Files
gstack/test/skill-size-budget.test.ts
T
Garry Tan 81fdf9cc61 test(budget): T5 — hard token budgets + override audit trail (Phase A.6)
Two new gate-tier guardrails for the v1.45.0.0 compression baseline:

1. test/skill-size-budget.test.ts (NEW) — per-skill SKILL.md size budget.
   Compares current state to test/fixtures/parity-baseline-v1.44.1.json.
   Three checks: per-skill (×1.05 default ratio), total corpus, and
   catalog token estimate (≤7000 for v1.45). The per-skill ratio is 1.05
   not 1.0 because the T4 catalog trim moves text from frontmatter to a
   body section; small skills see a tiny body growth that's fine when
   offset by the much larger catalog-token win.

2. test/skill-budget-regression.test.ts EXTENDED — hard dollar cap on
   per-run eval cost. Per-tier defaults: gate $25, periodic $70. Umbrella
   EVALS_BUDGET_HARD_CAP=$30. Catches runaway eval costs (infinite retry,
   model price changes) before they amortize across PRs.

Both checks support an override path with audit trail:
   GSTACK_SIZE_BUDGET_OVERRIDE_REASON="why this is OK"   — size
   EVALS_BUDGET_OVERRIDE_REASON="why this is OK"          — cost
Overrides log to ~/.gstack/analytics/spend-overrides.jsonl with
timestamp + scope + reason + CI provenance (runner, branch, commit)
via test/helpers/budget-override.ts.

Why the override audit: a hard cap with no escape valve becomes
operationally hostile (legit price changes, longer transcripts, new
required evals can all blow the cap). An override with no audit becomes
"everyone overrides everything and the gate is theater." This module
ships the audit half so reviewers can see what was waived and why.

Codex 2nd-pass critique #3 absorbed: per-suite caps + override path with
auditability + budget baselines checked into repo (parity-baseline-v1.44.1.json
already in test/fixtures/).

Test plan:
- bun test test/skill-size-budget.test.ts: 4 pass (per-skill, corpus, catalog, baseline-exists)
- bun test test/skill-budget-regression.test.ts: 4 pass (2 existing ratio checks + 2 new hard-cap checks)
- Existing eval runs ($14.11 e2e, $0.02 llm-judge) sit well under the new caps

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 20:36:43 -07:00

152 lines
6.3 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
/**
* Per-skill SKILL.md size budget regression (v1.45.0.0 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.`,
);
});
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.`,
);
});
});