mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-11 16:50:20 +02:00
* fix(careful): warn on chained rm even when the last target is safe The safe-exception block whitelisted rm -rf of build artifacts by extracting targets with a single greedy match (.*rm ...), which only ever inspects the LAST rm in the command. A chain like 'rm -rf /; rm -rf node_modules' was therefore judged solely by its trailing safe target and allowed without warning, waving through the destructive 'rm -rf /'. Gate the shortcut to single rm invocations: when any shell separator (; | & newline, incl. JSON-escaped \n/\r from the grep extraction path) is present, fall through to the destructive-pattern check, which warns on any recursive rm. Single-command artifact cleanups still allow. Adds 3 regression tests covering semicolon and && chains in both orders. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * harden(careful): substitution separators + capital -R recursive flag (#2039) Two residual fail-opens in the same guard PR #2040 hardened, both verified by executing the script pre-fix: - rm -rf $(./wipe-all)/node_modules silently allowed: the substitution token ends in a whitelisted suffix and the safe-exception early exit skipped ALL downstream checks. $( and backtick now count as chain separators; plain $VAR expansion stays allowed. - rm -R / silently allowed: both greps required a lowercase r in the flag cluster; capital -R is the documented BSD/macOS recursive flag. Both greps now match -[a-zA-Z]*[rR]. Six new tests: substitution x2 -> ask, capital-R x2 -> ask, rm -Rf node_modules single-command -> still allowed, escaped-newline branch (existing code, previously untested), and a pinned deliberate FP (cd app && rm -rf node_modules -> ask) documenting the fail-closed direction on chains. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(context-restore): prefer the current branch's own checkpoint (#2052) All worktrees of a repo share one origin-derived slug, so they share one `~/.gstack/projects/<slug>/checkpoints/` dir. `/context-restore` loaded the newest checkpoint across the whole dir, so in one worktree it could silently restore a *sibling worktree's* newer checkpoint. Step 1 now orders candidates current-branch-first (read from each file's `branch:` frontmatter), keeping other branches as a fallback. A branch is checked out in at most one worktree, so this stops cross-worktree contamination while preserving Conductor cross-branch handoff: when the current branch has no checkpoint of its own, the full newest-first set is still used. - scan the 200 newest before partitioning so a current-branch checkpoint sitting below a burst of sibling saves is still found; output still capped at 20 - non-git / detached HEAD / branchless legacy saves fall back to the old newest-first behavior (back-compat) - +5 regression tests in context-save-hardening.test.ts (the #2052 bug case fails on the old pipeline); regenerated SKILL.md + proactive-suggestions.json Fixes #2052 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(gbrain): pass --confirm-destructive on drift re-register (#1985) ensureSourceRegistered() handles match-but-different-path by removing the old source then re-adding it at the new path. The remove was issued as `gbrain sources remove <id> --yes`, but gbrain >= 0.42 gates `sources remove` behind `--confirm-destructive` (`--yes` alone no longer suppresses the data-loss prompt). The remove therefore fails with "To proceed, pass --confirm-destructive", which ensureSourceRegistered surfaces as "source registration failed" — aborting the entire /sync-gbrain code stage for any already-registered source whose path has drifted. The memory and brain-sync stages still pass, so the code index silently stops refreshing. The orchestrator's own safeSourcesRemove() already passes --confirm-destructive; this brings the lib helper in line with that convention. Keeps --yes for older gbrain. Tests: extend the fake gbrain shim in gbrain-sources.test.ts to simulate the gbrain >= 0.42 guard (remove without --confirm-destructive exits 1), update the drift re-register assertion, and add a regression test that proves the drift path no longer throws. Both fail on main with the exact "To proceed, pass --confirm-destructive" error and pass with the fix. Fixes #1985 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * harden(gbrain-sources): route drift remove through #1734 guards + realpath drift check Absorbing #2031 un-blocked a destructive remove that bypassed the #1734 data-loss guards: ensureSourceRegistered's drift path issued `gbrain sources remove` directly, without the detectAutopilot + decideSourceRemove checks every other remove routes through via safeSourcesRemove. gbrain >= 0.42's own prompt was accidentally blocking that path; with --confirm-destructive passed it is live again. - Drift remove now refuses LOUDLY (throws, actionable message) while an autopilot is active or when decideSourceRemove disallows; a silent changed=false would hide the drifted registration. - decideSourceRemove's extraArgs (--keep-storage when supported) propagate to the remove call, matching safeSourcesRemove. - Drift is realpath-normalized before being declared: a symlink alias of the same directory (macOS /tmp -> /private/tmp) is a match, not drift — the probable cause of #1985's reporter hitting the remove on an unmoved repo. - Drift fires a loud stderr line (old -> new path); perpetual drift in logs is the trigger for promoting #1985's reindex-in-place design. Tests: autopilot-active refusal (no remove in call log), fail-closed refusal on unreadable sources list, --keep-storage propagation, symlink-alias no-drift; existing drift tests pin the guard probes so a live autopilot on the dev machine can't flip them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(developer-profile): exclude mode:resources rows from SESSION_COUNT, TIER, NUDGE_ELIGIBLE (#2067) Every /office-hours run appends a mode:"resources" bookkeeping row alongside the real session row, so --read double-counted sessions (~2x): tiers promoted early and the builder-to-founder nudge armed prematurely. The file already filtered resources rows for LAST_*/CROSS_PROJECT; the same realSessions filter now feeds SESSION_COUNT/TIER, and the nudge predicate is the faithful allowlist (mode === 'builder') so a future mode #4 fails closed instead of re-opening this bug. 8 regression tests: count vs resources noise, tier boundaries both sides, nudge false-with-noise / true-at-3-builders, cross-project trailing row. Absorbed from PR #1991 by @mvann (fix + tests commits; the PR's version-bump commit is superseded by this wave's consolidated release commit). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(hooks): passThrough() two-branch contract — never emit permissionDecision:'defer' (#2035, #2006) Every AskUserQuestion died with "Tool result missing due to internal error" on current Claude Code builds (Desktop 1.14271.0, CC 2.1.177). Root cause: the question-preference-hook emitted permissionDecision:'defer' on every pass-through path. 'defer' is a real PreToolUse value, but since CC v2.1.89 its semantics are "pause this tool call for external resumption" (headless resume) — never "abstain". Interactive sessions have nothing to resume the paused call, so the tool orphaned. Pre-2.1.89 builds ignored the unknown value, which is why the hook worked when it shipped and broke later. The fix is the two-branch pass-through contract: - no context -> exit 0 with EXACTLY empty stdout - memory nuggets present -> hookSpecificOutput with hookEventName + additionalContext ONLY (the documented shape; plan-tune Layer 8 memory injection ships through this branch and keeps working) defer() is renamed passThrough() so the function says what it does, and docs/spikes/claude-code-hook-mutation.md's protocol contract (cited by the hook header) is corrected in the same commit — it taught '"defer" — let permission flow continue' and was the reintroduction vector. Test contract rewritten in the same commit (13 assertions across 3 files, verified fail-first against the unfixed hook): pass-through paths assert exact-empty stdout (a garbage/partial write cannot slip past an optional-chained parse), the nugget path asserts permissionDecision is ABSENT while additionalContext survives, and a new tripwire asserts no non-deny path ever puts the string "permissionDecision" on stdout. The deny (auto-decide) and Conductor prose-redirect paths are unchanged. Deployment: no migration needed — settings.json points at the absolute bash shim which execs the .ts live; /gstack-upgrade delivers the fix. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(one-way-doors): unify credential noun net + wire it into the runtime (#2024) Library fix: revoke/reset/rotate now share ONE noun alternation (api key, token, secret, credential, access key, password) with optional plural s?. Pre-fix leaks: "reset my secret", "reset my access key", "revoke my secret" (mismatched per-verb lists) and every plural form ("rotate the credentials", "revoke all tokens" — \b(...)