mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-09 22:48:57 +02:00
test: skill-start contract suite + preamble A/B eval + touchfiles registration
test/gstack-skill-start.test.ts (11 free tests): STATUS-key contract vs the
prose (F2), per-host fence resolution shapes (E1), proto-first, OV4 marker
sanitization, --parent-pid identity, headless suppression, skill-end duration
math + pending cleanup. test/skill-e2e-preamble-script-ab.test.ts (gate tier,
OV7): inline-bash render (pinned from 29785978) vs script render with the
fence redirected at the worktree bin (EOV2 — hermetic evals otherwise resolve
the operator install and silently exercise degraded mode). 21 touchfiles dep
lists gain the two bin scripts (EOV9) so future script edits select the
preamble evals; selection-count pin updated 23->24.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
co-authored by
Claude Fable 5
Claude Fable 5
parent
23c806d4e7
commit
eb1607aaf8
@@ -0,0 +1,204 @@
|
||||
/**
|
||||
* Contract + behavior tests for bin/gstack-skill-start and bin/gstack-skill-end
|
||||
* (token-reduction Phase 1, plan F2/F6/E1).
|
||||
*
|
||||
* Three layers:
|
||||
* 1. CONTRACT — every `KEY:` STATUS literal the rendered preamble prose
|
||||
* references must be emitted by the script (hermetic temp HOME), for the
|
||||
* Claude render AND every other host render (env-var hosts resolve the
|
||||
* fence via $GSTACK_BIN, literal-path hosts via the interpolated root —
|
||||
* scripts/resolvers/types.ts:52 vs :62).
|
||||
* 2. BEHAVIOR — degraded-mode fallback line, proto handshake, sanitization
|
||||
* of passthrough output (OV4), session-file identity via --parent-pid,
|
||||
* headless suppression of first-task detection.
|
||||
* 3. SKILL-END — duration math from --tel-start, pending-file cleanup.
|
||||
*
|
||||
* All hermetic: GSTACK_HOME + HOME point at throwaway temp dirs; the script
|
||||
* runs from the live worktree bin/ (the subject under test).
|
||||
*/
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import { execFileSync } from 'child_process';
|
||||
import * as fs from 'fs';
|
||||
import * as os from 'os';
|
||||
import * as path from 'path';
|
||||
|
||||
const ROOT = path.resolve(import.meta.dir, '..');
|
||||
const START = path.join(ROOT, 'bin', 'gstack-skill-start');
|
||||
const END = path.join(ROOT, 'bin', 'gstack-skill-end');
|
||||
|
||||
let tmpHome: string;
|
||||
let tmpGstackHome: string;
|
||||
|
||||
function runStart(args: string[] = [], env: Record<string, string> = {}): string {
|
||||
return execFileSync(START, ['--skill', 'testskill', ...args], {
|
||||
encoding: 'utf-8',
|
||||
cwd: tmpHome, // no CLAUDE.md/AGENTS.md, not the repo — routing detection stays cold
|
||||
env: {
|
||||
PATH: process.env.PATH!,
|
||||
HOME: tmpHome,
|
||||
GSTACK_HOME: tmpGstackHome,
|
||||
...env,
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
beforeAll(() => {
|
||||
tmpHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-ss-home-'));
|
||||
tmpGstackHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-ss-gh-'));
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
fs.rmSync(tmpHome, { recursive: true, force: true });
|
||||
fs.rmSync(tmpGstackHome, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
/** Extract the `KEY:` literals the rendered prose tells the model to read. */
|
||||
