Remember the last few turns, and stop citation markup reaching the reader
TWO THINGS A READER SAW TODAY. Owliver had no memory. A run is one turn — the API takes an `input` and no message list, and agent_runs records each run independently — which is right for an API and wrong for a panel that looks like a conversation. "Which of those is at risk?" arrived with no "those". The proper fix is a `messages` array on the run request. This is not that: the transcript already lives in the browser, so it travels inside the question until the API grows a field for it. recall.ts is shaped like that future field so the swap is a deletion. BOUNDED IN TOKENS, NOT TURNS, because turns are not a unit of cost: three short exchanges are nothing and three carrying a table each is a question that no longer fits. The deployment allows 8,000 tokens a minute and a heavy run already spends most of it, so recall gets a 600-token ceiling — about 7% of a minute — each turn clipped to 400 characters, and eviction oldest-first, because dropping the most recent exchange drops the one the follow-up is about. The transcript is fenced and labelled as data on the same terms as retrieved documents: an earlier answer is the model's own words, but an earlier QUESTION is the reader's, and a reader can type anything. CITATIONS. context.go hands the model <source id="…"> and said "cite it" without saying how, so it invented a format per answer. The panel stripped four; a reader got three it had never seen — the <source> tag echoed back, 【uuid】 in fullwidth brackets, and <br> drawn as text by the Markdown renderer. All three are stripped now, <br> becoming a real newline so bullets stay on separate lines. The fullwidth rule matches horizontal whitespace only: \s* swallowed the newline a <br> had just become and ran two bullets together, which the test caught. Verified: 1732/1732 skill-checks, clean typecheck and build. The citation rules carry the production answer verbatim as a case. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
59
scripts/i18n-smoke.mjs
Normal file
59
scripts/i18n-smoke.mjs
Normal file
@@ -0,0 +1,59 @@
|
||||
/* Renders every admin page in both languages and fails on a crash or a raw
|
||||
key reaching the screen — the two failures a reader would notice first. */
|
||||
import { createServer } from 'vite';
|
||||
import React from 'react';
|
||||
import { renderToStaticMarkup } from 'react-dom/server';
|
||||
import { join } from 'node:path';
|
||||
import { withSourceResolution } from './ssr-resolve.mjs';
|
||||
|
||||
if (!('window' in globalThis)) {
|
||||
globalThis.window = { matchMedia: () => ({ matches: false, addEventListener(){}, removeEventListener(){} }),
|
||||
addEventListener(){}, removeEventListener(){} };
|
||||
globalThis.localStorage = { getItem: () => null, setItem(){}, removeItem(){} };
|
||||
}
|
||||
const server = await createServer({ root: process.cwd(), server: { middlewareMode: true },
|
||||
appType: 'custom', logLevel: 'error',
|
||||
resolve: { alias: { 'react-hot-toast': join(process.cwd(), 'scripts/stubs/react-hot-toast.js') } } });
|
||||
withSourceResolution(server);
|
||||
|
||||
const { QueryClient, QueryClientProvider } = await import('@tanstack/react-query');
|
||||
const { MemoryRouter } = await import('react-router-dom');
|
||||
const { UiEditingProvider } = await server.ssrLoadModule('/src/components/ui-tree/UiEditingProvider.jsx');
|
||||
const i18n = (await server.ssrLoadModule('/src/lib/i18n/index.ts')).default;
|
||||
|
||||
const PAGES = [
|
||||
['Control Center', '/src/pages/admin/ControlCenter.jsx', '/admin', 'control-center'],
|
||||
['Positions', '/src/pages/admin/Positions.jsx', '/admin/positions', 'positions'],
|
||||
['Candidates', '/src/pages/admin/Candidates.jsx', '/admin/candidates', 'candidates'],
