@elyracode/workflows

Code-orchestrated workflows for Elyra. Define multi-step pipelines where code handles the control flow and the LLM handles judgment — no token tax from LLM-based orchestration.

Why

Traditional agent orchestration uses one LLM to plan, spawn sub-agents, collect results, and decide next steps. Every sub-agent result re-enters the orchestrator's context window, paying a "token tax" that degrades quality as the window fills.

Workflows flip this: code orchestrates, the LLM only judges. Each step is focused, deterministic, and reproducible.

Install

elyra install npm:@elyracode/workflows

Usage

Create workflow files in .elyra/workflows/:

{
  "name": "deploy",
  "description": "Build, test, review, deploy",
  "steps": [
    { "name": "test", "run": "npm test" },
    { "name": "review", "prompt": "Review test results:\n{{steps.test.output}}" },
    { "name": "deploy", "run": "npm run deploy", "if": "{{steps.test.code}} == 0" }
  ]
}

Run with /workflow deploy or ask the agent to run it.

Step Types

• prompt — Send a focused prompt to the LLM
• run — Execute a shell command
• if — Conditional execution based on previous step results
• parallel — Run multiple steps concurrently

Template Variables

Reference previous step outputs with {{steps.<name>.output}}, {{steps.<name>.code}}, or {{steps.<name>.stderr}}.