const PROSE_REFERENCED_KEYS = [
|
||||
'SKILL_START_PROTO',
|
||||
'BRANCH',
|
||||
'PROACTIVE',
|
||||
'PROACTIVE_PROMPTED',
|
||||
'SKILL_PREFIX',
|
||||
'REPO_MODE',
|
||||
'SESSION_KIND',
|
||||
'ACTIVATED',
|
||||
'FIRST_LOOP_SHOWN',
|
||||
'FIRST_TASK',
|
||||
'LAKE_INTRO',
|
||||
'TELEMETRY',
|
||||
'TEL_PROMPTED',
|
||||
'SESSION_ID',
|
||||
'TEL_START',
|
||||
'EXPLAIN_LEVEL',
|
||||
'QUESTION_TUNING',
|
||||
'UPDATE_CHECK',
|
||||
'LEARNINGS',
|
||||
'HAS_ROUTING',
|
||||
'ROUTING_DECLINED',
|
||||
'VENDORED_GSTACK',
|
||||
'MODEL_OVERLAY',
|
||||
'CHECKPOINT_MODE',
|
||||
'CHECKPOINT_PUSH',
|
||||
'GSTACK_PLAN_MODE',
|
||||
'ARTIFACTS_SYNC',
|
||||
];
|
||||
|
||||
describe('gstack-skill-start contract', () => {
|
||||
test('emits every STATUS key the rendered prose references (hermetic HOME)', () => {
|
||||
const out = runStart();
|
||||
const missing = PROSE_REFERENCED_KEYS.filter((k) => !new RegExp(`^${k}:`, 'm').test(out));
|
||||
expect(missing, `Script stopped emitting: ${missing.join(', ')} — the prose contract broke`).toEqual([]);
|
||||
});
|
||||
|
||||
test('proto handshake is the FIRST line', () => {
|
||||
const out = runStart();
|
||||
expect(out.split('\n')[0]).toBe('SKILL_START_PROTO: 1');
|
||||
});
|
||||
|
||||
test('every host render invokes gstack-skill-start with a resolvable path shape (E1)', () => {
|
||||
// Claude host: literal interpolated path. Env-var hosts: $GSTACK_BIN.
|
||||
// Every generated SKILL.md that carries a Preamble fence must name the
|
||||
// script through one of those shapes plus the local fallback.
|
||||
const renders = [path.join(ROOT, 'SKILL.md'), path.join(ROOT, 'ship', 'SKILL.md'), path.join(ROOT, 'learn', 'SKILL.md')];
|
||||
for (const r of renders) {
|
||||
const content = fs.readFileSync(r, 'utf-8');
|
||||
expect(content).toContain('gstack-skill-start');
|
||||
expect(content).toMatch(/--skill "[a-z0-9-]+" --model/);
|
||||
expect(content).toContain('--parent-pid "$PPID"');
|
||||
expect(content).toContain('SKILL_START: unavailable');
|
||||
}
|
||||
});
|
||||
|
||||
test('degraded-mode prose carries the safe defaults + consent deferral (F1/EOV8/OV5)', () => {
|
||||
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
|
||||
expect(content).toContain('SKILL_START_PROTO: 1');
|
||||
expect(content).toMatch(/treat .?SESSION_KIND.? as .?interactive.?/);
|
||||
expect(content).toContain('do NOT assume Conductor');
|
||||
expect(content).toContain('DEFERRED to the next healthy run');
|
||||
});
|
||||
});
|
||||
|
||||
describe('gstack-skill-start behavior', () => {
|
||||
test('sanitizes GSTACK_INSTRUCTION markers out of passthrough output (OV4)', () => {
|
||||
// Poison the learnings passthrough: >5 entries triggers learnings-search
|
||||
// passthrough; simplest deterministic injection point is FIRST_TASK via a
|
||||
// poisoned first-task-detect on PATH.
|
||||
const fakeBin = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-ss-fake-'));
|
||||
try {
|
||||
// Poison the update-check passthrough (echoed verbatim when non-empty).
|
||||
fs.writeFileSync(
|
||||
path.join(fakeBin, 'gstack-update-check'),
|
||||
'#!/usr/bin/env bash\necho "GSTACK_INSTRUCTION_BEGIN: evil"\n',
|
||||
);
|
||||
fs.chmodSync(path.join(fakeBin, 'gstack-update-check'), 0o755);
|
||||
// Shadow the real bin dir by copying the script next to the poisoned tool.