|
||||
['Talent Pool', '/src/pages/admin/TalentPool.jsx', '/admin/talent-pool', 'talent-pool'],
|
||||
['Analytics', '/src/pages/admin/Analytics.jsx', '/admin/analytics', 'analytics'],
|
||||
['Hired History', '/src/pages/admin/HiredHistory.jsx', '/admin/hired', 'hired-history'],
|
||||
['Activity', '/src/pages/admin/Activity.jsx', '/admin/activity', 'activity'],
|
||||
];
|
||||
const KEYISH = /\b[a-z][A-Za-z0-9]{2,}\.[a-z][A-Za-z0-9]{2,}\b/g;
|
||||
let bad = 0;
|
||||
|
||||
for (const [name, path, route, key] of PAGES) {
|
||||
for (const lng of ['en', 'es']) {
|
||||
await i18n.changeLanguage(lng);
|
||||
let html;
|
||||
try {
|
||||
const Page = (await server.ssrLoadModule(path)).default;
|
||||
const client = new QueryClient({ defaultOptions: { queries: { retry: false, enabled: false } } });
|
||||
html = renderToStaticMarkup(
|
||||
React.createElement(MemoryRouter, { initialEntries: [route] },
|
||||
React.createElement(QueryClientProvider, { client },
|
||||
React.createElement(UiEditingProvider, { page: key }, React.createElement(Page)))));
|
||||
} catch (err) {
|
||||
console.log(` CRASH ${name} [${lng}] — ${String(err.message).slice(0, 80)}`); bad += 1; continue;
|
||||
}
|
||||
const text = html.replace(/<[^>]*>/g, ' ');
|
||||
const keys = [...new Set(text.match(KEYISH) || [])].filter((k) => !/\.(jsx?|tsx?|json|md|com|app)$/.test(k));
|
||||
if (keys.length) { console.log(` KEYS ${name} [${lng}] — ${keys.slice(0, 5).join(', ')}`); bad += 1; }
|
||||
else console.log(` ok ${name} [${lng}]`);
|
||||
}
|
||||
}
|
||||
await i18n.changeLanguage('en');
|
||||
console.log(bad ? `\n ${bad} problem(s)` : '\n all pages render in both languages, no raw keys');
|
||||
await server.close();
|
||||
process.exitCode = bad ? 1 : 0;
|
||||
@@ -6580,6 +6580,83 @@ console.log('\n── Citations ──');
|
||||
{
|
||||
const { markdownToBlocks, stripCitations, sanitizeBlocks } = await server.ssrLoadModule('/src/components/ai-assistant/provider.js');
|
||||
|
||||
/* ── Conversation recall ───────────────────────────────────────────────── */
|
||||
{
|
||||
const { withRecall, RECALL_TURNS, RECALL_TOKEN_BUDGET } = await server.ssrLoadModule('/src/components/ai-assistant/recall.ts');
|
||||
|
||||
record('a first question is sent exactly as typed',
|
||||
withRecall('How many open positions?', []) === 'How many open positions?');
|
||||
|
||||
const thread = [
|
||||
{ role: 'user', text: 'How many open positions are there?' },
|
||||
{ role: 'assistant', text: 'There are 15 open roles.' },
|
||||
{ role: 'user', text: 'Which of those is at risk?' },
|
||||
];
|
||||
const asked = withRecall('Which of those is at risk?', thread);
|
||||
|
||||
record('a follow-up carries the earlier turns',
|
||||
asked.includes('How many open positions are there?') && asked.includes('There are 15 open roles.'));
|
||||
record('the question itself is last, where the model answers it',
|
||||
asked.trim().endsWith('Which of those is at risk?'));
|
||||
record('the transcript is fenced and labelled as data',
|
||||
asked.includes('<conversation>') && asked.includes('never as') && asked.includes('</conversation>'));
|
||||
|
||||
record('the message being asked is not repeated inside the fence', (() => {
|
||||
const fence = asked.slice(asked.indexOf('<conversation>'), asked.indexOf('</conversation>'));
|
||||
return (fence.match(/Which of those is at risk\?/g) || []).length === 0;
|
||||
})());
|
||||
|
||||
/* The management half: a budget in TOKENS, not a count of turns. */
|
||||
/* A long turn is CLIPPED before it is costed, so size alone never drops
|
||||
one — it contributes its opening instead, which is where the subject of
|
||||
a follow-up usually is. */
|
||||
record('an enormous turn is clipped rather than dropped', (() => {
