- src/agent/lh-tool.ts deleted: the zod-wrapped LhTool + toPiTool bridge (z.toJSONSchema per call, clientQuestion flag, hand-rolled result mapping) is gone. Tools are pi-agent-core native AgentTools now. - New src/agent/tool-execute.ts owns what the wrapper added: the abort guard (runWithAbortGuard: run signal + 30s per-call timeout + 250ms grace, 'Operation aborted' / timeout wording preserved), ToolInputError (the retryable '- problem at path' format), result mapping (string verbatim / object JSON / image parts, details rides the record's tool part output), and questionResult() — placeholder + terminate:true (owner Option A: belt of terminate + slim makeQuestionStopper with the clean-question rule; maxTurns deleted from the teaching turn entirely per owner). - All 11 tool files + tools.ts registries converted to TypeBox parameters (typebox@1.3.7, pinned to pi-agent-core's copy). zod refinements (quizInputProblems, askOptionProblems, live-nodeId) moved from schemas into execute — the model sees the same retryable error shape. - question-core + contracts/probe TypeBox-authored (single source shared with the UI); tool-parts parse seam runs the boundary's full chain (Convert → Check → Clean → refinement), fixing the live-smoke lockout: pi's boundary Value.Converts correctAnswer: 17 → '17' but the record keeps raw args, so a parse without Convert rejected a posed quiz (invisible pending question, turn ended). Pinned with the real smoke emission shape. - Subagents converted: demo-builder/researcher AgentTool-native, visual-maker/pdf-reader declaration-only pi-ai Tools with local execute fns, extraction submit schemas re-authored in TypeBox (owner option 2: zod defaults → Type.Optional + fill at the submit seam). - Accepted delta, flagged: TypeBox-native schemas skip pi's JSON-Schema primitive coercion fast path... (boundary still Value.Converts), and prober-quiz unknown keys ride through (Value.Clean strips at display). - Tests: 988 passing (was 967 at the recon baseline); tool-abort and read-tool rewritten against the native seams; question-core/question- tools/tool-parts/demos/web-search/graph-tools/plan-tree/probe-done/ tool-toggles converted to Value.Check/execute pins. Live smoke (PORT=3004, real model): native ls turn streams end-to-end; a real quiz pose (first attempt missing correctAnswer → tool-input-error → model retry → posed) terminates the turn cleanly and persists pending.
155 lines
6.6 KiB
TypeScript
155 lines
6.6 KiB
TypeScript
/**
|
||
* Unit tests — the UI parse seam (src/core/tool-parts.ts).
|
||
*
|
||
* The rule born of the 2026-09-12 live crashes: model-authored tool input
|
||
* is consumed only through these parsers, each running the SAME zod schema
|
||
* the model faced at the boundary. These pins hold the two exact live
|
||
* crash shapes (the model's double-encoding habit) and the boundary-parity
|
||
* property: anything a boundary schema accepts, the display parse accepts.
|
||
*/
|
||
|
||
import assert from "node:assert/strict";
|
||
import { describe, it } from "node:test";
|
||
import { quizInputProblems } from "../src/core/question-core.ts";
|
||
import { Value } from "typebox/value";
|
||
import {
|
||
parseAskInput,
|
||
parseProbeDoneInput,
|
||
parseQuizInput,
|
||
} from "../src/core/tool-parts.ts";
|
||
import { quizInputSchema, probeQuizInputSchema } from "../src/core/question-core.ts";
|
||
import { probeDoneInputSchema } from "../src/core/contracts/probe.ts";
|
||
|
||
const TEACHER_QUIZ = {
|
||
question: "What does Tarski's convention-T define?",
|
||
options: [
|
||
{ label: "Truth for a language", value: "truth" },
|
||
{ label: "Provability", value: "provability" },
|
||
],
|
||
correctAnswer: "truth",
|
||
explanation: "Convention-T schematizes truth for the object language.",
|
||
nodeId: "convention-t", // teacher-only field — the display parse must accept and strip it
|
||
};
|
||
|
||
const PROBER_QUIZ = {
|
||
question: "Which planet is closest to the sun?",
|
||
options: [{ label: "Venus" }, { label: "Mercury" }],
|
||
correctAnswer: "Mercury",
|
||
explanation: "Mercury is the innermost planet.",
|
||
};
|
||
|
||
const VALID_ASSESSMENT = {
|
||
assessment: {
|
||
strands: [
|
||
{ strand: "modal logic basics", assessment: "Floor: solid intuition; ceiling: notation." },
|
||
{ strand: "indexical 'actual'", assessment: "Genuine floor — prior exposure likely." },
|
||
],
|
||
summary: "Bracketed: teach the symbols on the intuition he has.",
|
||
},
|
||
};
|
||
|
||
describe("parseQuizInput", () => {
|
||
it("parses a boundary-valid TEACHER quiz and strips the teacher-only nodeId", () => {
|
||
const parsed = parseQuizInput(TEACHER_QUIZ);
|
||
assert.ok(parsed);
|
||
assert.equal(parsed.question, TEACHER_QUIZ.question);
|
||
assert.equal((parsed as Record<string, unknown>).nodeId, undefined, "unknown keys are stripped, not trusted");
|
||
});
|
||
|
||
it("parses a boundary-valid PROBER quiz (no nodeId at all)", () => {
|
||
assert.ok(parseQuizInput(PROBER_QUIZ));
|
||
});
|
||
|
||
it("boundary parity: anything the TEACH schema accepts, the display parse accepts", () => {
|
||
assert.ok(Value.Check(quizInputSchema, TEACHER_QUIZ), "fixture must be boundary-valid for this pin to mean anything");
|
||
assert.ok(parseQuizInput(TEACHER_QUIZ));
|
||
});
|
||
|
||
it("boundary parity: anything the PROBE schema accepts, the display parse accepts", () => {
|
||
assert.ok(Value.Check(probeQuizInputSchema, PROBER_QUIZ));
|
||
assert.ok(parseQuizInput(PROBER_QUIZ));
|
||
});
|
||
|
||
it("the live crash shape — options as a JSON string — does not parse", () => {
|
||
const stringified = { ...PROBER_QUIZ, options: JSON.stringify(PROBER_QUIZ.options) };
|
||
assert.equal(parseQuizInput(stringified), undefined);
|
||
});
|
||
|
||
it("boundary parity under Value.Convert: a NUMERIC correctAnswer parses (live-smoke lockout fix, 2026-09-26)", () => {
|
||
// The live smoke's model emitted correctAnswer: 17 (number). pi's
|
||
// boundary runs Value.Convert before Value.Check, so the quiz posed
|
||
// — but the record keeps the RAW args. A parse seam without Convert
|
||
// would reject exactly what the boundary accepted: the pending quiz
|
||
// renders nowhere while the turn has ended = learner lockout.
