Merge origin/main (v1.64.1.0 code-smell wave) into test-evals-ci-speedup

Both sides shipped overlapping test-infra work in parallel; resolutions
compose intent rather than picking sides:

- free-tests.yml (both added): keep this branch's lane (canonical
  strict-parallel runner, secretless, plain runner, ~2min) over main's
  per-file-serial container loop (45min budget, hand-curated skip list,
  needs GITHUB_TOKEN); ported main's git safe.directory insight.
- Dockerfile.ci Bun install: main discovered the installer IGNORES the
  BUN_VERSION env var (the old form silently installed latest) — main's
  arg-form mechanism + this branch's 1.3.13 target.
- parity baseline: both sides rebased after hitting the same silent
  drift; adopted main's v1.64.1.0 union-normalized fixture and dropped
  this branch's interim v1.64.0.0 capture. carve-guards caps: main's
  tighter re-ratchets win (all four).
- touchfiles: kept this branch's three-file facade split; ported main's
  pure-data removals (dead sidebar-agent entries, spec judge entry,
  ship-idempotency) into touchfiles-data.ts.
- ship-idempotency SDK variant: main deliberately removed it as
  redundant with the real-PTY test; adopted — dropped this branch's
  rehomed copy and its periodic matrix row (the zombie-monolith deletion
  stands; coverage-audit + triage rehomes verified untouched by main).
- e2e-tier-alignment: taught the new parent-mapper hard check main's
  consolidated describeE2ETier()/e2eTierEnabled() self-gate shapes (the
  helper's header names this file as a required recognizer).
- browse/test/compare-board.test.ts: quarantined behind
  GSTACK_COMPARE_BOARD_TESTS=1 — all 16 tests fail identically on
  origin/main solo on dev machines (blame protocol receipts in-file);
  main's own CI lane skip-lists it. An always-red file would block every
  PR now that free-tests is a required check.

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

test/helpers/e2e-helpers.ts

@@ -33,26 +33,36 @@ export const evalsEnabled = !!process.env.EVALS;
 // --- Diff-based test selection ---
 // When EVALS_ALL is not set, only run tests whose touchfiles were modified.
 // Set EVALS_ALL=1 to force all tests. Set EVALS_BASE to override base branch.
-export let selectedTests: string[] | null = null; // null = run all
 
-if (evalsEnabled && !process.env.EVALS_ALL) {
+/**
+ * Compute the diff-based selection for a touchfiles table. Returns null for
+ * "run all" (EVALS off, EVALS_ALL=1, or no diff vs the base branch — e.g. on
+ * main). Shared by this module (E2E_TOUCHFILES) and skill-llm-eval.test.ts
+ * (LLM_JUDGE_TOUCHFILES) so the selection logic exists exactly once.
+ */
+export function computeDiffSelection(
+  touchfiles: Record<string, string[]>,
+  label: string,
+): string[] | null {
+  if (!evalsEnabled || process.env.EVALS_ALL) return null;
   const baseBranch = process.env.EVALS_BASE
     || detectBaseBranch(ROOT)
     || 'main';
   const changedFiles = getChangedFiles(baseBranch, ROOT);
+  // If changedFiles is empty (e.g., on main branch), run all
+  if (changedFiles.length === 0) return null;
 
-  if (changedFiles.length > 0) {
-    const selection = selectTests(changedFiles, E2E_TOUCHFILES, GLOBAL_TOUCHFILES);
-    selectedTests = selection.selected;
-    process.stderr.write(`\nE2E selection (${selection.reason}): ${selection.selected.length}/${Object.keys(E2E_TOUCHFILES).length} tests\n`);
-    if (selection.skipped.length > 0) {
-      process.stderr.write(`  Skipped: ${selection.skipped.join(', ')}\n`);
-    }
-    process.stderr.write('\n');
+  const selection = selectTests(changedFiles, touchfiles, GLOBAL_TOUCHFILES);
+  process.stderr.write(`\n${label} selection (${selection.reason}): ${selection.selected.length}/${Object.keys(touchfiles).length} tests\n`);
+  if (selection.skipped.length > 0) {
+    process.stderr.write(`  Skipped: ${selection.skipped.join(', ')}\n`);
   }
-  // If changedFiles is empty (e.g., on main branch), selectedTests stays null → run all
+  process.stderr.write('\n');
+  return selection.selected;
 }
 
+export let selectedTests: string[] | null = computeDiffSelection(E2E_TOUCHFILES, 'E2E'); // null = run all
+
 // EVALS_TIER: filter tests by tier after diff-based selection.
 // 'gate' = gate tests only (CI default — blocks merge)
 // 'periodic' = periodic tests only (weekly cron / manual)
@@ -73,9 +83,14 @@ if (evalsEnabled && process.env.EVALS_TIER) {
 
 export const describeE2E = evalsEnabled ? describe : describe.skip;
 
-/** Wrap a describe block to skip entirely if none of its tests are selected. */
-export function describeIfSelected(name: string, testNames: string[], fn: () => void) {
-  const anySelected = selectedTests === null || testNames.some(t => selectedTests!.includes(t));
+/**
+ * Wrap a describe block to skip entirely if none of its tests are selected.
+ * `selected` defaults to this module's E2E selection (diff + EVALS_TIER);
+ * pass an explicit selection (e.g. computeDiffSelection over
+ * LLM_JUDGE_TOUCHFILES) to reuse the gating against a different table.
+ */
+export function describeIfSelected(name: string, testNames: string[], fn: () => void, selected: string[] | null = selectedTests) {
+  const anySelected = selected === null || testNames.some(t => selected.includes(t));
   (anySelected ? describeE2E : describe.skip)(name, fn);
 }
 
@@ -270,14 +285,14 @@ if (evalsEnabled) {
 }
 
 /** Skip an individual test if not selected (for multi-test describe blocks). */
-export function testIfSelected(testName: string, fn: () => Promise<void>, timeout: number) {
-  const shouldRun = selectedTests === null || selectedTests.includes(testName);
+export function testIfSelected(testName: string, fn: () => Promise<void>, timeout: number, selected: string[] | null = selectedTests) {
+  const shouldRun = selected === null || selected.includes(testName);
   (shouldRun ? test : test.skip)(testName, fn, timeout);
 }
 
 /** Concurrent version — runs in parallel with other concurrent tests within the same describe block. */
-export function testConcurrentIfSelected(testName: string, fn: () => Promise<void>, timeout: number) {
-  const shouldRun = selectedTests === null || selectedTests.includes(testName);
+export function testConcurrentIfSelected(testName: string, fn: () => Promise<void>, timeout: number, selected: string[] | null = selectedTests) {
+  const shouldRun = selected === null || selected.includes(testName);
   (shouldRun ? test.concurrent : test.skip)(testName, fn, timeout);
 }