CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-01 02:40:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(test): unique tmp dirs for plan artifacts + audited live-repo cwd sites

Browse Source 
Six paid PTY tests wrote their expected plan artifact to a FIXED shared
/tmp path ('/tmp/gstack-test-plan-<mode>.md') and rmSync'd it in
finally — under --retry 1, EVALS_JOBS>1, or two concurrent worktrees, a
sibling's cleanup deletes this run's artifact and the D19 'agent did
not produce expected plan file' assertion fires spuriously. Each test
now mkdtemps its own dir, interpolates the unique path into the agent
prompt (fixture-sourced prompts get a replaceAll + drift guard that
throws if the fixture's literal ever moves), and cleans up its own dir.

The 18 cwd:-into-the-live-repo sites were audited: all deliberate
(skill registry + hermetic pre-trusted dir, in-repo gen renders, git
history reads, slug resolution) — each now carries a
'// LIVE-REPO CWD: <reason>' comment so the next audit can tell
deliberate from accidental.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-29 04:59:48 +00:00
co-authored by Claude Fable 5
parent 0d2f703f28
commit ae5ffefb9a
16 changed files with 205 additions and 155 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-e2e-plan-ceo-split-overflow.test.ts
+27 -17
View File
@@ -35,6 +35,8 @@
import { test } from 'bun:test';
import { describeE2ETier } from './helpers/e2e-gate';
import * as fs from 'node:fs';
import * as os from 'node:os';
import * as path from 'node:path';
import {
runPlanSkillCounting,
ceoStep0Boundary,
@@ -46,30 +48,38 @@ const describeE2E = describeE2ETier('periodic');
const N = 5;
const FLOOR = N - 1; // 4 — must fire at least one AUQ per non-dropped option
const PLAN_PATH = '/tmp/gstack-test-plan-ceo-split-overflow.md';
/** Plan-file target baked into the FORCING_SPLIT_OVERFLOW_CEO fixture prompt.
* Rewritten per-run to a mkdtemp path so concurrent runs (--retry,
* EVALS_JOBS>1, sibling worktrees) never share one /tmp artifact. */
const FIXTURE_PLAN_PATH = '/tmp/gstack-test-plan-ceo-split-overflow.md';
describeE2E('/plan-ceo-review split-overflow regression (periodic)', () => {
test(
`5-option scope decision emits >= ${FLOOR} review-phase AskUserQuestions (no dropping)`,
async () => {
try {
fs.rmSync(PLAN_PATH, { force: true });
} catch {
/* best-effort */
const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-e2e-plan-ceo-split-overflow-'));
const planPath = path.join(tmpDir, 'gstack-test-plan-ceo-split-overflow.md');
const followUpPrompt = FORCING_SPLIT_OVERFLOW_CEO.replaceAll(FIXTURE_PLAN_PATH, planPath);
if (!followUpPrompt.includes(planPath)) {
throw new Error(
`fixture drift: FORCING_SPLIT_OVERFLOW_CEO no longer contains ${FIXTURE_PLAN_PATH} — update FIXTURE_PLAN_PATH`,
);
}
const obs = await runPlanSkillCounting({
skillName: 'plan-ceo-review',
slashCommand: '/plan-ceo-review',
followUpPrompt: FORCING_SPLIT_OVERFLOW_CEO,
isLastStep0AUQ: ceoStep0Boundary,
reviewCountCeiling: N + 3, // hard cap above floor + tolerance
cwd: process.cwd(),
timeoutMs: 1_500_000, // 25 min
env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
});
try {
const obs = await runPlanSkillCounting({
skillName: 'plan-ceo-review',
slashCommand: '/plan-ceo-review',
followUpPrompt,
isLastStep0AUQ: ceoStep0Boundary,
reviewCountCeiling: N + 3, // hard cap above floor + tolerance
// LIVE-REPO CWD: PTY session needs the repo cwd — gstack skill
// registry + hermetic pre-trusted dir (hermetic-env trustedDirs).
cwd: process.cwd(),
timeoutMs: 1_500_000, // 25 min
env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
});
if (!['plan_ready', 'completion_summary', 'ceiling_reached'].includes(obs.outcome)) {
throw new Error(
`split-overflow test FAILED: outcome=${obs.outcome}\n` +
@@ -97,7 +107,7 @@ describeE2E('/plan-ceo-review split-overflow regression (periodic)', () => {
}
} finally {
try {
fs.rmSync(PLAN_PATH, { force: true });
fs.rmSync(tmpDir, { recursive: true, force: true });
} catch {
/* best-effort */
}