Merge origin/main (v1.65.0.0 fork port wave 2) into test-evals-ci-speedup

Second overlapping-wave merge; resolutions compose intent:

- TEST_ROOTS: ours is the superset (main also wired ios-qa/daemon/test;
  ours additionally has ios-qa/scripts + browser-skills). package.json
  'test' keeps routing through the canonical strict runner.
- gbrainAvailable: main fixed the same load-flake with a strictly better
  mechanism (memoized stat-based PATH scan, no subprocess at all) —
  theirs supersedes this branch's memoized-exec probe. Main also made
  the query timeout env-overridable (GSTACK_BRAIN_TIMEOUT_MS).
- Model defaults: adopted main's lib/eval-model.ts abstraction (one
  resolution point, env-overridable per kind) and applied decision D1a
  inside it: capture defaults to Sonnet (Opus opt-in via explicit arg or
  GSTACK_EVAL_MODEL_CAPTURE); test pins updated to follow.
- Parent watchdog: main's rewrite (named parameterized tick, driven
  deterministically by its test via __testInternals__, plus handoff
  suppression semantics from session persistence) supersedes this
  branch's env-tunable interval; adopted their server + test wholesale.
- windows-free-tests: ours (curated bun run test:windows) — main's
  hand-list grew by one more file, which the curated runner subsumes
  automatically; that drift is the reason for D11.
- context-skills 0-for-26 fix: both waves made the IDENTICAL fix; kept
  this branch's comment (carries the receipts).
- .gitignore: main's superset (also ignores Package.resolved — their
  never-commit call; untracked the copy this branch had committed).

Verified: 239-test merge battery green, watchdog 8/8, eval-model 5/5,
actionlint clean, eval:select works.

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

test/helpers/auq-sdk-capture.ts

@@ -11,6 +11,7 @@
  * zero rendering loss. The TTY rendering layer is identical for fat and slim
  * skills, so it is not where token-reduction degradation can hide.
  */
+import { resolveEvalModel } from '../../lib/eval-model';
 import * as fs from 'node:fs';
 import * as os from 'node:os';
 import * as path from 'node:path';
@@ -191,7 +192,7 @@ This is a capture test, not an interactive session. Skip any system-audit / envi
     timeout: 240_000,
     testName: opts.testName,
     runId: opts.runId,
-    model: opts.model ?? 'claude-sonnet-4-6', // D1a: align with session-runner default; Opus is opt-in
+    model: resolveEvalModel('capture', opts.model),
   });
 
   try {
@@ -253,7 +254,7 @@ Rules for this run:
     timeout: opts.timeout ?? 300_000,
     testName: opts.testName,
     runId: opts.runId,
-    model: opts.model ?? 'claude-sonnet-4-6', // D1a: align with session-runner default; Opus is opt-in
+    model: resolveEvalModel('capture', opts.model),
   });
 
   const readSections = new Set<string>();
@@ -334,7 +335,7 @@ Write the verbatim text of that AskUserQuestion (the full decision brief: title,
     timeout: 240_000,
     testName: opts.testName,
     runId: opts.runId,
-    model: opts.model ?? 'claude-sonnet-4-6', // D1a: align with session-runner default; Opus is opt-in
+    model: resolveEvalModel('capture', opts.model),
   });
 
