refactor(test): migrate the 36 tier-gated eval files to describeE2ETier

Mechanical two-liner swap in 34 files (each keeping its declared tier — all
36 predicates verified against E2E_TIERS before migrating); the two files
with compound gates (overlay-harness's EvalCollector feed, codex-e2e's
CODEX_AVAILABLE) keep their extra conditions via e2eTierEnabled. Tier
rationale comments preserved. codex-e2e/gemini-e2e/benchmark-providers keep
their distinct stderr-message gate shapes by design.

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

test/carve-section-loading.test.ts

@@ -19,12 +19,12 @@
  * Step-0 mode loop) and keep their dedicated tests; E1 asserts those exist.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { setupSkillDir, skillFromWorktree, captureSectionReads } from './helpers/auq-sdk-capture';
 import { CARVE_GUARDS } from './helpers/carve-guards';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 const runId = `carve-section-loading-${process.env.EVALS_RUN_ID ?? 'local'}`;
 const only = process.env.GSTACK_CARVE_SKILL?.trim();
 

test/codex-e2e-recommendation-substance.test.ts

@@ -22,6 +22,7 @@
  */
 import { describe, test, expect } from 'bun:test';
 import * as path from 'node:path';
+import { e2eTierEnabled } from './helpers/e2e-gate';
 import { runCodexSkill } from './helpers/codex-session-runner';
 import { judgeRecommendation } from './helpers/llm-judge';
 
@@ -34,8 +35,7 @@ const CODEX_AVAILABLE = (() => {
     return false;
   }
 })();
-const shouldRun =
-  CODEX_AVAILABLE && !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
+const shouldRun = CODEX_AVAILABLE && e2eTierEnabled('periodic');
 const describeCodex = shouldRun ? describe : describe.skip;
 
 // A small fixture with two real, comparable problems so a good recommendation

test/skill-e2e-ask-user-question-format-compliance.test.ts

@@ -22,7 +22,8 @@
  * hide; the model's composed question is. Shares the engine with the periodic
  * A/B and matrix evals (test/helpers/auq-sdk-capture.ts).
  */
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   setupPlanCeoDir,
@@ -32,8 +33,7 @@ import {
   carvedSkill,
 } from './helpers/auq-sdk-capture';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 const runId = `auq-format-gate-${process.env.EVALS_RUN_ID ?? 'local'}`;
 
 describeE2E('AskUserQuestion format compliance (gate)', () => {

test/skill-e2e-auq-consistency.test.ts

@@ -15,7 +15,8 @@
  * Reports per-run scores so drift is visible even on a pass. Periodic tier
  * (N SDK runs, ~$0.50-1 each).
  */
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   setupPlanCeoDir,
@@ -25,8 +26,7 @@ import {
 } from './helpers/auq-sdk-capture';
 import { judgeRecommendation } from './helpers/llm-judge';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 const N_RUNS = Number(process.env.AUQ_CONSISTENCY_RUNS ?? '3');
 const runId = `auq-consistency-${process.env.EVALS_RUN_ID ?? 'local'}`;
 

test/skill-e2e-auq-matrix.test.ts

@@ -22,7 +22,8 @@
  *
  * Run a subset in the foreground with AUQ_MATRIX_ONLY="plan-eng-review,cso".
  */
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   setupSkillDir,
@@ -32,8 +33,7 @@ import {
   gradeAuqRecommendation,
 } from './helpers/auq-sdk-capture';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 const runId = `auq-matrix-${process.env.EVALS_RUN_ID ?? 'local'}`;
 const ONLY = (process.env.AUQ_MATRIX_ONLY ?? '').split(',').map(s => s.trim()).filter(Boolean);
 

test/skill-e2e-auq-verbose-vs-carved-ab.test.ts

@@ -22,7 +22,8 @@
  * carries the same {{PREAMBLE}} format spec + Step 0 prose as verbose, with
  * strictly less unrelated review-section text in context.
  */
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   setupPlanCeoDir,
@@ -33,8 +34,7 @@ import {
 } from './helpers/auq-sdk-capture';
 import { judgeRecommendation } from './helpers/llm-judge';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 const runId = `auq-ab-${process.env.EVALS_RUN_ID ?? 'local'}`;
 
 async function grade(label: string, dir: string) {

test/skill-e2e-auto-decide-preserved.test.ts

@@ -37,15 +37,15 @@
  * practice but not the load-bearing behavior).
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillObservation } from './helpers/claude-pty-runner';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
 import { spawnSync } from 'child_process';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const ROOT = path.resolve(import.meta.dir, '..');
 

