Files
gstack/test/skill-e2e-bws.test.ts
T
Garry Tan 9fd03fae9e v1.58.4.0 fix: high-priority community bug wave + PTY plan-mode smoke gate (#2077)
* fix(gbrain): stop forcing GBRAIN_PREPARE on transaction-mode poolers (#1965)

buildGbrainEnv auto-set GBRAIN_PREPARE=true whenever DATABASE_URL targeted
port 6543, and the /sync-gbrain capability check exported it for the rest
of the skill run. Both had the semantics inverted: gbrain auto-disables
prepared statements on transaction-mode poolers because they break every
write there ("prepared statement does not exist"); GBRAIN_PREPARE=true is
gbrain's documented override for SESSION-mode poolers on 6543, not a
requirement for transaction mode. The #1435 search symptom the auto-set
worked around was fixed gbrain-side.

Remove both force-sets. A caller-set GBRAIN_PREPARE (either value) still
passes through untouched, preserving the session-mode-on-6543 escape hatch.
isTransactionModePooler stays exported.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(gbrain): classify probe timeout as its own status; sync proceeds instead of skipping (#1964)

The 5s engine probe misclassified healthy-but-slow engines (cold Supabase
pooler connections measured at 6.9-10.7s) as broken-config, so /sync-gbrain
silently skipped code+memory and told the user their config was malformed.

- New "timeout" status: probe killed at the deadline with no recognized
  stderr pattern. Default deadline is now 15s, overridable via
  GSTACK_GBRAIN_PROBE_TIMEOUT_MS (tests set 300ms against a fake that
  sleeps 2s).
- Sync stages PROCEED on timeout with a stderr warning naming the env knob;
  a genuinely-dead engine surfaces its real error at the first operation
  instead of a false config diagnosis.
- Consistency everywhere "ok" gated behavior: gstack-gbrain-detect --is-ok
  exits 0 on timeout, and gen-skill-docs' detection gate accepts it, so a
  slow engine no longer silently suppresses brain-aware features.
- Status cache: key now includes the effective probe timeout (raising it
  invalidates a cached timeout) and GBRAIN_HOME; config detection honors
  GBRAIN_HOME so relocated-home users stop being misclassified as
  missing-config.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(bins): cygpath-normalize SCRIPT_DIR for bun imports; surface learnings-log errors (#1950)

Under Windows git-bash, pwd yields a POSIX path (/c/Users/...) that Bun on
Windows cannot resolve as an ES module specifier. gstack-learnings-log
interpolates SCRIPT_DIR into a bun -e import, so every invocation died with
"Cannot find module" — and 2>/dev/null swallowed the error, silently
dropping every AI-logged learning for Windows users.

- 3-line cygpath -m guard in gstack-learnings-log and gstack-question-log
  (which gains the same import shape in the next commit). Matches the
  duplicated IS_WINDOWS convention in setup; no shared shell lib exists.
- learnings-log adopts question-log's set +e / TMPERR capture pattern
  wholesale: validation errors now print to stderr. The old
  `if [ $? -ne 0 ]` check was dead code under set -euo pipefail — the
  script exited at the failing assignment before reaching it.
- New test/bin-windows-bun-import-paths.test.ts: static invariant (any
  bash bin interpolating $SCRIPT_DIR into a bun -e import must carry the
  guard) + behavioral end-to-end run invoked via `bash <bin>` — added to
  the windows-free-tests workflow list so the conversion is proven on the
  only platform where the bug exists.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(question-log): dedupe INJECTION_PATTERNS via lib/jsonl-store (#1934)

bin/gstack-question-log carried a local copy of the injection-pattern list,
so pattern fixes to lib/jsonl-store.ts never propagated — including the
/override[:\s]/i false-positive fix arriving via community PR #1940.
Import the shared hasInjection instead (enabled by the previous commit's
cygpath guard). question-log also gets the lib's stricter superset
(human:, disregard, from-now-on, approve-all patterns).

