From a70923ba216eb09c91634e6f0db1059ae089baa1 Mon Sep 17 00:00:00 2001
From: Tianyi Cui <53024+tianyicui@users.noreply.github.com>
Date: Mon, 27 Jul 2026 12:51:47 +0800
Subject: [PATCH] fix(session-checkpoint-policy): fail fast on an impossible
 crash marker

vi.waitFor retries every callback throw, so the mismatch branch inside
the callback waited the full 30s deadline for a fixture that writes the
marker once and cannot recover. Terminal states (complete marker, or
content that can no longer become the expected marker) now resolve out
of the retry loop and the mismatch throws after it, restoring the old
loop's immediate failure.
---
 .../tests/crash-recovery.e2e.ts                  | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts b/packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts
index d87ba13b3a..25c7d5797d 100644
--- a/packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts
+++ b/packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts
@@ -19,17 +19,21 @@ const roots: string[] = []
 const CHILD_FAILPOINT_TIMEOUT_MS = 30_000
 
 async function waitForMarker(path: string, expected: string): Promise<string> {
-  return await vi.waitFor(async () => {
-    const content = await readFile(path, 'utf8').catch((error: unknown) => {
+  // vi.waitFor retries every callback throw, so terminal states RESOLVE out
+  // of the retry loop (complete marker, or content that can no longer become
+  // the expected marker) and only the still-in-progress states throw-to-retry.
+  const content = await vi.waitFor(async () => {
+    const current = await readFile(path, 'utf8').catch((error: unknown) => {
       if ((error as NodeJS.ErrnoException).code !== 'ENOENT') throw error
       throw new Error(`crash child did not publish failpoint ${JSON.stringify(expected)} at ${path}`, { cause: error })
     })
-    if (content === expected) return content
-    if (!expected.startsWith(content)) {
-      throw new Error(`crash child wrote unexpected failpoint ${JSON.stringify(content)}`)
-    }
+    if (current === expected || !expected.startsWith(current)) return current
     throw new Error(`crash child has not finished publishing failpoint ${JSON.stringify(expected)}`)
   }, { interval: 10, timeout: CHILD_FAILPOINT_TIMEOUT_MS })
+  if (content !== expected) {
+    throw new Error(`crash child wrote unexpected failpoint ${JSON.stringify(content)}`)
+  }
+  return content
 }
 
 async function crashAt(mode: 'request' | 'tool'): Promise<{ root: string; markerText: string }> {