test/skill-e2e-autoplan-chain.test.ts

@@ -24,7 +24,8 @@
  * Cost: ~$5-8/run, 10-15 min wall clock. Periodic — runs weekly.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { spawnSync } from 'child_process';
 import * as fs from 'fs';
 import * as path from 'path';
@@ -36,8 +37,7 @@ import {
   isNumberedOptionListVisible,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const ROOT = path.resolve(import.meta.dir, '..');
 const UI_FIXTURE = path.join(ROOT, 'test', 'fixtures', 'plans', 'ui-heavy-feature.md');

test/skill-e2e-brain-privacy-gate.test.ts

@@ -20,14 +20,14 @@
  * prose contract this test locks in.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
 import { runAgentSdkTest, passThroughNonAskUserQuestion, resolveClaudeBinary } from './helpers/agent-sdk-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
   test('gstack skill preamble fires the 3-option AskUserQuestion when gbrain is detected', async () => {

test/skill-e2e-conductor-prose.test.ts

@@ -20,11 +20,11 @@
  * Periodic tier: model-behavior, non-deterministic.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillObservation } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const FLAWED_PLAN = `# Plan: add a "developer-friendly" pricing tier
 

test/skill-e2e-office-hours-auto-mode.test.ts

@@ -16,11 +16,11 @@
  * distinct silencing mechanism; both share the same fix surface.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillObservation, planFileHasDecisionsSection } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 describeE2E('office-hours AskUserQuestion-blocked smoke (gate)', () => {
   // Pass envelope is ['asked', 'plan_ready']; failure signals are

test/skill-e2e-overlay-harness.test.ts

@@ -20,7 +20,8 @@
  * Gated by EVALS=1 AND EVALS_TIER=periodic. Never runs under test:gate.
  */
 
-import { describe, test, expect, afterAll } from 'bun:test';
+import { test, expect, afterAll } from 'bun:test';
+import { describeE2ETier, e2eTierEnabled } from './helpers/e2e-gate';
 import * as fs from 'fs';
 import * as path from 'path';
 import * as os from 'os';
@@ -37,11 +38,9 @@ import {
 } from './fixtures/overlay-nudges';
 import { readOverlay } from '../scripts/resolvers/model-overlay';
 
-const evalsEnabled = !!process.env.EVALS;
-const periodicTier = process.env.EVALS_TIER === 'periodic';
-const shouldRun = evalsEnabled && periodicTier;
+const shouldRun = e2eTierEnabled('periodic');
 
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 // EvalCollector's tier must be 'e2e' | 'llm-judge' per its type signature.
 // The existing paid evals violate this by passing descriptive names like
 // 'e2e-opus-47' — a pre-existing pattern that only works because bun-test

test/skill-e2e-plan-ceo-finding-count.test.ts

@@ -15,7 +15,8 @@
  * test/helpers/claude-pty-runner.ts for runPlanSkillCounting internals.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   runPlanSkillCounting,
@@ -51,8 +52,7 @@ function pickSkipInterview(fp: AskUserQuestionFingerprint): number {
   return 1;
 }
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const N_DISTINCT = 5;
 const FLOOR_DISTINCT = N_DISTINCT - 1; // 4 (D11)

test/skill-e2e-plan-ceo-finding-floor.test.ts

@@ -4,12 +4,12 @@
  * See test/skill-e2e-plan-eng-finding-floor.test.ts for the contract.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
 import { FORCING_FLOOR_CEO } from './fixtures/forcing-finding-seeds';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 describeE2E('/plan-ceo-review AskUserQuestion floor (gate)', () => {
   test(

test/skill-e2e-plan-ceo-mode-routing.test.ts

@@ -30,7 +30,8 @@
  *   SCOPE EXPANSION   — "expansion" or "10x" or "delight" or "dream"
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   launchClaudePty,
   isNumberedOptionListVisible,
@@ -43,8 +44,7 @@ import {
   type ClaudePtySession,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 interface ModeCase {
   mode: 'HOLD SCOPE' | 'SCOPE EXPANSION';

test/skill-e2e-plan-ceo-plan-mode.test.ts

@@ -33,14 +33,14 @@
  * See test/helpers/claude-pty-runner.ts for runner internals.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   runPlanSkillObservation,
   assertReportAtBottomIfPlanWritten,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 describeE2E('plan-ceo-review plan-mode smoke (gate)', () => {
   test('first terminal outcome is asked (Step 0 fires before any plan write)', async () => {

test/skill-e2e-plan-ceo-review-section-loading.test.ts

@@ -24,15 +24,15 @@
  * ~$1-2/run. Periodic tier.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   setupSkillDir,
   skillFromWorktree,
   captureSectionReads,
 } from './helpers/auq-sdk-capture';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 const runId = `plan-ceo-section-loading-${process.env.EVALS_RUN_ID ?? 'local'}`;
 