   try {

test/helpers/carve-guards.ts

@@ -99,6 +99,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
   ship: {
     skill: 'ship',
     expectedSections: [
+      'apple-release.md',
       'tests.md',
       'test-coverage.md',
       'plan-completion.md',
@@ -129,7 +130,16 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     minUnionBytes: 120_000,
     mustContain: ['VERSION', 'CHANGELOG', 'review', 'merge', 'PR'],
     // v1.58.5.0: pre-push-guard install (#2077) stacks on the shared first-run-guidance preamble.
-    maxSizeRatio: 1.08,
+    // Fork port wave 2: multi-ecosystem test-detection evidence (Django/JVM
+    // markers, test-file census — e3259078 port) + the #1079 gh pr edit REST
+    // fallback grew the union to 1.090x; the third-party web-actions
+    // contract (consent-gated browser drive for API-key registration etc.)
+    // adds ~2.3KB inline judgment, measured 1.103x. The Apple release
+    // adapter (14.8KB carved section, 21 live releases of judgment — the
+    // wave's headline capability) grows the union to 1.195x. Deliberate:
+    // the section is on-demand (loads only for Apple store targets), so
+    // per-invocation cost for non-iOS ships is one manifest line.
+    maxSizeRatio: 1.22,
   },
   'plan-ceo-review': {
     skill: 'plan-ceo-review',
@@ -144,9 +154,10 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     },
     behavioral: 'external',
     externalTest: 'test/skill-e2e-plan-ceo-review-section-loading.test.ts',
-    // v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
-    // the skeleton at 90,280 B; +1 KB headroom.
-    maxSkeletonBytes: 91_000,
+    // v1.65 merge: provisional larger-of-both-waves budget; re-measured below.
+        // Fork port wave 2 (#703): the repo-doc-preference block in the design
+    // check grew every plan-review skeleton ~0.7KB. Measured values noted.
+    maxSkeletonBytes: 92_500, // v1.64+v1.65 merge: both waves' preamble growth; measured 92,004
     minUnionBytes: 80_000,
     mustContain: ['SCOPE EXPANSION', 'SELECTIVE EXPANSION', 'HOLD SCOPE', 'SCOPE REDUCTION'],
     // Default-on Codex outside-voice (codexPreflight block + CODEX_MODE branch
@@ -167,9 +178,10 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     behavioral: 'plan',
     // v1.2.0 activation lift (shared first-run-guidance preamble) + #2077 ask-first scope gate.
     // +~1 KB: plan-mode auto-select-B scope-gate exceptions (2026-08).
-    // v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
-    // the skeleton at 68,163 B; +~1 KB headroom.
-    maxSkeletonBytes: 69_000,
+    // v1.65 merge: provisional larger-of-both-waves budget; re-measured below.
+        // Fork port wave 2 (#703): the repo-doc-preference block in the design
+    // check grew every plan-review skeleton ~0.7KB. Measured values noted.
+    maxSkeletonBytes: 70_000, // measured 68,780
     minUnionBytes: 70_000,
     mustContain: ['Architecture', 'Code Quality', 'Test', 'Performance'],
     // Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback + the
@@ -180,7 +192,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // 1.08 → 1.10: the scope-gate exceptions block (+ its adversarial-review
     // hardening: host-anchored mode signal, precedence, passing-mention
     // guards) and the plan-mode preamble reword land the union at 1.092.
-    maxSizeRatio: 1.10,
+    maxSizeRatio: 1.12, // measured 1.103
   },
   'plan-design-review': {
     skill: 'plan-design-review',
@@ -198,13 +210,14 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // always-loaded AskUserQuestion Format section.
     // v1.2.0 activation lift (shared first-run-guidance preamble) + #2077 ask-first scope gate.
     // +~1.3 KB: plan-mode auto-select-B scope-gate exceptions (2026-08).
-    // +~340 B: telemetry --error-message/--failed-step flags + prose in the
-    // shared completion-status preamble (PR #769, 2026-08); this skill was the
-    // closest to its ceiling (landed 89040 / ratio 1.072).
-    maxSkeletonBytes: 89_400,
+    // Fork port wave 2 (D1): evidence directive adds ~0.45KB to every
+    // tier-2+ skeleton (measured 89,184). Main's v1.64.0.0 adds ~340 B more
+    // (telemetry --error-message/--failed-step preamble prose, PR #769).
+    // Budget covers the sum of both waves.
+    maxSkeletonBytes: 91_000,
     minUnionBytes: 70_000,
     mustContain: ['design', 'visual'],
-    maxSizeRatio: 1.08,
+    maxSizeRatio: 1.12, // D1 1.104 + main's ~0.008
   },
   'plan-devex-review': {
     skill: 'plan-devex-review',
@@ -221,7 +234,9 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // +Conductor AUQ-default-prose rule + one-way/destructive prose safety +
     // continuation protocol in the always-loaded AskUserQuestion Format section.
     // v1.2.0 activation lift: first-run-guidance section in the shared preamble.
-    maxSkeletonBytes: 80_000,
+        // Fork port wave 2 (#703): the repo-doc-preference block in the design
+    // check grew every plan-review skeleton ~0.7KB. Measured values noted.
+    maxSkeletonBytes: 82_000, // measured 80,493
     minUnionBytes: 70_000,
     mustContain: ['developer experience', 'Getting Started'],
     // Default-on Codex outside-voice (codexPreflight block + CODEX_MODE branch
@@ -244,12 +259,15 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     behavioral: 'prompt',
     // v1.2.0 activation lift: first-run-guidance section in the shared preamble,
     // plus the P1 office-hours closing handoff (AUQ that launches the next skill).
-    // v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
-    // the skeleton at 98,193 B; +~1 KB headroom.
-    maxSkeletonBytes: 99_000,
+    // v1.65 merge: provisional larger-of-both-waves budget; re-measured below.
+    // Fork port wave 2: the third-party web-actions contract sits inline
+    // (judgment must be visible before the workflow directs the user to a
+    // vendor site), plus the #703 dual-write + repo-doc-preference block and
+    // the #538 opt-out + D1 evidence directive — ratio 1.104 measured.
+    maxSkeletonBytes: 101_000,
     minUnionBytes: 70_000,
     mustContain: ['design doc', 'problem statement'],
-    maxSizeRatio: 1.07,
+    maxSizeRatio: 1.12,
   },
   'document-release': {
     skill: 'document-release',
@@ -267,7 +285,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // +Conductor AUQ-default-prose rule + one-way/continuation safety in the
     // always-loaded AskUserQuestion Format section.
     // v1.2.0 activation lift: first-run-guidance section in the shared preamble.
-    maxSkeletonBytes: 56_000,
+    maxSkeletonBytes: 56_500, // v1.64+v1.65 merge; measured 56,044
     minUnionBytes: 55_000,
     mustContain: ['CHANGELOG', 'Diataxis', 'coverage'],
     // Two intentional additions stack on this small skill: the AUQ-failure prose
@@ -295,6 +313,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // +Conductor AUQ-default-prose rule + one-way/continuation safety in the
     // always-loaded AskUserQuestion Format section.
     // v1.2.0 activation lift: first-run-guidance section in the shared preamble.
+    // v1.65 merge: provisional larger-of-both-waves budget; re-measured below.
     // v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
     // the skeleton at 69,022 B; +~1 KB headroom.
     maxSkeletonBytes: 70_000,
@@ -303,7 +322,8 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback ~2KB +
     // the cross-session decision-memory nudge) lands this carved skeleton just over
     // the strict 1.05; headroom for the shared preamble additions.
-    maxSizeRatio: 1.07,
+    // v1.64+v1.65 merge sums both waves' preamble growth; measured 1.073.
+    maxSizeRatio: 1.08,
   },
   cso: {
     skill: 'cso',
@@ -336,13 +356,14 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
     // +Conductor AUQ-default-prose rule + one-way/continuation safety in the
     // always-loaded AskUserQuestion Format section.
     // v1.2.0 activation lift: first-run-guidance section in the shared preamble.
-    maxSkeletonBytes: 75_000,
+    maxSkeletonBytes: 75_800, // v1.64+v1.65 merge; measured 75,364
     minUnionBytes: 72_000,
     mustContain: ['OWASP', 'STRIDE', 'daily', 'comprehensive', 'verif'],
     // cso keeps its mode-dispatch + FP-filtering phases always-loaded, so the
     // cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback ~2KB + the
     // decision-memory nudge) lands it just over 1.05; headroom for the shared additions.
-    maxSizeRatio: 1.07,
+    // v1.64+v1.65 merge sums both waves' preamble growth; measured 1.073.
+    maxSizeRatio: 1.08,
   },
 };
 