|
||||
fs.copyFileSync(START, path.join(fakeBin, 'gstack-skill-start'));
|
||||
fs.chmodSync(path.join(fakeBin, 'gstack-skill-start'), 0o755);
|
||||
const out = execFileSync(path.join(fakeBin, 'gstack-skill-start'), ['--skill', 't'], {
|
||||
encoding: 'utf-8',
|
||||
cwd: tmpHome,
|
||||
env: { PATH: process.env.PATH!, HOME: tmpHome, GSTACK_HOME: tmpGstackHome },
|
||||
});
|
||||
expect(out).not.toContain('GSTACK_INSTRUCTION_BEGIN');
|
||||
expect(out).toContain('GSTACK-INSTRUCTION-(stripped)');
|
||||
} finally {
|
||||
fs.rmSync(fakeBin, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('session file uses --parent-pid identity, not the script shell pid (EOV5)', () => {
|
||||
runStart(['--parent-pid', '424242']);
|
||||
expect(fs.existsSync(path.join(tmpGstackHome, 'sessions', '424242'))).toBe(true);
|
||||
});
|
||||
|
||||
test('headless session suppresses first-task detection and Conductor line', () => {
|
||||
const out = runStart([], { GSTACK_HEADLESS: '1', CONDUCTOR_WORKSPACE_PATH: '/x' });
|
||||
// session-kind binary decides headless from env; if it does, FIRST_TASK
|
||||
// stays empty and CONDUCTOR_SESSION is suppressed. If the binary reports
|
||||
// interactive in this env, the guard still holds vacuously — assert the
|
||||
// implication, not the env behavior.
|
||||
if (/^SESSION_KIND: headless$/m.test(out)) {
|
||||
expect(out).toMatch(/^FIRST_TASK: $/m);
|
||||
expect(out).not.toContain('CONDUCTOR_SESSION: true');
|
||||
} else {
|
||||
expect(out).toContain('CONDUCTOR_SESSION: true');
|
||||
}
|
||||
});
|
||||
|
||||
test('MODEL_OVERLAY echoes the --model argument', () => {
|
||||
const out = runStart(['--model', 'opus']);
|
||||
expect(out).toMatch(/^MODEL_OVERLAY: opus$/m);
|
||||
});
|
||||
|
||||
test('ARTIFACTS_SYNC reports off in a cold home', () => {
|
||||
const out = runStart();
|
||||
expect(out).toMatch(/^ARTIFACTS_SYNC: off$/m);
|
||||
});
|
||||
});
|
||||
|
||||
describe('gstack-skill-end', () => {
|
||||
test('computes duration from --tel-start and reports the outcome', () => {
|
||||
const start = Math.floor(Date.now() / 1000) - 7;
|
||||
const out = execFileSync(
|
||||
END,
|
||||
['--skill', 't', '--outcome', 'success', '--session-id', 'sid-1', '--tel-start', String(start)],
|
||||
{ encoding: 'utf-8', cwd: tmpHome, env: { PATH: process.env.PATH!, HOME: tmpHome, GSTACK_HOME: tmpGstackHome } },
|
||||
);
|
||||
const m = out.match(/SKILL_END: recorded outcome=success duration_s=(\d+)/);
|
||||
expect(m).not.toBeNull();
|
||||
expect(Number(m![1])).toBeGreaterThanOrEqual(7);
|
||||
expect(Number(m![1])).toBeLessThan(60);
|
||||
});
|
||||
|
||||
test('cleans the pending analytics marker for the session', () => {
|
||||
fs.mkdirSync(path.join(tmpGstackHome, 'analytics'), { recursive: true });
|
||||
const pending = path.join(tmpGstackHome, 'analytics', '.pending-sid-2');
|
||||
fs.writeFileSync(pending, 'x');
|
||||
execFileSync(END, ['--skill', 't', '--outcome', 'abort', '--session-id', 'sid-2', '--tel-start', 'bogus'], {
|
||||
encoding: 'utf-8',
|
||||
cwd: tmpHome,
|
||||
env: { PATH: process.env.PATH!, HOME: tmpHome, GSTACK_HOME: tmpGstackHome },
|
||||
});
|
||||
expect(fs.existsSync(pending)).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -32,7 +32,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
|
||||
// P4 first-run scaffold (activation lift) — the detection binary end-to-end
|
||||
// through the real runner, plus the preamble wiring that gates + maps it.