Tests pin the contract in a #1940-order-independent way: an "Override:
ignore all previous instructions" header is rejected, "prose overrides the
deterministic table" is accepted, and a static invariant keeps local
INJECTION_PATTERNS duplicates out of the bin.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(security): community-pulse + both dashboards never report fake zeros (#1947)

The security-signaling surface failed open at three layers — every failure
mode read as a reassuring "0 attacks" / "0 installs":

- community-pulse edge function: supabase-js returns {data,error} without
  throwing, and all five queries discarded `error` — a DB outage produced
  real-looking zeros via the SUCCESS path, and the catch (also returning
  zeros with HTTP 200) was unreachable for query failures. Every query now
  destructures and throws; the catch serves the stale cache (marked
  "stale": true) when one exists, else 503 {"error":"pulse_unavailable"}.
  Success responses carry "status":"ok" so clients can distinguish
  authoritative data from legacy backends. NOTE: the edge function deploys
  out-of-band (supabase functions deploy community-pulse).
- gstack-security-dashboard: captures the HTTP status; non-200 / network
  failure / error body / missing section → "unknown — backend error";
  jq missing → "unknown — install jq" (the lossy grep fallback broke on
  nested arrays and under-reported attacks as zero — removed); a 200
  without the new marker shows figures with an "unverified (legacy
  backend)" note. Also fixes a latent display bug: the TOTAL grep matched
  the digit 7 inside "attacks_last_7_days" and misreported every count.
- gstack-community-dashboard: same class — curl || echo "{}" plus
  grep || echo "0" printed "Weekly active installs: 0" on any failure.
  Now "unknown — backend error (HTTP N)".

test/security-dashboard-fallback.test.ts pins the matrix (200+marker,
200-legacy, 503, network failure) x (jq present, jq absent) for both bins:
"unknown" states never render as 0.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(telemetry): redact error_message spans before they leave the machine (#1947)

error_message was uploaded with only quote/newline escaping — stack traces
and failed-API errors can embed credentials, private paths, and hostnames,
and the sync path strips only _repo_slug/_branch.

New lib/redact-engine.ts export redactFindingSpans(): replaces EVERY
finding's span with <REDACTED-{id}> regardless of tier (applyRedactions is
the interactive PII-only path and exits nonzero on credential findings, so
it can't serve machine egress). Returns null when a span can't be located —
callers drop the whole payload rather than risk a leak.

gstack-telemetry-log pipes error_message through it at LOG time, so the
local JSONL at rest is clean too; surrounding text survives for crash
triage. FAIL CLOSED: bun missing, engine error, or non-JSON-string output
all null the field. Tests pin: embedded ghp_ token → <REDACTED-github.pat>
with context intact; redactor unavailable → null; raw bytes on disk never
contain the token.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(redact): prepush guard fails closed on git failure; /ship owns hook install (#1946)

Two gaps closed:

1. Fail closed. The git() helper returned "" on ANY non-zero exit or
   maxBuffer overflow (status null), addedLinesFor produced an empty
   string, and the push sailed through unscanned — fail-open on exactly
   the oversized-diff case where a large secret-bearing blob is most
   likely. The diff call now uses a strict variant that throws; main
   blocks with a clear message naming the GSTACK_REDACT_PREPUSH=skip
   escape valve. Probe calls (symbolic-ref, rev-parse, merge-base) keep
   the permissive helper — their failures are normal control flow.

2. Install path. The hook was installed by nothing ("opt-in, installed by
   nothing" was the issue's words). ./setup runs in the gstack checkout —
   the wrong repo for a per-project hook — so it gets a one-line hint
   only. /ship owns per-repo install: config redact_prepush_hook=true +
   hook missing → silent install (consent already given); config unset +
   no ~/.gstack/.redact-prepush-prompted marker → one-time machine-wide
   AskUserQuestion offer, answer persisted. ship/SKILL.md regenerated in
   this same commit (check-freshness bisect discipline).

Tests: unscannable diff (bogus SHAs) → exit 1 + valve named; empty-but-
successful diff → exit 0; static asserts pin setup as hint-only and the
ship template as the installer surface.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(redact): six new credential patterns — GitLab, HuggingFace, npm, DigitalOcean, Bearer, GCP SA (#1946)

Coverage gaps from the #1946 security review, including token types for
tooling gstack itself drives (glab):

HIGH (block): gitlab.token (glpat-/glptt-/gldt-), huggingface.token (hf_),
npm.token (npm_), digitalocean.token (dop_v1_), gcp.service_account (the
JSON-escaped "private_key" form that dodges pem.private_key's literal-block
match when minified, confirmed by "private_key_id" proximity).

MEDIUM (warn): auth.bearer — the most FP-prone shape in the set (docs are
full of "Authorization: Bearer <token>"), so it requires header-context
proximity and the same entropy>=3.0 + placeholder validator recipe as
env.kv. "Bearer YOUR_TOKEN_HERE" never fires; calibration over coverage,
per the cries-wolf principle.

