jevrecipes

Recipe catalog / task-dependency

Check the dependency between two tasks

Identify whether either of two tasks requires the other to finish before it can start.

You need to decide whether two tasks can run in parallel or require a particular order.

Explore this recipe interactively ยท Source and implementation guide

Use task-dependency in TypeScript

Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.

import { taskDependency } from 'jev-recipes/task-dependency';

const result = await taskDependency({
  "firstTask": "Build the release archive from the source code.",
  "secondTask": "Upload the completed release archive to the artifact store.",
  "context": "The source code is available. No release archive exists yet, and uploading requires the completed archive."
});
console.log(result);

Input contract

FieldTypeNeeded
firstTaskstringRequired
secondTaskstringRequired
contextstringOptional
minConfidencenumberOptional
Full input and result schemas
{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "firstTask": {
        "type": "string",
        "description": "The first task, including its inputs and output when known."
      },
      "secondTask": {
        "type": "string",
        "description": "The second task, including its inputs and output when known."
      },
      "context": {
        "type": "string",
        "description": "Known prerequisites, available inputs, and relevant workflow conditions."
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "firstTask",
      "secondTask"
    ]
  },
  "result": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "usage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          },
          "output_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "input_tokens",
          "output_tokens"
        ],
        "additionalProperties": false
      },
      "status": {
        "type": "string",
        "enum": [
          "ready",
          "review"
        ]
      },
      "verdict": {
        "type": "string",
        "enum": [
          "first_before_second",
          "second_before_first",
          "independent",
          "cyclic",
          "unclear"
        ]
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "probabilities": {
        "type": "object",
        "propertyNames": {
          "type": "string",
          "enum": [
            "first_before_second",
            "second_before_first",
            "independent",
            "cyclic",
            "unclear"
          ]
        },
        "additionalProperties": {
          "type": "number",
          "minimum": 0,
          "maximum": 1
        },
        "required": [
          "first_before_second",
          "second_before_first",
          "independent",
          "cyclic",
          "unclear"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "verdict",
      "confidence",
      "probabilities"
    ],
    "additionalProperties": false
  }
}

Saved example result

This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo task-dependency.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "verdict": "first_before_second",
  "confidence": 0.96,
  "probabilities": {
    "first_before_second": 0.96,
    "second_before_first": 0.01,
    "independent": 0.01,
    "cyclic": 0.01,
    "unclear": 0.01
  }
}

Evaluation evidence

Fixture only

No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.

Use the evaluation guide to measure this decision on your own labeled cases.

Limitations

Related recipes