test(evals): harden no-op asserts, close tier-invariant fail-open holes, pin gate question strings

- no-op regression: gate-must-ask is now UNCONDITIONAL for eng/design (the
  outcome==='asked' conditional let a silent-bypass plan_ready run sail
  through); eng/design cases force --disallowedTools so the pinned prose
  shape is contractual rather than hoping native AUQ renders match; the
  named-target case uses trackTokens for consumption and lists
  wrote_findings_before_asking in its diagnostic throw branch.
- tier-alignment invariant: both quote styles matched; zero-self-gate,
  mixed-tier, and owning-keys-without-E2E_TIERS-entries are all REPORTED
  instead of silently skipped (the fail-open holes three reviewers found).
- drift-guard: the generated gate menus must carry the exact question/option
  strings the PTY question detector anchors on — free CI fails before the
  paid smokes can go vacuous on a menu reword.
- touchfiles: corrected the no-op cost note for CI concurrency + retry
  semantics.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-08-12 09:09:48 -07:00
parent 4e61233021
commit 3ddbee5952
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
4 changed files with 76 additions and 32 deletions

View File

@ -22,7 +22,10 @@ import * as path from 'path';
import { E2E_TOUCHFILES, E2E_TIERS, LLM_JUDGE_TOUCHFILES } from './helpers/touchfiles';
const TEST_DIR = import.meta.dir;
const SELF_GATE_RE = /EVALS_TIER\s*===\s*'(gate|periodic)'/g;
// Both quote styles — a mechanical refactor to double quotes must not
// silently drop a file from the invariant (fail-open is the defect class
// this test exists to kill).
const SELF_GATE_RE = /EVALS_TIER\s*===\s*['"](gate|periodic)['"]/g;
describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () => {
const testFiles = readdirSync(TEST_DIR)
@ -33,24 +36,40 @@ describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () =>
test('every self-gated test file named in a dep list matches its declared tier', () => {
const misaligned: string[] = [];
const unmapped: string[] = [];
const reported: string[] = [];
for (const file of testFiles) {
const content = readFileSync(path.join(TEST_DIR, file), 'utf-8');
const tiers = new Set<string>();
for (const m of content.matchAll(SELF_GATE_RE)) tiers.add(m[1]);
if (tiers.size !== 1) continue; // no self-gate, or mixed-tier file — out of scope
const repoPath = `test/${file}`;
if (tiers.size === 0) {
// Every skill-e2e file is expected to self-gate; zero matches means
// either a genuinely ungated file or a gate shape the regex can't
// see — both worth a visible report, never a silent skip.
reported.push(`${repoPath}: no detectable EVALS_TIER self-gate`);
continue;
}
if (tiers.size > 1) {
reported.push(`${repoPath}: mixed-tier self-gates (${[...tiers].join(', ')}) — not tier-checked`);
continue;
}
const selfTier = [...tiers][0];
const repoPath = `test/${file}`;
const owningKeys = Object.keys(allDeps).filter((k) => allDeps[k].includes(repoPath));
if (owningKeys.length === 0) {
unmapped.push(`${repoPath} (self-gates '${selfTier}')`);
reported.push(`${repoPath} (self-gates '${selfTier}'): not named in any touchfiles dep list`);
continue;
}
for (const k of owningKeys) {
const declared = E2E_TIERS[k];
if (declared && declared !== selfTier) {
if (!declared) {
// A dep-list key with no E2E_TIERS entry (e.g. an LLM-judge key)
// can't tier-check this file — report instead of silently passing.
reported.push(`${repoPath}: matched key '${k}' which has no E2E_TIERS entry`);
continue;
}
if (declared !== selfTier) {
misaligned.push(
`${repoPath}: self-gates on '${selfTier}' but E2E_TIERS['${k}'] declares '${declared}' — the declaration is inert`,
);
@ -58,13 +77,12 @@ describe('E2E tier alignment (touchfiles declaration vs test self-gate)', () =>
}
}
// Reported, not asserted: these files' evals can't be tier-checked until
// their dep lists name the test file. Add `test/<file>` to the eval's
// touchfiles entry to bring them under the invariant.
if (unmapped.length > 0) {
// Reported, not asserted: coverage holes the invariant can see but not
// arbitrate. Add the test file to its eval's dep list (or a tier entry
// for the key) to bring it under the invariant.
if (reported.length > 0) {
console.warn(
`[tier-alignment] ${unmapped.length} self-gated test file(s) not named in any touchfiles dep list:\n ` +
unmapped.join('\n '),
`[tier-alignment] ${reported.length} file(s) outside the invariant:\n ` + reported.join('\n '),
);
}