All shapes are linear-time; test/redact-pattern-lint.test.ts covers them
automatically. Engine tests add positive + placeholder-negative cases per
pattern.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: coverage-audit additions for the fix wave

Ship Step 7 gap-fill (all passing, 248 tests across the touched suites):
memory + dream stage probe-timeout proceeds, gbrain-detect override paths,
stale-flag passthrough, 200-body-missing-.security fail-closed case,
telemetry redaction edges, and credential-pattern edge cases.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: pre-landing review fixes

Review army findings (1 critical, auto-fixed with regression tests):

- CRITICAL (security specialist, verified live): redactFindingSpans spliced
  only the regex capture span, and pem.private_key / gcp.service_account
  capture just the BEGIN-header — the key body survived "redaction" and
  shipped via telemetry. Marker-only patterns now drop the whole payload
  (null, fail closed). Overlapping spans (Bearer+JWT on the same bytes) are
  coalesced before splicing so stale offsets can't leave partial secret
  bytes behind.
- gitStrict: drop the dead `|| r.status === null` disjunct (null !== 0
  already covers it); add the signal-kill/null-status regression test the
  docstring promised.
- security-dashboard human mode flags stale snapshots ("figures may be out
  of date") instead of presenting frozen counts as current.
- community-dashboard marker check uses jq when available — the grep-only
  variant misclassified whitespaced/reserialized bodies as legacy.
- telemetry fail-closed test now shadows bun with a failing stub
  (deterministic on any host layout); stale "five status cases" describe
  title renamed.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: adversarial review fixes (Claude + Codex cross-model passes)

Both adversarial passes ran against the wave; every FIXABLE finding landed
with a regression test:

- probeTimeoutMs clamps to >=1ms: a fractional override floored to 0, and
  execFileSync treats timeout:0 as NO timeout — the probe that exists to
  bound hangs could hang forever (found by both models independently).
- /ship silent hook install now requires the hooks dir to live inside
  .git: with core.hooksPath (husky's COMMITTED .husky/), the chaining
  installer would have renamed the team's committed pre-push and written a
  machine-local wrapper into the working tree (found by both models).
- gstack-config gbrain-refresh accepts the "timeout" status — the last
  consumer still gating on literal "ok" (Codex); gstack-gbrain-detect's
  config-derived fields honor GBRAIN_HOME so the detection JSON can't
  report status ok alongside config_exists false (Codex).
- prepush: a remote sha absent locally (shallow clone / stale fetch) falls
  back to the merge-base/empty-tree range — scans MORE, never blocks a
  legitimate push into training users toward --no-verify.
- dashboards: curl's own 000 no longer doubles to "HTTP 000000"; the
  community dashboard flags stale snapshots like the security one; array
  sections parse via jq (the sed/grep loops truncated at the first ']');
  the no-jq marker grep tolerates whitespace.
- telemetry: multi-line redactor output nulls the field instead of
  corrupting the JSONL record; setup's hint fires only when the config key
  is genuinely unset (an explicit false is a recorded decline); the /ship
  prompt marker honors GSTACK_HOME.

Kept as designed (cross-model tension noted): Bearer stays MEDIUM in the
prepush gate — a HIGH Bearer would block every docs example; the entropy
validator can't eliminate that FP class, and MEDIUM warns visibly.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* chore: bump version and changelog (v1.57.11.0)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: P1 TODO — eval harness live progress + incremental persistence

Root-caused during this ship: a killed eval run was indistinguishable from a
healthy one for hours (per-file output buffering across mega test files, no
incremental eval-store writes, no honest liveness signal). Full context and
starting points in the entry.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: fix operational-learning E2E fixture — copy lib/jsonl-store.ts

Pre-existing breakage, proven on main: gstack-learnings-log has imported
lib/jsonl-store.ts (shared injection patterns) since v1.57.5.0 / #1910, but
the fixture copies only the bin scripts — the bin exits 1 before writing
anything, on main silently (stderr swallowed) and on this branch loudly
(the #1950 error-surfacing made the four-day-old failure visible). A real
install always ships bin/ and lib/ together; the fixture now does too.
Verified: the fixture-shaped invocation writes the learning (exit 0) with
lib present, exits 1 on both main and this branch without it.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ios-qa): isolate E2E tests under --concurrent (3 real races)

The ios-qa E2E file failed intermittently under `bun test --concurrent`
(the eval harness default). Three distinct shared-state races, all fixed:

1. Shared pidfile: a module-level `workDir` reassigned in beforeEach was
   clobbered by parallel tests, so concurrent daemons collided on the same
   pidfile and the loser returned `already_running`. Each test now gets its
   own dir via makeWorkDir().
2. process.env path globals: tests set GSTACK_IOS_AUDIT_PATH /
   _ATTEMPTS_PATH / _ALLOWLIST_PATH on the shared process env; concurrent
   tests stomped each other's audit/attempts destinations. Threaded
   auditPath/attemptsPath/allowlistPath through DaemonOptions (and
   mintForCaller) as explicit args — env is no longer load-bearing.
3. afterEach cleanup race: the per-test cleanup drained a shared dir array,
   so the first test to finish deleted still-running tests' workDirs
   mid-assertion. Moved to afterAll (cleans once, after all settle).