\b cannot match a trailing s). Runtime wiring — the regexes could never fire in production before: - gstack-question-preference --check gains --summary-stdin: the question text pipes via stdin (never argv — summaries carry quotes/newlines/shell metacharacters) and feeds isOneWayDoor alongside the id, so an ad-hoc destructive question with a stored never-ask preference now forces ASK_NORMALLY. Empty/absent stdin keeps exact id-only semantics. - question-preference-hook falls back to classifyQuestion(question text) when the registry lookup misses, so unregistered destructive questions pass through to a human instead of auto-deciding. - question-tuning resolver prose shows the piped form (SKILL.md regen lands in the wave's release commit). Tripwires (verified fail-first): full verbs x nouns x singular/plural matrix with the #2024 repro rows, benign-summary no-over-match rows, stdin transport survival (quotes/newlines), empty-stdin fail-safe, and hook fallback both directions (destructive -> pass-through, benign -> deny). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(design): loud integer-flag contract for --count/--retry/--timeout (#2032) design variants --count abc silently generated ZERO variants and exited 0: parseInt(NaN) flowed through Math.min into the generation loop bound. The same NaN class was live on the two sibling flags in the same file: --retry abc made generate() a silent no-op (attempt <= NaN never true, null output, exit 0) and --timeout abc killed the serve board ~immediately (setTimeout(NaN)). New design/src/flag-utils.ts: parseIntFlag (pure, unit-testable) + normalizeIntFlag (CLI wrapper). Contract matches the --viewports precedent (error loudly on nonsense — these commands spend real image-API money, a silent fixup hides typos from calling agents): undefined -> default; bare flag/empty/non-integer ("3.7" rejected, not truncated)/below-min -> exit 1 with usage hint; above-max -> clamp with stderr warning. --count normalizes at the variants() consumption site so programmatic callers are covered, with the ceiling derived from STYLE_VARIATIONS.length instead of a magic 7; the CLI passes the raw flag through (a pre-parseInt would truncate "3.7"). Tripwires live in test/design-flag-utils.test.ts — deliberately under test/, not design/test/, which is invisible to the bun test glob, TEST_ROOTS, and every workflow (wiring design/test/ into CI is a captured TODO). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(gbrain): thin-client state — remote-MCP brains no longer classify as broken-config (#2051) A thin client (remote-HTTP MCP brain, no local engine by design) probed `gbrain sources list`, which gbrain's dispatch guard REFUSES on thin clients (exit 1, no recognized error string), so the classifier fell to its defensive broken-config default and every suppression gate silently hid brain-aware blocks from exactly the users on a shared team brain. New 'thin-client' state, detected PRE-probe from gbrain's own remote_mcp config marker via the existing gbrainConfigPath() helper (mirrors gbrain's isThinClient(); honors GBRAIN_HOME; zero network, immune to error-string drift), with a /thin[- ]client/ stderr backstop in the probe catch. Remote reachability is deliberately NOT probed by the classifier — that is the #1964 pathology; gbrain calls degrade gracefully at use time, and the detect JSON says so honestly (gbrain_thin_client: {probed: false}). The state is admitted at every suppression gate — gstack-gbrain-detect --is-ok (drives setup + gbrain-refresh), gen-skill-docs' detection override, gstack-config gbrain-refresh — while the sync stages (code/memory/dream) SKIP with an accurate reason: code indexing runs on the brain server, memory syncs via the remote brain's artifacts pull. The two consumer classes need opposite answers, which is why this is a distinct state and not a skip-the-probe special case. sync-gbrain Step 1.5 and setup-gbrain prose route thin-client to proceed, never into broken-config remediation. detectMcpMode secondary generalization: url-match against the config's remote_mcp.mcp_url (deterministic — gbrain mounts at the generic /mcp path) -> name pattern gbrain[-_]* -> stdio command token; gbrain_mcp_mode stays a 3-value enum. Tripwires: end-to-end --is-ok exits 0 on a thin-client fixture AND still exits 1 on broken-config (the gate didn't widen); pre-probe + stderr-fallback classifier paths; 4 detectMcpMode identification cases incl. a non-matching url that must NOT false-positive. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * release: v1.60.0.0 — regen SKILL.md, VERSION, CHANGELOG, TODOS follow-ups - Regenerate all SKILL.md from templates (question-tuning --summary-stdin prose from #2024, context-restore branch preference from PR #2054, sync-gbrain/setup-gbrain thin-client prose from #2051) + llms.txt. - VERSION + package.json -> 1.60.0.0 (bin/gstack-next-version, queue-aware: #1815 claims 1.59.0.0, #2213 claims 1.59.1.0). - CHANGELOG release summary + itemized entry crediting @jbetala7 (x3) and @mvann. - TODOS.md: three eng-review follow-ups (design/test CI wiring + documented pre-existing retry-after flake, /context-save worktree identity, gbrain reindex-in-place conditional on the new drift log). