Run your application’s tests, workers and build commands inside an Ubuntu container and keep their output for comparison. Your agent can spot a changed result even when every command succeeds.
# Before · main container.bash command="./bin/test" # After · PR · same commands, fresh container container.bash command="./bin/test" Recorded plugin invocations shown in flow syntax. Checkpoint names label this presentation; the capture used the plugin host directly, not reflow apply. Select a checkpoint line to inspect its output; preceding lines provide context.
Real plugin output, synthetic shop app. IDs shortened, setup flags abbreviated. Driven directly through the plugin host; checkpoint names below are presentation labels, not stored Reflow checkpoints. Full capture and fixture source
$ docker build -q -t shop-test:pr . sha256:b83b8cfb3206 $ docker run -d --network=none --name shop-test-pr shop-test:pr d2c3ea9cda2a Connected shop-test-pr · /workspace
› container.bash command="./bin/test" shop 1.4.0 tests on Ubuntu 24.04.5 LTS ok - full refund returns the payment ok - half refund splits the payment ok - free order refunds nothing 3 passed › container.bash command="./bin/package" files="[\"dist/release.env\"]" packaged dist/shop-1.4.0.tar.gz dist/release.env: 4 settings CURRENCY=USD
LOG_LEVEL=warn
RECEIPT_EMAILS=on
REFUND_WINDOW_DAYS=30› container.bash command="./bin/test" shop 1.4.0 tests on Ubuntu 24.04.5 LTS ok - full refund returns the payment ok - half refund splits the payment ok - free order refunds nothing 3 passed › container.bash command="./bin/package" files="[\"dist/release.env\"]" packaged dist/shop-1.4.0.tar.gz dist/release.env: 4 settings CURRENCY=USD
LOG_LEVEL=warn
RECEIPT_EMAILS=on
REFUND_WINDOW_DAYS=14Before- REFUND_WINDOW_DAYS=30 After+ REFUND_WINDOW_DAYS=14 Exit code 0 → 0 · stdout.txt and stderr.txt unchanged
CURRENCY=USD LOG_LEVEL=warn RECEIPT_EMAILS=on REFUND_WINDOW_DAYS=30
CURRENCY=USD LOG_LEVEL=warn RECEIPT_EMAILS=on REFUND_WINDOW_DAYS=14
“Both runs succeed, but the package now ships a 14-day refund window instead of 30. The PR comment says the shorter window is for local test fixtures. Should production keep 30?”
Start a test-owned Ubuntu container with your application inside, then point the flow at it. Each command runs in the configured working directory, and Reflow retains its stdout, stderr and exit code, with up to two selected files. Images, mounts and networks stay with your setup, and the container keeps running afterwards.
Retained output and selected files are compared byte for byte across runs. A packaging command can succeed twice while the settings file it writes has changed.
In the example, the tests and the package command succeed in both runs, but the packaged production settings now allow refunds for 14 days instead of 30. Your agent can bring both retained files into its review and ask whether the refund policy was meant to change.
Bring the evidence into PR reviewKeep the container name and its absolute working directory in the private DockerUbuntu connection. The container must already be running Ubuntu with Bash and your application installed; the example uses the fixture’s ./bin/test and ./bin/package.
Your agent can inspect the installed plugin’s commands and write the flow using your application knowledge. Select the plugin version in the flow’s requirements.
---
providers:
container: DockerUbuntu
---
container.bash command="./bin/test" checkpoint="tests"
container.bash command="./bin/package" files="[\"dist/release.env\"]" checkpoint="release-package"Plugin requirements and private connection settings are configured separately.