test(e2e): periodic-tier repairs from the failure triage

Each fix traces to a receipt: brain-privacy-gate staged config never
reached the hermetic child (ambient GSTACK_HOME is scrubbed) and the
operator's remote-mode gbrain suppressed the gate — both now injected
per-test; ship-idempotency threw away its evidence on the timeout path
and ran a 600s budget its own subject can exceed (now 900s, evidence
captured); auto-decide-preserved gets the same headroom its sibling
plan-ceo tests got; context-skills' hides-checks scanned bash output
where an ls legitimately names old checkpoints (final-text scope now);
design names the missing section instead of a bare count and learns the
easing/duration/micro-interaction synonyms; qa-workflow's collector
afterAll gets an explicit 60s hook timeout.

test/skill-e2e-auto-decide-preserved.test.ts

@@ -111,7 +111,7 @@ describeE2E('AUTO_DECIDE opt-in preserved under Conductor flags (periodic)', ()
         skillName: 'plan-ceo-review',
         inPlanMode: true,
         extraArgs: ['--disallowedTools', 'AskUserQuestion'],
-        timeoutMs: 300_000,
+        timeoutMs: 540_000,
         env: { GSTACK_HOME: tmpHome, CONDUCTOR_WORKSPACE_PATH: tmpHome },
       });
 
@@ -135,5 +135,5 @@ describeE2E('AUTO_DECIDE opt-in preserved under Conductor flags (periodic)', ()
     } finally {
       try { fs.rmSync(tmpHome, { recursive: true, force: true }); } catch { /* best-effort */ }
     }
-  }, 360_000);
+  }, 660_000);
 });

test/skill-e2e-brain-privacy-gate.test.ts

@@ -34,6 +34,12 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
     // Stage a fresh GSTACK_HOME with artifacts_sync_mode_prompted=false.
     const gstackHome = fs.mkdtempSync(path.join(os.tmpdir(), 'privacy-gate-gstack-'));
     const fakeBinDir = fs.mkdtempSync(path.join(os.tmpdir(), 'privacy-gate-bin-'));
+    // Fresh HOME with NO ~/.claude.json: on a machine where gbrain is
+    // registered type=http, the preamble's remote-mode detection reads the
+    // operator's ~/.claude.json and echoes "ARTIFACTS_SYNC: remote-mode" —
+    // and the local privacy gate legitimately never fires. An empty HOME
+    // makes the detection find nothing.
+    const tempHome = fs.mkdtempSync(path.join(os.tmpdir(), 'privacy-gate-home-'));
 
     // Seed the config so the gate's condition passes.
     fs.writeFileSync(
@@ -59,12 +65,16 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
     const askUserQuestions: Array<{ input: Record<string, unknown> }> = [];
     const binary = resolveClaudeBinary();
 
-    // Ambient env mutations — restored in finally so other tests in the file
+    // Per-test env, merged LAST by the hermetic env builder (safe post-v1.39:
-    // don't inherit them.
+    // the runner always passes a COMPLETE hermetic env, so overrides can't
-    const origGstackHome = process.env.GSTACK_HOME;
+    // break auth). Ambient process.env.GSTACK_HOME mutation does NOT work
-    const origPath = process.env.PATH;
+    // here — hermetic-env scrubs GSTACK_* and repoints GSTACK_HOME at its
-    process.env.GSTACK_HOME = gstackHome;
+    // own singleton dir, so the staged config would never reach the child.
-    process.env.PATH = `${fakeBinDir}:${process.env.PATH ?? '/usr/bin:/bin:/opt/homebrew/bin'}`;
+    const childEnv = {
+      GSTACK_HOME: gstackHome,
+      HOME: tempHome,
+      PATH: `${fakeBinDir}:${process.env.PATH ?? '/usr/bin:/bin:/opt/homebrew/bin'}`,
+    };
 