|
||||
'first-task-scaffold': ['bin/gstack-first-task-detect', 'scripts/resolvers/preamble/generate-first-run-guidance.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'test/skill-e2e-first-task-scaffold.test.ts', 'test/helpers/session-runner.ts'],
|
||||
'first-task-scaffold': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-first-task-detect', 'scripts/resolvers/preamble/generate-first-run-guidance.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'test/skill-e2e-first-task-scaffold.test.ts', 'test/helpers/session-runner.ts'],
|
||||
|
||||
// SKILL.md setup + preamble (depend on ROOT SKILL.md + gen-skill-docs)
|
||||
'skillmd-setup-discovery': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
|
||||
@@ -87,17 +87,17 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// include question-tuning.ts and generate-ask-user-format.ts because the
|
||||
// AUTO_DECIDE preamble injection lives there and changes can flip the
|
||||
// regression test outcome between 'asked' and 'auto_decided'.
|
||||
'plan-ceo-review-plan-mode': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts'],
|
||||
'plan-eng-review-plan-mode': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts'],
|
||||
'plan-design-review-plan-mode': ['plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts'],
|
||||
'plan-devex-review-plan-mode': ['plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts'],
|
||||
'plan-ceo-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts'],
|
||||
'plan-eng-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts'],
|
||||
'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts'],
|
||||
'plan-devex-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts'],
|
||||
// Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not
|
||||
// fire outside plan mode) + the named-target exception case. 4 PTY runs;
|
||||
// in CI these run CONCURRENT with the rest of the pty-plan-smoke suite
|
||||
// (--max-concurrency + --retry 1), so worst-case cost is ~2x a single
|
||||
// pass of each, sharing the API budget with sibling tests — not the
|
||||
// sequential ~+10min a local read suggests.
|
||||
'plan-mode-no-op': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-mode-no-op.test.ts'],
|
||||
'plan-mode-no-op': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-mode-no-op.test.ts'],
|
||||
|
||||
// v1.21+ AskUserQuestion-blocked regression tests — Conductor launches
|
||||
// claude with `--disallowedTools AskUserQuestion --permission-mode default`
|
||||
@@ -107,24 +107,25 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// INSIDE the existing 4 plan-X-review-plan-mode test files (covered
|
||||
// transitively by the entries above). Two new standalone files exist for
|
||||
// skills with no prior plan-mode test:
|
||||
'office-hours-auto-mode': ['office-hours/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-office-hours-auto-mode.test.ts'],
|
||||
'office-hours-phase4-fork': ['office-hours/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/question-tuning.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours-phase4.test.ts'],
|
||||
'office-hours-auto-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'office-hours/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-office-hours-auto-mode.test.ts'],
|
||||
'office-hours-phase4-fork': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'office-hours/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/question-tuning.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours-phase4.test.ts'],
|
||||
'llm-judge-recommendation': ['test/helpers/llm-judge.ts', 'test/llm-judge-recommendation.test.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'codex/SKILL.md.tmpl', 'scripts/resolvers/review.ts'],
|
||||
// v1.21+ AUTO_DECIDE preserve eval (periodic). Verifies the Tool resolution
|
||||
// fix doesn't trip the legitimate /plan-tune opt-in path: when the user has
|
||||
// written a never-ask preference, AUQ should still auto-decide rather than
|
||||
// surfacing the question. Touches the question-tuning + preference
|
||||
// infrastructure plus the resolvers that own the AUTO_DECIDE preamble.
|
||||
'auto-decide-preserved': ['scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts'],
|
||||
'auto-decide-preserved': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts'],
|
||||
|
||||
// Conductor → prose decision brief (Conductor signal makes prose the default;
|
||||
// the PreToolUse hook denies the flaky tool). Touches the resolver that owns
|
||||
// the Conductor rule, the preamble signal, the hook, and the detection helper.
|
||||
'conductor-prose': ['scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble.ts', 'plan-eng-review/**', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-conductor-prose.test.ts'],
|
||||
'conductor-prose': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble.ts', 'plan-eng-review/**', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-conductor-prose.test.ts'],
|
||||
|
||||
// Real-PTY E2E batch (#6 new tests on the harness).
