Files
gstack/test/memory-cache-injection.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

238 lines
8.5 KiB
TypeScript

/**
* Layer 8 memory cache + injection (plan-tune cathedral T12).
*
* Verifies the PreToolUse hook reads ~/.gstack/free-text-memory.json and
* surfaces matching nuggets via additionalContext-only output (#2035: never a permissionDecision).
* Cache: per-session memory-cache.json populated on first read, sub-1ms
* thereafter (D13 perf).
*/
import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import { spawnSync } from 'child_process';
import { slugCacheFile } from '../lib/bin-context';
const ROOT = path.resolve(import.meta.dir, '..');
const HOOK = path.join(ROOT, 'hosts', 'claude', 'hooks', 'question-preference-hook');
let stateRoot: string;
let fixtureCwd: string;
let cwdSlug: string;
beforeEach(() => {
stateRoot = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-memcache-'));
cwdSlug = 'memcache-fixture';
fixtureCwd = path.join(stateRoot, cwdSlug);
fs.mkdirSync(fixtureCwd, { recursive: true });
});
afterEach(() => {
fs.rmSync(stateRoot, { recursive: true, force: true });
});
function writeMemory(nuggets: Array<{ nugget: string; applies_to_signal_keys: string[]; applied_at?: string }>) {
fs.writeFileSync(path.join(stateRoot, 'free-text-memory.json'), JSON.stringify({ nuggets }));
}
function runHook(stdin: object): { stdout: string; stderr: string; status: number; parsed: any } {
const env: Record<string, string> = {};
for (const [k, v] of Object.entries(process.env)) {
if (v !== undefined) env[k] = v;
}
env.GSTACK_STATE_ROOT = stateRoot;
env.GSTACK_QUESTION_LOG_NO_DERIVE = '1';
delete env.GSTACK_HOME;
// These cases assert the pass-through memoryContext injection. Strip ambient
// Conductor markers so running inside Conductor (CONDUCTOR_WORKSPACE_PATH/PORT
// set) doesn't flip the hook into the [conductor] prose deny instead of pass-through.
delete env.CONDUCTOR_WORKSPACE_PATH;
delete env.CONDUCTOR_PORT;
const res = spawnSync(HOOK, [], {
env,
input: JSON.stringify({ ...stdin, cwd: fixtureCwd }),
encoding: 'utf-8',
cwd: ROOT,
timeout: 30_000,
});
let parsed: any = null;
try { parsed = JSON.parse(res.stdout || '{}'); } catch {}
return {
stdout: res.stdout ?? '',
stderr: res.stderr ?? '',
status: res.status ?? -1,
parsed,
};
}
// ----------------------------------------------------------------------
// Injection behavior
// ----------------------------------------------------------------------
describe('memory injection', () => {
test('injects matching nugget into additionalContext on pass-through', () => {
writeMemory([
{
nugget: 'User prefers verbose explanations with tradeoffs',
applies_to_signal_keys: ['detail-preference'],
applied_at: '2026-05-01T00:00:00Z',
},
]);
// ship-todos-reorganize has signal_key 'detail-preference' per registry.
const r = runHook({
session_id: 's1',
tool_name: 'AskUserQuestion',
tool_use_id: 'tu-1',
tool_input: {
questions: [
{
question: '<gstack-qid:ship-todos-reorganize> Reorganize?',
options: ['A) Accept (recommended)', 'B) Skip'],
},
],
},
});
// #2035: nugget delivery is additionalContext-ONLY — a permissionDecision
// here (any value) would orphan the tool call on CC >= 2.1.89.
expect('permissionDecision' in (r.parsed?.hookSpecificOutput ?? {})).toBe(false);
expect(r.parsed?.hookSpecificOutput?.hookEventName).toBe('PreToolUse');
expect(r.parsed?.hookSpecificOutput?.additionalContext).toContain('verbose explanations');
});
test('does not inject when no nugget matches the signal_key', () => {
writeMemory([
{
nugget: 'Unrelated nugget',
applies_to_signal_keys: ['totally-different-key'],
},
]);
const r = runHook({
session_id: 's2',
tool_name: 'AskUserQuestion',
tool_use_id: 'tu-2',
tool_input: {
questions: [
{
question: '<gstack-qid:ship-todos-reorganize> Reorganize?',
options: ['A) Accept (recommended)', 'B) Skip'],
},
],
},
});
// No nugget → pure pass-through: exit 0 with EXACTLY empty stdout.
