mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-28 12:39:58 +02:00
b5f75c18c7
Five behaviors that v1.46 ships but had no test coverage. All now pinned. A) --host all idempotency (test/gen-skill-docs-idempotency.test.ts) The default test ran Claude host only. Non-Claude hosts (Codex, Factory, Cursor, OpenClaw, GBrain, Slate, OpenCode, Hermes, Kiro) each have their own output paths and could carry their own non-deterministic fields. We hit a "--host all needed for freshness check" mid-/ship. Now: two consecutive `bun run gen:skill-docs --host all` runs must produce byte-identical outputs across a per-host sample (.agents/, .cursor/, .factory/, .gbrain/). Catches per-host adapter regressions before CI. B) --catalog-mode=full opt-out (test/catalog-mode-full.test.ts) The legacy escape hatch had zero tests. 6 new tests across two layers: static (CATALOG_MODE_ARG parsed; conditional gate present; default is "trim"; invalid value throws) + smoke (actual --catalog-mode=full run produces a multi-line `description: |` block + omits "## When to invoke" body section; mutates the working tree then restores in a finally block). C) parity-baseline-v1.44.1.json integrity (test/parity-baseline-integrity.test.ts) The baseline is the source of every v1→v2 number cited in the CHANGELOG v1.46.0.0 entry. Anyone could edit it without test failure until now. 8 new tests pin: existence, tag, capturedFromCommit allowlist, expected v1.44 numbers (51 skills, ~2,915 KB, ~9,319 catalog tokens), CHANGELOG references this file by path, per-skill shape, and a SHA256 byte-stability hash. Any edit fails with a clear "if intentional, update EXPECTED_HASH AND the CHANGELOG numbers" signal. D) Live appliesTo gate end-to-end (test/resolver-entry.test.ts extended) The unwrapResolver unit tests covered the function; the gen-skill-docs.ts substitution loop that USES the gate had no integration coverage. 6 new tests simulate the exact 4-line shape from gen-skill-docs.ts:457-467 against synthetic registries: plain-function fires unconditionally, gated fires when true / empty-string when false, mixed registries compose, parameterized resolvers respect gates, unknown resolvers throw. E) Per-skill min-size floor (test/skill-size-budget.test.ts extended) The existing 200-byte body coverage-floor is a noise floor — a skill that lost 99.75% of content still passes. 1 new test asserts every skill stays ≥80% of its v1.44.1 baseline size (the parity-suite content invariants only covered 10 of 51 skills; the remaining 41 were uncovered). SECTIONS_EXTRACTED hook in place for v2.0.0.0 when the sections/ pattern legitimately shrinks ship/plan-ceo/etc. past the floor. Test plan: - bun test focused 17-file suite: 1202 pass, 0 fail (+23 new tests vs the pre-fill 1179 baseline) - catalog-mode=full mutates working tree then restores cleanly - --host all idempotency runs two full gen passes in <1s on this machine Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
221 lines
9.4 KiB
TypeScript
221 lines
9.4 KiB
TypeScript
/**
|
||
* Per-skill SKILL.md size budget regression (v1.46.0.0 T5).
|
||
*
|
||
* Asserts that no skill's generated SKILL.md grew beyond the v1.44.1
|
||
* baseline. Catches preamble/resolver changes that bloat skills back to
|
||
* the pre-compression size. Free — pure file IO + JSON diff.
|
||
*
|
||
* Why a separate test from skill-budget-regression.test.ts: that one
|
||
* compares LIVE eval runs (tool calls, turns, cost); this one compares
|
||
* static SKILL.md sizes. Both gate-tier.
|
||
*
|
||
* The baseline lives at test/fixtures/parity-baseline-v1.44.1.json,
|
||
* captured by scripts/capture-baseline.ts before any Phase A work landed.
|
||
*
|
||
* Override:
|
||
* - GSTACK_SIZE_BUDGET_RATIO=<n> changes the per-skill regression ratio.
|
||
* Default 1.0 (no growth allowed). Set to 1.10 to permit 10% growth
|
||
* (e.g., during deliberate feature additions that the catalog trim
|
||
* doesn't offset).
|
||
* - GSTACK_SIZE_BUDGET_OVERRIDE_REASON="text" allows a regression to
|
||
* pass and logs the reason to ~/.gstack/analytics/spend-overrides.jsonl
|
||
* for audit. Use sparingly; the next baseline should bake in the new
|
||
* size.
|
||
*/
|
||
|
||
import { describe, test, expect } from 'bun:test';
|
||
import * as fs from 'fs';
|
||
import * as path from 'path';
|
||
import { captureBaseline, type ParityBaseline } from './helpers/capture-parity-baseline';
|
||
import { logBudgetOverride } from './helpers/budget-override';
|
||
|
||
const REPO_ROOT = path.resolve(import.meta.dir, '..');
|
||
const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.44.1.json');
|
||
|
||
// Default per-skill ratio is 1.05 (5% growth tolerance). T4 catalog trim
|
||
// MOVES text from frontmatter (always-loaded catalog) to a body section
|
||
// ("## When to invoke"), so small skills with already-short descriptions
|
||
// see a tiny body growth from the section header itself (~20 bytes). The
|
||
// 5% per-skill tolerance accommodates that while still catching real bloat;
|
||
// the always-loaded catalog cost is enforced separately with a hard ceiling.
