The windows-test-parity ratchet greps test source for fs.rmSync-without-
maxRetries (and six other Windows-portability anti-patterns), failing when an
integer offender COUNT exceeds a frozen baseline (rmSync: 95). A count ratchet
is a Goodhart metric: fixing one offender and adding another keeps the count
constant, so a new defect slips through green. Replace it — and every other
count ratchet in the repo — with a layered, masking-proof design.
Behavioral seam test
- tests/helpers-cleanup.test.cjs proves helpers.cleanup() carries the Windows
EBUSY retry budget. cleanup() delegates retries to Node's fs.rmSync via
maxRetries (it owns no loop), so the test asserts the option contract
(recursive/force/maxRetries>0/retryDelay>0) + real-FS removal + the cwd-guard,
rather than a loop that does not exist. The EBUSY risk is now tested ONCE at
the helper, not approximated textually at every call site.
Write-time ESLint rule (AST-accurate, replaces the grep)
- eslint-rules/no-raw-rmsync-in-tests.cjs (error in tests/**/*.test.cjs) bans
raw fs.rmSync, steering to cleanup(). Catches member, computed (fs['rmSync']),
destructured and aliased forms; escape hatch is inline
`// eslint-disable-next-line local/no-raw-rmsync-in-tests -- <reason>` only.
- Migrated 336 raw fs.rmSync teardown calls across ~116 test files to cleanup().
~18 genuinely load-bearing sites (mid-test SUT/fault-injection removals,
error-swallowing or name-colliding local teardown helpers) keep the raw call
with an inline eslint-disable + reason.
Shared anti-ratchet primitive
- scripts/lib/allowlist-ratchet.cjs:
- assertWithinAllowlist: fails on NOVEL ids (new offender introduced) AND on
STALE ids (a known offender was fixed but not pruned) — identity, not count,
and a ratchet DOWN toward zero.
- assertTightCeiling: a size/length budget whose ceiling must stay within a
grace band of the high-water mark, so budgets may only tighten, never creep.
Ratchets converted onto the primitive
- windows-test-parity-guard.test.cjs: rmSync rule deleted (now ESLint-enforced);
the remaining six patterns moved from integer baselines to named-set
allowlists with ratchet-down.
- scripts/lint-test-file-count.{cjs,allowlist.json}: per-module integer counts →
named filename sets (closes the swap-a-file-keep-the-count blind spot); a
module dropping under cap now FAILS to force pruning its allowlist entry.
- enh-2790 skill-count `<= 63` → named skill allowlist (ratchets toward ~58).
Size budgets hardened (tighten-only)
- agent-size / workflow-size / feat-3039 help-tiered: ceilings lowered to the
current high-water mark and an assertTightCeiling anti-creep check added per
tier. Fixed external-contract limits (description ≤100 chars, agent ≤100 KB)
are intentionally left as-is — they are not grandfathered creeping budgets.
No user-facing behavior change (tests + tooling only); no USER_FACING_PREFIXES
touched, so no changeset fragment is required.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
180 lines
6.5 KiB
JavaScript
180 lines
6.5 KiB
JavaScript
'use strict';
|
|
// allow-test-rule: reads runtime STATE.md written to temp dir — behavioral output test, not source-grep
|
|
|
|
// Regression tests for bug #3127.
|
|
//
|
|
// state.begin-phase is non-idempotent: when execute-phase calls it on a phase
|
|
// that is already mid-flight (e.g. --wave N resume), the handler unconditionally
|
|
// overwrites execution-progress fields with stale values from the last plan-phase run:
|
|
// - stopped_at / Last Activity Description reset to "context gathered; ready for plan-phase"
|
|
// - Current Plan reset to 1 (from plan being executed, e.g. 3)
|
|
// - Plan: N of M body line reset to "Plan: 1 of M"
|
|
// - Last activity timestamp reverted to an older value
|
|
// - progress.percent may decrease
|
|
//
|
|
// Fix: read the current Status field before writing. If the phase is already
|
|
// "Executing Phase N", skip the execution-progress fields (Current Plan, plan body
|
|
// line, Last Activity Description) and only update fields safe to overwrite on
|
|
// resume (Last Activity date, Status if somehow wrong).
