---
type: "post"
id: "a-configuration-mismatch-in-glm-5-3-on-8c8082"
slug: "a-configuration-mismatch-in-glm-5-3-on-8c8082"
title: "A configuration mismatch in GLM 5.3 on Workers AI triggered an SGLang bug that exposed KV cache pages across requests."
description: "Cloudflare published a remediation report for a cross-request KV-cache exposure involving GLM-5.3 on Workers AI."
retrieval_nugget: "Cloudflare published a remediation report for a cross-request KV-cache exposure involving GLM-5.3 on Workers AI."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["agent-security","sandbox"]
entities: ["Cloudflare","Workers AI","GLM-5.3","SGLang"]
related_patterns: ["agent-security-moves-to-runtime-boundaries"]
novelty_label: "new_fact"
what_changed: "Cloudflare reports a distinct Workers AI incident: a GLM-5.3 configuration mismatch triggered an SGLang bug exposing KV cache pages across requests, followed by remediation."
prior_refs: ["memory:394ec971-1a24-82e1-ae2f-978f5f8b920a","memory:f7a7e07e-8774-8e64-ab44-e76dddf4c92d"]
source_url: "https://blog.cloudflare.com/kv-cache-exposure-remediation"
source_urls: ["https://blog.cloudflare.com/kv-cache-exposure-remediation"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:a-configuration-mismatch-in-glm-5-3-on-8c8082"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/a-configuration-mismatch-in-glm-5-3-on-8c8082/","markdown":"https://newruntime.com/posts/a-configuration-mismatch-in-glm-5-3-on-8c8082.md","json":"https://newruntime.com/posts/a-configuration-mismatch-in-glm-5-3-on-8c8082.json"}
---

# A configuration mismatch in GLM 5.3 on Workers AI triggered an SGLang bug that exposed KV cache pages across requests.

## Retrieval answer

Cloudflare published a remediation report for a cross-request KV-cache exposure involving GLM-5.3 on Workers AI.

Cloudflare published a remediation report for a cross-request KV-cache exposure involving GLM-5.3 on Workers AI. The company says a configuration mismatch triggered a bug in SGLang, the inference engine used for the deployment.

According to Cloudflare, the bug could expose KV-cache pages across requests. KV cache stores intermediate model state used during inference; cross-request exposure therefore concerns separation of request context within the managed service. Cloudflare describes the post as a remediation undertaken with SGLang.

The report identifies the affected model deployment as GLM-5.3 on Workers AI and attributes the issue to the combination of a configuration mismatch and an SGLang bug. It does not, from the supplied source material, establish which customers or requests were affected, whether any exposed cache content was accessed, what data it contained, or the duration and scale of the exposure.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Security](https://newruntime.com/topics/agent-security.md): Explore the agent-security topic hub.
- topic hub: [Sandbox](https://newruntime.com/topics/sandbox.md): Explore the sandbox topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)