View File

@ -3256,7 +3256,7 @@ describe('scope-gate exceptions drift-guard', () => {
// instead of drifting. The real fix (shared {{SCOPE_GATE}} resolver) is a
// filed TODO — this guard is the stopgap that makes the duplication safe.
const START_MARKER = '**Exceptions — check in this order, BEFORE asking:**';
const END_MARKER = 'nothing changes: this gate is a hard STOP.';
const END_MARKER = 'in any mode — it is a hard STOP.';
function extractExceptionsBlock(skill: string): string {
const md = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
@ -3290,6 +3290,18 @@ describe('scope-gate exceptions drift-guard', () => {
);
}
});
test('gate menu carries the question strings the PTY question detector pins', () => {
// isScopeGateQuestionVisible (claude-pty-runner.ts) anchors on the
// question text + option A's body. If the menu is reworded without
// updating the detector, the paid smokes' must-stay-false assertions go
// vacuous — this free pin fails first.
for (const skill of ['plan-eng-review', 'plan-design-review']) {
const md = fs.readFileSync(path.join(ROOT, skill, 'SKILL.md'), 'utf-8');
expect(md, `${skill}: gate question text`).toContain('What should I review?');
expect(md, `${skill}: option A body text`).toContain('The current branch diff');
}
});
});
describe('GSTACK REVIEW REPORT mandatory unresolved-decisions status', () => {

View File

@ -103,8 +103,11 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'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'],
// Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not
// fire outside plan mode) + the named-target exception case. 4 sequential
// PTY runs (~+10 min, ~+$2 vs the pre-bypass single run).
// 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 2), so worst-case cost is ~3x 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'],
// v1.21+ AskUserQuestion-blocked regression tests — Conductor launches

View File

@ -31,7 +31,6 @@
*/
import { describe, test, expect } from 'bun:test';
import { existsSync, readFileSync } from 'node:fs';
import { runPlanSkillObservation } from './helpers/claude-pty-runner';
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
@ -64,6 +63,15 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
skillName,
inPlanMode: false,
timeoutMs: 300_000,
// eng/design: force the prose-fallback path. The unconditional
// gate-must-ask assert below pins the render shape the detector
// anchors on, and only the --disallowedTools prose fallback makes
// that shape CONTRACTUAL ("use exactly this shape" in the template);
// native AskUserQuestion could render terse option labels that a
// correct run would fail on (red-team finding).
...(skillName === 'plan-ceo-review'
? {}
: { extraArgs: ['--disallowedTools', 'AskUserQuestion'] }),
});
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
@ -85,12 +93,13 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
// Scope-gate bypass must not misfire: no auto-select announcement
// outside plan mode.
expect(obs.scopeGateAutoSelectObserved ?? false).toBe(false);
// And when a question fired, it must have been the scope gate —
// outside plan mode with no named target, the gate is the FIRST
// question by contract (hard STOP before any tool call).
if (obs.outcome === 'asked') {
expect(obs.scopeGateQuestionObserved ?? false).toBe(true);
}
// UNCONDITIONAL: outside plan mode with no named target, the gate is
// a hard STOP before any tool call, so the gate question must have
// rendered no matter which terminal outcome fired. Gating this on
// outcome === 'asked' would let a silent-bypass run that reaches
// plan_ready (isPlanReadyVisible also matches common prose) sail
// through — the exact regression this test exists to catch.
expect(obs.scopeGateQuestionObserved ?? false).toBe(true);
}
}, 360_000);
}
@ -106,10 +115,16 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
skillName: 'plan-eng-review',
inPlanMode: false,
initialPlanContent: NAMED_TARGET_SEED,
trackTokens: [SEED_TOKEN],
timeoutMs: 300_000,
});
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
if (
obs.outcome === 'wrote_findings_before_asking' ||
obs.outcome === 'silent_write' ||
obs.outcome === 'exited' ||
obs.outcome === 'timeout'
) {
throw new Error(
`named-target no-op FAILED: outcome=${obs.outcome}\n` +
`summary: ${obs.summary}\n` +
@ -125,14 +140,10 @@ describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
expect(obs.scopeGateQuestionObserved ?? false).toBe(false);
expect(obs.scopeGateAutoSelectObserved ?? false).toBe(false);
// Target consumption: the review must reference the seeded feature.
// evidence is the lossy 2KB tail, so also accept the token appearing in
// the plan file the review wrote — the token names the component, route,
// and test file every finding has to discuss, so absence from BOTH means
// the pasted target was not actually reviewed.
const inEvidence = obs.evidence.includes(SEED_TOKEN);
const inPlanFile =
!!obs.planFile && existsSync(obs.planFile) && readFileSync(obs.planFile, 'utf-8').includes(SEED_TOKEN);
expect(inEvidence || inPlanFile).toBe(true);
// Target consumption via high-water token tracking over the CUMULATIVE
// buffer — the 2KB evidence tail is lossy and the plan-file fallback is
// unreachable outside plan mode (extractPlanFilePath only matches
// plan-mode save renders).
expect(obs.tokensObserved?.[SEED_TOKEN] ?? false).toBe(true);
}, 360_000);
});