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(resolvers): compress --summary-stdin preamble prose to fit parity budget; re-bless ship goldens The v1.57.7.0 parity suite caps investigate's generated size at 1.09x baseline; the #2024 question-tuning prose (duplicated into every tier->=2 skill) tipped it to 1.092. Compressed to a single inline command + short pointer (the full rationale lives in bin/gstack-question-preference's header and the one-way-doors module docs). Ship goldens re-blessed against the final resolver text (conscious template-change acknowledgment, per the golden-file regression contract). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): office-hours-spec-review turn budget fits the carved skill layout (#2473) The test failed deterministically with error_max_turns at 9 turns on main and this branch alike (CI attempt logs + local main repro). Root cause from the failing transcript: the Spec Review Loop content is carved out of office-hours/SKILL.md into office-hours/sections/, so the agent needs discovery hops (grep SKILL.md -> ls sections/ -> read the section) before it can write — 8 tool turns + the closing text turn = 9 > the 8-turn budget, which predates the carve. Observed failures wrote a CORRECT summary on tool turn 8 and died on the closing turn. maxTurns 8 -> 12. Verified: PASS locally post-fix (7 turns this run — the extra headroom absorbs discovery-path nondeterminism). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): review-dashboard-via session budget survives runner contention (#2473) The test failed on CI (and its baseline run) with the timeout signature: 0 turns, $0.00, exactly 183s, 3/3 attempts — the spawned claude -p session never emitted a single stream event before the 180s inner timeout. The file's tests run concurrently on one runner; session startup queues behind sibling sessions, and this test had the tightest budget in the file (the 240s-budget tests in the same job passed). A clean local run takes 270s wall for 4 turns, confirming 180s was too tight even without contention. Inner timeout 180s -> 300s; outer bun timeout 240s -> 360s to keep headroom over the inner budget. Verified: PASS locally post-fix (4 turns, 270s). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): retro-base-branch session budget survives runner contention (#2473) Same class as review-dashboard-via, one test over in the same file: /retro is a long multi-step flow whose clean pass measures 225-239s — a coin flip against the 240s inner budget. First CI run passed at 225s; the rerun timed out at the 240s line on all 3 attempts (exitReason "timeout"); the local verification run passed at 239s, ONE second under the old cap. Inner timeout 240s -> 360s; outer bun timeout 300s -> 480s for headroom. Verified: PASS locally post-fix (17 turns, 239s). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Michael Vann <9221873+mvann@users.noreply.github.com>
462 lines
16 KiB
TypeScript
462 lines
16 KiB
TypeScript
/**
|
|
* /plan-tune cathedral E2E (T16) — 5 scenarios, all gate tier per D12.
|
|
*
|
|
* Each scenario verifies that the cathedral's substrate works end-to-end
|
|
* against a real `claude -p` invocation. Unit tests in test/{question-log-hook,
|
|
* question-preference-hook, declared-annotation, distill-*}.test.ts cover
|
|
* deterministic plumbing; this file proves the agent obeys the hook
|
|
* contracts in a live session.
|
|
*
|
|
* Touchfile registration in test/helpers/touchfiles.ts:
|
|
* - plan-tune-hook-capture
|
|
* - plan-tune-enforcement
|
|
* - plan-tune-annotation
|
|
* - plan-tune-codex-import
|
|
* - plan-tune-dream-cycle
|
|
*
|
|
* Each scenario uses GSTACK_STATE_ROOT to isolate from the user's real
|
|
* ~/.gstack (per cathedral T1 + Codex D16 fix). Cost budget ~$3-4/scenario.
|
|
*/
|
|
|
|
import { beforeAll, afterAll, expect } from 'bun:test';
|
|
import {
|
|
ROOT,
|
|
describeIfSelected,
|
|
testConcurrentIfSelected,
|
|
copyDirSync,
|
|
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 collector = createEvalCollector('e2e-plan-tune-cathedral');
|
|
|
|
afterAll(() => {
|
|
finalizeEvalCollector(collector);
|
|
});
|
|
|
|
/** Scaffold a fixture project with the bins + scripts the cathedral needs. */
|
|
function scaffoldFixture(prefix: string): { workDir: string; stateRoot: string; slug: string } {
|
|
const workDir = fs.mkdtempSync(path.join(os.tmpdir(), prefix));
|
|
const stateRoot = path.join(workDir, '.gstack-state');
|
|
fs.mkdirSync(stateRoot, { recursive: true });
|
|
|
|
// git init so gstack-slug resolves a deterministic slug.