|
|
// A --force flag bypasses the guard for intentional full resets.
|
|
|
|
const { describe, test } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const fs = require('node:fs');
|
|
const os = require('node:os');
|
|
const path = require('node:path');
|
|
const { cleanup } = require('./helpers.cjs');
|
|
|
|
const ROOT = path.join(__dirname, '..');
|
|
|
|
// Load the state.cjs module internals via the command router
|
|
function requireStateCjs() {
|
|
return require(path.join(ROOT, 'get-shit-done', 'bin', 'lib', 'state.cjs'));
|
|
}
|
|
|
|
function makeTempPlanning(stateContent) {
|
|
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-3127-'));
|
|
const planningDir = path.join(dir, '.planning');
|
|
fs.mkdirSync(planningDir, { recursive: true });
|
|
fs.writeFileSync(path.join(planningDir, 'STATE.md'), stateContent, 'utf8');
|
|
return dir;
|
|
}
|
|
|
|
// A STATE.md that is mid-flight on Phase 5 (Plan 3 of 8 in progress)
|
|
const MID_FLIGHT_STATE = `# GSD State
|
|
|
|
## Configuration
|
|
Current Phase: 5
|
|
Current Phase Name: test-phase
|
|
Total Plans in Phase: 8
|
|
Current Plan: 3
|
|
Status: Executing Phase 5
|
|
|
|
## Current Position
|
|
|
|
Phase: 5 (test-phase) — EXECUTING
|
|
Plan: 3 of 8 (Plan 00 SHIPPED — wave 1 complete; Plan 01 SHIPPED; Plan 02 next)
|
|
Status: Executing Phase 5
|
|
Last activity: 2026-05-05 -- Plan 02 SHIPPED wave 2 GREEN
|
|
|
|
## Progress
|
|
|
|
progress:
|
|
total_phases: 10
|
|
completed_phases: 4
|
|
percent: 89
|
|
|
|
stopped_at: Phase 5 Plan 02 SHIPPED — Wave 2 GREEN detailed narrative here; ready for Plan 03
|
|
`;
|
|
|
|
// A STATE.md that is NOT yet executing (plan-phase just ran)
|
|
const PRE_EXECUTE_STATE = `# GSD State
|
|
|
|
## Configuration
|
|
Current Phase: 5
|
|
Current Phase Name: test-phase
|
|
Total Plans in Phase: 8
|
|
Current Plan: 1
|
|
Status: Ready to execute
|
|
|
|
## Current Position
|
|
|
|
Phase: 5 (test-phase) — READY
|
|
Plan: 1 of 8
|
|
Status: Ready to execute
|
|
Last activity: 2026-05-04 -- context gathered; ready for plan-phase
|
|
|
|
stopped_at: Phase 5 context gathered; ready for plan-phase
|
|
`;
|
|
|
|
describe('bug #3127: state.begin-phase idempotency guard', () => {
|
|
test('begin-phase on a mid-flight phase does not reset Current Plan', () => {
|
|
const stateModule = requireStateCjs();
|
|
const { cmdStateBeginPhase } = stateModule;
|
|
if (!cmdStateBeginPhase) {
|
|
// Skip if not exported — the guard may be inside a private function
|
|
return;
|
|
}
|
|
const dir = makeTempPlanning(MID_FLIGHT_STATE);
|
|
try {
|
|
cmdStateBeginPhase(dir, '5', 'test-phase', 8, false);
|
|
const after = fs.readFileSync(path.join(dir, '.planning', 'STATE.md'), 'utf8');
|
|
// Current Plan must not have been reset to 1
|
|
const planMatch = after.match(/^Current Plan:\s*(\S+)/m);
|
|
if (planMatch) {
|
|
assert.notStrictEqual(planMatch[1], '1',
|
|