|
||
const DEFAULT_RATIO = 1.05;
|
||
const RATIO = Number(process.env.GSTACK_SIZE_BUDGET_RATIO) || DEFAULT_RATIO;
|
||
|
||
interface Regression {
|
||
skill: string;
|
||
beforeBytes: number;
|
||
afterBytes: number;
|
||
growth: number;
|
||
}
|
||
|
||
describe('SKILL.md size budget regression (gate, free)', () => {
|
||
test('parity-baseline-v1.44.1.json exists', () => {
|
||
expect(fs.existsSync(BASELINE_PATH)).toBe(true);
|
||
});
|
||
|
||
test('no skill exceeds v1.44.1 baseline size × ratio', () => {
|
||
const baseline: ParityBaseline = JSON.parse(fs.readFileSync(BASELINE_PATH, 'utf-8'));
|
||
const current = captureBaseline({ repoRoot: REPO_ROOT });
|
||
|
||
const regressions: Regression[] = [];
|
||
for (const [skill, before] of Object.entries(baseline.skills)) {
|
||
const after = current.skills[skill];
|
||
if (!after) continue; // skill removed since v1.44 — not a regression
|
||
if (after.skillMdBytes <= before.skillMdBytes * RATIO) continue;
|
||
regressions.push({
|
||
skill,
|
||
beforeBytes: before.skillMdBytes,
|
||
afterBytes: after.skillMdBytes,
|
||
growth: after.skillMdBytes / before.skillMdBytes,
|
||
});
|
||
}
|
||
|
||
if (regressions.length === 0) return;
|
||
|
||
const overrideReason = process.env.GSTACK_SIZE_BUDGET_OVERRIDE_REASON?.trim();
|
||
if (overrideReason) {
|
||
logBudgetOverride({
|
||
scope: 'skill-size-budget',
|
||
reason: overrideReason,
|
||
details: { ratio: RATIO, regressions },
|
||
});
|
||
// eslint-disable-next-line no-console
|
||
console.warn(
|
||
`[skill-size-budget] OVERRIDE APPLIED (${overrideReason}) — ${regressions.length} regression(s) allowed:`,
|
||
);
|
||
for (const r of regressions) {
|
||
// eslint-disable-next-line no-console
|
||
console.warn(` ${r.skill}: ${r.beforeBytes} → ${r.afterBytes} bytes (×${r.growth.toFixed(2)})`);
|
||
}
|
||
return;
|
||
}
|
||
|
||
const msg = regressions.map(r =>
|
||
` ${r.skill}: ${r.beforeBytes} → ${r.afterBytes} bytes (×${r.growth.toFixed(2)})`,
|
||
).join('\n');
|
||
throw new Error(
|
||
`${regressions.length} skill(s) regressed past v1.44.1 baseline × ${RATIO}:\n${msg}\n` +
|
||
`Override: set GSTACK_SIZE_BUDGET_OVERRIDE_REASON="why this is OK" to allow and audit-log.`,
|
||
);
|
||
});
|
||
|
||
test('total corpus byte count does not regress past baseline × ratio', () => {
|
||
const baseline: ParityBaseline = JSON.parse(fs.readFileSync(BASELINE_PATH, 'utf-8'));
|
||
const current = captureBaseline({ repoRoot: REPO_ROOT });
|
||
const ratio = current.totalCorpusBytes / baseline.totalCorpusBytes;
|
||
if (current.totalCorpusBytes <= baseline.totalCorpusBytes * RATIO) {
|
||
// eslint-disable-next-line no-console
|
||
console.log(
|
||
`[skill-size-budget] corpus OK: ${baseline.totalCorpusBytes} → ${current.totalCorpusBytes} bytes (×${ratio.toFixed(3)})`,
|
||
);
|
||
return;
|
||
}
|
||
const overrideReason = process.env.GSTACK_SIZE_BUDGET_OVERRIDE_REASON?.trim();
|
||
if (overrideReason) {
|
||
logBudgetOverride({
|
||
scope: 'skill-size-budget-corpus',
|
||
reason: overrideReason,
|
||
details: { ratio: RATIO, observed: ratio, before: baseline.totalCorpusBytes, after: current.totalCorpusBytes },
|
||
});
|
||
return;
|
||
}
|
||
throw new Error(
|
||
`Total corpus regressed past v1.44.1 baseline × ${RATIO}: ` +
|
||
`${baseline.totalCorpusBytes} → ${current.totalCorpusBytes} bytes (×${ratio.toFixed(3)}). ` +
|
||
`Override: set GSTACK_SIZE_BUDGET_OVERRIDE_REASON to allow.`,
|
||
);
|
||
});
|
||
|
||
/**
|
||
* Gap E (v1.46.0.0): per-skill min-size floor.