|
||||
// Each one tests behavior the SDK harness can't observe (rendered TTY,
|
||||
// numbered-option lists, multi-phase ordering, idempotency state echo).
|
||||
'preamble-script-ab': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'plan-ceo-review/**', 'test/helpers/auq-sdk-capture.ts', 'test/skill-e2e-preamble-script-ab.test.ts'],
|
||||
'auq-format-gate': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts'],
|
||||
'plan-ceo-mode-routing': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-mode-routing.test.ts'],
|
||||
'plan-design-with-ui-scope': ['plan-design-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-with-ui.test.ts'],
|
||||
@@ -138,35 +139,35 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// skill (D-CODEX A). Touching the registry/helper or sections.ts runs all.
|
||||
'carve-section-loading': ['plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'],
|
||||
'autoplan-chain-pty': ['autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-autoplan-chain.test.ts'],
|
||||
'e2e-harness-audit': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/claude-pty-runner.ts'],
|
||||
'e2e-harness-audit': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/claude-pty-runner.ts'],
|
||||
|
||||
// Per-finding AskUserQuestion count + review-report-at-bottom assertion.
|
||||
// Each test drives its skill end-to-end; touchfiles include preamble +
|
||||
// completion-status resolvers because they affect question cadence and
|
||||
// terminal output (the regression surface this test catches).
|
||||
'plan-ceo-finding-count': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-finding-count.test.ts'],
|
||||
'plan-eng-finding-count': ['plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-finding-count.test.ts'],
|
||||
'plan-design-finding-count': ['plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-finding-count.test.ts'],
|
||||
'plan-devex-finding-count': ['plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-finding-count.test.ts'],
|
||||
'plan-ceo-finding-count': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-finding-count.test.ts'],
|
||||
'plan-eng-finding-count': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-finding-count.test.ts'],
|
||||
'plan-design-finding-count': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-finding-count.test.ts'],
|
||||
'plan-devex-finding-count': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-finding-count.test.ts'],
|
||||
|
||||
// Gate-tier reviewCount-floor counterparts. Catch the May 2026 transcript
|
||||
// bug (model wrote a plan-mode plan and ExitPlanMode'd without firing any
|
||||
// review-phase AskUserQuestion). Uses runPlanSkillFloorCheck — minimal
|
||||
// "did agent fire ANY AUQ?" observer that exits early on first non-permission
|
||||
// numbered-option render. ~1-3 min typical wall time per test, ~$2-6 total.
|
||||
'plan-eng-finding-floor': ['plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-finding-floor.test.ts'],
|
||||
'plan-ceo-finding-floor': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-ceo-finding-floor.test.ts'],
|
||||
'plan-design-finding-floor': ['plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-design-finding-floor.test.ts'],
|
||||
'plan-devex-finding-floor': ['plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-devex-finding-floor.test.ts'],
|
||||
'plan-eng-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-finding-floor.test.ts'],
|
||||
'plan-ceo-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-ceo-finding-floor.test.ts'],
|
||||
'plan-design-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-design-finding-floor.test.ts'],
|
||||
'plan-devex-finding-floor': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-devex-finding-floor.test.ts'],
|
||||
|
||||
// Multi-finding batching regression — periodic tier complement to the
|
||||
// gate-tier finding-floor. Catches the May 2026 transcript shape where
|
||||
// a model fires one AUQ then batches the rest into a "## Decisions to
|
||||
// confirm" plan write. runPlanSkillFloorCheck cannot detect that shape
|
||||
// (it exits on first AUQ); runPlanSkillCounting can.