Verified: 5/5 clean full-suite runs at --max-concurrency 15 (was
intermittent); daemon unit suite 91/91; daemon source compiles. The paths
default to the env-derived locations when options are omitted, so the
production CLI path is unchanged.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test(pty): pin spawned claude to EVALS model chain (default claude-sonnet-4-6)

launchClaudePty spawned the interactive `claude` TUI with no --model flag, so
the child inherited the operator's ~/.claude/settings.json model. On a
slow-thinking model that meant 5+ min of extended thinking on empty plan-mode
context, timing out the plan-mode smoke tests regardless of contention. Pin the
model via opts.model ?? EVALS_MODEL ?? 'claude-sonnet-4-6' — byte-identical to
session-runner.ts:144, so PTY and `claude -p` evals always agree.

Pushed before extraArgs (last flag wins, so a per-test --model still overrides).
Placement leaves the spawn region byte-stable for a clean merge with the
in-flight hermetic-env branch. Plumbed model through the three plan-skill
wrappers. Static-grep tripwires guard the pin, its fallback chain, the
before-extraArgs ordering, and all three wrapper forwards.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(pty): detect markdown bold-bullet prose AUQs (fixes office-hours smoke)

office-hours auto-mode renders its mode question as `- **Building a startup**`
markdown bullets (office-hours/SKILL.md.tmpl:102) with no letter/number marker.
isProseAUQVisible only matched `A)`-style lettered or `1.`-style numbered
options, so the question went undetected: the model surfaced it at ~2m19s
(well under the 300s budget) but the harness kept scoring the run "working"
off the spinner glyphs and timed out — a false timeout on a question that was
already on screen.

Add Pattern 3: when an interrogative line ('?') is present AND 3+ bold-bullet
markers (`- **`) appear in the 4KB tail, classify as a prose AUQ. Bold is the
discriminator vs incidental prose bullets; the line anchor is dropped (stripAnsi
can collapse option lines) and the existing `❯ 1.` cursor gate still defers to a
live native list. Wires through the existing classifyVisible 'asked' path and the
timeout high-water-mark, so office-hours now classifies 'asked' instead of
'timeout'. Five unit cases: the office-hours render passes; no-'?', <3-bullet,
plain-bullet, and native-cursor cases stay false.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(pty): detect stripAnsi-collapsed prose AUQs + judge spinner-precedence

The plan-eng/plan-design plan-mode + finding-floor smokes timed out even when
the skill HAD rendered a complete prose AskUserQuestion and was waiting: the PTY
strips cursor-positioning escapes, collapsing the option newlines/spaces so
"A) ..." arrives as "A(recommended)" / "-B:" and "Reply with A, B, or C" as
"ReplywithA,B,orC". Every line-anchored detector (Patterns 1-3) returns false on
those bytes, so proseAUQEverObserved never latched and the run timed out on a
question that was already on screen.

Add Pattern 4/5: a two-signal collapsed-form detector — a reply/recommendation
marker (space-insensitive "reply with [A-D]", "Recommendation:", or
"(recommended)") AND 2+ distinct A-D letters each punctuated by ) : or (. The
conjunction is what separates a real AUQ from incidental report prose; verified
true on the verbatim failing-run buffers where Patterns 1-3 return false.

Also fix the Haiku judge spinner bias: of 614 verdicts, 569 were 'working' and
95 of those noted a question was visible — Claude Code keeps the spinner
animating at an idle prose decision, so the judge coin-flipped. Add a precedence
override: when an option list AND a Recommendation/Reply instruction are both
visible, classify WAITING even with spinner glyphs. Kept the strict dual-signal
gate (never option-list-alone) so auto-decide-preserved doesn't flip.

5 unit tests pin the two-signal contract (2 true on real collapsed bytes, 3
false guards). 90 -> 95 pass.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(plan-review): ask-first scope gate for plan-eng + plan-design review

On an empty/cold invocation, plan-eng-review and plan-design-review would dive
straight into repo exploration (plan-eng) or a 7-pass mockup+audit (plan-design)
and only ask the user much later, if at all. plan-ceo-review already asks first
via an unconditional Step-0 gate and behaves well; these two did not.

