Retrieved Context Chunks
The RAG debugging surface: ranked passages with similarity as a meter, matched spans in real mark elements, and filter chips wired as a radiogroup so arrows move between them.
Which sources this answer may draw on, shown as a scope the user can read before asking rather than a citation list after.
components/context-scope-list.tsxnpx hoverlab add context-scope-list
Or over MCP, from your editor's agent — no account needed.
Free to read, copy and install, for personal and non-commercial projects. Shipping it in client work or a paid product needs Pro ($79 once). The source lands in your repo and stops being ours — no attribution, nothing to upgrade.
Start a page with this section — add more, order them, and leave with the page source.
Citations tell you what an answer used. Scope tells you what it could have used, which is the question behind "why did it not know that".
Rendered live in your current theme — this is the same component whose source is below, not a screenshot of it.
'use client'
/**
* <ContextScopeList> — Which sources this answer may draw on, shown as a scope the user can read before asking rather than a citation list after.
*
* Citations answer "what did this use". Nobody asks that first. The
* question that actually arrives is "why did it not know that", and the
* answer is scope — what the system could have looked at — which no
* retrieval UI shows.
*
* The layout problem is that scope is a permission model, and the obvious
* wrong answer is to render it as toggles. Some of these are not choices:
* billing records are not in scope and there is no setting that puts them
* there, and a switched-off toggle beside them would imply the opposite.
*
* So rows are informational and the badge carries the modality — always, on,
* org only, never. The last row is the important one. A scope list where
* everything is available is a list nobody needs to read; the value is in
* the boundary.
*
* Rows are `<button>` elements with `aria-pressed` rather than divs, because
* selecting one is how a real implementation would show which documents that
* scope contains. Operable means focusable, activatable by Enter and Space,
* and announcing its selected state, and a div carries none of the three.
*
* The badge text is separate from the tone. `status` says "never", `tone`
* makes it red — so the severity survives for a reader who cannot
* distinguish the colour, which on a page about data access is not an
* optional consideration.
*
* The demo selects the first row, the most permissive one, so the panel
* opens on the state most sources are in.
*/
import * as React from 'react'
type Tone = 'neutral' | 'positive' | 'warning' | 'critical'
export interface ContextScopeListRow {
id: string
label: string
detail?: string
tone?: Tone
/** What the badge says. Falls back to the tone name when absent. */
status?: string
}
export interface ContextScopeListProps {
heading?: string
intro?: string
rows?: ContextScopeListRow[]
className?: string
}
/*
Tones as complete utility classes, never assembled from fragments.
Tailwind scans source text, so `text-${tone}-foreground` produces no
class at all — the same failure as an undefined token, and just as
invisible in review.
*/
const TONE_CLASS: Record<Tone, string> = {
neutral: 'bg-muted text-muted-foreground',
positive: 'bg-primary/10 text-primary',
warning: 'bg-accent text-accent-foreground',
critical: 'bg-destructive/10 text-destructive',
}
const ROWS: ContextScopeListRow[] = [
{ id: "row-1", label: "Public documentation", detail: "Always in scope. Re-indexed on every deploy.", tone: "positive", status: "always" },
{ id: "row-2", label: "Your workspace files", detail: "In scope. Only files your own account can already open.", tone: "positive", status: "on" },
{ id: "row-3", label: "Support ticket history", detail: "In scope for your organisation's tickets, never another customer's.", tone: "neutral", status: "org only" },
{ id: "row-4", label: "Billing and payment records", detail: "Out of scope. No retrieval path reaches them, and turning it on is not an option here.", tone: "critical", status: "never" },
]
export function ContextScopeList({
heading = "What it can see",
intro = "Citations tell you what an answer used. Scope tells you what it could have used, which is the question behind \"why did it not know that\".",
rows = ROWS,
className,
}: ContextScopeListProps) {
/*
Per-instance prefix for every id this block emits.
