Files
gstack/test/writing-style-resolver.test.ts
T
Garry Tan 16b80100c6 test: align unit tests with slim resolvers + exempt 27MB security fixture
- test/skill-validation.test.ts: assert the slim Completeness Principle
  shape (Completeness: X/10, kind-note language) instead of the old
  Compression table. Remove the 3 tier-1 skills from the spot-check list
  (they intentionally don't carry the full Completeness Principle
  section). Exempt browse/test/fixtures/security-bench-haiku-responses.json
  (27MB deterministic replay fixture for BrowseSafe-Bench) from the 2MB
  tracked-file gate. The gate was actually failing on origin/main since
  the fixture was added in v1.6.4.0 — this is a side-fix to a real
  regression.

- test/brain-sync.test.ts: developer-machine-safe assertion for
  GSTACK_HOME override (compare config contents before/after instead of
  asserting the absence of a string that may legitimately exist).

- test/gen-skill-docs.test.ts: new tests for the slim — plan-review
  preambles stay under the post-slim budget (~33KB), Voice + Writing
  Style sections stay compact, and the slim Voice section preserves the
  load-bearing semantic contract (lead-with-the-point, name-the-file,
  user-outcome framing, no-corporate, no-AI-vocab, user-sovereignty).
  Update path-leakage scan to allow repo-root sidecar symlinks.

- test/writing-style-resolver.test.ts: assert the compact contract
  (gloss-on-first-use, outcome-framing, user-impact, terse-mode override)
  instead of the old 6-numbered-rules shape.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-25 21:24:12 -07:00

93 lines
3.8 KiB
TypeScript

/**
* Writing Style preamble section — gate-tier assertions on generated prose.
*
* These tests assert the V1 Writing Style section is properly composed into
* tier-≥2 preamble output, in both Claude and Codex host outputs. Since the
* block itself is prose the agent obeys at runtime, we can't test the agent's
* compliance here — that's the periodic LLM-judge E2E test (to-be-added).
*
* What this test enforces:
* - Writing Style section header present in tier-≥2 generated preamble
* - Compact semantic contract present (gloss, outcome, impact, override)
* - Jargon list inlined (sample terms appear)
* - Terse-mode gate condition text present
* - Codex output uses $GSTACK_BIN, not ~/.claude/... (host-aware paths)
* - Tier-1 preamble does NOT include Writing Style section
*/
import { describe, test, expect } from 'bun:test';
import type { TemplateContext } from '../scripts/resolvers/types';
import { HOST_PATHS } from '../scripts/resolvers/types';
import { generatePreamble } from '../scripts/resolvers/preamble';
function makeCtx(host: 'claude' | 'codex', tier: 1 | 2 | 3 | 4): TemplateContext {
return {
skillName: 'test-skill',
tmplPath: 'test.tmpl',
host,
paths: HOST_PATHS[host],
preambleTier: tier,
};
}
describe('Writing Style preamble section', () => {
test('tier 2+ Claude preamble includes Writing Style header', () => {
const out = generatePreamble(makeCtx('claude', 2));
expect(out).toContain('## Writing Style');
});
test('tier 2+ preamble includes EXPLAIN_LEVEL echo in bash', () => {
const out = generatePreamble(makeCtx('claude', 2));
expect(out).toContain('_EXPLAIN_LEVEL');
expect(out).toContain('EXPLAIN_LEVEL:');
});
test('tier 2+ preamble includes the compact writing-style contract', () => {
const out = generatePreamble(makeCtx('claude', 2));
expect(out).toMatch(/gloss.*first use|first-use.*gloss/i);
expect(out).toMatch(/outcome/i);
expect(out).toMatch(/user impact|user.*experience|what.*user.*sees/i);
expect(out).toMatch(/terse|no explanations|user-turn override|current message/i);
});
test('tier 2+ preamble inlines jargon list', () => {
const out = generatePreamble(makeCtx('claude', 2));
// Spot-check a few terms from scripts/jargon-list.json
expect(out).toContain('idempotent');
expect(out).toContain('race condition');
});
test('tier 2+ preamble includes terse-mode gate condition', () => {
const out = generatePreamble(makeCtx('claude', 2));
expect(out).toContain('EXPLAIN_LEVEL: terse');
expect(out).toMatch(/skip.*terse|Terse mode.*skip/is);
});
test('Codex tier-2 preamble uses host-aware path (no .claude/)', () => {
const out = generatePreamble(makeCtx('codex', 2));
// The Writing Style section shouldn't reference a Claude-specific bin path.
// Specifically check the EXPLAIN_LEVEL bash line.
const explainLine = out.split('\n').find(l => l.includes('_EXPLAIN_LEVEL='));
expect(explainLine).toBeDefined();
expect(explainLine).not.toMatch(/~\/\.claude\//);
// Codex uses $GSTACK_BIN
expect(explainLine).toContain('$GSTACK_BIN');
});
test('tier 1 preamble does NOT include Writing Style section', () => {
const out = generatePreamble(makeCtx('claude', 1));
expect(out).not.toContain('## Writing Style');
});
test('tier 2+ preamble composition note references AskUserQuestion Format', () => {
const out = generatePreamble(makeCtx('claude', 2));
// The Writing Style section should explicitly compose with the existing Format section
expect(out).toContain('AskUserQuestion Format');
});
test('tier 2+ preamble migration-prompt block appears', () => {
const out = generatePreamble(makeCtx('claude', 2));
expect(out).toContain('WRITING_STYLE_PENDING');
expect(out).toMatch(/writing-style-prompt-pending/);
});
});