v1.57.10.0 feat: Codex review default-on across review/ship/plan/docs (#1966)

* feat(config): make codex_reviews the master switch for all Codex review

Broaden the codex_reviews doc to describe it governing /review, /ship,
/document-release, plan reviews, and /autoplan. Reject invalid values on
set (preserving the existing value) so a typo can never silently flip
paid Codex calls on or off.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(review): Codex review default-on across review/ship/plan/docs

Add a shared codexPreflight() helper (constants.ts) that, in one bash
block, reads codex_reviews, sources gstack-codex-probe, checks install +
auth, and echoes a single canonical mode (ready/not_installed/not_authed/
disabled). All Codex resolvers route through it.

- generateCodexPlanReview: opt-in question removed; the outside voice now
  runs automatically (default-on), falling back to a Claude subagent when
  Codex is missing/unauthed. Cross-model tension still gates on user
  approval (sovereignty preserved).
- generateAdversarialStep: probe-based availability (install AND auth),
  distinct not-installed vs not-authed guidance; 200-line structured-review
  threshold unchanged.
- generateCodexDocReview (new, wired via CODEX_DOC_REVIEW): reviews the
  release's docs against the shipped diff range, informational + an explicit
  apply-fixes decision point, never auto-edits.
- autoplan Phase 0.5 now honors codex_reviews=disabled so the switch is
  truly global.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore(docs): regenerate SKILL docs + refresh ship golden

Output of gen:skill-docs for the Codex-default-on resolver/template
changes. Refreshes the factory-ship golden fixture (codex-host output
unchanged — resolvers strip for the codex host).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(infra): widen size-budget guards for default-on Codex outside-voice

The codexPreflight() block + CODEX_MODE branch prose (replacing the
smaller opt-in question) grows plan-ceo/eng/devex-review and review by
5-7% over baseline. Each bump carries a comment justifying it as
intentional capability, not slop.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: guard Codex default-on + config reject-on-set

skill-validation: assert plan reviews no longer carry the opt-in question
and render the default-on outside-voice, document-release carries the doc
review, and the codex host strips all of it.

gstack-config: codex_reviews defaults to enabled, accepts enabled/disabled,
and rejects an invalid value while preserving the existing one.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(test): align gstack-config tests with defaults-fallback behavior

Three tests (last touched v0.13.7.0) asserted get/list print empty for
unset keys, but gstack-config falls back to the documented defaults table
(get returns the default, list shows the active-values block). Update the
assertions to the real behavior and split out an unknown-key case that does
still return empty. Pre-existing red, unrelated to codex review.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* v1.57.10.0 feat: Codex review default-on across review/ship/plan/docs

Codex cross-model review now runs by default on /review, /ship, all four
plan reviews, /document-release, and /autoplan, governed by one master
switch (codex_reviews, default enabled). Plan-review outside voice is
default-on; /document-release gets a new Codex doc-vs-diff audit; every
call site detects install AND auth and falls back to a Claude subagent
with a clear reason. Disable everything with:
gstack-config set codex_reviews disabled

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

test/skill-validation.test.ts

@@ -1386,15 +1386,16 @@ describe('Codex skill', () => {
     expect(content).toContain('Adversarial review (always-on)');
     // Always-on: both Claude and Codex adversarial
     expect(content).toContain('Claude adversarial subagent (always runs)');
-    expect(content).toContain('Codex adversarial challenge (always runs when available)');
+    expect(content).toContain('Codex adversarial challenge (runs whenever');
     // Claude adversarial subagent dispatch
     expect(content).toContain('Agent tool');
     expect(content).toContain('FIXABLE');
     expect(content).toContain('INVESTIGATE');
-    // Codex availability check
-    expect(content).toContain('CODEX_NOT_AVAILABLE');
-    // OLD_CFG only gates Codex, not Claude
-    expect(content).toContain('skip Codex passes only');
+    // Probe-based availability via the shared codexPreflight() (install + auth)
+    expect(content).toContain('CODEX_MODE');
+    expect(content).toContain('command -v codex'); // install check kept literal
+    // codex_reviews=disabled gates Codex passes only; Claude adversarial still runs
+    expect(content).toContain('skip the Codex passes ONLY');
     // Review log
     expect(content).toContain('adversarial-review');
     expect(content).toContain('reasoning_effort="high"');
@@ -1449,6 +1450,43 @@ describe('Codex skill', () => {
     expect(content).toContain('codex exec');
   });
 
+  // D5 regression guard: the Codex outside voice is default-on, not opt-in. A future
+  // gen-skill-docs change must not silently reintroduce the "Want an outside voice?"
+  // AskUserQuestion. The CODEX_PLAN_REVIEW content renders into each skill's
+  // sections/review-sections.md (the skeleton points at it). plan-design-review uses
+  // DESIGN_OUTSIDE_VOICES, not CODEX_PLAN_REVIEW, so it is excluded here.
+  test('plan reviews run the Codex outside voice default-on (no opt-in question)', () => {
+    for (const skill of ['plan-eng-review', 'plan-ceo-review', 'plan-devex-review']) {
+      const content = fs.readFileSync(
+        path.join(ROOT, skill, 'sections', 'review-sections.md'), 'utf-8');
+      expect(content).not.toContain('Want an outside voice');
+      expect(content).toContain('Outside Voice — Independent Plan Challenge (default-on)');
+      expect(content).toContain('CODEX_MODE');
+      expect(content).toContain('command -v codex'); // preflight install check (e2e relies on it)
+    }
+  });
+
+  test('/document-release includes the default-on Codex documentation review', () => {
+    // The doc-review renders into the carved release-body section (kept out of the
+    // always-loaded skeleton to respect the skeleton-byte budget).
+    const content = fs.readFileSync(
+      path.join(ROOT, 'document-release', 'sections', 'release-body.md'), 'utf-8');
+    expect(content).toContain('Codex Documentation Review (default-on)');
+    expect(content).toContain('CODEX_MODE');
+    expect(content).toContain('codex-doc-review');
+  });
+
+  test('codex-host document-release does NOT contain the Codex doc review', () => {
+    // .agents/ is gitignored — generate on demand (codex never invokes itself)
+    Bun.spawnSync(['bun', 'run', 'scripts/gen-skill-docs.ts', '--host', 'codex'], {
+      cwd: ROOT, stdout: 'pipe', stderr: 'pipe',
+    });
+    const content = fs.readFileSync(
+      path.join(ROOT, '.agents', 'skills', 'gstack-document-release', 'SKILL.md'), 'utf-8');
+    expect(content).not.toContain('Codex Documentation Review');
+    expect(content).not.toContain('codex-doc-review');
+  });
+
   test('codex review invocations avoid the prompt plus --base argument shape', () => {
     for (const rel of ['codex/SKILL.md', 'review/SKILL.md', 'ship/SKILL.md']) {
       // ship's codex command moved into sections/adversarial.md (T9 carve).