 // Sections every plan-ceo-review run must consult after Step 0.

test/skill-e2e-plan-ceo-split-overflow.test.ts

@@ -32,7 +32,8 @@
  * Sequential by default.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   runPlanSkillCounting,
@@ -40,8 +41,7 @@ import {
 } from './helpers/claude-pty-runner';
 import { FORCING_SPLIT_OVERFLOW_CEO } from './fixtures/forcing-finding-seeds';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const N = 5;
 const FLOOR = N - 1; // 4 — must fire at least one AUQ per non-dropped option

test/skill-e2e-plan-design-finding-count.test.ts

@@ -8,7 +8,8 @@
  * Tier: periodic (~25 min, ~$5/run). Sequential by default per plan §D15.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   runPlanSkillCounting,
@@ -16,8 +17,7 @@ import {
   assertReviewReportAtBottom,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const N = 5;
 const FLOOR = N - 1;

test/skill-e2e-plan-design-finding-floor.test.ts

@@ -4,12 +4,12 @@
  * See test/skill-e2e-plan-eng-finding-floor.test.ts for the contract.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
 import { FORCING_FLOOR_DESIGN } from './fixtures/forcing-finding-seeds';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 describeE2E('/plan-design-review AskUserQuestion floor (periodic)', () => {
   test(

test/skill-e2e-plan-design-plan-mode.test.ts

@@ -9,14 +9,14 @@
  * 'plan_ready' are valid pass outcomes.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   runPlanSkillObservation,
   assertReportAtBottomIfPlanWritten,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 // UI-heavy seed with guaranteed design gaps (center-aligned everything, no
 // empty states, no responsive intent) so the review has real findings to

test/skill-e2e-plan-design-with-ui.test.ts

@@ -19,7 +19,8 @@
  * contain "no UI scope".
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as path from 'path';
 import {
   launchClaudePty,
@@ -29,8 +30,7 @@ import {
   isPlanReadyVisible,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 const ROOT = path.resolve(import.meta.dir, '..');
 const FIXTURE = path.join(ROOT, 'test', 'fixtures', 'plans', 'ui-heavy-feature.md');

test/skill-e2e-plan-devex-finding-count.test.ts

@@ -8,7 +8,8 @@
  * Tier: periodic (~25 min, ~$5/run). Sequential by default per plan §D15.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   runPlanSkillCounting,
@@ -16,8 +17,7 @@ import {
   assertReviewReportAtBottom,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const N = 5;
 const FLOOR = N - 1;

test/skill-e2e-plan-devex-finding-floor.test.ts

@@ -4,12 +4,12 @@
  * See test/skill-e2e-plan-eng-finding-floor.test.ts for the contract.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
 import { FORCING_FLOOR_DEVEX } from './fixtures/forcing-finding-seeds';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 describeE2E('/plan-devex-review AskUserQuestion floor (gate)', () => {
   test(

test/skill-e2e-plan-devex-plan-mode.test.ts

@@ -5,15 +5,15 @@
  * contract. Exercises the same contract against /plan-devex-review.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   runPlanSkillObservation,
   planFileHasDecisionsSection,
   assertReportAtBottomIfPlanWritten,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 describeE2E('plan-devex-review plan-mode smoke (gate)', () => {
   test('reaches a terminal outcome (asked or plan_ready) without silent writes', async () => {

test/skill-e2e-plan-eng-finding-count.test.ts

@@ -8,7 +8,8 @@
  * Tier: periodic (~25 min, ~$5/run). Sequential by default per plan §D15.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   runPlanSkillCounting,
@@ -16,8 +17,7 @@ import {
   assertReviewReportAtBottom,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const N = 5;
 const FLOOR = N - 1; // 4

test/skill-e2e-plan-eng-finding-floor.test.ts

@@ -15,12 +15,12 @@
  * Cost: ~$0.50-$1.50 per run depending on early-exit timing.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillFloorCheck } from './helpers/claude-pty-runner';
 import { FORCING_FLOOR_ENG } from './fixtures/forcing-finding-seeds';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 describeE2E('/plan-eng-review AskUserQuestion floor (periodic)', () => {
   test(

test/skill-e2e-plan-eng-multi-finding-batching.test.ts

@@ -24,7 +24,8 @@
  * Tier: periodic (~25 min, ~$5/run). Sequential by default.
  */
 