The literals these replaced were a latent duplicate the moment the
block appeared twice on one document, and `aria-labelledby` on a
duplicated id resolves to the first match -- so the second copy was
labelled by the first copy's heading. Client component, so `useId` is
the right tool.
*/
const uid = React.useId()
const [selected, setSelected] = React.useState<string | null>(rows[0]?.id ?? null)
return (
<section
aria-labelledby={`${uid}-context-scope-list-heading`}
className={`w-full bg-background px-6 py-16 ${className ?? ''}`}
>
<div className="mx-auto max-w-3xl">
<h2
id={`${uid}-context-scope-list-heading`}
className="text-2xl font-semibold tracking-tight text-foreground"
>
{heading}
</h2>
<p className="mt-2 text-sm text-muted-foreground">{intro}</p>
<ul className="mt-8 divide-y divide-border overflow-hidden rounded-xl border border-border bg-card">
{rows.map((row) => {
const isSelected = row.id === selected
return (
<li key={row.id}>
{/*
A button, not a div with onClick. The row is operable, so
it has to be reachable by keyboard and announce its
selected state — aria-pressed is what carries that.
*/}
<button
type="button"
aria-pressed={isSelected}
onClick={() => setSelected(row.id)}
className={`flex w-full items-center justify-between gap-4 px-5 py-4 text-start transition-colors hover:bg-muted/60 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-inset ${
isSelected ? 'bg-muted/40' : ''
}`}
>
<span className="min-w-0">
<span className="block truncate text-sm font-medium text-foreground">
{row.label}
</span>
{row.detail ? (
<span className="mt-0.5 block text-sm text-muted-foreground">
{row.detail}
</span>
) : null}
</span>
<span
className={`shrink-0 rounded-full px-2.5 py-1 text-xs font-medium ${
TONE_CLASS[row.tone ?? 'neutral']
}`}
>
{row.status ?? row.tone ?? 'neutral'}
</span>
</button>
</li>
)
})}
</ul>
</div>
</section>
)
}
bg-card, text-muted-foreground) — it inherits your theme instead of overriding it.Drop it at components/context-scope-list.tsx and import it where you need the section:
import { ContextScopeList } from '@/components/context-scope-list'1 of this block’s props are simple enough to drive from here. Change them and the block below re-renders — it is the same component whose source is above, not a mock of it. Everything else it accepts is in the table underneath.
Read out of the component’s own type and signature, so this cannot drift from the source below. Every prop has a default — the component renders standalone before you pass it anything.
| Prop | Type | Default |
|---|---|---|
heading | string | "What it can see" |
intro | string | — |
rows | ContextScopeListRow[] | ROWS |
className | string | — |
The same block rendered once to markup, wrapped as a file your framework compiles. Tailwind classes are framework-agnostic, so the design transfers intact — the behaviour does not.
This block is interactive. The markup below is its initial state with the event handlers stripped — you will need to re-wire the behaviour in your framework.
<!--
Context Scope List — markup from the Hoverlab catalog.
This is the block rendered once to HTML and wrapped as a component
file. It is not a port of the React source: the Tailwind classes carry
the design, which is the part that took the work, and they are the same
in every framework.
This block is interactive in React and the handlers are NOT here.
Buttons, toggles and menus render in their initial state and do
nothing until you wire them up.