Add a hard-STOP scope gate as the FIRST operational instruction in each skill
(above the design-doc check / pre-review audit / mockup defaults it explicitly
overrides): the first tool call must be AskUserQuestion confirming the review
target, before any git/Read/Grep/Glob/Bash or mockup generation. Under
--disallowedTools the options render as plain column-0 lettered prose with a
Recommendation + "Reply with A, B, or C" line so the answer is detectable.

This is correct cold-start UX (confirm what to review before grinding a full
review on nothing) and it is the product half of the plan-mode smoke fix; the
harness collapsed-form detector is the deterministic half that catches the ask
however it renders. Templates + regenerated SKILL.md (default variant).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(tiers): reclassify stochastic plan-eng/plan-design ask-first smokes as periodic

plan-eng-review and plan-design-review run a long explore/audit before their
first AskUserQuestion, so whether the plan-mode + finding-floor smokes reach a
terminal outcome within the 300s/600s budget depends on stochastic ask-first
compliance (measured ~50-67%/run even with the hardened gate). Per the
"non-deterministic -> periodic" tiering rule, move the four affected smokes
(plan-eng/plan-design review-plan-mode + finding-floor) to periodic.

The deterministic harness fix (collapsed-form detector + judge precedence) and
the ask-first gate lift these from always-failing to mostly-passing and are the
real product+harness improvements; periodic monitoring tracks the rate weekly
without blocking PRs on an LLM coin-flip. plan-ceo/plan-devex ask-first reliably
and stay gate-tier.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* ci(evals): gate the deterministic PTY plan-mode smokes in CI

The real-PTY plan-mode smokes never ran in CI — the gate was local-only. Add an
e2e-pty-plan-smoke matrix suite running the two deterministically-reliable ones
(office-hours-auto-mode, plan-mode-no-op) so a regression there blocks PRs. The
stochastic plan-eng/plan-design ask-first smokes stay periodic (touchfiles
E2E_TIERS) and are not CI-gated.

A fresh CI container has no ~/.claude.json, so the spawned interactive `claude`
would wedge on the onboarding + API-key-approval dialog. Add a scoped seed step
(hasCompletedOnboarding + key approval, its own ANTHROPIC_API_KEY env) before the
run — mirrors what the hermetic E2E child env seeds. Per-suite timeout override
(35 min) via matrix.suite.timeout so the PTY suite has headroom for --retry 2
without bumping the other 12 suites. Report runner count 12 -> 13.

Validate via workflow_dispatch before relying on the gate (PTY-in-CI is new).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* ci(evals): install gstack skill registry for the PTY smoke suite

The first dry-run of e2e-pty-plan-smoke failed: the spawned interactive `claude`
printed "Unknown command: /plan-ceo-review". .claude/skills is gitignored, so a
fresh CI checkout has no gstack skill registry and the TUI can't resolve
/office-hours or /plan-ceo-review.

Add a Register step (scoped to the suite, after Seed, before Run) that mirrors
setup's --no-prefix user-scoped registry minimally: $HOME/.claude/skills/gstack
-> repo (resolves the preambles' absolute ~/.claude/skills/gstack/bin/* and
<skill>/sections/* paths) + per-skill SKILL.md/sections symlinks for the two
skills these tests invoke. HOME is /github/home in this container and the runner
adds no HOME/CLAUDE_CONFIG_DIR override (no hermetic mode), so $HOME is the right
anchor — the Seed step already proved claude reads it. No ./setup (binary build
+ Chromium + fonts + /dev/tty prompt); SKILL.md + bin/ + sections/ are committed.

Self-validating: fails the step loudly on a dangling symlink or missing
`name:` frontmatter, so a moved target surfaces here instead of as a silent
35-min "Unknown command" timeout.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v1.58.4.0)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-06-21 07:15:19 -07:00

