jevrecipes

Recipe catalog / budget-fit

Check plan against budget

Does plan, as described, plausibly fit within budget, the stated limits on steps, time, cost, or calls?

You need a yes/no check before an agent starts executing a plan under a step, time, cost, or call limit, so it can trim or ask instead of running out midway.

Explore this recipe interactively ยท Source and implementation guide

Use budget-fit 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 { budgetFit } from 'jev-recipes/budget-fit';

const result = await budgetFit({
  "plan": "1. Clone the repository and install dependencies. 2. Run the full test suite to record the baseline (about 12 minutes). 3. For each of the 9 failing tests, read the test, read the code under test, propose a fix, apply it, and rerun the full suite. 4. Open a pull request with a summary of every fix.",
  "budget": "At most 20 tool calls and 30 minutes of wall-clock time. No more than 5 full test-suite runs.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

FieldTypeNeeded
planstringRequired
budgetstringRequired
minConfidencenumberOptional
Full input and result schemas
{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "plan": {
        "type": "string"
      },
      "budget": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "plan",
      "budget"
    ]
  },
  "result": {
    "$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"
        ]
      },
      "probability": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "verdict": {
        "type": "string",
        "enum": [
          "fits",
          "exceeds"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "probability",
      "confidence",
      "verdict"
    ],
    "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 budget-fit.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "probability": 0.08,
  "confidence": 0.92,
  "verdict": "exceeds"
}

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