diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 956eacf31..9dea6b38d 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "d3683a61c5f8b7a42e66c291d6646dd67eafc1a5",
-  "syncedAt": "2026-04-28T23:51:00.305Z"
+  "sha": "8f4cbbbe6658608f95525dff84041669ced2f581",
+  "syncedAt": "2026-04-28T23:51:04.440Z"
 }
diff --git a/docs/concepts/system-prompt.md b/docs/concepts/system-prompt.md
index 35abeb9db..32a3504c0 100644
--- a/docs/concepts/system-prompt.md
+++ b/docs/concepts/system-prompt.md
@@ -53,6 +53,14 @@ The prompt is intentionally compact and uses fixed sections:
 - **Runtime**: host, OS, node, model, repo root (when detected), thinking level (one line).
 - **Reasoning**: current visibility level + /reasoning toggle hint.
 
+OpenClaw keeps large stable content, including **Project Context**, above the
+internal prompt cache boundary. Volatile channel/session sections such as
+Control UI embed guidance, **Messaging**, **Voice**, **Group Chat Context**,
+**Reactions**, **Heartbeats**, and **Runtime** are appended below that boundary
+so local backends with prefix caches can reuse the stable workspace prefix
+across channel turns. Tool descriptions should likewise avoid embedding current
+channel names when the accepted schema already carries that runtime detail.
+
 The Tooling section also includes runtime guidance for long-running work:
 
 - use cron for future follow-up (`check back later`, reminders, recurring work)