398 lines
16 KiB
TypeScript

import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { runSkillTest } from './helpers/session-runner';
import {
ROOT, browseBin, runId, evalsEnabled,
describeIfSelected, testConcurrentIfSelected,
copyDirSync, setupBrowseShims, logCost, recordE2E,
createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
import { startTestServer } from '../browse/test/test-server';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
const evalCollector = createEvalCollector('e2e-browse');
let testServer: ReturnType<typeof startTestServer>;
let tmpDir: string;
describeIfSelected('Skill E2E tests', [
'browse-basic', 'browse-snapshot', 'skillmd-setup-discovery',
'skillmd-no-local-binary', 'skillmd-outside-git', 'session-awareness',
'operational-learning',
], () => {
beforeAll(() => {
testServer = startTestServer();
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-'));
setupBrowseShims(tmpDir);
// Pre-warm the browse server so Chromium is already launched for tests.
// In CI, Chromium can take 10-20s to launch (Docker + --no-sandbox).
spawnSync(browseBin, ['goto', testServer.url], { cwd: tmpDir, timeout: 30000, stdio: 'pipe' });
}, 45_000);
afterAll(() => {
testServer?.server?.stop();
try { fs.rmSync(tmpDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('browse-basic', async () => {
const result = await runSkillTest({
prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run these commands in sequence:
1. $B goto ${testServer.url}
2. $B snapshot -i
3. $B text
4. $B screenshot /tmp/skill-e2e-test.png
Report the results of each command.`,
workingDirectory: tmpDir,
maxTurns: 7,
timeout: 60_000,
testName: 'browse-basic',
runId,
});
logCost('browse basic', result);
recordE2E(evalCollector, 'browse basic commands', 'Skill E2E tests', result);
expect(result.browseErrors).toHaveLength(0);
expect(result.exitReason).toBe('success');
}, 90_000);
testConcurrentIfSelected('browse-snapshot', async () => {
const result = await runSkillTest({
prompt: `You have a browse binary at ${browseBin}. Assign it to B variable and run:
1. $B goto ${testServer.url}
2. $B snapshot -i
3. $B snapshot -c
4. $B snapshot -D
5. $B snapshot -i -a -o /tmp/skill-e2e-annotated.png
Report what each command returned.`,
workingDirectory: tmpDir,
maxTurns: 9,
timeout: 60_000,
testName: 'browse-snapshot',
runId,
});
logCost('browse snapshot', result);
recordE2E(evalCollector, 'browse snapshot flags', 'Skill E2E tests', result);
// browseErrors can include false positives from hallucinated paths (e.g. "baltimore" vs "bangalore")
if (result.browseErrors.length > 0) {
console.warn('Browse errors (non-fatal):', result.browseErrors);
}
expect(result.exitReason).toBe('success');
}, 90_000);
testConcurrentIfSelected('skillmd-setup-discovery', async () => {
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const setupStart = skillMd.indexOf('## SETUP');
const setupEnd = skillMd.indexOf('## IMPORTANT');
const setupBlock = skillMd.slice(setupStart, setupEnd);
// Guard: verify we extracted a valid setup block
expect(setupBlock).toContain('browse/dist/browse');
const result = await runSkillTest({
prompt: `Follow these instructions to find the browse binary and run a basic command.
${setupBlock}
After finding the binary, run: $B goto ${testServer.url}
Then run: $B text
Report whether it worked.`,
workingDirectory: tmpDir,
maxTurns: 10,
timeout: 60_000,
testName: 'skillmd-setup-discovery',
runId,
});
recordE2E(evalCollector, 'SKILL.md setup block discovery', 'Skill E2E tests', result);
expect(result.browseErrors).toHaveLength(0);
expect(result.exitReason).toBe('success');
}, 90_000);
testConcurrentIfSelected('skillmd-no-local-binary', async () => {
// Create a tmpdir with no browse binary — no local .claude/skills/gstack/browse/dist/browse
const emptyDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-empty-'));
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const setupStart = skillMd.indexOf('## SETUP');
const setupEnd = skillMd.indexOf('## IMPORTANT');
const setupBlock = skillMd.slice(setupStart, setupEnd);
const result = await runSkillTest({
prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
${setupBlock}
Report the exact output. Do NOT try to fix or install anything — just report what you see.`,
workingDirectory: emptyDir,
maxTurns: 5,
timeout: 30_000,
testName: 'skillmd-no-local-binary',
runId,
});
// Setup block should either find the global binary (READY) or show NEEDS_SETUP.
// On dev machines with gstack installed globally, the fallback path
// ~/.claude/skills/gstack/browse/dist/browse exists, so we get READY.
// The important thing is it doesn't crash or give a confusing error.
const allText = result.output || '';
recordE2E(evalCollector, 'SKILL.md setup block (no local binary)', 'Skill E2E tests', result);
