fix(memory): retry reindex on socket errors (#76311)

buyitsydney · clawsweeper[bot] · web-flow · commit 5f5e0a3633c2 · 2026-05-03T03:21:06.000Z
Summary: - The PR broadens memory-core's embedding retry classifier for socket/network errors, adds focused classifier tests, and adds an Unreleased changelog fix. - Reproducibility: yes. Current main's retry classifier rejects the socket/fetch samples, and the reindex embedding path delegates to that classifier; a read-only regex probe confirmed the PR accepts the target samples. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(memory): retry reindex on socket errors Validation: - ClawSweeper review passed for head b4618c4. - Required merge gates passed before the squash merge. Prepared head SHA: b4618c4 Review: #76311 (comment) Co-authored-by: buyitsydney <buyitsydney@users.noreply.github.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -25,6 +25,7 @@ Docs: https://docs.openclaw.ai
 - Auto-reply/queue: treat reset-triggered `/new` and `/reset` turns as interrupt runs across active-run queue handling, so steer/followup modes cannot delay a fresh session behind existing work. Fixes #74093. (#74144) Thanks @ruji9527 and @yelog.
 - Cron: preserve manual `cron.run` IDs in `cron.runs` history so manual run acknowledgements can be correlated with finished run records. Fixes #76276.
 - CLI/devices: request `operator.admin` for `openclaw devices approve <requestId>` only when the exact pending device request would mint or inherit admin-scoped operator access, while keeping lower-scope approvals on the pairing scope.
+- Memory/embedding: broaden the embedding reindex retry classifier to include transient socket-layer errors (`fetch failed`, `ECONNRESET`, `socket hang up`, `UND_ERR_*`, `closed`) so memory reindex survives provider network hiccups instead of aborting mid-run. Related #56815, #44166. (#76311) Thanks @buyitsydney.
 - Gateway: keep directly requested plugin tools invokable under restrictive tool profiles while preserving explicit deny lists and the HTTP safety deny list, preventing catalog/invoke mismatches that surface as "Tool not available". Thanks @BunsDev.
 - Gateway/update: allow beta binaries to refresh gateway services when the config was last written by the matching stable release version, avoiding false newer-config downgrade blocks during beta channel updates.
 - Channels: keep Matrix and Mattermost bundled in the core package instead of advertising external npm installs before those channels are cut over. Thanks @vincentkoc.
diff --git a/extensions/memory-core/src/memory/manager-embedding-policy.test.ts b/extensions/memory-core/src/memory/manager-embedding-policy.test.ts
@@ -71,6 +71,20 @@ describe("memory embedding policy", () => {
     expect(waits).toEqual([500, 1000]);
   });
 
+  it("retries transient socket/network embedding errors", async () => {
+    const messages = [
+      "TypeError: fetch failed | other side closed",
+      "undici error: UND_ERR_SOCKET",
+      "read ECONNRESET",
+      "socket hang up",
+      "ETIMEDOUT",
+    ];
+
+    for (const message of messages) {
+      expect(isRetryableMemoryEmbeddingError(message)).toBe(true);
+    }
+  });
+
   it("retries too-many-tokens-per-day errors", async () => {
     let calls = 0;
     const waits: number[] = [];
diff --git a/extensions/memory-core/src/memory/manager-embedding-policy.ts b/extensions/memory-core/src/memory/manager-embedding-policy.ts
@@ -81,7 +81,7 @@ export function buildMemoryEmbeddingBatches<T extends MemoryEmbeddingChunk>(
 }
 
 export function isRetryableMemoryEmbeddingError(message: string): boolean {
-  return /(rate[_ ]limit|too many requests|429|resource has been exhausted|5\d\d|cloudflare|tokens per day)/i.test(
+  return /(rate[_ ]limit|too many requests|429|resource has been exhausted|5\d\d|cloudflare|tokens per day|fetch failed|other side closed|ECONNRESET|ECONNREFUSED|ETIMEDOUT|EPIPE|UND_ERR_|socket hang up|network error|read ECONN|timed out)/i.test(
     message,
   );
 }

Original file line number	Diff line number	Diff line change
`@@ -81,7 +81,7 @@ export function buildMemoryEmbeddingBatches<T extends MemoryEmbeddingChunk>(`
`81`	`81`	`}`
`82`	`82`
`83`	`83`	`export function isRetryableMemoryEmbeddingError(message: string): boolean {`
`84`		`- return /(rate[_ ]limit\|too many requests\|429\|resource has been exhausted\|5\d\d\|cloudflare\|tokens per day)/i.test(`
	`84`	`+ return /(rate[_ ]limit\|too many requests\|429\|resource has been exhausted\|5\d\d\|cloudflare\|tokens per day\|fetch failed\|other side closed\|ECONNRESET\|ECONNREFUSED\|ETIMEDOUT\|EPIPE\|UND_ERR_\|socket hang up\|network error\|read ECONN\|timed out)/i.test(`
`85`	`85`	`message,`
`86`	`86`	`);`
`87`	`87`	`}`