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

@restormel/context-packs

v0.1.2

Published

Pass-specific text context packs (analysis, critique, synthesis) from a minimal graph-shaped retrieval payload — no DB or engine dependencies.

Readme

@restormel/context-packs

Pure, dependency-free TypeScript library that turns a minimal graph-shaped retrieval payload into three pass-specific text blocks (analysis, critique, synthesis) plus diagnostic stats for token budgets, role mix, reply chains, and unresolved tensions.

Problem

Downstream LLM pipelines (for example SOPHIA’s multi-pass analysis) need stable, budget-aware prose built from claims, relations, and arguments — without importing database drivers, full retrieval DTOs, or SSE machinery.

Install

npm install @restormel/context-packs

Usage

import {
  buildPassSpecificContextPacks,
  type ContextPackRetrievalInput,
} from "@restormel/context-packs";

const input: ContextPackRetrievalInput = {
  claims: [
    {
      id: "c1",
      text: "Example claim text.",
      claim_type: "thesis",
      source_title: "Source A",
      confidence: 0.9,
    },
  ],
  relations: [],
  arguments: [],
  seed_claim_ids: ["c1"],
};

const packs = buildPassSpecificContextPacks(input, { depthMode: "standard" });
console.log(packs.analysis.block);
console.log(packs.analysis.stats.estimated_tokens, packs.analysis.stats.token_budget);

Imports

  • Supported: import … from "@restormel/context-packs" (ESM + TypeScript types via dist/index.d.ts).
  • CJS: not shipped; consume from ESM bundlers or Node ESM.

SOPHIA integration

SOPHIA keeps a full RetrievalResult in engine.ts. Map it into this package’s input with contextPackInputFromRetrieval(result) in SOPHIA (shallow pick of claims, relations, arguments, seed_claim_ids); that adapter lives in SOPHIA — do not import SOPHIA from this package.

API

| Export | Role | |--------|------| | buildPassSpecificContextPacks(input, options?) | Main entry; options.depthMode is quick | standard | deep (token budgets per pass match SOPHIA). | | ContextPackRetrievalInput | Input: claims, relations, arguments, seed_claim_ids. | | ContextPackClaim, ContextPackRelation, ContextPackArgument | Element types; arguments may include key_premises and conclusion_text for ranking. | | PassSpecificContextPacks, ContextPack, ContextPackStats, … | Output shapes and pass/role unions. |

Token estimation is Math.ceil(characterLength / 4). See TSDoc on ContextPackStats for field meanings.

Publishing

Tag platform-v* triggers publish-restormel-platform.yml together with other platform packages. See CHANGELOG.md for semver policy.

Docs