Sycophancy mitigation as a structural commitment: the model writes its full correctAnswer (plus explanation, in that order) BEFORE the learner sees the question; the commitment rides the persisted call args, is revealed on submit, and grades his free text in the model's next reply — the client never grades free recall. - tools.explain setting (segmented 'Quizzing — Multiple choice | Free recall' in Agent settings' Tools group): free arms explain and drops quiz for BOTH agents (prober variant carries no nodeId, same pattern as the probe quiz); mechanics keys never pass filterEnabledTools — quiz stays unwritable (the 2026-09-19 wedge ruling stands) - doctrine lives pi-natively in the tool descriptions (owner ruling — no conditional system-prompt chunks): explain carries the commitment rule; the MC option-building craft moved out of the prompt into the quiz description; shared/20-question-tools.md slims to the quiz-agnostic core - display seams: parseExplainInput (LaTeX-debris restoration included), dock text-mode with an 'I don't know' row (kbd row 0), AnsweredCard reveal (The answer / Why, no verdict chips), [Explain answer] format - phases/plan seams recognize both quizzing tools' nodeId tags; explain answers deliberately feed no ledger evidence (no client grading to key on — a future ruling can parse the model's grade) 1049/1049 tests, typecheck/lint/build green.
151 lines
6.1 KiB
TypeScript
151 lines
6.1 KiB
TypeScript
"use client";
|
|
|
|
import { GlyphMark } from "@/components/ui/glyph-mark";
|
|
import { cn } from "@/lib/utils";
|
|
import { MessageResponse } from "@/components/ai-elements/message";
|
|
import type { QuestionAnswerData } from "@/src/core";
|
|
|
|
/**
|
|
* Static rendering of an answered question (tool part in `output-available`).
|
|
*
|
|
* Quiz answers are GRADED: ✓/✗ marks, the correct answers, and the
|
|
* explanation. Ask answers are NOT graded — a plain record of what was said.
|
|
* (The v1 bug this pins: ask answers must never get quiz grading UI.)
|
|
* Explain answers are graded by the MODEL in its next reply, not by the
|
|
* client — the card reveals his answer, the committed correct answer, and
|
|
* the explanation, with NO verdict chips (owner ruling 2026-09-27).
|
|
*/
|
|
export function AnsweredCard({ answer }: { answer: QuestionAnswerData }) {
|
|
if (answer.dismissed) {
|
|
return (
|
|
<div className="rounded-xl border bg-card p-4 text-sm text-muted-foreground">
|
|
<span className="font-medium">{answer.questionText}</span> — skipped
|
|
</div>
|
|
);
|
|
}
|
|
|
|
const isQuiz = answer.kind === "quiz";
|
|
const isExplain = answer.kind === "explain";
|
|
const selectedIdx = new Set(answer.answers.map((a) => a.index));
|
|
const correctIdx = new Set(answer.correctIndices ?? []);
|
|
|
|
return (
|
|
<div className="rounded-xl border bg-card p-4 text-card-foreground" data-testid="answered-card">
|
|
<div className="mb-1 flex items-center gap-2 text-xs font-medium uppercase tracking-wide text-muted-foreground">
|
|
{isQuiz ? "Quiz" : isExplain ? "Explain" : "Question"}
|
|
{isQuiz &&
|
|
(answer.dontKnow ? (
|
|
<span className="rounded bg-muted px-1.5 py-0.5">didn't know</span>
|
|
) : answer.correct ? (
|
|
<span className="rounded bg-green-500/15 px-1.5 py-0.5 text-green-500">correct</span>
|
|
) : (
|
|
<span className="rounded bg-red-500/15 px-1.5 py-0.5 text-red-500">incorrect</span>
|
|
))}
|
|
</div>
|
|
<div className="mb-3 font-medium">
|
|
<MessageResponse>{answer.questionText}</MessageResponse>
|
|
</div>
|
|
|
|
{((answer.options?.length ?? 0) > 0 || answer.other) && (
|
|
<div className="flex flex-col gap-1.5 text-sm">
|
|
{answer.options?.map((opt) => {
|
|
const sel = selectedIdx.has(opt.index);
|
|
const key = isQuiz && correctIdx.has(opt.index);
|
|
return (
|
|
<div
|
|
key={opt.index}
|
|
className={cn(
|
|
"flex items-center gap-2 rounded-lg border px-3 py-1.5",
|
|
sel && key && "border-green-500/60 bg-green-500/10",
|
|
sel && !key && isQuiz && "border-red-500/60 bg-red-500/10",
|
|
sel && !isQuiz && "border-primary bg-accent",
|
|
!sel && key && "border-green-500/40",
|
|
)}
|
|
>
|
|
{isQuiz && (
|
|
// Zapf-Dingbats-derived SVG outlines — the exact LaTeX \ding{51}/
|
|
// \ding{55} hand-drawn shapes (owner, round 6); see ui/glyph-mark.