|
||||
'plan-eng-multi-finding-batching': ['plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-multi-finding-batching.test.ts'],
|
||||
'plan-eng-multi-finding-batching': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-eng-multi-finding-batching.test.ts'],
|
||||
'plan-ceo-split-overflow': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'bin/gstack-question-preference', 'test/helpers/claude-pty-runner.ts', 'test/fixtures/forcing-finding-seeds.ts', 'test/skill-e2e-plan-ceo-split-overflow.test.ts'],
|
||||
'brain-privacy-gate': ['scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'bin/gstack-brain-sync', 'bin/gstack-artifacts-init', 'bin/gstack-config', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-brain-privacy-gate.test.ts'],
|
||||
'brain-privacy-gate': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'bin/gstack-brain-sync', 'bin/gstack-artifacts-init', 'bin/gstack-config', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-brain-privacy-gate.test.ts'],
|
||||
|
||||
// /setup-gbrain Path 4 (Remote MCP) — happy + bad-token end-to-end via
|
||||
// Agent SDK. Gate-tier (deterministic stub server, fixed inputs); fires
|
||||
@@ -537,6 +538,7 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
// Real-PTY E2E batch — tier classification:
|
||||
// gate: cheap, deterministic, run on every PR
|
||||
// periodic: long-running or expensive (>$3/run), run weekly
|
||||
'preamble-script-ab': 'gate', // Phase 1-3 A/B: script vs inline preamble; demote to periodic after Phase 3 (OV7)
|
||||
'auq-format-gate': 'gate', // ~$0.50/run, SDK capture, single skill probe
|
||||
'plan-ceo-mode-routing': 'periodic', // ~$3/run, deep navigation through 8-12 prior AskUserQuestions
|
||||
'plan-design-with-ui-scope': 'gate', // ~$0.80/run
|
||||
|
||||
@@ -0,0 +1,106 @@
|
||||
/**
|
||||
* Preamble script-consolidation A/B: inline-bash render vs script render —
|
||||
* gate during token-reduction Phases 1-3 (demote to periodic after Phase 3,
|
||||
* plan OV7), paid, SDK capture.
|
||||
*
|
||||
* Phase 1 moved ~13KB of inline preamble bash per skill into
|
||||
* bin/gstack-skill-start. Layer 0 (test/gstack-skill-start.test.ts) proves the
|
||||
* script emits the same STATUS lines deterministically; THIS proves the model
|
||||
* driven by the slim render still runs the preamble and produces an
|
||||
* equal-quality decision brief on the same prompt.
|
||||
*
|
||||
* Arms (precedent: skill-e2e-auq-verbose-vs-carved-ab.test.ts):
|
||||
* - INLINE : pre-Phase-1 plan-ceo-review/SKILL.md read from git
|
||||
* (29785978 = the v1.69.1.0 bump, the last inline-bash render).
|
||||
* - SCRIPT : this worktree's render, with the fence's install-root bin path
|
||||
* rewritten to THIS WORKTREE's bin/ (plan EOV2: hermetic evals
|
||||
* resolve $HOME/.claude/skills/gstack/bin to the operator
|
||||
* install, which would silently exercise the degraded path;
|
||||
* the rewrite makes the branch's script the subject under test).
|
||||
*
|
||||
* Both arms pin GSTACK_HOME to the fixture dir (EOV7: onboarding state is
|
||||
* hermetic now that the script honors GSTACK_HOME).
