Files
gstack/test/skill-e2e-write-skill.test.ts
T
Garry Tanandcapy-ai[bot] 7204a39a27 v1.91.287.0 feat(write-skill): write, change and diet skills; /learn at half its template size (#3524)
* test(skill-evals): /learn before/after tasks, written before any cut (GSTA-133)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(learnings): --help, unknown-flag errors and --stats on the learnings bins; cross-project search no longer drops every project when the state root path contains the slug

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* refactor(learn): diet /learn onto the levels: tool flags replace the inline stats program, one mode table, prune rules kept

Skill-Diet: learn
Skill-Size: 5797→2586 bytes (SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(write-skill): /write-skill skill, gstack-skill-bill, static skill-to-bin drift ratchet, shared skill eval contract

Skill-Size: 0→3245 bytes (write-skill/SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(learn): guard the state-root lookup in Prune; re-measure the learn ceiling

Skill-Size: 2586→2707 bytes (learn/SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix: pre-landing review fixes (drift scanner, learnings flags, skill-bill baselines, eval fixtures)

- skill-bin-drift: a redirect no longer ends a command, so `bin/x 2>/dev/null --bogus` is checked
- gstack-learnings-search: a missing value or a non-positive --limit exits 2 like an unknown flag
- gstack-skill-bill: the gstack root skill is a checkout skill; Skill-Diet trailers match the exact name; the baseline counts the committed bytes untrimmed
- skill-evals task files get a free contract test and are registered in FREE_FIXTURES, with the drift allowlist
- learn eval: the no-code-change safety task no longer asks the model to fix code (its check penalised obeying the user)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(learn,write-skill): full bin paths in the mode table; prune asks per entry unless the request names the action

Skill-Diet: learn
Skill-Size: 2707→2955 bytes (learn/SKILL.md.tmpl)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(changelog): /write-skill, gstack-skill-bill, drift ratchet, eval contract, /learn diet

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: drift ratchet in CONTRIBUTING's static tests; /learn prune example asks per entry

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(skill-bill): report a checkout skill's eval task file and check it against the contract

The skill-evals task-file test now exercises lib/skill-bill.ts's checkEvalTasks, with a negative control, instead of a test-only validator (test-of-test ratchet).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(skill-bill): EVAL TASKS path uses forward slashes on every platform; a non-object task entry is a problem, not a crash

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(learn): BASH_COMPAT guard on in-window heredocs; count skill-e2e-write-skill in the paid census

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>
2026-10-28 02:58:29 +00:00

78 lines
3.2 KiB
TypeScript

import { describe, expect, beforeAll, afterAll } from 'bun:test';
import { CAPTURE_MS, JUDGE_MS } from './helpers/eval-budgets';
import { runSkillTest } from './helpers/session-runner';
import {
ROOT, runId, describeIfSelected, testConcurrentIfSelected, copyDirSync, logCost, recordE2E,
createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
const evalCollector = createEvalCollector('e2e-write-skill');
const DEPLOY_SKILL = `---
name: deploy
description: Deploy the web app to production.
---
# Deploy
1. Build the release image with \`make release\`.
2. Run database migrations before restarting the web servers.
3. Restart the web servers one at a time.
4. Check the health endpoint returns 200.
`;
describeIfSelected('/write-skill E2E', ['write-skill-add-lesson'], () => {
let workDir: string;
beforeAll(() => {
workDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-write-skill-'));
copyDirSync(path.join(ROOT, 'write-skill'), path.join(workDir, 'write-skill'));
fs.mkdirSync(path.join(workDir, 'deploy'));
fs.writeFileSync(path.join(workDir, 'deploy', 'SKILL.md'), DEPLOY_SKILL);
});
afterAll(() => {
try { fs.rmSync(workDir, { recursive: true, force: true }); } catch {}
finalizeEvalCollector(evalCollector);
});
testConcurrentIfSelected('write-skill-add-lesson', async () => {
const result = await runSkillTest({
prompt: `Read the file write-skill/SKILL.md for the /write-skill skill instructions.
Add this lesson to the deploy skill in ./deploy: "Last Tuesday we restarted the web servers while migrations were still running and the site returned 500s for ten minutes. Migrations must finish before any restart."
IMPORTANT:
- The gstack bin scripts are at ${ROOT}/bin/, not at ~/.claude/skills/gstack/bin/; use that path.
- ./deploy is a skill folder the user owns, not a git repository.
- Do NOT use AskUserQuestion. Edit the file, then report what you changed and its size before and after.`.replace('${ROOT}', ROOT),
workingDirectory: workDir,
maxTurns: 15,
allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Grep', 'Glob'],
timeout: JUDGE_MS,
testName: 'write-skill-add-lesson',
runId,
});
logCost('/write-skill add lesson', result);
const after = fs.readFileSync(path.join(workDir, 'deploy', 'SKILL.md'), 'utf-8');
const grewBy = after.trimEnd().split('\n').length - DEPLOY_SKILL.trimEnd().split('\n').length;
const ruleLanded = /finish|complete|wait/i.test(after.split('\n').find(l => /migration/i.test(l)) ?? '');
const storyKept = /tuesday|500s?|ten minutes/i.test(after);
const reportedSize = /\d+\s*(B|bytes)?\s*(→|->|to)\s*\d+/i.test(result.output);
const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
recordE2E(evalCollector, '/write-skill', 'Add a lesson by editing the existing line', result, {
passed: exitOk && grewBy <= 1 && ruleLanded && !storyKept && reportedSize,
});
expect(exitOk).toBe(true);
expect(ruleLanded).toBe(true);
expect(storyKept).toBe(false);
expect(grewBy).toBeLessThanOrEqual(1);
expect(reportedSize).toBe(true);
}, CAPTURE_MS);
});