|
|
<span
|
|
aria-hidden
|
|
data-mark={sel && key ? "check" : sel && !key ? "x" : !sel && key ? "check" : undefined}
|
|
className={cn(
|
|
"flex shrink-0 items-center",
|
|
sel && key && "text-green-500",
|
|
sel && !key && "text-red-500",
|
|
!sel && key && "text-green-500",
|
|
)}
|
|
>
|
|
{/* Owner round 8: a touch smaller than the text (size-4→size-3.5,
|
|
≈14px vs the 16px row) while centered. */}
|
|
{(key || sel) && <GlyphMark kind={key ? "check" : "x"} className="size-3.5" />}
|
|
</span>
|
|
)}
|
|
<span className={cn(!sel && "text-muted-foreground")}>
|
|
<MessageResponse>{opt.label}</MessageResponse>
|
|
</span>
|
|
</div>
|
|
);
|
|
})}
|
|
{/* The learner's own typed option is an OPTION — same container,
|
|
same selected styling as its siblings, not a loose quote
|
|
floating outside the list. Quotes keep the learner's words. */}
|
|
{answer.other && (
|
|
<div
|
|
data-testid="answered-other"
|
|
className="flex items-center gap-2 rounded-lg border border-primary bg-accent px-3 py-1.5"
|
|
>
|
|
<span>“{answer.other}”</span>
|
|
</div>
|
|
)}
|
|
</div>
|
|
)}
|
|
|
|
{answer.text && <div className="lh-prose mt-2 whitespace-pre-wrap">“{answer.text}”</div>}
|
|
{answer.dontKnow && (isQuiz || isExplain) && (
|
|
<div className="mt-2 text-sm text-muted-foreground">Answered “I don't know”.</div>
|
|
)}
|
|
|
|
{answer.note && (
|
|
<div data-testid="your-thinking" className="mt-3 border-l-2 border-primary/40 pl-3">
|
|
<span className="mb-0.5 block text-xs font-medium uppercase tracking-wide text-muted-foreground">
|
|
Your thinking
|
|
</span>
|
|
<span className="lh-prose block whitespace-pre-wrap text-foreground/90">{answer.note}</span>
|
|
</div>
|
|
)}
|
|
|
|
{/* px-3→removed: card p-4 + box px-3 double-inset sat the "Why" label deeper
|
|
than the option box edges (owner, round 3). Sides flush with everything
|
|
else; py-2 stays for vertical air. */}
|
|
{isQuiz && answer.explanation && (
|
|
<div className="mt-3 rounded-lg bg-muted py-2 text-sm text-muted-foreground">
|
|
<span className="font-medium text-foreground">Why: </span>
|
|
{/* The markdown wrapper must go truly inline — a block <p> after the
|
|
"Why:" label created the oversized leading gap (owner's fix list). */}
|
|
<MessageResponse className="inline [&_p]:inline [&_p]:m-0">{answer.explanation}</MessageResponse>
|
|
</div>
|
|
)}
|
|
{/* The explain reveal (owner ruling 2026-09-27): the committed answer
|
|
and its explanation, shown on submit — no verdict, the model's next
|
|
reply IS the grading. */}
|
|
{isExplain && (answer.committed || answer.explanation) && (
|
|
<div className="mt-3 rounded-lg bg-muted py-2 text-sm text-muted-foreground">
|
|
{answer.committed && (
|
|
<>
|
|
<span className="font-medium text-foreground">The answer: </span>
|
|
<MessageResponse className="inline [&_p]:inline [&_p]:m-0">{answer.committed}</MessageResponse>
|
|
</>
|
|
)}
|
|
{answer.committed && answer.explanation && <div className="my-1" />}
|
|
{answer.explanation && (
|
|
<>
|
|
<span className="font-medium text-foreground">Why: </span>
|
|
<MessageResponse className="inline [&_p]:inline [&_p]:m-0">{answer.explanation}</MessageResponse>
|
|
</>
|
|
)}
|
|
</div>
|
|
)}
|
|
</div>
|
|
);
|
|
}
|