How to Run Apache Airflow in a Cloud Sandbox

set -e
AIRFLOW_VERSION=3.3.2
PYTHON_VERSION="$(python3 -c 'import sys; print(f"{sys.version_info.major}.{sys.version_info.minor}")')"
CONSTRAINT_URL="https://raw.githubusercontent.com/apache/airflow/constraints-${AIRFLOW_VERSION}/constraints-${PYTHON_VERSION}.txt"
uv venv ~/airflow-venv --python 3.12
. ~/airflow-venv/bin/activate
uv pip install "apache-airflow==${AIRFLOW_VERSION}" --constraint "${CONSTRAINT_URL}"
airflow version

sbx new --name airflow --type default
id=sb_g8mptg3wbr    # the id that sbx new printed

sbx scp ./install.sh $id:/home/user/
sbx exec $id --timeout 600 "bash install.sh 2>&1 | tail -3"

 + wrapt==2.4.1
 + zipp==4.1.0
3.3.2

from datetime import datetime
import json, platform, statistics, urllib.request

from airflow.sdk import dag, task


@dag(schedule="@hourly", start_date=datetime(2026, 10, 1), catchup=False, tags=["sandbox"])
def hello_pipeline():
    @task
    def extract() -> list[float]:
        # Real network call from inside the sandbox: wheel sizes of every apache-airflow release
        with urllib.request.urlopen("https://pypi.org/pypi/apache-airflow/json", timeout=20) as r:
            releases = json.load(r)["releases"]
        sizes = [f["size"] / 1e6 for files in releases.values() for f in files if f["packagetype"] == "bdist_wheel"]
        return sizes

    @task
    def transform(sizes: list[float]) -> dict:
        return {
            "wheels": len(sizes),
            "median_mb": round(statistics.median(sizes), 2),
            "max_mb": round(max(sizes), 2),
            "host": platform.node(),
        }

    @task
    def load(summary: dict) -> None:
        with open("/home/user/airflow/report.json", "w") as f:
            json.dump(summary, f)
        print("report:", summary)

    load(transform(extract()))


hello_pipeline()

sbx exec $id "mkdir -p ~/airflow/dags"
sbx scp ./hello_pipeline.py $id:/home/user/airflow/dags/
sbx exec $id --timeout 300 "export AIRFLOW_HOME=~/airflow AIRFLOW__CORE__LOAD_EXAMPLES=False
  . ~/airflow-venv/bin/activate
  airflow db migrate > /tmp/migrate.log 2>&1
  airflow dags test hello_pipeline 2>&1 | grep -E 'report:|DagRun Finished'"

report: {'wheels': 289, 'median_mb': 5.25, 'max_mb': 13.68, 'host': 'cloudy-fancy-sapphire'}
… DagRun Finished: dag_id=hello_pipeline, … run_duration=4.895654, state=success, run_type=manual, …

[Unit]
Description=Apache Airflow (standalone)
After=network-online.target
Wants=network-online.target

[Service]
User=user
WorkingDirectory=/home/user/airflow
Environment=AIRFLOW_HOME=/home/user/airflow
Environment=AIRFLOW__CORE__LOAD_EXAMPLES=False
Environment=PATH=/home/user/airflow-venv/bin:/usr/local/bin:/usr/bin:/bin
ExecStart=/home/user/airflow-venv/bin/airflow standalone
StandardOutput=append:/home/user/airflow/standalone.log
StandardError=inherit
Restart=on-failure
RestartSec=5
KillMode=mixed
TimeoutStopSec=30

[Install]
WantedBy=multi-user.target

sbx scp ./airflow.service $id:/home/user/
sbx exec $id "sudo mv airflow.service /etc/systemd/system/ && sudo systemctl daemon-reload && sudo systemctl enable --now airflow"
sbx exec $id --timeout 170 "until curl -sf -o /dev/null http://localhost:8080/api/v2/monitor/health; do sleep 1; done
  curl -s http://localhost:8080/api/v2/monitor/health"

{"metadatabase":{"status":"healthy"},"scheduler":{"status":"healthy","latest_scheduler_heartbeat":"2026-10-27T09:41:59.811942+00:00"},"triggerer":{"status":"healthy",…},"dag_processor":{"status":"healthy",…}}

Exception in thread dag-processor:
…
FileNotFoundError: [Errno 2] No such file or directory: 'airflow'

sbx host $id 8080 --title airflow

{"ok":true,"type":"port.hosted","sandboxId":"sb_g8mptg3wbr","port":8080,"url":"https://cloudy-fancy-sapphire-8080.box.sandboxer.com?_token=<token>","access":"private",…}

no token:              401
with ?_token=<token>:  302 (sets the __sbx_auth cookie)
UI with the cookie:    200

URL="https://cloudy-fancy-sapphire-8080.box.sandboxer.com?_token=<token>"   # from sbx host
BASE=${URL%%\?*}
curl -s -o /dev/null -c jar "$URL"                       # 302: trade the token for the cookie

PW=$(sbx exec $id "python3 -c 'import json;print(json.load(open(\"/home/user/airflow/simple_auth_manager_passwords.json.generated\"))[\"admin\"])'")
JWT=$(curl -s -b jar -X POST $BASE/auth/token -H 'Content-Type: application/json' \
  -d "{\"username\":\"admin\",\"password\":\"$PW\"}" | jq -r .access_token); unset PW
api() { curl -s -b jar -H "Authorization: Bearer $JWT" -H 'Content-Type: application/json' "$@"; }

api -X PATCH $BASE/api/v2/dags/hello_pipeline -d '{"is_paused":false}' | jq -c '{dag_id,is_paused}'
RID=$(api -X POST $BASE/api/v2/dags/hello_pipeline/dagRuns -d '{"logical_date":null}' | jq -r .dag_run_id)
E=$(jq -rn --arg r "$RID" '$r|@uri')
until st=$(api "$BASE/api/v2/dags/hello_pipeline/dagRuns/$E" | jq -r .state); [ "$st" = success ] || [ "$st" = failed ]; do sleep 1; done
echo "state=$st"
api "$BASE/api/v2/dags/hello_pipeline/dagRuns/$E/taskInstances" | jq -c '.task_instances[] | {task_id,state,duration}'
api "$BASE/api/v2/dags/hello_pipeline/dagRuns/$E/taskInstances/transform/xcomEntries/return_value" | jq -c .value

{"dag_id":"hello_pipeline","is_paused":false}
state=success
{"task_id":"extract","state":"success","duration":3.613}
{"task_id":"transform","state":"success","duration":0.138}
{"task_id":"load","state":"success","duration":0.074}
{"wheels":289,"median_mb":5.25,"max_mb":13.68,"host":"cloudy-fancy-sapphire"}

{"run_type":"manual","state":"success","run_after":"2026-10-27T09:42:31.654995Z"}
{"run_type":"scheduled","state":"success","run_after":"2026-10-27T09:00:00Z"}

sbx exec $id "export AIRFLOW_HOME=~/airflow PATH=~/airflow-venv/bin:\$PATH; airflow dags trigger hello_pipeline -o plain 2>/dev/null"

conf    dag_id          dag_run_id                                …
{}      hello_pipeline  manual__2026-10-27T09:43:50.422068+00:00  …