npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@p-vbordei/think-scrubber

v1.0.0

Published

Stateful streaming reasonings scrubber for LLM streams

Readme

think-scrubber

A stateful, zero-dependency character/token stream parser to strip <think> tags and reasoning blocks from LLM output streams in real-time.

License

Apache License 2.0 (100% independent and open-source).

Features

  • Stateful Boundary Resolution: Safely handles partial tags split across stream delta boundaries (e.g., chunk 1 ends in </thi and chunk 2 starts with nk>).
  • Orphan-Close Cleanup: Detects and strips orphaned close tags (e.g., </think>) when no open tag is active.
  • Boundary Gating: Ensures <think> used in conversation as normal text (e.g. "Write a <think> block here.") is not accidentally stripped, while genuine reasoning blocks are safely discarded.
  • Multiple Tag Support: Handles <think>, <thinking>, <reasoning>, <thought>, and <REASONING_SCRATCHPAD> tags (case-insensitive).
  • Environment Agnostic: Works perfectly in Node.js, browsers, Cloudflare Workers, and Edge runtimes.

Installation

npm install think-scrubber

Usage

1. Simple Stream Feed

Use StreamingThinkScrubber statefully chunk-by-chunk:

import { StreamingThinkScrubber } from 'think-scrubber';

const scrubber = new StreamingThinkScrubber();

// On stream start
scrubber.reset();

// Inside your stream reader
const chunk1 = scrubber.feed("Hello "); // returns "Hello "
const chunk2 = scrubber.feed("<thi");   // returns "" (buffered)
const chunk3 = scrubber.feed("nk>hidden thought</"); // returns "" (buffered)
const chunk4 = scrubber.feed("think> World"); // returns " World"

// On stream end
const tail = scrubber.flush(); // returns ""

2. Async Generator Stream Helper

Scrub an async iterable of string chunks directly:

import { scrubStream } from 'think-scrubber';

const rawStream = getLlmStream(); // AsyncIterable<string>

for await (const cleanChunk of scrubStream(rawStream)) {
  process.stdout.write(cleanChunk);
}

3. Static String Helper

For non-streaming string cleanup:

import { scrubString } from 'think-scrubber';

const cleaned = scrubString("Normal prose <think>some reasoning</think> other prose");
// returns "Normal prose  other prose"