { type: "string", description: "The workflow execution ID to retry", }, resumeSubworkflowTasks: { type: "boolean", description: "Resume subworkflow tasks (default: false)", }, }, required: ["workflowId"], }, },
  • The handler logic for 'retry_workflow' tool execution. It extracts parameters, makes a POST request to Conductor's /workflow/{id}/retry endpoint with optional resumeSubworkflowTasks param, and returns a success message.
    case "retry_workflow": { const { workflowId, resumeSubworkflowTasks = false } = args as any; await conductorClient.post(`/workflow/${workflowId}/retry`, null, { params: { resumeSubworkflowTasks }, }); return { content: [ { type: "text", text: `Workflow ${workflowId} retry initiated successfully.`, }, ], }; }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/opensensor/conductor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server