timmy-talking-turd/tests/grounded-chat.test.js

import test from 'node:test';
import assert from 'node:assert/strict';

import { answerFromLedger, buildChatLedger, resolveAgentReply } from '../src/grounded-chat.js';

const DAY = 86400000;
const NOW = Date.parse('2026-09-20T12:00:00.000Z');
const entry = (id, daysAgo, bristolType, extra = {}) => ({
  id,
  occurredAt: new Date(NOW - daysAgo * DAY).toISOString(),
  bristolType,
  color: 'brown',
  urgency: 1,
  discomfort: 1,
  note: '',
  photoDataUrl: '',
  symptoms: {},
  ...extra,
});

test('a frequency question answers with the count from the window and cites exactly those logs', () => {
  const answer = answerFromLedger(
    'How many times have I logged in the last four weeks?',
    [entry('a', 2, 4), entry('b', 5, 3), entry('c', 9, 6), entry('d', 12, 4), entry('old', 40, 2)],
    { now: NOW },
  );

  assert.equal(answer.kind, 'frequency');
  assert.equal(answer.grounded, true);
  assert.match(answer.text, /4 confirmed logs/);
  assert.match(answer.text, /last 28 days/);
  assert.deepEqual(answer.citations.map(citation => citation.id).sort(), ['a', 'b', 'c', 'd']);
  // The out-of-window log is never counted and never offered as a source.
  assert.equal(answer.citations.some(citation => citation.id === 'old'), false);
});

test('a recency question cites the one log it names, even when the ledger is out of order', () => {
  const answer = answerFromLedger(
    'When did I last log something?',
    [entry('middle', 6, 5), entry('newest', 1, 3), entry('older', 11, 2)],
    { now: NOW },
  );

  assert.equal(answer.kind, 'latest');
  assert.equal(answer.grounded, true);
  assert.equal(answer.citations.length, 1);
  assert.equal(answer.citations[0].id, 'newest');
  assert.equal(answer.citations[0].bristolType, 3);
  assert.match(answer.text, /most recent confirmed log/i);
  assert.match(answer.text, /Type 3/);
});

test('a question the journal cannot answer refuses instead of reassuring', () => {
  const answer = answerFromLedger(
    'Is it safe to eat tacos with this?',
    [entry('a', 2, 4), entry('b', 5, 3), entry('c', 9, 6)],
    { now: NOW },
  );

  assert.equal(answer.kind, 'unsupported');
  assert.equal(answer.grounded, false);
  assert.deepEqual(answer.citations, []);
  assert.match(answer.text, /cannot (clear|decide|tell)/i);
  // Boundary copy may not invent a verdict about health or food.
  assert.doesNotMatch(answer.text, /safe to eat|it is fine|you should eat|diagnos/i);
});

test('a pattern question on a sparse window refuses to describe a trend', () => {
  const answer = answerFromLedger(
    'What pattern do you see?',
    [entry('a', 2, 4), entry('b', 5, 6)],
    { now: NOW },
  );

  assert.equal(answer.kind, 'insufficient');
  assert.equal(answer.grounded, false);
  assert.deepEqual(answer.citations, []);
  assert.match(answer.text, /not enough confirmed logs/i);
  assert.match(answer.text, /2 of 3/);
});

test('a pattern question cites every confirmed log the described pattern rests on', () => {
  const answer = answerFromLedger(
    'What pattern do you see?',
    [entry('a', 2, 1), entry('b', 5, 4), entry('c', 9, 4), entry('d', 12, 4)],
    { now: NOW },
  );

  assert.equal(answer.kind, 'pattern');
  assert.equal(answer.grounded, true);
  assert.match(answer.text, /4 confirmed logs/);
  assert.match(answer.text, /Firm side \(Type 1–2\): 1 of 4/);
  assert.deepEqual(answer.citations.map(citation => citation.id).sort(), ['a', 'b', 'c', 'd']);
});

test('a Hermes reply resolves the record references it cites and never shows the raw marker', () => {
  const { chatRecords } = buildChatLedger([entry('a', 2, 4), entry('b', 5, 3)], { now: NOW });

  const resolved = resolveAgentReply(
    'Your newest Type 4 log is the one from this week [entry:L1], and the Type 3 before it [entry:L2].',
    chatRecords,
  );

  assert.equal(resolved.text.includes('[entry:'), false);
  assert.match(resolved.text, /newest Type 4 log/);
  assert.deepEqual(resolved.citations.map(citation => citation.id), ['a', 'b']);
  assert.equal(resolved.unverified, false);
});

test('a citation to a record that is not in the ledger is dropped instead of being shown as a source', () => {
  const { chatRecords } = buildChatLedger([entry('a', 2, 4)], { now: NOW });

  const resolved = resolveAgentReply('You had 9 logs last month [entry:L99].', chatRecords);

  assert.equal(resolved.text.includes('[entry:'), false);
  assert.deepEqual(resolved.citations, []);
  assert.equal(resolved.unresolvedRefs, 1);
  assert.equal(resolved.unverified, true);
});

test('an uncited claim about the journal is flagged as unverified rather than presented as fact', () => {
  const { chatRecords } = buildChatLedger([entry('a', 2, 4), entry('b', 5, 3)], { now: NOW });

  const resolved = resolveAgentReply('You logged 7 times this week and you are improving.', chatRecords);

  assert.equal(resolved.unverified, true);
  assert.deepEqual(resolved.citations, []);
  assert.match(resolved.notice, /not verified against your journal/i);
});

test('a privacy question answers with the stored-data boundary instead of the journal summary', () => {
  const answer = answerFromLedger('What happens to my photo?', [entry('a', 2, 4), entry('b', 5, 3), entry('c', 9, 6)], { now: NOW });

  assert.equal(answer.kind, 'privacy');
  assert.equal(answer.grounded, false);
  assert.deepEqual(answer.citations, []);
  assert.match(answer.text, /browser/i);
  assert.match(answer.text, /never receives photos/i);
});

test('an unmatched question still gets a grounded answer instead of an empty bubble', () => {
  const answer = answerFromLedger('hello', [entry('a', 2, 4), entry('b', 5, 3), entry('c', 9, 6)], { now: NOW });

  assert.equal(answer.kind, 'summary');
  assert.equal(answer.grounded, true);
  assert.ok(answer.text.length > 20, 'a general question must not produce an empty reply');
  assert.equal(answer.citations.length, 3);

  const empty = answerFromLedger('hello', [], { now: NOW });
  assert.equal(empty.grounded, false);
  assert.deepEqual(empty.citations, []);
  assert.match(empty.text, /no confirmed logs|not enough/i);
});