|
|
spawnSync('git', ['init', '-b', 'main'], { cwd: workDir, stdio: 'pipe' });
|
|
spawnSync('git', ['config', 'user.email', 't@t.com'], { cwd: workDir, stdio: 'pipe' });
|
|
spawnSync('git', ['config', 'user.name', 'T'], { cwd: workDir, stdio: 'pipe' });
|
|
fs.writeFileSync(path.join(workDir, 'README.md'), '# cathedral fixture\n');
|
|
spawnSync('git', ['add', '.'], { cwd: workDir, stdio: 'pipe' });
|
|
spawnSync('git', ['commit', '-m', 'init'], { cwd: workDir, stdio: 'pipe' });
|
|
|
|
// Copy bins.
|
|
const binDir = path.join(workDir, 'bin');
|
|
fs.mkdirSync(binDir, { recursive: true });
|
|
for (const script of [
|
|
'gstack-slug',
|
|
'gstack-config',
|
|
'gstack-paths',
|
|
'gstack-question-log',
|
|
'gstack-question-preference',
|
|
'gstack-developer-profile',
|
|
'gstack-codex-session-import',
|
|
'gstack-distill-free-text',
|
|
'gstack-distill-apply',
|
|
]) {
|
|
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);
|
|
}
|
|
}
|
|
|
|
// Copy scripts that the bins import.
|
|
const scriptsDir = path.join(workDir, 'scripts');
|
|
fs.mkdirSync(scriptsDir, { recursive: true });
|
|
for (const f of [
|
|
'question-registry.ts',
|
|
'psychographic-signals.ts',
|
|
'archetypes.ts',
|
|
'one-way-doors.ts',
|
|
'declared-annotation.ts',
|
|
]) {
|
|
const src = path.join(ROOT, 'scripts', f);
|
|
if (fs.existsSync(src)) fs.copyFileSync(src, path.join(scriptsDir, f));
|
|
}
|
|
|
|
// Copy hooks dir.
|
|
copyDirSync(path.join(ROOT, 'hosts', 'claude', 'hooks'), path.join(workDir, 'hosts', 'claude', 'hooks'));
|
|
|
|
const slug = path.basename(workDir).replace(/[^a-zA-Z0-9._-]/g, '');
|
|
return { workDir, stateRoot, slug };
|
|
}
|
|
|
|
function cleanupFixture(workDir: string): void {
|
|
try {
|
|
fs.rmSync(workDir, { recursive: true, force: true });
|
|
} catch {
|
|
// best-effort
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Scenario 1: Hook capture — PostToolUse hook writes to question-log.jsonl
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describeIfSelected('PlanTune cathedral E2E: hook capture', ['plan-tune-hook-capture'], () => {
|
|
let fixture: ReturnType<typeof scaffoldFixture>;
|
|
|
|
beforeAll(() => {
|
|
fixture = scaffoldFixture('cathedral-cap-');
|
|
});
|
|
|
|
afterAll(() => {
|
|
cleanupFixture(fixture.workDir);
|
|
});
|
|
|
|
testConcurrentIfSelected('hook directly invoked → log fills', async () => {
|
|
// Direct hook invocation simulates Claude Code's PostToolUse delivery.
|
|
// E2E verifies the hook + bin chain works against real bins on disk
|
|
// (the unit test exercises this with mocks).
|
|
const hookPath = path.join(fixture.workDir, 'hosts', 'claude', 'hooks', 'question-log-hook');
|
|
const payload = {
|
|
session_id: 'cathedral-e2e-cap',
|
|
tool_name: 'AskUserQuestion',
|
|
tool_use_id: 'tu-cap-1',
|
|
tool_input: {
|
|
questions: [
|
|
{
|
|
question:
|
|
'D1 — Cathedral E2E capture <gstack-qid:ship-test-failure-triage>\nRecommendation: A',
|
|
options: ['A) Fix now (recommended)', 'B) Investigate'],
|
|
},
|
|
],
|
|
},
|
|
tool_response: { answers: [{ option_label: 'A) Fix now (recommended)' }] },
|
|
cwd: fixture.workDir,
|
|
};
|
|
const res = spawnSync(hookPath, [], {
|
|
env: {
|
|
...process.env,
|
|
GSTACK_STATE_ROOT: fixture.stateRoot,
|
|
GSTACK_QUESTION_LOG_NO_DERIVE: '1',
|
|
},
|
|
input: JSON.stringify(payload),
|
|
encoding: 'utf-8',
|
|
});
|
|
expect(res.status).toBe(0);
|
|
