Files
gstack/test/e2e-harness-audit.test.ts
Garry Tan 9e244c0bed v1.11.1.0 fix: plan-mode handshake + canUseTool test harness (#1182)
* feat: plan-mode handshake for interactive review skills

Add a preamble-level STOP-Ask handshake that fires when the user invokes any
of the 4 interactive review skills (plan-ceo-review, plan-eng-review,
plan-design-review, plan-devex-review) while their Claude Code session is
in plan mode. Without this gate, plan mode's "this supercedes any other
instructions" system-reminder outranked the skills' interactive STOP gates
and the skills silently wrote plan files without any per-finding AskUserQuestion.

The handshake offers 2 options (exit-and-rerun, cancel) — the original
third "stay and batch" option was dropped after two independent reviewers
flagged it as a silent bypass of the skills' anti-skip rule.

Architecture decisions (CEO+Eng review):
- Preamble-level resolver, not per-template injection (Codex finding #2)
- Position 1 in preamble composition: after bash block (_SESSION_ID live),
  before onboarding AskUserQuestion gates (so fresh-install users see the
  handshake first, not drowned in telemetry/proactive/routing prompts)
- Generator-only `interactive: true` frontmatter flag, following the
  `preamble-tier` precedent (no host-config frontmatter allowlist edits)
- Host-scoped to Claude via `ctx.host === 'claude'` check inside the
  resolver (simpler than `suppressedResolvers` which only gates `{{}}`
  placeholders)
- One-way-door classification in scripts/question-registry.ts for all 4
  skills so question-tuning `never-ask` preferences can't suppress the gate
- Synchronous telemetry write to ~/.gstack/analytics/skill-usage.jsonl on
  handshake fire (captures A-exit and C-cancel outcomes that terminate the
  skill before end-of-run telemetry runs)

Also adds an explicit STOP block to plan-ceo-review Step 0C-bis so the
approach-selection question can't silently skip to mode selection.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat: extend agent-sdk-runner with canUseTool for AskUserQuestion interception

Test harness at test/helpers/agent-sdk-runner.ts gains an optional
`canUseTool` callback parameter. When a test supplies it, the harness
flips `permissionMode` from `bypassPermissions` (overlay-harness default)
to `default` so the SDK actually invokes the callback on every tool use,
and auto-adds `AskUserQuestion` to `allowedTools` so Claude can fire it
at all.

Exports a `passThroughNonAskUserQuestion` helper so tests that only want
to intercept AskUserQuestion can auto-allow every other tool with one
line: `return passThroughNonAskUserQuestion(toolName, input)`.

This is the foundation for D14 — every future interactive-skill E2E test
can now assert on AskUserQuestion shape and routing. Previous E2E tests
at `test/skill-e2e.test.ts` explicitly instructed the model to skip
AskUserQuestion ("non-interactive run") which meant no test could actually
verify the question content or routing.

6 new unit tests in test/agent-sdk-runner.test.ts cover:
- permissionMode flips to 'default' when canUseTool supplied
- permissionMode stays 'bypassPermissions' when canUseTool absent
- canUseTool callback reaches the SDK options
- AskUserQuestion auto-added to allowedTools when canUseTool supplied
- AskUserQuestion NOT added when canUseTool absent
- passThroughNonAskUserQuestion helper returns allow+updatedInput

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* test: plan-mode handshake E2E coverage and unit assertions

Adds 6 E2E test files and 8 new unit assertions to verify the plan-mode
handshake works end-to-end and stays correct under regeneration.

E2E tests (gate-tier, paid, EVALS=1 EVALS_TIER=gate):
- test/skill-e2e-plan-ceo-plan-mode.test.ts — handshake fires before any
  Write/Edit when plan-mode distinctive phrase is present; 2-option shape
  (Exit/Cancel); option A routes to ExitPlanMode cleanly
- test/skill-e2e-plan-eng-plan-mode.test.ts — same contract for plan-eng
- test/skill-e2e-plan-design-plan-mode.test.ts — same contract for
  plan-design; exercises C-cancel branch instead of A-exit
- test/skill-e2e-plan-devex-plan-mode.test.ts — same contract for plan-devex
- test/skill-e2e-plan-mode-no-op.test.ts — negative regression: handshake
  must NOT fire when distinctive phrase is absent; skill proceeds normally
  through Step 0 (REGRESSION RULE guardrail against breaking existing
  interactive-review sessions)
- test/e2e-harness-audit.test.ts — free unit test asserting every
  `interactive: true` skill has at least one canUseTool-using test file
  (prevents future drift where a skill opts in without coverage)

Shared helper test/helpers/plan-mode-handshake-helpers.ts centralizes the
canUseTool interceptor + distinctive-phrase injection so the 4 sibling
E2E tests are thin wiring (~20 LOC each) and can't drift out of sync.

