chore: release v0.1.1 and add example demos

1. 新增3个官方示例代码：ETL流水线、并行执行、异步聚合
2. 添加__main__.py入口和示例包导出
3. 补充项目依赖声明和控制台脚本配置
4. 更新uv.lock和包版本号至0.1.1

src/pyflowx/examples/parallel_run.py

@@ -0,0 +1,59 @@
+"""Example 2: parallel execution (thread strategy).
+
+Same DAG run with sequential vs. thread strategy to show layer-internal
+parallelism. Tasks within a layer run concurrently; layers are barriers.
+
+Layer 1: [fetch_a, fetch_b]   (parallel)
+Layer 2: [merge]              (waits for both)
+"""
+
+from __future__ import annotations
+
+import time
+
+import pyflowx as px
+
+
+def fetch_a() -> str:
+    time.sleep(0.5)
+    return "a"
+
+
+def fetch_b() -> str:
+    time.sleep(0.5)
+    return "b"
+
+
+def merge(fetch_a: str, fetch_b: str) -> str:
+    return fetch_a + fetch_b
+
+
+def main() -> None:
+    graph = px.Graph.from_specs(
+        [
+            px.TaskSpec("fetch_a", fetch_a),
+            px.TaskSpec("fetch_b", fetch_b),
+            px.TaskSpec("merge", merge, ("fetch_a", "fetch_b")),
+        ]
+    )
+
+    print("=== Mermaid diagram ===")
+    print(graph.to_mermaid("LR"))
+
+    print("\n=== Sequential (expect ~1.0s) ===")
+    start = time.time()
+    report_seq = px.run(graph, strategy="sequential")
+    t_seq = time.time() - start
+    print(f"  result={report_seq['merge']}  time={t_seq:.2f}s")
+
+    print("\n=== Threaded (expect ~0.5s) ===")
+    start = time.time()
+    report_thr = px.run(graph, strategy="thread", max_workers=2)
+    t_thr = time.time() - start
+    print(f"  result={report_thr['merge']}  time={t_thr:.2f}s")
+
+    print(f"\nspeedup = {t_seq / t_thr:.2f}x")
+
+
+if __name__ == "__main__":
+    main()