test/helpers/claude-pty-runner.ts

@@ -21,6 +21,7 @@
  * tests don't need it).
  */
 
+import { resolveEvalModel } from '../../lib/eval-model';
 import * as fs from 'fs';
 import * as os from 'os';
 import * as path from 'path';
@@ -459,7 +460,7 @@ ${tail}
     // below resolveClaudeBinary(), breaking under hermetic PATHs.
     const result = nodeSpawnSync(
       resolveClaudeBinary() ?? 'claude',
-      ['-p', '--model', 'claude-haiku-4-5', '--max-turns', '1'],
+      ['-p', '--model', resolveEvalModel('warmup'), '--max-turns', '1'],
       {
         input: prompt,
         stdio: ['pipe', 'pipe', 'pipe'],
@@ -1256,7 +1257,15 @@ export const ceoStep0Boundary: Step0BoundaryPredicate = (fp) =>
 export const engStep0Boundary: Step0BoundaryPredicate = (fp) =>
   /scope reduction recommendation|cross[\s-]?project learnings/i.test(
     fp.promptSnippet,
-  );
+  ) ||
+  // plan-eng-review's Step 0 may legitimately end with NO scope-reduction /
+  // learnings AUQ. When it does, the first answered review-phase question —
+  // tagged <gstack-qid:plan-eng-review-...> ({skill}-{slug} convention) —
+  // must fire the boundary, or every per-finding AUQ stays classified
+  // preReview and the multi-finding batching counter reads 0. Anchor allows
+  // the skill-name prefix; live qids observed: plan-eng-review-jitter,
+  // plan-eng-review-idempotency, plan-eng-review-todos-e2e-concurrent.
+  /gstack-qid:\s*(?:plan-)?eng-review-/i.test(fp.promptSnippet);
 
 export const designStep0Boundary: Step0BoundaryPredicate = (fp) =>
   /design system|design posture|design score|first dimension/i.test(