Unit assertions added to test/gen-skill-docs.test.ts:
- handshake section present in all 4 Claude-generated SKILL.md files
- handshake section absent from non-interactive Claude skills (ship,
  review, qa, office-hours, codex, retro, cso)
- handshake section absent from non-Claude host outputs (.agents, etc.)
- 0C-bis STOP block present in plan-ceo-review/SKILL.md at correct
  position (between the "Present these approach options" line and
  "### 0D-prelude" header)
- handshake resolver wired BEFORE generateUpgradeCheck in preamble
  composition order

6 new gate-tier entries added to test/helpers/touchfiles.ts so any change
to the handshake resolver, preamble composition, skill templates, question
registry, one-way-door classifier, or agent-sdk-runner fires the relevant
E2E tests. test/touchfiles.test.ts updated for the new selection count
(plan-ceo-review/** now triggers 15 tests, up from 8).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* chore(v1.11.1.0): VERSION bump + CHANGELOG entry + TODOS follow-ups

Bumps from main's v1.11.0.0 to v1.11.1.0 (PATCH — bug-fix release, no new
user-facing artifacts). CHANGELOG entry covers the plan-mode handshake,
agent-sdk-runner canUseTool extension, and the 2 follow-up TODOs.

CHANGELOG order: v1.11.1.0 (this) → v1.11.0.0 (workspace-aware ship,
merged from main) → v1.10.1.0 (overlay efficacy harness). No duplicate
headers.

Syncs package.json version to match VERSION per the Step 12 idempotency
invariant (both files must agree or /ship halts).

TODOS.md:
- Preserves the Testing/security-bench-haiku-responses P1 added on main
- Adds P1 "Structural STOP-Ask forcing function" — broader class of the
  bug this release fixes
- Adds P2 "Apply interactive: true to non-review skills (office-hours,
  codex, investigate, qa, retro, cso)"

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-24 00:04:53 -07:00

114 lines
3.4 KiB
TypeScript

/**
* E2E harness audit — every skill with `interactive: true` in its frontmatter
* must have at least one test file that uses `canUseTool` via the extended
* agent-sdk-runner. This prevents future drift where a skill opts into the
* handshake without adding real coverage.
*
* Runs as a free unit test (no API calls). Pure filesystem scan.
*/
import { describe, test, expect } from 'bun:test';
import * as fs from 'fs';
import * as path from 'path';
const ROOT = path.resolve(import.meta.dir, '..');
const SKILL_GLOBS = [
'plan-ceo-review',
'plan-eng-review',
'plan-design-review',
'plan-devex-review',
'office-hours',
'codex',
'investigate',
'qa',
'retro',
'cso',
'review',
'ship',
'design-review',
'devex-review',
'qa-only',
'design-consultation',
'design-shotgun',
'autoplan',
'land-and-deploy',
'plan-tune',
'document-release',
'context-save',
'context-restore',
'health',
'setup-deploy',
'setup-browser-cookies',
'canary',
'learn',
'benchmark',
'benchmark-models',
'make-pdf',
'open-gstack-browser',
'gstack-upgrade',
'pair-agent',
'design-html',
'freeze',
'unfreeze',
'careful',
'guard',
];
/**
* Load .tmpl files for each skill and return the names of those that have
* `interactive: true` in frontmatter.
*/
function findInteractiveSkills(): string[] {
const interactive: string[] = [];
for (const skill of SKILL_GLOBS) {
const tmplPath = path.join(ROOT, skill, 'SKILL.md.tmpl');
if (!fs.existsSync(tmplPath)) continue;
const content = fs.readFileSync(tmplPath, 'utf-8');
// Frontmatter lives between the first '---' and the next '---'.
const fmEnd = content.indexOf('\n---', 4);
if (fmEnd < 0) continue;
const frontmatter = content.slice(0, fmEnd);
if (/^interactive:\s*true\s*$/m.test(frontmatter)) {
interactive.push(skill);
}
}
return interactive;
}
/**
* Scan a test file's contents for the canUseTool-via-harness pattern.
* Either: direct canUseTool usage in runAgentSdkTest, or usage of the
* shared plan-mode-handshake-helpers that wrap it.
*/
function hasCanUseToolCoverage(testFile: string): boolean {
const content = fs.readFileSync(testFile, 'utf-8');
if (content.includes('canUseTool')) return true;
if (content.includes('runPlanModeHandshakeTest')) return true;
return false;
}
describe('E2E harness audit — interactive skills must have canUseTool coverage', () => {
test('every interactive: true skill has at least one canUseTool test', () => {
const interactive = findInteractiveSkills();
expect(interactive.length).toBeGreaterThan(0);
const testFiles = fs
.readdirSync(path.join(ROOT, 'test'))
.filter((f) => f.startsWith('skill-e2e-') && f.endsWith('.test.ts'))
.map((f) => path.join(ROOT, 'test', f));
const filesWithCoverage = testFiles.filter(hasCanUseToolCoverage);
for (const skill of interactive) {
// Match the skill name in any test file that uses canUseTool. File
// naming convention is `skill-e2e-<skill>-*.test.ts` — either the full
// name (plan-ceo-review) or a subset token.
const hasDedicatedTest = filesWithCoverage.some((f) => {
const base = path.basename(f, '.test.ts');
return base.includes(skill) || base.includes(skill.replace(/-review$/, ''));
});
expect(hasDedicatedTest, `skill "${skill}" has interactive:true but no canUseTool-based E2E test`).toBe(true);
}
});
});