free-recall explain tool: the quizzing-mechanic switch (owner 2026-09-27)
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.
This commit is contained in:
@@ -85,7 +85,9 @@ export function derivePlanStatuses(tree: PlanTree, messages: readonly PartsCarri
|
||||
// duplicates collapsed (several checks on one node = one stay on it)
|
||||
for (const m of messages) {
|
||||
for (const part of m.parts) {
|
||||
if (part.type !== "tool-quiz") continue;
|
||||
// Either quizzing tool (quiz/explain) tags position — the mechanic
|
||||
// is a settings switch; the fold recognizes both (owner 2026-09-27).
|
||||
if (part.type !== "tool-quiz" && part.type !== "tool-explain") continue;
|
||||
const nodeId = (part.input as { nodeId?: unknown } | undefined)?.nodeId;
|
||||
if (typeof nodeId !== "string" || !ids.has(nodeId)) continue; // untagged/unknown — moves nothing
|
||||
if (runs.at(-1) !== nodeId) runs.push(nodeId);
|
||||
@@ -130,7 +132,7 @@ export function derivePlanStatusesLh(tree: PlanTree, messages: readonly LhMessag
|
||||
const content = (m as { content?: unknown }).content;
|
||||
if (!Array.isArray(content)) continue;
|
||||
for (const block of content as Array<{ type?: string; name?: string; arguments?: unknown }>) {
|
||||
if (block.type !== "toolCall" || block.name !== "quiz") continue;
|
||||
if (block.type !== "toolCall" || (block.name !== "quiz" && block.name !== "explain")) continue;
|
||||
const nodeId = (block.arguments as { nodeId?: unknown } | undefined)?.nodeId;
|
||||
if (typeof nodeId !== "string" || !ids.has(nodeId)) continue;
|
||||
if (runs.at(-1) !== nodeId) runs.push(nodeId);
|
||||
|
||||
Reference in New Issue
Block a user