Files
gstack/test/skill-size-budget.test.ts
T
Garry Tan a6fb31726c v1.48.0.0 feat: AskUserQuestion split rule + runtime AUTO_DECIDE carve-out (#1740)
* feat(preamble): add "Handling 5+ options — split, never drop" rule

Agents repeatedly hit Conductor's 4-option AskUserQuestion cap and
silently drop one option to fit, shrinking the user's decision space.
This rule names the bug and gives two compliant shapes: batch into
≤4-groups (for coherent alternatives) or split into N sequential
per-option calls (for independent scope items, default).

Inline preamble subsection is ~15 lines (rule + buckets + pointer).
Full reference with worked examples, Hold/dependency semantics, and
final-summary validation lives in docs/askuserquestion-split.md.
The agent loads the docs file on demand when N>4.

Per-option call shape: D<N>.k header, ELI10, Recommendation, kind-note
(no completeness score — decision actions, not coverage), Include /
Defer / Cut / Hold buckets. Hold stops the chain immediately; the
final D<N>.final call validates dependencies and confirms the
assembled scope.

question_ids: <skill>-split-<option-slug> (kebab-case ASCII, ≤64
chars). Also fixes orphan "12. " prefix on the existing CJK rule.

Tier-2+ skills inherit via the existing resolver. SKILL.md regenerated
for all 41 affected skills + 3 golden fixtures. Net diff per SKILL.md:
~34 lines (vs ~110 for the full inline version).

6 tests pin the inline contract (4-option cap, buckets, D-numbering,
docs pointer, runtime AUTO_DECIDE gate reference, orphan 12 regression).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(question-pref): runtime AUTO_DECIDE carve-out for *-split-* ids

Split chains (per-option AskUserQuestion calls emitted by the new
"Handling 5+ options" rule) must never be silently auto-approved
via /plan-tune preferences. The user's option set is sacred.

Layer 1 (mechanism): unique <skill>-split-<option-slug> ids prevent
cross-option preference leakage. Layer 2 (this commit): the runtime
checker `gstack-question-preference --check` detects any id matching
*-split-* and forces ASK_NORMALLY even when never-ask or
ask-only-for-one-way preferences exist for that exact id. An
explanatory note tells the user their preference was bypassed and why.

7 tests pin the carve-out: no-pref baseline, never-ask override,
explanatory note text, ask-only-for-one-way override, always-ask
(no note), non-split id containing "split" word (negative case for
regex specificity), multi-skill split id formats.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(e2e): split-overflow regression for /plan-ceo-review

Periodic-tier E2E test that catches the original failure mode the
user complained about: 5+ options for ONE decision must split into
N sequential AskUserQuestion calls, not drop one to fit Conductor's
4-option cap.

Fixture: 5 independent chat-platform integration candidates
(Slack/Discord/Teams/Telegram/Mattermost), each carrying its own
include/defer/cut decision. Floor = 4 review-phase AUQs (standard
[N-1] tolerance band). Pre-fix "drop to 4 + 1 dropped" fails this
floor.

Wired into test/helpers/touchfiles.ts: tier periodic, depends on
plan-ceo-review/**, the new preamble subsection, the question-pref
binary (for the carve-out), and the runner helper. touchfiles.test.ts
expected count bumped 21 → 22 to account for the new entry.

Cost: ~$0.30/run when EVALS_TIER=periodic. Skips silently otherwise.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: post-merge regen + rebase size-budget baseline to v1.47.0.0

After merging origin/main (v1.45 → v1.47), three things needed cleanup:

1. spec/SKILL.md (main's new skill) regenerated to include our split-vs-drop
   preamble subsection — same mechanical regen as the other 41 tier-2+ skills.
2. Three golden ship fixtures refreshed to capture main's GSTACK_PLAN_MODE
   block + /spec routing entry + jargon-list.json refactor.
3. docs/skills.md — added /spec table row that main's PR (#1698/#1733) shipped
   without. Pre-existing failure on main; this PR catches and fixes.

Also rebased test/skill-size-budget.test.ts from v1.44.1 → v1.47.0.0 baseline.
Main's v1.46 (catalog tokens trim) + v1.47 (/spec skill) pushed the v1.44.1
anchor past the 5% ratchet to ×1.059 — pre-existing failure on main. This
PR captures a fresh parity-baseline-v1.47.0.0.json and re-anchors the test
there. Historical v1.44.1.json and v1.46.0.0.json retained in test/fixtures/
for reference. Our subsection contributes ~0.1% of the post-rebase corpus.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v1.48.0.0)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 23:43:07 -07:00

226 lines
9.7 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 (v1.46.0.0 T5).
*
* Asserts that no skill's generated SKILL.md grew beyond the v1.47.0.0
* baseline. Catches preamble/resolver changes that bloat skills back to
* the pre-compression size. Free — pure file IO + JSON diff.
*
* Baseline rebased v1.44.1 → v1.47.0.0 in the AskUserQuestion split-rule
* PR after main merged GSTACK_PLAN_MODE + /spec, pushing the v1.44.1
* anchor past the 5% ratchet. Historical v1.44.1.json and v1.46.0.0.json
* are retained in test/fixtures/ for reference.
*
* 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-v1.47.0.0.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-v1.47.0.0.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-v1.47.0.0.json exists', () => {
expect(fs.existsSync(BASELINE_PATH)).toBe(true);
});
test('no skill exceeds v1.47.0.0 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 v1.47.0.0 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 v1.47.0.0 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 v1.47.0.0 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 v1.47.0.0 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 v1.47.0.0 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 v1.47.0.0 × ${MIN_RATIO} floor:\n${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.`,
);
});
});