const logPath = path.join(fixture.stateRoot, 'projects', fixture.slug, 'question-log.jsonl');
|
|
expect(fs.existsSync(logPath)).toBe(true);
|
|
const lines = fs.readFileSync(logPath, 'utf-8').trim().split('\n');
|
|
expect(lines.length).toBeGreaterThanOrEqual(1);
|
|
const evt = JSON.parse(lines[0]);
|
|
expect(evt.source).toBe('hook');
|
|
expect(evt.question_id).toBe('ship-test-failure-triage');
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Scenario 2: Enforcement — never-ask preference + marker + 2-way → deny
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describeIfSelected('PlanTune cathedral E2E: enforcement', ['plan-tune-enforcement'], () => {
|
|
let fixture: ReturnType<typeof scaffoldFixture>;
|
|
|
|
beforeAll(() => {
|
|
fixture = scaffoldFixture('cathedral-enf-');
|
|
fs.mkdirSync(path.join(fixture.stateRoot, 'projects', fixture.slug), { recursive: true });
|
|
fs.writeFileSync(
|
|
path.join(fixture.stateRoot, 'projects', fixture.slug, 'question-preferences.json'),
|
|
JSON.stringify({ 'ship-changelog-voice-polish': 'never-ask' }),
|
|
);
|
|
});
|
|
|
|
afterAll(() => {
|
|
cleanupFixture(fixture.workDir);
|
|
});
|
|
|
|
testConcurrentIfSelected('PreToolUse hook denies + logs auto-decided event', async () => {
|
|
const hookPath = path.join(
|
|
fixture.workDir,
|
|
'hosts',
|
|
'claude',
|
|
'hooks',
|
|
'question-preference-hook',
|
|
);
|
|
const payload = {
|
|
session_id: 'cathedral-e2e-enf',
|
|
tool_name: 'AskUserQuestion',
|
|
tool_use_id: 'tu-enf-1',
|
|
tool_input: {
|
|
questions: [
|
|
{
|
|
question:
|
|
'<gstack-qid:ship-changelog-voice-polish> Polish CHANGELOG entry?',
|
|
options: ['A) Accept (recommended)', 'B) Skip'],
|
|
},
|
|
],
|
|
},
|
|
cwd: fixture.workDir,
|
|
};
|
|
const res = spawnSync(hookPath, [], {
|
|
env: {
|
|
...process.env,
|
|
GSTACK_STATE_ROOT: fixture.stateRoot,
|
|
GSTACK_QUESTION_LOG_NO_DERIVE: '1',
|
|
},
|
|
input: JSON.stringify(payload),
|
|
encoding: 'utf-8',
|
|
});
|
|
expect(res.status).toBe(0);
|
|
const parsed = JSON.parse(res.stdout || '{}');
|
|
expect(parsed.hookSpecificOutput?.permissionDecision).toBe('deny');
|
|
expect(parsed.hookSpecificOutput?.permissionDecisionReason).toContain('Accept');
|
|
|
|
// Auto-decided event was logged.
|
|
const logPath = path.join(fixture.stateRoot, 'projects', fixture.slug, 'question-log.jsonl');
|
|
expect(fs.existsSync(logPath)).toBe(true);
|
|
const events = fs
|
|
.readFileSync(logPath, 'utf-8')
|
|
.trim()
|
|
.split('\n')
|
|
.filter(Boolean)
|
|
.map((l) => JSON.parse(l));
|
|
const auto = events.filter((e) => e.source === 'auto-decided');
|
|
expect(auto.length).toBe(1);
|
|
expect(auto[0].question_id).toBe('ship-changelog-voice-polish');
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Scenario 3: Annotation — declared profile injected via additionalContext
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describeIfSelected('PlanTune cathedral E2E: annotation', ['plan-tune-annotation'], () => {
|
|
let fixture: ReturnType<typeof scaffoldFixture>;
|
|
|
|
beforeAll(() => {
|
|
fixture = scaffoldFixture('cathedral-ann-');
|
|
// Strong declared profile that should annotate any signal_key=detail-preference question.
|
|
fs.writeFileSync(
|
|
path.join(fixture.stateRoot, 'developer-profile.json'),
|
|
JSON.stringify({ declared: { detail_preference: 0.9 } }),
|
|
);
|
|
// Seed a memory nugget for the matching signal_key.
