diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index fb0e0ebb4..280352069 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "73a6a2a6ab4d815457aba2d74b50d2eda2194bc3",
-  "syncedAt": "2026-04-25T03:20:58.633Z"
+  "sha": "678ed5d512cc8b090701a414a056401fcd6df356",
+  "syncedAt": "2026-04-25T03:27:11.849Z"
 }
diff --git a/docs/providers/deepseek.md b/docs/providers/deepseek.md
index 2209c9e3e..ad80736e5 100644
--- a/docs/providers/deepseek.md
+++ b/docs/providers/deepseek.md
@@ -90,6 +90,12 @@ back on the follow-up request. OpenClaw handles this inside the DeepSeek plugin,
 so normal multi-turn tool use works with `deepseek/deepseek-v4-flash` and
 `deepseek/deepseek-v4-pro`.
 
+If you switch an existing session from another OpenAI-compatible provider to a
+DeepSeek V4 model, older assistant tool-call turns may not have native
+DeepSeek `reasoning_content`. OpenClaw fills that missing field for DeepSeek V4
+thinking requests so the provider can accept the replayed tool-call history
+without requiring `/new`.
+
 When thinking is disabled in OpenClaw (including the UI **None** selection),
 OpenClaw sends DeepSeek `thinking: { type: "disabled" }` and strips replayed
 `reasoning_content` from the outgoing history. This keeps disabled-thinking