mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-18 14:14:37 +01:00
* Say when to use each gstack skill in Claude Code's skill list (GST-2774) Claude Code's listing of each gstack skill now keeps a short when-to-use clause after its first sentence, so Opus 5.5 loads /review on "review my changes" and /plan-eng-review on "plan this feature" (GSTA-558). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Keep /review and /plan-eng-review within their size pins and refresh budgets CI on the first head found five size and fact checks the new catalog clause moved: the per-host SKILL.md size pins, the context-budget ceilings, the deslop-shared-libs catalog byte pin, the Claude ship golden and the catalog ceiling CLAUDE.md states. /review's and /plan-eng-review's full descriptions are now shorter than before, so their pins go down, and /plan-eng-review's scope gate is unchanged from main. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Say which skills keep no when-to-use clause in the changelog entry Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Update the catalog budget and voice-trigger docs for the when-to-use clause Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Drop "deploy this" from /ship's Claude Code skill list line Deploying belongs to /land-and-deploy, so /ship's when-to-use clause keeps "ship it, create a pr, push to main" only. Budgets, the size ledger and the Claude ship golden are re-measured. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Review-Finding: p1/specialist-batched#1 reader=specialist-batched Review-Finding: p1/red-team#1 reader=red-team Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Re-measure the setup-gbrain size cap after merging main Main grew setup-gbrain's always-loaded part to 38,621 bytes, and this branch's when-to-use clause adds 55 more, so the cap measured on the old base (38,637) is stale. The cap is now the merged measurement, 38,676. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
71 lines
4.4 KiB
TypeScript
71 lines
4.4 KiB
TypeScript
/**
|
|
* lib/skill-triggers.ts: the trigger-first wording rule for harness listings
|
|
* (Hermes description leads, router lines), on its branches the full-catalog
|
|
* render tests in test/harness-register.test.ts never reach because every
|
|
* current skill has a trigger sentence and a triggers list.
|
|
*
|
|
* Value: protects=Hermes descriptions keep every non-trigger sentence and the (gstack) tag; router/lead fallbacks stay trigger-first and within max;
|
|
* fails_when=withTriggerLead drops the wrong sentence or the tag, or a fallback branch (no trigger sentence, no triggers, overlong entry) exceeds max or loses its lead;
|
|
* why_new=the render tests check only the lead's prefix and length over skills that all take the triggers-list branch; seam=none;
|
|
* no_claim=how any harness ranks or shows the text (pure string functions; synthetic descriptions)
|
|
*/
|
|
import { describe, expect, test } from 'bun:test';
|
|
import { frontmatterList, routerLine, triggerList, withTriggerLead } from '../lib/skill-triggers';
|
|
|
|
const DESC = 'Pre-landing PR review. Analyzes the diff for structural issues. Use when asked to "review this PR" or "check my diff". Proactively suggest before a merge. (gstack)';
|
|
const TRIGGERS = ['review this pr', 'code review', 'check my diff', 'pre-landing review'];
|
|
|
|
describe('withTriggerLead (Hermes descriptions)', () => {
|
|
test('a triggers-list lead replaces the trigger sentence; every other sentence and the (gstack) tag stay, once', () => {
|
|
const [lead, rest, ...more] = withTriggerLead(DESC, TRIGGERS, 57).split('\n');
|
|
expect(more).toEqual([]);
|
|
expect(lead).toStartWith('Use for: review this pr');
|
|
expect(lead.length).toBeLessThanOrEqual(57);
|
|
expect(rest).toBe('Pre-landing PR review. Analyzes the diff for structural issues. Proactively suggest before a merge. (gstack)');
|
|
});
|
|
|
|
test('without triggers the lead is the trigger sentence cut at a word, and the whole description follows unchanged', () => {
|
|
const [lead, ...rest] = withTriggerLead(DESC, [], 40).split('\n');
|
|
expect(lead).toStartWith('Use when asked to');
|
|
expect(lead).toEndWith('...');
|
|
expect(lead.length).toBeLessThanOrEqual(40);
|
|
expect(rest.join('\n')).toBe(DESC);
|
|
});
|
|
});
|
|
|
|
describe('routerLine (router-mode targets)', () => {
|
|
const cases: Array<[string, string, string[], number, (line: string) => void]> = [
|
|
['trigger sentence and first sentence both fit', 'Debug a crash. Use to find the root cause.', [], 160,
|
|
l => expect(l).toBe('Use to find the root cause. Debug a crash.')],
|
|
['trigger sentence alone when both do not fit', DESC, [], 60,
|
|
l => { expect(l).toStartWith('Use when asked to'); expect(l).not.toContain('Pre-landing'); }],
|
|
['no trigger sentence: the triggers list leads', 'Pre-landing PR review. Analyzes the diff.', TRIGGERS, 160,
|
|
l => expect(l).toStartWith('Use for: review this pr, code review')],
|
|
['the catalog-trimmed "Use for:" clause gives way to the full triggers list', 'Pre-landing PR review. Use for: review this pr, code review. (gstack)', TRIGGERS, 160,
|
|
l => expect(l).toBe('Use for: review this pr, code review, check my diff, pre-landing review. Pre-landing PR review.')],
|
|
['neither: the first sentence, cut at a word', 'A very long first sentence about a workflow that goes on and on and on.', [], 40,
|
|
l => { expect(l).toStartWith('A very long first sentence'); expect(l).toEndWith('...'); }],
|
|
];
|
|
for (const [name, desc, triggers, max, check] of cases) {
|
|
test(name, () => {
|
|
const line = routerLine(desc, triggers, max);
|
|
expect(line.length).toBeLessThanOrEqual(max);
|
|
check(line);
|
|
});
|
|
}
|
|
});
|
|
|
|
test('triggerList: an entry longer than max is cut to fit instead of overflowing', () => {
|
|
const lead = triggerList(['find out why the nightly deploy pipeline keeps failing on the staging cluster'], 57);
|
|
expect(lead).toStartWith('Use for: find out why');
|
|
expect(lead).toEndWith('...');
|
|
expect(lead.length).toBeLessThanOrEqual(57);
|
|
});
|
|
|
|
test('frontmatterList reads one block list, unquoting values and stopping at the next field', () => {
|
|
const md = '---\nname: x\ntriggers:\n - "quoted one"\n - \'single\'\n - plain\nallowed-tools:\n - Bash\n---\nbody\n - not frontmatter\n';
|
|
expect(frontmatterList(md, 'triggers')).toEqual(['quoted one', 'single', 'plain']);
|
|
expect(frontmatterList(md, 'voice-triggers')).toEqual([]);
|
|
expect(frontmatterList('no frontmatter\ntriggers:\n - x\n', 'triggers')).toEqual([]);
|
|
});
|