Files
gstack/test/skill-e2e-plan-tune.test.ts
T
f30b7b788a v1.91.13.0 fix: severe bug wave (autoplan guard, land-and-deploy CI gate, project identity, gbrain, review gates) (#3013)
* fix(land-and-deploy): never merge over red, pending or missing CI (#2995)

/land-and-deploy gated only on required checks, so a repo with none
(every GitHub Free private repo, any repo without branch protection)
skipped the CI wait and could merge over red CI. The verdict now comes
from bin/gstack-ci-gate, a tested helper bound to the head SHA: all
checks by default, cancel/unknown buckets fail, NO_CHECKS needs explicit
per-head approval, and both merge commands (including --auto) run only
after a PASS for the same SHA they pin with --match-head-commit.

Co-authored-by: harshitgavita-07 <harshit.gavita@gmail.com>

* fix(slug): give nested-group projects their own state bucket and verify checkpoint identity (#3003, #2901)

gstack-slug kept only the last two remote path segments, so
customer-a/product/repo and customer-b/product/repo shared one bucket
and /context-restore could present another project's checkpoint.

- One canonical-remote rule (bash + TS, golden vectors) used by all six
  resolvers: lowercased host, no userinfo/port/.git, Azure DevOps and
  Bitbucket Server normalized. 3+ segment remotes get
  <last-two>-<16 hex>; two-segment remotes (all of GitHub) are unchanged.
- Versioned sticky cache (v2:) keeps cache hits git-free.
- context-save stamps the credential-free remote and root;
  context-restore only treats this project's checkpoints as latest,
  reports foreign/unverified ones first, and treats a different root
  with the same remote (Conductor handoff) as information.
- gstack-slug --adopt-legacy copies only files the user confirms.
- question-preference-hook reads the same versioned cache, so never-ask
  preferences fire; unknown identity asks instead of auto-deciding.

* fix(gbrain): brain context loads, managed sync works, memory sync stops duplicating (#2883, #2985, #2922)

- brain-context-load called 'gbrain list_pages' (an MCP tool name), so
  every skill's brain context was 0 bytes. It now uses 'gbrain list'
  with gbrain's real filter flags, and prints one line when queries fail.
- The code-stage sync always passes --no-pull (managed gbrain >= 0.51
  refuses without it); a gbrain that rejects the flag fails with an
  upgrade message and is never retried without it. stderr is streamed
  with a bounded tail and quoted in failure summaries.
- /sync-gbrain gains --sources (and GSTACK_MEMORY_INGEST_SOURCES); by
  default it skips types already synced through a federated curated
  source, so curated pages stop being re-duplicated.

Co-authored-by: Vitor Cepeda Lopes <vitor@vitorcepedalopes.com>
Co-authored-by: harshitgavita-07 <harshit.gavita@gmail.com>

* fix(codex,cso): clean Codex reviews stop failing; semgrep and trivy SARIF results import (#2769, #3011)

- Codex review gate is PASS / FAIL / UNVERIFIED. Untagged output (what
  a clean 'codex review --base' prints) is UNVERIFIED, not FAIL, and
  never a false PASS; P2/P3-only output passes.
- import-sarif resolves semgrep's undeclared %SRCROOT% and trivy's
  ROOTPATH (including git-URL targets) through explicit, captured
  mappings; declared bases must sit inside the source root or the
  run's checkout, URIs are percent-decoded, and rejected results are
  counted with rule, base and path instead of silently dropped.

* fix: version strings are not IPs, failed update checks are not 'up to date', private security reporting (#2856, #2786, #2984)

- The pre-push redact hook exempts a root VERSION file that is only a
  version string and the version token in CHANGELOG release headings;
  the engine allowlist is untouched.
- gstack-update-check caches an unreadable remote as CHECK_FAILED with
  a short TTL instead of UP_TO_DATE; /gstack-upgrade never reports
  'latest' after a failed check.
- SECURITY.md points reporters at GitHub private vulnerability
  reporting.
- pr-title-sync (pull_request_target, write token) pins actions/checkout
  to a reviewed SHA.

* fix(autoplan): publication guard accepts real Claude Code journals (#3007, #3009, #2968, #2977, #2986, #3006)

The guard required a session journal to start with a user message, but
Claude Code starts it with SessionStart hook attachments (and a forked
compacted session starts with a compact_boundary), so every phase was
denied for anyone with a SessionStart hook. Windows path spellings
(C:/, /c/, drive case) were rejected too.

