v1.90.2.0 perf: halve local free-suite time and preserve coverage (#2972)

* perf: remove repeated test work and preserve AUQ execution budgets

* fix: validate native evaluation fixture evidence at its actual boundaries

* fix: clarify deployment approval and recovery state transitions

* chore: document coverage and release v1.90.2.0

* test: preserve Windows scheduling and native no-change consent

* test: recognize verified reads through fixture symlinks

* test: isolate alias-name installation from runtime assets

scripts/test-free-shards.ts

@@ -91,10 +91,13 @@ import {
   installChildSignalForwarding,
   isTerminationRequested,
   killProcessGroup,
+  normalizeRelativePath,
   strictTestExitCode,
   stripAnsiLine,
 } from './test-strict-output';
 
+export { normalizeRelativePath } from './test-strict-output';
+
 const ROOT = path.resolve(import.meta.dir, '..');
 // design/test was silently absent from BOTH the package.json test script and
 // this list — design tests (including a teardown bomb) never ran in any CI
@@ -420,10 +423,14 @@ export function wallTimeoutForPackedShard(predictedMs: number, baseMs = DEFAULT_
   return Math.max(baseMs, Math.ceil(predictedMs * 3), fileCount * PER_FILE_WALL_MS);
 }
 /**
- * Full-suite parallelism: leave RESERVED_CPUS cores for the parent runner +
- * OS, cap at MAX_FULL_SUITE_JOBS — beyond ~6 concurrent bun processes the
- * playwright-heavy shards contend on browser launches instead of finishing
- * sooner (measured on an M-series dev box).
+ * Full-suite parallelism: use all available CPUs, with a floor of one and a
+ * cap of MAX_FULL_SUITE_JOBS. Shards stay serial internally; separate shard
+ * processes can overlap subprocess and I/O waits without a fixed CPU reserve.
+ * Prefer availableParallelism() to honor CPU affinity, falling back to cpus()
+ * on runtimes without it. Keep the existing cap: beyond ~6 concurrent bun
+ * processes, playwright-heavy shards contended on browser launches in the
+ * original M-series measurement. More shards are not a guaranteed speedup;
+ * compare complete-suite runs before raising the default further.
  *
  * GSTACK_FREE_JOBS overrides the computed count (the free runner's analogue
  * of the paid runner's EVALS_JOBS). Exists for syscall-supervised sandboxes:
@@ -437,7 +444,6 @@ export function wallTimeoutForPackedShard(predictedMs: number, baseMs = DEFAULT_
  * beefy box can also raise it deliberately.
  */
 export const MAX_FULL_SUITE_JOBS = 6;
-export const RESERVED_CPUS = 2;
 
 export function fullSuiteJobs(): number {
   const raw = process.env.GSTACK_FREE_JOBS;
@@ -449,7 +455,8 @@ export function fullSuiteJobs(): number {
     }
     return Number.parseInt(raw, 10);
   }
-  return Math.max(1, Math.min(MAX_FULL_SUITE_JOBS, os.cpus().length - RESERVED_CPUS));
+  const availableCpus = os.availableParallelism?.() ?? os.cpus().length;
+  return Math.max(1, Math.min(MAX_FULL_SUITE_JOBS, availableCpus));
 }
 
 /**
@@ -486,10 +493,6 @@ export const WORKER_HOSTILE: Record<string, string> = {
  */
 export const TREE_MUTATING: Record<string, string> = {};
 
-export function normalizeRelativePath(filePath: string): string {
-  return filePath.replace(/\\/g, '/');
-}
-
 export function isFreeTestFile(relativePath: string): boolean {
   const normalized = normalizeRelativePath(relativePath);
   if (!TEST_FILE_REGEX.test(normalized)) return false;

scripts/test-paid-shards.ts

@@ -54,12 +54,12 @@ import * as fs from 'node:fs';
 import * as os from 'node:os';
 import * as path from 'node:path';
 import { spawnSync } from 'node:child_process';
-import { normalizeRelativePath } from './test-free-shards';
 import {
   BunTestOutputClassifier,
   exactTestFileSelectors,
   forwardAndClassify,
   isTerminationRequested,
+  normalizeRelativePath,
   runShardChild,
   strictTestExitCode,
 } from './test-strict-output';

scripts/test-pr-profile.ts

@@ -92,6 +92,11 @@ function matches(file: string, patterns: readonly string[]): boolean {
   return patterns.some(pattern => matchGlob(file, pattern));
 }
 
+export const FREE_ONLY_PR_FILES = [
+  'scripts/test-free-shards.ts',
+  'test/helpers/auq-parallel-worker.ts',
+] as const;
+
 function knownNonBehaviorFile(file: string): boolean {
   // A mapped dependency still wins over these exemptions. New helper/fixture,
   // runtime, dependency, or workflow files are deliberately not exempted.
@@ -99,6 +104,7 @@ function knownNonBehaviorFile(file: string): boolean {
     // Hermetic skill views exclude checkout instructions; these are maintained
     // by free doc/generation checks and are not copied into paid fixtures.
     || ['AGENTS.md', 'CLAUDE.md', 'agents-digest/gstack-AGENTS.md'].includes(file)
+    || FREE_ONLY_PR_FILES.some(freeOnly => freeOnly === file)
     || (file.startsWith('test/') && /\.test\.tsx?$/.test(file) && !isPaidTestFile(file));
 }
 

scripts/test-strict-output.ts

@@ -310,6 +310,10 @@ export function strictTestExitCode(
   return 0;
 }
 
+export function normalizeRelativePath(filePath: string): string {
+  return filePath.replace(/\\/g, '/');
+}
+
 /**
  * Bun treats positional test paths as substring filters. Resolve every
  * canonical relative path before spawning so `test/foo.test.ts` cannot also