Files
learnharness/src/core/pending.ts
T
amosblomqvist 1f41fb05a5 question tools: phase-visible names, hardened teach schemas, context-slim seams
The tools_fails_2 diagnosis (glm-5.3 dropping trailing required fields):
- probe-phase quiz/explain renamed to probe/recall — a shared name carried
  the probe call shape into teaching (the first teach quiz dropped nodeId);
  display seams accept the old names forever
- teach quiz+explain schemas lead with the required pair (type, nodeId);
  explain gains the predict/check type and joins the reveal law (checks
  collapse, predictions arrive open; no-type records render check-style)
- plan_init/probe_done results go context-slim (owner, context diet):
  content = validated nodeIds + binding-id reminder / fixed ack; details
  keeps the tree for the popup and {ok:true} — serializer-verified that
  details never reaches the model; failure echoes dropped
- the cards carry the tool's own name (Probe/Recall) and the quiz type
  reads on the label (Prediction/Check) in composer and transcript
2026-10-09 07:59:23 +03:00

175 lines
7.6 KiB
TypeScript

/**
* Wave D: these scans read VIEW messages (core/view.ts LhViewMessage — the
* client's grouped transcript). The part shapes are the same vocabulary the
* pre-Wave-D client dialect used; a tool part is structural: `tool-` prefix +
* toolCallId. The server-side record scans (danglingQuestionOf over native
* LhMessage[]) live in native-messages.ts.
*/
interface UIMessage {
role?: string;
parts: Array<Record<string, unknown> & { type: string }>;
}
function isToolUIPart(part: UIMessage["parts"][number]): boolean {
return part.type.startsWith("tool-") && typeof part.toolCallId === "string";
}
/**
* The pending-question gate: an unanswered QUESTION tool part (quiz/ask)
* blocks the composer — one question at a time, mirroring the teacher's
* prompt contract. Derived client state; the server enforces nothing.
*
* Scan order: MESSAGES newest-first (a later turn's live question supersedes
* an older dangling one), but PARTS forward within a message — the model's
* FIRST unanswered question is the dock subject. Parallel question calls
* (pi executes them in one batch) are thus answered in the same order they
* were asked, saved, and rendered as cards; a backward part scan reversed
* that order (the live modal-realism observation).
*
* Job tool parts (research/demo/visual) never pend client-side — the async
* protocol resolves them server-side with an immediate ack (see
* contracts/jobs.ts "THE ASYNC PROTOCOL"), so job tools are NOT returned
* here. This file carries only the question gate and the shared scan helper.
*/
export interface PendingToolCall {
toolCallId: string;
tool: string;
/** Tool input (quiz/ask args) — lets the composer pick note vs answer mode. */
input: unknown;
}
/** Tools that render in the question dock and gate the composer. The
* probe-phase names (probe/recall, owner 2026-10-09) join their teach
* twins — old records keep the teach names; new probe-phase calls carry
* the phase names. */
export const QUESTION_TOOLS = [
"quiz",
"probe",
"ask_user_question",
"explain",
"recall",
] as const;
/** The tool→kind map (the dock's own fold, named once — the dismissal
* path and the dock must never disagree on what a tool is). The probe
* names fold onto their teach kinds — the dock is kind-driven. */
export function toolQuestionKind(tool: string): "quiz" | "ask" | "explain" {
return tool === "quiz" || tool === "probe" ? "quiz" : tool === "explain" || tool === "recall" ? "explain" : "ask";
}
/** Tools fulfilled by background sub-agent jobs (W2/W6). */
export const JOB_TOOLS = ["research", "demo", "visual"] as const;
// ─── Tool availability (2026-09 settings seam) ─────────────────────────────
/** The tools a user may toggle off in settings — THE DEFINITIVE LIST
* (adjudicated 2026-09-19, P2 reconciliation: the sub-agent JOB tools
* only — research/demo/visual/pdf). Deliberately NOT toggleable, ever:
* quiz + ask_user_question (the prober's flow is graded-quiz brackets →
* probe_done; quiz-off would collapse the assessment and teaching
* doctrine is built on graded verification — the wedge danger), the
* learner-filesystem set (user-decided 2026-09, sources v1: always-on),
* plan tools, and probe_done (it is how the phase ENDS — a prober that
* can never conclude is a lockout).
