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.
145 lines
6.6 KiB
TypeScript
145 lines
6.6 KiB
TypeScript
/**
|
|
* Plan-tree contracts — the session-scoped dependency tree
|
|
*
|
|
* Part of the domain-split contracts (src/core/contracts/): each domain file
|
|
* is owned outright by its stream — cross-domain schema changes go through
|
|
* master. Pure types + protocol docs + tiny pure helpers; type-only imports
|
|
* of "ai" (safe everywhere: server, client, tests). See docs/vision.md.
|
|
*/
|
|
// ─── Plan tree (vision §2 "formal plan tree") ────────────────────────────────
|
|
// A session-scoped dependency tree authored by the teacher via plan tools.
|
|
// One substrate with the global graph: tree nodes fold into graph nodes.
|
|
|
|
export interface PlanNode {
|
|
/** Opaque, agent-chosen slug, stable across edits: "chain-rule-intuition". */
|
|
id: string;
|
|
/** Short label for the tree panel. */
|
|
title: string;
|
|
/** 1-2 sentences: what this node covers. */
|
|
summary?: string;
|
|
}
|
|
|
|
export interface PlanEdge {
|
|
/** Prerequisite node id. */
|
|
from: string;
|
|
/** Node that depends on `from`. */
|
|
to: string;
|
|
}
|
|
|
|
export interface PlanTree {
|
|
nodes: PlanNode[];
|
|
edges: PlanEdge[];
|
|
/** Increments on every mutation — lets the UI animate/react to changes. */
|
|
version: number;
|
|
}
|
|
|
|
// NOTE (2026-09-11 pivot, docs/probe-teach-split.md): the tree once carried
|
|
// `currentNodeId` / `doneNodeIds` — progress fields. They are GONE by
|
|
// design: the tree carries structure ONLY; position and visited-ness derive
|
|
// from the transcript at render time (derivePlanStatuses below). There is no
|
|
// done ledger of any kind. No backwards compatibility for old records.
|
|
|
|
/** Derived, never stored: status of a node for the panel (vision §2). */
|
|
export type PlanNodeStatus = "current" | "visited" | "upcoming";
|
|
|
|
// ─── derived statuses: position from CALLS, never from results ─────────────
|
|
//
|
|
// (2026-09-11 pivot — docs/probe-teach-split.md §3.) The teacher AUTHORS the
|
|
// map (plan_init, mermaid — re-callable rewrite) and never tracks progress.
|
|
// The quiz `nodeId` means "this question is ABOUT this node" — a position
|
|
// signal, never a completion signal. Derivation reads CALLS only:
|
|
// current — the node of the most RECENT tagged quiz call (any state)
|
|
// visited — every node referenced by an EARLIER tagged call
|
|
// Consequences: a node spans multiple turns/checks naturally (several
|
|
// questions may tag the same node — the map holds still); moving to a new
|
|
// node is the teacher's judgment the previous one is finished, regardless of
|
|
// check outcomes (a failed check then a move-on is still visited); results
|
|
// feed nothing; there is NO fallback current (before the first tagged check
|
|
// nothing is current). Untagged checks no longer exist (nodeId is required
|
|
// on the teach quiz, owner ruling 2026-09-26). NodeIds missing from the
|
|
// current tree are ignored (a rewrite may have dropped the node).
|
|
|
|
/** Minimal structural message slice — anything with typed parts (mirrors
|
|
* phases.ts: pure, no runtime deps, safe on server, client, and in tests). */
|
|
interface PartsCarrier {
|
|
parts: Array<{ type: string; state?: string; input?: unknown; output?: unknown }>;
|
|
}
|
|
|
|
export interface DerivedPlanStatuses {
|
|
/** The node the most recent tagged quiz call is about; null before any. */
|
|
current: string | null;
|
|
/** Nodes referenced by earlier tagged calls — been there, monotonic. */
|
|
visited: ReadonlySet<string>;
|
|
}
|
|
|
|
/** Statuses of a node: the derived view the plan panel should render. */
|
|
export function derivedNodeStatus(statuses: DerivedPlanStatuses, nodeId: string): PlanNodeStatus {
|
|
if (statuses.current === nodeId) return "current";
|
|
if (statuses.visited.has(nodeId)) return "visited";
|
|
return "upcoming";
|
|
}
|
|
|
|
export function derivePlanStatuses(tree: PlanTree, messages: readonly PartsCarrier[]): DerivedPlanStatuses {
|
|
const ids = new Set(tree.nodes.map((n) => n.id));
|
|
const runs: string[] = []; // distinct tagged nodes in call order, CONSECUTIVE
|
|
// duplicates collapsed (several checks on one node = one stay on it)
|
|
for (const m of messages) {
|
|
for (const part of m.parts) {
|
|
// 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);
|
|
}
|
|
}
|
|
const current = runs.at(-1) ?? null;
|
|
// Visited = been there in an EARLIER stay: everything before the current
|
|
// run. A revisit (a→b→a) puts a in visited AND current — current wins at
|
|
// render (derivedNodeStatus), visited records it has been left before.
|
|
const visited = new Set(runs.slice(0, -1));
|
|
return { current, visited };
|
|
}
|
|
|
|
/**
|
|
* The plan tool result (author-once protocol, 2026-09-03): ONE server-side
|
|
* tool, plan_init (tools/plan.ts) — a mermaid `graph TD` block canonicalized
|
|
* into the structured tree, called once at the probe→teach seam and
|
|
* re-callable to rewrite. The former mutation/tracking tools are gone:
|
|
* statuses derive from check outcomes (derivePlanStatuses above), so the
|
|
* tree carries structure, never progress. The tree panel still derives its
|
|
* display from the LATEST plan tool output in the transcript — plus the
|
|
* derived statuses — with no separate state channel.
|
|
*/
|
|
export interface PlanToolResult {
|
|
ok: boolean;
|
|
error?: string;
|
|
tree: PlanTree;
|
|
}
|
|
|
|
|
|
// ─── the native fold (Wave D: derivePlanStatuses over LhMessage[]) ───────────
|
|
|
|
import type { LhMessage } from "../native-messages.ts";
|
|
|
|
/** The same derivation over the NATIVE record: quiz CALLS only (any state —
|
|
* a dangling call still moves position; results feed nothing). */
|
|
export function derivePlanStatusesLh(tree: PlanTree, messages: readonly LhMessage[]): DerivedPlanStatuses {
|
|
const ids = new Set(tree.nodes.map((n) => n.id));
|
|
const runs: string[] = [];
|
|
for (const m of messages) {
|
|
if ((m as { role?: string }).role !== "assistant") continue;
|
|
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" && 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);
|
|
}
|
|
}
|
|
const current = runs.at(-1) ?? null;
|
|
const visited = new Set(runs.slice(0, -1));
|
|
return { current, visited };
|
|
}
|