diff --git a/workers/example/stream_chat.toml b/workers/example/stream_chat.toml
new file mode 100644
index 0000000..f8273e5
--- /dev/null
+++ b/workers/example/stream_chat.toml
@@ -0,0 +1,13 @@
+[POST]
+summary = "模拟 AI 流式对话（SSE，逐 token 输出）"
+docstring = "流式端点示例：@rpc_method 返回生成器，框架逐块多回复推送，网关以 text/event-stream 转发。curl -N 可观察逐块到达。"
+auth_required = false
+stream = true
+# 流式超时模型: timeout = 流总寿命上限（zenoh query deadline），
+# stream_idle_timeout = 网关侧连续无数据块的最大间隔
+timeout = 300.0
+stream_idle_timeout = 10.0
+params = [
+    "prompt: str",
+    "tokens: int"
+]