eb88138d15
Five parallel lanes plus an integration pass. The header, gallery, router and sitemap are all generated from the demo registry, so adding src/demos/<slug>/ puts a demo everywhere with zero edits to shared files — which is the whole reason demo nine cannot break demo one. check-demos enforces the twelve contract rules: 142 checks over one live demo. Two worth naming. The shell may not mention a specific slug, because an 'if (slug === wordle)' in src/components/demo/ is a contract bug wearing a patch. And a spec-status demo must ship a real specification — task, actions, grader, counterweight, eval command — since a coming-soon card reads worse than an honest empty gallery. Bundle budget holds: entry 108.79 kB gzipped against a 160 kB ceiling, the demo chunk 21.15 kB against 90 kB. recharts is 108 kB gzipped and lives behind a lazy import so it never touches the entry. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019mt6sHQHEnEYrJZvoMCJSB
182 lines
6.5 KiB
TypeScript
182 lines
6.5 KiB
TypeScript
import { useState } from 'react';
|
|
import type { ComponentType } from 'react';
|
|
import { Eye, Trophy } from 'lucide-react';
|
|
import type { DemoStep } from '@/lib/demo-kit/types';
|
|
import { Button } from '@/components/ui/button';
|
|
import { cn } from '@/lib/utils';
|
|
import { formatOrDash } from './format';
|
|
|
|
export interface BlindCompareRun<T> {
|
|
runId: string;
|
|
/** The identity, revealed only after the visitor commits. */
|
|
label: string;
|
|
model: string;
|
|
/** Required by the contract on an `intervened` run; shown at reveal. */
|
|
intervention?: string;
|
|
steps: DemoStep<T>[];
|
|
total: number | null;
|
|
}
|
|
|
|
export type BlindVote = 'A' | 'B' | 'tie';
|
|
|
|
export interface BlindCompareProps<T> {
|
|
/** Both runs must be the same seed or the comparison is meaningless. */
|
|
seed: number;
|
|
a: BlindCompareRun<T>;
|
|
b: BlindCompareRun<T>;
|
|
Surface: ComponentType<{ state: T; compact?: boolean }>;
|
|
question?: string;
|
|
onVote?: (vote: BlindVote) => void;
|
|
className?: string;
|
|
}
|
|
|
|
/**
|
|
* Two runs on the same seed, unlabelled, until you commit.
|
|
*
|
|
* The point is not the vote. The point is that the visitor forms an opinion
|
|
* from the behaviour BEFORE they learn which one had the better prompt, the
|
|
* bigger model or the training run — because once they know, they cannot
|
|
* unknow it, and every "obviously the trained one looks better" is worthless
|
|
* after the fact.
|
|
*
|
|
* There is a "reveal without voting" escape on purpose: a visitor who does not
|
|
* want to play should not be held hostage by a modal-shaped page.
|
|
*/
|
|
export function BlindCompare<T>({
|
|
seed,
|
|
a,
|
|
b,
|
|
Surface,
|
|
question = 'Which agent would you rather have running this?',
|
|
onVote,
|
|
className,
|
|
}: BlindCompareProps<T>) {
|
|
const [vote, setVote] = useState<BlindVote | null>(null);
|
|
const [revealed, setRevealed] = useState(false);
|
|
|
|
const commit = (choice: BlindVote) => {
|
|
setVote(choice);
|
|
setRevealed(true);
|
|
onVote?.(choice);
|
|
};
|
|
|
|
const winner: 'A' | 'B' | 'tie' =
|
|
a.total === null || b.total === null
|
|
? 'tie'
|
|
: a.total > b.total
|
|
? 'A'
|
|
: b.total > a.total
|
|
? 'B'
|
|
: 'tie';
|
|
|
|
const sides: { id: 'A' | 'B'; run: BlindCompareRun<T> }[] = [
|
|
{ id: 'A', run: a },
|
|
{ id: 'B', run: b },
|
|
];
|
|
|
|
return (
|
|