|
|
fs.writeFileSync(
|
|
path.join(fixture.stateRoot, 'free-text-memory.json'),
|
|
JSON.stringify({
|
|
nuggets: [
|
|
{
|
|
nugget: 'User prefers verbose explanations with tradeoffs',
|
|
applies_to_signal_keys: ['detail-preference'],
|
|
applied_at: new Date().toISOString(),
|
|
},
|
|
],
|
|
}),
|
|
);
|
|
});
|
|
|
|
afterAll(() => {
|
|
cleanupFixture(fixture.workDir);
|
|
});
|
|
|
|
testConcurrentIfSelected('PreToolUse hook surfaces memory nugget on defer', async () => {
|
|
const hookPath = path.join(
|
|
fixture.workDir,
|
|
'hosts',
|
|
'claude',
|
|
'hooks',
|
|
'question-preference-hook',
|
|
);
|
|
const payload = {
|
|
session_id: 'cathedral-e2e-ann',
|
|
tool_name: 'AskUserQuestion',
|
|
tool_use_id: 'tu-ann-1',
|
|
tool_input: {
|
|
questions: [
|
|
{
|
|
question: '<gstack-qid:ship-todos-reorganize> Reorganize TODOs?',
|
|
options: ['A) Accept (recommended)', 'B) Skip'],
|
|
},
|
|
],
|
|
},
|
|
cwd: fixture.workDir,
|
|
};
|
|
const res = spawnSync(hookPath, [], {
|
|
env: {
|
|
...process.env,
|
|
GSTACK_STATE_ROOT: fixture.stateRoot,
|
|
GSTACK_QUESTION_LOG_NO_DERIVE: '1',
|
|
},
|
|
input: JSON.stringify(payload),
|
|
encoding: 'utf-8',
|
|
});
|
|
expect(res.status).toBe(0);
|
|
const parsed = JSON.parse(res.stdout || '{}');
|
|
// #2035: memory-nugget delivery is additionalContext-ONLY. Emitting a
|
|
// permissionDecision here (the old 'defer') pauses the tool call for a
|
|
// resumption that never comes in interactive sessions.
|
|
expect('permissionDecision' in (parsed.hookSpecificOutput ?? {})).toBe(false);
|
|
expect(parsed.hookSpecificOutput?.additionalContext).toContain('verbose explanations');
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Scenario 4: Codex import — JSONL session → import bin → log fills
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describeIfSelected('PlanTune cathedral E2E: codex import', ['plan-tune-codex-import'], () => {
|
|
let fixture: ReturnType<typeof scaffoldFixture>;
|
|
let sessionFile: string;
|
|
|
|
beforeAll(() => {
|
|
fixture = scaffoldFixture('cathedral-cdx-');
|
|
sessionFile = path.join(fixture.workDir, 'rollout-cathedral.jsonl');
|
|
const lines = [
|
|
JSON.stringify({
|
|
type: 'session_meta',
|
|
payload: { id: 'cathedral-sess-1', cwd: fixture.workDir },
|
|
}),
|
|
JSON.stringify({
|
|
timestamp: new Date().toISOString(),
|
|
type: 'event_msg',
|
|
payload: {
|
|
type: 'agent_message',
|
|
message:
|
|
'D1 — Cathedral import <gstack-qid:plan-eng-review-scope-reduce>\nRecommendation: A\nA) Reduce (recommended)\nB) Keep',
|
|
},
|
|
}),
|
|
JSON.stringify({
|
|
timestamp: new Date().toISOString(),
|
|
type: 'event_msg',
|
|
payload: { type: 'user_message', message: 'A' },
|
|
}),
|
|
];
|
|
fs.writeFileSync(sessionFile, lines.join('\n') + '\n');
|
|
});
|
|
|
|
afterAll(() => {
|
|
cleanupFixture(fixture.workDir);
|
|
});
|
|
|
|
testConcurrentIfSelected('importer extracts events with codex-import-marker source', async () => {
|
|
const bin = path.join(fixture.workDir, 'bin', 'gstack-codex-session-import');
|
|
const res = spawnSync(bin, [sessionFile], {
|
|
env: {
|
|
...process.env,
|
|
GSTACK_STATE_ROOT: fixture.stateRoot,
|
|
GSTACK_QUESTION_LOG_NO_DERIVE: '1',
|
|
},
|
|
encoding: 'utf-8',
|
|
cwd: fixture.workDir,
|
|
});
|
|
expect(res.status).toBe(0);
|
|
expect(res.stdout).toContain('IMPORTED: 1');
|
|
const logPath = path.join(fixture.stateRoot, 'projects', fixture.slug, 'question-log.jsonl');
|
|
expect(fs.existsSync(logPath)).toBe(true);
|
|
const events = fs
|
|
.readFileSync(logPath, 'utf-8')
|
|
.trim()
|
|
.split('\n')
|
|
.filter(Boolean)
|
|
.map((l) => JSON.parse(l));
|
|
expect(events.length).toBe(1);
|
|
expect(events[0].source).toBe('codex-import-marker');
|
|
expect(events[0].question_id).toBe('plan-eng-review-scope-reduce');
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Scenario 5: Dream cycle round-trip — capture → distill (mocked) → apply →
|
|
// re-fire → memory injection
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describeIfSelected('PlanTune cathedral E2E: dream cycle', ['plan-tune-dream-cycle'], () => {
|
|
let fixture: ReturnType<typeof scaffoldFixture>;
|
|
|
|
beforeAll(() => {
|
|
fixture = scaffoldFixture('cathedral-dream-');
|
|
// Seed proposals file directly (the SDK call is exercised by the unit
|
|
// test; here we verify apply → re-fire round-trip on top of a known
|
|
// proposal shape).