|
||
*
|
||
* The existing skill-coverage-floor enforces body ≥ 200 bytes, which is
|
||
* a tiny noise floor. A skill that was 100 KB at v1.44.1 and shrinks to
|
||
* 250 bytes passes that check despite losing 99.75% of content. The
|
||
* parity-suite content invariants cover this for 10 hand-picked skills
|
||
* (cso, ship, plan-ceo, etc.); the remaining 41 skills had no per-skill
|
||
* shrinkage floor.
|
||
*
|
||
* Floor: 80% of the v1.44.1 baseline. v1.46 actual shrinkage is <1% per
|
||
* skill, so this is a comfortable ceiling that still catches accidental
|
||
* mass deletion (e.g., a refactor that strips the body of a skill).
|
||
*
|
||
* v2.0.0.0 will introduce the sections/ pattern for 5 heavyweights
|
||
* (ship, plan-ceo-review, office-hours, plan-eng-review,
|
||
* plan-design-review). Those skills will legitimately shrink to ~15 KB
|
||
* skeletons. When that lands, add them to SECTIONS_EXTRACTED so the floor
|
||
* relaxes for them.
|
||
*/
|
||
test('no skill shrinks past 80% of v1.44.1 baseline (catches accidental body strip)', () => {
|
||
const baseline: ParityBaseline = JSON.parse(fs.readFileSync(BASELINE_PATH, 'utf-8'));
|
||
const current = captureBaseline({ repoRoot: REPO_ROOT });
|
||
const MIN_RATIO = 0.80; // a skill at <80% of its v1.44 size signals mass-deletion
|
||
const SECTIONS_EXTRACTED = new Set<string>(); // populate in v2.0.0.0 when sections/ lands
|
||
|
||
const undershoots: Array<{
|
||
skill: string; beforeBytes: number; afterBytes: number; ratio: number;
|
||
}> = [];
|
||
for (const [skill, before] of Object.entries(baseline.skills)) {
|
||
if (SECTIONS_EXTRACTED.has(skill)) continue;
|
||
const after = current.skills[skill];
|
||
if (!after) continue; // skill removed since baseline — separate concern
|
||
const ratio = after.skillMdBytes / before.skillMdBytes;
|
||
if (ratio < MIN_RATIO) {
|
||
undershoots.push({
|
||
skill, beforeBytes: before.skillMdBytes, afterBytes: after.skillMdBytes, ratio,
|
||
});
|
||
}
|
||
}
|
||
|
||
if (undershoots.length === 0) return;
|
||
|
||
const overrideReason = process.env.GSTACK_SIZE_BUDGET_OVERRIDE_REASON?.trim();
|
||
if (overrideReason) {
|
||
logBudgetOverride({
|
||
scope: 'skill-size-budget-floor',
|
||
reason: overrideReason,
|
||
details: { min_ratio: MIN_RATIO, undershoots },
|
||
});
|
||
// eslint-disable-next-line no-console
|
||
console.warn(
|
||
`[skill-size-budget-floor] OVERRIDE APPLIED (${overrideReason}) — ${undershoots.length} undershoot(s) allowed`,
|
||
);
|
||
return;
|
||
}
|
||
|
||
const msg = undershoots.map(u =>
|
||
` ${u.skill}: ${u.beforeBytes} → ${u.afterBytes} bytes (×${u.ratio.toFixed(2)} — below ${MIN_RATIO} floor)`,
|
||
).join('\n');
|
||
throw new Error(
|
||
`${undershoots.length} skill(s) shrunk past v1.44.1 × ${MIN_RATIO} floor:\n${msg}\n` +
|
||
`This usually signals accidental body strip (e.g., a resolver returning empty, a ` +
|
||
`template losing a section). If the shrinkage is intentional (e.g., the skill moved ` +
|
||
`to the sections/ pattern), add it to SECTIONS_EXTRACTED in this test. Override: ` +
|
||
`GSTACK_SIZE_BUDGET_OVERRIDE_REASON="why" allows + audit-logs.`,
|
||
);
|
||
});
|
||
|
||
test('catalog token estimate stays compressed (v1.45 target ≤ 7000)', () => {
|
||
const current = captureBaseline({ repoRoot: REPO_ROOT });
|
||
const v145Target = 7000;
|
||
if (current.estTotalCatalogTokens <= v145Target) {
|
||
// eslint-disable-next-line no-console
|
||
console.log(`[skill-size-budget] catalog OK: ~${current.estTotalCatalogTokens} tokens (target ≤${v145Target})`);
|
||
return;
|
||
}
|
||
const overrideReason = process.env.GSTACK_SIZE_BUDGET_OVERRIDE_REASON?.trim();
|
||
if (overrideReason) {
|
||
logBudgetOverride({
|
||
scope: 'skill-size-budget-catalog',
|
||
reason: overrideReason,
|
||
details: { target: v145Target, observed: current.estTotalCatalogTokens },
|
||
});
|
||
return;
|
||
}
|
||
throw new Error(
|
||
`Catalog token estimate regressed past v1.45 target: ${current.estTotalCatalogTokens} tokens > ${v145Target}. ` +
|
||
`T4 catalog trim should keep this under control. Override: set GSTACK_SIZE_BUDGET_OVERRIDE_REASON to allow.`,
|
||
);
|
||
});
|
||
});
|