fix(test): unique tmp dirs for plan artifacts + audited live-repo cwd sites

Six paid PTY tests wrote their expected plan artifact to a FIXED shared
/tmp path ('/tmp/gstack-test-plan-<mode>.md') and rmSync'd it in
finally — under --retry 1, EVALS_JOBS>1, or two concurrent worktrees, a
sibling's cleanup deletes this run's artifact and the D19 'agent did
not produce expected plan file' assertion fires spuriously. Each test
now mkdtemps its own dir, interpolates the unique path into the agent
prompt (fixture-sourced prompts get a replaceAll + drift guard that
throws if the fixture's literal ever moves), and cleans up its own dir.

The 18 cwd:-into-the-live-repo sites were audited: all deliberate
(skill registry + hermetic pre-trusted dir, in-repo gen renders, git
history reads, slug resolution) — each now carries a
'// LIVE-REPO CWD: <reason>' comment so the next audit can tell
deliberate from accidental.

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

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

@@ -11,6 +11,8 @@
 import { test } from 'bun:test';
 import { describeE2ETier } from './helpers/e2e-gate';
 import * as fs from 'node:fs';
+import * as os from 'node:os';
+import * as path from 'node:path';
 import {
   runPlanSkillCounting,
   devexStep0Boundary,
@@ -23,8 +25,8 @@ const N = 5;
 const FLOOR = N - 1;
 const CEILING = N + 2;
 
-const PLAN_DEVEX_5_FINDINGS = [
-  'Please review this plan thoroughly. As you go, write your plan-mode plan to /tmp/gstack-test-plan-devex.md (use Edit/Write to that exact path).',
+const planDevex5Findings = (planPath: string) => [
+  `Please review this plan thoroughly. As you go, write your plan-mode plan to ${planPath} (use Edit/Write to that exact path).`,
   '',
   '# Plan: Public SDK Beta Launch',
   '',
@@ -50,30 +52,30 @@ const PLAN_DEVEX_5_FINDINGS = [
   'of solved problems.',
 ].join('\n');
 
-const PLAN_DEVEX_PATH = '/tmp/gstack-test-plan-devex.md';
-
 describeE2E('/plan-devex-review per-finding AskUserQuestion count (periodic)', () => {
   test(
     `5-finding plan emits ${FLOOR}-${CEILING} review-phase AskUserQuestions`,
     async () => {
-      try {
-        fs.rmSync(PLAN_DEVEX_PATH, { force: true });
-      } catch {
-        /* best-effort */
-      }
-
-      const obs = await runPlanSkillCounting({
-        skillName: 'plan-devex-review',
-        slashCommand: '/plan-devex-review',
-        followUpPrompt: PLAN_DEVEX_5_FINDINGS,
-        isLastStep0AUQ: devexStep0Boundary,
-        reviewCountCeiling: CEILING + 1,
-        cwd: process.cwd(),
-        timeoutMs: 1_500_000,
-        env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
-      });
+      // Per-run artifact dir: a hardcoded shared /tmp path collides under
+      // --retry, EVALS_JOBS>1, or concurrent worktrees (a sibling's finally-
+      // rmSync deletes this run's artifact → spurious D19 failure).
+      const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-e2e-plan-devex-'));
+      const planPath = path.join(tmpDir, 'gstack-test-plan-devex.md');
 
       try {
+        const obs = await runPlanSkillCounting({
+          skillName: 'plan-devex-review',
+          slashCommand: '/plan-devex-review',
+          followUpPrompt: planDevex5Findings(planPath),
+          isLastStep0AUQ: devexStep0Boundary,
+          reviewCountCeiling: CEILING + 1,
+          // LIVE-REPO CWD: PTY session needs the repo cwd — gstack skill
+          // registry + hermetic pre-trusted dir (hermetic-env trustedDirs).
+          cwd: process.cwd(),
+          timeoutMs: 1_500_000,
+          env: { QUESTION_TUNING: 'false', EXPLAIN_LEVEL: 'default' },
+        });
+
         if (!['plan_ready', 'completion_summary', 'ceiling_reached'].includes(obs.outcome)) {
           throw new Error(
             `plan-devex-review finding-count FAILED: outcome=${obs.outcome}\n` +
@@ -105,17 +107,17 @@ describeE2E('/plan-devex-review per-finding AskUserQuestion count (periodic)', (
           );
         }
 
-        if (!fs.existsSync(PLAN_DEVEX_PATH)) {
+        if (!fs.existsSync(planPath)) {
           throw new Error(
-            `D19 FAIL: agent did not produce expected plan file at ${PLAN_DEVEX_PATH}. ` +
+            `D19 FAIL: agent did not produce expected plan file at ${planPath}. ` +
               `outcome=${obs.outcome} review=${obs.reviewCount}`,
           );
         }
-        const planContent = fs.readFileSync(PLAN_DEVEX_PATH, 'utf-8');
+        const planContent = fs.readFileSync(planPath, 'utf-8');
         const verdict = assertReviewReportAtBottom(planContent);
         if (!verdict.ok) {
           throw new Error(
-            `D19 FAIL: plan file at ${PLAN_DEVEX_PATH} ${verdict.reason}\n` +
+            `D19 FAIL: plan file at ${planPath} ${verdict.reason}\n` +
               (verdict.trailingHeadings
                 ? `Trailing headings: ${verdict.trailingHeadings.join(' | ')}\n`
                 : '') +
@@ -124,7 +126,7 @@ describeE2E('/plan-devex-review per-finding AskUserQuestion count (periodic)', (
         }
       } finally {
         try {
-          fs.rmSync(PLAN_DEVEX_PATH, { force: true });
+          fs.rmSync(tmpDir, { recursive: true, force: true });
         } catch {
           /* best-effort */
         }