* The write side validates against this list (settings-body.ts: unknown
* key = 400 with the supported list); the read-side sanitizer stays
* lenient for forward-compat. The names are the MODEL-FACING tool names
* (research, not researcher; pdf is the PDF-reader dispatch, sources v0
* 2026-09). */
export const TOGGLEABLE_TOOLS = ["research", "demo", "visual", "pdf"] as const;
/** The keys the settings WRITE side accepts in agent.tools: the plain
* toggleables PLUS the quizzing-mechanics switch (`explain: true` arms
* free-recall quizzing and drops the MC quiz — see quizMechanics in
* agent/tools.ts; owner 2026-09-27). `quiz` itself stays unwritable:
* mechanics-managed, never individually toggleable. */
export const WRITABLE_TOOL_KEYS = [...TOGGLEABLE_TOOLS, "explain"] as const;
/** The resolved settings → factory seam shape (Platform wires chat-handler
* to pass this through from the settings record; storage and defaults are
* Platform's lane). JSON-native: a partial record keyed by tool name.
* Absent key / undefined = enabled — old records behave exactly as today.
* Any explicit `false` removes that tool from the registry, whatever its
* name — the machinery stays generic for future toggleables. */
export type EnabledTools = Partial<Record<string, boolean>>;
/** Drop every tool the resolved settings mark as disabled. The single
* filtering site every factory shares (prober/teacher). */
export function filterEnabledTools<T>(tools: Record<string, T>, enabled?: EnabledTools): Record<string, T> {
if (!enabled) return tools;
const out: Record<string, T> = {};
for (const [name, tool] of Object.entries(tools)) {
if (enabled[name] === false) continue;
out[name] = tool;
}
return out;
}
function findPending(messages: UIMessage[], names: readonly string[]): PendingToolCall | null {
for (let m = messages.length - 1; m >= 0; m--) {
const msg = messages[m]!;
for (let p = 0; p < msg.parts.length; p++) {
const part = msg.parts[p]!;
if (isToolUIPart(part) && part.state === "input-available") {
const tool = part.type.slice("tool-".length);
if (names.includes(tool)) {
return { toolCallId: part.toolCallId as string, tool, input: part.input };
}
}
}
}
return null;
}
export function findPendingToolCall(messages: UIMessage[]): PendingToolCall | null {
return findPending(messages, QUESTION_TOOLS);
}
// ─── Turn activity label (2026-09-19, the “Writing a question…” fix) ──────
/**
* The transcript's turn-activity shimmer text: what the teacher is
* doing RIGHT NOW. A tool part sits in `input-streaming` for its whole
* execution (the bridge defers `tool-input-available` to
* tool_execution_end — the invalid-input gate for the question dock), so
* keying the old “Writing a question…” shimmer on ANY streaming tool
* part mislabeled minutes-long local greps as question-writing. The label
* now names the actual activity; chat.tsx gates it on `!pending` and
* renders it as the quiet transcript shimmer.
*/
const ACTIVITY_LABELS: Record<string, string> = {
read: "Reading a file…",
ls: "Listing a directory…",
find: "Finding files…",
grep: "Searching file contents…",
research: "Dispatching research…",
demo: "Building a demo…",
visual: "Making a visual…",
pdf: "Reading a PDF…",
plan_init: "Drawing up the plan…",
probe_done: "Concluding the assessment…",
};
/** The activity label for ONE running tool (owner, streaming round
* 2026-10-01): the live tool-input card carries it inline — spinner +
* shimmered label on the card itself, replacing the retired transcript
* bottom line. Question tools are excluded here: their input-streaming
* part renders in the dock, never a live card. */
export function toolActivityLabel(tool: string): string {
if ((QUESTION_TOOLS as readonly string[]).includes(tool)) return "Writing a question…";
return ACTIVITY_LABELS[tool] ?? "Working…";
}
export function streamingToolActivity(messages: UIMessage[]): string | null {
const last = messages.at(-1);
if (!last || last.role !== "assistant") return null;
for (const part of last.parts) {
if (isToolUIPart(part) && part.state === "input-streaming") {
return toolActivityLabel(part.type.slice("tool-".length));
}
}
return null;
}