<section aria-label="Blind comparison" className={cn('space-y-3', className)}>
|
|
<div className="flex flex-wrap items-baseline gap-x-3 gap-y-1">
|
|
<h3 className="text-sm font-semibold">{question}</h3>
|
|
<p className="nums text-xs text-muted">Same puzzle, same seed ({seed}).</p>
|
|
</div>
|
|
|
|
<div className="grid grid-cols-1 gap-3 sm:grid-cols-2">
|
|
{sides.map(({ id, run }) => {
|
|
const last = run.steps[run.steps.length - 1];
|
|
const picked = vote === id;
|
|
return (
|
|
<div
|
|
key={id}
|
|
className={cn(
|
|
'card flex flex-col gap-3 p-3 transition-colors duration-2 ease-enter',
|
|
picked && 'border-brand',
|
|
revealed && winner === id && 'border-positive',
|
|
)}
|
|
>
|
|
<div className="flex items-center justify-between gap-2">
|
|
<h4 className="text-sm font-semibold">Agent {id}</h4>
|
|
<span className="nums text-xs text-muted">{run.steps.length} steps</span>
|
|
</div>
|
|
|
|
<div className="rounded-lg bg-surface-2 p-3">
|
|
{last ? (
|
|
<Surface state={last.state} />
|
|
) : (
|
|
<p className="text-sm text-muted">This run recorded no steps.</p>
|
|
)}
|
|
</div>
|
|
|
|
{!revealed ? (
|
|
<Button size="touch" className="w-full" onClick={() => commit(id)}>
|
|
Agent {id} is better
|
|
</Button>
|
|
) : (
|
|
<dl className="space-y-1 text-sm">
|
|
<div className="flex items-baseline justify-between gap-2">
|
|
<dt className="text-muted">Identity</dt>
|
|
<dd className="text-right font-medium">{run.label}</dd>
|
|
</div>
|
|
<div className="flex items-baseline justify-between gap-2">
|
|
<dt className="text-muted">Model</dt>
|
|
<dd className="nums text-right font-mono text-xs">{run.model}</dd>
|
|
</div>
|
|
<div className="flex items-baseline justify-between gap-2">
|
|
<dt className="text-muted">Intervention</dt>
|
|
<dd className="text-right text-xs">
|
|
{run.intervention ?? (
|
|
<span className="text-muted">none — plain rollout</span>
|
|
)}
|
|
</dd>
|
|
</div>
|
|
<div className="flex items-baseline justify-between gap-2 border-t border-border pt-1">
|
|
<dt className="text-muted">Reward</dt>
|
|
<dd className="nums flex items-center gap-1 text-right font-mono font-semibold">
|
|
{revealed && winner === id ? (
|
|
<Trophy className="size-3.5 text-positive" aria-hidden="true" />
|
|
) : null}
|
|
{formatOrDash(run.total)}
|
|
</dd>
|
|
</div>
|
|
</dl>
|
|
)}
|
|
</div>
|
|
);
|
|
})}
|
|
</div>
|
|
|
|
{!revealed ? (
|
|
<div className="flex flex-wrap gap-2">
|
|
<Button variant="outline" size="touch" onClick={() => commit('tie')}>
|
|
Too close to call
|
|
</Button>
|
|
<Button variant="ghost" size="touch" className="text-muted" onClick={() => setRevealed(true)}>
|
|
<Eye aria-hidden="true" />
|
|
Just show me
|
|
</Button>
|
|
</div>
|
|
) : (
|
|
<p role="status" className="card bg-surface-2 p-3 text-sm leading-relaxed">
|
|
{vote === null ? (
|
|
<>Revealed without a vote. </>
|
|
) : vote === winner ? (
|
|
<>
|
|
<span className="font-semibold text-positive">You picked the higher-scoring run.</span>{' '}
|
|
</>
|
|
) : (
|
|
<>
|
|
<span className="font-semibold text-warning">
|
|
You picked the lower-scoring run.
|
|
</span>{' '}
|
|
</>
|
|
)}
|
|
The environment scored these two with the same grader, on the same seed. The difference
|
|
between them is stated above — and if it is a prompt change rather than a training run,
|
|
it says so, because a prompt change presented as a training result is the oldest trick
|
|
in this business.
|
|
</p>
|
|
)}
|
|
</section>
|
|
);
|
|
}
|