expect(allText).toMatch(/READY|NEEDS_SETUP/);
expect(result.exitReason).toBe('success');
// Clean up
try { fs.rmSync(emptyDir, { recursive: true, force: true }); } catch {}
}, 60_000);
testConcurrentIfSelected('skillmd-outside-git', async () => {
// Create a tmpdir outside any git repo
const nonGitDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-nogit-'));
const skillMd = fs.readFileSync(path.join(ROOT, 'SKILL.md'), 'utf-8');
const setupStart = skillMd.indexOf('## SETUP');
const setupEnd = skillMd.indexOf('## IMPORTANT');
const setupBlock = skillMd.slice(setupStart, setupEnd);
const result = await runSkillTest({
prompt: `Follow these instructions exactly. Run the bash code block below and report what it outputs.
${setupBlock}
Report the exact output — either "READY: <path>" or "NEEDS_SETUP".`,
workingDirectory: nonGitDir,
maxTurns: 5,
timeout: 30_000,
testName: 'skillmd-outside-git',
runId,
});
// Should either find global binary (READY) or show NEEDS_SETUP — not crash
const allText = result.output || '';
recordE2E(evalCollector, 'SKILL.md outside git repo', 'Skill E2E tests', result);
expect(allText).toMatch(/READY|NEEDS_SETUP/);
// Clean up
try { fs.rmSync(nonGitDir, { recursive: true, force: true }); } catch {}
}, 60_000);
testConcurrentIfSelected('operational-learning', async () => {
const opDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-oplearn-'));
const gstackHome = path.join(opDir, '.gstack-home');
// Init git repo
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: opDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
fs.writeFileSync(path.join(opDir, 'app.ts'), 'console.log("hello");\n');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'initial']);
// Copy bin scripts + the lib module they import. gstack-learnings-log
// does `import ... from '$SCRIPT_DIR/../lib/jsonl-store.ts'` (v1.57.5.0
// injection sanitization) — without lib/ alongside bin/, the script exits
// 1 before writing anything, failing this test for a fixture reason, not
// a model-behavior reason (root-caused during the v1.58.0.0 ship; fails
// identically on main).
const binDir = path.join(opDir, 'bin');
fs.mkdirSync(binDir, { recursive: true });
for (const script of ['gstack-learnings-log', 'gstack-slug']) {
fs.copyFileSync(path.join(ROOT, 'bin', script), path.join(binDir, script));
fs.chmodSync(path.join(binDir, script), 0o755);
}
// gstack-learnings-log imports $SCRIPT_DIR/../lib/jsonl-store.ts (shared
// injection patterns, since v1.57.5.0) — a real install always ships bin/
// and lib/ together, so the fixture must too. Without it the bin exits 1
// before writing anything and the test fails on every attempt.
const libDir = path.join(opDir, 'lib');
fs.mkdirSync(libDir, { recursive: true });
fs.copyFileSync(path.join(ROOT, 'lib', 'jsonl-store.ts'), path.join(libDir, 'jsonl-store.ts'));
// gstack-learnings-log will create the project dir automatically via gstack-slug
const result = await runSkillTest({
prompt: `You just ran \`npm test\` in this project and it failed with this error:
Error: --experimental-vm-modules flag is required for ESM support in this project.
Run: npm test --experimental-vm-modules
Per the Operational Self-Improvement instructions below, log an operational learning about this failure.
## Operational Self-Improvement
Before completing, reflect on this session:
- Did any commands fail unexpectedly?
If yes, log an operational learning for future sessions:
\`\`\`bash
GSTACK_HOME="${gstackHome}" ${binDir}/gstack-learnings-log '{"skill":"qa","type":"operational","key":"SHORT_KEY","insight":"DESCRIPTION","confidence":N,"source":"observed"}'
\`\`\`
Replace SHORT_KEY with a kebab-case key like "esm-vm-modules-flag".
Replace DESCRIPTION with a one-sentence description of what you learned.
Replace N with a confidence score 1-10.
Log the operational learning now. Then say what you logged.`,
workingDirectory: opDir,
maxTurns: 5,
timeout: 30_000,
testName: 'operational-learning',
runId,
});
logCost('operational learning', result);
const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
// Check if learnings file was created with an operational entry
// The slug is derived from the git repo (dirname), so search all project dirs
let hasOperational = false;
const projectsDir = path.join(gstackHome, 'projects');
if (fs.existsSync(projectsDir)) {
for (const slug of fs.readdirSync(projectsDir)) {
const lPath = path.join(projectsDir, slug, 'learnings.jsonl');
if (fs.existsSync(lPath)) {
const jsonl = fs.readFileSync(lPath, 'utf-8').trim();
if (jsonl) {
const entries = jsonl.split('\n').map(l => { try { return JSON.parse(l); } catch { return null; } }).filter(Boolean);
const opEntry = entries.find(e => e.type === 'operational');
if (opEntry) {