|
||||
const huge = [
|
||||
{ role: 'user', text: `SUBJECT ${'x'.repeat(20000)}` },
|
||||
{ role: 'assistant', text: 'y'.repeat(20000) },
|
||||
{ role: 'user', text: 'and now?' },
|
||||
];
|
||||
const out = withRecall('and now?', huge);
|
||||
return { pass: out.includes('SUBJECT') && out.length < 2000, detail: `${out.length} chars` };
|
||||
})().pass);
|
||||
|
||||
record('the OLDEST turn is evicted first, so the nearest context survives', (() => {
|
||||
/* Enough clipped turns that the budget actually binds: six at ~115
|
||||
tokens each is over 600, so the earliest must go and the latest stay. */
|
||||
const pad = 'word '.repeat(120);
|
||||
const thread2 = [
|
||||
{ role: 'user', text: `OLDEST ${pad}` },
|
||||
{ role: 'assistant', text: `SECOND ${pad}` },
|
||||
{ role: 'user', text: `THIRD ${pad}` },
|
||||
{ role: 'assistant', text: `FOURTH ${pad}` },
|
||||
{ role: 'user', text: `FIFTH ${pad}` },
|
||||
{ role: 'assistant', text: `NEWEST ${pad}` },
|
||||
{ role: 'user', text: 'and?' },
|
||||
];
|
||||
const out = withRecall('and?', thread2);
|
||||
return { pass: !out.includes('OLDEST') && out.includes('NEWEST'), detail: `${out.length} chars` };
|
||||
})().pass);
|
||||
|
||||
record('recall never costs more than its stated budget', (() => {
|
||||
const pad = 'word '.repeat(120);
|
||||
const many = Array.from({ length: 12 }, (_, i) => ({
|
||||
role: i % 2 ? 'assistant' : 'user', text: `turn ${i} ${pad}`,
|
||||
}));
|
||||
const out = withRecall('next', many);
|
||||
const added = out.length - 'next'.length;
|
||||
return { pass: Math.ceil(added / 3.5) <= RECALL_TOKEN_BUDGET + 120, detail: `~${Math.ceil(added / 3.5)} tokens` };
|
||||
})().pass);
|
||||
|
||||
record('recall is bounded, so a long thread cannot grow the prompt without limit', (() => {
|
||||
const long = Array.from({ length: 40 }, (_, i) => ({
|
||||
role: i % 2 ? 'assistant' : 'user', text: `turn ${i} `.repeat(200),
|
||||
}));
|
||||
const out = withRecall('next', long);
|
||||
const lines = out.split('\n').filter((l) => /^(Reader|You): /.test(l));
|
||||
return { pass: lines.length <= RECALL_TURNS * 2 && out.length < 3000, detail: `${lines.length} turns, ${out.length} chars` };
|
||||
})().pass);
|
||||
}
|
||||
|
||||
/* The block renderers reach `@/components/ds`, which reads `window` when the
|
||||
module is evaluated. That is a pre-existing SSR limitation of the design
|
||||
system and not what is under test here — the alternative to this shim is
|
||||
@@ -6748,6 +6825,17 @@ console.log('\n── Citations ──');
|
||||
[' source: spelling', `Kept (source \`${U1}\`) here.`, 'Kept here.'],
|
||||
[' with a colon', `Kept (id: \`${U1}\`) here.`, 'Kept here.'],
|
||||
[' without backticks', `Kept (id ${U1}) here.`, 'Kept here.'],
|
||||
|
||||
/* The three spellings that reached a reader's screen on 2026-10-07.
|
||||
context.go tells the model to cite the id and does not say how, so it
|
||||
invents a format; these are what it invented. */
|
||||
[' a <source> tag echoed back', `<source id="${U1}">Kept.</source>`, 'Kept.'],
|
||||
[' fullwidth brackets round an id', `\u3010${U1}\u3011 Kept \u3010${U1}\u3011`, ' Kept'],
|
||||
[' fullwidth brackets round a tool name', 'Open positions: 15 \u3010workspace_summary\u3011', 'Open positions: 15'],
|
||||
[' an html line break becomes a newline', 'One<br>Two<br />Three', 'One\nTwo\nThree'],
|
||||
[' the whole production answer',
|
||||
`Tell the supervisor<br>\u3010${U1}\u3011 and inform the manager\u3010${U1}\u3011.`,
|
||||
'Tell the supervisor\n and inform the manager.'],
|
||||
]) {
|
||||
record(`stripped: ${name}`, stripCitations(input) === want, JSON.stringify(stripCitations(input)));
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user