- Reader accepts the captured startup, compact, clear and fork shapes
  (claude 2.1.284 fixture), computes root uniqueness over every
  candidate, and returns typed reason codes instead of one string.
- Hard denials (competing root, foreign cwd, sidechain, agent, cycle,
  malformed, identity) say what happened and how to run the reviews by
  hand; unflushed journals still retry.
- A well-formed, stable journal whose root shape is unrecognized now
  warns ('phase publication was NOT verified') and continues, without
  overriding Claude Code's own permission check; no bypass switch.
- Windows paths fold before validation, so '..' is still rejected.
- Periodic drift canary runs the reader on fresh journals from the
  pinned claude.

Co-authored-by: Charles M Berg <77517285+CharlesBerg85@users.noreply.github.com>
Co-authored-by: laurenbdaniels-coder <264343335+laurenbdaniels-coder@users.noreply.github.com>
Co-authored-by: Jordan Mayer <176445995+maydaycyber@users.noreply.github.com>
Co-authored-by: elmesery-dev <elmesery.dev@gmail.com>

* v1.91.13.0: severe bug fix wave release notes, stale gbrain verbs in docs

* test: seed the versioned slug cache in the memory-injection deny case (#2901)

The preference hook now resolves the project bucket from gstack-slug's
v2 slug-cache entry instead of basename(cwd); this fixture still wrote
preferences under the basename bucket without the entry the skill
preamble always writes first.

* fix: full-suite follow-ups for the fix wave

- gstack-slug's --help heredoc is over 512B, so it gets the BASH_COMPAT=50
  pipe-deadlock guard like the other bins.
- Refresh the codex/factory ship goldens for the plan-gates slug change.
- The periodic lane gains the autoplan journal drift canary (107 paid
  files); raise the eval-slices cap to 25 so every slice still starts
  at once until its recorded duration lets the planner pack it.

* fix(plan-eng-review): clearer Step 0 sequencing, write routes and section outputs

The workflow judge scored plan-eng-review's instructions at
actionability 3.67 (bar 4) on text unchanged from main. Resolve the
ambiguities it named together, without changing any gate or output:
Step 0 names the Read's order and keeps one STOP; the pending-call,
read-only, forbidden-write and failed-save rules become one Write
routes block; header/label limits and grid checks are concrete;
Performance gets a checklist; each section has a stated output shape;
Lake Score is defined. Same total length (parity cap).

---------

Co-authored-by: harshitgavita-07 <harshit.gavita@gmail.com>
Co-authored-by: Vitor Cepeda Lopes <vitor@vitorcepedalopes.com>
Co-authored-by: Charles M Berg <77517285+CharlesBerg85@users.noreply.github.com>
Co-authored-by: laurenbdaniels-coder <264343335+laurenbdaniels-coder@users.noreply.github.com>
Co-authored-by: Jordan Mayer <176445995+maydaycyber@users.noreply.github.com>
Co-authored-by: elmesery-dev <elmesery.dev@gmail.com>
2026-10-02 11:11:00 -07:00