test/helpers/parity-harness.ts

@@ -214,7 +214,9 @@ const MONOLITH_INVARIANTS: ParityInvariant[] = [
     // codexPreflight() block (install + auth tri-state + CODEX_MODE branch prose),
     // landing ~6.3% over the v1.53.0.0 baseline. Intentional: it adds proper
     // not-installed vs not-authed handling, not slop.
-    maxSizeRatio: 1.08,
+    // v1.64+v1.65 merge: both waves grew the shared preamble (evidence
+    // directive + telemetry failure flags); measured 1.094.
+    maxSizeRatio: 1.10,
     minBytes: 70_000,
   },
   {
@@ -223,7 +225,11 @@ const MONOLITH_INVARIANTS: ParityInvariant[] = [
     mustHaveHeadings: ['## Preamble', '## When to invoke'],
     // v1.2.0 activation lift: the unified first-run-guidance section (P4 scaffold +
     // P3 loop tip) is added to every skill's shared preamble — intentional, ~1KB.
-    maxSizeRatio: 1.07,
+    // Fork port wave 2: the shared coverage-audit detection block gained the
+    // multi-ecosystem markers (Django/JVM, script/target/test-file census —
+    // e3259078 port); measured 1.111x. v1.64+v1.65 merge sums both waves'
+    // preamble growth; measured 1.125.
+    maxSizeRatio: 1.13,
     minBytes: 50_000,
   },
   {
@@ -237,7 +243,9 @@ const MONOLITH_INVARIANTS: ParityInvariant[] = [
     // 1.09 → 1.10: the plan-mode preamble reword (scope-gate auto-select-B
     // change) adds ~250 B to every skill's shared preamble; investigate was
     // the closest to its ceiling (landed 1.092).
-    maxSizeRatio: 1.10,
+        // Fork port wave 2 (D1): the evidence-before-claimed-limitations preamble
+    // directive adds ~0.45KB to every tier-2+ skill. Measured values noted.
+    maxSizeRatio: 1.12, // D1 measured
     minBytes: 30_000,
   },
   {
@@ -245,7 +253,9 @@ const MONOLITH_INVARIANTS: ParityInvariant[] = [
     mustContain: ['ceo', 'eng', 'design'],
     mustHaveHeadings: ['## Preamble', '## When to invoke'],
     // v1.2.0 activation lift: shared first-run-guidance preamble section.
-    maxSizeRatio: 1.07,
+        // Fork port wave 2 (D1): the evidence-before-claimed-limitations preamble
+    // directive adds ~0.45KB to every tier-2+ skill. Measured values noted.
+    maxSizeRatio: 1.09, // D1 measured
     minBytes: 70_000,
   },
 ];

test/helpers/providers/claude.ts

@@ -1,6 +1,6 @@
 import type { ProviderAdapter, RunOpts, RunResult, AvailabilityCheck } from './types';
 import { estimateCostUsd } from '../pricing';
-import { execFileSync } from 'child_process';
+import { execFileSync, spawnSync } from 'child_process';
 import * as fs from 'fs';
 import * as path from 'path';
 import * as os from 'os';
@@ -25,11 +25,30 @@ export class ClaudeAdapter implements ProviderAdapter {
     if (!resolved) {
       return { ok: false, reason: 'claude CLI not found on PATH. Install from https://claude.ai/download or npm i -g @anthropic-ai/claude-code (or set GSTACK_CLAUDE_BIN)' };
     }
-    // Auth sniff: ~/.claude/.credentials.json OR ANTHROPIC_API_KEY
+    // Auth sniff: ~/.claude/.credentials.json OR ANTHROPIC_API_KEY OR (macOS)
+    // the Keychain entry subscription installs use instead of the creds file.
+    // #1890: the default macOS install stores OAuth under the generic-password
+    // service "Claude Code-credentials" and never writes .credentials.json,
+    // so the file-or-env sniff reported "No Claude auth found" while
+    // `claude -p` worked fine. Metadata probe only (no -w — never reads the
+    // secret), and any failure of `security` itself falls through to the
+    // not-found reason rather than throwing.
     const credsPath = path.join(os.homedir(), '.claude', '.credentials.json');
     const hasCreds = fs.existsSync(credsPath);
     const hasKey = !!process.env.ANTHROPIC_API_KEY;
-    if (!hasCreds && !hasKey) {
+    let hasKeychain = false;
+    if (!hasCreds && !hasKey && process.platform === 'darwin') {
+      try {
+        const probe = spawnSync('security', ['find-generic-password', '-s', 'Claude Code-credentials'], {
+          stdio: 'ignore',
+          timeout: 5000,
+        });
+        hasKeychain = probe.status === 0;
+      } catch {
+        hasKeychain = false;
+      }
+    }
+    if (!hasCreds && !hasKey && !hasKeychain) {
       return { ok: false, reason: 'No Claude auth found. Log in via `claude` interactive session, or export ANTHROPIC_API_KEY.' };
     }
     return { ok: true };