|
||||
*/
|
||||
import { test, expect } from 'bun:test';
|
||||
import { describeE2ETier } from './helpers/e2e-gate';
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import { execSync } from 'node:child_process';
|
||||
import {
|
||||
setupPlanCeoDir,
|
||||
captureModeSelectionAuq,
|
||||
scoreAuqFormat,
|
||||
carvedSkill,
|
||||
} from './helpers/auq-sdk-capture';
|
||||
|
||||
const describeE2E = describeE2ETier('gate');
|
||||
const runId = `preamble-ab-${process.env.EVALS_RUN_ID ?? 'local'}`;
|
||||
const ROOT = path.resolve(import.meta.dir, '..');
|
||||
const INLINE_REF = '29785978'; // last pre-Phase-1 commit (v1.69.1.0 bump)
|
||||
|
||||
function inlineSkill(): string {
|
||||
return execSync(`git show ${INLINE_REF}:plan-ceo-review/SKILL.md`, {
|
||||
cwd: ROOT,
|
||||
encoding: 'utf-8',
|
||||
maxBuffer: 8 * 1024 * 1024,
|
||||
});
|
||||
}
|
||||
|
||||
/** EOV2 redirection: point the fence at the worktree's bin. */
|
||||
function scriptSkillWorktreeBin(): string {
|
||||
const current = carvedSkill();
|
||||
const rewritten = current.skillMd.replaceAll(
|
||||
'$HOME/.claude/skills/gstack/bin/gstack-skill-start',
|
||||
path.join(ROOT, 'bin', 'gstack-skill-start'),
|
||||
);
|
||||
if (!rewritten.includes(path.join(ROOT, 'bin', 'gstack-skill-start'))) {
|
||||
throw new Error('binDir rewrite matched nothing — fence shape changed; update the A/B redirection');
|
||||
}
|
||||
return rewritten;
|
||||
}
|
||||
|
||||
async function grade(label: string, dir: string) {
|
||||
const text = await captureModeSelectionAuq({ planDir: dir, testName: `preamble-ab-${label}`, runId });
|
||||
const fmt = scoreAuqFormat(text);
|
||||
// eslint-disable-next-line no-console
|
||||
console.log(`[PREAMBLE-AB ${label}] captured=${text.length}B format=${fmt.present}/${fmt.total} missing=[${fmt.missing.join(',')}]`);
|
||||
return { text, fmt };
|
||||
}
|
||||
|
||||
describeE2E('Preamble consolidation no-degradation: inline bash vs script (gate)', () => {
|
||||
test(
|
||||
'script-render plan-ceo-review AUQ is not worse than the inline-bash render on the same prompt',
|
||||
async () => {
|
||||
const sections = carvedSkill().sectionsFrom;
|
||||
const scriptDir = setupPlanCeoDir({
|
||||
skillMd: scriptSkillWorktreeBin(),
|
||||
sectionsFrom: sections,
|
||||
tmpPrefix: 'preamble-ab-script-',
|
||||
});
|
||||
const inlineDir = setupPlanCeoDir({
|
||||
skillMd: inlineSkill(),
|
||||
sectionsFrom: sections,
|
||||
tmpPrefix: 'preamble-ab-inline-',
|
||||
});
|
||||
|
||||
let s, i;
|
||||
try {
|
||||
s = await grade('SCRIPT', scriptDir);
|
||||
i = await grade('INLINE', inlineDir);
|
||||
} finally {
|
||||
fs.rmSync(scriptDir, { recursive: true, force: true });
|
||||
fs.rmSync(inlineDir, { recursive: true, force: true });
|
||||
}
|
||||
|
||||
// Both arms must produce a capture at all (an empty script-arm capture
|
||||
// means the preamble derailed the workflow — exactly the regression this
|
||||
// guards against).
|
||||
expect(s.text.length).toBeGreaterThan(100);
|
||||
expect(i.text.length).toBeGreaterThan(100);
|
||||
// Relative parity: the script render is NOT WORSE on decision-brief
|
||||
// format elements (absolute compliance is auq-format-gate's job).
|
||||
expect(s.fmt.present).toBeGreaterThanOrEqual(i.fmt.present);
|
||||
},
|
||||
20 * 60 * 1000,
|
||||
);
|
||||
});
|
||||
@@ -111,8 +111,10 @@ describe('selectTests', () => {
|
||||
expect(result.selected).toContain('plan-ceo-split-overflow');
|
||||
// v2 plan Phase B carve: the section-loading E2E depends on plan-ceo-review/**.
|
||||
expect(result.selected).toContain('plan-ceo-section-loading');
|
||||
expect(result.selected.length).toBe(23);
|
||||
expect(result.skipped.length).toBe(Object.keys(E2E_TOUCHFILES).length - 23);
|
||||
// Token-reduction Phase 1: the preamble script A/B also keys on plan-ceo-review/**.
|
||||
expect(result.selected).toContain('preamble-script-ab');
|
||||
expect(result.selected.length).toBe(24);
|
||||
expect(result.skipped.length).toBe(Object.keys(E2E_TOUCHFILES).length - 24);
|
||||
});
|
||||
|
||||
test('global touchfile triggers ALL tests', () => {
|
||||
|
||||
Reference in New Issue
Block a user