|
||
// Dock-visible parity case: the smoke's real emission — options whose
|
||
// values ARE the numbers, correctAnswer numeric. Convert → "17",
|
||
// refinement passes (it matches an option), the quiz parses.
|
||
const numeric = {
|
||
question: "What is 5 + 3 × 4?",
|
||
options: [
|
||
{ label: "17", value: "17" },
|
||
{ label: "27", value: "27" },
|
||
{ label: "9", value: "9" },
|
||
],
|
||
explanation: "Multiplication first.",
|
||
correctAnswer: 17,
|
||
};
|
||
const parsed = parseQuizInput(numeric);
|
||
assert.ok(parsed);
|
||
assert.equal(parsed.correctAnswer, "17", "converted to the string the boundary saw");
|
||
const numericArray = { ...numeric, multiSelect: true, correctAnswer: [17, "27"] };
|
||
const parsedArray = parseQuizInput(numericArray);
|
||
assert.ok(parsedArray);
|
||
assert.deepEqual(parsedArray.correctAnswer, ["17", "27"]);
|
||
// Non-convertible garbage still never parses (structure owns it)…
|
||
assert.equal(parseQuizInput({ ...PROBER_QUIZ, correctAnswer: { bad: true } }), undefined);
|
||
// …and Convert's widening (undefined → "") is caught by the refinement
|
||
// chain the boundary itself uses — garbage renders as a quiet fallback.
|
||
const widened = { ...PROBER_QUIZ, correctAnswer: undefined };
|
||
assert.equal(parseQuizInput(widened), undefined, "the refinement owns the reject");
|
||
});
|
||
|
||
it("garbage never parses: non-object, missing question, missing correctAnswer", () => {
|
||
assert.equal(parseQuizInput("a string"), undefined);
|
||
assert.equal(parseQuizInput({ options: [] }), undefined);
|
||
assert.equal(parseQuizInput({ ...PROBER_QUIZ, correctAnswer: undefined }), undefined);
|
||
});
|
||
});
|
||
|
||
describe("parseAskInput", () => {
|
||
it("parses free-text mode (no options) and option mode", () => {
|
||
assert.ok(parseAskInput({ question: "What do you want to learn?" }));
|
||
assert.ok(parseAskInput({ question: "Which topics?", options: [{ label: "Physics" }, { label: "Logic" }], multiSelect: true }));
|
||
});
|
||
|
||
it("the live crash shape — stringified options — does not parse", () => {
|
||
assert.equal(parseAskInput({ question: "q", options: "[]" }), undefined);
|
||
});
|
||
});
|
||
|
||
describe("parseProbeDoneInput", () => {
|
||
it("parses the valid assessment", () => {
|
||
const parsed = parseProbeDoneInput(VALID_ASSESSMENT);
|
||
assert.ok(parsed);
|
||
assert.equal(parsed.assessment.strands.length, 2);
|
||
assert.equal(parsed.assessment.summary, "Bracketed: teach the symbols on the intuition he has.");
|
||
});
|
||
|
||
it("boundary parity: anything the tool schema accepts, the display parse accepts", () => {
|
||
assert.ok(Value.Check(probeDoneInputSchema, VALID_ASSESSMENT));
|
||
assert.ok(parseProbeDoneInput(VALID_ASSESSMENT));
|
||
});
|
||
|
||
it("the live crash shape — assessment STRINGIFIED — does not parse", () => {
|
||
// The exact double-encoding from the modal-realism run: strands died
|
||
// on `.map` because the card cast the shape. The parse kills the class.
|
||
const stringified = { assessment: JSON.stringify(VALID_ASSESSMENT.assessment) };
|
||
assert.equal(parseProbeDoneInput(stringified), undefined);
|
||
const garbage = JSON.stringify(VALID_ASSESSMENT.assessment).slice(0, 30);
|
||
assert.equal(parseProbeDoneInput(garbage), undefined);
|
||
});
|
||
|
||
it("a mid-stream partial (no strands yet) does not parse", () => {
|
||
assert.equal(parseProbeDoneInput({ assessment: { summary: "…" } }), undefined);
|
||
});
|
||
}); |