hasOperational = true;
console.log(`Operational learning logged: key="${opEntry.key}" insight="${opEntry.insight}" (slug: ${slug})`);
break;
}
}
}
}
}
recordE2E(evalCollector, 'operational learning', 'Skill E2E tests', result, {
passed: exitOk && hasOperational,
});
expect(exitOk).toBe(true);
expect(hasOperational).toBe(true);
// Clean up
try { fs.rmSync(opDir, { recursive: true, force: true }); } catch {}
}, 90_000);
testConcurrentIfSelected('session-awareness', async () => {
const sessionDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-session-'));
// Set up a git repo so there's project/branch context to reference
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: sessionDir, 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(sessionDir, 'app.rb'), '# my app\n');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'init']);
run('git', ['checkout', '-b', 'feature/add-payments']);
// Add a remote so the agent can derive a project name
run('git', ['remote', 'add', 'origin', 'https://github.com/acme/billing-app.git']);
// Extract AskUserQuestion format instructions from a generated SKILL.md.
// ROOT/SKILL.md is the browse skill (Tier 1) and does NOT contain the
// "## AskUserQuestion Format" section — that block is only emitted for
// Tier 2+ skills by scripts/resolvers/preamble.ts. Use office-hours/SKILL.md
// (Tier 3) which always has the format guidance baked in. Falls back to
// the first SKILL.md that contains the header so a future template move
// doesn't break this test again.
let skillMdPath = path.join(ROOT, 'office-hours', 'SKILL.md');
let skillMd = '';
if (fs.existsSync(skillMdPath)) {
skillMd = fs.readFileSync(skillMdPath, 'utf-8');
}
if (!skillMd.includes('## AskUserQuestion Format')) {
// Fallback: scan top-level skill dirs for the first match.
const skillDirs = fs.readdirSync(ROOT, { withFileTypes: true })
.filter(d => d.isDirectory())
.map(d => path.join(ROOT, d.name, 'SKILL.md'));
for (const candidate of skillDirs) {
if (!fs.existsSync(candidate)) continue;
const content = fs.readFileSync(candidate, 'utf-8');
if (content.includes('## AskUserQuestion Format')) {
skillMd = content;
skillMdPath = candidate;
break;
}
}
}
const aqStart = skillMd.indexOf('## AskUserQuestion Format');
const aqEnd = skillMd.indexOf('\n## ', aqStart + 1);
const aqBlock = aqStart >= 0
? skillMd.slice(aqStart, aqEnd > 0 ? aqEnd : undefined)
: '';
const outputPath = path.join(sessionDir, 'question-output.md');
const result = await runSkillTest({
prompt: `You are running a gstack skill. The session preamble detected _SESSIONS=4 (the user has 4 gstack windows open).
${aqBlock}
You are on branch feature/add-payments in the billing-app project. You were reviewing a plan to add Stripe integration.
You've hit a decision point: the plan doesn't specify whether to use Stripe Checkout (hosted) or Stripe Elements (embedded). You need to ask the user which approach to use.
Since this is non-interactive, DO NOT actually call AskUserQuestion. Instead, write the EXACT text you would display to the user (the full AskUserQuestion content) to the file: ${outputPath}
Remember: _SESSIONS=4, so ELI16 mode is active. The user is juggling multiple windows and may not remember what this conversation is about. Re-ground them.`,
workingDirectory: sessionDir,
maxTurns: 8,
timeout: 60_000,
testName: 'session-awareness',
runId,
});
logCost('session awareness', result);
recordE2E(evalCollector, 'session awareness ELI16', 'Skill E2E tests', result);
// Verify the output contains ELI16 re-grounding context
if (fs.existsSync(outputPath)) {
const output = fs.readFileSync(outputPath, 'utf-8');
const lower = output.toLowerCase();
// Must mention project name
expect(lower.includes('billing') || lower.includes('acme')).toBe(true);
// Must mention branch
expect(lower.includes('payment') || lower.includes('feature')).toBe(true);
// Must mention what we're working on
expect(lower.includes('stripe') || lower.includes('checkout') || lower.includes('payment')).toBe(true);
// Must have a recommendation or structured options
expect(
output.includes('RECOMMENDATION') ||
lower.includes('recommend') ||
lower.includes('option a') ||
lower.includes('which do you want') ||
lower.includes('which approach')
).toBe(true);
} else {
// Check agent output as fallback
const output = result.output || '';
const lowerOut = output.toLowerCase();
expect(
output.includes('RECOMMENDATION') ||
lowerOut.includes('recommend') ||
lowerOut.includes('option a') ||
lowerOut.includes('which do you want') ||
lowerOut.includes('which approach')
).toBe(true);
}
// Clean up
try { fs.rmSync(sessionDir, { recursive: true, force: true }); } catch {}
}, 90_000);
});
// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {
await finalizeEvalCollector(evalCollector);
});