'begin-phase reset Current Plan to 1 on a mid-flight phase — idempotency guard not applied');
|
|
}
|
|
} finally {
|
|
cleanup(dir);
|
|
}
|
|
});
|
|
|
|
test('begin-phase on a mid-flight phase does not overwrite stopped_at narrative', () => {
|
|
const stateModule = requireStateCjs();
|
|
const { cmdStateBeginPhase } = stateModule;
|
|
if (!cmdStateBeginPhase) return;
|
|
const dir = makeTempPlanning(MID_FLIGHT_STATE);
|
|
try {
|
|
cmdStateBeginPhase(dir, '5', 'test-phase', 8, false);
|
|
const after = fs.readFileSync(path.join(dir, '.planning', 'STATE.md'), 'utf8');
|
|
// The rich stopped_at narrative must be preserved
|
|
assert.ok(
|
|
after.includes('Plan 02 SHIPPED') || after.includes('Wave 2 GREEN'),
|
|
'begin-phase overwrote stopped_at narrative on a mid-flight phase',
|
|
);
|
|
} finally {
|
|
cleanup(dir);
|
|
}
|
|
});
|
|
|
|
test('begin-phase on a NOT-yet-executing phase sets Current Plan to 1 (normal path)', () => {
|
|
const stateModule = requireStateCjs();
|
|
const { cmdStateBeginPhase } = stateModule;
|
|
if (!cmdStateBeginPhase) return;
|
|
const dir = makeTempPlanning(PRE_EXECUTE_STATE);
|
|
try {
|
|
cmdStateBeginPhase(dir, '5', 'test-phase', 8, false);
|
|
const after = fs.readFileSync(path.join(dir, '.planning', 'STATE.md'), 'utf8');
|
|
// Normal path: Current Plan should become 1 (or stay 1)
|
|
const planMatch = after.match(/^Current Plan:\s*(\S+)/m);
|
|
if (planMatch) {
|
|
assert.strictEqual(planMatch[1], '1',
|
|
'begin-phase should set Current Plan to 1 on a fresh phase');
|
|
}
|
|
} finally {
|
|
cleanup(dir);
|
|
}
|
|
});
|
|
|
|
test('begin-phase always updates Last Activity date (safe on resume, pinned via GSD_NOW_MS)', () => {
|
|
const stateModule = requireStateCjs();
|
|
const { cmdStateBeginPhase } = stateModule;
|
|
if (!cmdStateBeginPhase) return;
|
|
const dir = makeTempPlanning(MID_FLIGHT_STATE);
|
|
|
|
const PINNED_MS = Date.parse('2020-11-25T09:00:00.000Z');
|
|
const PINNED_DATE = '2020-11-25';
|
|
// Pin the in-process clock via env vars before calling the function directly.
|
|
const origTestMode = process.env.GSD_TEST_MODE;
|
|
const origNowMs = process.env.GSD_NOW_MS;
|
|
process.env.GSD_TEST_MODE = '1';
|
|
process.env.GSD_NOW_MS = String(PINNED_MS);
|
|
try {
|
|
cmdStateBeginPhase(dir, '5', 'test-phase', 8, false);
|
|
const after = fs.readFileSync(path.join(dir, '.planning', 'STATE.md'), 'utf8');
|
|
assert.ok(
|
|
after.includes(PINNED_DATE),
|
|
`begin-phase must update Last Activity date to the pinned date ${PINNED_DATE} even on resume (safe field)`,
|
|
);
|
|
} finally {
|
|
// Restore env vars before cleanup to avoid leaking state to other tests.
|
|
if (origTestMode === undefined) delete process.env.GSD_TEST_MODE;
|
|
else process.env.GSD_TEST_MODE = origTestMode;
|
|
if (origNowMs === undefined) delete process.env.GSD_NOW_MS;
|
|
else process.env.GSD_NOW_MS = origNowMs;
|
|
cleanup(dir);
|
|
}
|
|
});
|
|
});
|