192 lines
7.3 KiB
TypeScript

import { beforeAll, afterAll, expect } from 'bun:test';
import { JUDGE_MS, CAPTURE_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 { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
const evalCollector = createEvalCollector('e2e-plan-tune');
// ---------------------------------------------------------------------------
// /plan-tune E2E: verify the skill recognizes plain-English intent and hits
// the right binary paths without CLI subcommand syntax.
//
// This is a gate-tier test — if /plan-tune requires memorized subcommands or
// fails on plain English, that is a regression of the core v1 DX promise.
// ---------------------------------------------------------------------------
describeIfSelected('PlanTune E2E', ['plan-tune-inspect'], () => {
let workDir: string;
let gstackHome: string;
let slug: string;
beforeAll(() => {
workDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-plan-tune-'));
gstackHome = path.join(workDir, '.gstack-home');
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: workDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
fs.writeFileSync(path.join(workDir, 'README.md'), '# test\n');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'initial']);
// Copy the /plan-tune skill (extract the flow section only — full template
// is ~45KB and includes preamble boilerplate the agent doesn't need).
copyDirSync(path.join(ROOT, 'plan-tune'), path.join(workDir, 'plan-tune'));
// Copy required bins — the skill references these by path.
const binDir = path.join(workDir, 'bin');
fs.mkdirSync(binDir, { recursive: true });
for (const script of [
'gstack-slug',
'gstack-config',
'gstack-state-root.sh',
'gstack-remote-identity.sh',
'gstack-question-log',
'gstack-question-preference',
'gstack-developer-profile',
'gstack-builder-profile',
]) {
const src = path.join(ROOT, 'bin', script);
if (fs.existsSync(src)) {
fs.copyFileSync(src, path.join(binDir, script));
fs.chmodSync(path.join(binDir, script), 0o755);
}
}
// gstack-developer-profile --derive imports from scripts/ — copy those too.
const scriptsDir = path.join(workDir, 'scripts');
fs.mkdirSync(scriptsDir, { recursive: true });
for (const src of ['question-registry.ts', 'psychographic-signals.ts', 'archetypes.ts', 'one-way-doors.ts']) {
fs.copyFileSync(path.join(ROOT, 'scripts', src), path.join(scriptsDir, src));
}
// Compute slug the same way the binary does (basename fallback).
slug = path.basename(workDir).replace(/[^a-zA-Z0-9._-]/g, '');
// Seed a few question-log entries so "review questions" has something to show.
const projectDir = path.join(gstackHome, 'projects', slug);
fs.mkdirSync(projectDir, { recursive: true });
const entries = [
{
ts: '2026-04-10T10:00:00Z',
skill: 'plan-ceo-review',
question_id: 'plan-ceo-review-mode',
question_summary: 'Which review mode?',
category: 'routing',
door_type: 'two-way',
options_count: 4,
user_choice: 'expand',
recommended: 'selective',
followed_recommendation: false,
session_id: 's1',
},
{
ts: '2026-04-11T10:00:00Z',
skill: 'ship',
question_id: 'ship-test-failure-triage',
question_summary: 'Test failed',
category: 'approval',
door_type: 'one-way',
options_count: 3,
user_choice: 'fix-now',
recommended: 'fix-now',
followed_recommendation: true,
session_id: 's2',
},
{
ts: '2026-04-12T10:00:00Z',
skill: 'ship',
question_id: 'ship-changelog-voice-polish',
question_summary: 'Polish changelog voice',
category: 'approval',
door_type: 'two-way',
options_count: 2,
user_choice: 'skip',
recommended: 'accept',
followed_recommendation: false,
session_id: 's3',
},
];
fs.writeFileSync(
path.join(projectDir, 'question-log.jsonl'),
entries.map((e) => JSON.stringify(e)).join('\n') + '\n',
);
// Pre-set question_tuning=true so the skill doesn't enter the first-time setup flow.
const cfgDir = path.join(gstackHome);
fs.mkdirSync(cfgDir, { recursive: true });
fs.writeFileSync(path.join(cfgDir, 'config.yaml'), 'question_tuning: true\n');
});
afterAll(() => {
try { fs.rmSync(workDir, { recursive: true, force: true }); } catch {}
finalizeEvalCollector(evalCollector);
});
// -------------------------------------------------------------------------
// Plain-English intent: "review my questions"
// -------------------------------------------------------------------------
testConcurrentIfSelected('plan-tune-inspect', async () => {
const result = await runSkillTest({
prompt: `Read ./plan-tune/SKILL.md for the /plan-tune skill instructions.
The user has invoked /plan-tune and says: "Review the questions I've been asked recently."
IMPORTANT:
- Use GSTACK_HOME="${gstackHome}" as an environment variable for all bin calls.
- Replace any ~/.claude/skills/gstack/bin/ references with ./bin/ (relative path).
- Replace any ~/.claude/skills/gstack/scripts/ references with ./scripts/.
- Do NOT use AskUserQuestion.
- Do NOT implement code changes.
- Route the user's intent to the right section of the skill (Review question log).
- Show them the logged questions with counts and the follow/override ratio.`,
workingDirectory: workDir,
maxTurns: 15,
allowedTools: ['Bash', 'Read', 'Grep', 'Glob'],
timeout: JUDGE_MS,
testName: 'plan-tune-inspect',
runId,
});
logCost('/plan-tune review', result);
const output = result.output.toLowerCase();
// Agent must have surfaced at least 2 of the 3 logged question_ids
const mentionsCEO = output.includes('plan-ceo-review-mode') || output.includes('review mode');
const mentionsShipTest = output.includes('ship-test-failure-triage') || output.includes('test failed');
const mentionsChangelog = output.includes('changelog') || output.includes('ship-changelog-voice-polish');
const foundCount = [mentionsCEO, mentionsShipTest, mentionsChangelog].filter(Boolean).length;
// Agent should note override behavior (user overrode CEO review and changelog polish)
const noticedOverride =
output.includes('overrid') ||
output.includes('skip') ||
output.includes('expand');
const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
recordE2E(evalCollector, '/plan-tune', 'Plan-tune inspection flow (plain English)', result, {
passed: exitOk && foundCount >= 2,
});
expect(exitOk).toBe(true);
expect(foundCount).toBeGreaterThanOrEqual(2);
if (!noticedOverride) {
console.warn('Agent did not surface override/skip behavior from the log');
}
}, CAPTURE_MS);
});