-->
<section aria-labelledby="_R_0_-context-scope-list-heading" class="w-full bg-background px-6 py-16 ">
<div class="mx-auto max-w-3xl">
<h2 id="_R_0_-context-scope-list-heading" class="text-2xl font-semibold tracking-tight text-foreground">What it can see</h2>
<p class="mt-2 text-sm text-muted-foreground">Citations tell you what an answer used. Scope tells you what it could have used, which is the question behind "why did it not know that".</p>
<ul class="mt-8 divide-y divide-border overflow-hidden rounded-xl border border-border bg-card">
<li>
<button type="button" aria-pressed="true" class="flex w-full items-center justify-between gap-4 px-5 py-4 text-start transition-colors hover:bg-muted/60 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-inset bg-muted/40">
<span class="min-w-0">
<span class="block truncate text-sm font-medium text-foreground">Public documentation</span>
<span class="mt-0.5 block text-sm text-muted-foreground">Always in scope. Re-indexed on every deploy.</span>
</span>
<span class="shrink-0 rounded-full px-2.5 py-1 text-xs font-medium bg-primary/10 text-primary">always</span>
</button>
</li>
<li>
<button type="button" aria-pressed="false" class="flex w-full items-center justify-between gap-4 px-5 py-4 text-start transition-colors hover:bg-muted/60 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-inset ">
<span class="min-w-0">
<span class="block truncate text-sm font-medium text-foreground">Your workspace files</span>
<span class="mt-0.5 block text-sm text-muted-foreground">In scope. Only files your own account can already open.</span>
</span>
<span class="shrink-0 rounded-full px-2.5 py-1 text-xs font-medium bg-primary/10 text-primary">on</span>
</button>
</li>
<li>
<button type="button" aria-pressed="false" class="flex w-full items-center justify-between gap-4 px-5 py-4 text-start transition-colors hover:bg-muted/60 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-inset ">
<span class="min-w-0">
<span class="block truncate text-sm font-medium text-foreground">Support ticket history</span>
<span class="mt-0.5 block text-sm text-muted-foreground">In scope for your organisation's tickets, never another customer's.</span>
</span>
<span class="shrink-0 rounded-full px-2.5 py-1 text-xs font-medium bg-muted text-muted-foreground">org only</span>
</button>
</li>
<li>
<button type="button" aria-pressed="false" class="flex w-full items-center justify-between gap-4 px-5 py-4 text-start transition-colors hover:bg-muted/60 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-inset ">
<span class="min-w-0">
<span class="block truncate text-sm font-medium text-foreground">Billing and payment records</span>
<span class="mt-0.5 block text-sm text-muted-foreground">Out of scope. No retrieval path reaches them, and turning it on is not an option here.</span>
</span>
<span class="shrink-0 rounded-full px-2.5 py-1 text-xs font-medium bg-destructive/10 text-destructive">never</span>
</button>
</li>
</ul>
</div>
</section>
What each framework gets across the whole catalog — effects convert properly; this rung is markup.
The component, its props, the design tokens it expects and the command that installs it — as one prompt. Paste it into Claude, Cursor, v0 or ChatGPT and what they build around it will match the rest of the catalog instead of inventing its own system.
Want the whole screen instead of this one section? Open a page and copy it entire.
All of them free to read, copy and install — no account, no locked tiles, no watermarked preview. The whole catalog is open, and so are the API and the CLI.
Browse Retrieval & ContextCopying the code is free. Putting it in client work or a paid product is what Pro is for — the licence, not the access.
The RAG debugging surface: ranked passages with similarity as a meter, matched spans in real mark elements, and filter chips wired as a radiogroup so arrows move between them.
The published footnotes under an answer — ordered list, real cite and time elements, the claim each source supports, and a staleness warning written in words rather than shown as an amber dot.
Choosing what the assistant may read, with indexing state told honestly — a half-indexed source says so rather than showing a green tick — and the footer stating the effect of the selection, not its cardinality.
The refusal screen: says plainly that nothing was found, shows where it looked and the near-misses below threshold, and offers the two real ways out instead of inventing an answer.
What is in the context and what fell out of it — a stacked budget with the reply reserve drawn as a segment, and the dropped chunks named with the reason, which is the part nobody ships.
A green tick means the connector works, not that the answers are current. Freshness as an age in words per source, the headline taken from the stalest one, and a failed sync that still says what age it is answering from.
Retrieved sources ranked by how stale they are, because a confident answer from a two-year-old document is the failure people do not catch.
How an answer is tied to its sources, and what the system does when it cannot find any.