expect(r.status).toBe(0);
expect(r.stdout).toBe('');
});
test('caps to 3 most-recent nuggets when many match', () => {
writeMemory([
{ nugget: 'old-1', applies_to_signal_keys: ['detail-preference'], applied_at: '2026-01-01T00:00:00Z' },
{ nugget: 'old-2', applies_to_signal_keys: ['detail-preference'], applied_at: '2026-02-01T00:00:00Z' },
{ nugget: 'old-3', applies_to_signal_keys: ['detail-preference'], applied_at: '2026-03-01T00:00:00Z' },
{ nugget: 'old-4', applies_to_signal_keys: ['detail-preference'], applied_at: '2026-04-01T00:00:00Z' },
{ nugget: 'newest', applies_to_signal_keys: ['detail-preference'], applied_at: '2026-05-01T00:00:00Z' },
]);
const r = runHook({
session_id: 's3',
tool_name: 'AskUserQuestion',
tool_use_id: 'tu-3',
tool_input: {
questions: [
{
question: '<gstack-qid:ship-todos-reorganize> Reorganize?',
options: ['A) Accept (recommended)', 'B) Skip'],
},
],
},
});
const ctx = r.parsed?.hookSpecificOutput?.additionalContext || '';
expect(ctx).toContain('newest');
expect(ctx).toContain('old-4');
expect(ctx).toContain('old-3');
expect(ctx).not.toContain('old-1');
});
test('memory injection works alongside deny enforcement', () => {
writeMemory([
{
nugget: 'User prefers reorganizing for clarity',
applies_to_signal_keys: ['detail-preference'],
applied_at: '2026-05-01T00:00:00Z',
},
]);
// Set a never-ask preference and check both deny AND memory are surfaced.
// The hook resolves the project bucket from gstack-slug's versioned
// slug-cache entry (#2901), which the skill preamble writes first.
const cacheFile = slugCacheFile(stateRoot, fixtureCwd);
fs.mkdirSync(path.dirname(cacheFile), { recursive: true });
fs.writeFileSync(cacheFile, `v2:${cwdSlug}`);
fs.mkdirSync(path.join(stateRoot, 'projects', cwdSlug), { recursive: true });
fs.writeFileSync(
path.join(stateRoot, 'projects', cwdSlug, 'question-preferences.json'),
JSON.stringify({ 'ship-todos-reorganize': 'never-ask' }),
);
const r = runHook({
session_id: 's4',
tool_name: 'AskUserQuestion',
tool_use_id: 'tu-4',
tool_input: {
questions: [
{
question: '<gstack-qid:ship-todos-reorganize> Reorganize?',
options: ['A) Accept (recommended)', 'B) Skip'],
},
],
},
});
// ship-todos-reorganize is two-way per registry — enforcement should fire.
expect(r.parsed?.hookSpecificOutput?.permissionDecision).toBe('deny');
expect(r.parsed?.hookSpecificOutput?.permissionDecisionReason).toContain('plan-tune auto-decide');
// Memory context isn't injected on deny path (it's already in the reason),
// but the deny reason should mention the auto-decision clearly.
});
});
// ----------------------------------------------------------------------
// Cache behavior
// ----------------------------------------------------------------------
describe('per-session memory cache', () => {
test('first read writes cache; subsequent reads use cache', () => {
writeMemory([
{ nugget: 'cached nugget', applies_to_signal_keys: ['detail-preference'] },
]);
runHook({
session_id: 'cache-test',
tool_name: 'AskUserQuestion',
tool_use_id: 'tu-c1',
tool_input: {
questions: [
{ question: '<gstack-qid:ship-todos-reorganize> Q', options: ['A', 'B'] },
],
},
});
const cachePath = path.join(stateRoot, 'sessions', 'cache-test', 'memory-cache.json');
expect(fs.existsSync(cachePath)).toBe(true);
const cached = JSON.parse(fs.readFileSync(cachePath, 'utf-8'));
expect(cached.nuggets).toHaveLength(1);
expect(cached.nuggets[0].nugget).toBe('cached nugget');
});
test('cache miss when canonical file empty/missing → empty nuggets', () => {
const r = runHook({
session_id: 'empty',
tool_name: 'AskUserQuestion',
tool_use_id: 'tu-e',
tool_input: {
questions: [
{ question: '<gstack-qid:ship-todos-reorganize> Q', options: ['A', 'B'] },
],
},
});
// No nugget → pure pass-through: exit 0 with EXACTLY empty stdout.
expect(r.status).toBe(0);
expect(r.stdout).toBe('');
});
});