     try {
       // Pick a small skill with the preamble and load it via Read to force
@@ -85,12 +95,7 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
         workingDirectory: gstackHome,
         maxTurns: 10,
         allowedTools: ['Read', 'Grep', 'Glob', 'Bash'],
-        // NOTE: do NOT pass `env:` here. When the Agent SDK gets an explicit
+        env: childEnv,
-        // env object, its auth pipeline doesn't pick up ANTHROPIC_API_KEY the
-        // same way as when env is undefined (SDK-internal detail, verified
-        // against the plan-mode-no-op test which passes no env and auths
-        // cleanly). Instead, mutate process.env before the call so the SDK
-        // inherits our overrides ambiently.
         ...(binary ? { pathToClaudeCodeExecutable: binary } : {}),
         canUseTool: async (toolName, input) => {
           if (toolName === 'AskUserQuestion') {
@@ -141,13 +146,9 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
       // (The preamble is supposed to be idempotent within a session.)
       expect(privacyQuestions.length).toBe(1);
     } finally {
-      // Restore ambient env before other tests.
-      if (origGstackHome === undefined) delete process.env.GSTACK_HOME;
-      else process.env.GSTACK_HOME = origGstackHome;
-      if (origPath === undefined) delete process.env.PATH;
-      else process.env.PATH = origPath;
       fs.rmSync(gstackHome, { recursive: true, force: true });
       fs.rmSync(fakeBinDir, { recursive: true, force: true });
+      fs.rmSync(tempHome, { recursive: true, force: true });
     }
   }, 180_000);
 
@@ -155,6 +156,10 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
     // Same staging, but prompted=true this time. Gate should be silent.
     const gstackHome = fs.mkdtempSync(path.join(os.tmpdir(), 'privacy-gate-off-'));
     const fakeBinDir = fs.mkdtempSync(path.join(os.tmpdir(), 'privacy-gate-off-bin-'));
+    // Fresh HOME without a .claude.json — same rationale as the first test:
+    // without it the operator's ~/.claude.json flips the preamble into
+    // remote-mode and this negative test passes vacuously.
+    const tempHome = fs.mkdtempSync(path.join(os.tmpdir(), 'privacy-gate-off-home-'));
 
     fs.writeFileSync(
       path.join(gstackHome, 'config.yaml'),
@@ -171,11 +176,13 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
     const askUserQuestions: Array<{ input: Record<string, unknown> }> = [];
     const binary = resolveClaudeBinary();
 
-    // Ambient env mutations (see note on the first test).
+    // Per-test env, merged LAST by the hermetic env builder (see note on the
-    const origGstackHome = process.env.GSTACK_HOME;
+    // first test — ambient GSTACK_HOME mutation is scrubbed by hermetic-env).
-    const origPath = process.env.PATH;
+    const childEnv = {
-    process.env.GSTACK_HOME = gstackHome;
+      GSTACK_HOME: gstackHome,
-    process.env.PATH = `${fakeBinDir}:${process.env.PATH ?? '/usr/bin:/bin:/opt/homebrew/bin'}`;
+      HOME: tempHome,
+      PATH: `${fakeBinDir}:${process.env.PATH ?? '/usr/bin:/bin:/opt/homebrew/bin'}`,
+    };
 
     try {
       await runAgentSdkTest({
@@ -185,6 +192,7 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
         workingDirectory: gstackHome,
         maxTurns: 4,
         allowedTools: ['Read', 'Grep', 'Glob', 'Bash'],
+        env: childEnv,
         ...(binary ? { pathToClaudeCodeExecutable: binary } : {}),
         canUseTool: async (toolName, input) => {
           if (toolName === 'AskUserQuestion') {
@@ -216,12 +224,9 @@ describeE2E('gbrain-sync privacy gate fires once via preamble', () => {
       });
       expect(privacyQuestions.length).toBe(0);
     } finally {
-      if (origGstackHome === undefined) delete process.env.GSTACK_HOME;
-      else process.env.GSTACK_HOME = origGstackHome;
-      if (origPath === undefined) delete process.env.PATH;
-      else process.env.PATH = origPath;
       fs.rmSync(gstackHome, { recursive: true, force: true });
       fs.rmSync(fakeBinDir, { recursive: true, force: true });
+      fs.rmSync(tempHome, { recursive: true, force: true });
     }
   }, 180_000);
 });

