Files
gstack/test/voice-directive.test.ts
T
e5dc011b7c voice: reply in the language of the user's latest message
Every skill's voice directive now tells the agent to reply in the language
of the user's latest message unless asked otherwise, so long English skill
text no longer drags a Chinese (or any non-English) session into English.
Mixed-language sessions follow the latest message. Code, commands, paths,
identifiers and quoted output stay verbatim, and at tier 2+ so do the
machine-read question markers (D<N>, option letters, (recommended)).

The rule costs 205 bytes per tier-2+ skill and 144 per tier-1 skill. A
further 25-byte cut to the bounded closer's exemption list leaves the net
for this wave at +17 bytes per tier-2+ skill and +158 per tier-1 skill.
review, qa and browse caps rise with measured notes; the ship goldens are
refreshed.

Co-authored-by: Xianying Tan <shrektan@126.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-10-08 15:10:10 +00:00

40 lines
2.2 KiB
TypeScript

import { describe, expect, test } from 'bun:test';
import { execFileSync } from 'node:child_process';
import { readFileSync } from 'node:fs';
import { join } from 'node:path';
import { generateVoiceDirective } from '../scripts/resolvers/preamble/generate-voice-directive';
import { HOST_PATHS, type TemplateContext } from '../scripts/resolvers/types';
import { between, expectMentions } from './helpers/prompt-structure';
const ctx: TemplateContext = { skillName: 'review', tmplPath: 'review/SKILL.md.tmpl', host: 'claude', paths: HOST_PATHS.claude };
const tiers: number[] = [1, 3];
describe('shared voice directive', () => {
test.each(tiers)('tier %i bans the load-bearing stock phrase on the AI-vocabulary line', tier => {
const banLine = generateVoiceDirective(ctx, tier).split('\n').find(line => line.includes('No AI vocabulary:'));
expect(banLine).toBeDefined();
expect(banLine!).toContain('load-bearing');
});
test.each(tiers)('tier %i replies in the language of the latest message and keeps technical text verbatim', tier => {
const voice = generateVoiceDirective(ctx, tier);
expectMentions(voice, [
['reply', 'language', "user's latest message", 'unless'],
['code', 'commands', 'paths', 'identifiers', 'quoted output', 'verbatim'],
], `tier ${tier} voice`);
if (tier >= 2) expectMentions(voice, [['question markers', '`D<N>`', 'option letters', '`(recommended)`', 'verbatim']], 'tier 3 voice');
});
test('every generated skill with a Voice section carries the reply-language rule', () => {
const root = join(import.meta.dir, '..');
const skills = execFileSync('git', ['ls-files', 'SKILL.md', '*/SKILL.md'], { cwd: root, encoding: 'utf8', timeout: 10_000 }).split('\n').filter(Boolean);
const voiced = skills.filter(file => readFileSync(join(root, file), 'utf8').includes('\n## Voice\n'));
expect(voiced.length).toBeGreaterThan(40);
const missing = voiced.filter(file => {
const voice = between(readFileSync(join(root, file), 'utf8'), '\n## Voice\n', /\n## /).toLowerCase();
return !(voice.includes('language') && voice.includes('latest message') && voice.includes('verbatim'));
});
expect(missing).toEqual([]);
});
});