feat: 增加失败任务重试与 CUDA 动态库路径注入

tests/test_apps_api.py

@@ -139,3 +139,57 @@ def test_upload_rejects_workflow_without_version() -> None:
             files={"file": ("x.txt", b"x", "text/plain")},
         )
         assert response.status_code == 422
+
+
+def test_retry_failed_run_requeues_and_reruns() -> None:
+    with TestClient(app) as client:
+        workflow_id = _create_published_echo_workflow(client)
+        uploaded = client.post(
+            f"/api/apps/{workflow_id}/runs",
+            files={"file": ("sample.txt", b"hello retry", "text/plain")},
+        )
+        run_id = uploaded.json()["id"]
+        db = app.state.db
+        db.update_run(
+            run_id,
+            status="FAILED",
+            error="boom",
+            updated_at="2026-01-01T00:00:00+00:00",
+        )
+        db.create_artifact(
+            {
+                "run_id": run_id,
+                "node_id": "step",
+                "name": "stale",
+                "uri": "stale.txt",
+                "mime_type": "text/plain",
+                "size": 1,
+            }
+        )
+
+        response = client.post(f"/api/runs/{run_id}/retry")
+
+        assert response.status_code == 200
+        assert response.json() == {"id": run_id, "status": "QUEUED"}
+        run = client.get(f"/api/runs/{run_id}").json()
+        assert run["status"] == "QUEUED"
+        assert run["error"] is None
+        assert run["artifacts"] == []
+
+        app.state.scheduler.execute_run(run_id)
+        completed = client.get(f"/api/runs/{run_id}").json()
+        assert completed["status"] == "COMPLETED"
+        assert any(item["name"] == "result" for item in completed["artifacts"])
+
+
+def test_retry_rejects_non_failed_and_missing_runs() -> None:
+    with TestClient(app) as client:
+        workflow_id = _create_published_echo_workflow(client)
+        uploaded = client.post(
+            f"/api/apps/{workflow_id}/runs",
+            files={"file": ("sample.txt", b"x", "text/plain")},
+        )
+        run_id = uploaded.json()["id"]
+
+        assert client.post(f"/api/runs/{run_id}/retry").status_code == 422
+        assert client.post("/api/runs/missing/retry").status_code == 404