jev-leftpad
Deliberately silly npm package that left-pads a string by asking Jev to choose how many spaces to add.
Overview
jev-leftpad is a joke package that left-pads a value using Jev. It asks one Choice question whose options are space_0 through space_10; Jev should pick the right number of spaces, and JavaScript builds the padding. The README openly says padStart() does this in one line without a model call.
It can add between 0 and 10 spaces only, makes one TypeSafe request per call with retries disabled, can fail or pick the wrong option, and costs more than the built-in. The author asks people not to use it in production. Tests mock Jev and need no key.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | How many spaces should be added? | space_0 · space_1 · space_2 · space_3 · space_4 · space_5 · space_6 · space_7 · space_8 · space_9 · space_10 |
How it works
- Call leftPad(value, targetLength)
- Ask Jev to choose a number of spaces
- Build the padded string in JavaScript
Strengths
- Illustrates Choice in a tiny example
Caveats
- Joke package; use padStart()
- Limited to 10 spaces
- Can be wrong and costs an API call
Getting started
`npm install jev-leftpad`, set TYPESAFE_API_KEY, then `await leftPad('jev', 8)`.At a glance
- Type
- Project
- Status
- prototype
- Language
- JavaScript
- Runtime
- Node 20+ library
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
Left-pad strings with TypeSafe AI.
wh000wh000/awesome-jev-liveLeft-pad strings with TypeSafe AI's Jev. For reasons.
hellogumbo/awesome-jev
Frequently asked questions
Should I use this?
No, the author says not to use it for anything important.
How does it work?
Jev chooses how many spaces to add from 0 to 10.
Do tests call the API?
No, they mock Jev.
Related projects
Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.
MCP serverproductionTypeScriptAx, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.
PluginproductionTypeScriptEffect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.
ProjectproductionTypeScriptPHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.
ProjectproductionPHPGo MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.
MCP serverproductionGoSimon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.
PluginproductionPython