|
|
fs.mkdirSync(path.join(fixture.stateRoot, 'projects', fixture.slug), { recursive: true });
|
|
fs.writeFileSync(
|
|
path.join(fixture.stateRoot, 'projects', fixture.slug, 'distillation-proposals.json'),
|
|
JSON.stringify({
|
|
generated_at: new Date().toISOString(),
|
|
source_event_count: 1,
|
|
proposals: [
|
|
{
|
|
kind: 'memory-nugget',
|
|
confidence: 0.95,
|
|
nugget: 'User wants every fix tested before shipping',
|
|
applies_to_signal_keys: ['test-discipline'],
|
|
source_quotes: ['always add tests for any fix'],
|
|
},
|
|
],
|
|
}),
|
|
);
|
|
});
|
|
|
|
afterAll(() => {
|
|
cleanupFixture(fixture.workDir);
|
|
});
|
|
|
|
testConcurrentIfSelected('apply → re-fire → memory injected via additionalContext', async () => {
|
|
// 1. Apply the proposal via gstack-distill-apply.
|
|
const applyBin = path.join(fixture.workDir, 'bin', 'gstack-distill-apply');
|
|
const applyRes = spawnSync(applyBin, ['--proposal', '0'], {
|
|
env: { ...process.env, GSTACK_STATE_ROOT: fixture.stateRoot },
|
|
encoding: 'utf-8',
|
|
cwd: fixture.workDir,
|
|
});
|
|
expect(applyRes.status).toBe(0);
|
|
|
|
// Memory file should now contain the nugget.
|
|
const memPath = path.join(fixture.stateRoot, 'free-text-memory.json');
|
|
expect(fs.existsSync(memPath)).toBe(true);
|
|
const mem = JSON.parse(fs.readFileSync(memPath, 'utf-8'));
|
|
expect(mem.nuggets.length).toBe(1);
|
|
|
|
// 2. Re-fire a question whose signal_key matches the nugget. PreToolUse
|
|
// hook should surface the nugget via additionalContext.
|
|
const hookPath = path.join(
|
|
fixture.workDir,
|
|
'hosts',
|
|
'claude',
|
|
'hooks',
|
|
'question-preference-hook',
|
|
);
|
|
const payload = {
|
|
session_id: 'cathedral-e2e-dream',
|
|
tool_name: 'AskUserQuestion',
|
|
tool_use_id: 'tu-dream-1',
|
|
tool_input: {
|
|
questions: [
|
|
{
|
|
question:
|
|
'<gstack-qid:plan-eng-review-test-gap> Add tests for this gap?',
|
|
options: ['A) Add (recommended)', 'B) Skip'],
|
|
},
|
|
],
|
|
},
|
|
cwd: fixture.workDir,
|
|
};
|
|
const hookRes = spawnSync(hookPath, [], {
|
|
env: {
|
|
...process.env,
|
|
GSTACK_STATE_ROOT: fixture.stateRoot,
|
|
GSTACK_QUESTION_LOG_NO_DERIVE: '1',
|
|
},
|
|
input: JSON.stringify(payload),
|
|
encoding: 'utf-8',
|
|
});
|
|
expect(hookRes.status).toBe(0);
|
|
const parsed = JSON.parse(hookRes.stdout || '{}');
|
|
expect(parsed.hookSpecificOutput?.additionalContext).toContain('User wants every fix tested');
|
|
});
|
|
});
|