diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8d8ca555a7d..6a8fb90767d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -45,6 +45,7 @@ Docs: https://docs.openclaw.ai
 ### Fixes
 
 - Agents/image generation: allow distinct `image_generate` prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614) Thanks @Elarwei001.
+- Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515) Thanks @njuboy11.
 - Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)
 - Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635) Thanks @yaoyi1222.
 - Memory Wiki: keep `wiki_lint` tool output path-safe by reporting vault-internal lint reports as relative paths in tool text and details while preserving absolute report paths for CLI/file callers. (#83439) Thanks @LLagoon3.
diff --git a/ui/src/ui/views/chat.test.ts b/ui/src/ui/views/chat.test.ts
index 4f4d2bc5e66..e5921a6aaff 100644
--- a/ui/src/ui/views/chat.test.ts
+++ b/ui/src/ui/views/chat.test.ts
@@ -503,6 +503,23 @@ describe("chat loading skeleton", () => {
     expect(container.querySelector(".chat-reading-indicator")).not.toBeNull();
   });
 
+  it("does not keep the reading indicator after an assistant response has rendered", () => {
+    const container = renderChatView({
+      canAbort: true,
+      messages: [
+        {
+          role: "assistant",
+          content: "Finished answer",
+          timestamp: 1,
+        },
+      ],
+      stream: null,
+    });
+
+    expect(container.querySelector(".chat-reading-indicator")).toBeNull();
+    expect(container.querySelector(".chat-group")?.textContent?.trim()).toBe("Finished answer");
+  });
+
   it("keeps existing messages visible without the skeleton during a background reload", () => {
     const container = renderChatView({
       loading: true,