-import { describe, test } from 'bun:test';
+import { test } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
 import {
   runPlanSkillCounting,
@@ -32,8 +33,7 @@ import {
 } from './helpers/claude-pty-runner';
 import { FORCING_BATCHING_ENG } from './fixtures/forcing-finding-seeds';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const N = 4;
 const FLOOR = N - 1; // 3 — agent must fire at least one AUQ per non-batched finding

test/skill-e2e-plan-eng-plan-mode.test.ts

@@ -5,15 +5,15 @@
  * contract. This file exercises the same contract against /plan-eng-review.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   runPlanSkillObservation,
   planFileHasDecisionsSection,
   assertReportAtBottomIfPlanWritten,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 // SEED_PLAN_FORCING_FINDINGS: 8+ files + custom-vs-builtin smell forces the
 // Step 0 complexity check to trigger. Passed via runPlanSkillObservation's

test/skill-e2e-plan-mode-no-op.test.ts

@@ -30,11 +30,11 @@
  * change (see 'plan-mode-no-op' in touchfiles.ts).
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { runPlanSkillObservation } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('gate');
 
 const PLAN_MODE_REMINDER =
   'Plan mode is active. The user indicated that they do not want you to execute yet';

test/skill-e2e-setup-gbrain-bad-token.test.ts

@@ -8,7 +8,8 @@
 //
 // Cost: ~$0.30-$0.50 per run. Gate-tier (EVALS=1 EVALS_TIER=gate).
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
@@ -17,8 +18,7 @@ import { runAgentSdkTest, passThroughNonAskUserQuestion, resolveClaudeBinary } f
 
 // Periodic-tier (companion to skill-e2e-setup-gbrain-remote.test.ts).
 // Deterministic gate coverage lives in setup-gbrain-path4-structure.test.ts.
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 function startStub401(): Promise<{ url: string; close: () => Promise<void> }> {
   return new Promise((resolve) => {

test/skill-e2e-setup-gbrain-path4-local-pglite.test.ts

@@ -18,7 +18,8 @@
 //
 // Cost: ~$0.50-$1.00 per run. Periodic-tier (EVALS=1 EVALS_TIER=periodic).
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
@@ -29,8 +30,7 @@ import {
   resolveClaudeBinary,
 } from './helpers/agent-sdk-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 /**
  * Minimal stub MCP server that returns success on initialize / tools/list.

test/skill-e2e-setup-gbrain-remote.test.ts

@@ -11,7 +11,8 @@
 //
 // See setup-gbrain/SKILL.md.tmpl Step 4 (Path 4) for the contract under test.
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
@@ -22,8 +23,7 @@ import { runAgentSdkTest, passThroughNonAskUserQuestion, resolveClaudeBinary } f
 // non-deterministic (it sometimes skips Step 8 CLAUDE.md write, sometimes
 // shortcuts past the verify helper). The deterministic gate coverage for
 // Path 4 lives in test/setup-gbrain-path4-structure.test.ts (free, <200ms).
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 // Spin up a stub MCP server that responds to initialize + tools/list.
 function startStubMcpServer(opts: { failWithStatus?: number; failBody?: string } = {}): Promise<{ url: string; close: () => Promise<void> }> {

test/skill-e2e-ship-idempotency.test.ts

@@ -30,7 +30,8 @@
  * Cost: ~$2-4/run. Periodic tier — long, runs weekly.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import { spawnSync } from 'child_process';
 import * as fs from 'fs';
 import * as path from 'path';
@@ -41,8 +42,7 @@ import {
   isNumberedOptionListVisible,
 } from './helpers/claude-pty-runner';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 interface ShipFixture {
   workTree: string;

test/skill-e2e-ship-section-loading.test.ts

@@ -23,15 +23,15 @@
  * Periodic tier.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import {
   setupSkillDir,
   skillFromWorktree,
   captureSectionReads,
 } from './helpers/auq-sdk-capture';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 const runId = `ship-section-loading-${process.env.EVALS_RUN_ID ?? 'local'}`;
 
 // Sections every version-changing ship must consult.

test/skill-e2e-spec-execute.test.ts

@@ -16,12 +16,12 @@
  * minimum smoke that proves --execute end-to-end works.
  */
 
-import { describe, test, expect } from 'bun:test';
+import { test, expect } from 'bun:test';
+import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'fs';
 import * as path from 'path';
 
-const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
-const describeE2E = shouldRun ? describe : describe.skip;
+const describeE2E = describeE2ETier('periodic');
 
 const ROOT = path.resolve(import.meta.dir, '..');