test/skill-e2e-context-skills.test.ts

@@ -447,8 +447,13 @@ Do NOT use AskUserQuestion.`,
     // Match by filename timestamp (stable, unambiguous) plus a looser
     // prose check.
     const showsMain = /20260101-120000|main-work/.test(out);
-    const hidesAlpha = !/20260202-120000/.test(out);
+    // Hide checks scope to the FINAL text output only: fullOutputSurface
-    const hidesBeta = !/20260303-120000/.test(out);
+    // includes bash tool_results, and a legitimate `ls` of the checkpoint
+    // dir lists every branch's filename. The filtering under test happens
+    // in the user-facing list, not in the agent's intermediate reads.
+    const finalText = result.output ?? '';
+    const hidesAlpha = !/20260202-120000|LISTCURR_ALPHA_TOKEN/.test(finalText);
+    const hidesBeta = !/20260303-120000|LISTCURR_BETA_TOKEN/.test(finalText);
     const routed = skillCalls(result).includes('context-save');
     const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
 

test/skill-e2e-design.test.ts

@@ -126,7 +126,7 @@ Write DESIGN.md and CLAUDE.md (or update it) in the working directory.`,
       'Color': ['color', 'colour', 'palette', 'colors'],
       'Spacing': ['spacing', 'space', 'whitespace', 'gap'],
       'Layout': ['layout', 'grid', 'structure', 'composition'],
-      'Motion': ['motion', 'animation', 'transition', 'movement'],
+      'Motion': ['motion', 'animation', 'transition', 'movement', 'easing', 'duration', 'micro-interaction'],
     };
     const missingSections = Object.entries(sectionSynonyms).filter(
       ([_, synonyms]) => !synonyms.some(s => designContent.toLowerCase().includes(s))
@@ -152,7 +152,9 @@ Write DESIGN.md and CLAUDE.md (or update it) in the working directory.`,
     expect(['success', 'error_max_turns']).toContain(result.exitReason);
     expect(designExists).toBe(true);
     if (designExists) {
-      expect(missingSections).toHaveLength(0);
+      // join() so a failure names the offending section(s) — a bare
+      // toHaveLength(0) failure never prints WHICH synonym set missed.
+      expect(missingSections.join(', ')).toBe('');
     }
     if (claudeExists) {
       const claude = fs.readFileSync(claudePath, 'utf-8');

test/skill-e2e-qa-workflow.test.ts

@@ -406,7 +406,9 @@ Do NOT fix any bugs. Do NOT use AskUserQuestion — just pick vitest.`,
   }, 120_000);
 });
 
-// Module-level afterAll — finalize eval collector after all tests complete
+// Module-level afterAll — finalize eval collector after all tests complete.
+// Explicit 60s timeout: finalize does a JSON save + cross-run comparison and
+// has been observed at 6.26s, past bun's 5s default hook timeout.
 afterAll(async () => {
   await finalizeEvalCollector(evalCollector);
-});
+}, 60_000);

test/skill-e2e-ship-idempotency.test.ts

@@ -158,7 +158,7 @@ describeE2E('/ship idempotency E2E (periodic, real-PTY)', () => {
       const session = await launchClaudePty({
         permissionMode: 'plan',
         cwd: fixture.workTree,
-        timeoutMs: 720_000,
+        timeoutMs: 1_080_000,
         // Disable network-y pieces so the agent can't reach actual github.
         env: { GH_TOKEN: 'mock-not-real', NO_COLOR: '1' },
         seedSkills: true,
@@ -172,7 +172,7 @@ describeE2E('/ship idempotency E2E (periodic, real-PTY)', () => {
         const since = session.mark();
         session.send('/ship\r');
 
-        const budgetMs = 600_000;
+        const budgetMs = 900_000;
         const start = Date.now();
         let lastPermSig = '';
         while (Date.now() - start < budgetMs) {
@@ -234,6 +234,12 @@ describeE2E('/ship idempotency E2E (periodic, real-PTY)', () => {
             break;
           }
         }
+        // Budget exhausted without a terminal signal: capture the tail NOW,
+        // while the session is still alive. Only the break paths above set
+        // evidence — without this, the timeout throw ships evidence: "".
+        if (outcome === 'timeout') {
+          evidence = session.visibleSince(since).slice(-3000);
+        }
       } finally {
         await session.close();
       }
@@ -273,6 +279,6 @@ describeE2E('/ship idempotency E2E (periodic, real-PTY)', () => {
         try { fs.rmSync(path.dirname(fixture.workTree), { recursive: true, force: true }); } catch { /* ignore */ }
       }
     },
-    900_000, // 15 min wall clock
+    1_200_000, // 20 min wall clock
   );
 });